From 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d Mon Sep 17 00:00:00 2001
From: Zeng Chi <zengchi@kylinos.cn>
Date: Mon, 21 Sep 2026 18:24:42 +0800
Subject: KVM: Don't pre-reserve xarray entries when storing empty/NULL
 attributes

Skip the xarray reservation loop when clearing all memory attributes, as
storing NULL only erases the entry and never needs to allocate, so no
reservation (and no cleanup of a failed one) is required in that case.

Suggested-by: Sean Christopherson <seanjc@google.com>
Cc: David Ballesteros <davimaba.v@proton.me>
Signed-off-by: Zeng Chi <zengchi@kylinos.cn>
Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com
[sean: split to separate patch]
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 security/Kconfig                                   |  305 +
 security/Kconfig.hardening                         |  349 +
 security/Makefile                                  |   31 +
 security/apparmor/.gitignore                       |    4 +
 security/apparmor/.kunitconfig                     |    5 +
 security/apparmor/Kconfig                          |  134 +
 security/apparmor/Makefile                         |  114 +
 security/apparmor/af_inet.c                        |  565 ++
 security/apparmor/af_unix.c                        |  812 ++
 security/apparmor/apparmorfs.c                     | 2981 ++++++++
 security/apparmor/audit.c                          |  325 +
 security/apparmor/capability.c                     |  223 +
 security/apparmor/crypto.c                         |   61 +
 security/apparmor/domain.c                         | 1663 ++++
 security/apparmor/file.c                           |  754 ++
 security/apparmor/include/af_inet.h                |   36 +
 security/apparmor/include/af_unix.h                |   55 +
 security/apparmor/include/apparmor.h               |   69 +
 security/apparmor/include/apparmorfs.h             |  151 +
 security/apparmor/include/audit.h                  |  218 +
 security/apparmor/include/capability.h             |   49 +
 security/apparmor/include/cred.h                   |  246 +
 security/apparmor/include/crypto.h                 |   38 +
 security/apparmor/include/domain.h                 |   33 +
 security/apparmor/include/file.h                   |  133 +
 security/apparmor/include/ipc.h                    |   23 +
 security/apparmor/include/label.h                  |  492 ++
 security/apparmor/include/lib.h                    |  363 +
 security/apparmor/include/match.h                  |  195 +
 security/apparmor/include/mount.h                  |   60 +
 security/apparmor/include/net.h                    |  120 +
 security/apparmor/include/path.h                   |   36 +
 security/apparmor/include/perms.h                  |  220 +
 security/apparmor/include/policy.h                 |  457 ++
 security/apparmor/include/policy_compat.h          |   33 +
 security/apparmor/include/policy_ns.h              |  153 +
 security/apparmor/include/policy_unpack.h          |  217 +
 security/apparmor/include/procattr.h               |   19 +
 security/apparmor/include/resource.h               |   47 +
 security/apparmor/include/secid.h                  |   37 +
 security/apparmor/include/sig_names.h              |   97 +
 security/apparmor/include/signal.h                 |   19 +
 security/apparmor/include/task.h                   |  117 +
 security/apparmor/ipc.c                            |  116 +
 security/apparmor/label.c                          | 2170 ++++++
 security/apparmor/lib.c                            |  514 ++
 security/apparmor/lsm.c                            | 2642 +++++++
 security/apparmor/match.c                          |  835 ++
 security/apparmor/mount.c                          |  709 ++
 security/apparmor/net.c                            |  415 +
 security/apparmor/nulldfa.in                       |  107 +
 security/apparmor/path.c                           |  222 +
 security/apparmor/policy.c                         | 1537 ++++
 security/apparmor/policy_compat.c                  |  333 +
 security/apparmor/policy_ns.c                      |  398 +
 security/apparmor/policy_unpack.c                  | 1821 +++++
 security/apparmor/policy_unpack_test.c             |  616 ++
 security/apparmor/procattr.c                       |  141 +
 security/apparmor/resource.c                       |  206 +
 security/apparmor/secid.c                          |  155 +
 security/apparmor/stacksplitdfa.in                 |  114 +
 security/apparmor/task.c                           |  399 +
 security/bpf/Makefile                              |    5 +
 security/bpf/hooks.c                               |   42 +
 security/commoncap.c                               | 1527 ++++
 security/commoncap_test.c                          |  288 +
 security/device_cgroup.c                           |  870 +++
 security/inode.c                                   |  380 +
 security/integrity/Kconfig                         |  137 +
 security/integrity/Makefile                        |   24 +
 security/integrity/digsig.c                        |  228 +
 security/integrity/digsig_asymmetric.c             |  302 +
 security/integrity/efi_secureboot.c                |   56 +
 security/integrity/evm/Kconfig                     |   76 +
 security/integrity/evm/Makefile                    |    8 +
 security/integrity/evm/evm.h                       |   89 +
 security/integrity/evm/evm_crypto.c                |  459 ++
 security/integrity/evm/evm_main.c                  | 1236 +++
 security/integrity/evm/evm_posix_acl.c             |   23 +
 security/integrity/evm/evm_secfs.c                 |  346 +
 security/integrity/iint.c                          |   71 +
 security/integrity/ima/Kconfig                     |  360 +
 security/integrity/ima/Makefile                    |   20 +
 security/integrity/ima/ima.h                       |  630 ++
 security/integrity/ima/ima_api.c                   |  470 ++
 security/integrity/ima/ima_appraise.c              |  836 ++
 security/integrity/ima/ima_asymmetric_keys.c       |   66 +
 security/integrity/ima/ima_crypto.c                |  519 ++
 security/integrity/ima/ima_efi.c                   |   35 +
 security/integrity/ima/ima_fs.c                    |  856 +++
 security/integrity/ima/ima_iint.c                  |  138 +
 security/integrity/ima/ima_init.c                  |  174 +
 security/integrity/ima/ima_kexec.c                 |  351 +
 security/integrity/ima/ima_main.c                  | 1406 ++++
 security/integrity/ima/ima_modsig.c                |  151 +
 security/integrity/ima/ima_mok.c                   |   49 +
 security/integrity/ima/ima_policy.c                | 2473 ++++++
 security/integrity/ima/ima_queue.c                 |  577 ++
 security/integrity/ima/ima_queue_keys.c            |  177 +
 security/integrity/ima/ima_template.c              |  537 ++
 security/integrity/ima/ima_template_lib.c          |  765 ++
 security/integrity/ima/ima_template_lib.h          |   69 +
 security/integrity/integrity.h                     |  281 +
 security/integrity/integrity_audit.c               |   69 +
 security/integrity/platform_certs/efi_parser.c     |  108 +
 .../integrity/platform_certs/keyring_handler.c     |  102 +
 .../integrity/platform_certs/keyring_handler.h     |   55 +
 security/integrity/platform_certs/load_ipl_s390.c  |   36 +
 security/integrity/platform_certs/load_powerpc.c   |  160 +
 security/integrity/platform_certs/load_uefi.c      |  238 +
 .../integrity/platform_certs/machine_keyring.c     |   91 +
 .../integrity/platform_certs/platform_keyring.c    |   58 +
 security/ipe/.gitignore                            |    2 +
 security/ipe/Kconfig                               |  117 +
 security/ipe/Makefile                              |   31 +
 security/ipe/audit.c                               |  279 +
 security/ipe/audit.h                               |   19 +
 security/ipe/digest.c                              |  119 +
 security/ipe/digest.h                              |   26 +
 security/ipe/eval.c                                |  393 +
 security/ipe/eval.h                                |   70 +
 security/ipe/fs.c                                  |  246 +
 security/ipe/fs.h                                  |   16 +
 security/ipe/hooks.c                               |  342 +
 security/ipe/hooks.h                               |   55 +
 security/ipe/ipe.c                                 |  100 +
 security/ipe/ipe.h                                 |   28 +
 security/ipe/policy.c                              |  244 +
 security/ipe/policy.h                              |   98 +
 security/ipe/policy_fs.c                           |  490 ++
 security/ipe/policy_parser.c                       |  559 ++
 security/ipe/policy_parser.h                       |   11 +
 security/ipe/policy_tests.c                        |  297 +
 security/keys/Kconfig                              |  131 +
 security/keys/Makefile                             |   32 +
 security/keys/big_key.c                            |  290 +
 security/keys/compat.c                             |  132 +
 security/keys/compat_dh.c                          |   36 +
 security/keys/dh.c                                 |  313 +
 security/keys/encrypted-keys/Makefile              |   11 +
 security/keys/encrypted-keys/ecryptfs_format.c     |   76 +
 security/keys/encrypted-keys/ecryptfs_format.h     |   27 +
 security/keys/encrypted-keys/encrypted.c           | 1002 +++
 security/keys/encrypted-keys/encrypted.h           |   67 +
 security/keys/encrypted-keys/masterkey_trusted.c   |   43 +
 security/keys/gc.c                                 |  374 +
 security/keys/internal.h                           |  378 +
 security/keys/key.c                                | 1293 ++++
 security/keys/keyctl.c                             | 2038 +++++
 security/keys/keyctl_pkey.c                        |  335 +
 security/keys/keyring.c                            | 1800 +++++
 security/keys/permission.c                         |  123 +
 security/keys/persistent.c                         |  167 +
 security/keys/proc.c                               |  323 +
 security/keys/process_keys.c                       |  965 +++
 security/keys/request_key.c                        |  821 ++
 security/keys/request_key_auth.c                   |  312 +
 security/keys/sysctl.c                             |   76 +
 security/keys/trusted-keys/Kconfig                 |   82 +
 security/keys/trusted-keys/Makefile                |   20 +
 security/keys/trusted-keys/tpm2key.asn1            |   11 +
 security/keys/trusted-keys/trusted_caam.c          |  191 +
 security/keys/trusted-keys/trusted_core.c          |  410 +
 security/keys/trusted-keys/trusted_dcp.c           |  363 +
 security/keys/trusted-keys/trusted_pkwm.c          |  190 +
 security/keys/trusted-keys/trusted_tee.c           |  287 +
 security/keys/trusted-keys/trusted_tpm1.c          |  998 +++
 security/keys/trusted-keys/trusted_tpm2.c          |  605 ++
 security/keys/user_defined.c                       |  207 +
 security/landlock/.kunitconfig                     |    6 +
 security/landlock/Kconfig                          |   42 +
 security/landlock/Makefile                         |   22 +
 security/landlock/access.h                         |  151 +
 security/landlock/audit.c                          |  237 +
 security/landlock/audit.h                          |   43 +
 security/landlock/common.h                         |   22 +
 security/landlock/cred.c                           |   69 +
 security/landlock/cred.h                           |  157 +
 security/landlock/domain.c                         |  775 ++
 security/landlock/domain.h                         |  326 +
 security/landlock/errata.h                         |   99 +
 security/landlock/errata/abi-1.h                   |   47 +
 security/landlock/errata/abi-4.h                   |   22 +
 security/landlock/errata/abi-6.h                   |   29 +
 security/landlock/fs.c                             | 2136 ++++++
 security/landlock/fs.h                             |  188 +
 security/landlock/id.c                             |  295 +
 security/landlock/id.h                             |   25 +
 security/landlock/limits.h                         |   42 +
 security/landlock/log.c                            |  587 ++
 security/landlock/log.h                            |   86 +
 security/landlock/net.c                            |  413 +
 security/landlock/net.h                            |   34 +
 security/landlock/object.c                         |   67 +
 security/landlock/object.h                         |   91 +
 security/landlock/ruleset.c                        |  354 +
 security/landlock/ruleset.h                        |  250 +
 security/landlock/setup.c                          |   81 +
 security/landlock/setup.h                          |   22 +
 security/landlock/syscalls.c                       |  706 ++
 security/landlock/task.c                           |  509 ++
 security/landlock/task.h                           |   14 +
 security/landlock/trace.c                          |  185 +
 security/landlock/trace.h                          |   44 +
 security/landlock/tsync.c                          |  639 ++
 security/landlock/tsync.h                          |   18 +
 security/loadpin/Kconfig                           |   44 +
 security/loadpin/Makefile                          |    2 +
 security/loadpin/loadpin.c                         |  442 ++
 security/lockdown/Kconfig                          |   47 +
 security/lockdown/Makefile                         |    1 +
 security/lockdown/lockdown.c                       |  172 +
 security/lsm.h                                     |   50 +
 security/lsm_audit.c                               |  457 ++
 security/lsm_init.c                                |  577 ++
 security/lsm_notifier.c                            |   31 +
 security/lsm_syscalls.c                            |  129 +
 security/min_addr.c                                |   62 +
 security/safesetid/Kconfig                         |   15 +
 security/safesetid/Makefile                        |    7 +
 security/safesetid/lsm.c                           |  293 +
 security/safesetid/lsm.h                           |   75 +
 security/safesetid/securityfs.c                    |  347 +
 security/security.c                                | 5717 ++++++++++++++
 security/selinux/.gitignore                        |    4 +
 security/selinux/Kconfig                           |  100 +
 security/selinux/Makefile                          |   44 +
 security/selinux/avc.c                             | 1207 +++
 security/selinux/genheaders.c                      |  154 +
 security/selinux/hooks.c                           | 8008 ++++++++++++++++++++
 security/selinux/ibpkey.c                          |  235 +
 security/selinux/ima.c                             |  121 +
 security/selinux/include/audit.h                   |   71 +
 security/selinux/include/avc.h                     |  172 +
 security/selinux/include/avc_ss.h                  |   23 +
 security/selinux/include/classmap.h                |  193 +
 security/selinux/include/conditional.h             |   23 +
 security/selinux/include/hash.h                    |   47 +
 security/selinux/include/ibpkey.h                  |   35 +
 security/selinux/include/ima.h                     |   32 +
 security/selinux/include/initcalls.h               |   19 +
 security/selinux/include/initial_sid_to_string.h   |   38 +
 security/selinux/include/netif.h                   |   24 +
 security/selinux/include/netlabel.h                |  137 +
 security/selinux/include/netnode.h                 |   26 +
 security/selinux/include/netport.h                 |   25 +
 security/selinux/include/objsec.h                  |  290 +
 security/selinux/include/policycap.h               |   29 +
 security/selinux/include/policycap_names.h         |   29 +
 security/selinux/include/security.h                |  414 +
 security/selinux/include/xfrm.h                    |   94 +
 security/selinux/initcalls.c                       |   52 +
 security/selinux/netif.c                           |  283 +
 security/selinux/netlabel.c                        |  619 ++
 security/selinux/netlink.c                         |  120 +
 security/selinux/netnode.c                         |  307 +
 security/selinux/netport.c                         |  235 +
 security/selinux/nlmsgtab.c                        |  234 +
 security/selinux/selinuxfs.c                       | 2023 +++++
 security/selinux/ss/avtab.c                        |  618 ++
 security/selinux/ss/avtab.h                        |  141 +
 security/selinux/ss/conditional.c                  |  765 ++
 security/selinux/ss/conditional.h                  |   84 +
 security/selinux/ss/constraint.h                   |   65 +
 security/selinux/ss/context.c                      |   32 +
 security/selinux/ss/context.h                      |  204 +
 security/selinux/ss/ebitmap.c                      |  603 ++
 security/selinux/ss/ebitmap.h                      |  156 +
 security/selinux/ss/hashtab.c                      |  199 +
 security/selinux/ss/hashtab.h                      |  154 +
 security/selinux/ss/mls.c                          |  653 ++
 security/selinux/ss/mls.h                          |   96 +
 security/selinux/ss/mls_types.h                    |   52 +
 security/selinux/ss/policydb.c                     | 4155 ++++++++++
 security/selinux/ss/policydb.h                     |  428 ++
 security/selinux/ss/services.c                     | 3962 ++++++++++
 security/selinux/ss/services.h                     |   47 +
 security/selinux/ss/sidtab.c                       |  638 ++
 security/selinux/ss/sidtab.h                       |  160 +
 security/selinux/ss/symtab.c                       |   56 +
 security/selinux/ss/symtab.h                       |   26 +
 security/selinux/status.c                          |  122 +
 security/selinux/xfrm.c                            |  466 ++
 security/smack/Kconfig                             |   55 +
 security/smack/Makefile                            |    9 +
 security/smack/smack.h                             |  543 ++
 security/smack/smack_access.c                      |  765 ++
 security/smack/smack_lsm.c                         | 5411 +++++++++++++
 security/smack/smack_netfilter.c                   |   78 +
 security/smack/smackfs.c                           | 2954 ++++++++
 security/tomoyo/.gitignore                         |    3 +
 security/tomoyo/Kconfig                            |   85 +
 security/tomoyo/Makefile                           |   21 +
 security/tomoyo/audit.c                            |  477 ++
 security/tomoyo/common.c                           | 3025 ++++++++
 security/tomoyo/common.h                           | 1292 ++++
 security/tomoyo/condition.c                        | 1122 +++
 security/tomoyo/domain.c                           |  950 +++
 security/tomoyo/environ.c                          |  124 +
 security/tomoyo/file.c                             | 1050 +++
 security/tomoyo/gc.c                               |  682 ++
 security/tomoyo/group.c                            |  209 +
 security/tomoyo/load_policy.c                      |  110 +
 security/tomoyo/memory.c                           |  207 +
 security/tomoyo/mount.c                            |  242 +
 security/tomoyo/network.c                          |  780 ++
 .../tomoyo/policy/exception_policy.conf.default    |    2 +
 security/tomoyo/realpath.c                         |  310 +
 security/tomoyo/securityfs_if.c                    |  271 +
 security/tomoyo/tomoyo.c                           |  621 ++
 security/tomoyo/util.c                             | 1106 +++
 security/yama/Kconfig                              |   14 +
 security/yama/Makefile                             |    4 +
 security/yama/yama_lsm.c                           |  481 ++
 314 files changed, 131257 insertions(+)
 create mode 100644 security/Kconfig
 create mode 100644 security/Kconfig.hardening
 create mode 100644 security/Makefile
 create mode 100644 security/apparmor/.gitignore
 create mode 100644 security/apparmor/.kunitconfig
 create mode 100644 security/apparmor/Kconfig
 create mode 100644 security/apparmor/Makefile
 create mode 100644 security/apparmor/af_inet.c
 create mode 100644 security/apparmor/af_unix.c
 create mode 100644 security/apparmor/apparmorfs.c
 create mode 100644 security/apparmor/audit.c
 create mode 100644 security/apparmor/capability.c
 create mode 100644 security/apparmor/crypto.c
 create mode 100644 security/apparmor/domain.c
 create mode 100644 security/apparmor/file.c
 create mode 100644 security/apparmor/include/af_inet.h
 create mode 100644 security/apparmor/include/af_unix.h
 create mode 100644 security/apparmor/include/apparmor.h
 create mode 100644 security/apparmor/include/apparmorfs.h
 create mode 100644 security/apparmor/include/audit.h
 create mode 100644 security/apparmor/include/capability.h
 create mode 100644 security/apparmor/include/cred.h
 create mode 100644 security/apparmor/include/crypto.h
 create mode 100644 security/apparmor/include/domain.h
 create mode 100644 security/apparmor/include/file.h
 create mode 100644 security/apparmor/include/ipc.h
 create mode 100644 security/apparmor/include/label.h
 create mode 100644 security/apparmor/include/lib.h
 create mode 100644 security/apparmor/include/match.h
 create mode 100644 security/apparmor/include/mount.h
 create mode 100644 security/apparmor/include/net.h
 create mode 100644 security/apparmor/include/path.h
 create mode 100644 security/apparmor/include/perms.h
 create mode 100644 security/apparmor/include/policy.h
 create mode 100644 security/apparmor/include/policy_compat.h
 create mode 100644 security/apparmor/include/policy_ns.h
 create mode 100644 security/apparmor/include/policy_unpack.h
 create mode 100644 security/apparmor/include/procattr.h
 create mode 100644 security/apparmor/include/resource.h
 create mode 100644 security/apparmor/include/secid.h
 create mode 100644 security/apparmor/include/sig_names.h
 create mode 100644 security/apparmor/include/signal.h
 create mode 100644 security/apparmor/include/task.h
 create mode 100644 security/apparmor/ipc.c
 create mode 100644 security/apparmor/label.c
 create mode 100644 security/apparmor/lib.c
 create mode 100644 security/apparmor/lsm.c
 create mode 100644 security/apparmor/match.c
 create mode 100644 security/apparmor/mount.c
 create mode 100644 security/apparmor/net.c
 create mode 100644 security/apparmor/nulldfa.in
 create mode 100644 security/apparmor/path.c
 create mode 100644 security/apparmor/policy.c
 create mode 100644 security/apparmor/policy_compat.c
 create mode 100644 security/apparmor/policy_ns.c
 create mode 100644 security/apparmor/policy_unpack.c
 create mode 100644 security/apparmor/policy_unpack_test.c
 create mode 100644 security/apparmor/procattr.c
 create mode 100644 security/apparmor/resource.c
 create mode 100644 security/apparmor/secid.c
 create mode 100644 security/apparmor/stacksplitdfa.in
 create mode 100644 security/apparmor/task.c
 create mode 100644 security/bpf/Makefile
 create mode 100644 security/bpf/hooks.c
 create mode 100644 security/commoncap.c
 create mode 100644 security/commoncap_test.c
 create mode 100644 security/device_cgroup.c
 create mode 100644 security/inode.c
 create mode 100644 security/integrity/Kconfig
 create mode 100644 security/integrity/Makefile
 create mode 100644 security/integrity/digsig.c
 create mode 100644 security/integrity/digsig_asymmetric.c
 create mode 100644 security/integrity/efi_secureboot.c
 create mode 100644 security/integrity/evm/Kconfig
 create mode 100644 security/integrity/evm/Makefile
 create mode 100644 security/integrity/evm/evm.h
 create mode 100644 security/integrity/evm/evm_crypto.c
 create mode 100644 security/integrity/evm/evm_main.c
 create mode 100644 security/integrity/evm/evm_posix_acl.c
 create mode 100644 security/integrity/evm/evm_secfs.c
 create mode 100644 security/integrity/iint.c
 create mode 100644 security/integrity/ima/Kconfig
 create mode 100644 security/integrity/ima/Makefile
 create mode 100644 security/integrity/ima/ima.h
 create mode 100644 security/integrity/ima/ima_api.c
 create mode 100644 security/integrity/ima/ima_appraise.c
 create mode 100644 security/integrity/ima/ima_asymmetric_keys.c
 create mode 100644 security/integrity/ima/ima_crypto.c
 create mode 100644 security/integrity/ima/ima_efi.c
 create mode 100644 security/integrity/ima/ima_fs.c
 create mode 100644 security/integrity/ima/ima_iint.c
 create mode 100644 security/integrity/ima/ima_init.c
 create mode 100644 security/integrity/ima/ima_kexec.c
 create mode 100644 security/integrity/ima/ima_main.c
 create mode 100644 security/integrity/ima/ima_modsig.c
 create mode 100644 security/integrity/ima/ima_mok.c
 create mode 100644 security/integrity/ima/ima_policy.c
 create mode 100644 security/integrity/ima/ima_queue.c
 create mode 100644 security/integrity/ima/ima_queue_keys.c
 create mode 100644 security/integrity/ima/ima_template.c
 create mode 100644 security/integrity/ima/ima_template_lib.c
 create mode 100644 security/integrity/ima/ima_template_lib.h
 create mode 100644 security/integrity/integrity.h
 create mode 100644 security/integrity/integrity_audit.c
 create mode 100644 security/integrity/platform_certs/efi_parser.c
 create mode 100644 security/integrity/platform_certs/keyring_handler.c
 create mode 100644 security/integrity/platform_certs/keyring_handler.h
 create mode 100644 security/integrity/platform_certs/load_ipl_s390.c
 create mode 100644 security/integrity/platform_certs/load_powerpc.c
 create mode 100644 security/integrity/platform_certs/load_uefi.c
 create mode 100644 security/integrity/platform_certs/machine_keyring.c
 create mode 100644 security/integrity/platform_certs/platform_keyring.c
 create mode 100644 security/ipe/.gitignore
 create mode 100644 security/ipe/Kconfig
 create mode 100644 security/ipe/Makefile
 create mode 100644 security/ipe/audit.c
 create mode 100644 security/ipe/audit.h
 create mode 100644 security/ipe/digest.c
 create mode 100644 security/ipe/digest.h
 create mode 100644 security/ipe/eval.c
 create mode 100644 security/ipe/eval.h
 create mode 100644 security/ipe/fs.c
 create mode 100644 security/ipe/fs.h
 create mode 100644 security/ipe/hooks.c
 create mode 100644 security/ipe/hooks.h
 create mode 100644 security/ipe/ipe.c
 create mode 100644 security/ipe/ipe.h
 create mode 100644 security/ipe/policy.c
 create mode 100644 security/ipe/policy.h
 create mode 100644 security/ipe/policy_fs.c
 create mode 100644 security/ipe/policy_parser.c
 create mode 100644 security/ipe/policy_parser.h
 create mode 100644 security/ipe/policy_tests.c
 create mode 100644 security/keys/Kconfig
 create mode 100644 security/keys/Makefile
 create mode 100644 security/keys/big_key.c
 create mode 100644 security/keys/compat.c
 create mode 100644 security/keys/compat_dh.c
 create mode 100644 security/keys/dh.c
 create mode 100644 security/keys/encrypted-keys/Makefile
 create mode 100644 security/keys/encrypted-keys/ecryptfs_format.c
 create mode 100644 security/keys/encrypted-keys/ecryptfs_format.h
 create mode 100644 security/keys/encrypted-keys/encrypted.c
 create mode 100644 security/keys/encrypted-keys/encrypted.h
 create mode 100644 security/keys/encrypted-keys/masterkey_trusted.c
 create mode 100644 security/keys/gc.c
 create mode 100644 security/keys/internal.h
 create mode 100644 security/keys/key.c
 create mode 100644 security/keys/keyctl.c
 create mode 100644 security/keys/keyctl_pkey.c
 create mode 100644 security/keys/keyring.c
 create mode 100644 security/keys/permission.c
 create mode 100644 security/keys/persistent.c
 create mode 100644 security/keys/proc.c
 create mode 100644 security/keys/process_keys.c
 create mode 100644 security/keys/request_key.c
 create mode 100644 security/keys/request_key_auth.c
 create mode 100644 security/keys/sysctl.c
 create mode 100644 security/keys/trusted-keys/Kconfig
 create mode 100644 security/keys/trusted-keys/Makefile
 create mode 100644 security/keys/trusted-keys/tpm2key.asn1
 create mode 100644 security/keys/trusted-keys/trusted_caam.c
 create mode 100644 security/keys/trusted-keys/trusted_core.c
 create mode 100644 security/keys/trusted-keys/trusted_dcp.c
 create mode 100644 security/keys/trusted-keys/trusted_pkwm.c
 create mode 100644 security/keys/trusted-keys/trusted_tee.c
 create mode 100644 security/keys/trusted-keys/trusted_tpm1.c
 create mode 100644 security/keys/trusted-keys/trusted_tpm2.c
 create mode 100644 security/keys/user_defined.c
 create mode 100644 security/landlock/.kunitconfig
 create mode 100644 security/landlock/Kconfig
 create mode 100644 security/landlock/Makefile
 create mode 100644 security/landlock/access.h
 create mode 100644 security/landlock/audit.c
 create mode 100644 security/landlock/audit.h
 create mode 100644 security/landlock/common.h
 create mode 100644 security/landlock/cred.c
 create mode 100644 security/landlock/cred.h
 create mode 100644 security/landlock/domain.c
 create mode 100644 security/landlock/domain.h
 create mode 100644 security/landlock/errata.h
 create mode 100644 security/landlock/errata/abi-1.h
 create mode 100644 security/landlock/errata/abi-4.h
 create mode 100644 security/landlock/errata/abi-6.h
 create mode 100644 security/landlock/fs.c
 create mode 100644 security/landlock/fs.h
 create mode 100644 security/landlock/id.c
 create mode 100644 security/landlock/id.h
 create mode 100644 security/landlock/limits.h
 create mode 100644 security/landlock/log.c
 create mode 100644 security/landlock/log.h
 create mode 100644 security/landlock/net.c
 create mode 100644 security/landlock/net.h
 create mode 100644 security/landlock/object.c
 create mode 100644 security/landlock/object.h
 create mode 100644 security/landlock/ruleset.c
 create mode 100644 security/landlock/ruleset.h
 create mode 100644 security/landlock/setup.c
 create mode 100644 security/landlock/setup.h
 create mode 100644 security/landlock/syscalls.c
 create mode 100644 security/landlock/task.c
 create mode 100644 security/landlock/task.h
 create mode 100644 security/landlock/trace.c
 create mode 100644 security/landlock/trace.h
 create mode 100644 security/landlock/tsync.c
 create mode 100644 security/landlock/tsync.h
 create mode 100644 security/loadpin/Kconfig
 create mode 100644 security/loadpin/Makefile
 create mode 100644 security/loadpin/loadpin.c
 create mode 100644 security/lockdown/Kconfig
 create mode 100644 security/lockdown/Makefile
 create mode 100644 security/lockdown/lockdown.c
 create mode 100644 security/lsm.h
 create mode 100644 security/lsm_audit.c
 create mode 100644 security/lsm_init.c
 create mode 100644 security/lsm_notifier.c
 create mode 100644 security/lsm_syscalls.c
 create mode 100644 security/min_addr.c
 create mode 100644 security/safesetid/Kconfig
 create mode 100644 security/safesetid/Makefile
 create mode 100644 security/safesetid/lsm.c
 create mode 100644 security/safesetid/lsm.h
 create mode 100644 security/safesetid/securityfs.c
 create mode 100644 security/security.c
 create mode 100644 security/selinux/.gitignore
 create mode 100644 security/selinux/Kconfig
 create mode 100644 security/selinux/Makefile
 create mode 100644 security/selinux/avc.c
 create mode 100644 security/selinux/genheaders.c
 create mode 100644 security/selinux/hooks.c
 create mode 100644 security/selinux/ibpkey.c
 create mode 100644 security/selinux/ima.c
 create mode 100644 security/selinux/include/audit.h
 create mode 100644 security/selinux/include/avc.h
 create mode 100644 security/selinux/include/avc_ss.h
 create mode 100644 security/selinux/include/classmap.h
 create mode 100644 security/selinux/include/conditional.h
 create mode 100644 security/selinux/include/hash.h
 create mode 100644 security/selinux/include/ibpkey.h
 create mode 100644 security/selinux/include/ima.h
 create mode 100644 security/selinux/include/initcalls.h
 create mode 100644 security/selinux/include/initial_sid_to_string.h
 create mode 100644 security/selinux/include/netif.h
 create mode 100644 security/selinux/include/netlabel.h
 create mode 100644 security/selinux/include/netnode.h
 create mode 100644 security/selinux/include/netport.h
 create mode 100644 security/selinux/include/objsec.h
 create mode 100644 security/selinux/include/policycap.h
 create mode 100644 security/selinux/include/policycap_names.h
 create mode 100644 security/selinux/include/security.h
 create mode 100644 security/selinux/include/xfrm.h
 create mode 100644 security/selinux/initcalls.c
 create mode 100644 security/selinux/netif.c
 create mode 100644 security/selinux/netlabel.c
 create mode 100644 security/selinux/netlink.c
 create mode 100644 security/selinux/netnode.c
 create mode 100644 security/selinux/netport.c
 create mode 100644 security/selinux/nlmsgtab.c
 create mode 100644 security/selinux/selinuxfs.c
 create mode 100644 security/selinux/ss/avtab.c
 create mode 100644 security/selinux/ss/avtab.h
 create mode 100644 security/selinux/ss/conditional.c
 create mode 100644 security/selinux/ss/conditional.h
 create mode 100644 security/selinux/ss/constraint.h
 create mode 100644 security/selinux/ss/context.c
 create mode 100644 security/selinux/ss/context.h
 create mode 100644 security/selinux/ss/ebitmap.c
 create mode 100644 security/selinux/ss/ebitmap.h
 create mode 100644 security/selinux/ss/hashtab.c
 create mode 100644 security/selinux/ss/hashtab.h
 create mode 100644 security/selinux/ss/mls.c
 create mode 100644 security/selinux/ss/mls.h
 create mode 100644 security/selinux/ss/mls_types.h
 create mode 100644 security/selinux/ss/policydb.c
 create mode 100644 security/selinux/ss/policydb.h
 create mode 100644 security/selinux/ss/services.c
 create mode 100644 security/selinux/ss/services.h
 create mode 100644 security/selinux/ss/sidtab.c
 create mode 100644 security/selinux/ss/sidtab.h
 create mode 100644 security/selinux/ss/symtab.c
 create mode 100644 security/selinux/ss/symtab.h
 create mode 100644 security/selinux/status.c
 create mode 100644 security/selinux/xfrm.c
 create mode 100644 security/smack/Kconfig
 create mode 100644 security/smack/Makefile
 create mode 100644 security/smack/smack.h
 create mode 100644 security/smack/smack_access.c
 create mode 100644 security/smack/smack_lsm.c
 create mode 100644 security/smack/smack_netfilter.c
 create mode 100644 security/smack/smackfs.c
 create mode 100644 security/tomoyo/.gitignore
 create mode 100644 security/tomoyo/Kconfig
 create mode 100644 security/tomoyo/Makefile
 create mode 100644 security/tomoyo/audit.c
 create mode 100644 security/tomoyo/common.c
 create mode 100644 security/tomoyo/common.h
 create mode 100644 security/tomoyo/condition.c
 create mode 100644 security/tomoyo/domain.c
 create mode 100644 security/tomoyo/environ.c
 create mode 100644 security/tomoyo/file.c
 create mode 100644 security/tomoyo/gc.c
 create mode 100644 security/tomoyo/group.c
 create mode 100644 security/tomoyo/load_policy.c
 create mode 100644 security/tomoyo/memory.c
 create mode 100644 security/tomoyo/mount.c
 create mode 100644 security/tomoyo/network.c
 create mode 100644 security/tomoyo/policy/exception_policy.conf.default
 create mode 100644 security/tomoyo/realpath.c
 create mode 100644 security/tomoyo/securityfs_if.c
 create mode 100644 security/tomoyo/tomoyo.c
 create mode 100644 security/tomoyo/util.c
 create mode 100644 security/yama/Kconfig
 create mode 100644 security/yama/Makefile
 create mode 100644 security/yama/yama_lsm.c

(limited to 'security')

diff --git a/security/Kconfig b/security/Kconfig
new file mode 100644
index 000000000..f7bf6cdc6
--- /dev/null
+++ b/security/Kconfig
@@ -0,0 +1,305 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Security configuration
+#
+
+menu "Security options"
+
+source "security/keys/Kconfig"
+
+config SECURITY_DMESG_RESTRICT
+	bool "Restrict unprivileged access to the kernel syslog"
+	default n
+	help
+	  This enforces restrictions on unprivileged users reading the kernel
+	  syslog via dmesg(8).
+
+	  If this option is not selected, no restrictions will be enforced
+	  unless the dmesg_restrict sysctl is explicitly set to (1).
+
+	  If you are unsure how to answer this question, answer N.
+
+choice
+	prompt "Allow /proc/pid/mem access override"
+	default PROC_MEM_FORCE_PTRACE
+	help
+	  Traditionally /proc/pid/mem allows users to override memory
+	  permissions for users like ptrace, assuming they have ptrace
+	  capability.
+
+	  This allows people to limit that - either never override, or
+	  require actual active ptrace attachment (default).
+
+config PROC_MEM_ALWAYS_FORCE
+	bool "Traditional /proc/pid/mem behavior"
+	help
+	  This allows /proc/pid/mem accesses to override memory mapping
+	  permissions if you have ptrace access rights.
+
+config PROC_MEM_FORCE_PTRACE
+	bool "Require active ptrace() use for access override"
+	help
+	  This allows /proc/pid/mem accesses to override memory mapping
+	  permissions for active ptracers like gdb.
+
+config PROC_MEM_NO_FORCE
+	bool "Never"
+	help
+	  Never override memory mapping permissions
+
+endchoice
+
+config MSEAL_SYSTEM_MAPPINGS
+	bool "mseal system mappings"
+	depends on 64BIT
+	depends on ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS
+	depends on !CHECKPOINT_RESTORE
+	help
+	  Apply mseal on system mappings.
+	  The system mappings includes vdso, vvar, vvar_vclock,
+	  vectors (arm compat-mode), sigpage (arm compat-mode), uprobes.
+
+	  A 64-bit kernel is required for the memory sealing feature.
+	  No specific hardware features from the CPU are needed.
+
+	  WARNING: This feature breaks programs which rely on relocating
+	  or unmapping system mappings. Known broken software at the time
+	  of writing includes CHECKPOINT_RESTORE, UML, gVisor, rr. Therefore
+	  this config can't be enabled universally.
+
+	  For complete descriptions of memory sealing, please see
+	  Documentation/userspace-api/mseal.rst
+
+config SECURITY
+	bool "Enable different security models"
+	depends on SYSFS
+	depends on MULTIUSER
+	help
+	  This allows you to choose different security modules to be
+	  configured into your kernel.
+
+	  If this option is not selected, the default Linux security
+	  model will be used.
+
+	  If you are unsure how to answer this question, answer N.
+
+config HAS_SECURITY_AUDIT
+	def_bool y
+	depends on AUDIT
+	depends on SECURITY
+
+config SECURITYFS
+	bool "Enable the securityfs filesystem"
+	help
+	  This will build the securityfs filesystem.  It is currently used by
+	  various security modules (AppArmor, IMA, SafeSetID, TOMOYO, TPM).
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_NETWORK
+	bool "Socket and Networking Security Hooks"
+	depends on SECURITY
+	help
+	  This enables the socket and networking security hooks.
+	  If enabled, a security module can use these hooks to
+	  implement socket and networking access controls.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_INFINIBAND
+	bool "Infiniband Security Hooks"
+	depends on SECURITY && INFINIBAND
+	help
+	  This enables the Infiniband security hooks.
+	  If enabled, a security module can use these hooks to
+	  implement Infiniband access controls.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_NETWORK_XFRM
+	bool "XFRM (IPSec) Networking Security Hooks"
+	depends on XFRM && SECURITY_NETWORK
+	help
+	  This enables the XFRM (IPSec) networking security hooks.
+	  If enabled, a security module can use these hooks to
+	  implement per-packet access controls based on labels
+	  derived from IPSec policy.  Non-IPSec communications are
+	  designated as unlabelled, and only sockets authorized
+	  to communicate unlabelled data can send without using
+	  IPSec.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_PATH
+	bool "Security hooks for pathname based access control"
+	depends on SECURITY
+	help
+	  This enables the security hooks for pathname based access control.
+	  If enabled, a security module can use these hooks to
+	  implement pathname based access controls.
+	  If you are unsure how to answer this question, answer N.
+
+config INTEL_TXT
+	bool "Enable Intel(R) Trusted Execution Technology (Intel(R) TXT)"
+	depends on HAVE_INTEL_TXT
+	help
+	  This option enables support for booting the kernel with the
+	  Trusted Boot (tboot) module. This will utilize
+	  Intel(R) Trusted Execution Technology to perform a measured launch
+	  of the kernel. If the system does not support Intel(R) TXT, this
+	  will have no effect.
+
+	  Intel TXT will provide higher assurance of system configuration and
+	  initial state as well as data reset protection.  This is used to
+	  create a robust initial kernel measurement and verification, which
+	  helps to ensure that kernel security mechanisms are functioning
+	  correctly. This level of protection requires a root of trust outside
+	  of the kernel itself.
+
+	  Intel TXT also helps solve real end user concerns about having
+	  confidence that their hardware is running the VMM or kernel that
+	  it was configured with, especially since they may be responsible for
+	  providing such assurances to VMs and services running on it.
+
+	  See <https://www.intel.com/technology/security/> for more information
+	  about Intel(R) TXT.
+	  See <http://tboot.sourceforge.net> for more information about tboot.
+	  See Documentation/arch/x86/intel_txt.rst for a description of how to enable
+	  Intel TXT support in a kernel boot.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config LSM_MMAP_MIN_ADDR
+	int "Low address space for LSM to protect from user allocation"
+	depends on SECURITY && SECURITY_SELINUX
+	default 32768 if ARM || (ARM64 && COMPAT)
+	default 65536
+	help
+	  This is the portion of low virtual memory which should be protected
+	  from userspace allocation.  Keeping a user from writing to low pages
+	  can help reduce the impact of kernel NULL pointer bugs.
+
+	  For most ia64, ppc64 and x86 users with lots of address space
+	  a value of 65536 is reasonable and should cause no problems.
+	  On arm and other archs it should not be higher than 32768.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need the permission specific to the
+	  systems running LSM.
+
+config STATIC_USERMODEHELPER
+	bool "Force all usermode helper calls through a single binary"
+	help
+	  By default, the kernel can call many different userspace
+	  binary programs through the "usermode helper" kernel
+	  interface.  Some of these binaries are statically defined
+	  either in the kernel code itself, or as a kernel configuration
+	  option.  However, some of these are dynamically created at
+	  runtime, or can be modified after the kernel has started up.
+	  To provide an additional layer of security, route all of these
+	  calls through a single executable that can not have its name
+	  changed.
+
+	  Note, it is up to this single binary to then call the relevant
+	  "real" usermode helper binary, based on the first argument
+	  passed to it.  If desired, this program can filter and pick
+	  and choose what real programs are called.
+
+	  If you wish for all usermode helper programs are to be
+	  disabled, choose this option and then set
+	  STATIC_USERMODEHELPER_PATH to an empty string.
+
+config STATIC_USERMODEHELPER_PATH
+	string "Path to the static usermode helper binary"
+	depends on STATIC_USERMODEHELPER
+	default "/sbin/usermode-helper"
+	help
+	  The binary called by the kernel when any usermode helper
+	  program is wish to be run.  The "real" application's name will
+	  be in the first argument passed to this program on the command
+	  line.
+
+	  If you wish for all usermode helper programs to be disabled,
+	  specify an empty string here (i.e. "").
+
+source "security/selinux/Kconfig"
+source "security/smack/Kconfig"
+source "security/tomoyo/Kconfig"
+source "security/apparmor/Kconfig"
+source "security/loadpin/Kconfig"
+source "security/yama/Kconfig"
+source "security/safesetid/Kconfig"
+source "security/lockdown/Kconfig"
+source "security/landlock/Kconfig"
+source "security/ipe/Kconfig"
+
+source "security/integrity/Kconfig"
+
+choice
+	prompt "First legacy 'major LSM' to be initialized"
+	default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX
+	default DEFAULT_SECURITY_SMACK if SECURITY_SMACK
+	default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO
+	default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR
+	default DEFAULT_SECURITY_DAC
+
+	help
+	  This choice is there only for converting CONFIG_DEFAULT_SECURITY
+	  in old kernel configs to CONFIG_LSM in new kernel configs. Don't
+	  change this choice unless you are creating a fresh kernel config,
+	  for this choice will be ignored after CONFIG_LSM has been set.
+
+	  Selects the legacy "major security module" that will be
+	  initialized first. Overridden by non-default CONFIG_LSM.
+
+	config DEFAULT_SECURITY_SELINUX
+		bool "SELinux" if SECURITY_SELINUX=y
+
+	config DEFAULT_SECURITY_SMACK
+		bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y
+
+	config DEFAULT_SECURITY_TOMOYO
+		bool "TOMOYO" if SECURITY_TOMOYO=y
+
+	config DEFAULT_SECURITY_APPARMOR
+		bool "AppArmor" if SECURITY_APPARMOR=y
+
+	config DEFAULT_SECURITY_DAC
+		bool "Unix Discretionary Access Controls"
+
+endchoice
+
+config LSM
+	string "Ordered list of enabled LSMs"
+	depends on SECURITY
+	default "landlock,lockdown,yama,loadpin,safesetid,smack,selinux,tomoyo,apparmor,ipe,bpf" if DEFAULT_SECURITY_SMACK
+	default "landlock,lockdown,yama,loadpin,safesetid,apparmor,selinux,smack,tomoyo,ipe,bpf" if DEFAULT_SECURITY_APPARMOR
+	default "landlock,lockdown,yama,loadpin,safesetid,tomoyo,ipe,bpf" if DEFAULT_SECURITY_TOMOYO
+	default "landlock,lockdown,yama,loadpin,safesetid,ipe,bpf" if DEFAULT_SECURITY_DAC
+	default "landlock,lockdown,yama,loadpin,safesetid,selinux,smack,tomoyo,apparmor,ipe,bpf"
+	help
+	  A comma-separated list of LSMs, in initialization order.
+	  Any LSMs left off this list, except for those with order
+	  LSM_ORDER_FIRST and LSM_ORDER_LAST, which are always enabled
+	  if selected in the kernel configuration, will be ignored.
+	  This can be controlled at boot with the "lsm=" parameter.
+
+	  If unsure, leave this as the default.
+
+config SECURITY_COMMONCAP_KUNIT_TEST
+	bool "Build KUnit tests for commoncap" if !KUNIT_ALL_TESTS
+	depends on KUNIT=y && USER_NS
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the commoncap KUnit tests.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
+	  running KUnit test harness and are not for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
+source "security/Kconfig.hardening"
+
+endmenu
+
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
new file mode 100644
index 000000000..6923036e1
--- /dev/null
+++ b/security/Kconfig.hardening
@@ -0,0 +1,349 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menu "Kernel hardening options"
+
+menu "Memory initialization"
+
+config CC_HAS_AUTO_VAR_INIT_PATTERN
+	def_bool $(cc-option,-ftrivial-auto-var-init=pattern)
+
+config CC_HAS_AUTO_VAR_INIT_ZERO_BARE
+	def_bool $(cc-option,-ftrivial-auto-var-init=zero)
+
+config CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER
+	# Clang 16 and later warn about using the -enable flag, but it
+	# is required before then.
+	def_bool $(cc-option,-ftrivial-auto-var-init=zero -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang)
+	depends on !CC_HAS_AUTO_VAR_INIT_ZERO_BARE
+
+config CC_HAS_AUTO_VAR_INIT_ZERO
+	def_bool CC_HAS_AUTO_VAR_INIT_ZERO_BARE || CC_HAS_AUTO_VAR_INIT_ZERO_ENABLER
+
+choice
+	prompt "Initialize kernel stack variables at function entry"
+	default INIT_STACK_ALL_PATTERN if COMPILE_TEST && CC_HAS_AUTO_VAR_INIT_PATTERN
+	default INIT_STACK_ALL_ZERO if CC_HAS_AUTO_VAR_INIT_ZERO
+	default INIT_STACK_NONE
+	help
+	  This option enables initialization of stack variables at
+	  function entry time. This has the possibility to have the
+	  greatest coverage (since all functions can have their
+	  variables initialized), but the performance impact depends
+	  on the function calling complexity of a given workload's
+	  syscalls.
+
+	  This chooses the level of coverage over classes of potentially
+	  uninitialized variables. The selected class of variable will be
+	  initialized before use in a function.
+
+	config INIT_STACK_NONE
+		bool "no automatic stack variable initialization (weakest)"
+		help
+		  Disable automatic stack variable initialization.
+		  This leaves the kernel vulnerable to the standard
+		  classes of uninitialized stack variable exploits
+		  and information exposures.
+
+	config INIT_STACK_ALL_PATTERN
+		bool "pattern-init everything (strongest)"
+		depends on CC_HAS_AUTO_VAR_INIT_PATTERN
+		depends on !KMSAN
+		help
+		  Initializes everything on the stack (including padding)
+		  with a specific debug value. This is intended to eliminate
+		  all classes of uninitialized stack variable exploits and
+		  information exposures, even variables that were warned about
+		  having been left uninitialized.
+
+		  Pattern initialization is known to provoke many existing bugs
+		  related to uninitialized locals, e.g. pointers receive
+		  non-NULL values, buffer sizes and indices are very big. The
+		  pattern is situation-specific; Clang on 64-bit uses 0xAA
+		  repeating for all types and padding except float and double
+		  which use 0xFF repeating (-NaN). Clang on 32-bit uses 0xFF
+		  repeating for all types and padding.
+		  GCC uses 0xFE repeating for all types, and zero for padding.
+
+	config INIT_STACK_ALL_ZERO
+		bool "zero-init everything (strongest and safest)"
+		depends on CC_HAS_AUTO_VAR_INIT_ZERO
+		depends on !KMSAN
+		help
+		  Initializes everything on the stack (including padding)
+		  with a zero value. This is intended to eliminate all
+		  classes of uninitialized stack variable exploits and
+		  information exposures, even variables that were warned
+		  about having been left uninitialized.
+
+		  Zero initialization provides safe defaults for strings
+		  (immediately NUL-terminated), pointers (NULL), indices
+		  (index 0), and sizes (0 length), so it is therefore more
+		  suitable as a production security mitigation than pattern
+		  initialization.
+
+endchoice
+
+config CC_HAS_SANCOV_STACK_DEPTH_CALLBACK
+	def_bool $(cc-option,-fsanitize-coverage-stack-depth-callback-min=1)
+
+config KSTACK_ERASE
+	bool "Poison kernel stack before returning from syscalls"
+	depends on HAVE_ARCH_KSTACK_ERASE
+	depends on GCC_PLUGINS || CC_HAS_SANCOV_STACK_DEPTH_CALLBACK
+	help
+	  This option makes the kernel erase the kernel stack before
+	  returning from system calls. This has the effect of leaving
+	  the stack initialized to the poison value, which both reduces
+	  the lifetime of any sensitive stack contents and reduces
+	  potential for uninitialized stack variable exploits or information
+	  exposures (it does not cover functions reaching the same stack
+	  depth as prior functions during the same syscall). This blocks
+	  most uninitialized stack variable attacks, with the performance
+	  impact being driven by the depth of the stack usage, rather than
+	  the function calling complexity.
+
+	  The performance impact on a single CPU system kernel compilation
+	  sees a 1% slowdown, other systems and workloads may vary and you
+	  are advised to test this feature on your expected workload before
+	  deploying it.
+
+config GCC_PLUGIN_STACKLEAK
+	def_bool KSTACK_ERASE
+	depends on GCC_PLUGINS
+	help
+	  This plugin was ported from grsecurity/PaX. More information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
+config GCC_PLUGIN_STACKLEAK_VERBOSE
+	bool "Report stack depth analysis instrumentation" if EXPERT
+	depends on GCC_PLUGIN_STACKLEAK
+	depends on !COMPILE_TEST	# too noisy
+	help
+	  This option will cause a warning to be printed each time the
+	  stackleak plugin finds a function it thinks needs to be
+	  instrumented. This is useful for comparing coverage between
+	  builds.
+
+config KSTACK_ERASE_TRACK_MIN_SIZE
+	int "Minimum stack frame size of functions tracked by KSTACK_ERASE"
+	default 100
+	range 0 4096
+	depends on KSTACK_ERASE
+	help
+	  The KSTACK_ERASE option instruments the kernel code for tracking
+	  the lowest border of the kernel stack (and for some other purposes).
+	  It inserts the __sanitizer_cov_stack_depth() call for the functions
+	  with a stack frame size greater than or equal to this parameter.
+	  If unsure, leave the default value 100.
+
+config KSTACK_ERASE_METRICS
+	bool "Show KSTACK_ERASE metrics in the /proc file system"
+	depends on KSTACK_ERASE
+	depends on PROC_FS
+	help
+	  If this is set, KSTACK_ERASE metrics for every task are available
+	  in the /proc file system. In particular, /proc/<pid>/stack_depth
+	  shows the maximum kernel stack consumption for the current and
+	  previous syscalls. Although this information is not precise, it
+	  can be useful for estimating the KSTACK_ERASE performance impact
+	  for your workloads.
+
+config KSTACK_ERASE_RUNTIME_DISABLE
+	bool "Allow runtime disabling of kernel stack erasing"
+	depends on KSTACK_ERASE
+	help
+	  This option provides 'stack_erasing' sysctl, which can be used in
+	  runtime to control kernel stack erasing for kernels built with
+	  CONFIG_KSTACK_ERASE.
+
+config INIT_ON_ALLOC_DEFAULT_ON
+	bool "Enable heap memory zeroing on allocation by default"
+	depends on !KMSAN
+	help
+	  This has the effect of setting "init_on_alloc=1" on the kernel
+	  command line. This can be disabled with "init_on_alloc=0".
+	  When "init_on_alloc" is enabled, all page allocator and slab
+	  allocator memory will be zeroed when allocated, eliminating
+	  many kinds of "uninitialized heap memory" flaws, especially
+	  heap content exposures. The performance impact varies by
+	  workload, but most cases see <1% impact. Some synthetic
+	  workloads have measured as high as 7%.
+
+config INIT_ON_FREE_DEFAULT_ON
+	bool "Enable heap memory zeroing on free by default"
+	depends on !KMSAN
+	help
+	  This has the effect of setting "init_on_free=1" on the kernel
+	  command line. This can be disabled with "init_on_free=0".
+	  Similar to "init_on_alloc", when "init_on_free" is enabled,
+	  all page allocator and slab allocator memory will be zeroed
+	  when freed, eliminating many kinds of "uninitialized heap memory"
+	  flaws, especially heap content exposures. The primary difference
+	  with "init_on_free" is that data lifetime in memory is reduced,
+	  as anything freed is wiped immediately, making live forensics or
+	  cold boot memory attacks unable to recover freed memory contents.
+	  The performance impact varies by workload, but is more expensive
+	  than "init_on_alloc" due to the negative cache effects of
+	  touching "cold" memory areas. Most cases see 3-5% impact. Some
+	  synthetic workloads have measured as high as 8%.
+
+config CC_HAS_ZERO_CALL_USED_REGS
+	# supported by gcc-11 or newer and all supported versions of clang
+	def_bool $(cc-option,-fzero-call-used-regs=used-gpr)
+
+config ZERO_CALL_USED_REGS
+	bool "Enable register zeroing on function exit"
+	depends on CC_HAS_ZERO_CALL_USED_REGS
+	help
+	  At the end of functions, always zero any caller-used register
+	  contents. This helps ensure that temporary values are not
+	  leaked beyond the function boundary. This means that register
+	  contents are less likely to be available for side channels
+	  and information exposures. Additionally, this helps reduce the
+	  number of useful ROP gadgets by about 20% (and removes compiler
+	  generated "write-what-where" gadgets) in the resulting kernel
+	  image. This has a less than 1% performance impact on most
+	  workloads. Image size growth depends on architecture, and should
+	  be evaluated for suitability. For example, x86_64 grows by less
+	  than 1%, and arm64 grows by about 5%.
+
+endmenu
+
+menu "Bounds checking"
+
+config FORTIFY_SOURCE
+	bool "Harden common str/mem functions against buffer overflows"
+	depends on ARCH_HAS_FORTIFY_SOURCE
+	help
+	  Detect overflows of buffers in common string and memory functions
+	  where the compiler can determine and validate the buffer sizes.
+
+config HARDENED_USERCOPY
+	bool "Harden memory copies between kernel and userspace"
+	imply STRICT_DEVMEM
+	help
+	  This option checks for obviously wrong memory regions when
+	  copying memory to/from the kernel (via copy_to_user() and
+	  copy_from_user() functions) by rejecting memory ranges that
+	  are larger than the specified heap object, span multiple
+	  separately allocated pages, are not on the process stack,
+	  or are part of the kernel text. This prevents entire classes
+	  of heap overflow exploits and similar kernel memory exposures.
+
+config HARDENED_USERCOPY_DEFAULT_ON
+	bool "Harden memory copies by default"
+	depends on HARDENED_USERCOPY
+	default HARDENED_USERCOPY
+	help
+	  This has the effect of setting "hardened_usercopy=on" on the kernel
+	  command line. This can be disabled with "hardened_usercopy=off".
+
+endmenu
+
+menu "Hardening of kernel data structures"
+
+config LIST_HARDENED
+	bool "Check integrity of linked list manipulation"
+	help
+	  Minimal integrity checking in the linked-list manipulation routines
+	  to catch memory corruptions that are not guaranteed to result in an
+	  immediate access fault.
+
+	  If unsure, say N.
+
+config RUST_BITMAP_HARDENED
+	bool "Check integrity of bitmap Rust API"
+	depends on RUST
+	help
+	  Enables additional assertions in the Rust Bitmap API to catch
+	  arguments that are not guaranteed to result in an immediate access
+	  fault.
+
+	  If unsure, say N.
+
+config BUG_ON_DATA_CORRUPTION
+	bool "Trigger a BUG when data corruption is detected"
+	select LIST_HARDENED
+	help
+	  Select this option if the kernel should BUG when it encounters
+	  data corruption in kernel memory structures when they get checked
+	  for validity.
+
+	  If unsure, say N.
+
+endmenu
+
+config CC_HAS_RANDSTRUCT
+	def_bool $(cc-option,-frandomize-layout-seed-file=/dev/null)
+
+choice
+	prompt "Randomize layout of sensitive kernel structures"
+	default RANDSTRUCT_FULL if COMPILE_TEST && (GCC_PLUGINS || CC_HAS_RANDSTRUCT)
+	default RANDSTRUCT_NONE
+	help
+	  If you enable this, the layouts of structures that are entirely
+	  function pointers (and have not been manually annotated with
+	  __no_randomize_layout), or structures that have been explicitly
+	  marked with __randomize_layout, will be randomized at compile-time.
+	  This can introduce the requirement of an additional information
+	  exposure vulnerability for exploits targeting these structure
+	  types.
+
+	  Enabling this feature will introduce some performance impact,
+	  slightly increase memory usage, and prevent the use of forensic
+	  tools like Volatility against the system (unless the kernel
+	  source tree isn't cleaned after kernel installation).
+
+	  The seed used for compilation is in scripts/basic/randomize.seed.
+	  It remains after a "make clean" to allow for external modules to
+	  be compiled with the existing seed and will be removed by a
+	  "make mrproper" or "make distclean". This file should not be made
+	  public, or the structure layout can be determined.
+
+	config RANDSTRUCT_NONE
+		bool "Disable structure layout randomization"
+		help
+		  Build normally: no structure layout randomization.
+
+	config RANDSTRUCT_FULL
+		bool "Fully randomize structure layout"
+		depends on CC_HAS_RANDSTRUCT || GCC_PLUGINS
+		select MODVERSIONS if MODULES && !COMPILE_TEST
+		help
+		  Fully randomize the member layout of sensitive
+		  structures as much as possible, which may have both a
+		  memory size and performance impact.
+
+		  One difference between the Clang and GCC plugin
+		  implementations is the handling of bitfields. The GCC
+		  plugin treats them as fully separate variables,
+		  introducing sometimes significant padding. Clang tries
+		  to keep adjacent bitfields together, but with their bit
+		  ordering randomized.
+
+	config RANDSTRUCT_PERFORMANCE
+		bool "Limit randomization of structure layout to cache-lines"
+		depends on GCC_PLUGINS
+		select MODVERSIONS if MODULES && !COMPILE_TEST
+		help
+		  Randomization of sensitive kernel structures will make a
+		  best effort at restricting randomization to cacheline-sized
+		  groups of members. It will further not randomize bitfields
+		  in structures. This reduces the performance hit of RANDSTRUCT
+		  at the cost of weakened randomization.
+endchoice
+
+config RANDSTRUCT
+	def_bool !RANDSTRUCT_NONE
+
+config GCC_PLUGIN_RANDSTRUCT
+	def_bool GCC_PLUGINS && RANDSTRUCT
+	help
+	  Use GCC plugin to randomize structure layout.
+
+	  This plugin was ported from grsecurity/PaX. More
+	  information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
+endmenu
diff --git a/security/Makefile b/security/Makefile
new file mode 100644
index 000000000..4601230ba
--- /dev/null
+++ b/security/Makefile
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the kernel security code
+#
+
+obj-$(CONFIG_KEYS)			+= keys/
+
+# always enable default capabilities
+obj-y					+= commoncap.o
+obj-$(CONFIG_SECURITY) 			+= lsm_syscalls.o
+obj-$(CONFIG_MMU)			+= min_addr.o
+
+# Object file lists
+obj-$(CONFIG_SECURITY)			+= security.o lsm_notifier.o lsm_init.o
+obj-$(CONFIG_SECURITYFS)		+= inode.o
+obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/
+obj-$(CONFIG_SECURITY_SMACK)		+= smack/
+obj-$(CONFIG_HAS_SECURITY_AUDIT)	+= lsm_audit.o
+obj-$(CONFIG_SECURITY_TOMOYO)		+= tomoyo/
+obj-$(CONFIG_SECURITY_APPARMOR)		+= apparmor/
+obj-$(CONFIG_SECURITY_YAMA)		+= yama/
+obj-$(CONFIG_SECURITY_LOADPIN)		+= loadpin/
+obj-$(CONFIG_SECURITY_SAFESETID)       += safesetid/
+obj-$(CONFIG_SECURITY_LOCKDOWN_LSM)	+= lockdown/
+obj-$(CONFIG_CGROUPS)			+= device_cgroup.o
+obj-$(CONFIG_BPF_LSM)			+= bpf/
+obj-$(CONFIG_SECURITY_LANDLOCK)		+= landlock/
+obj-$(CONFIG_SECURITY_IPE)		+= ipe/
+
+# Object integrity file lists
+obj-$(CONFIG_INTEGRITY)			+= integrity/
diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore
new file mode 100644
index 000000000..6d1eb1c15
--- /dev/null
+++ b/security/apparmor/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+net_names.h
+capability_names.h
+rlim_names.h
diff --git a/security/apparmor/.kunitconfig b/security/apparmor/.kunitconfig
new file mode 100644
index 000000000..aa842a026
--- /dev/null
+++ b/security/apparmor/.kunitconfig
@@ -0,0 +1,5 @@
+CONFIG_KUNIT=y
+CONFIG_NET=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_APPARMOR=y
+CONFIG_SECURITY_APPARMOR_KUNIT_TEST=y
diff --git a/security/apparmor/Kconfig b/security/apparmor/Kconfig
new file mode 100644
index 000000000..a1f3749bd
--- /dev/null
+++ b/security/apparmor/Kconfig
@@ -0,0 +1,134 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_APPARMOR
+	bool "AppArmor support"
+	depends on SECURITY && NET
+	select AUDIT
+	select SECURITY_PATH
+	select SECURITYFS
+	select SECURITY_NETWORK
+	default n
+	help
+	  This enables the AppArmor security module.
+	  Required userspace tools (if they are not included in your
+	  distribution) and further information may be found at
+	  https://apparmor.wiki.kernel.org
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_APPARMOR_DEBUG
+	bool "Build AppArmor with debug code"
+	depends on SECURITY_APPARMOR
+	default n
+	help
+	  Build apparmor with debugging logic in apparmor. Not all
+	  debugging logic will necessarily be enabled. A submenu will
+	  provide fine grained control of the debug options that are
+	  available.
+
+config SECURITY_APPARMOR_DEBUG_ASSERTS
+	bool "Build AppArmor with debugging asserts"
+	depends on SECURITY_APPARMOR_DEBUG
+	default y
+	help
+	  Enable code assertions made with AA_BUG. These are primarily
+	  function entry preconditions but also exist at other key
+	  points. If the assert is triggered it will trigger a WARN
+	  message.
+
+config SECURITY_APPARMOR_DEBUG_MESSAGES
+	bool "Debug messages enabled by default"
+	depends on SECURITY_APPARMOR_DEBUG
+	default n
+	help
+	  Set the default value of the apparmor.debug kernel parameter.
+	  When enabled, various debug messages will be logged to
+	  the kernel message buffer.
+
+config SECURITY_APPARMOR_INTROSPECT_POLICY
+	bool "Allow loaded policy to be introspected"
+	depends on SECURITY_APPARMOR
+	default y
+	help
+	  This option selects whether introspection of loaded policy
+	  is available to userspace via the apparmor filesystem. This
+	  adds to kernel memory usage. It is required for introspection
+	  of loaded policy, and check point and restore support. It
+	  can be disabled for embedded systems where reducing memory and
+	  cpu is paramount.
+
+config SECURITY_APPARMOR_HASH
+	bool "Enable introspection of sha256 hashes for loaded profiles"
+	depends on SECURITY_APPARMOR_INTROSPECT_POLICY
+	select CRYPTO_LIB_SHA256
+	default y
+	help
+	  This option selects whether introspection of loaded policy
+	  hashes is available to userspace via the apparmor
+	  filesystem. This option provides a light weight means of
+	  checking loaded policy.  This option adds to policy load
+	  time and can be disabled for small embedded systems.
+
+config SECURITY_APPARMOR_HASH_DEFAULT
+       bool "Enable policy hash introspection by default"
+       depends on SECURITY_APPARMOR_HASH
+       default y
+       help
+	 This option selects whether sha256 hashing of loaded policy
+	 is enabled by default. The generation of sha256 hashes for
+	 loaded policy provide system administrators a quick way to
+	 verify that policy in the kernel matches what is expected,
+	 however it can slow down policy load on some devices. In
+	 these cases policy hashing can be disabled by default and
+	 enabled only if needed.
+
+config SECURITY_APPARMOR_EXPORT_BINARY
+	bool "Allow exporting the raw binary policy"
+	depends on SECURITY_APPARMOR_INTROSPECT_POLICY
+	select ZSTD_COMPRESS
+	select ZSTD_DECOMPRESS
+	default y
+	help
+	  This option allows reading back binary policy as it was loaded.
+	  It increases the amount of kernel memory needed by policy and
+	  also increases policy load time. This option is required for
+	  checkpoint and restore support, and debugging of loaded policy.
+
+config SECURITY_APPARMOR_COMPRESSED_POLICY
+	bool "Allow loading policy in a compressed format"
+	depends on SECURITY_APPARMOR
+	select ZSTD_DECOMPRESS
+	default y
+	help
+	  This option allows loading policy from userspace in a
+	  compressed format. This allows for userspace to not have to
+	  decrompress caches before loading policy, and also allows
+	  for less kernel memory to be used when "exporting the raw
+	  binary policy" is enabled.
+
+config SECURITY_APPARMOR_PARANOID_LOAD
+	bool "Perform full verification of loaded policy"
+	depends on SECURITY_APPARMOR
+	default y
+	help
+	  This options allows controlling whether apparmor does a full
+	  verification of loaded policy. This should not be disabled
+	  except for embedded systems where the image is read only,
+	  includes policy, and has some form of integrity check.
+	  Disabling the check will speed up policy loads.
+
+config SECURITY_APPARMOR_KUNIT_TEST
+	tristate "Build KUnit tests for policy_unpack.c" if !KUNIT_ALL_TESTS
+	depends on KUNIT && SECURITY_APPARMOR
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the AppArmor KUnit tests.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
+	  running KUnit test harness and are not for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
diff --git a/security/apparmor/Makefile b/security/apparmor/Makefile
new file mode 100644
index 000000000..8aed0d7ed
--- /dev/null
+++ b/security/apparmor/Makefile
@@ -0,0 +1,114 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for AppArmor Linux Security Module
+#
+obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o
+
+apparmor-y := apparmorfs.o audit.o capability.o task.o ipc.o lib.o match.o \
+              path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \
+              resource.o secid.o file.o policy_ns.o label.o mount.o net.o \
+              policy_compat.o af_unix.o af_inet.o
+apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o
+
+obj-$(CONFIG_SECURITY_APPARMOR_KUNIT_TEST) += apparmor_policy_unpack_test.o
+apparmor_policy_unpack_test-objs += policy_unpack_test.o
+
+clean-files := capability_names.h rlim_names.h net_names.h
+
+# Build a lower case string table of address family names
+# Transform lines from
+#    #define AF_LOCAL		1	/* POSIX name for AF_UNIX	*/
+#    #define AF_INET		2	/* Internet IP Protocol 	*/
+# to
+#    [1] = "local",
+#    [2] = "inet",
+#
+# and build the securityfs entries for the mapping.
+# Transforms lines from
+#    #define AF_INET		2	/* Internet IP Protocol 	*/
+# to
+#    #define AA_SFS_AF_MASK "local inet"
+quiet_cmd_make-af = GEN     $@
+cmd_make-af = echo "static const char *const address_family_names[] = {" > $@ ;\
+	sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+	 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+	echo "};" >> $@ ;\
+	printf '%s' '\#define AA_SFS_AF_MASK "' >> $@ ;\
+	sed -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+	 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\
+	 $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+# Build a lower case string table of sock type names
+# Transform lines from
+#    SOCK_STREAM	= 1,
+# to
+#    [1] = "stream",
+quiet_cmd_make-sock = GEN     $@
+cmd_make-sock = echo "static const char *const sock_type_names[] = {" >> $@ ;\
+	sed $^ >>$@ -r -n \
+	-e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+	echo "};" >> $@
+
+# Build a lower case string table of capability names
+# Transforms lines from
+#    #define CAP_DAC_OVERRIDE     1
+# to
+#    [1] = "dac_override",
+quiet_cmd_make-caps = GEN     $@
+cmd_make-caps = echo "static const char *const capability_names[] = {" > $@ ;\
+	sed $< >>$@ -r -n -e '/CAP_FS_MASK/d' \
+	-e 's/^\#define[ \t]+CAP_([A-Z0-9_]+)[ \t]+([0-9]+)/[\2] = "\L\1",/p';\
+	echo "};" >> $@ ;\
+	printf '%s' '\#define AA_SFS_CAPS_MASK "' >> $@ ;\
+	sed $< -r -n -e '/CAP_FS_MASK/d' \
+	    -e 's/^\#define[ \t]+CAP_([A-Z0-9_]+)[ \t]+([0-9]+)/\L\1/p' | \
+	     tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+
+# Build a lower case string table of rlimit names.
+# Transforms lines from
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+#    [RLIMIT_STACK] = "stack",
+#
+# and build a second integer table (with the second sed cmd), that maps
+# RLIMIT defines to the order defined in asm-generic/resource.h  This is
+# required by policy load to map policy ordering of RLIMITs to internal
+# ordering for architectures that redefine an RLIMIT.
+# Transforms lines from
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+# RLIMIT_STACK, 
+#
+# and build the securityfs entries for the mapping.
+# Transforms lines from
+#    #define RLIMIT_FSIZE        1   /* Maximum filesize */
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+# #define AA_SFS_RLIMIT_MASK "fsize stack"
+quiet_cmd_make-rlim = GEN     $@
+cmd_make-rlim = echo "static const char *const rlim_names[RLIM_NLIMITS] = {" \
+	> $@ ;\
+	sed $< >> $@ -r -n \
+	    -e 's/^\# ?define[ \t]+(RLIMIT_([A-Z0-9_]+)).*/[\1] = "\L\2",/p';\
+	echo "};" >> $@ ;\
+	echo "static const int rlim_map[RLIM_NLIMITS] = {" >> $@ ;\
+	sed -r -n "s/^\# ?define[ \t]+(RLIMIT_[A-Z0-9_]+).*/\1,/p" $< >> $@ ;\
+	echo "};" >> $@ ; \
+	printf '%s' '\#define AA_SFS_RLIMIT_MASK "' >> $@ ;\
+	sed -r -n 's/^\# ?define[ \t]+RLIMIT_([A-Z0-9_]+).*/\L\1/p' $< | \
+	    tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+$(obj)/capability.o : $(obj)/capability_names.h
+$(obj)/net.o : $(obj)/net_names.h
+$(obj)/resource.o : $(obj)/rlim_names.h
+$(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \
+			    $(src)/Makefile
+	$(call cmd,make-caps)
+$(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \
+		      $(src)/Makefile
+	$(call cmd,make-rlim)
+$(obj)/net_names.h : $(srctree)/include/linux/socket.h \
+		     $(srctree)/include/linux/net.h \
+		     $(src)/Makefile
+	$(call cmd,make-af)
+	$(call cmd,make-sock)
diff --git a/security/apparmor/af_inet.c b/security/apparmor/af_inet.c
new file mode 100644
index 000000000..516c90165
--- /dev/null
+++ b/security/apparmor/af_inet.c
@@ -0,0 +1,565 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor inet fine grained mediation
+ *
+ * Copyright 2024 Canonical Ltd.
+ *
+ */
+
+#include <net/tcp_states.h>
+
+#include "include/audit.h"
+#include "include/af_inet.h"
+#include "include/apparmor.h"
+#include "include/file.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/cred.h"
+
+
+static inline aa_state_t RULE_MEDIATES_SK(struct aa_ruleset *rules,
+					  const struct sock *sk)
+{
+	return RULE_MEDIATES_NET(rules);
+}
+
+
+enum addr_type {
+	ADDR_LOCAL = 0,
+	ADDR_LOCAL_PRIV	= 1,
+	ADDR_REMOTE = 2,
+};
+
+struct match_addr {
+	const char *addrp;
+	enum addr_type addrtype;
+	int len;
+	__be16 port;
+};
+
+struct stored_match_addr {
+	union {
+		struct sockaddr addr;
+		struct sockaddr_in addr4;
+		struct sockaddr_in6 addr6;
+	};
+	int addrlen;
+	struct match_addr maddr;
+};
+
+static void set_ad_create(struct apparmor_audit_data *ad,
+			 int family, int type, int protocol)
+{
+	ad->common.u.net->family = family;
+	ad->net.type = type;
+	ad->net.protocol = protocol;
+}
+
+static int set_ad_addr(struct apparmor_audit_data *ad,
+		       u16 family, bool source, struct match_addr *maddr)
+{
+	ad->common.u.net->family = family;
+
+	if (source) {
+		ad->common.u.net->sport = maddr->port;
+		if (maddr->addrp) {
+			if (family == AF_INET)
+				/* ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; */
+				ad->common.u.net->v4info.saddr = *(__be32 *)maddr->addrp;
+			else
+				/* ad.u.net->v4info.saddr = addr6->sin6_addr.s6_addr; */
+				ad->common.u.net->v6info.saddr = *(struct in6_addr *)maddr->addrp;
+		}
+	} else {
+		ad->common.u.net->dport = maddr->port;
+		if (maddr->addrp) {
+			if (family == AF_INET)
+				/* ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; */
+				ad->common.u.net->v4info.daddr = *(__be32 *)maddr->addrp;
+			else
+				/* ad.u.net->v4info.saddr = addr6->sin6_addr.s6_addr; */
+				ad->common.u.net->v6info.daddr = *(struct in6_addr *)maddr->addrp;
+		}
+	}
+	return 0;
+}
+
+/* returns 0 on success
+* raw_port - if set raw_port (protocol) when SOCK_RAW */
+static int map_addr(struct sockaddr *addr, int addrlen, u16 raw_port,
+		    enum addr_type addrtype, struct match_addr *maddr,
+		    struct apparmor_audit_data *ad)
+{
+	struct sockaddr_in *addr4 = NULL;
+	struct sockaddr_in6 *addr6 = NULL;
+
+	AA_BUG(!addr);
+	AA_BUG(!maddr);
+
+	maddr->addrtype = addrtype;
+	if (!addr || addrlen < offsetofend(struct sockaddr, sa_family)) {
+		maddr->addrp = NULL;
+		maddr->port = 0;
+		maddr->len = 0;
+		return 0;
+	}
+
+	/*
+	 * its possibly to have sk->sk_family == PF_INET6 and
+	 * addr->sa_family == AF_INET. sk_family is used for socket
+	 * mediation, sa_family for when we have address ...
+	 */
+	switch (addr->sa_family) {
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)addr;
+		if (addrlen < sizeof(struct sockaddr_in))
+			return -EINVAL;
+		maddr->port = addr4->sin_port;
+		maddr->addrp = (char *)&addr4->sin_addr.s_addr;
+		maddr->len = 4;
+		break;
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)addr;
+		if (addrlen < SIN6_LEN_RFC2133)
+			return -EINVAL;
+		maddr->port = addr6->sin6_port;
+		maddr->addrp = (char *)&addr6->sin6_addr.s6_addr;
+		maddr->len = 16;
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+	/* per ip spec, && sk->sk_type == SOCK_RAW*/
+	if (raw_port && addrtype != ADDR_REMOTE)
+		maddr->port = htons(raw_port);
+	if (ad)
+		set_ad_addr(ad, addr->sa_family, addrtype != ADDR_REMOTE, maddr);
+
+	return 0;
+}
+
+/* -ENOTCONN if not connected */
+static int map_sock_addr(struct socket *sock, enum addr_type addrtype,
+			 struct stored_match_addr *maddr,
+			 struct apparmor_audit_data *ad)
+{
+	/* do we need early bailout for !family ... */
+	maddr->addrlen = sock->ops->getname(sock, (struct sockaddr *) &maddr->addr, addrtype != ADDR_REMOTE ? 0 : 1);
+	if (maddr->addrlen == -ENOTCONN) {
+		maddr->addrlen = 0;
+		return map_addr(NULL, 0, 0, addrtype, &maddr->maddr, ad);
+	} else if (maddr->addrlen < 0)
+		return maddr->addrlen;
+	return map_addr(&maddr->addr, maddr->addrlen, 0, addrtype,
+			&maddr->maddr, ad);
+}
+
+/* TODO: combine with connect map addr */
+/* TODO: raw_port */
+static int bind_map_addr(const struct sock *sk, struct sockaddr *addr,
+			 int addrlen,
+			 struct match_addr *maddr,
+			 struct apparmor_audit_data *ad)
+{
+	struct sockaddr_in *addr4 = NULL;
+	struct sockaddr_in6 *addr6 = NULL;
+	u16 family;
+
+	AA_BUG(!sk);
+	AA_BUG(!addr);
+	AA_BUG(!maddr);
+
+	if (addrlen < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
+
+	maddr->addrtype = ADDR_LOCAL;
+	/*
+	 * its possibly to have sk->sk_family == PF_INET6 and
+	 * addr->sa_family == AF_INET. sk_family is used for socket
+	 * mediation, sa_family for when we have address ...
+	 */
+	family = addr->sa_family;
+	switch (addr->sa_family) {
+	case AF_UNSPEC:
+		if (sk->sk_family == PF_INET6) {
+			/* Length check from inet6_bind_sk() */
+			if (addrlen < SIN6_LEN_RFC2133)
+				return -EINVAL;
+			/* Family check from __inet6_bind() */
+			return -EAFNOSUPPORT;
+		}
+		/* see __inet_bind(), we only want to allow
+		 * AF_UNSPEC if the address is INADDR_ANY
+		 */
+		addr4 = (struct sockaddr_in *)addr;
+		if (addr4->sin_addr.s_addr != htonl(INADDR_ANY))
+			return -EAFNOSUPPORT;
+		family = AF_INET;
+		fallthrough;
+	case AF_INET:
+		addr4 = (struct sockaddr_in *)addr;
+		if (addrlen < sizeof(struct sockaddr_in))
+			return -EINVAL;
+		maddr->port = addr4->sin_port;
+		maddr->addrp = (char *)&addr4->sin_addr.s_addr;
+		maddr->len = 4;
+		break;
+	case AF_INET6:
+		addr6 = (struct sockaddr_in6 *)addr;
+		if (addrlen < SIN6_LEN_RFC2133)
+			return -EINVAL;
+		maddr->port = addr6->sin6_port;
+		maddr->addrp = (char *)&addr6->sin6_addr.s6_addr;
+		maddr->len = 16;
+		break;
+	default:
+		return -EAFNOSUPPORT;
+	}
+
+	if (ad)
+		set_ad_addr(ad, family, true, maddr);
+
+	return 0;
+}
+
+
+static inline int profile_sk_perm(struct aa_profile *profile, u32 request,
+				  const struct sock *sk,
+				  struct match_addr *maddr,
+				  struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+/* no kernel_t bailout */
+static int profile_create_perm(struct aa_profile *profile, int family,
+			       int type, int protocol,
+			       struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+
+	return aa_profile_af_perm(profile, ad, AA_MAY_CREATE, family, type,
+				  protocol);
+}
+
+
+/* sendmsg/rcvmsg/connect */
+static int profile_remote_perm(struct aa_profile *profile,
+			       const struct sock *sk,
+			       u32 request, struct match_addr *raddr,
+			       struct match_addr *laddr,
+			       struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!raddr);
+	AA_BUG(!laddr);
+	AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6,
+	       "family=%d", sk->sk_family);
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+static int profile_bind_perm(struct aa_profile *profile,
+			     const struct sock *sk,
+			     struct match_addr *maddr,
+			     struct apparmor_audit_data *ad)
+{
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_BIND, sk);
+
+}
+
+static int profile_listen_perm(struct aa_profile *profile,
+			       const struct sock *sk,
+			       struct match_addr *maddr, int backlog,
+			       struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!maddr);
+	AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6,
+	       "family=%d", sk->sk_family);
+
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_LISTEN, sk);
+}
+
+static inline int profile_accept_perm(struct aa_profile *profile,
+				      const struct sock *sk,
+				      struct match_addr *maddr,
+				      const struct sock *newsk,
+				      struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	/* AA_BUG(!newsk);  newsk can be null here, since not using atm ... */
+	AA_BUG(!maddr);
+	AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6,
+	       "family=%d", sk->sk_family);
+
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_ACCEPT, sk);
+}
+
+/* getopt/setopt */
+static int profile_opt_perm(struct aa_profile *profile, u32 request,
+			    const struct sock *sk, struct match_addr *maddr,
+			    int level, int optname,
+			    struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!maddr);
+	AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6,
+	       "family=%d", sk->sk_family);
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+/* ---------------------------------------------------------------------- */
+
+// TODO: cleanup init to use recursion, so we can have N init fns, in 1 macro
+// TODO: lift DEFINE_AUDIT out of macro into init fn???
+
+/* no kernel_t bailout */
+#define label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXX, YYYY, CALLBACKFN) \
+({								\
+	int __EERROR = 0;					\
+	if (label_mediates(LABEL, AA_CLASS_NET)) {		\
+		struct aa_profile *PROFILE;			\
+		DEFINE_AUDIT_SK(AAD, OP, CRED, SOCKSK);		\
+		(AAD).subj_cred = (CRED);			\
+		(AAD).request = (REQUEST);			\
+		__EERROR = (XXXX);				\
+		if (__EERROR == 0) {				\
+			__EERROR = (YYYY);			\
+			if (__EERROR == 0) {			\
+				__EERROR = fn_for_each(LABEL, PROFILE,	\
+						       (CALLBACKFN));	\
+			}						\
+		}							\
+	}							\
+	__EERROR;						\
+})
+
+/* no kernel_t bailout */
+#define label_sk_has_perm(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, CALLBACKFN) \
+	label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, \
+			   0, 0, CALLBACKFN)
+
+/* no kernel_t bailout */
+#define label_sk_has_perm1(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXX, CALLBACKFN) \
+	label_sk_has_perm2(CRED, LABEL, SOCKSK, OP, REQUEST, PROFILE, AAD, \
+			   XXXX, 0, CALLBACKFN)
+
+
+/* Early bailout for kernel_t - 2 init args before callback */
+#define sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, YYYYX, CALLBACKFN) \
+({									\
+	struct aa_label *__label;					\
+	struct aa_sk_ctx *__ctx = aa_sock(SOCKSK);			\
+	int __ERROR = 0;						\
+	bool __needput;						\
+	if (rcu_access_pointer(__ctx->label) != kernel_t) {		\
+									\
+		__label = begin_current_label_crit_section(&__needput);	\
+                __ERROR = label_sk_has_perm2(current_cred(), __label, SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, YYYYX, CALLBACKFN); \
+		end_current_label_crit_section(__label, __needput);	\
+	}								\
+	__ERROR;							\
+})
+
+/* Early bailout for kernel_t - no init args before callback */
+#define sk_has_perm(SOCKSK, OP, REQUEST, PROFILE, AAD, CALLBACKFN)	\
+	sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, 0, 0, CALLBACKFN)
+
+
+/* Early bailout for kernel_t - 1 init arg before callback */
+#define sk_has_perm1(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, CALLBACKFN) \
+	sk_has_perm2(SOCKSK, OP, REQUEST, PROFILE, AAD, XXXXY, 0, CALLBACKFN)
+
+
+
+/* no kernel_t early bailout */
+/* NOTE: already lifted label_mediates into lsm.c */
+int aa_inet_create_perm(struct aa_label *label, int family, int type,
+			int protocol)
+{
+	struct aa_profile *profile;
+	int error = 0;
+	DEFINE_AUDIT_NET(ad, OP_CREATE, current_cred(), NULL, family, type,
+			 protocol);
+
+	ad.subj_cred = current_cred();
+	set_ad_create(&ad, family, type, protocol);
+	error = fn_for_each(label, profile,
+			    profile_create_perm(profile, family, type,
+						protocol, &ad));
+
+	return error;
+}
+
+int aa_inet_bind_perm(struct socket *sock, struct sockaddr *addr,
+		      int addrlen)
+{
+	struct match_addr maddr;
+
+	return sk_has_perm1(sock->sk, OP_BIND, AA_MAY_BIND, profile, ad,
+			    bind_map_addr(sock->sk, addr, addrlen, &maddr,
+					  &ad),
+			    profile_bind_perm(profile, sock->sk, &maddr, &ad));
+}
+
+int aa_inet_connect_perm(struct socket *sock, struct sockaddr *addr,
+			 int addrlen)
+{
+	struct stored_match_addr laddr;
+	struct match_addr raddr;
+
+	/* disconnect socket */
+	if (addrlen < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
+	if (addr->sa_family == AF_UNSPEC)
+		return 0;
+
+	/* do we need early bailout for !family ... */
+	return sk_has_perm2(sock->sk, OP_CONNECT, AA_MAY_CONNECT, profile, ad,
+			    map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad),
+			    map_addr(addr, addrlen, 0, ADDR_REMOTE, &raddr,
+				     &ad),
+			    profile_remote_perm(profile, sock->sk,
+						AA_MAY_CONNECT, &raddr,
+						&laddr.maddr, &ad));
+}
+
+int aa_inet_listen_perm(struct socket *sock, int backlog)
+{
+	struct stored_match_addr maddr;
+
+	/* do we need early bailout for !family ... */
+	return sk_has_perm1(sock->sk, OP_LISTEN, AA_MAY_LISTEN, profile, ad,
+			    map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad),
+			    profile_listen_perm(profile, sock->sk, &maddr.maddr,
+						backlog, &ad));
+}
+
+/* ability of sock to connect, not peer address binding */
+int aa_inet_accept_perm(struct socket *sock, struct socket *newsock)
+{
+	struct stored_match_addr maddr;
+	int error;
+
+	error = sk_has_perm1(sock->sk, OP_ACCEPT, AA_MAY_ACCEPT, profile, ad,
+			     map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad),
+			     profile_accept_perm(profile, sock->sk,
+						 &maddr.maddr,
+						 newsock->sk, &ad));
+
+	/* selinux updates inode - need to investigate this more */
+	return error;
+}
+
+/* sendmsg, recvmsg. */
+int aa_inet_msg_perm(const char *op, u32 request, struct socket *sock,
+		     struct msghdr *msg, int size)
+{
+	struct stored_match_addr laddr;
+	struct match_addr raddr;
+
+	/* do we need early bailout for !family ... */
+	return sk_has_perm2(sock->sk, op, request, profile, ad,
+			    map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad),
+			    map_addr(msg->msg_name, msg->msg_namelen, 0,
+				     ADDR_REMOTE, &raddr, &ad),
+			    profile_remote_perm(profile, sock->sk, request,
+						&raddr, &laddr.maddr, &ad));
+}
+
+/* getopt, setopt */
+int aa_inet_opt_perm(const char *op, u32 request, struct socket *sock,
+		     int level, int optname)
+{
+	struct stored_match_addr maddr;
+
+	return sk_has_perm1(sock->sk, op, request, profile, ad,
+			    map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad),
+			    profile_opt_perm(profile, request, sock->sk,
+					    &maddr.maddr, level, optname, &ad));
+}
+
+static int inet_label_sock_perm(const struct cred *cred, struct aa_label *label,
+				const char *op, u32 request,
+				struct socket *sock)
+{
+	struct stored_match_addr maddr;
+
+	return label_sk_has_perm1(cred, label, sock->sk, op, request, profile,
+				  ad,
+			map_sock_addr(sock, ADDR_LOCAL, &maddr, &ad),
+			profile_sk_perm(profile, request, sock->sk,
+					&maddr.maddr, &ad));
+}
+
+/* revalidation, get/set attr/getsockname/peername */
+int aa_inet_sock_perm(const char *op, u32 request, struct socket *sock)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sock->sk);
+	struct aa_label *label;
+	bool needput;
+	int error;
+
+	if (rcu_access_pointer(ctx->label) == kernel_t)
+		return 0;
+
+	label = begin_current_label_crit_section(&needput);
+	error = inet_label_sock_perm(current_cred(), label, op, request, sock);
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+int aa_inet_file_perm(const struct cred *subj_cred, struct aa_label *label,
+		      const char *op, u32 request, struct socket *sock)
+{
+	u32 sk_req = request & ~NET_PEER_MASK;
+	struct stored_match_addr laddr;
+	const struct sock *sk = sock->sk;
+	int error = 0;
+
+	AA_BUG(!label);
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(sk->sk_family != PF_INET && sk->sk_family != PF_INET6,
+	       "family=%d", sk->sk_family);
+
+	/* access to the local sock */
+	error = label_sk_has_perm1(subj_cred, label, sock->sk, op, request,
+				   profile, ad,
+			map_sock_addr(sock, ADDR_LOCAL, &laddr, &ad),
+			profile_sk_perm(profile, sk_req, sock->sk, &laddr.maddr,
+					&ad));
+
+	if (!error) {
+		struct stored_match_addr raddr;
+
+		/* TODO: have ad here: instead of in CB so we do have to redo */
+		error = map_sock_addr(sock, ADDR_REMOTE, &raddr, NULL);
+		if (!error && raddr.maddr.addrp) {
+			error = label_sk_has_perm1(subj_cred, label, sock->sk,
+						   op, request, profile, ad,
+					set_ad_addr(&ad, raddr.addr.sa_family,
+						    false, &raddr.maddr),
+					profile_remote_perm(profile, sock->sk,
+							    request,
+							    &raddr.maddr,
+							    &laddr.maddr, &ad));
+		}
+	}
+
+	return error;
+}
diff --git a/security/apparmor/af_unix.c b/security/apparmor/af_unix.c
new file mode 100644
index 000000000..b908e7448
--- /dev/null
+++ b/security/apparmor/af_unix.c
@@ -0,0 +1,812 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor af_unix fine grained mediation
+ *
+ * Copyright 2023 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+
+#include <linux/fs.h>
+#include <net/tcp_states.h>
+
+#include "include/audit.h"
+#include "include/af_unix.h"
+#include "include/apparmor.h"
+#include "include/file.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/cred.h"
+
+
+static inline struct sock *aa_unix_sk(struct unix_sock *u)
+{
+	return &u->sk;
+}
+
+static int unix_fs_perm(const char *op, u32 mask, const struct cred *subj_cred,
+			struct aa_label *label, const struct path *path)
+{
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (unconfined(label) || !label_mediates(label, AA_CLASS_FILE))
+		return 0;
+
+	mask &= NET_FS_PERMS;
+	/* if !u->path.dentry socket is being shutdown - implicit delegation
+	 * until obj delegation is supported
+	 */
+	if (path->dentry) {
+		/* the sunpath may not be valid for this ns so use the path */
+		struct inode *inode = path->dentry->d_inode;
+		vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(path->mnt), inode);
+		struct path_cond cond = {
+			.uid = vfsuid_into_kuid(vfsuid),
+			.mode = inode->i_mode,
+		};
+
+		return aa_path_perm(op, subj_cred, label, path,
+				    PATH_SOCK_COND, mask, &cond);
+	} /* else implicitly delegated */
+
+	return 0;
+}
+
+/* match_addr special constants */
+#define ABSTRACT_ADDR "\x00"		/* abstract socket addr */
+#define ANONYMOUS_ADDR "\x01"		/* anonymous endpoint, no addr */
+#define DISCONNECTED_ADDR "\x02"	/* addr is another namespace */
+#define SHUTDOWN_ADDR "\x03"		/* path addr is shutdown and cleared */
+#define FS_ADDR "/"			/* path addr in fs */
+
+static aa_state_t match_addr(const struct aa_dfa *dfa, aa_state_t state,
+			     struct sockaddr_un *addr, int addrlen)
+{
+	if (addr)
+		/* include leading \0 */
+		state = aa_dfa_match_len(dfa, state, addr->sun_path,
+					 unix_addr_len(addrlen));
+	else
+		state = aa_dfa_match_len(dfa, state, ANONYMOUS_ADDR, 1);
+	/* todo: could change to out of band for cleaner separation */
+	state = aa_dfa_null_transition(dfa, state);
+
+	return state;
+}
+
+static aa_state_t match_to_local(struct aa_policydb *policy,
+				 aa_state_t state, u32 request,
+				 int type, int protocol,
+				 struct sockaddr_un *addr, int addrlen,
+				 struct aa_perms **p,
+				 const char **info)
+{
+	state = aa_match_to_prot(policy, state, request, PF_UNIX, type,
+				 protocol, NULL, info);
+	if (state) {
+		state = match_addr(policy->dfa, state, addr, addrlen);
+		if (state) {
+			/* todo: local label matching */
+			state = aa_dfa_null_transition(policy->dfa, state);
+			if (!state)
+				*info = "failed local label match";
+		} else {
+			*info = "failed local address match";
+		}
+	}
+
+	return state;
+}
+
+struct sockaddr_un *aa_sunaddr(const struct unix_sock *u, int *addrlen)
+{
+	struct unix_address *addr;
+
+	/* memory barrier is sufficient see note in net/unix/af_unix.c */
+	addr = smp_load_acquire(&u->addr);
+	if (addr) {
+		*addrlen = addr->len;
+		return addr->name;
+	}
+	*addrlen = 0;
+	return NULL;
+}
+
+static aa_state_t match_to_sk(struct aa_policydb *policy,
+			      aa_state_t state, u32 request,
+			      struct unix_sock *u, struct aa_perms **p,
+			      const char **info)
+{
+	int addrlen;
+	struct sockaddr_un *addr = aa_sunaddr(u, &addrlen);
+
+	return match_to_local(policy, state, request, u->sk.sk_type,
+			      u->sk.sk_protocol, addr, addrlen, p, info);
+}
+
+#define CMD_ADDR	1
+#define CMD_LISTEN	2
+#define CMD_OPT		4
+
+static aa_state_t match_to_cmd(struct aa_policydb *policy, aa_state_t state,
+			       u32 request, struct unix_sock *u,
+			       char cmd, struct aa_perms **p,
+			       const char **info)
+{
+	AA_BUG(!p);
+
+	state = match_to_sk(policy, state, request, u, p, info);
+	if (state && !*p) {
+		state = aa_dfa_match_len(policy->dfa, state, &cmd, 1);
+		if (!state)
+			*info = "failed cmd selection match";
+	}
+
+	return state;
+}
+
+static aa_state_t match_to_peer(struct aa_policydb *policy, aa_state_t state,
+				u32 request, struct unix_sock *u,
+				struct sockaddr_un *peer_addr, int peer_addrlen,
+				struct aa_perms **p, const char **info)
+{
+	AA_BUG(!p);
+
+	state = match_to_cmd(policy, state, request, u, CMD_ADDR, p, info);
+	if (state && !*p) {
+		state = match_addr(policy->dfa, state, peer_addr, peer_addrlen);
+		if (!state)
+			*info = "failed peer address match";
+	}
+
+	return state;
+}
+
+static aa_state_t match_label(struct aa_profile *profile,
+			      struct aa_ruleset *rule, aa_state_t state,
+			      u32 request, struct aa_profile *peer,
+			      const struct aa_perms *p,
+			      struct apparmor_audit_data *ad)
+{
+	AA_BUG(!profile);
+	AA_BUG(!peer);
+
+	ad->peer = &peer->label;
+
+	if (state && !p) {
+		state = aa_dfa_match(rule->policy->dfa, state,
+				     peer->base.hname);
+		if (!state)
+			ad->info = "failed peer label match";
+
+	}
+
+	return aa_do_perms(profile, rule->policy, state, request, p, ad);
+}
+
+
+/* unix sock creation comes before we know if the socket will be an fs
+ * socket
+ * v6 - semantics are handled by mapping in profile load
+ * v7 - semantics require sock create for tasks creating an fs socket.
+ * v8 - same as v7
+ */
+static int profile_create_perm(struct aa_profile *profile, int family,
+			       int type, int protocol,
+			       struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		state = aa_match_to_prot(rules->policy, state, AA_MAY_CREATE,
+					 PF_UNIX, type, protocol, NULL,
+					 &ad->info);
+
+		return aa_do_perms(profile, rules->policy, state, AA_MAY_CREATE,
+				   NULL, ad);
+	}
+
+	return aa_profile_af_perm(profile, ad, AA_MAY_CREATE, family, type,
+				  protocol);
+}
+
+static int profile_sk_perm(struct aa_profile *profile,
+			   struct apparmor_audit_data *ad,
+			   u32 request, struct sock *sk, const struct path *path)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		if (is_unix_fs(sk))
+			return unix_fs_perm(ad->op, request, ad->subj_cred,
+					    &profile->label,
+					    &unix_sk(sk)->path);
+
+		state = match_to_sk(rules->policy, state, request, unix_sk(sk),
+				    &p, &ad->info);
+
+		return aa_do_perms(profile, rules->policy, state, request, p,
+				   ad);
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+static int profile_bind_perm(struct aa_profile *profile, struct sock *sk,
+			     struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!ad);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		if (is_unix_addr_fs(ad->net.addr, ad->net.addrlen))
+			/* under v7-9 fs hook handles bind */
+			return 0;
+		/* bind for abstract socket */
+		state = match_to_local(rules->policy, state, AA_MAY_BIND,
+				       sk->sk_type, sk->sk_protocol,
+				       unix_addr(ad->net.addr),
+				       ad->net.addrlen,
+				       &p, &ad->info);
+
+		return aa_do_perms(profile, rules->policy, state, AA_MAY_BIND,
+				   p, ad);
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_BIND, sk);
+}
+
+static int profile_listen_perm(struct aa_profile *profile, struct sock *sk,
+			       int backlog, struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!ad);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		__be16 b = cpu_to_be16(backlog);
+
+		if (is_unix_fs(sk))
+			return unix_fs_perm(ad->op, AA_MAY_LISTEN,
+					    ad->subj_cred, &profile->label,
+					    &unix_sk(sk)->path);
+
+		state = match_to_cmd(rules->policy, state, AA_MAY_LISTEN,
+				     unix_sk(sk), CMD_LISTEN, &p, &ad->info);
+		if (state && !p) {
+			state = aa_dfa_match_len(rules->policy->dfa, state,
+						 (char *) &b, 2);
+			if (!state)
+				ad->info = "failed listen backlog match";
+		}
+		return aa_do_perms(profile, rules->policy, state, AA_MAY_LISTEN,
+				   p, ad);
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_LISTEN, sk);
+}
+
+static int profile_accept_perm(struct aa_profile *profile,
+			       struct sock *sk,
+			       struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!ad);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		if (is_unix_fs(sk))
+			return unix_fs_perm(ad->op, AA_MAY_ACCEPT,
+					    ad->subj_cred, &profile->label,
+					    &unix_sk(sk)->path);
+
+		state = match_to_sk(rules->policy, state, AA_MAY_ACCEPT,
+				    unix_sk(sk), &p, &ad->info);
+
+		return aa_do_perms(profile, rules->policy, state, AA_MAY_ACCEPT,
+				   p, ad);
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, AA_MAY_ACCEPT, sk);
+}
+
+static int profile_opt_perm(struct aa_profile *profile, u32 request,
+			    struct sock *sk, int optname,
+			    struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(!sk);
+	AA_BUG(!ad);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		__be16 b = cpu_to_be16(optname);
+		if (is_unix_fs(sk))
+			return unix_fs_perm(ad->op, request,
+					    ad->subj_cred, &profile->label,
+					    &unix_sk(sk)->path);
+
+		state = match_to_cmd(rules->policy, state, request, unix_sk(sk),
+				     CMD_OPT, &p, &ad->info);
+		if (state && !p) {
+			state = aa_dfa_match_len(rules->policy->dfa, state,
+						 (char *) &b, 2);
+			if (!state)
+				ad->info = "failed sockopt match";
+		}
+		return aa_do_perms(profile, rules->policy, state, request, p,
+				   ad);
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+/* null peer_label is allowed, in which case the peer_sk label is used */
+static int profile_peer_perm(struct aa_profile *profile, u32 request,
+			     struct sock *sk, const struct path *path,
+			     struct sockaddr_un *peer_addr,
+			     int peer_addrlen, const struct path *peer_path,
+			     struct aa_label *peer_label,
+			     struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(!profile);
+	AA_BUG(profile_unconfined(profile));
+	AA_BUG(!sk);
+	AA_BUG(!peer_label);
+	AA_BUG(!ad);
+
+	state = RULE_MEDIATES_UNIX(rules);
+	if (state) {
+		struct aa_profile *peerp;
+
+		if (peer_path)
+			return unix_fs_perm(ad->op, request, ad->subj_cred,
+					    &profile->label, peer_path);
+		else if (path)
+			return unix_fs_perm(ad->op, request, ad->subj_cred,
+					    &profile->label, path);
+		state = match_to_peer(rules->policy, state, request,
+				      unix_sk(sk),
+				      peer_addr, peer_addrlen, &p, &ad->info);
+
+		return fn_for_each_in_scope(peer_label, peerp,
+				match_label(profile, rules, state, request,
+					    peerp, p, ad));
+	}
+
+	return aa_profile_af_sk_perm(profile, ad, request, sk);
+}
+
+/* -------------------------------- */
+
+int aa_unix_create_perm(struct aa_label *label, int family, int type,
+			int protocol)
+{
+	if (!unconfined(label)) {
+		struct aa_profile *profile;
+		DEFINE_AUDIT_NET(ad, OP_CREATE, current_cred(), NULL, family,
+				 type, protocol);
+
+		return fn_for_each_confined(label, profile,
+				profile_create_perm(profile, family, type,
+						    protocol, &ad));
+	}
+
+	return 0;
+}
+
+static int aa_unix_label_sk_perm(const struct cred *subj_cred,
+				 struct aa_label *label,
+				 const char *op, u32 request, struct sock *sk,
+				 const struct path *path)
+{
+	if (!unconfined(label)) {
+		struct aa_profile *profile;
+		DEFINE_AUDIT_SK(ad, op, subj_cred, sk);
+
+		return fn_for_each_confined(label, profile,
+				profile_sk_perm(profile, &ad, request, sk,
+						path));
+	}
+	return 0;
+}
+
+/* revalidation, get/set attr, shutdown */
+int aa_unix_sock_perm(const char *op, u32 request, struct socket *sock)
+{
+	struct aa_label *label;
+	bool needput;
+	int error;
+
+	label = begin_current_label_crit_section(&needput);
+	error = aa_unix_label_sk_perm(current_cred(), label, op,
+				      request, sock->sk,
+				      is_unix_fs(sock->sk) ? &unix_sk(sock->sk)->path : NULL);
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int valid_addr(struct sockaddr *addr, int addr_len)
+{
+	struct sockaddr_un *sunaddr = unix_addr(addr);
+
+	/* addr_len == offsetof(struct sockaddr_un, sun_path) is autobind */
+	if (addr_len < offsetof(struct sockaddr_un, sun_path) ||
+	    addr_len > sizeof(*sunaddr))
+		return -EINVAL;
+	return 0;
+}
+
+int aa_unix_bind_perm(struct socket *sock, struct sockaddr *addr,
+		      int addrlen)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	bool needput;
+	int error = 0;
+
+	error = valid_addr(addr, addrlen);
+	if (error)
+		return error;
+
+	label = begin_current_label_crit_section(&needput);
+	/* fs bind is handled by mknod */
+	if (!unconfined(label)) {
+		DEFINE_AUDIT_SK(ad, OP_BIND, current_cred(), sock->sk);
+
+		ad.net.addr = unix_addr(addr);
+		ad.net.addrlen = addrlen;
+
+		error = fn_for_each_confined(label, profile,
+				profile_bind_perm(profile, sock->sk, &ad));
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+/*
+ * unix connections are covered by the
+ * - unix_stream_connect (stream) and unix_may_send hooks (dgram)
+ * - fs connect is handled by open
+ * This is just here to document this is not needed for af_unix
+ *
+int aa_unix_connect_perm(struct socket *sock, struct sockaddr *address,
+			 int addrlen)
+{
+	return 0;
+}
+*/
+
+int aa_unix_listen_perm(struct socket *sock, int backlog)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	bool needput;
+	int error = 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		DEFINE_AUDIT_SK(ad, OP_LISTEN, current_cred(), sock->sk);
+
+		error = fn_for_each_confined(label, profile,
+				profile_listen_perm(profile, sock->sk,
+						    backlog, &ad));
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+
+/* ability of sock to connect, not peer address binding */
+int aa_unix_accept_perm(struct socket *sock, struct socket *newsock)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	bool needput;
+	int error = 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		DEFINE_AUDIT_SK(ad, OP_ACCEPT, current_cred(), sock->sk);
+
+		error = fn_for_each_confined(label, profile,
+				profile_accept_perm(profile, sock->sk, &ad));
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+
+/*
+ * dgram handled by unix_may_sendmsg, right to send on stream done at connect
+ * could do per msg unix_stream here, but connect + socket transfer is
+ * sufficient. This is just here to document this is not needed for af_unix
+ *
+ * sendmsg, recvmsg
+int aa_unix_msg_perm(const char *op, u32 request, struct socket *sock,
+		     struct msghdr *msg, int size)
+{
+	return 0;
+}
+*/
+
+int aa_unix_opt_perm(const char *op, u32 request, struct socket *sock,
+		     int level, int optname)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	bool needput;
+	int error = 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		DEFINE_AUDIT_SK(ad, op, current_cred(), sock->sk);
+
+		error = fn_for_each_confined(label, profile,
+				profile_opt_perm(profile, request, sock->sk,
+						 optname, &ad));
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int unix_peer_perm(const struct cred *subj_cred,
+			  struct aa_label *label, const char *op, u32 request,
+			  struct sock *sk, const struct path *path,
+			  struct sockaddr_un *peer_addr, int peer_addrlen,
+			  const struct path *peer_path, struct aa_label *peer_label)
+{
+	struct aa_profile *profile;
+	DEFINE_AUDIT_SK(ad, op, subj_cred, sk);
+
+	ad.net.peer.addr = peer_addr;
+	ad.net.peer.addrlen = peer_addrlen;
+
+	return fn_for_each_confined(label, profile,
+			profile_peer_perm(profile, request, sk, path,
+					  peer_addr, peer_addrlen, peer_path,
+					  peer_label, &ad));
+}
+
+/*
+ *
+ * Requires: lock held on both @sk and @peer_sk
+ *           called by unix_stream_connect, unix_may_send
+ */
+int aa_unix_peer_perm(const struct cred *subj_cred,
+		      struct aa_label *label, const char *op, u32 request,
+		      struct sock *sk, struct sock *peer_sk,
+		      struct aa_label *peer_label)
+{
+	struct unix_sock *peeru = unix_sk(peer_sk);
+	struct unix_sock *u = unix_sk(sk);
+	int plen;
+	struct sockaddr_un *paddr = aa_sunaddr(unix_sk(peer_sk), &plen);
+
+	AA_BUG(!label);
+	AA_BUG(!sk);
+	AA_BUG(!peer_sk);
+	AA_BUG(!peer_label);
+
+	return unix_peer_perm(subj_cred, label, op, request, sk,
+			      is_unix_fs(sk) ? &u->path : NULL,
+			      paddr, plen,
+			      is_unix_fs(peer_sk) ? &peeru->path : NULL,
+			      peer_label);
+}
+
+/* sk_plabel for comparison only */
+static void update_sk_ctx(struct sock *sk, struct aa_label *label,
+			  struct aa_label *plabel)
+{
+	struct aa_label *l, *old;
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	bool update_sk;
+
+	rcu_read_lock();
+	update_sk = (plabel &&
+		     (plabel != rcu_access_pointer(ctx->peer_lastupdate) ||
+		      !aa_label_is_subset(plabel, rcu_dereference(ctx->peer)))) ||
+	  !__aa_subj_label_is_cached(label, rcu_dereference(ctx->label));
+	rcu_read_unlock();
+	if (!update_sk)
+		return;
+
+	spin_lock(&unix_sk(sk)->lock);
+	old = rcu_dereference_protected(ctx->label,
+					lockdep_is_held(&unix_sk(sk)->lock));
+	l = aa_label_merge(old, label, GFP_ATOMIC);
+	if (l) {
+		if (l != old) {
+			rcu_assign_pointer(ctx->label, l);
+			aa_put_label(old);
+		} else
+			aa_put_label(l);
+	}
+	if (plabel && rcu_access_pointer(ctx->peer_lastupdate) != plabel) {
+		old = rcu_dereference_protected(ctx->peer, lockdep_is_held(&unix_sk(sk)->lock));
+
+		if (old == plabel) {
+			rcu_assign_pointer(ctx->peer_lastupdate,
+					   aa_get_label(plabel));
+		} else if (aa_label_is_subset(plabel, old)) {
+			rcu_assign_pointer(ctx->peer_lastupdate,
+					   aa_get_label(plabel));
+			rcu_assign_pointer(ctx->peer, aa_get_label(plabel));
+			aa_put_label(old);
+		} /* else race or a subset - don't update */
+	}
+	spin_unlock(&unix_sk(sk)->lock);
+}
+
+static void update_peer_ctx(struct sock *sk, struct aa_sk_ctx *ctx,
+			    struct aa_label *label)
+{
+	struct aa_label *l, *old;
+
+	spin_lock(&unix_sk(sk)->lock);
+	old = rcu_dereference_protected(ctx->peer,
+					lockdep_is_held(&unix_sk(sk)->lock));
+	l = aa_label_merge(old, label, GFP_ATOMIC);
+	if (l) {
+		if (l != old) {
+			rcu_assign_pointer(ctx->peer, l);
+			aa_put_label(old);
+		} else
+			aa_put_label(l);
+	}
+	spin_unlock(&unix_sk(sk)->lock);
+}
+
+/* This fn is only checked if something has changed in the security
+ * boundaries. Otherwise cached info off file is sufficient
+ */
+int aa_unix_file_perm(const struct cred *subj_cred, struct aa_label *label,
+		      const char *op, u32 request, struct file *file)
+{
+	struct socket *sock = (struct socket *) file->private_data;
+	struct sockaddr_un *addr, *peer_addr;
+	int addrlen, peer_addrlen;
+	struct aa_label *plabel = NULL;
+	struct sock *peer_sk = NULL;
+	u32 sk_req = request & ~NET_PEER_MASK;
+	struct path path;
+	bool is_sk_fs;
+	int error = 0;
+
+	AA_BUG(!label);
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(sock->sk->sk_family != PF_UNIX);
+
+	/* investigate only using lock via unix_peer_get()
+	 * addr only needs the memory barrier, but need to investigate
+	 * path
+	 */
+	unix_state_lock(sock->sk);
+	peer_sk = unix_peer(sock->sk);
+	if (peer_sk)
+		sock_hold(peer_sk);
+
+	is_sk_fs = is_unix_fs(sock->sk);
+	addr = aa_sunaddr(unix_sk(sock->sk), &addrlen);
+	path = unix_sk(sock->sk)->path;
+	unix_state_unlock(sock->sk);
+
+	if (is_sk_fs && peer_sk)
+		sk_req = request;
+	if (sk_req) {
+			error = aa_unix_label_sk_perm(subj_cred, label, op,
+						      sk_req, sock->sk,
+						      is_sk_fs ? &path : NULL);
+	}
+	if (!peer_sk)
+		goto out;
+
+	if (!is_sk_fs) {
+		bool is_peer_fs = is_unix_fs(peer_sk);
+
+		peer_addr = aa_sunaddr(unix_sk(peer_sk), &peer_addrlen);
+		if (is_peer_fs) {
+			struct path peer_path;
+
+			unix_state_lock(peer_sk);
+			peer_path = unix_sk(peer_sk)->path;
+			if (peer_path.dentry)
+				path_get(&peer_path);
+			unix_state_unlock(peer_sk);
+
+			last_error(error,
+				   unix_fs_perm(op, request, subj_cred, label,
+						&peer_path));
+			if (peer_path.dentry)
+				path_put(&peer_path);
+		} else {
+			struct aa_sk_ctx *pctx = aa_sock(peer_sk);
+
+			rcu_read_lock();
+			plabel = aa_get_newest_label(pctx->label);
+			rcu_read_unlock();
+			/* no fs check of aa_unix_peer_perm because conditions
+			 * above ensure they will never be done
+			 */
+			last_error(error,
+				xcheck(unix_peer_perm(subj_cred, label, op,
+					      MAY_READ | MAY_WRITE, sock->sk,
+					      is_sk_fs ? &path : NULL,
+					      peer_addr, peer_addrlen,
+					      NULL, plabel),
+				       unix_peer_perm(file->f_cred, plabel, op,
+					      MAY_READ | MAY_WRITE, peer_sk,
+					      NULL, addr, addrlen,
+					      is_sk_fs ? &path : NULL,
+					      label)));
+			if (!error && !__aa_subj_label_is_cached(plabel, label))
+				update_peer_ctx(peer_sk, pctx, label);
+		}
+	}
+	sock_put(peer_sk);
+
+out:
+
+	/* update peer cache to latest successful perm check */
+	if (error == 0)
+		update_sk_ctx(sock->sk, label, plabel);
+	aa_put_label(plabel);
+
+	return error;
+}
+
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
new file mode 100644
index 000000000..5b42140e1
--- /dev/null
+++ b/security/apparmor/apparmorfs.c
@@ -0,0 +1,2981 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /sys/kernel/security/apparmor interface functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/ctype.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/capability.h>
+#include <linux/rcupdate.h>
+#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/poll.h>
+#include <linux/zstd.h>
+#include <linux/string.h>
+#include <uapi/linux/major.h>
+#include <uapi/linux/magic.h>
+
+#include "include/apparmor.h"
+#include "include/apparmorfs.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/crypto.h"
+#include "include/ipc.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/lib.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+#include "include/resource.h"
+#include "include/policy_unpack.h"
+#include "include/task.h"
+
+/*
+ * The apparmor filesystem interface used for policy load and introspection
+ * The interface is split into two main components based on their function
+ * a securityfs component:
+ *   used for static files that are always available, and which allows
+ *   userspace to specify the location of the security filesystem.
+ *
+ *   fns and data are prefixed with
+ *      aa_sfs_
+ *
+ * an apparmorfs component:
+ *   used loaded policy content and introspection. It is not part of  a
+ *   regular mounted filesystem and is available only through the magic
+ *   policy symlink in the root of the securityfs apparmor/ directory.
+ *   Tasks queries will be magically redirected to the correct portion
+ *   of the policy tree based on their confinement.
+ *
+ *   fns and data are prefixed with
+ *      aafs_
+ *
+ * The aa_fs_ prefix is used to indicate the fn is used by both the
+ * securityfs and apparmorfs filesystems.
+ */
+
+#define IREF_POISON 101
+
+/*
+ * support fns
+ */
+
+struct rawdata_f_data {
+	struct aa_loaddata *loaddata;
+	DECLARE_FLEX_ARRAY(char, data);
+};
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+
+static void rawdata_f_data_free(struct rawdata_f_data *private)
+{
+	if (!private)
+		return;
+
+	aa_put_i_loaddata(private->loaddata);
+	kvfree(private);
+}
+
+static struct rawdata_f_data *rawdata_f_data_alloc(size_t size)
+{
+	struct rawdata_f_data *ret;
+
+	if (size > SIZE_MAX - sizeof(*ret))
+		return ERR_PTR(-EINVAL);
+
+	ret = kvzalloc(sizeof(*ret) + size, GFP_KERNEL);
+	if (!ret)
+		return ERR_PTR(-ENOMEM);
+
+	return ret;
+}
+#endif
+
+/**
+ * mangle_name - mangle a profile name to std profile layout form
+ * @name: profile name to mangle  (NOT NULL)
+ * @target: buffer to store mangled name, same length as @name (MAYBE NULL)
+ *
+ * Returns: length of mangled name
+ */
+static int mangle_name(const char *name, char *target)
+{
+	char *t = target;
+
+	while (*name == '/' || *name == '.')
+		name++;
+
+	if (target) {
+		for (; *name; name++) {
+			if (*name == '/')
+				*(t)++ = '.';
+			else if (isspace(*name))
+				*(t)++ = '_';
+			else if (isalnum(*name) || strchr("._-", *name))
+				*(t)++ = *name;
+		}
+
+		*t = 0;
+	} else {
+		int len = 0;
+		for (; *name; name++) {
+			if (isalnum(*name) || isspace(*name) ||
+			    strchr("/._-", *name))
+				len++;
+		}
+
+		return len;
+	}
+
+	return t - target;
+}
+
+
+/*
+ * aafs - core fns and data for the policy tree
+ */
+
+#define AAFS_NAME		"apparmorfs"
+static struct vfsmount *aafs_mnt;
+static int aafs_count;
+
+
+static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
+{
+	seq_printf(seq, "%s:[%llu]", AAFS_NAME, d_inode(dentry)->i_ino);
+	return 0;
+}
+
+static struct aa_ns *get_ns_common_ref(struct aa_common_ref *ref)
+{
+	if (ref) {
+		struct aa_label *reflabel = container_of(ref, struct aa_label,
+							 count);
+		return aa_get_ns(labels_ns(reflabel));
+	}
+
+	return NULL;
+}
+
+static struct aa_proxy *get_proxy_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_proxy(container_of(ref, struct aa_proxy, count));
+
+	return NULL;
+}
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+static struct aa_loaddata *get_loaddata_common_ref(struct aa_common_ref *ref)
+{
+	if (ref)
+		return aa_get_i_loaddata(container_of(ref, struct aa_loaddata,
+						      count));
+	return NULL;
+}
+#endif
+
+static void aa_put_common_ref(struct aa_common_ref *ref)
+{
+	if (!ref)
+		return;
+
+	switch (ref->reftype) {
+	case REF_RAWDATA:
+		aa_put_i_loaddata(container_of(ref, struct aa_loaddata,
+					       count));
+		break;
+	case REF_PROXY:
+		aa_put_proxy(container_of(ref, struct aa_proxy,
+					  count));
+		break;
+	case REF_NS:
+		/* ns count is held on its unconfined label */
+		aa_put_ns(labels_ns(container_of(ref, struct aa_label, count)));
+		break;
+	default:
+		AA_BUG(true, "unknown refcount type");
+		break;
+	}
+}
+
+static void aa_get_common_ref(struct aa_common_ref *ref)
+{
+	kref_get(&ref->count);
+}
+
+static void aafs_evict(struct inode *inode)
+{
+	struct aa_common_ref *ref = inode->i_private;
+
+	clear_inode(inode);
+	aa_put_common_ref(ref);
+	inode->i_private = (void *) IREF_POISON;
+}
+
+static void aafs_free_inode(struct inode *inode)
+{
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static const struct super_operations aafs_super_ops = {
+	.statfs = simple_statfs,
+	.evict_inode = aafs_evict,
+	.free_inode = aafs_free_inode,
+	.show_path = aafs_show_path,
+};
+
+static int apparmorfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	static struct tree_descr files[] = { {""} };
+	int error;
+
+	error = simple_fill_super(sb, AAFS_MAGIC, files);
+	if (error)
+		return error;
+	sb->s_op = &aafs_super_ops;
+
+	return 0;
+}
+
+static int apparmorfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, apparmorfs_fill_super);
+}
+
+static const struct fs_context_operations apparmorfs_context_ops = {
+	.get_tree	= apparmorfs_get_tree,
+};
+
+static int apparmorfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &apparmorfs_context_ops;
+	return 0;
+}
+
+static struct file_system_type aafs_ops = {
+	.owner = THIS_MODULE,
+	.name = AAFS_NAME,
+	.init_fs_context = apparmorfs_init_fs_context,
+	.kill_sb = kill_anon_super,
+};
+
+/**
+ * __aafs_setup_d_inode - basic inode setup for apparmorfs
+ * @dir: parent directory for the dentry
+ * @dentry: dentry we are setting the inode up for
+ * @mode: permissions the file should have
+ * @data: data to store on inode.i_private, available in open()
+ * @link: if symlink, symlink target string
+ * @fops: struct file_operations that should be used
+ * @iops: struct of inode_operations that should be used
+ */
+static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry,
+			       umode_t mode, void *data, char *link,
+			       const struct file_operations *fops,
+			       const struct inode_operations *iops)
+{
+	struct inode *inode = new_inode(dir->i_sb);
+
+	AA_BUG(!dir);
+	AA_BUG(!dentry);
+
+	if (!inode)
+		return -ENOMEM;
+
+	inode->i_ino = get_next_ino();
+	inode->i_mode = mode;
+	simple_inode_init_ts(inode);
+	inode->i_private = data;
+	if (S_ISDIR(mode)) {
+		inode->i_op = iops ? iops : &simple_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		inc_nlink(inode);
+		inc_nlink(dir);
+	} else if (S_ISLNK(mode)) {
+		inode->i_op = iops ? iops : &simple_symlink_inode_operations;
+		inode->i_link = link;
+	} else {
+		inode->i_fop = fops;
+	}
+	d_instantiate(dentry, inode);
+	dget(dentry);
+
+	return 0;
+}
+
+/**
+ * aafs_create - create a dentry in the apparmorfs filesystem
+ *
+ * @name: name of dentry to create
+ * @mode: permissions the file should have
+ * @parent: parent directory for this dentry
+ * @data: data to store on inode.i_private, available in open()
+ * @link: if symlink, symlink target string
+ * @fops: struct file_operations that should be used for
+ * @iops: struct of inode_operations that should be used
+ *
+ * This is the basic "create a xxx" function for apparmorfs.
+ *
+ * Returns a pointer to a dentry if it succeeds, that must be free with
+ * aafs_remove(). Will return ERR_PTR on failure.
+ */
+static struct dentry *aafs_create(const char *name, umode_t mode,
+				  struct dentry *parent,
+				  struct aa_common_ref *data, void *link,
+				  const struct file_operations *fops,
+				  const struct inode_operations *iops)
+{
+	struct dentry *dentry;
+	struct inode *dir;
+	int error;
+
+	AA_BUG(!name);
+	AA_BUG(!parent);
+
+	if (!(mode & S_IFMT))
+		mode = (mode & S_IALLUGO) | S_IFREG;
+
+	error = simple_pin_fs(&aafs_ops, &aafs_mnt, &aafs_count);
+	if (error)
+		return ERR_PTR(error);
+
+	dir = d_inode(parent);
+
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry)) {
+		error = PTR_ERR(dentry);
+		goto fail;
+	}
+
+	error = __aafs_setup_d_inode(dir, dentry, mode, data, link, fops, iops);
+	simple_done_creating(dentry);
+	if (error)
+		goto fail;
+
+	if (data)
+		aa_get_common_ref(data);
+
+	return dentry;
+
+fail:
+	simple_release_fs(&aafs_mnt, &aafs_count);
+	return ERR_PTR(error);
+}
+
+/**
+ * aafs_create_file - create a file in the apparmorfs filesystem
+ *
+ * @name: name of dentry to create
+ * @mode: permissions the file should have
+ * @parent: parent directory for this dentry
+ * @data: data to store on inode.i_private, available in open()
+ * @fops: struct file_operations that should be used for
+ *
+ * see aafs_create
+ */
+static struct dentry *aafs_create_file(const char *name, umode_t mode,
+				       struct dentry *parent,
+				       struct aa_common_ref *data,
+				       const struct file_operations *fops)
+{
+	return aafs_create(name, mode, parent, data, NULL, fops, NULL);
+}
+
+/**
+ * aafs_create_dir - create a directory in the apparmorfs filesystem
+ *
+ * @name: name of dentry to create
+ * @parent: parent directory for this dentry
+ *
+ * see aafs_create
+ */
+static struct dentry *aafs_create_dir(const char *name, struct dentry *parent)
+{
+	return aafs_create(name, S_IFDIR | 0755, parent, NULL, NULL, NULL,
+			   NULL);
+}
+
+/**
+ * aafs_remove - removes a file or directory from the apparmorfs filesystem
+ *
+ * @dentry: dentry of the file/directory/symlink to removed.
+ */
+static void aafs_remove(struct dentry *dentry)
+{
+	struct inode *dir;
+
+	if (!dentry || IS_ERR(dentry))
+		return;
+
+	/* ->d_parent is stable as rename is not supported */
+	dir = d_inode(dentry->d_parent);
+	dentry = start_removing_dentry(dentry->d_parent, dentry);
+	if (!IS_ERR(dentry) && simple_positive(dentry)) {
+		if (d_is_dir(dentry)) {
+			if (!WARN_ON(!simple_empty(dentry))) {
+				__simple_rmdir(dir, dentry);
+				dput(dentry);
+			}
+		} else {
+			__simple_unlink(dir, dentry);
+			dput(dentry);
+		}
+		d_delete(dentry);
+	}
+	end_removing(dentry);
+	simple_release_fs(&aafs_mnt, &aafs_count);
+}
+
+
+/*
+ * aa_fs - policy load/replace/remove
+ */
+
+/**
+ * aa_simple_write_to_buffer - common routine for getting policy from user
+ * @userbuf: user buffer to copy data from  (NOT NULL)
+ * @alloc_size: size of user buffer (REQUIRES: @alloc_size >= @copy_size)
+ * @copy_size: size of data to copy from user buffer
+ * @pos: position write is at in the file (NOT NULL)
+ *
+ * Returns: kernel buffer containing copy of user buffer data or an
+ *          ERR_PTR on failure.
+ */
+static struct aa_loaddata *aa_simple_write_to_buffer(const char __user *userbuf,
+						     size_t alloc_size,
+						     size_t copy_size,
+						     loff_t *pos)
+{
+	struct aa_loaddata *data;
+
+	AA_BUG(copy_size > alloc_size);
+
+	if (*pos != 0)
+		/* only writes from pos 0, that is complete writes */
+		return ERR_PTR(-ESPIPE);
+
+	/* freed by caller to simple_write_to_buffer */
+	data = aa_loaddata_alloc(alloc_size);
+	if (IS_ERR(data))
+		return data;
+
+	data->size = copy_size;
+	if (copy_from_user(data->data, userbuf, copy_size)) {
+		/* trigger free - don't need to put pcount */
+		aa_put_i_loaddata(data);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return data;
+}
+
+#if defined(CONFIG_SECURITY_APPARMOR_COMPRESSED_POLICY) || \
+    defined(CONFIG_SECURITY_APPARMOR_EXPORT_BINARY)
+static int decompress_zstd(char *src, size_t slen, char *dst, size_t dlen)
+{
+	if (slen < dlen) {
+		const size_t wksp_len = zstd_dctx_workspace_bound();
+		zstd_dctx *ctx;
+		void *wksp;
+		size_t out_len;
+		int ret = 0;
+
+		wksp = kvzalloc(wksp_len, GFP_KERNEL);
+		if (!wksp) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+		ctx = zstd_init_dctx(wksp, wksp_len);
+		if (ctx == NULL) {
+			ret = -ENOMEM;
+			goto cleanup;
+		}
+		out_len = zstd_decompress_dctx(ctx, dst, dlen, src, slen);
+		if (zstd_is_error(out_len)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+cleanup:
+		kvfree(wksp);
+		return ret;
+	}
+
+	if (dlen < slen)
+		return -EINVAL;
+	memcpy(dst, src, slen);
+	return 0;
+}
+#endif
+
+
+#ifdef CONFIG_SECURITY_APPARMOR_COMPRESSED_POLICY
+/**
+ * aa_get_data_from_compressed - common routine for getting compressed policy
+ * from user and get both compressed and uncompressed version.
+ * @userbuf: user buffer to copy data from  (NOT NULL)
+ * @buffer_size: size of user buffer
+ * @pos: position write is at in the file (NOT NULL)
+ * @compressed_data: Ptr on compressed data. *compressed_data is allocated there
+ *
+ * Returns: kernel buffer containing copy of user buffer data or an
+ *          ERR_PTR on failure.
+ */
+static struct aa_loaddata *aa_get_data_from_compressed(const char __user *userbuf,
+						  size_t buffer_size,
+						  loff_t *pos,
+						  char **compressed_data)
+{
+	struct aa_loaddata *data;
+	zstd_frame_header header;
+	int error;
+
+	if (!userbuf || !pos)
+		return ERR_PTR(-EINVAL);
+	if (*pos)
+		return ERR_PTR(-ESPIPE);
+
+	*compressed_data = kvmalloc(buffer_size, GFP_KERNEL);
+	if (!*compressed_data)
+		return ERR_PTR(-ENOMEM);
+	if (copy_from_user(*compressed_data, userbuf, buffer_size)) {
+		error = -EFAULT;
+		goto fail;
+	}
+	error = zstd_get_frame_header(&header, *compressed_data, buffer_size);
+	if (error || header.frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN ||
+	    header.frameContentSize == ZSTD_CONTENTSIZE_ERROR) {
+		error = -EINVAL;
+		goto fail;
+	}
+
+	data = aa_loaddata_alloc(header.frameContentSize);
+	if (IS_ERR(data)) {
+		error = PTR_ERR(data);
+		goto fail;
+	}
+
+	// We then decompress the data
+	error = decompress_zstd(*compressed_data, buffer_size, data->data,
+				header.frameContentSize);
+	if (error)
+		goto fail_decompress;
+
+	data->size = header.frameContentSize;
+	return data;
+
+fail_decompress:
+	aa_put_i_loaddata(data);
+fail:
+	kvfree(*compressed_data);
+	return ERR_PTR(error);
+
+}
+#else
+static struct aa_loaddata *aa_get_data_from_compressed(const char __user *userbuf __always_unused,
+						  size_t buffer_size __always_unused,
+						  loff_t *pos __always_unused,
+						  char **compressed_data __always_unused)
+{
+	return ERR_PTR(-EINVAL);
+}
+#endif /* CONFIG_SECURITY_APPARMOR_COMPRESSED_POLICY */
+
+struct aa_user_hdr {
+	uint8_t version;
+	uint8_t compress_level;
+	uint8_t padding[6];	/* force 8-byte alignment */
+} __packed __aligned(8);
+
+#define aa_hdr_magic "\x04\x08\x00\x76\x65\x72\x73\x69\x6f\x6e\x00\x02"
+#define aa_hdr_magic_size 12
+
+static ssize_t policy_update(u32 mask, const char __user *buf, size_t size,
+			     loff_t *pos, struct aa_ns *ns,
+			     const struct cred *ocred)
+{
+	struct aa_loaddata *data;
+	struct aa_label *label;
+	ssize_t error;
+	char *compressed_data = NULL;
+	__le32 magic_le;
+	bool is_compressed;
+	u8 aahdr[aa_hdr_magic_size];
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+
+	/* high level check about policy management - fine grained in
+	 * below after unpack
+	 */
+	error = aa_may_manage_policy(current_cred(), label, ns, ocred, mask);
+	if (error)
+		goto end_section;
+
+	/* If the policy is userspace compressed we start by decompressing it
+	 * to make the required checks (computing hash, verifying profile, ...)
+	 *
+	 * Getting a userspace-compressed version then decompressing it in the
+	 * kernel actually makes sense since zstd decompression is ~3.5x faster
+	 * than compression. This also allow to increase the compression level.
+	 */
+
+	if (size >= sizeof(__le32) &&
+	    !copy_from_user(&magic_le, buf, sizeof(magic_le)) &&
+	    le32_to_cpu(magic_le) == ZSTD_MAGICNUMBER) {
+		is_compressed = true;
+	} else if (size >= sizeof(struct aa_user_hdr) + sizeof(__le32) &&
+		   !copy_from_user(&magic_le,
+				   buf + sizeof(struct aa_user_hdr),
+				   sizeof(magic_le)) &&
+		   le32_to_cpu(magic_le) == ZSTD_MAGICNUMBER) {
+		is_compressed = true;
+		/* skip the userspace header if present */
+		buf += sizeof(struct aa_user_hdr);
+		size -= sizeof(struct aa_user_hdr);
+	} else if (size >= sizeof(struct aa_user_hdr) +
+		   aa_hdr_magic_size &&
+		   !copy_from_user(&aahdr,
+				   buf + sizeof(struct aa_user_hdr),
+				   aa_hdr_magic_size) &&
+		   memcmp(&aahdr, aa_hdr_magic, aa_hdr_magic_size) == 0) {
+		/* uncompressed blob with user hdr */
+		buf += sizeof(struct aa_user_hdr);
+		size -= sizeof(struct aa_user_hdr);
+		is_compressed = false;
+	} else {
+		is_compressed = false;
+	}
+	if (is_compressed) {
+
+		data = aa_get_data_from_compressed(buf, size, pos, &compressed_data);
+		error = PTR_ERR(data);
+	} else {
+		data = aa_simple_write_to_buffer(buf, size, size, pos);
+		error = PTR_ERR(data);
+	}
+
+	if (!IS_ERR(data)) {
+		error = aa_replace_profiles(ns, label, mask, data,
+					    compressed_data, size);
+		/* put pcount, which will put count and free if no
+		 * profiles referencing it.
+		 */
+		aa_put_profile_loaddata(data);
+	}
+end_section:
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+/* .load file hook fn to load policy */
+static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
+			    loff_t *pos)
+{
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
+	int error = policy_update(AA_MAY_LOAD_POLICY, buf, size, pos, ns,
+				  f->f_cred);
+
+	aa_put_ns(ns);
+
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_load = {
+	.write = profile_load,
+	.llseek = default_llseek,
+};
+
+/* .replace file hook fn to load and/or replace policy */
+static ssize_t profile_replace(struct file *f, const char __user *buf,
+			       size_t size, loff_t *pos)
+{
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
+	int error = policy_update(AA_MAY_LOAD_POLICY | AA_MAY_REPLACE_POLICY,
+				  buf, size, pos, ns, f->f_cred);
+	aa_put_ns(ns);
+
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_replace = {
+	.write = profile_replace,
+	.llseek = default_llseek,
+};
+
+
+/* .remove file hook fn to remove loaded policy */
+static ssize_t profile_remove(struct file *f, const char __user *buf,
+			      size_t size, loff_t *pos)
+{
+	struct aa_loaddata *data;
+	struct aa_label *label;
+	ssize_t error;
+	struct aa_ns *ns = get_ns_common_ref(f->f_inode->i_private);
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+	/* high level check about policy management - fine grained in
+	 * below after unpack
+	 */
+	error = aa_may_manage_policy(current_cred(), label, ns,
+				     f->f_cred, AA_MAY_REMOVE_POLICY);
+	if (error)
+		goto out;
+
+	/*
+	 * aa_remove_profile needs a null terminated string so 1 extra
+	 * byte is allocated and the copied data is null terminated.
+	 */
+	data = aa_simple_write_to_buffer(buf, size + 1, size, pos);
+
+	error = PTR_ERR(data);
+	if (!IS_ERR(data)) {
+		data->data[size] = 0;
+		error = aa_remove_profiles(ns, label, data->data, size);
+		aa_put_profile_loaddata(data);
+	}
+ out:
+	end_current_label_crit_section(label, needput);
+	aa_put_ns(ns);
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_remove = {
+	.write = profile_remove,
+	.llseek = default_llseek,
+};
+
+struct aa_revision {
+	struct aa_ns *ns;
+	long last_read;
+};
+
+/* revision file hook fn for policy loads */
+static int ns_revision_release(struct inode *inode, struct file *file)
+{
+	struct aa_revision *rev = file->private_data;
+
+	if (rev) {
+		aa_put_ns(rev->ns);
+		kfree(rev);
+	}
+
+	return 0;
+}
+
+static ssize_t ns_revision_read(struct file *file, char __user *buf,
+				size_t size, loff_t *ppos)
+{
+	struct aa_revision *rev = file->private_data;
+	char buffer[32];
+	long last_read;
+	int avail;
+
+	mutex_lock_nested(&rev->ns->lock, rev->ns->level);
+	last_read = rev->last_read;
+	if (last_read == rev->ns->revision) {
+		mutex_unlock(&rev->ns->lock);
+		if (file->f_flags & O_NONBLOCK)
+			return -EAGAIN;
+		if (wait_event_interruptible(rev->ns->wait,
+					     last_read !=
+					     READ_ONCE(rev->ns->revision)))
+			return -ERESTARTSYS;
+		mutex_lock_nested(&rev->ns->lock, rev->ns->level);
+	}
+
+	avail = sprintf(buffer, "%ld\n", rev->ns->revision);
+	if (*ppos + size > avail) {
+		rev->last_read = rev->ns->revision;
+		*ppos = 0;
+	}
+	mutex_unlock(&rev->ns->lock);
+
+	return simple_read_from_buffer(buf, size, ppos, buffer, avail);
+}
+
+static int ns_revision_open(struct inode *inode, struct file *file)
+{
+	struct aa_revision *rev = kzalloc_obj(*rev);
+
+	if (!rev)
+		return -ENOMEM;
+
+	rev->ns = get_ns_common_ref(inode->i_private);
+	if (!rev->ns)
+		rev->ns = aa_get_current_ns();
+	file->private_data = rev;
+
+	return 0;
+}
+
+static __poll_t ns_revision_poll(struct file *file, poll_table *pt)
+{
+	struct aa_revision *rev = file->private_data;
+	__poll_t mask = 0;
+
+	if (rev) {
+		mutex_lock_nested(&rev->ns->lock, rev->ns->level);
+		poll_wait(file, &rev->ns->wait, pt);
+		if (rev->last_read < rev->ns->revision)
+			mask |= EPOLLIN | EPOLLRDNORM;
+		mutex_unlock(&rev->ns->lock);
+	}
+
+	return mask;
+}
+
+void __aa_bump_ns_revision(struct aa_ns *ns)
+{
+	WRITE_ONCE(ns->revision, READ_ONCE(ns->revision) + 1);
+	wake_up_interruptible(&ns->wait);
+}
+
+static const struct file_operations aa_fs_ns_revision_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ns_revision_open,
+	.poll		= ns_revision_poll,
+	.read		= ns_revision_read,
+	.llseek		= generic_file_llseek,
+	.release	= ns_revision_release,
+};
+
+static void profile_query_cb(const struct aa_profile *profile,
+			     struct aa_perms *perms,
+			     const char *match_str, size_t match_len)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms tmp = { };
+	aa_state_t state = DFA_NOMATCH;
+
+	if (profile_unconfined(profile))
+		return;
+	if (rules->file->dfa && *match_str == AA_CLASS_FILE) {
+		state = aa_dfa_match_len(rules->file->dfa,
+					 rules->file->start[AA_CLASS_FILE],
+					 match_str + 1, match_len - 1);
+		if (state) {
+			struct path_cond cond = { };
+
+			tmp = *(aa_lookup_condperms(current_fsuid(),
+						    rules->file, state, &cond));
+		}
+	} else if (rules->policy->dfa) {
+		if (!RULE_MEDIATES(rules, *match_str))
+			return;	/* no change to current perms */
+		/* old user space does not correctly detect dbus mediation
+		 * support so we may get dbus policy and requests when
+		 * the abi doesn't support it. This can cause mediation
+		 * regressions, so explicitly test for this situation.
+		 */
+		if (*match_str == AA_CLASS_DBUS &&
+		    !RULE_MEDIATES_v9NET(rules))
+			return; /* no change to current perms */
+		state = aa_dfa_match_len(rules->policy->dfa,
+					 rules->policy->start[0],
+					 match_str, match_len);
+		if (state)
+			tmp = *aa_lookup_perms(rules->policy, state);
+	}
+	aa_apply_modes_to_perms(profile, &tmp);
+	aa_perms_accum_raw(perms, &tmp);
+}
+
+
+/**
+ * query_data - queries a policy and writes its data to buf
+ * @buf: the resulting data is stored here (NOT NULL)
+ * @buf_len: size of buf
+ * @query: query string used to retrieve data
+ * @query_len: size of query including second NUL byte
+ *
+ * The buffers pointed to by buf and query may overlap. The query buffer is
+ * parsed before buf is written to.
+ *
+ * The query should look like "<LABEL>\0<KEY>\0", where <LABEL> is the name of
+ * the security confinement context and <KEY> is the name of the data to
+ * retrieve. <LABEL> and <KEY> must not be NUL-terminated.
+ *
+ * Don't expect the contents of buf to be preserved on failure.
+ *
+ * Returns: number of characters written to buf or -errno on failure
+ */
+static ssize_t query_data(char *buf, size_t buf_len,
+			  char *query, size_t query_len)
+{
+	char *out;
+	const char *key;
+	struct label_it i;
+	struct aa_label *label, *curr;
+	struct aa_profile *profile;
+	struct aa_data *data;
+	u32 bytes, blocks;
+	__le32 outle32;
+	bool needput;
+
+	if (!query_len)
+		return -EINVAL; /* need a query */
+
+	key = query + strnlen(query, query_len) + 1;
+	if (key + 1 >= query + query_len)
+		return -EINVAL; /* not enough space for a non-empty key */
+	if (key + strnlen(key, query + query_len - key) >= query + query_len)
+		return -EINVAL; /* must end with NUL */
+
+	if (buf_len < sizeof(bytes) + sizeof(blocks))
+		return -EINVAL; /* not enough space */
+
+	curr = begin_current_label_crit_section(&needput);
+	label = aa_label_parse(curr, query, GFP_KERNEL, false, false);
+	end_current_label_crit_section(curr, needput);
+	if (IS_ERR(label))
+		return PTR_ERR(label);
+
+	/* We are going to leave space for two numbers. The first is the total
+	 * number of bytes we are writing after the first number. This is so
+	 * users can read the full output without reallocation.
+	 *
+	 * The second number is the number of data blocks we're writing. An
+	 * application might be confined by multiple policies having data in
+	 * the same key.
+	 */
+	memset(buf, 0, sizeof(bytes) + sizeof(blocks));
+	out = buf + sizeof(bytes) + sizeof(blocks);
+
+	blocks = 0;
+	label_for_each_confined(i, label, profile) {
+		if (!profile->data)
+			continue;
+
+		data = rhashtable_lookup_fast(profile->data, &key,
+					      profile->data->p);
+
+		if (data) {
+			if (out + sizeof(outle32) + data->size > buf +
+			    buf_len) {
+				aa_put_label(label);
+				return -EINVAL; /* not enough space */
+			}
+			outle32 = __cpu_to_le32(data->size);
+			memcpy(out, &outle32, sizeof(outle32));
+			out += sizeof(outle32);
+			memcpy(out, data->data, data->size);
+			out += data->size;
+			blocks++;
+		}
+	}
+	aa_put_label(label);
+
+	outle32 = __cpu_to_le32(out - buf - sizeof(bytes));
+	memcpy(buf, &outle32, sizeof(outle32));
+	outle32 = __cpu_to_le32(blocks);
+	memcpy(buf + sizeof(bytes), &outle32, sizeof(outle32));
+
+	return out - buf;
+}
+
+/**
+ * query_label - queries a label and writes permissions to buf
+ * @buf: the resulting permissions string is stored here (NOT NULL)
+ * @buf_len: size of buf
+ * @query: binary query string to match against the dfa
+ * @query_len: size of query
+ * @view_only: only compute for querier's view
+ *
+ * The buffers pointed to by buf and query may overlap. The query buffer is
+ * parsed before buf is written to.
+ *
+ * The query should look like "LABEL_NAME\0DFA_STRING" where LABEL_NAME is
+ * the name of the label, in the current namespace, that is to be queried and
+ * DFA_STRING is a binary string to match against the label(s)'s DFA.
+ *
+ * LABEL_NAME must be NUL terminated. DFA_STRING may contain NUL characters
+ * but must *not* be NUL terminated.
+ *
+ * Returns: number of characters written to buf or -errno on failure
+ */
+static ssize_t query_label(char *buf, size_t buf_len,
+			   char *query, size_t query_len, bool view_only)
+{
+	struct aa_profile *profile;
+	struct aa_label *label, *curr;
+	char *label_name, *match_str;
+	size_t label_name_len, match_len;
+	struct aa_perms perms;
+	struct label_it i;
+	bool needput;
+
+	if (!query_len)
+		return -EINVAL;
+
+	label_name = query;
+	label_name_len = strnlen(query, query_len);
+	if (!label_name_len || label_name_len == query_len)
+		return -EINVAL;
+
+	/**
+	 * The extra byte is to account for the null byte between the
+	 * profile name and dfa string. profile_name_len is greater
+	 * than zero and less than query_len, so a byte can be safely
+	 * added or subtracted.
+	 */
+	match_str = label_name + label_name_len + 1;
+	match_len = query_len - label_name_len - 1;
+
+	curr = begin_current_label_crit_section(&needput);
+	label = aa_label_parse(curr, label_name, GFP_KERNEL, false, false);
+	end_current_label_crit_section(curr, needput);
+	if (IS_ERR(label))
+		return PTR_ERR(label);
+
+	perms = allperms;
+	if (view_only) {
+		label_for_each_in_scope(i, labels_ns(label), label, profile) {
+			profile_query_cb(profile, &perms, match_str, match_len);
+		}
+	} else {
+		label_for_each(i, label, profile) {
+			profile_query_cb(profile, &perms, match_str, match_len);
+		}
+	}
+	aa_put_label(label);
+
+	return scnprintf(buf, buf_len,
+		      "allow 0x%08x\ndeny 0x%08x\naudit 0x%08x\nquiet 0x%08x\n",
+		      perms.allow, perms.deny, perms.audit, perms.quiet);
+}
+
+/*
+ * Transaction based IO.
+ * The file expects a write which triggers the transaction, and then
+ * possibly a read(s) which collects the result - which is stored in a
+ * file-local buffer. Once a new write is performed, a new set of results
+ * are stored in the file-local buffer.
+ */
+struct multi_transaction {
+	struct kref count;
+	ssize_t size;
+	char data[];
+};
+
+#define MULTI_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct multi_transaction))
+
+static void multi_transaction_kref(struct kref *kref)
+{
+	struct multi_transaction *t;
+
+	t = container_of(kref, struct multi_transaction, count);
+	kfree(t);
+}
+
+static struct multi_transaction *
+get_multi_transaction(struct multi_transaction *t)
+{
+	if  (t)
+		kref_get(&(t->count));
+
+	return t;
+}
+
+static void put_multi_transaction(struct multi_transaction *t)
+{
+	if (t)
+		kref_put(&(t->count), multi_transaction_kref);
+}
+
+/* does not increment @new's count */
+static void multi_transaction_set(struct file *file,
+				  struct multi_transaction *new, size_t n)
+{
+	struct multi_transaction *old;
+
+	AA_BUG(n > MULTI_TRANSACTION_LIMIT);
+
+	new->size = n;
+	spin_lock(&file->f_lock);
+	old = (struct multi_transaction *) file->private_data;
+	file->private_data = new;
+	spin_unlock(&file->f_lock);
+	put_multi_transaction(old);
+}
+
+static struct multi_transaction *multi_transaction_new(struct file *file,
+						       const char __user *buf,
+						       size_t size)
+{
+	struct multi_transaction *t;
+
+	if (size > MULTI_TRANSACTION_LIMIT - 1)
+		return ERR_PTR(-EFBIG);
+
+	t = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!t)
+		return ERR_PTR(-ENOMEM);
+	kref_init(&t->count);
+	if (copy_from_user(t->data, buf, size)) {
+		put_multi_transaction(t);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return t;
+}
+
+static ssize_t multi_transaction_read(struct file *file, char __user *buf,
+				       size_t size, loff_t *pos)
+{
+	struct multi_transaction *t;
+	ssize_t ret;
+
+	spin_lock(&file->f_lock);
+	t = get_multi_transaction(file->private_data);
+	spin_unlock(&file->f_lock);
+
+	if (!t)
+		return 0;
+
+	ret = simple_read_from_buffer(buf, size, pos, t->data, t->size);
+	put_multi_transaction(t);
+
+	return ret;
+}
+
+static int multi_transaction_release(struct inode *inode, struct file *file)
+{
+	put_multi_transaction(file->private_data);
+
+	return 0;
+}
+
+#define QUERY_CMD_LABEL		"label\0"
+#define QUERY_CMD_LABEL_LEN	6
+#define QUERY_CMD_PROFILE	"profile\0"
+#define QUERY_CMD_PROFILE_LEN	8
+#define QUERY_CMD_LABELALL	"labelall\0"
+#define QUERY_CMD_LABELALL_LEN	9
+#define QUERY_CMD_DATA		"data\0"
+#define QUERY_CMD_DATA_LEN	5
+
+/**
+ * aa_write_access - generic permissions and data query
+ * @file: pointer to open apparmorfs/access file
+ * @ubuf: user buffer containing the complete query string (NOT NULL)
+ * @count: size of ubuf
+ * @ppos: position in the file (MUST BE ZERO)
+ *
+ * Allows for one permissions or data query per open(), write(), and read()
+ * sequence. The only queries currently supported are label-based queries for
+ * permissions or data.
+ *
+ * For permissions queries, ubuf must begin with "label\0", followed by the
+ * profile query specific format described in the query_label() function
+ * documentation.
+ *
+ * For data queries, ubuf must have the form "data\0<LABEL>\0<KEY>\0", where
+ * <LABEL> is the name of the security confinement context and <KEY> is the
+ * name of the data to retrieve.
+ *
+ * Returns: number of bytes written or -errno on failure
+ */
+static ssize_t aa_write_access(struct file *file, const char __user *ubuf,
+			       size_t count, loff_t *ppos)
+{
+	struct multi_transaction *t;
+	ssize_t len;
+
+	if (*ppos)
+		return -ESPIPE;
+
+	t = multi_transaction_new(file, ubuf, count);
+	if (IS_ERR(t))
+		return PTR_ERR(t);
+
+	if (count > QUERY_CMD_PROFILE_LEN &&
+	    !memcmp(t->data, QUERY_CMD_PROFILE, QUERY_CMD_PROFILE_LEN)) {
+		len = query_label(t->data, MULTI_TRANSACTION_LIMIT,
+				  t->data + QUERY_CMD_PROFILE_LEN,
+				  count - QUERY_CMD_PROFILE_LEN, true);
+	} else if (count > QUERY_CMD_LABEL_LEN &&
+		   !memcmp(t->data, QUERY_CMD_LABEL, QUERY_CMD_LABEL_LEN)) {
+		len = query_label(t->data, MULTI_TRANSACTION_LIMIT,
+				  t->data + QUERY_CMD_LABEL_LEN,
+				  count - QUERY_CMD_LABEL_LEN, true);
+	} else if (count > QUERY_CMD_LABELALL_LEN &&
+		   !memcmp(t->data, QUERY_CMD_LABELALL,
+			   QUERY_CMD_LABELALL_LEN)) {
+		len = query_label(t->data, MULTI_TRANSACTION_LIMIT,
+				  t->data + QUERY_CMD_LABELALL_LEN,
+				  count - QUERY_CMD_LABELALL_LEN, false);
+	} else if (count > QUERY_CMD_DATA_LEN &&
+		   !memcmp(t->data, QUERY_CMD_DATA, QUERY_CMD_DATA_LEN)) {
+		len = query_data(t->data, MULTI_TRANSACTION_LIMIT,
+				 t->data + QUERY_CMD_DATA_LEN,
+				 count - QUERY_CMD_DATA_LEN);
+	} else
+		len = -EINVAL;
+
+	if (len < 0) {
+		put_multi_transaction(t);
+		return len;
+	}
+
+	multi_transaction_set(file, t, len);
+
+	return count;
+}
+
+static const struct file_operations aa_sfs_access = {
+	.write		= aa_write_access,
+	.read		= multi_transaction_read,
+	.release	= multi_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+static int aa_sfs_seq_show(struct seq_file *seq, void *v)
+{
+	struct aa_sfs_entry *fs_file = seq->private;
+
+	if (!fs_file)
+		return 0;
+
+	switch (fs_file->v_type) {
+	case AA_SFS_TYPE_BOOLEAN:
+		seq_printf(seq, "%s\n", str_yes_no(fs_file->v.boolean));
+		break;
+	case AA_SFS_TYPE_STRING:
+		seq_printf(seq, "%s\n", fs_file->v.string);
+		break;
+	case AA_SFS_TYPE_U64:
+		seq_printf(seq, "%#08lx\n", fs_file->v.u64);
+		break;
+	default:
+		/* Ignore unprintable entry types. */
+		break;
+	}
+
+	return 0;
+}
+
+static int aa_sfs_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aa_sfs_seq_show, inode->i_private);
+}
+
+const struct file_operations aa_sfs_seq_file_ops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_sfs_seq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/*
+ * profile based file operations
+ *     policy/profiles/XXXX/profiles/ *
+ */
+
+#define SEQ_PROFILE_FOPS(NAME)						      \
+static int seq_profile_ ##NAME ##_open(struct inode *inode, struct file *file)\
+{									      \
+	return seq_profile_open(inode, file, seq_profile_ ##NAME ##_show);    \
+}									      \
+									      \
+static const struct file_operations seq_profile_ ##NAME ##_fops = {	      \
+	.owner		= THIS_MODULE,					      \
+	.open		= seq_profile_ ##NAME ##_open,			      \
+	.read		= seq_read,					      \
+	.llseek		= seq_lseek,					      \
+	.release	= seq_profile_release,				      \
+}									      \
+
+static int seq_profile_open(struct inode *inode, struct file *file,
+			    int (*show)(struct seq_file *, void *))
+{
+	struct aa_proxy *proxy = get_proxy_common_ref(inode->i_private);
+	int error = single_open(file, show, proxy);
+
+	if (error) {
+		file->private_data = NULL;
+		aa_put_proxy(proxy);
+	}
+
+	return error;
+}
+
+static int seq_profile_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = (struct seq_file *) file->private_data;
+	if (seq)
+		aa_put_proxy(seq->private);
+	return single_release(inode, file);
+}
+
+static int seq_profile_name_show(struct seq_file *seq, void *v)
+{
+	struct aa_proxy *proxy = seq->private;
+	struct aa_label *label = aa_get_label_rcu(&proxy->label);
+	struct aa_profile *profile = labels_profile(label);
+	seq_printf(seq, "%s\n", profile->base.name);
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int seq_profile_mode_show(struct seq_file *seq, void *v)
+{
+	struct aa_proxy *proxy = seq->private;
+	struct aa_label *label = aa_get_label_rcu(&proxy->label);
+	struct aa_profile *profile = labels_profile(label);
+	seq_printf(seq, "%s\n", aa_profile_mode_names[profile->mode]);
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int seq_profile_attach_show(struct seq_file *seq, void *v)
+{
+	struct aa_proxy *proxy = seq->private;
+	struct aa_label *label = aa_get_label_rcu(&proxy->label);
+	struct aa_profile *profile = labels_profile(label);
+	if (profile->attach.xmatch_str)
+		seq_printf(seq, "%s\n", profile->attach.xmatch_str);
+	else if (profile->attach.xmatch->dfa)
+		seq_puts(seq, "<unknown>\n");
+	else
+		seq_printf(seq, "%s\n", profile->base.name);
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int seq_profile_hash_show(struct seq_file *seq, void *v)
+{
+	struct aa_proxy *proxy = seq->private;
+	struct aa_label *label = aa_get_label_rcu(&proxy->label);
+	struct aa_profile *profile = labels_profile(label);
+	unsigned int i, size = aa_hash_size();
+
+	if (profile->hash) {
+		for (i = 0; i < size; i++)
+			seq_printf(seq, "%.2x", profile->hash[i]);
+		seq_putc(seq, '\n');
+	}
+	aa_put_label(label);
+
+	return 0;
+}
+
+SEQ_PROFILE_FOPS(name);
+SEQ_PROFILE_FOPS(mode);
+SEQ_PROFILE_FOPS(attach);
+SEQ_PROFILE_FOPS(hash);
+
+/*
+ * namespace based files
+ *     several root files and
+ *     policy/ *
+ */
+
+#define SEQ_NS_FOPS(NAME)						      \
+static int seq_ns_ ##NAME ##_open(struct inode *inode, struct file *file)     \
+{									      \
+	return single_open(file, seq_ns_ ##NAME ##_show, inode->i_private);   \
+}									      \
+									      \
+static const struct file_operations seq_ns_ ##NAME ##_fops = {	      \
+	.owner		= THIS_MODULE,					      \
+	.open		= seq_ns_ ##NAME ##_open,			      \
+	.read		= seq_read,					      \
+	.llseek		= seq_lseek,					      \
+	.release	= single_release,				      \
+}									      \
+
+static int seq_ns_stacked_show(struct seq_file *seq, void *v)
+{
+	struct aa_label *label;
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+	seq_printf(seq, "%s\n", str_yes_no(label->size > 1));
+	end_current_label_crit_section(label, needput);
+
+	return 0;
+}
+
+static int seq_ns_nsstacked_show(struct seq_file *seq, void *v)
+{
+	struct aa_label *label;
+	struct aa_profile *profile;
+	struct label_it it;
+	int count = 1;
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+
+	if (label->size > 1) {
+		label_for_each(it, label, profile)
+			if (profile->ns != labels_ns(label)) {
+				count++;
+				break;
+			}
+	}
+
+	seq_printf(seq, "%s\n", str_yes_no(count > 1));
+	end_current_label_crit_section(label, needput);
+
+	return 0;
+}
+
+static int seq_ns_level_show(struct seq_file *seq, void *v)
+{
+	struct aa_label *label;
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+	seq_printf(seq, "%d\n", labels_ns(label)->level);
+	end_current_label_crit_section(label, needput);
+
+	return 0;
+}
+
+static int seq_ns_name_show(struct seq_file *seq, void *v)
+{
+	bool needput;
+	struct aa_label *label = begin_current_label_crit_section(&needput);
+
+	seq_printf(seq, "%s\n", labels_ns(label)->base.name);
+	end_current_label_crit_section(label, needput);
+
+	return 0;
+}
+
+SEQ_NS_FOPS(stacked);
+SEQ_NS_FOPS(nsstacked);
+SEQ_NS_FOPS(level);
+SEQ_NS_FOPS(name);
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+static int seq_ns_compress_min_show(struct seq_file *seq, void *v)
+{
+	seq_printf(seq, "%d\n", AA_MIN_CLEVEL);
+	return 0;
+}
+
+static int seq_ns_compress_max_show(struct seq_file *seq, void *v)
+{
+	seq_printf(seq, "%d\n", AA_MAX_CLEVEL);
+	return 0;
+}
+
+SEQ_NS_FOPS(compress_min);
+SEQ_NS_FOPS(compress_max);
+
+
+/* policy/raw_data/ * file ops */
+#define SEQ_RAWDATA_FOPS(NAME)						      \
+static int seq_rawdata_ ##NAME ##_open(struct inode *inode, struct file *file)\
+{									      \
+	return seq_rawdata_open(inode, file, seq_rawdata_ ##NAME ##_show);    \
+}									      \
+									      \
+static const struct file_operations seq_rawdata_ ##NAME ##_fops = {	      \
+	.owner		= THIS_MODULE,					      \
+	.open		= seq_rawdata_ ##NAME ##_open,			      \
+	.read		= seq_read,					      \
+	.llseek		= seq_lseek,					      \
+	.release	= seq_rawdata_release,				      \
+}									      \
+
+static int seq_rawdata_open(struct inode *inode, struct file *file,
+			    int (*show)(struct seq_file *, void *))
+{
+	struct aa_loaddata *data = get_loaddata_common_ref(inode->i_private);
+	int error;
+
+	if (!data)
+		return -ENOENT;
+
+	error = single_open(file, show, data);
+	if (error) {
+		AA_BUG(file->private_data &&
+		       ((struct seq_file *)file->private_data)->private);
+		aa_put_i_loaddata(data);
+	}
+
+	return error;
+}
+
+static int seq_rawdata_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = (struct seq_file *) file->private_data;
+
+	if (seq)
+		aa_put_i_loaddata(seq->private);
+
+	return single_release(inode, file);
+}
+
+static int seq_rawdata_abi_show(struct seq_file *seq, void *v)
+{
+	struct aa_loaddata *data = seq->private;
+
+	seq_printf(seq, "v%d\n", data->abi);
+
+	return 0;
+}
+
+static int seq_rawdata_revision_show(struct seq_file *seq, void *v)
+{
+	struct aa_loaddata *data = seq->private;
+
+	seq_printf(seq, "%ld\n", data->revision);
+
+	return 0;
+}
+
+static int seq_rawdata_hash_show(struct seq_file *seq, void *v)
+{
+	struct aa_loaddata *data = seq->private;
+	unsigned int i, size = aa_hash_size();
+
+	if (data->hash) {
+		for (i = 0; i < size; i++)
+			seq_printf(seq, "%.2x", data->hash[i]);
+		seq_putc(seq, '\n');
+	}
+
+	return 0;
+}
+
+static int seq_rawdata_compressed_size_show(struct seq_file *seq, void *v)
+{
+	struct aa_loaddata *data = seq->private;
+
+	seq_printf(seq, "%zu\n", data->compressed_size);
+
+	return 0;
+}
+
+SEQ_RAWDATA_FOPS(abi);
+SEQ_RAWDATA_FOPS(revision);
+SEQ_RAWDATA_FOPS(hash);
+SEQ_RAWDATA_FOPS(compressed_size);
+
+static ssize_t rawdata_read(struct file *file, char __user *buf, size_t size,
+			    loff_t *ppos)
+{
+	struct rawdata_f_data *private = file->private_data;
+
+	return simple_read_from_buffer(buf, size, ppos,
+				       private->data,
+				       private->loaddata->size);
+}
+
+static int rawdata_release(struct inode *inode, struct file *file)
+{
+	rawdata_f_data_free(file->private_data);
+
+	return 0;
+}
+
+static int rawdata_open(struct inode *inode, struct file *file)
+{
+	int error;
+	struct aa_loaddata *loaddata;
+	struct rawdata_f_data *private;
+
+	if (!aa_current_policy_view_capable(NULL))
+		return -EACCES;
+
+	loaddata = get_loaddata_common_ref(inode->i_private);
+	if (!loaddata)
+		return -ENOENT;
+
+	private = rawdata_f_data_alloc(loaddata->size);
+	if (IS_ERR(private)) {
+		error = PTR_ERR(private);
+		goto fail_private_alloc;
+	}
+
+	private->loaddata = loaddata;
+
+	error = decompress_zstd(loaddata->data, loaddata->compressed_size,
+				private->data, loaddata->size);
+	if (error)
+		goto fail_decompress;
+
+	file->private_data = private;
+	return 0;
+
+fail_decompress:
+	rawdata_f_data_free(private);
+	return error;
+
+fail_private_alloc:
+	aa_put_i_loaddata(loaddata);
+	return error;
+}
+
+static const struct file_operations rawdata_fops = {
+	.open = rawdata_open,
+	.read = rawdata_read,
+	.llseek = generic_file_llseek,
+	.release = rawdata_release,
+};
+
+static void remove_rawdata_dents(struct aa_loaddata *rawdata)
+{
+	int i;
+
+	for (i = 0; i < AAFS_LOADDATA_NDENTS; i++) {
+		if (!IS_ERR_OR_NULL(rawdata->dents[i])) {
+			aafs_remove(rawdata->dents[i]);
+			rawdata->dents[i] = NULL;
+		}
+	}
+}
+
+void __aa_fs_remove_rawdata(struct aa_loaddata *rawdata)
+{
+	AA_BUG(rawdata->ns && !mutex_is_locked(&rawdata->ns->lock));
+
+	if (rawdata->ns) {
+		remove_rawdata_dents(rawdata);
+		list_del_init(&rawdata->list);
+		aa_put_ns(rawdata->ns);
+		rawdata->ns = NULL;
+	}
+}
+
+int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata)
+{
+	struct dentry *dent, *dir;
+
+	AA_BUG(!ns);
+	AA_BUG(!rawdata);
+	AA_BUG(!mutex_is_locked(&ns->lock));
+	AA_BUG(!ns_subdata_dir(ns));
+
+	/*
+	 * just use ns revision dir was originally created at. This is
+	 * under ns->lock and if load is successful revision will be
+	 * bumped and is guaranteed to be unique
+	 */
+	rawdata->name = kasprintf(GFP_KERNEL, "%ld", ns->revision);
+	if (!rawdata->name)
+		return -ENOMEM;
+
+	dir = aafs_create_dir(rawdata->name, ns_subdata_dir(ns));
+	if (IS_ERR(dir))
+		/* ->name freed when rawdata freed */
+		return PTR_ERR(dir);
+	rawdata->dents[AAFS_LOADDATA_DIR] = dir;
+
+	dent = aafs_create_file("abi", S_IFREG | 0444, dir, &rawdata->count,
+				      &seq_rawdata_abi_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	rawdata->dents[AAFS_LOADDATA_ABI] = dent;
+
+	dent = aafs_create_file("revision", S_IFREG | 0444, dir,
+				&rawdata->count,
+				&seq_rawdata_revision_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	rawdata->dents[AAFS_LOADDATA_REVISION] = dent;
+
+	if (aa_g_hash_policy) {
+		dent = aafs_create_file("sha256", S_IFREG | 0444, dir,
+					&rawdata->count,
+					&seq_rawdata_hash_fops);
+		if (IS_ERR(dent))
+			goto fail;
+		rawdata->dents[AAFS_LOADDATA_HASH] = dent;
+	}
+
+	dent = aafs_create_file("compressed_size", S_IFREG | 0444, dir,
+				&rawdata->count,
+				&seq_rawdata_compressed_size_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	rawdata->dents[AAFS_LOADDATA_COMPRESSED_SIZE] = dent;
+
+	dent = aafs_create_file("raw_data", S_IFREG | 0444, dir,
+				&rawdata->count, &rawdata_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	rawdata->dents[AAFS_LOADDATA_DATA] = dent;
+	d_inode(dent)->i_size = rawdata->size;
+
+	rawdata->ns = aa_get_ns(ns);
+	list_add(&rawdata->list, &ns->rawdata_list);
+
+	return 0;
+
+fail:
+	remove_rawdata_dents(rawdata);
+	return PTR_ERR(dent);
+}
+#endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
+
+
+/** fns to setup dynamic per profile/namespace files **/
+
+/*
+ *
+ * Requires: @profile->ns->lock held
+ */
+void __aafs_profile_rmdir(struct aa_profile *profile)
+{
+	struct aa_profile *child;
+	int i;
+
+	if (!profile)
+		return;
+
+	list_for_each_entry(child, &profile->base.profiles, base.list)
+		__aafs_profile_rmdir(child);
+
+	for (i = AAFS_PROF_SIZEOF - 1; i >= 0; --i) {
+		if (!profile->dents[i])
+			continue;
+
+		aafs_remove(profile->dents[i]);
+		profile->dents[i] = NULL;
+	}
+}
+
+/*
+ *
+ * Requires: @old->ns->lock held
+ */
+void __aafs_profile_migrate_dents(struct aa_profile *old,
+				  struct aa_profile *new)
+{
+	int i;
+
+	AA_BUG(!old);
+	AA_BUG(!new);
+	AA_BUG(!mutex_is_locked(&profiles_ns(old)->lock));
+
+	for (i = 0; i < AAFS_PROF_SIZEOF; i++) {
+		new->dents[i] = old->dents[i];
+		if (new->dents[i]) {
+			struct inode *inode = d_inode(new->dents[i]);
+
+			inode_set_mtime_to_ts(inode,
+					      inode_set_ctime_current(inode));
+		}
+		old->dents[i] = NULL;
+	}
+}
+
+static struct dentry *create_profile_file(struct dentry *dir, const char *name,
+					  struct aa_profile *profile,
+					  const struct file_operations *fops)
+{
+	return aafs_create_file(name, S_IFREG | 0444, dir, &profile->label.proxy->count, fops);
+}
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+static int profile_depth(struct aa_profile *profile)
+{
+	int depth = 0;
+
+	rcu_read_lock();
+	for (depth = 0; profile; profile = rcu_access_pointer(profile->parent))
+		depth++;
+	rcu_read_unlock();
+
+	return depth;
+}
+
+static char *gen_symlink_name(int depth, const char *dirname, const char *fname)
+{
+	char *buffer, *s;
+	int error;
+	const char *path = "../../";
+	size_t path_len = strlen(path);
+	int size;
+
+	/* Extra 11 bytes: "raw_data" (9) + two slashes "//" (2) */
+	size = depth * path_len + strlen(dirname) + strlen(fname) + 11;
+	s = buffer = kmalloc(size, GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	for (; depth > 0; depth--) {
+		memcpy(s, path, path_len);
+		s += path_len;
+		size -= path_len;
+	}
+
+	error = snprintf(s, size, "raw_data/%s/%s", dirname, fname);
+	if (error >= size || error < 0) {
+		kfree(buffer);
+		return ERR_PTR(-ENAMETOOLONG);
+	}
+
+	return buffer;
+}
+
+static const char *rawdata_get_link_base(struct dentry *dentry,
+					 struct inode *inode,
+					 struct delayed_call *done,
+					 const char *name)
+{
+	struct aa_common_ref *ref = inode->i_private;
+	struct aa_proxy *proxy = container_of(ref, struct aa_proxy, count);
+	struct aa_label *label;
+	struct aa_profile *profile;
+	char *target;
+	int depth;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	label = aa_get_label_rcu(&proxy->label);
+	profile = labels_profile(label);
+
+	/* rawdata can be null when aa_g_export_binary is unset during
+	 * runtime and a profile is replaced
+	 */
+	if (!profile->rawdata) {
+		aa_put_label(label);
+		return ERR_PTR(-ENOENT);
+	}
+
+	depth = profile_depth(profile);
+	target = gen_symlink_name(depth, profile->rawdata->name, name);
+	aa_put_label(label);
+
+	if (IS_ERR(target))
+		return target;
+
+	set_delayed_call(done, kfree_link, target);
+
+	return target;
+}
+
+static const char *rawdata_get_link_sha256(struct dentry *dentry,
+					 struct inode *inode,
+					 struct delayed_call *done)
+{
+	return rawdata_get_link_base(dentry, inode, done, "sha256");
+}
+
+static const char *rawdata_get_link_abi(struct dentry *dentry,
+					struct inode *inode,
+					struct delayed_call *done)
+{
+	return rawdata_get_link_base(dentry, inode, done, "abi");
+}
+
+static const char *rawdata_get_link_data(struct dentry *dentry,
+					 struct inode *inode,
+					 struct delayed_call *done)
+{
+	return rawdata_get_link_base(dentry, inode, done, "raw_data");
+}
+
+static const struct inode_operations rawdata_link_sha256_iops = {
+	.get_link	= rawdata_get_link_sha256,
+};
+
+static const struct inode_operations rawdata_link_abi_iops = {
+	.get_link	= rawdata_get_link_abi,
+};
+static const struct inode_operations rawdata_link_data_iops = {
+	.get_link	= rawdata_get_link_data,
+};
+
+/*
+ * Requires: @profile->ns->lock held
+ */
+void __aa_remove_rawdata_symlink_dents(struct aa_profile *profile)
+{
+	aafs_remove(profile->dents[AAFS_PROF_RAW_HASH]);
+	profile->dents[AAFS_PROF_RAW_HASH] = NULL;
+	aafs_remove(profile->dents[AAFS_PROF_RAW_ABI]);
+	profile->dents[AAFS_PROF_RAW_ABI] = NULL;
+	aafs_remove(profile->dents[AAFS_PROF_RAW_DATA]);
+	profile->dents[AAFS_PROF_RAW_DATA] = NULL;
+}
+
+static inline int create_symlink_dent(struct aa_profile *profile,
+				      const char *name,
+				      enum aafs_prof_type type,
+				      const struct inode_operations *iops)
+{
+	struct dentry *dent = NULL;
+	struct dentry *dir = prof_dir(profile);
+
+	if (profile->dents[type])
+		return 0;
+
+	dent = aafs_create(name, S_IFLNK | 0444, dir,
+			   &profile->label.proxy->count, NULL, NULL, iops);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+
+	profile->dents[type] = dent;
+	return 0;
+}
+
+/*
+ * Requires: @profile->ns->lock held
+ */
+int __aa_create_rawdata_symlink_dents(struct aa_profile *profile)
+{
+	int error;
+
+	if (!profile ||
+	    (profile->dents[AAFS_PROF_RAW_HASH] &&
+	     profile->dents[AAFS_PROF_RAW_ABI] &&
+	     profile->dents[AAFS_PROF_RAW_DATA]))
+		return 0;
+
+	if (!profile->rawdata)
+		return 0;
+
+	if (aa_g_hash_policy) {
+		error = create_symlink_dent(profile, "raw_sha256",
+					    AAFS_PROF_RAW_HASH,
+					    &rawdata_link_sha256_iops);
+		if (error)
+			return error;
+	}
+
+	error = create_symlink_dent(profile, "raw_abi",
+				    AAFS_PROF_RAW_ABI,
+				    &rawdata_link_abi_iops);
+	if (error)
+		return error;
+
+
+	error = create_symlink_dent(profile, "raw_data",
+				    AAFS_PROF_RAW_DATA,
+				    &rawdata_link_data_iops);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+#endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
+
+/*
+ * Requires: @profile->ns->lock held
+ */
+int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
+{
+	struct aa_profile *child;
+	struct dentry *dent = NULL, *dir;
+	int error;
+
+	AA_BUG(!profile);
+	AA_BUG(!mutex_is_locked(&profiles_ns(profile)->lock));
+
+	if (!parent) {
+		struct aa_profile *p;
+		p = aa_deref_parent(profile);
+		dent = prof_dir(p);
+		if (!dent) {
+			error = -ENOENT;
+			goto fail2;
+		}
+		/* adding to parent that previously didn't have children */
+		dent = aafs_create_dir("profiles", dent);
+		if (IS_ERR(dent))
+			goto fail;
+		prof_child_dir(p) = parent = dent;
+	}
+
+	if (!profile->dirname) {
+		int len, id_len;
+		len = mangle_name(profile->base.name, NULL);
+		id_len = snprintf(NULL, 0, ".%ld", profile->ns->uniq_id);
+
+		profile->dirname = kmalloc(len + id_len + 1, GFP_KERNEL);
+		if (!profile->dirname) {
+			error = -ENOMEM;
+			goto fail2;
+		}
+
+		mangle_name(profile->base.name, profile->dirname);
+		sprintf(profile->dirname + len, ".%ld", profile->ns->uniq_id++);
+	}
+
+	dent = aafs_create_dir(profile->dirname, parent);
+	if (IS_ERR(dent))
+		goto fail;
+	prof_dir(profile) = dir = dent;
+
+	dent = create_profile_file(dir, "name", profile,
+				   &seq_profile_name_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_NAME] = dent;
+
+	dent = create_profile_file(dir, "mode", profile,
+				   &seq_profile_mode_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_MODE] = dent;
+
+	dent = create_profile_file(dir, "attach", profile,
+				   &seq_profile_attach_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_ATTACH] = dent;
+
+	if (profile->hash) {
+		dent = create_profile_file(dir, "sha256", profile,
+					   &seq_profile_hash_fops);
+		if (IS_ERR(dent))
+			goto fail;
+		profile->dents[AAFS_PROF_HASH] = dent;
+	}
+
+	error = __aa_create_rawdata_symlink_dents(profile);
+	if (error)
+		goto fail2;
+
+	list_for_each_entry(child, &profile->base.profiles, base.list) {
+		error = __aafs_profile_mkdir(child, prof_child_dir(profile));
+		if (error)
+			goto fail2;
+	}
+
+	return 0;
+
+fail:
+	error = PTR_ERR(dent);
+
+fail2:
+	__aafs_profile_rmdir(profile);
+
+	return error;
+}
+
+static struct dentry *ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir,
+				  struct dentry *dentry, umode_t mode)
+{
+	struct aa_ns *ns, *parent;
+	/* TODO: improve permission check */
+	struct aa_label *label;
+	int error;
+	bool needput;
+
+	label = begin_current_label_crit_section(&needput);
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
+				     AA_MAY_LOAD_POLICY);
+	end_current_label_crit_section(label, needput);
+	if (error)
+		return ERR_PTR(error);
+
+	parent = get_ns_common_ref(dir->i_private);
+	AA_BUG(d_inode(ns_subns_dir(parent)) != dir);
+
+	/* we have to unlock and then relock to get locking order right
+	 * for pin_fs
+	 */
+	inode_unlock(dir);
+	error = simple_pin_fs(&aafs_ops, &aafs_mnt, &aafs_count);
+	mutex_lock_nested(&parent->lock, parent->level);
+	inode_lock_nested(dir, I_MUTEX_PARENT);
+	if (error)
+		goto out;
+
+	error = __aafs_setup_d_inode(dir, dentry, mode | S_IFDIR,  NULL,
+				     NULL, NULL, NULL);
+	if (error)
+		goto out_pin;
+
+	ns = __aa_find_or_create_ns(parent, READ_ONCE(dentry->d_name.name),
+				    dentry);
+	if (IS_ERR(ns)) {
+		error = PTR_ERR(ns);
+		ns = NULL;
+	}
+
+	aa_put_ns(ns);		/* list ref remains */
+out_pin:
+	if (error)
+		simple_release_fs(&aafs_mnt, &aafs_count);
+out:
+	mutex_unlock(&parent->lock);
+	aa_put_ns(parent);
+
+	return error ? ERR_PTR(error) : NULL;
+}
+
+static int ns_rmdir_op(struct inode *dir, struct dentry *dentry)
+{
+	struct aa_ns *ns, *parent;
+	/* TODO: improve permission check */
+	struct aa_label *label;
+	bool needput;
+	int error;
+
+	label = begin_current_label_crit_section(&needput);
+	error = aa_may_manage_policy(current_cred(), label, NULL, NULL,
+				     AA_MAY_LOAD_POLICY);
+	end_current_label_crit_section(label, needput);
+	if (error)
+		return error;
+
+	parent = get_ns_common_ref(dir->i_private);
+	/* rmdir calls the generic securityfs functions to remove files
+	 * from the apparmor dir. It is up to the apparmor ns locking
+	 * to avoid races.
+	 */
+	inode_unlock(dir);
+	inode_unlock(dentry->d_inode);
+
+	mutex_lock_nested(&parent->lock, parent->level);
+	ns = aa_get_ns(__aa_findn_ns(&parent->sub_ns, dentry->d_name.name,
+				     dentry->d_name.len));
+	if (!ns) {
+		error = -ENOENT;
+		goto out;
+	}
+	AA_BUG(ns_dir(ns) != dentry);
+
+	__aa_remove_ns(ns);
+	aa_put_ns(ns);
+
+out:
+	mutex_unlock(&parent->lock);
+	inode_lock_nested(dir, I_MUTEX_PARENT);
+	inode_lock(dentry->d_inode);
+	aa_put_ns(parent);
+
+	return error;
+}
+
+static const struct inode_operations ns_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.mkdir		= ns_mkdir_op,
+	.rmdir		= ns_rmdir_op,
+};
+
+static void __aa_fs_list_remove_rawdata(struct aa_ns *ns)
+{
+	struct aa_loaddata *ent, *tmp;
+
+	AA_BUG(!mutex_is_locked(&ns->lock));
+
+	list_for_each_entry_safe(ent, tmp, &ns->rawdata_list, list)
+		__aa_fs_remove_rawdata(ent);
+}
+
+/*
+ *
+ * Requires: @ns->lock held
+ */
+void __aafs_ns_rmdir(struct aa_ns *ns)
+{
+	struct aa_ns *sub;
+	struct aa_profile *child;
+	int i;
+
+	if (!ns)
+		return;
+	AA_BUG(!mutex_is_locked(&ns->lock));
+
+	list_for_each_entry(child, &ns->base.profiles, base.list)
+		__aafs_profile_rmdir(child);
+
+	list_for_each_entry(sub, &ns->sub_ns, base.list) {
+		mutex_lock_nested(&sub->lock, sub->level);
+		__aafs_ns_rmdir(sub);
+		mutex_unlock(&sub->lock);
+	}
+
+	__aa_fs_list_remove_rawdata(ns);
+
+	for (i = AAFS_NS_SIZEOF - 1; i >= 0; --i) {
+		aafs_remove(ns->dents[i]);
+		ns->dents[i] = NULL;
+	}
+}
+
+/* assumes cleanup in caller */
+static int __aafs_ns_mkdir_entries(struct aa_ns *ns, struct dentry *dir)
+{
+	struct dentry *dent;
+
+	AA_BUG(!ns);
+	AA_BUG(!dir);
+
+	dent = aafs_create_dir("profiles", dir);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subprofs_dir(ns) = dent;
+
+	dent = aafs_create_dir("raw_data", dir);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subdata_dir(ns) = dent;
+
+	dent = aafs_create_file("revision", 0444, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_ns_revision_fops);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subrevision(ns) = dent;
+
+	dent = aafs_create_file(".load", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_load);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subload(ns) = dent;
+
+	dent = aafs_create_file(".replace", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_replace);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subreplace(ns) = dent;
+
+	dent = aafs_create_file(".remove", 0640, dir,
+				&ns->unconfined->label.count,
+				&aa_fs_profile_remove);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subremove(ns) = dent;
+
+	  /* use create_dentry so we can supply private data */
+	dent = aafs_create("namespaces", S_IFDIR | 0755, dir,
+			   &ns->unconfined->label.count,
+			   NULL, NULL, &ns_dir_inode_operations);
+	if (IS_ERR(dent))
+		return PTR_ERR(dent);
+	ns_subns_dir(ns) = dent;
+
+	return 0;
+}
+
+/*
+ * Requires: @ns->lock held
+ */
+int __aafs_ns_mkdir(struct aa_ns *ns, struct dentry *parent, const char *name,
+		    struct dentry *dent)
+{
+	struct aa_ns *sub;
+	struct aa_profile *child;
+	struct dentry *dir;
+	int error;
+
+	AA_BUG(!ns);
+	AA_BUG(!parent);
+	AA_BUG(!mutex_is_locked(&ns->lock));
+
+	if (!name)
+		name = ns->base.name;
+
+	if (!dent) {
+		/* create ns dir if it doesn't already exist */
+		dent = aafs_create_dir(name, parent);
+		if (IS_ERR(dent))
+			goto fail;
+	} else
+		dget(dent);
+	ns_dir(ns) = dir = dent;
+	error = __aafs_ns_mkdir_entries(ns, dir);
+	if (error)
+		goto fail2;
+
+	/* profiles */
+	list_for_each_entry(child, &ns->base.profiles, base.list) {
+		error = __aafs_profile_mkdir(child, ns_subprofs_dir(ns));
+		if (error)
+			goto fail2;
+	}
+
+	/* subnamespaces */
+	list_for_each_entry(sub, &ns->sub_ns, base.list) {
+		mutex_lock_nested(&sub->lock, sub->level);
+		error = __aafs_ns_mkdir(sub, ns_subns_dir(ns), NULL, NULL);
+		mutex_unlock(&sub->lock);
+		if (error)
+			goto fail2;
+	}
+
+	return 0;
+
+fail:
+	error = PTR_ERR(dent);
+
+fail2:
+	__aafs_ns_rmdir(ns);
+
+	return error;
+}
+
+/**
+ * __next_ns - find the next namespace to list
+ * @root: root namespace to stop search at (NOT NULL)
+ * @ns: current ns position (NOT NULL)
+ *
+ * Find the next namespace from @ns under @root and handle all locking needed
+ * while switching current namespace.
+ *
+ * Returns: next namespace or NULL if at last namespace under @root
+ * Requires: ns->parent->lock to be held
+ * NOTE: will not unlock root->lock
+ */
+static struct aa_ns *__next_ns(struct aa_ns *root, struct aa_ns *ns)
+{
+	struct aa_ns *parent, *next;
+
+	AA_BUG(!root);
+	AA_BUG(!ns);
+	AA_BUG(ns != root && !mutex_is_locked(&ns->parent->lock));
+
+	/* is next namespace a child */
+	if (!list_empty(&ns->sub_ns)) {
+		next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list);
+		mutex_lock_nested(&next->lock, next->level);
+		return next;
+	}
+
+	/* check if the next ns is a sibling, parent, gp, .. */
+	parent = ns->parent;
+	while (ns != root) {
+		mutex_unlock(&ns->lock);
+		next = list_next_entry(ns, base.list);
+		if (!list_entry_is_head(next, &parent->sub_ns, base.list)) {
+			mutex_lock_nested(&next->lock, next->level);
+			return next;
+		}
+		ns = parent;
+		parent = parent->parent;
+	}
+
+	return NULL;
+}
+
+/**
+ * __first_profile - find the first profile in a namespace
+ * @root: namespace that is root of profiles being displayed (NOT NULL)
+ * @ns: namespace to start in   (NOT NULL)
+ *
+ * Returns: unrefcounted profile or NULL if no profile
+ * Requires: profile->ns.lock to be held
+ */
+static struct aa_profile *__first_profile(struct aa_ns *root,
+					  struct aa_ns *ns)
+{
+	AA_BUG(!root);
+	AA_BUG(ns && !mutex_is_locked(&ns->lock));
+
+	for (; ns; ns = __next_ns(root, ns)) {
+		if (!list_empty(&ns->base.profiles))
+			return list_first_entry(&ns->base.profiles,
+						struct aa_profile, base.list);
+	}
+	return NULL;
+}
+
+/**
+ * __next_profile - step to the next profile in a profile tree
+ * @p: current profile in tree (NOT NULL)
+ *
+ * Perform a depth first traversal on the profile tree in a namespace
+ *
+ * Returns: next profile or NULL if done
+ * Requires: profile->ns.lock to be held
+ */
+static struct aa_profile *__next_profile(struct aa_profile *p)
+{
+	struct aa_profile *parent;
+	struct aa_ns *ns = p->ns;
+
+	AA_BUG(!mutex_is_locked(&profiles_ns(p)->lock));
+
+	/* is next profile a child */
+	if (!list_empty(&p->base.profiles))
+		return list_first_entry(&p->base.profiles, typeof(*p),
+					base.list);
+
+	/* is next profile a sibling, parent sibling, gp, sibling, .. */
+	parent = rcu_dereference_protected(p->parent,
+					   mutex_is_locked(&p->ns->lock));
+	while (parent) {
+		p = list_next_entry(p, base.list);
+		if (!list_entry_is_head(p, &parent->base.profiles, base.list))
+			return p;
+		p = parent;
+		parent = rcu_dereference_protected(parent->parent,
+					    mutex_is_locked(&parent->ns->lock));
+	}
+
+	/* is next another profile in the namespace */
+	p = list_next_entry(p, base.list);
+	if (!list_entry_is_head(p, &ns->base.profiles, base.list))
+		return p;
+
+	return NULL;
+}
+
+/**
+ * next_profile - step to the next profile in where ever it may be
+ * @root: root namespace  (NOT NULL)
+ * @profile: current profile  (NOT NULL)
+ *
+ * Returns: next profile or NULL if there isn't one
+ */
+static struct aa_profile *next_profile(struct aa_ns *root,
+				       struct aa_profile *profile)
+{
+	struct aa_profile *next = __next_profile(profile);
+	if (next)
+		return next;
+
+	/* finished all profiles in namespace move to next namespace */
+	return __first_profile(root, __next_ns(root, profile->ns));
+}
+
+/**
+ * p_start - start a depth first traversal of profile tree
+ * @f: seq_file to fill
+ * @pos: current position
+ *
+ * Returns: first profile under current namespace or NULL if none found
+ *
+ * acquires first ns->lock
+ */
+static void *p_start(struct seq_file *f, loff_t *pos)
+{
+	struct aa_profile *profile = NULL;
+	struct aa_ns *root = aa_get_current_ns();
+	loff_t l = *pos;
+	f->private = root;
+
+	/* find the first profile */
+	mutex_lock_nested(&root->lock, root->level);
+	profile = __first_profile(root, root);
+
+	/* skip to position */
+	for (; profile && l > 0; l--)
+		profile = next_profile(root, profile);
+
+	return profile;
+}
+
+/**
+ * p_next - read the next profile entry
+ * @f: seq_file to fill
+ * @p: profile previously returned
+ * @pos: current position
+ *
+ * Returns: next profile after @p or NULL if none
+ *
+ * may acquire/release locks in namespace tree as necessary
+ */
+static void *p_next(struct seq_file *f, void *p, loff_t *pos)
+{
+	struct aa_profile *profile = p;
+	struct aa_ns *ns = f->private;
+	(*pos)++;
+
+	return next_profile(ns, profile);
+}
+
+/**
+ * p_stop - stop depth first traversal
+ * @f: seq_file we are filling
+ * @p: the last profile written
+ *
+ * Release all locking done by p_start/p_next on namespace tree
+ */
+static void p_stop(struct seq_file *f, void *p)
+{
+	struct aa_profile *profile = p;
+	struct aa_ns *root = f->private, *ns;
+
+	if (profile) {
+		for (ns = profile->ns; ns && ns != root; ns = ns->parent)
+			mutex_unlock(&ns->lock);
+	}
+	mutex_unlock(&root->lock);
+	aa_put_ns(root);
+}
+
+/**
+ * seq_show_profile - show a profile entry
+ * @f: seq_file to file
+ * @p: current position (profile)    (NOT NULL)
+ *
+ * Returns: error on failure
+ */
+static int seq_show_profile(struct seq_file *f, void *p)
+{
+	struct aa_profile *profile = (struct aa_profile *)p;
+	struct aa_ns *root = f->private;
+
+	aa_label_seq_xprint(f, root, &profile->label,
+			    FLAG_SHOW_MODE | FLAG_VIEW_SUBNS, GFP_KERNEL);
+	seq_putc(f, '\n');
+
+	return 0;
+}
+
+static const struct seq_operations aa_sfs_profiles_op = {
+	.start = p_start,
+	.next = p_next,
+	.stop = p_stop,
+	.show = seq_show_profile,
+};
+
+static int profiles_open(struct inode *inode, struct file *file)
+{
+	if (!aa_current_policy_view_capable(NULL))
+		return -EACCES;
+
+	return seq_open(file, &aa_sfs_profiles_op);
+}
+
+static int profiles_release(struct inode *inode, struct file *file)
+{
+	return seq_release(inode, file);
+}
+
+static const struct file_operations aa_sfs_profiles_fops = {
+	.open = profiles_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = profiles_release,
+};
+
+
+/** Base file system setup **/
+static struct aa_sfs_entry aa_sfs_entry_file[] = {
+	AA_SFS_FILE_STRING("mask",
+			   "create read write exec append mmap_exec link lock"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_ptrace[] = {
+	AA_SFS_FILE_STRING("mask", "read trace"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_signal[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_SIG_MASK),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_attach[] = {
+	AA_SFS_FILE_BOOLEAN("xattr", 1),
+	{ }
+};
+static struct aa_sfs_entry aa_sfs_entry_domain[] = {
+	AA_SFS_FILE_BOOLEAN("change_hat",	1),
+	AA_SFS_FILE_BOOLEAN("change_hatv",	1),
+	AA_SFS_FILE_BOOLEAN("unconfined_allowed_children",	1),
+	AA_SFS_FILE_BOOLEAN("change_onexec",	1),
+	AA_SFS_FILE_BOOLEAN("change_profile",	1),
+	AA_SFS_FILE_BOOLEAN("stack",		1),
+	AA_SFS_FILE_BOOLEAN("fix_binfmt_elf_mmap",	1),
+	AA_SFS_FILE_BOOLEAN("post_nnp_subset",	1),
+	AA_SFS_FILE_BOOLEAN("computed_longest_left",	1),
+	AA_SFS_DIR("attach_conditions",		aa_sfs_entry_attach),
+	AA_SFS_FILE_BOOLEAN("disconnected.path",            1),
+	AA_SFS_FILE_BOOLEAN("kill.signal",		1),
+	AA_SFS_FILE_STRING("version", "1.2"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_unconfined[] = {
+	AA_SFS_FILE_BOOLEAN("change_profile", 1),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_versions[] = {
+	AA_SFS_FILE_BOOLEAN("v5",	1),
+	AA_SFS_FILE_BOOLEAN("v6",	1),
+	AA_SFS_FILE_BOOLEAN("v7",	1),
+	AA_SFS_FILE_BOOLEAN("v8",	1),
+	AA_SFS_FILE_BOOLEAN("v9",	1),
+	{ }
+};
+
+#define PERMS32STR "allow deny subtree cond kill complain prompt audit quiet hide xindex tag label"
+static struct aa_sfs_entry aa_sfs_entry_policy[] = {
+	AA_SFS_DIR("versions",			aa_sfs_entry_versions),
+	AA_SFS_FILE_BOOLEAN("set_load",		1),
+	AA_SFS_FILE_BOOLEAN("diff-encode",		1),
+	/* number of out of band transitions supported */
+	AA_SFS_FILE_U64("outofband",		MAX_OOB_SUPPORTED),
+	AA_SFS_FILE_U64("permstable32_version",	3),
+	AA_SFS_FILE_STRING("permstable32", PERMS32STR),
+	AA_SFS_FILE_U64("state32",	1),
+	AA_SFS_DIR("unconfined_restrictions",   aa_sfs_entry_unconfined),
+#ifdef CONFIG_SECURITY_APPARMOR_COMPRESSED_POLICY
+	AA_SFS_FILE_BOOLEAN("compressed_load",	1),
+	AA_SFS_FILE_BOOLEAN("extended_policy_header",	1),
+#endif
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_mount[] = {
+	AA_SFS_FILE_STRING("mask", "mount umount pivot_root"),
+	AA_SFS_FILE_STRING("move_mount", "detached"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_ns[] = {
+	AA_SFS_FILE_BOOLEAN("profile",		1),
+	AA_SFS_FILE_BOOLEAN("pivot_root",	0),
+	AA_SFS_FILE_STRING("mask", "userns_create"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_dbus[] = {
+	AA_SFS_FILE_STRING("mask", "acquire send receive"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_query_label[] = {
+	AA_SFS_FILE_STRING("perms", "allow deny audit quiet"),
+	AA_SFS_FILE_BOOLEAN("data",		1),
+	AA_SFS_FILE_BOOLEAN("multi_transaction",	1),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_query[] = {
+	AA_SFS_DIR("label",			aa_sfs_entry_query_label),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_io_uring[] = {
+	AA_SFS_FILE_STRING("mask", "sqpoll override_creds"),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_features[] = {
+	AA_SFS_DIR("policy",			aa_sfs_entry_policy),
+	AA_SFS_DIR("domain",			aa_sfs_entry_domain),
+	AA_SFS_DIR("file",			aa_sfs_entry_file),
+	AA_SFS_DIR("network_v8",		aa_sfs_entry_network),
+	AA_SFS_DIR("network_v9",		aa_sfs_entry_networkv9),
+	AA_SFS_DIR("mount",			aa_sfs_entry_mount),
+	AA_SFS_DIR("namespaces",		aa_sfs_entry_ns),
+	AA_SFS_FILE_U64("capability",		VFS_CAP_FLAGS_MASK),
+	AA_SFS_DIR("rlimit",			aa_sfs_entry_rlimit),
+	AA_SFS_DIR("caps",			aa_sfs_entry_caps),
+	AA_SFS_DIR("ptrace",			aa_sfs_entry_ptrace),
+	AA_SFS_DIR("signal",			aa_sfs_entry_signal),
+	AA_SFS_DIR("dbus",			aa_sfs_entry_dbus),
+	AA_SFS_DIR("query",			aa_sfs_entry_query),
+	AA_SFS_DIR("io_uring",			aa_sfs_entry_io_uring),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry_apparmor[] = {
+	AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access),
+	AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops),
+	AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops),
+	AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops),
+	AA_SFS_FILE_FOPS(".ns_name", 0444, &seq_ns_name_fops),
+	AA_SFS_FILE_FOPS("profiles", 0444, &aa_sfs_profiles_fops),
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+	AA_SFS_FILE_FOPS("raw_data_compression_level_min", 0444, &seq_ns_compress_min_fops),
+	AA_SFS_FILE_FOPS("raw_data_compression_level_max", 0444, &seq_ns_compress_max_fops),
+#endif
+	AA_SFS_DIR("features", aa_sfs_entry_features),
+	{ }
+};
+
+static struct aa_sfs_entry aa_sfs_entry =
+	AA_SFS_DIR("apparmor", aa_sfs_entry_apparmor);
+
+/**
+ * entry_create_file - create a file entry in the apparmor securityfs
+ * @fs_file: aa_sfs_entry to build an entry for (NOT NULL)
+ * @parent: the parent dentry in the securityfs
+ *
+ * Use entry_remove_file to remove entries created with this fn.
+ */
+static int __init entry_create_file(struct aa_sfs_entry *fs_file,
+				    struct dentry *parent)
+{
+	int error = 0;
+
+	fs_file->dentry = securityfs_create_file(fs_file->name,
+						 S_IFREG | fs_file->mode,
+						 parent, fs_file,
+						 fs_file->file_ops);
+	if (IS_ERR(fs_file->dentry)) {
+		error = PTR_ERR(fs_file->dentry);
+		fs_file->dentry = NULL;
+	}
+	return error;
+}
+
+static void __init entry_remove_dir(struct aa_sfs_entry *fs_dir);
+/**
+ * entry_create_dir - recursively create a directory entry in the securityfs
+ * @fs_dir: aa_sfs_entry (and all child entries) to build (NOT NULL)
+ * @parent: the parent dentry in the securityfs
+ *
+ * Use entry_remove_dir to remove entries created with this fn.
+ */
+static int __init entry_create_dir(struct aa_sfs_entry *fs_dir,
+				   struct dentry *parent)
+{
+	struct aa_sfs_entry *fs_file;
+	struct dentry *dir;
+	int error;
+
+	dir = securityfs_create_dir(fs_dir->name, parent);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+	fs_dir->dentry = dir;
+
+	for (fs_file = fs_dir->v.files; fs_file && fs_file->name; ++fs_file) {
+		if (fs_file->v_type == AA_SFS_TYPE_DIR)
+			error = entry_create_dir(fs_file, fs_dir->dentry);
+		else
+			error = entry_create_file(fs_file, fs_dir->dentry);
+		if (error)
+			goto failed;
+	}
+
+	return 0;
+
+failed:
+	entry_remove_dir(fs_dir);
+
+	return error;
+}
+
+/**
+ * entry_remove_file - drop a single file entry in the apparmor securityfs
+ * @fs_file: aa_sfs_entry to detach from the securityfs (NOT NULL)
+ */
+static void __init entry_remove_file(struct aa_sfs_entry *fs_file)
+{
+	if (!fs_file->dentry)
+		return;
+
+	securityfs_remove(fs_file->dentry);
+	fs_file->dentry = NULL;
+}
+
+/**
+ * entry_remove_dir - recursively drop a directory entry from the securityfs
+ * @fs_dir: aa_sfs_entry (and all child entries) to detach (NOT NULL)
+ */
+static void __init entry_remove_dir(struct aa_sfs_entry *fs_dir)
+{
+	struct aa_sfs_entry *fs_file;
+
+	for (fs_file = fs_dir->v.files; fs_file && fs_file->name; ++fs_file) {
+		if (fs_file->v_type == AA_SFS_TYPE_DIR)
+			entry_remove_dir(fs_file);
+		else
+			entry_remove_file(fs_file);
+	}
+
+	entry_remove_file(fs_dir);
+}
+
+/**
+ * aa_destroy_aafs - cleanup and free aafs
+ *
+ * releases dentries allocated by aa_create_aafs
+ */
+void __init aa_destroy_aafs(void)
+{
+	entry_remove_dir(&aa_sfs_entry);
+}
+
+
+#define NULL_FILE_NAME ".null"
+struct path aa_null;
+
+static int aa_mk_null_file(struct dentry *parent)
+{
+	struct vfsmount *mount = NULL;
+	struct dentry *dentry;
+	struct inode *inode;
+	int count = 0;
+	int error = simple_pin_fs(parent->d_sb->s_type, &mount, &count);
+
+	if (error)
+		return error;
+
+	dentry = simple_start_creating(parent, NULL_FILE_NAME);
+	if (IS_ERR(dentry)) {
+		error = PTR_ERR(dentry);
+		goto out;
+	}
+	inode = new_inode(parent->d_inode->i_sb);
+	if (!inode) {
+		error = -ENOMEM;
+		goto out;
+	}
+
+	inode->i_ino = get_next_ino();
+	inode->i_mode = S_IFCHR | S_IRUGO | S_IWUGO;
+	simple_inode_init_ts(inode);
+	init_special_inode(inode, S_IFCHR | S_IRUGO | S_IWUGO,
+			   MKDEV(MEM_MAJOR, 3));
+	d_instantiate(dentry, inode);
+	aa_null.dentry = dget(dentry);
+	aa_null.mnt = mntget(mount);
+
+out:
+	simple_done_creating(dentry);
+	simple_release_fs(&mount, &count);
+	return error;
+}
+
+static const char *policy_get_link(struct dentry *dentry,
+				   struct inode *inode,
+				   struct delayed_call *done)
+{
+	struct aa_ns *ns;
+	struct path path;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	ns = aa_get_current_ns();
+	path.mnt = mntget(aafs_mnt);
+	path.dentry = dget(ns_dir(ns));
+	error = nd_jump_link(&path);
+	aa_put_ns(ns);
+
+	return ERR_PTR(error);
+}
+
+static int policy_readlink(struct dentry *dentry, char __user *buffer,
+			   int buflen)
+{
+	char name[32];
+	int res;
+
+	res = snprintf(name, sizeof(name), "%s:[%llu]", AAFS_NAME,
+		       d_inode(dentry)->i_ino);
+	if (res > 0 && res < sizeof(name))
+		res = readlink_copy(buffer, buflen, name, strlen(name));
+	else
+		res = -ENOENT;
+
+	return res;
+}
+
+static const struct inode_operations policy_link_iops = {
+	.readlink	= policy_readlink,
+	.get_link	= policy_get_link,
+};
+
+
+/**
+ * aa_create_aafs - create the apparmor security filesystem
+ *
+ * dentries created here are released by aa_destroy_aafs
+ *
+ * Returns: error on failure
+ */
+int __init aa_create_aafs(void)
+{
+	struct dentry *dent;
+	int error;
+
+	if (!apparmor_initialized)
+		return 0;
+
+	if (aa_sfs_entry.dentry) {
+		AA_ERROR("%s: AppArmor securityfs already exists\n", __func__);
+		return -EEXIST;
+	}
+
+	/* setup apparmorfs used to virtualize policy/ */
+	aafs_mnt = kern_mount(&aafs_ops);
+	if (IS_ERR(aafs_mnt))
+		panic("can't set apparmorfs up\n");
+	aafs_mnt->mnt_sb->s_flags &= ~SB_NOUSER;
+
+	/* Populate fs tree. */
+	error = entry_create_dir(&aa_sfs_entry, NULL);
+	if (error)
+		goto error;
+
+	dent = securityfs_create_file(".load", 0666, aa_sfs_entry.dentry,
+				      NULL, &aa_fs_profile_load);
+	if (IS_ERR(dent))
+		goto dent_error;
+	ns_subload(root_ns) = dent;
+
+	dent = securityfs_create_file(".replace", 0666, aa_sfs_entry.dentry,
+				      NULL, &aa_fs_profile_replace);
+	if (IS_ERR(dent))
+		goto dent_error;
+	ns_subreplace(root_ns) = dent;
+
+	dent = securityfs_create_file(".remove", 0666, aa_sfs_entry.dentry,
+				      NULL, &aa_fs_profile_remove);
+	if (IS_ERR(dent))
+		goto dent_error;
+	ns_subremove(root_ns) = dent;
+
+	dent = securityfs_create_file("revision", 0444, aa_sfs_entry.dentry,
+				      NULL, &aa_fs_ns_revision_fops);
+	if (IS_ERR(dent))
+		goto dent_error;
+	ns_subrevision(root_ns) = dent;
+
+	/* policy tree referenced by magic policy symlink */
+	mutex_lock_nested(&root_ns->lock, root_ns->level);
+	error = __aafs_ns_mkdir(root_ns, aafs_mnt->mnt_root, ".policy",
+				aafs_mnt->mnt_root);
+	mutex_unlock(&root_ns->lock);
+	if (error)
+		goto error;
+
+	/* magic symlink similar to nsfs redirects based on task policy */
+	dent = securityfs_create_symlink("policy", aa_sfs_entry.dentry,
+					 NULL, &policy_link_iops);
+	if (IS_ERR(dent))
+		goto dent_error;
+
+	error = aa_mk_null_file(aa_sfs_entry.dentry);
+	if (error)
+		goto error;
+
+	/* TODO: add default profile to apparmorfs */
+
+	/* Report that AppArmor fs is enabled */
+	aa_info_message("AppArmor Filesystem Enabled");
+	return 0;
+
+dent_error:
+	error = PTR_ERR(dent);
+error:
+	aa_destroy_aafs();
+	AA_ERROR("Error creating AppArmor securityfs\n");
+	return error;
+}
diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c
new file mode 100644
index 000000000..5752bb93a
--- /dev/null
+++ b/security/apparmor/audit.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor auditing functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/audit.h>
+#include <linux/socket.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+#include "include/secid.h"
+
+const char *const audit_mode_names[] = {
+	"normal",
+	"quiet_denied",
+	"quiet.allowed",
+	"quiet",
+	"noquiet",
+	"all"
+};
+
+static const char *const aa_audit_type[] = {
+	"AUDIT",
+	"ALLOWED",
+	"DENIED",
+	"HINT",
+	"STATUS",
+	"ERROR",
+	"KILLED",
+	"AUTO"
+};
+
+static const char *const aa_class_names[] = {
+	"none",
+	"unknown",
+	"file",
+	"cap",
+	"net",
+	"rlimits",
+	"domain",
+	"mount",
+	"unknown",
+	"ptrace",
+	"signal",
+	"xmatch",
+	"unknown",
+	"unknown",
+	"net",
+	"netv9",
+	"label",
+	"posix_mqueue",
+	"io_uring",
+	"module",
+	"lsm",
+	"namespace",
+	"io_uring",
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+	"netv9_packet",
+	"X",
+	"dbus",
+};
+
+
+/*
+ * Currently AppArmor auditing is fed straight into the audit framework.
+ *
+ * TODO:
+ * netlink interface for complain mode
+ * user auditing, - send user auditing to netlink interface
+ * system control of whether user audit messages go to system log
+ */
+
+/**
+ * audit_pre() - core AppArmor function.
+ * @ab: audit buffer to fill (NOT NULL)
+ * @va: audit structure containing data to audit (NOT NULL)
+ *
+ * Record common AppArmor audit data from @va
+ */
+static void audit_pre(struct audit_buffer *ab, void *va)
+{
+	struct apparmor_audit_data *ad = aad_of_va(va);
+
+	if (aa_g_audit_header) {
+		audit_log_format(ab, "apparmor=\"%s\"",
+				 aa_audit_type[ad->type]);
+	}
+
+	if (ad->op)
+		audit_log_format(ab, " operation=\"%s\"", ad->op);
+
+	if (ad->class)
+		audit_log_format(ab, " class=\"%s\"",
+				 ad->class <= AA_CLASS_LAST ?
+				 aa_class_names[ad->class] :
+				 "unknown");
+
+	if (ad->info) {
+		audit_log_format(ab, " info=\"%s\"", ad->info);
+		if (ad->error)
+			audit_log_format(ab, " error=%d", ad->error);
+	}
+
+	if (ad->subj_label) {
+		struct aa_label *label = ad->subj_label;
+
+		if (label_isprofile(label)) {
+			struct aa_profile *profile = labels_profile(label);
+
+			if (profile->ns != root_ns) {
+				audit_log_format(ab, " namespace=");
+				audit_log_untrustedstring(ab,
+						       profile->ns->base.hname);
+			}
+			audit_log_format(ab, " profile=");
+			audit_log_untrustedstring(ab, profile->base.hname);
+		} else {
+			audit_log_format(ab, " label=");
+			aa_label_xaudit(ab, root_ns, label, FLAG_VIEW_SUBNS,
+					GFP_ATOMIC);
+		}
+	}
+
+	if (ad->name) {
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, ad->name);
+	}
+}
+
+int aa_select_audit_type(u32 denied, const struct aa_perms *perms)
+{
+	if (likely(!denied))
+		return AUDIT_APPARMOR_AUDIT;
+	else if (denied & perms->kill)
+		return AUDIT_APPARMOR_KILL;
+	else if (denied == (denied & perms->complain))
+		return AUDIT_APPARMOR_ALLOWED;
+	return AUDIT_APPARMOR_DENIED;
+}
+
+/**
+ * aa_audit_msg - Log a message to the audit subsystem
+ * @type: audit type for the message
+ * @ad: audit event structure (NOT NULL)
+ * @cb: optional callback fn for type specific fields (MAYBE NULL)
+ */
+void aa_audit_msg(int type, struct apparmor_audit_data *ad,
+		  void (*cb) (struct audit_buffer *, void *))
+{
+	ad->type = type;
+	common_lsm_audit(&ad->common, audit_pre, cb);
+}
+
+int aa_audit_perm_error(struct aa_label *label, u32 request, int error,
+			struct apparmor_audit_data *ad,
+			void (*cb)(struct audit_buffer *, void *))
+{
+	int type = aa_select_audit_type(request, &nullperms);
+
+	if (ad) {
+		struct aa_profile *profile;
+		struct label_it i;
+
+		ad->request = request;
+		ad->denied = request;
+		ad->error = error;
+		label_for_each_confined(i, label, profile) {
+			ad->subj_label = &profile->label;
+			aa_audit_msg(type, ad, cb);
+		}
+	}
+
+	return error;
+}
+
+/**
+ * aa_audit - Log a profile based audit event to the audit subsystem
+ * @type: audit type for the message
+ * @profile: profile to check against (NOT NULL)
+ * @ad: audit event (NOT NULL)
+ * @cb: optional callback fn for type specific fields (MAYBE NULL)
+ *
+ * Handle default message switching based off of audit mode flags
+ *
+ * Returns: error on failure
+ */
+int aa_audit(int type, struct aa_profile *profile,
+	     struct apparmor_audit_data *ad,
+	     void (*cb) (struct audit_buffer *, void *))
+{
+	AA_BUG(!profile);
+
+	if (type == AUDIT_APPARMOR_AUTO) {
+		if (likely(!ad->error)) {
+			if (AUDIT_MODE(profile) != AUDIT_ALL)
+				return 0;
+			type = AUDIT_APPARMOR_AUDIT;
+		} else if (COMPLAIN_MODE(profile))
+			type = AUDIT_APPARMOR_ALLOWED;
+		else
+			type = AUDIT_APPARMOR_DENIED;
+	}
+	if (AUDIT_MODE(profile) == AUDIT_QUIET ||
+	    (type == AUDIT_APPARMOR_DENIED &&
+	     AUDIT_MODE(profile) == AUDIT_QUIET_DENIED))
+		return ad->error;
+
+	if (KILL_MODE(profile) && type == AUDIT_APPARMOR_DENIED)
+		type = AUDIT_APPARMOR_KILL;
+
+	ad->subj_label = &profile->label;
+
+	aa_audit_msg(type, ad, cb);
+
+	if (ad->type == AUDIT_APPARMOR_KILL)
+		send_sig_info(profile->signal, SEND_SIG_NOINFO,
+			ad->common.type == LSM_AUDIT_DATA_TASK &&
+			ad->common.u.tsk ? ad->common.u.tsk : current);
+
+	if (ad->type == AUDIT_APPARMOR_ALLOWED)
+		return complain_error(ad->error);
+
+	return ad->error;
+}
+
+struct aa_audit_rule {
+	struct aa_label *label;
+};
+
+void aa_audit_rule_free(void *vrule)
+{
+	struct aa_audit_rule *rule = vrule;
+
+	if (rule) {
+		if (!IS_ERR(rule->label))
+			aa_put_label(rule->label);
+		kfree(rule);
+	}
+}
+
+int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp)
+{
+	struct aa_audit_rule *rule;
+
+	switch (field) {
+	case AUDIT_SUBJ_ROLE:
+		if (op != Audit_equal && op != Audit_not_equal)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rule = kzalloc_obj(struct aa_audit_rule, gfp);
+
+	if (!rule)
+		return -ENOMEM;
+
+	/* Currently rules are treated as coming from the root ns */
+	rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr,
+				     gfp, true, false);
+	if (IS_ERR(rule->label)) {
+		int err = PTR_ERR(rule->label);
+		aa_audit_rule_free(rule);
+		return err;
+	}
+
+	*vrule = rule;
+	return 0;
+}
+
+int aa_audit_rule_known(struct audit_krule *rule)
+{
+	int i;
+
+	for (i = 0; i < rule->field_count; i++) {
+		struct audit_field *f = &rule->fields[i];
+
+		switch (f->type) {
+		case AUDIT_SUBJ_ROLE:
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+int aa_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule)
+{
+	struct aa_audit_rule *rule = vrule;
+	struct aa_label *label;
+	int found = 0;
+
+	label = prop->apparmor.label;
+
+	if (!label)
+		return -ENOENT;
+
+	if (aa_label_is_subset(label, rule->label))
+		found = 1;
+
+	switch (field) {
+	case AUDIT_SUBJ_ROLE:
+		switch (op) {
+		case Audit_equal:
+			return found;
+		case Audit_not_equal:
+			return !found;
+		}
+	}
+	return 0;
+}
diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c
new file mode 100644
index 000000000..2f3c6c843
--- /dev/null
+++ b/security/apparmor/capability.c
@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor capability mediation functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/security.h>
+#include <linux/timekeeping.h>
+
+#include "include/apparmor.h"
+#include "include/capability.h"
+#include "include/cred.h"
+#include "include/policy.h"
+#include "include/audit.h"
+
+/*
+ * Table of capability names: we generate it from capabilities.h.
+ */
+#include "capability_names.h"
+
+struct aa_sfs_entry aa_sfs_entry_caps[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_CAPS_MASK),
+	AA_SFS_FILE_BOOLEAN("extended", 1),
+	{ }
+};
+
+struct audit_cache {
+	const struct cred *ad_subj_cred;
+	/* Capabilities go from 0 to CAP_LAST_CAP */
+	u64 ktime_ns_expiration[CAP_LAST_CAP+1];
+};
+
+static DEFINE_PER_CPU(struct audit_cache, audit_cache);
+
+/**
+ * audit_cb - call back for capability components of audit struct
+ * @ab: audit buffer   (NOT NULL)
+ * @va: audit struct to audit data from  (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+
+	audit_log_format(ab, " capname=");
+	audit_log_untrustedstring(ab, capability_names[sa->u.cap]);
+}
+
+/**
+ * audit_caps - audit a capability
+ * @ad: audit data
+ * @profile: profile being tested for confinement (NOT NULL)
+ * @cap: capability tested
+ * @error: error code returned by test
+ *
+ * Do auditing of capability and handle, audit/complain/kill modes switching
+ * and duplicate message elimination.
+ *
+ * Returns: 0 or ad->error on success,  error code on failure
+ */
+static int audit_caps(struct apparmor_audit_data *ad, struct aa_profile *profile,
+		      int cap, int error)
+{
+	const u64 AUDIT_CACHE_TIMEOUT_NS = 1000*1000*1000; /* 1 second */
+
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct audit_cache *ent;
+	int type = AUDIT_APPARMOR_AUTO;
+
+	ad->error = error;
+
+	if (likely(!error)) {
+		/* test if auditing is being forced */
+		if (likely((AUDIT_MODE(profile) != AUDIT_ALL) &&
+			   !cap_raised(rules->caps.audit, cap)))
+			return 0;
+		type = AUDIT_APPARMOR_AUDIT;
+	} else if (KILL_MODE(profile) ||
+		   cap_raised(rules->caps.kill, cap)) {
+		type = AUDIT_APPARMOR_KILL;
+	} else if (cap_raised(rules->caps.quiet, cap) &&
+		   AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		   AUDIT_MODE(profile) != AUDIT_ALL) {
+		/* quiet auditing */
+		return error;
+	}
+
+	/* Do simple duplicate message elimination */
+	ent = &get_cpu_var(audit_cache);
+	/* If the capability was never raised the timestamp check would also catch that */
+	if (ad->subj_cred == ent->ad_subj_cred && ktime_get_ns() <= ent->ktime_ns_expiration[cap]) {
+		put_cpu_var(audit_cache);
+		if (COMPLAIN_MODE(profile))
+			return complain_error(error);
+		return error;
+	} else {
+		put_cred(ent->ad_subj_cred);
+		ent->ad_subj_cred = get_cred(ad->subj_cred);
+		ent->ktime_ns_expiration[cap] = ktime_get_ns() + AUDIT_CACHE_TIMEOUT_NS;
+	}
+	put_cpu_var(audit_cache);
+
+	return aa_audit(type, profile, ad, audit_cb);
+}
+
+/**
+ * profile_capable - test if profile allows use of capability @cap
+ * @profile: profile being enforced    (NOT NULL, NOT unconfined)
+ * @cap: capability to test if allowed
+ * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated
+ * @ad: audit data (NOT NULL)
+ *
+ * Returns: 0 if allowed else -EPERM
+ */
+static int profile_capable(struct aa_profile *profile, int cap,
+			   unsigned int opts, struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state;
+	int error;
+
+	state = RULE_MEDIATES(rules, ad->class);
+	if (state) {
+		struct aa_perms perms = { };
+		u32 request;
+
+		/* caps broken into 256 x 32 bit permission chunks */
+		state = aa_dfa_next(rules->policy->dfa, state, cap >> 5);
+		request = 1 << (cap & 0x1f);
+		perms = *aa_lookup_perms(rules->policy, state);
+		aa_apply_modes_to_perms(profile, &perms);
+
+		if (opts & CAP_OPT_NOAUDIT) {
+			if (perms.complain & request)
+				ad->info = "optional: no audit";
+			else
+				ad = NULL;
+		}
+		return aa_check_perms(profile, &perms, request, ad,
+				      audit_cb);
+	}
+
+	/* fallback to old caps mediation that doesn't support conditionals */
+	if (cap_raised(rules->caps.allow, cap) &&
+	    !cap_raised(rules->caps.denied, cap))
+		error = 0;
+	else
+		error = -EPERM;
+
+	if (opts & CAP_OPT_NOAUDIT) {
+		if (!COMPLAIN_MODE(profile))
+			return error;
+		/* audit the cap request in complain mode but note that it
+		 * should be optional.
+		 */
+		ad->info = "optional: no audit";
+	}
+
+	return audit_caps(ad, profile, cap, error);
+}
+
+/**
+ * aa_capable - test permission to use capability
+ * @subj_cred: cred we are testing capability against
+ * @label: label being tested for capability (NOT NULL)
+ * @cap: capability to be tested
+ * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated
+ *
+ * Look up capability in profile capability set.
+ *
+ * Returns: 0 on success, or else an error code.
+ */
+int aa_capable(const struct cred *subj_cred, struct aa_label *label,
+	       int cap, unsigned int opts)
+{
+	struct aa_profile *profile;
+	int error = 0;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_CAP, AA_CLASS_CAP, OP_CAPABLE);
+
+	ad.subj_cred = subj_cred;
+	ad.common.u.cap = cap;
+	error = fn_for_each_confined(label, profile,
+			profile_capable(profile, cap, opts, &ad));
+
+	return error;
+}
+
+kernel_cap_t aa_profile_capget(const struct aa_profile *profile)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state;
+
+	state = RULE_MEDIATES(rules, AA_CLASS_CAP);
+	if (state) {
+		kernel_cap_t caps = CAP_EMPTY_SET;
+		int i;
+
+		/* caps broken into up to 256, 32 bit permission chunks */
+		for (i = 0; i < (CAP_LAST_CAP >> 5); i++) {
+			struct aa_perms perms = { };
+			aa_state_t tmp;
+
+			tmp = aa_dfa_next(rules->policy->dfa, state, i);
+			perms = *aa_lookup_perms(rules->policy, tmp);
+			aa_apply_modes_to_perms(profile, &perms);
+			caps.val |= ((u64)(perms.allow)) << (i * 5);
+			caps.val |= ((u64)(perms.complain)) << (i * 5);
+		}
+		return caps;
+	}
+
+	/* fallback to old caps */
+	if (COMPLAIN_MODE(profile))
+		return CAP_FULL_SET;
+
+	return rules->caps.allow;
+}
diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c
new file mode 100644
index 000000000..d8a7bde94
--- /dev/null
+++ b/security/apparmor/crypto.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright 2013 Canonical Ltd.
+ *
+ * Fns to provide a checksum of policy that has been loaded this can be
+ * compared to userspace policy compiles to check loaded policy is what
+ * it should be.
+ */
+
+#include <crypto/sha2.h>
+
+#include "include/apparmor.h"
+#include "include/crypto.h"
+
+unsigned int aa_hash_size(void)
+{
+	return SHA256_DIGEST_SIZE;
+}
+
+char *aa_calc_hash(void *data, size_t len)
+{
+	char *hash;
+
+	hash = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
+	if (!hash)
+		return ERR_PTR(-ENOMEM);
+
+	sha256(data, len, hash);
+	return hash;
+}
+
+int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start,
+			 size_t len)
+{
+	struct sha256_ctx sctx;
+	__le32 le32_version = cpu_to_le32(version);
+
+	if (!aa_g_hash_policy)
+		return 0;
+
+	profile->hash = kzalloc(SHA256_DIGEST_SIZE, GFP_KERNEL);
+	if (!profile->hash)
+		return -ENOMEM;
+
+	sha256_init(&sctx);
+	sha256_update(&sctx, (u8 *)&le32_version, 4);
+	sha256_update(&sctx, (u8 *)start, len);
+	sha256_final(&sctx, profile->hash);
+	return 0;
+}
+
+int __init init_profile_hash(void)
+{
+	if (apparmor_initialized)
+		aa_info_message("AppArmor sha256 policy hashing enabled");
+	return 0;
+}
diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c
new file mode 100644
index 000000000..af9e8431e
--- /dev/null
+++ b/security/apparmor/domain.c
@@ -0,0 +1,1663 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy attachment and domain transitions
+ *
+ * Copyright (C) 2002-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/syscalls.h>
+#include <linux/personality.h>
+#include <linux/xattr.h>
+#include <linux/user_namespace.h>
+
+#include "include/audit.h"
+#include "include/apparmorfs.h"
+#include "include/cred.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/ipc.h"
+#include "include/lib.h"
+#include "include/match.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+
+static const char * const CONFLICTING_ATTACH_STR = "conflicting profile attachments";
+static const char * const CONFLICTING_ATTACH_STR_IX =
+	"conflicting profile attachments - ix fallback";
+static const char * const CONFLICTING_ATTACH_STR_UX =
+	"conflicting profile attachments - ux fallback";
+
+/**
+ * may_change_ptraced_domain - check if can change profile on ptraced task
+ * @to_cred: cred of task changing domain
+ * @to_label: profile to change to  (NOT NULL)
+ * @info: message if there is an error
+ *
+ * Check if current is ptraced and if so if the tracing task is allowed
+ * to trace the new domain
+ *
+ * Returns: %0 or error if change not allowed
+ */
+static int may_change_ptraced_domain(const struct cred *to_cred,
+				     struct aa_label *to_label,
+				     const char **info)
+{
+	struct task_struct *tracer;
+	struct aa_label *tracerl = NULL;
+	const struct cred *tracer_cred = NULL;
+
+	int error = 0;
+
+	rcu_read_lock();
+	tracer = ptrace_parent(current);
+	if (tracer) {
+		/* released below */
+		tracerl = aa_get_task_label(tracer);
+		tracer_cred = get_task_cred(tracer);
+	}
+	/* not ptraced */
+	if (!tracer || unconfined(tracerl))
+		goto out;
+
+	error = aa_may_ptrace(tracer_cred, tracerl, to_cred, to_label,
+			      PTRACE_MODE_ATTACH);
+
+out:
+	rcu_read_unlock();
+	aa_put_label(tracerl);
+	put_cred(tracer_cred);
+
+	if (error)
+		*info = "ptrace prevents transition";
+	return error;
+}
+
+/**** TODO: dedup to aa_label_match - needs perm and dfa, merging
+ * specifically this is an exact copy of aa_label_match except
+ * aa_compute_perms is replaced with aa_compute_fperms
+ * and policy->dfa with file->dfa
+ ****/
+/* match a profile and its associated ns component if needed
+ * Assumes visibility test has already been done.
+ * If a subns profile is not to be matched should be prescreened with
+ * visibility test.
+ */
+static inline aa_state_t match_component(const struct aa_profile *profile,
+					 const struct aa_profile *tp,
+					 bool stack, aa_state_t state)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	const char *ns_name;
+
+	if (stack)
+		state = aa_dfa_match(rules->file->dfa, state, "&");
+	if (profile->ns == tp->ns)
+		return aa_dfa_match(rules->file->dfa, state, tp->base.hname);
+
+	/* try matching with namespace name and then profile */
+	ns_name = aa_ns_name(profile->ns, tp->ns, true);
+	state = aa_dfa_match_len(rules->file->dfa, state, ":", 1);
+	state = aa_dfa_match(rules->file->dfa, state, ns_name);
+	state = aa_dfa_match_len(rules->file->dfa, state, ":", 1);
+	return aa_dfa_match(rules->file->dfa, state, tp->base.hname);
+}
+
+/**
+ * label_compound_match - find perms for full compound label
+ * @profile: profile to find perms for
+ * @label: label to check access permissions for
+ * @stack: whether this is a stacking request
+ * @state: state to start match in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permissions to request
+ * @perms: perms struct to set
+ *
+ * Returns: 0 on success else ERROR
+ *
+ * For the label A//&B//&C this does the perm match for A//&B//&C
+ * @perms should be preinitialized with allperms OR a previous permission
+ *        check to be stacked.
+ */
+static int label_compound_match(const struct aa_profile *profile,
+				struct aa_label *label, bool stack,
+				aa_state_t state, bool inview, u32 request,
+				struct aa_perms *perms)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_profile *tp;
+	struct label_it i;
+	struct path_cond cond = { };
+
+	/* find first subcomponent that is in view and going to be interacted with */
+	label_for_each(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, tp, stack, state);
+		if (!state)
+			goto fail;
+		goto next;
+	}
+
+	/* no component visible */
+	*perms = allperms;
+	return 0;
+
+next:
+	label_for_each_cont(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = aa_dfa_match(rules->file->dfa, state, "//&");
+		state = match_component(profile, tp, false, state);
+		if (!state)
+			goto fail;
+	}
+	*perms = *(aa_lookup_condperms(current_fsuid(), rules->file, state,
+				       &cond));
+	aa_apply_modes_to_perms(profile, perms);
+	if ((perms->allow & request) != request)
+		return -EACCES;
+
+	return 0;
+
+fail:
+	*perms = nullperms;
+	return -EACCES;
+}
+
+/**
+ * label_components_match - find perms for all subcomponents of a label
+ * @profile: profile to find perms for
+ * @label: label to check access permissions for
+ * @stack: whether this is a stacking request
+ * @start: state to start match in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permissions to request
+ * @perms: an initialized perms struct to add accumulation to
+ *
+ * Returns: 0 on success else ERROR
+ *
+ * For the label A//&B//&C this does the perm match for each of A and B and C
+ * @perms should be preinitialized with allperms OR a previous permission
+ *        check to be stacked.
+ */
+static int label_components_match(const struct aa_profile *profile,
+				  struct aa_label *label, bool stack,
+				  aa_state_t start, bool inview, u32 request,
+				  struct aa_perms *perms)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_profile *tp;
+	struct label_it i;
+	struct aa_perms tmp;
+	struct path_cond cond = { };
+	aa_state_t state = 0;
+
+	/* find first subcomponent to test */
+	label_for_each(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, tp, stack, start);
+		if (!state)
+			goto fail;
+		goto next;
+	}
+
+	/* no subcomponents visible - no change in perms */
+	return 0;
+
+next:
+	tmp = *(aa_lookup_condperms(current_fsuid(), rules->file, state,
+				    &cond));
+	aa_apply_modes_to_perms(profile, &tmp);
+	aa_perms_accum(perms, &tmp);
+	label_for_each_cont(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, tp, stack, start);
+		if (!state)
+			goto fail;
+		tmp = *(aa_lookup_condperms(current_fsuid(), rules->file, state,
+					    &cond));
+		aa_apply_modes_to_perms(profile, &tmp);
+		aa_perms_accum(perms, &tmp);
+	}
+
+	if ((perms->allow & request) != request)
+		return -EACCES;
+
+	return 0;
+
+fail:
+	*perms = nullperms;
+	return -EACCES;
+}
+
+/**
+ * label_match - do a multi-component label match
+ * @profile: profile to match against (NOT NULL)
+ * @label: label to match (NOT NULL)
+ * @stack: whether this is a stacking request
+ * @state: state to start in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permission request
+ * @perms: Returns computed perms (NOT NULL)
+ *
+ * Returns: the state the match finished in, may be the none matching state
+ */
+static int label_match(const struct aa_profile *profile, struct aa_label *label,
+		       bool stack, aa_state_t state, bool inview, u32 request,
+		       struct aa_perms *perms)
+{
+	int error;
+
+	*perms = nullperms;
+	error = label_compound_match(profile, label, stack, state, inview,
+				     request, perms);
+	if (!error)
+		return error;
+
+	*perms = allperms;
+	return label_components_match(profile, label, stack, state, inview,
+				      request, perms);
+}
+
+/******* end TODO: dedup *****/
+
+/**
+ * change_profile_perms - find permissions for change_profile
+ * @profile: the current profile  (NOT NULL)
+ * @target: label to transition to (NOT NULL)
+ * @stack: whether this is a stacking request
+ * @request: requested perms
+ * @start: state to start matching in
+ * @perms: Returns computed perms (NOT NULL)
+ *
+ *
+ * Returns: permission set
+ *
+ * currently only matches full label A//&B//&C or individual components A, B, C
+ * not arbitrary combinations. Eg. A//&B, C
+ */
+static int change_profile_perms(const struct aa_profile *profile,
+				struct aa_label *target, bool stack,
+				u32 request, aa_state_t start,
+				struct aa_perms *perms)
+{
+	if (profile_unconfined(profile)) {
+		perms->allow = AA_MAY_CHANGE_PROFILE | AA_MAY_ONEXEC;
+		perms->audit = perms->quiet = perms->kill = 0;
+		return 0;
+	}
+
+	/* TODO: add profile in ns screening */
+	return label_match(profile, target, stack, start, true, request, perms);
+}
+
+/**
+ * aa_xattrs_match - check whether a file matches the xattrs defined in profile
+ * @path: path for file being matched (NOT NULL)
+ * @profile: profile to match against (NOT NULL)
+ * @state: state to start match in
+ *
+ * Returns: number of extended attributes that matched, or < 0 on error
+ */
+static int aa_xattrs_match(const struct path *path,
+			   const struct aa_profile *profile, aa_state_t state)
+{
+	AA_BUG(!path);
+	AA_BUG(!profile);
+
+	int i;
+	struct dentry *d;
+	char *value = NULL;
+	const struct aa_attachment *attach = &profile->attach;
+	int size, value_size = 0, ret = attach->xattr_count;
+
+	if (!attach->xattr_count)
+		return 0;
+	might_sleep();
+
+	/* transition from exec match to xattr set */
+	state = aa_dfa_outofband_transition(attach->xmatch->dfa, state);
+	d = path->dentry;
+
+	for (i = 0; i < attach->xattr_count; i++) {
+		size = vfs_getxattr_alloc(&nop_mnt_idmap, d, attach->xattrs[i],
+					  &value, value_size, GFP_KERNEL);
+		if (size >= 0) {
+			struct aa_perms *perms;
+
+			/*
+			 * Check the xattr presence before value. This ensure
+			 * that not present xattr can be distinguished from a 0
+			 * length value or rule that matches any value
+			 */
+			state = aa_dfa_null_transition(attach->xmatch->dfa,
+						       state);
+			/* Check xattr value */
+			state = aa_dfa_match_len(attach->xmatch->dfa, state,
+						 value, size);
+			perms = aa_lookup_perms(attach->xmatch, state);
+			if (!(perms->allow & MAY_EXEC)) {
+				ret = -EINVAL;
+				goto out;
+			}
+		}
+		/* transition to next element */
+		state = aa_dfa_outofband_transition(attach->xmatch->dfa, state);
+		if (size < 0) {
+			/*
+			 * No xattr match, so verify if transition to
+			 * next element was valid. IFF so the xattr
+			 * was optional.
+			 */
+			if (!state) {
+				ret = -EINVAL;
+				goto out;
+			}
+			/* don't count missing optional xattr as matched */
+			ret--;
+		}
+	}
+
+out:
+	kfree(value);
+	return ret;
+}
+
+/**
+ * find_attach - do attachment search for unconfined processes
+ * @path: path of file in question (NOT NULL)
+ * @ns: the current namespace  (NOT NULL)
+ * @head: profile list to walk  (NOT NULL)
+ * @name: to match against  (NOT NULL)
+ * @info: info message if there was an error (NOT NULL)
+ *
+ * Do a linear search on the profiles in the list.  There is a matching
+ * preference where an exact match is preferred over a name which uses
+ * expressions to match, and matching expressions with the greatest
+ * xmatch_len are preferred.
+ *
+ * Requires: @head not be shared or have appropriate locks held
+ *
+ * Returns: label or NULL if no match found
+ */
+static struct aa_label *find_attach(const struct path *path,
+				    struct aa_ns *ns, struct list_head *head,
+				    const char *name, const char **info)
+{
+	int candidate_len = 0, candidate_xattrs = 0;
+	bool conflict = false;
+	struct aa_profile *profile, *candidate = NULL;
+
+	AA_BUG(!path);
+	AA_BUG(!name);
+	AA_BUG(!head);
+
+	rcu_read_lock();
+restart:
+	list_for_each_entry_rcu(profile, head, base.list) {
+		struct aa_attachment *attach = &profile->attach;
+
+		if (profile->label.flags & FLAG_NULL &&
+		    &profile->label == ns_unconfined(profile->ns))
+			continue;
+
+		/* Find the "best" matching profile. Profiles must
+		 * match the path and extended attributes (if any)
+		 * associated with the file. A more specific path
+		 * match will be preferred over a less specific one,
+		 * and a match with more matching extended attributes
+		 * will be preferred over one with fewer. If the best
+		 * match has both the same level of path specificity
+		 * and the same number of matching extended attributes
+		 * as another profile, signal a conflict and refuse to
+		 * match.
+		 */
+		if (attach->xmatch->dfa) {
+			unsigned int count;
+			aa_state_t state;
+			struct aa_perms *perms;
+
+			state = aa_dfa_leftmatch(attach->xmatch->dfa,
+					attach->xmatch->start[AA_CLASS_XMATCH],
+					name, &count);
+			perms = aa_lookup_perms(attach->xmatch, state);
+			/* any accepting state means a valid match. */
+			if (perms->allow & MAY_EXEC) {
+				int ret = 0;
+
+				if (count < candidate_len)
+					continue;
+
+				if (attach->xattr_count) {
+					long rev = READ_ONCE(ns->revision);
+
+					if (!aa_get_profile_not0(profile))
+						goto restart;
+					rcu_read_unlock();
+					ret = aa_xattrs_match(path, profile,
+							      state);
+					rcu_read_lock();
+					aa_put_profile(profile);
+					if (rev !=
+					    READ_ONCE(ns->revision))
+						/* policy changed */
+						goto restart;
+					/*
+					 * Fail matching if the xattrs don't
+					 * match
+					 */
+					if (ret < 0)
+						continue;
+				}
+				/*
+				 * TODO: allow for more flexible best match
+				 *
+				 * The new match isn't more specific
+				 * than the current best match
+				 */
+				if (count == candidate_len &&
+				    ret <= candidate_xattrs) {
+					/* Match is equivalent, so conflict */
+					if (ret == candidate_xattrs)
+						conflict = true;
+					continue;
+				}
+
+				/* Either the same length with more matching
+				 * xattrs, or a longer match
+				 */
+				candidate = profile;
+				candidate_len = max(count, attach->xmatch_len);
+				candidate_xattrs = ret;
+				conflict = false;
+			}
+		} else if (!strcmp(profile->base.name, name)) {
+			/*
+			 * old exact non-re match, without conditionals such
+			 * as xattrs. no more searching required
+			 */
+			candidate = profile;
+			goto out;
+		}
+	}
+
+	if (!candidate || conflict) {
+		if (conflict)
+			*info = CONFLICTING_ATTACH_STR;
+		rcu_read_unlock();
+		return NULL;
+	}
+
+out:
+	candidate = aa_get_newest_profile(candidate);
+	rcu_read_unlock();
+
+	return &candidate->label;
+}
+
+static const char *next_name(int xtype, const char *name)
+{
+	return NULL;
+}
+
+/**
+ * x_table_lookup - lookup an x transition name via transition table
+ * @profile: current profile (NOT NULL)
+ * @xindex: index into x transition table
+ * @name: returns: name tested to find label (NOT NULL)
+ *
+ * Returns: refcounted label, or NULL on failure (MAYBE NULL)
+ *          @name will always be set with the last name tried
+ */
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+				const char **name)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_label *label = NULL;
+	u32 xtype = xindex & AA_X_TYPE_MASK;
+	int index = xindex & AA_X_INDEX_MASK;
+	const char *next;
+
+	AA_BUG(!name);
+
+	/* index is guaranteed to be in range, validated at load time */
+	/* TODO: move lookup parsing to unpack time so this is a straight
+	 *       index into the resultant label
+	 */
+	for (next = rules->file->trans.table[index].strs; next;
+	     next = next_name(xtype, next)) {
+		const char *lookup = (*next == '&') ? next + 1 : next;
+		*name = next;
+		if (xindex & AA_X_CHILD) {
+			/* TODO: switich to parse to get stack of child */
+			struct aa_profile *new = aa_find_child(profile, lookup);
+
+			if (new)
+				/* release by caller */
+				return &new->label;
+			continue;
+		}
+		label = aa_label_parse(&profile->label, lookup, GFP_KERNEL,
+				       true, false);
+		if (!IS_ERR_OR_NULL(label))
+			/* release by caller */
+			return label;
+	}
+
+	return NULL;
+}
+
+/**
+ * x_to_label - get target label for a given xindex
+ * @profile: current profile  (NOT NULL)
+ * @path: path of file in question
+ * @name: name to lookup (NOT NULL)
+ * @xindex: index into x transition table
+ * @lookupname: returns: name used in lookup if one was specified (NOT NULL)
+ * @info: info message if there was an error (NOT NULL)
+ *
+ * find label for a transition index
+ *
+ * Returns: refcounted label or NULL if not found available
+ */
+static struct aa_label *x_to_label(struct aa_profile *profile,
+				   const struct path *path,
+				   const char *name, u32 xindex,
+				   const char **lookupname,
+				   const char **info)
+{
+	struct aa_label *new = NULL;
+	struct aa_label *stack = NULL;
+	struct aa_ns *ns = profile->ns;
+	u32 xtype = xindex & AA_X_TYPE_MASK;
+	/* Used for info checks during fallback handling */
+	const char *old_info = NULL;
+
+	switch (xtype) {
+	case AA_X_NONE:
+		/* fail exec unless ix || ux fallback - handled by caller */
+		*lookupname = NULL;
+		break;
+	case AA_X_TABLE:
+		/* TODO: fix when perm mapping done at unload */
+		/* released by caller
+		 * if null for both stack and direct want to try fallback
+		 */
+		new = x_table_lookup(profile, xindex, lookupname);
+		if (!new || **lookupname != '&')
+			break;
+		stack = new;
+		new = NULL;
+		fallthrough;	/* to X_NAME */
+	case AA_X_NAME:
+		if (xindex & AA_X_CHILD)
+			/* released by caller */
+			new = find_attach(path, ns, &profile->base.profiles,
+					  name, info);
+		else
+			/* released by caller */
+			new = find_attach(path, ns, &ns->base.profiles,
+					  name, info);
+		*lookupname = name;
+		break;
+	}
+
+	/* fallback transition check */
+	if (!new) {
+		if (xindex & AA_X_INHERIT) {
+			/* (p|c|n)ix - don't change profile but do
+			 * use the newest version
+			 */
+			if (*info == CONFLICTING_ATTACH_STR) {
+				*info = CONFLICTING_ATTACH_STR_IX;
+			} else {
+				old_info = *info;
+				*info = "ix fallback";
+			}
+			/* no profile && no error */
+			new = aa_get_newest_label(&profile->label);
+		} else if (xindex & AA_X_UNCONFINED) {
+			new = aa_get_newest_label(ns_unconfined(profile->ns));
+			if (*info == CONFLICTING_ATTACH_STR) {
+				*info = CONFLICTING_ATTACH_STR_UX;
+			} else {
+				old_info = *info;
+				*info = "ux fallback";
+			}
+		}
+		/* We set old_info on the code paths above where overwriting
+		 * could have happened, so now check if info was set by
+		 * find_attach as well (i.e. whether we actually overwrote)
+		 * and warn accordingly.
+		 */
+		if (old_info && old_info != CONFLICTING_ATTACH_STR) {
+			pr_warn_ratelimited(
+				"AppArmor: find_attach (from profile %s) audit info \"%s\" dropped",
+				profile->base.hname, old_info);
+		}
+	}
+
+	if (new && stack) {
+		/* base the stack on post domain transition */
+		struct aa_label *base = new;
+
+		new = aa_label_merge(base, stack, GFP_KERNEL);
+		/* null on error */
+		aa_put_label(base);
+	}
+
+	aa_put_label(stack);
+	/* released by caller */
+	return new;
+}
+
+static struct aa_label *profile_transition(const struct cred *subj_cred,
+					   struct aa_profile *profile,
+					   const struct linux_binprm *bprm,
+					   char *buffer, struct path_cond *cond,
+					   bool *secure_exec)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_label *new = NULL;
+	struct aa_profile *new_profile = NULL;
+	const char *info = NULL, *name = NULL, *target = NULL;
+	aa_state_t state = rules->file->start[AA_CLASS_FILE];
+	struct aa_perms perms = {};
+	bool nonewprivs = false;
+	int error = 0;
+
+	AA_BUG(!profile);
+	AA_BUG(!bprm);
+	AA_BUG(!buffer);
+
+	error = aa_path_name(&bprm->file->f_path, profile->path_flags, buffer,
+			     &name, &info, profile->disconnected);
+	if (error) {
+		if (profile_unconfined(profile) ||
+		    (profile->label.flags & FLAG_IX_ON_NAME_ERROR)) {
+			AA_DEBUG(DEBUG_DOMAIN, "name lookup ix on error");
+			error = 0;
+			new = aa_get_newest_label(&profile->label);
+		}
+		name = bprm->filename;
+		goto audit;
+	}
+
+	if (profile_unconfined(profile)) {
+		new = find_attach(&bprm->file->f_path, profile->ns,
+				  &profile->ns->base.profiles, name, &info);
+		/* info set -> something unusual that we should report
+		 * Currently this is only conflicting attachments, but other
+		 * infos added in the future should also be logged by default
+		 * and only excluded on a case-by-case basis
+		 */
+		if (info) {
+			/* Because perms is never used again after this audit
+			 * we don't need to care about clobbering it
+			 */
+			perms.audit |= MAY_EXEC;
+			perms.allow |= MAY_EXEC;
+			/* Don't cause error if auditing fails */
+			(void) aa_audit_file(subj_cred, profile, &perms,
+				OP_EXEC, MAY_EXEC, name, target, new, cond->uid,
+				info, error);
+		}
+		if (new) {
+			AA_DEBUG(DEBUG_DOMAIN, "unconfined attached to new label");
+			return new;
+		}
+		AA_DEBUG(DEBUG_DOMAIN, "unconfined exec no attachment");
+		return aa_get_newest_label(&profile->label);
+	}
+
+	/* find exec permissions for name */
+	state = aa_str_perms(rules->file, state, name, cond, &perms);
+	if (perms.allow & MAY_EXEC) {
+		/* exec permission determine how to transition */
+		new = x_to_label(profile, &bprm->file->f_path, name,
+				 perms.xindex, &target, &info);
+		if (new && new->proxy == profile->label.proxy && info) {
+			/* Force audit on conflicting attachment fallback
+			 * Because perms is never used again after this audit
+			 * we don't need to care about clobbering it
+			 */
+			if (info == CONFLICTING_ATTACH_STR_IX
+			    || info == CONFLICTING_ATTACH_STR_UX)
+				perms.audit |= MAY_EXEC;
+			/* hack ix fallback - improve how this is detected */
+			goto audit;
+		} else if (!new) {
+			if (info) {
+				pr_warn_ratelimited(
+					"AppArmor: %s (from profile %s) audit info \"%s\" dropped on missing transition",
+					__func__, profile->base.hname, info);
+			}
+			info = "profile transition not found";
+			/* remove MAY_EXEC to audit as failure or complaint */
+			perms.allow &= ~MAY_EXEC;
+			if (COMPLAIN_MODE(profile)) {
+				/* create null profile instead of failing */
+				goto create_learning_profile;
+			}
+			error = -EACCES;
+		}
+	} else if (COMPLAIN_MODE(profile)) {
+create_learning_profile:
+		/* no exec permission - learning mode */
+		new_profile = aa_new_learning_profile(profile, false, name,
+						      GFP_KERNEL);
+		if (!new_profile) {
+			error = -ENOMEM;
+			info = "could not create null profile";
+		} else {
+			error = -EACCES;
+			new = &new_profile->label;
+		}
+		perms.xindex |= AA_X_UNSAFE;
+	} else
+		/* fail exec */
+		error = -EACCES;
+
+	if (!new)
+		goto audit;
+
+
+	if (!(perms.xindex & AA_X_UNSAFE)) {
+		if (DEBUG_ON) {
+			dbg_printk("apparmor: setting AT_SECURE for %s profile=",
+				   name);
+			aa_label_printk(new, GFP_KERNEL);
+			dbg_printk("\n");
+		}
+		*secure_exec = true;
+	}
+
+audit:
+	aa_audit_file(subj_cred, profile, &perms, OP_EXEC, MAY_EXEC, name,
+		      target, new,
+		      cond->uid, info, error);
+	if (!new || nonewprivs) {
+		aa_put_label(new);
+		return ERR_PTR(error);
+	}
+
+	return new;
+}
+
+static int profile_onexec(const struct cred *subj_cred,
+			  struct aa_profile *profile, struct aa_label *onexec,
+			  bool stack, const struct linux_binprm *bprm,
+			  char *buffer, struct path_cond *cond,
+			  bool *secure_exec)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	aa_state_t state = rules->file->start[AA_CLASS_FILE];
+	struct aa_perms perms = {};
+	const char *xname = NULL, *info = "change_profile onexec";
+	int error = -EACCES;
+
+	AA_BUG(!profile);
+	AA_BUG(!onexec);
+	AA_BUG(!bprm);
+	AA_BUG(!buffer);
+
+	if (profile_unconfined(profile)) {
+		/* change_profile on exec already granted */
+		/*
+		 * NOTE: Domain transitions from unconfined are allowed
+		 * even when no_new_privs is set because this always results
+		 * in a further reduction of permissions.
+		 */
+		return 0;
+	}
+
+	error = aa_path_name(&bprm->file->f_path, profile->path_flags, buffer,
+			     &xname, &info, profile->disconnected);
+	if (error) {
+		if (profile_unconfined(profile) ||
+		    (profile->label.flags & FLAG_IX_ON_NAME_ERROR)) {
+			AA_DEBUG(DEBUG_DOMAIN, "name lookup ix on error");
+			error = 0;
+		}
+		xname = bprm->filename;
+		goto audit;
+	}
+
+	/* find exec permissions for name */
+	state = aa_str_perms(rules->file, state, xname, cond, &perms);
+	if (!(perms.allow & AA_MAY_ONEXEC)) {
+		info = "no change_onexec valid for executable";
+		goto audit;
+	}
+	/* test if this exec can be paired with change_profile onexec.
+	 * onexec permission is linked to exec with a standard pairing
+	 * exec\0change_profile
+	 */
+	state = aa_dfa_null_transition(rules->file->dfa, state);
+	error = change_profile_perms(profile, onexec, stack, AA_MAY_ONEXEC,
+				     state, &perms);
+	if (error) {
+		perms.allow &= ~AA_MAY_ONEXEC;
+		goto audit;
+	}
+
+	if (!(perms.xindex & AA_X_UNSAFE)) {
+		if (DEBUG_ON) {
+			dbg_printk("apparmor: setting AT_SECURE for %s label=",
+				   xname);
+			aa_label_printk(onexec, GFP_KERNEL);
+			dbg_printk("\n");
+		}
+		*secure_exec = true;
+	}
+
+audit:
+	return aa_audit_file(subj_cred, profile, &perms, OP_EXEC,
+			     AA_MAY_ONEXEC, xname,
+			     NULL, onexec, cond->uid, info, error);
+}
+
+/* ensure none ns domain transitions are correctly applied with onexec */
+static struct aa_label *label_merge_wrap(struct aa_label *a, struct aa_label *b,
+					 gfp_t gfp)
+{
+	struct aa_label *label = aa_label_merge(a, b, gfp);
+
+	if (!label)
+		return ERR_PTR(-ENOMEM);
+	return label;
+}
+
+static bool is_profile_priv_restricted_to_stack(const struct cred *subj_cred,
+						struct aa_profile *profile)
+{
+	if (profile_unconfined(profile) && profile == profile->ns->unconfined &&
+	    aa_unprivileged_unconfined_restricted &&
+	    /* cap_capable returns false (0) if true, hence true here means
+	     * doesn't have capability and the stack will be restricted
+	     */
+	    cap_capable(current_cred(), &init_user_ns, CAP_MAC_OVERRIDE,
+			CAP_OPT_NOAUDIT))
+		return true;
+	return false;
+}
+
+static const char *stack_msg = "change_profile unprivileged unconfined converted to stacking";
+
+static struct aa_label *priv_restricted_transition(const struct cred *subj_cred,
+						   struct aa_profile *profile,
+						   const char *op, u32 request,
+						   const char *name,
+						   struct aa_label *transition,
+						   gfp_t gfp)
+{
+	if (!is_profile_priv_restricted_to_stack(subj_cred, profile))
+		return aa_get_newest_label(transition);
+
+	/* transition allowed but only via stack */
+	struct aa_label *target = label_merge_wrap(&profile->label,
+						      transition, gfp);
+	if (IS_ERR_OR_NULL(target))
+		return target;
+
+	/* doing this here is less than optimal but good enough until the
+	 * fs mediation rework lands
+	 */
+	struct aa_perms perms = {
+		.allow = request,
+		.audit = request,
+	};
+	aa_audit_file(subj_cred, profile, &perms, op,
+		      request, name, NULL, target,
+		      subj_cred->euid, stack_msg, 0);
+
+	return target;
+}
+
+static struct aa_label *handle_onexec(const struct cred *subj_cred,
+				      struct aa_label *label,
+				      struct aa_label *onexec, bool stack,
+				      const struct linux_binprm *bprm,
+				      char *buffer, struct path_cond *cond,
+				      bool *unsafe)
+{
+	struct aa_profile *profile;
+	struct aa_label *new;
+	int error;
+
+	AA_BUG(!label);
+	AA_BUG(!onexec);
+	AA_BUG(!bprm);
+	AA_BUG(!buffer);
+
+	/* TODO: determine how much we want to loosen this
+	 * only check profiles in scope for permission to change at exec
+	 */
+	error = fn_for_each_in_scope(label, profile,
+			profile_onexec(subj_cred, profile, onexec, stack,
+				       bprm, buffer, cond, unsafe));
+	if (error)
+		return ERR_PTR(error);
+
+	new = fn_label_build_in_scope(label, profile, GFP_KERNEL,
+			stack ? label_merge_wrap(&profile->label, onexec,
+						 GFP_KERNEL)
+			      : priv_restricted_transition(subj_cred, profile,
+						OP_CHANGE_ONEXEC, AA_MAY_ONEXEC,
+						bprm->filename, onexec,
+						GFP_KERNEL),
+			profile_transition(subj_cred, profile, bprm,
+					   buffer, cond, unsafe));
+	AA_BUG(!new);
+	if (!IS_ERR(new))
+		return new;
+
+	/* TODO: get rid of GLOBAL_ROOT_UID */
+	error = fn_for_each_in_scope(label, profile,
+			aa_audit_file(subj_cred, profile, &nullperms,
+				      OP_CHANGE_ONEXEC,
+				      AA_MAY_ONEXEC, bprm->filename, NULL,
+				      onexec, GLOBAL_ROOT_UID,
+				      "failed to build target label",
+				      PTR_ERR(new)));
+	return ERR_PTR(error);
+}
+
+/**
+ * apparmor_bprm_creds_for_exec - Update the new creds on the bprm struct
+ * @bprm: binprm for the exec  (NOT NULL)
+ *
+ * Returns: %0 or error on failure
+ *
+ * TODO: once the other paths are done see if we can't refactor into a fn
+ */
+int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	struct aa_task_ctx *ctx;
+	struct aa_label *label, *new = NULL;
+	const struct cred *subj_cred;
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	const char *info = NULL;
+	int error = 0;
+	bool unsafe = false;
+	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(bprm->file),
+					    file_inode(bprm->file));
+	struct path_cond cond = {
+		vfsuid_into_kuid(vfsuid),
+		file_inode(bprm->file)->i_mode
+	};
+
+	subj_cred = current_cred();
+	ctx = task_ctx(current);
+	AA_BUG(!cred_label(bprm->cred));
+	AA_BUG(!ctx);
+
+	label = aa_get_newest_label(cred_label(bprm->cred));
+
+	/*
+	 * Detect no new privs being set, and store the label it
+	 * occurred under. Ideally this would happen when nnp
+	 * is set but there isn't a good way to do that yet.
+	 *
+	 * Testing for unconfined must be done before the subset test
+	 */
+	if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) && !unconfined(label) &&
+	    !ctx->nnp)
+		ctx->nnp = aa_get_label(label);
+
+	/* buffer freed below, name is pointer into buffer */
+	buffer = aa_get_buffer(false);
+	if (!buffer) {
+		error = -ENOMEM;
+		goto done;
+	}
+
+	/* Test for onexec first as onexec override other x transitions. */
+	if (ctx->onexec)
+		new = handle_onexec(subj_cred, label, ctx->onexec, ctx->token,
+				    bprm, buffer, &cond, &unsafe);
+	else
+		new = fn_label_build(label, profile, GFP_KERNEL,
+				profile_transition(subj_cred, profile, bprm,
+						   buffer,
+						   &cond, &unsafe));
+	AA_BUG(!new);
+	if (IS_ERR(new)) {
+		error = PTR_ERR(new);
+		goto done;
+	}
+
+	/* Policy has specified a domain transitions. If no_new_privs and
+	 * confined ensure the transition is to confinement that is subset
+	 * of the confinement when the task entered no new privs.
+	 *
+	 * NOTE: Domain transitions from unconfined and to stacked
+	 * subsets are allowed even when no_new_privs is set because this
+	 * always results in a further reduction of permissions.
+	 */
+	if ((bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) &&
+	    !unconfined(label) &&
+	    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
+		error = -EPERM;
+		info = "no new privs";
+		goto audit;
+	}
+
+	if (bprm->unsafe & LSM_UNSAFE_SHARE) {
+		/* FIXME: currently don't mediate shared state */
+		;
+	}
+
+	if (bprm->unsafe & (LSM_UNSAFE_PTRACE)) {
+		/* TODO: test needs to be profile of label to new */
+		error = may_change_ptraced_domain(bprm->cred, new, &info);
+		if (error)
+			goto audit;
+	}
+
+	if (unsafe) {
+		if (DEBUG_ON) {
+			dbg_printk("setting AT_SECURE for %s label=",
+				   bprm->filename);
+			aa_label_printk(new, GFP_KERNEL);
+			dbg_printk("\n");
+		}
+		bprm->secureexec = 1;
+	}
+
+	if (label->proxy != new->proxy) {
+		/* when transitioning clear unsafe personality bits */
+		if (DEBUG_ON) {
+			dbg_printk("apparmor: clearing unsafe personality bits. %s label=",
+				   bprm->filename);
+			aa_label_printk(new, GFP_KERNEL);
+			dbg_printk("\n");
+		}
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+	}
+	aa_put_label(cred_label(bprm->cred));
+	/* transfer reference, released when cred is freed */
+	set_cred_label(bprm->cred, new);
+
+done:
+	aa_put_label(label);
+	aa_put_buffer(buffer);
+
+	return error;
+
+audit:
+	error = fn_for_each(label, profile,
+			aa_audit_file(current_cred(), profile, &nullperms,
+				      OP_EXEC, MAY_EXEC,
+				      bprm->filename, NULL, new,
+				      vfsuid_into_kuid(vfsuid), info, error));
+	aa_put_label(new);
+	goto done;
+}
+
+/*
+ * Functions for self directed profile change
+ */
+
+
+/* helper fn for change_hat
+ *
+ * Returns: label for hat transition OR ERR_PTR.  Does NOT return NULL
+ */
+static struct aa_label *build_change_hat(const struct cred *subj_cred,
+					 struct aa_profile *profile,
+					 const char *name, bool sibling)
+{
+	struct aa_profile *root, *hat = NULL;
+	const char *info = NULL;
+	int error = 0;
+
+	if (sibling && PROFILE_IS_HAT(profile)) {
+		root = aa_get_profile_rcu(&profile->parent);
+	} else if (!sibling && !PROFILE_IS_HAT(profile)) {
+		root = aa_get_profile(profile);
+	} else {
+		info = "conflicting target types";
+		error = -EPERM;
+		goto audit;
+	}
+
+	hat = aa_find_child(root, name);
+	if (!hat) {
+		error = -ENOENT;
+		if (COMPLAIN_MODE(profile)) {
+			hat = __aa_new_learning_profile(profile, true, name,
+							GFP_KERNEL);
+			if (!hat) {
+				info = "failed null profile create";
+				error = -ENOMEM;
+			}
+		}
+	}
+	aa_put_profile(root);
+
+audit:
+	aa_audit_file(subj_cred, profile, &nullperms, OP_CHANGE_HAT,
+		      AA_MAY_CHANGEHAT,
+		      name, hat ? hat->base.hname : NULL,
+		      hat ? &hat->label : NULL, GLOBAL_ROOT_UID, info,
+		      error);
+	if (!hat || (error && error != -ENOENT))
+		return ERR_PTR(error);
+	/* if hat && error - complain mode, already audited and we adjust for
+	 * complain mode allow by returning hat->label
+	 */
+	return &hat->label;
+}
+
+/* helper fn for changing into a hat
+ *
+ * Returns: label for hat transition or ERR_PTR. Does not return NULL
+ */
+static struct aa_label *change_hat(const struct cred *subj_cred,
+				   struct aa_label *label, const char *hats[],
+				   int count, int flags)
+{
+	struct aa_profile *profile, *root, *hat = NULL;
+	struct aa_ns *ns, *new_ns;
+	struct aa_label *new;
+	struct label_it it;
+	bool sibling = false;
+	const char *name, *info = NULL;
+	int i, error;
+	bool needput = false;
+
+	AA_BUG(!label);
+	AA_BUG(!hats);
+	AA_BUG(count < 1);
+
+	/*
+	 * Acquire the newest label and then hold the lock until we choose a
+	 * hat, so that profile replacement doesn't atomically truncate the
+	 * list of potential hats. Because we are getting the namespaces from
+	 * the profiles and label, we can rely on the namespaces being live
+	 * and avoid incrementing their refcounts while grabbing the lock.
+	 */
+	ns = labels_ns(label);
+
+retry:
+	mutex_lock_nested(&ns->lock, ns->level);
+	if (label_is_stale(label)) {
+		new = aa_get_newest_label(label);
+		new_ns = labels_ns(new);
+
+		if (needput)
+			/* aa_put_label() is safe to call when under lock */
+			aa_put_label(label);
+		label = new;
+		needput = true;
+		/* check if replaced with label in parent ns, and lock there */
+		if (new_ns != ns) {
+			mutex_unlock(&ns->lock);
+			ns = new_ns;
+			/* retry will bottom out at the root of the tree */
+			goto retry;
+		}
+	}
+
+	if (PROFILE_IS_HAT(labels_profile(label)))
+		sibling = true;
+
+	/*find first matching hat */
+	for (i = 0; i < count && !hat; i++) {
+		name = hats[i];
+		label_for_each_in_scope(it, labels_ns(label), label, profile) {
+			if (sibling && PROFILE_IS_HAT(profile)) {
+				root = aa_get_profile(rcu_dereference_protected(profile->parent,
+						      mutex_is_locked(&ns->lock)));
+			} else if (!sibling && !PROFILE_IS_HAT(profile)) {
+				root = aa_get_profile(profile);
+			} else {	/* conflicting change type */
+				info = "conflicting targets types";
+				error = -EPERM;
+				goto fail;
+			}
+			hat = aa_find_child(root, name);
+			aa_put_profile(root);
+			if (!hat) {
+				if (!COMPLAIN_MODE(profile))
+					goto outer_continue;
+				/* complain mode succeed as if hat */
+			} else if (!PROFILE_IS_HAT(hat)) {
+				info = "target not hat";
+				error = -EPERM;
+				aa_put_profile(hat);
+				goto fail;
+			}
+			aa_put_profile(hat);
+		}
+		/* found a hat for all profiles in ns */
+		goto build;
+outer_continue:
+	;
+	}
+	/* no hats that match, find appropriate error
+	 *
+	 * In complain mode audit of the failure is based off of the first
+	 * hat supplied.  This is done due how userspace interacts with
+	 * change_hat.
+	 */
+	name = NULL;
+	label_for_each_in_scope(it, labels_ns(label), label, profile) {
+		if (!list_empty(&profile->base.profiles)) {
+			info = "hat not found";
+			error = -ENOENT;
+			goto fail;
+		}
+	}
+	info = "no hats defined";
+	error = -ECHILD;
+
+fail:
+	label_for_each_in_scope(it, labels_ns(label), label, profile) {
+		/*
+		 * no target as it has failed to be found or built
+		 *
+		 * change_hat uses probing and should not log failures
+		 * related to missing hats
+		 */
+		/* TODO: get rid of GLOBAL_ROOT_UID */
+		if (count > 1 || COMPLAIN_MODE(profile)) {
+			aa_audit_file(subj_cred, profile, &nullperms,
+				      OP_CHANGE_HAT,
+				      AA_MAY_CHANGEHAT, name, NULL, NULL,
+				      GLOBAL_ROOT_UID, info, error);
+		}
+	}
+	mutex_unlock(&ns->lock);
+	if (needput)
+		aa_put_label(label);
+	return ERR_PTR(error);
+
+build:
+	new = fn_label_build_in_scope(label, profile, GFP_KERNEL,
+				   build_change_hat(subj_cred, profile, name,
+						    sibling),
+				   aa_get_label(&profile->label));
+	mutex_unlock(&ns->lock);
+	AA_BUG(!new);
+	/* return new label or error ptr */
+	if (needput)
+		aa_put_label(label);
+	return new;
+}
+
+/**
+ * aa_change_hat - change hat to/from subprofile
+ * @hats: vector of hat names to try changing into (MAYBE NULL if @count == 0)
+ * @count: number of hat names in @hats
+ * @token: magic value to validate the hat change
+ * @flags: flags affecting behavior of the change
+ *
+ * Returns %0 on success, error otherwise.
+ *
+ * Change to the first profile specified in @hats that exists, and store
+ * the @hat_magic in the current task context.  If the count == 0 and the
+ * @token matches that stored in the current task context, return to the
+ * top level profile.
+ *
+ * change_hat only applies to profiles in the current ns, and each profile
+ * in the ns must make the same transition otherwise change_hat will fail.
+ */
+int aa_change_hat(const char *hats[], int count, u64 token, int flags)
+{
+	const struct cred *subj_cred;
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct aa_label *label, *previous, *new = NULL, *target = NULL;
+	struct aa_profile *profile;
+	struct aa_perms perms = {};
+	const char *info = NULL;
+	int error = 0;
+
+	/* released below */
+	subj_cred = get_current_cred();
+	label = aa_get_newest_cred_label(subj_cred);
+	previous = aa_get_newest_label(ctx->previous);
+
+	/*
+	 * Detect no new privs being set, and store the label it
+	 * occurred under. Ideally this would happen when nnp
+	 * is set but there isn't a good way to do that yet.
+	 *
+	 * Testing for unconfined must be done before the subset test
+	 */
+	if (task_no_new_privs(current) && !unconfined(label) && !ctx->nnp)
+		ctx->nnp = aa_get_label(label);
+
+	/* return -EPERM when unconfined doesn't have children to avoid
+	 * changing the traditional error code for unconfined.
+	 */
+	if (unconfined(label)) {
+		struct label_it i;
+		bool empty = true;
+
+		rcu_read_lock();
+		label_for_each_in_scope(i, labels_ns(label), label, profile) {
+			empty &= list_empty(&profile->base.profiles);
+		}
+		rcu_read_unlock();
+
+		if (empty) {
+			info = "unconfined can not change_hat";
+			error = -EPERM;
+			goto fail;
+		}
+	}
+
+	if (count) {
+		new = change_hat(subj_cred, label, hats, count, flags);
+		AA_BUG(!new);
+		if (IS_ERR(new)) {
+			error = PTR_ERR(new);
+			new = NULL;
+			/* already audited */
+			goto out;
+		}
+
+		/* target cred is the same as current except new label */
+		error = may_change_ptraced_domain(subj_cred, new, &info);
+		if (error)
+			goto fail;
+
+		/*
+		 * no new privs prevents domain transitions that would
+		 * reduce restrictions.
+		 */
+		if (task_no_new_privs(current) && !unconfined(label) &&
+		    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
+			/* not an apparmor denial per se, so don't log it */
+			AA_DEBUG(DEBUG_DOMAIN,
+				 "no_new_privs - change_hat denied");
+			error = -EPERM;
+			goto out;
+		}
+
+		if (flags & AA_CHANGE_TEST)
+			goto out;
+
+		target = new;
+		error = aa_set_current_hat(new, token);
+		if (error == -EACCES)
+			/* kill task in case of brute force attacks */
+			goto kill;
+	} else if (previous && !(flags & AA_CHANGE_TEST)) {
+		/*
+		 * no new privs prevents domain transitions that would
+		 * reduce restrictions.
+		 */
+		if (task_no_new_privs(current) && !unconfined(label) &&
+		    !aa_label_is_unconfined_subset(previous, ctx->nnp)) {
+			/* not an apparmor denial per se, so don't log it */
+			AA_DEBUG(DEBUG_DOMAIN,
+				 "no_new_privs - change_hat denied");
+			error = -EPERM;
+			goto out;
+		}
+
+		/* Return to saved label.  Kill task if restore fails
+		 * to avoid brute force attacks
+		 */
+		target = previous;
+		error = aa_restore_previous_label(token);
+		if (error) {
+			if (error == -EACCES)
+				goto kill;
+			goto fail;
+		}
+	} /* else ignore @flags && restores when there is no saved profile */
+
+out:
+	aa_put_label(new);
+	aa_put_label(previous);
+	aa_put_label(label);
+	put_cred(subj_cred);
+
+	return error;
+
+kill:
+	info = "failed token match";
+	perms.kill = AA_MAY_CHANGEHAT;
+
+fail:
+	fn_for_each_in_scope(label, profile,
+		aa_audit_file(subj_cred, profile, &perms, OP_CHANGE_HAT,
+			      AA_MAY_CHANGEHAT, NULL, NULL, target,
+			      GLOBAL_ROOT_UID, info, error));
+
+	goto out;
+}
+
+
+static int change_profile_perms_wrapper(const char *op, const char *name,
+					const struct cred *subj_cred,
+					struct aa_profile *profile,
+					struct aa_label *target, bool stack,
+					u32 request, struct aa_perms *perms)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	const char *info = NULL;
+	int error = 0;
+
+	if (!error)
+		error = change_profile_perms(profile, target, stack, request,
+					     rules->file->start[AA_CLASS_FILE],
+					     perms);
+	if (error)
+		error = aa_audit_file(subj_cred, profile, perms, op, request,
+				      name,
+				      NULL, target, GLOBAL_ROOT_UID, info,
+				      error);
+
+	return error;
+}
+
+/**
+ * aa_change_profile - perform a one-way profile transition
+ * @fqname: name of profile may include namespace (NOT NULL)
+ * @flags: flags affecting change behavior
+ *
+ * Change to new profile @name.  Unlike with hats, there is no way
+ * to change back.  If @name isn't specified the current profile name is
+ * used.
+ * If @onexec then the transition is delayed until
+ * the next exec.
+ *
+ * Returns %0 on success, error otherwise.
+ */
+int aa_change_profile(const char *fqname, int flags)
+{
+	struct aa_label *label, *new = NULL, *target = NULL;
+	struct aa_profile *profile;
+	struct aa_perms perms = {};
+	const char *info = NULL;
+	const char *auditname = fqname;		/* retain leading & if stack */
+	bool stack = flags & AA_CHANGE_STACK;
+	struct aa_task_ctx *ctx = task_ctx(current);
+	const struct cred *subj_cred = get_current_cred();
+	int error = 0;
+	char *op;
+	u32 request;
+
+	label = aa_get_current_label();
+
+	/*
+	 * Detect no new privs being set, and store the label it
+	 * occurred under. Ideally this would happen when nnp
+	 * is set but there isn't a good way to do that yet.
+	 *
+	 * Testing for unconfined must be done before the subset test
+	 */
+	if (task_no_new_privs(current) && !unconfined(label) && !ctx->nnp)
+		ctx->nnp = aa_get_label(label);
+
+	if (!fqname || !*fqname) {
+		aa_put_label(label);
+		AA_DEBUG(DEBUG_DOMAIN, "no profile name");
+		return -EINVAL;
+	}
+
+	if (flags & AA_CHANGE_ONEXEC) {
+		request = AA_MAY_ONEXEC;
+		if (stack)
+			op = OP_STACK_ONEXEC;
+		else
+			op = OP_CHANGE_ONEXEC;
+	} else {
+		request = AA_MAY_CHANGE_PROFILE;
+		if (stack)
+			op = OP_STACK;
+		else
+			op = OP_CHANGE_PROFILE;
+	}
+
+	if (*fqname == '&') {
+		stack = true;
+		/* don't have label_parse() do stacking */
+		fqname++;
+	}
+	target = aa_label_parse(label, fqname, GFP_KERNEL, true, false);
+	if (IS_ERR(target)) {
+		struct aa_profile *tprofile;
+
+		info = "label not found";
+		error = PTR_ERR(target);
+		target = NULL;
+		/*
+		 * TODO: fixme using labels_profile is not right - do profile
+		 * per complain profile
+		 */
+		if ((flags & AA_CHANGE_TEST) ||
+		    !COMPLAIN_MODE(labels_profile(label)))
+			goto audit;
+		/* released below */
+		tprofile = aa_new_learning_profile(labels_profile(label), false,
+						   fqname, GFP_KERNEL);
+		if (!tprofile) {
+			info = "failed null profile create";
+			error = -ENOMEM;
+			goto audit;
+		}
+		target = &tprofile->label;
+		goto check;
+	}
+
+	/*
+	 * self directed transitions only apply to current policy ns
+	 * TODO: currently requiring perms for stacking and straight change
+	 *       stacking doesn't strictly need this. Determine how much
+	 *       we want to loosen this restriction for stacking
+	 *
+	 * if (!stack) {
+	 */
+	error = fn_for_each_in_scope(label, profile,
+			change_profile_perms_wrapper(op, auditname,
+						     subj_cred,
+						     profile, target, stack,
+						     request, &perms));
+	if (error)
+		/* auditing done in change_profile_perms_wrapper */
+		goto out;
+
+	/* } */
+
+check:
+	/* check if tracing task is allowed to trace target domain */
+	error = may_change_ptraced_domain(subj_cred, target, &info);
+	if (error && !fn_for_each_in_scope(label, profile,
+					COMPLAIN_MODE(profile)))
+		goto audit;
+
+	/* TODO: add permission check to allow this
+	 * if ((flags & AA_CHANGE_ONEXEC) && !current_is_single_threaded()) {
+	 *      info = "not a single threaded task";
+	 *      error = -EACCES;
+	 *      goto audit;
+	 * }
+	 */
+	if (flags & AA_CHANGE_TEST)
+		goto out;
+
+	/* stacking is always a subset, so only check the nonstack case */
+	if (!stack) {
+		new = fn_label_build_in_scope(label, profile, GFP_KERNEL,
+				priv_restricted_transition(subj_cred, profile,
+							   op, request,
+							   auditname, target,
+							   GFP_KERNEL),
+					   aa_get_label(&profile->label));
+		AA_BUG(!new);
+		if (IS_ERR(new))
+			goto build_fail;
+		/*
+		 * no new privs prevents domain transitions that would
+		 * reduce restrictions.
+		 */
+		if (task_no_new_privs(current) && !unconfined(label) &&
+		    !aa_label_is_unconfined_subset(new, ctx->nnp)) {
+			/* not an apparmor denial per se, so don't log it */
+			AA_DEBUG(DEBUG_DOMAIN,
+				 "no_new_privs - change_hat denied");
+			error = -EPERM;
+			goto out;
+		}
+	}
+
+	if (!(flags & AA_CHANGE_ONEXEC)) {
+		/* only transition profiles in the current ns */
+		if (stack)
+			new = aa_label_merge(label, target, GFP_KERNEL);
+		if (IS_ERR_OR_NULL(new))
+			goto build_fail;
+		error = aa_replace_current_label(new);
+	} else {
+		/* new will be recomputed so at exec time. So discard */
+		aa_put_label(new);
+		new = NULL;
+
+		/* full transition will be built in exec path */
+		aa_set_current_onexec(target, stack);
+	}
+
+	goto audit;
+
+build_fail:
+	info = "failed to build target label";
+	if (!new)
+		error = -ENOMEM;
+	else
+		error = PTR_ERR(new);
+	new = NULL;
+	perms.allow = 0;
+
+audit:
+	error = fn_for_each_in_scope(label, profile,
+			aa_audit_file(subj_cred,
+				      profile, &perms, op, request, auditname,
+				      NULL, new ? new : target,
+				      GLOBAL_ROOT_UID, info, error));
+
+out:
+	aa_put_label(new);
+	aa_put_label(target);
+	aa_put_label(label);
+	put_cred(subj_cred);
+
+	return error;
+}
diff --git a/security/apparmor/file.c b/security/apparmor/file.c
new file mode 100644
index 000000000..3e74b613d
--- /dev/null
+++ b/security/apparmor/file.c
@@ -0,0 +1,754 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/tty.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+
+#include "include/af_unix.h"
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/label.h"
+
+static u32 map_mask_to_chr_mask(u32 mask)
+{
+	u32 m = mask & PERMS_CHRS_MASK;
+
+	if (mask & AA_MAY_GETATTR)
+		m |= MAY_READ;
+	if (mask & (AA_MAY_SETATTR | AA_MAY_CHMOD | AA_MAY_CHOWN))
+		m |= MAY_WRITE;
+
+	return m;
+}
+
+/**
+ * file_audit_cb - call back for file specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void file_audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+	kuid_t fsuid = ad->subj_cred ? ad->subj_cred->fsuid : current_fsuid();
+	char str[10];
+
+	if (ad->request & AA_AUDIT_FILE_MASK) {
+		aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs,
+				    map_mask_to_chr_mask(ad->request));
+		audit_log_format(ab, " requested_mask=\"%s\"", str);
+	}
+	if (ad->denied & AA_AUDIT_FILE_MASK) {
+		aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs,
+				    map_mask_to_chr_mask(ad->denied));
+		audit_log_format(ab, " denied_mask=\"%s\"", str);
+	}
+	if (ad->request & AA_AUDIT_FILE_MASK) {
+		audit_log_format(ab, " fsuid=%d",
+				 from_kuid(&init_user_ns, fsuid));
+		audit_log_format(ab, " ouid=%d",
+				 from_kuid(&init_user_ns, ad->fs.ouid));
+	}
+
+	if (ad->peer) {
+		audit_log_format(ab, " target=");
+		aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+				FLAG_VIEW_SUBNS, GFP_KERNEL);
+	} else if (ad->fs.target) {
+		audit_log_format(ab, " target=");
+		audit_log_untrustedstring(ab, ad->fs.target);
+	}
+}
+
+/**
+ * aa_audit_file - handle the auditing of file operations
+ * @subj_cred: cred of the subject
+ * @profile: the profile being enforced  (NOT NULL)
+ * @perms: the permissions computed for the request (NOT NULL)
+ * @op: operation being mediated
+ * @request: permissions requested
+ * @name: name of object being mediated (MAYBE NULL)
+ * @target: name of target (MAYBE NULL)
+ * @tlabel: target label (MAY BE NULL)
+ * @ouid: object uid
+ * @info: extra information message (MAYBE NULL)
+ * @error: 0 if operation allowed else failure error code
+ *
+ * Returns: %0 or error on failure
+ */
+int aa_audit_file(const struct cred *subj_cred,
+		  struct aa_profile *profile, const struct aa_perms *perms,
+		  const char *op, u32 request, const char *name,
+		  const char *target, struct aa_label *tlabel,
+		  kuid_t ouid, const char *info, int error)
+{
+	u32 quiet = perms->quiet;
+	u32 complain = perms->complain;
+	int type = AUDIT_APPARMOR_AUTO;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_FILE, op);
+
+	ad.subj_cred = subj_cred;
+	ad.request = request;
+	ad.tags = perms->tag;
+	ad.name = name;
+	ad.fs.target = target;
+	ad.peer = tlabel;
+	ad.fs.ouid = ouid;
+	ad.info = info;
+	ad.error = error;
+	ad.common.u.tsk = NULL;
+
+	if (COMPLAIN_MODE(profile))
+		complain |= ~(perms->allow | perms->deny);
+	if (likely(!ad.error)) {
+		u32 mask = perms->audit;
+
+		if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
+			mask = 0xffff;
+
+		/* mask off perms that are not being force audited */
+		ad.request &= mask;
+
+		if (likely(!ad.request))
+			return 0;
+		type = AUDIT_APPARMOR_AUDIT;
+	} else {
+		/* only report permissions that were denied */
+		ad.request = ad.request & ~perms->allow;
+		AA_BUG(!ad.request);
+
+		if (ad.request & perms->kill)
+			type = AUDIT_APPARMOR_KILL;
+
+		if (AUDIT_MODE(profile) == AUDIT_QUIET_ALLOWED)
+			quiet |= complain | perms->allow;
+
+		/* quiet known rejects, assumes quiet and kill do not overlap */
+		if ((ad.request & quiet) &&
+		    AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		    AUDIT_MODE(profile) != AUDIT_ALL)
+			ad.request &= ~quiet;
+
+		if (!ad.request)
+			return ad.error;
+	}
+
+	ad.denied = ad.request & ~perms->allow;
+	return aa_audit(type, profile, &ad, file_audit_cb);
+}
+
+static int path_name(const char *op, const struct cred *subj_cred,
+		     struct aa_label *label,
+		     const struct path *path, int flags, char *buffer,
+		     const char **name, struct path_cond *cond, u32 request)
+{
+	struct aa_profile *profile;
+	const char *info = NULL;
+	int error;
+
+	/* don't reaudit files closed during inheritance */
+	if (unlikely(path->dentry == aa_null.dentry))
+		return -EACCES;
+
+	error = aa_path_name(path, flags, buffer, name, &info,
+			     labels_profile(label)->disconnected);
+	if (error) {
+		fn_for_each_confined(label, profile,
+			aa_audit_file(subj_cred,
+				      profile, &nullperms, op, request, *name,
+				      NULL, NULL, cond->uid, info, error));
+		return error;
+	}
+
+	return 0;
+}
+
+struct aa_perms default_perms = {};
+/**
+ * aa_lookup_condperms - convert dfa compressed perms to internal perms
+ * @subj_uid: uid to use for subject owner test
+ * @rules: the aa_policydb to lookup perms for  (NOT NULL)
+ * @state: state in dfa
+ * @cond:  conditions to consider  (NOT NULL)
+ *
+ * TODO: convert from dfa + state to permission entry
+ *
+ * Returns: a pointer to a file permission set
+ */
+struct aa_perms *aa_lookup_condperms(kuid_t subj_uid, struct aa_policydb *rules,
+				     aa_state_t state, struct path_cond *cond)
+{
+	unsigned int index = ACCEPT_TABLE(rules->dfa)[state];
+
+	if (!(rules->perms))
+		return &default_perms;
+
+	if ((ACCEPT_TABLE2(rules->dfa)[state] & ACCEPT_FLAG_OWNER)) {
+		if (uid_eq(subj_uid, cond->uid))
+			return &(rules->perms[index]);
+		return &(rules->perms[index + 1]);
+	}
+
+	return &(rules->perms[index]);
+}
+
+/**
+ * aa_str_perms - find permission that match @name
+ * @file_rules: the aa_policydb to match against  (NOT NULL)
+ * @start: state to start matching in
+ * @name: string to match against dfa  (NOT NULL)
+ * @cond: conditions to consider for permission set computation  (NOT NULL)
+ * @perms: Returns - the permissions found when matching @name
+ *
+ * Returns: the final state in @dfa when beginning @start and walking @name
+ */
+aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start,
+			const char *name, struct path_cond *cond,
+			struct aa_perms *perms)
+{
+	aa_state_t state;
+	state = aa_dfa_match(file_rules->dfa, start, name);
+	*perms = *(aa_lookup_condperms(current_fsuid(), file_rules, state,
+				       cond));
+
+	return state;
+}
+
+int __aa_path_perm(const char *op, const struct cred *subj_cred,
+		   struct aa_profile *profile, const char *name,
+		   u32 request, struct path_cond *cond, int flags,
+		   struct aa_perms *perms)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	int e = 0;
+
+	if (profile_unconfined(profile) ||
+	    ((flags & PATH_SOCK_COND) && !RULE_MEDIATES_UNIX(rules)))
+		return 0;
+	aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE],
+		     name, cond, perms);
+	if (request & ~perms->allow)
+		e = -EACCES;
+	return aa_audit_file(subj_cred,
+			     profile, perms, op, request, name, NULL, NULL,
+			     cond->uid, NULL, e);
+}
+
+
+static int profile_path_perm(const char *op, const struct cred *subj_cred,
+			     struct aa_profile *profile,
+			     const struct path *path, char *buffer, u32 request,
+			     struct path_cond *cond, int flags,
+			     struct aa_perms *perms)
+{
+	const char *name = NULL;
+	int error;
+
+	if (profile_unconfined(profile))
+		return 0;
+
+	error = path_name(op, subj_cred, &profile->label, path,
+			  flags | profile->path_flags, buffer, &name, cond,
+			  request);
+	if (error)
+		return error;
+	return __aa_path_perm(op, subj_cred, profile, name, request, cond,
+			      flags, perms);
+}
+
+/**
+ * aa_path_perm - do permissions check & audit for @path
+ * @op: operation being checked
+ * @subj_cred: subject cred
+ * @label: profile being enforced  (NOT NULL)
+ * @path: path to check permissions of  (NOT NULL)
+ * @flags: any additional path flags beyond what the profile specifies
+ * @request: requested permissions
+ * @cond: conditional info for this request  (NOT NULL)
+ *
+ * Returns: %0 else error if access denied or other error
+ */
+int aa_path_perm(const char *op, const struct cred *subj_cred,
+		 struct aa_label *label,
+		 const struct path *path, int flags, u32 request,
+		 struct path_cond *cond)
+{
+	struct aa_perms perms = {};
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	int error;
+
+	flags |= PATH_DELEGATE_DELETED | (S_ISDIR(cond->mode) ? PATH_IS_DIR :
+								0);
+	buffer = aa_get_buffer(false);
+	if (!buffer)
+		return -ENOMEM;
+	error = fn_for_each_confined(label, profile,
+			profile_path_perm(op, subj_cred, profile, path, buffer,
+					  request, cond, flags, &perms));
+
+	aa_put_buffer(buffer);
+
+	return error;
+}
+
+/**
+ * xindex_is_subset - helper for aa_path_link
+ * @link: link permission set
+ * @target: target permission set
+ *
+ * test target x permissions are equal OR a subset of link x permissions
+ * this is done as part of the subset test, where a hardlink must have
+ * a subset of permissions that the target has.
+ *
+ * Returns: true if subset else false
+ */
+static inline bool xindex_is_subset(u32 link, u32 target)
+{
+	if (((link & ~AA_X_UNSAFE) != (target & ~AA_X_UNSAFE)) ||
+	    ((link & AA_X_UNSAFE) && !(target & AA_X_UNSAFE)))
+		return false;
+
+	return true;
+}
+
+static int profile_path_link(const struct cred *subj_cred,
+			     struct aa_profile *profile,
+			     const struct path *link, char *buffer,
+			     const struct path *target, char *buffer2,
+			     struct path_cond *cond)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	const char *lname = NULL, *tname = NULL;
+	struct aa_perms lperms = {}, perms;
+	const char *info = NULL;
+	u32 request = AA_MAY_LINK;
+	aa_state_t state;
+	int error;
+
+	error = path_name(OP_LINK, subj_cred, &profile->label, link,
+			  profile->path_flags,
+			  buffer, &lname, cond, AA_MAY_LINK);
+	if (error)
+		goto audit;
+
+	/* buffer2 freed below, tname is pointer in buffer2 */
+	error = path_name(OP_LINK, subj_cred, &profile->label, target,
+			  profile->path_flags,
+			  buffer2, &tname, cond, AA_MAY_LINK);
+	if (error)
+		goto audit;
+
+	error = -EACCES;
+	/* aa_str_perms - handles the case of the dfa being NULL */
+	state = aa_str_perms(rules->file,
+			     rules->file->start[AA_CLASS_FILE], lname,
+			     cond, &lperms);
+
+	if (!(lperms.allow & AA_MAY_LINK))
+		goto audit;
+
+	/* test to see if target can be paired with link */
+	state = aa_dfa_null_transition(rules->file->dfa, state);
+	aa_str_perms(rules->file, state, tname, cond, &perms);
+
+	/* force audit/quiet masks for link are stored in the second entry
+	 * in the link pair.
+	 */
+	lperms.audit = perms.audit;
+	lperms.quiet = perms.quiet;
+	lperms.kill = perms.kill;
+
+	if (!(perms.allow & AA_MAY_LINK)) {
+		info = "target restricted";
+		lperms = perms;
+		goto audit;
+	}
+
+	/* done if link subset test is not required */
+	if (!(perms.allow & AA_LINK_SUBSET))
+		goto done_tests;
+
+	/* Do link perm subset test requiring allowed permission on link are
+	 * a subset of the allowed permissions on target.
+	 */
+	aa_str_perms(rules->file, rules->file->start[AA_CLASS_FILE],
+		     tname, cond, &perms);
+
+	/* AA_MAY_LINK is not considered in the subset test */
+	request = lperms.allow & ~AA_MAY_LINK;
+	lperms.allow &= perms.allow | AA_MAY_LINK;
+
+	request |= AA_AUDIT_FILE_MASK & (lperms.allow & ~perms.allow);
+	if (request & ~lperms.allow) {
+		goto audit;
+	} else if ((lperms.allow & MAY_EXEC) &&
+		   !xindex_is_subset(lperms.xindex, perms.xindex)) {
+		lperms.allow &= ~MAY_EXEC;
+		request |= MAY_EXEC;
+		info = "link not subset of target";
+		goto audit;
+	}
+
+done_tests:
+	error = 0;
+
+audit:
+	return aa_audit_file(subj_cred,
+			     profile, &lperms, OP_LINK, request, lname, tname,
+			     NULL, cond->uid, info, error);
+}
+
+/**
+ * aa_path_link - Handle hard link permission check
+ * @subj_cred: subject cred
+ * @label: the label being enforced  (NOT NULL)
+ * @old_dentry: the target dentry  (NOT NULL)
+ * @new_dir: directory the new link will be created in  (NOT NULL)
+ * @new_dentry: the link being created  (NOT NULL)
+ *
+ * Handle the permission test for a link & target pair.  Permission
+ * is encoded as a pair where the link permission is determined
+ * first, and if allowed, the target is tested.  The target test
+ * is done from the point of the link match (not start of DFA)
+ * making the target permission dependent on the link permission match.
+ *
+ * The subset test if required forces that permissions granted
+ * on link are a subset of the permission granted to target.
+ *
+ * Returns: %0 if allowed else error
+ */
+int aa_path_link(const struct cred *subj_cred,
+		 struct aa_label *label, struct dentry *old_dentry,
+		 const struct path *new_dir, struct dentry *new_dentry)
+{
+	struct path link = { .mnt = new_dir->mnt, .dentry = new_dentry };
+	struct path target = { .mnt = new_dir->mnt, .dentry = old_dentry };
+	struct inode *inode = d_backing_inode(old_dentry);
+	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(target.mnt), inode);
+	struct path_cond cond = {
+		.uid = vfsuid_into_kuid(vfsuid),
+		.mode = inode->i_mode,
+	};
+	char *buffer = NULL, *buffer2 = NULL;
+	struct aa_profile *profile;
+	int error;
+
+	/* buffer freed below, lname is pointer in buffer */
+	buffer = aa_get_buffer(false);
+	buffer2 = aa_get_buffer(false);
+	error = -ENOMEM;
+	if (!buffer || !buffer2)
+		goto out;
+
+	error = fn_for_each_confined(label, profile,
+			profile_path_link(subj_cred, profile, &link, buffer,
+					  &target, buffer2, &cond));
+out:
+	aa_put_buffer(buffer);
+	aa_put_buffer(buffer2);
+	return error;
+}
+
+static void update_file_ctx(struct aa_file_ctx *fctx, struct aa_label *label,
+			    u32 request)
+{
+	struct aa_label *l, *old;
+
+	/* update caching of label on file_ctx */
+	spin_lock(&fctx->lock);
+	old = rcu_dereference_protected(fctx->label,
+					lockdep_is_held(&fctx->lock));
+	l = aa_label_merge(old, label, GFP_ATOMIC);
+	if (l) {
+		if (l != old) {
+			rcu_assign_pointer(fctx->label, l);
+			aa_put_label(old);
+		} else
+			aa_put_label(l);
+		fctx->allow |= request;
+	}
+	spin_unlock(&fctx->lock);
+}
+
+static int __file_path_perm(const char *op, const struct cred *subj_cred,
+			    struct aa_label *label,
+			    struct aa_label *flabel, struct file *file,
+			    u32 request, u32 denied, bool in_atomic)
+{
+	struct aa_profile *profile;
+	struct aa_perms perms = {};
+	vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(file),
+					    file_inode(file));
+	struct path_cond cond = {
+		.uid = vfsuid_into_kuid(vfsuid),
+		.mode = file_inode(file)->i_mode
+	};
+	char *buffer;
+	int flags, error;
+
+	/* revalidation due to label out of date. No revocation at this time */
+	if (!denied && aa_label_is_subset(flabel, label))
+		/* TODO: check for revocation on stale profiles */
+		return 0;
+
+	flags = PATH_DELEGATE_DELETED | (S_ISDIR(cond.mode) ? PATH_IS_DIR : 0);
+	buffer = aa_get_buffer(in_atomic);
+	if (!buffer)
+		return -ENOMEM;
+
+	/* check every profile in task label not in current cache */
+	error = fn_for_each_not_in_set(flabel, label, profile,
+			profile_path_perm(op, subj_cred, profile,
+					  &file->f_path, buffer,
+					  request, &cond, flags, &perms));
+	if (denied && !error) {
+		/*
+		 * check every profile in file label that was not tested
+		 * in the initial check above.
+		 *
+		 * TODO: cache full perms so this only happens because of
+		 * conditionals
+		 * TODO: don't audit here
+		 */
+		if (label == flabel)
+			error = fn_for_each(label, profile,
+				profile_path_perm(op, subj_cred,
+						  profile, &file->f_path,
+						  buffer, request, &cond, flags,
+						  &perms));
+		else
+			error = fn_for_each_not_in_set(label, flabel, profile,
+				profile_path_perm(op, subj_cred,
+						  profile, &file->f_path,
+						  buffer, request, &cond, flags,
+						  &perms));
+	}
+	if (!error)
+		update_file_ctx(file_ctx(file), label, request);
+
+	aa_put_buffer(buffer);
+
+	return error;
+}
+
+static int __file_sock_perm(const char *op, const struct cred *subj_cred,
+			    struct aa_label *label,
+			    struct aa_label *flabel, struct file *file,
+			    u32 request, u32 denied)
+{
+	int error;
+
+	/* revalidation due to label out of date. No revocation at this time */
+	if (!denied && aa_label_is_subset(flabel, label))
+		return 0;
+
+	/* TODO: improve to skip profiles cached in flabel */
+	error = aa_sock_file_perm(subj_cred, label, op, request, file);
+	if (denied) {
+		/* TODO: improve to skip profiles checked above */
+		/* check every profile in file label to is cached */
+		last_error(error, aa_sock_file_perm(subj_cred, flabel, op,
+						    request, file));
+	}
+	if (!error)
+		update_file_ctx(file_ctx(file), label, request);
+
+	return error;
+}
+
+/* for now separate fn to indicate semantics of the check */
+static bool __file_is_delegated(struct aa_label *obj_label)
+{
+	return unconfined(obj_label);
+}
+
+static bool __is_unix_file(struct file *file)
+{
+	struct socket *sock = (struct socket *) file->private_data;
+
+	lockdep_assert_in_rcu_read_lock();
+
+	if (!S_ISSOCK(file_inode(file)->i_mode))
+		return false;
+	/* sock and sock->sk can be NULL for sockets being set up or torn down */
+	if (!sock || !sock->sk)
+		return false;
+	if (sock->sk->sk_family == PF_UNIX)
+		return true;
+	return false;
+}
+
+static bool __unix_needs_revalidation(struct file *file, struct aa_label *label,
+				      u32 request)
+{
+	struct socket *sock = (struct socket *) file->private_data;
+
+	AA_BUG(!__is_unix_file(file));
+	lockdep_assert_in_rcu_read_lock();
+
+	struct aa_sk_ctx *skctx = aa_sock(sock->sk);
+
+	if (rcu_access_pointer(skctx->peer) !=
+	    rcu_access_pointer(skctx->peer_lastupdate))
+		return true;
+
+	return !__aa_subj_label_is_cached(rcu_dereference(skctx->label), label);
+}
+
+/**
+ * aa_file_perm - do permission revalidation check & audit for @file
+ * @op: operation being checked
+ * @subj_cred: subject cred
+ * @label: label being enforced   (NOT NULL)
+ * @file: file to revalidate access permissions on  (NOT NULL)
+ * @request: requested permissions
+ * @in_atomic: whether allocations need to be done in atomic context
+ *
+ * Returns: %0 if access allowed else error
+ */
+int aa_file_perm(const char *op, const struct cred *subj_cred,
+		 struct aa_label *label, struct file *file,
+		 u32 request, bool in_atomic)
+{
+	struct aa_file_ctx *fctx;
+	struct aa_label *flabel;
+	u32 denied;
+	int error = 0;
+
+	AA_BUG(!label);
+	AA_BUG(!file);
+
+	/* don't reaudit files closed during inheritance */
+	if (unlikely(file->f_path.dentry == aa_null.dentry))
+		return -EACCES;
+
+	fctx = file_ctx(file);
+
+	rcu_read_lock();
+	flabel  = rcu_dereference(fctx->label);
+	AA_BUG(!flabel);
+
+	/* revalidate access, if task is unconfined, or the cached cred
+	 * doesn't match or if the request is for more permissions than
+	 * was granted.
+	 *
+	 * Note: the test for !unconfined(flabel) is to handle file
+	 *       delegation from unconfined tasks
+	 */
+	denied = request & ~fctx->allow;
+	if (unconfined(label) || __file_is_delegated(flabel) ||
+	    (!denied && __is_unix_file(file) && !__unix_needs_revalidation(file, label, request)) ||
+	    (!denied && __aa_subj_label_is_cached(label, flabel))) {
+		rcu_read_unlock();
+		goto done;
+	}
+
+	/* slow path - revalidate access */
+	flabel  = aa_get_newest_label(flabel);
+	rcu_read_unlock();
+
+	if (path_mediated_fs(file->f_path.dentry))
+		error = __file_path_perm(op, subj_cred, label, flabel, file,
+					 request, denied, in_atomic);
+
+	else if (S_ISSOCK(file_inode(file)->i_mode))
+		error = __file_sock_perm(op, subj_cred, label, flabel, file,
+					 request, denied);
+	aa_put_label(flabel);
+
+done:
+	return error;
+}
+
+static void revalidate_tty(const struct cred *subj_cred, struct aa_label *label)
+{
+	struct tty_struct *tty;
+	int drop_tty = 0;
+
+	tty = get_current_tty();
+	if (!tty)
+		return;
+
+	spin_lock(&tty->files_lock);
+	if (!list_empty(&tty->tty_files)) {
+		struct tty_file_private *file_priv;
+		struct file *file;
+		/* TODO: Revalidate access to controlling tty. */
+		file_priv = list_first_entry(&tty->tty_files,
+					     struct tty_file_private, list);
+		file = file_priv->file;
+
+		if (aa_file_perm(OP_INHERIT, subj_cred, label, file,
+				 MAY_READ | MAY_WRITE, IN_ATOMIC))
+			drop_tty = 1;
+	}
+	spin_unlock(&tty->files_lock);
+	tty_kref_put(tty);
+
+	if (drop_tty)
+		no_tty();
+}
+
+struct cred_label {
+	const struct cred *cred;
+	struct aa_label *label;
+};
+
+static int match_file(const void *p, struct file *file, unsigned int fd)
+{
+	struct cred_label *cl = (struct cred_label *)p;
+
+	if (aa_file_perm(OP_INHERIT, cl->cred, cl->label, file,
+			 aa_map_file_to_perms(file), IN_ATOMIC))
+		return fd + 1;
+	return 0;
+}
+
+
+/* based on selinux's flush_unauthorized_files */
+void aa_inherit_files(const struct cred *cred, struct files_struct *files)
+{
+	struct aa_label *label = aa_get_newest_cred_label(cred);
+	struct cred_label cl = {
+		.cred = cred,
+		.label = label,
+	};
+	struct file *devnull = NULL;
+	unsigned int n;
+
+	revalidate_tty(cred, label);
+
+	/* Revalidate access to inherited open files. */
+	n = iterate_fd(files, 0, match_file, &cl);
+	if (!n) /* none found? */
+		goto out;
+
+	devnull = dentry_open(&aa_null, O_RDWR, cred);
+	if (IS_ERR(devnull))
+		devnull = NULL;
+	/* replace all the matching ones with this */
+	do {
+		replace_fd(n - 1, devnull, 0);
+	} while ((n = iterate_fd(files, n, match_file, &cl)) != 0);
+	if (devnull)
+		fput(devnull);
+out:
+	aa_put_label(label);
+}
diff --git a/security/apparmor/include/af_inet.h b/security/apparmor/include/af_inet.h
new file mode 100644
index 000000000..601ab44bd
--- /dev/null
+++ b/security/apparmor/include/af_inet.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor inet/inet6 fine grained mediation
+ *
+ * Copyright 2024 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+#ifndef __AA_AF_INET_H
+#define __AA_AF_INET_H
+
+#include "label.h"
+
+int aa_inet_sock_perm(const char *op, u32 request, struct socket *sock);
+int aa_inet_create_perm(struct aa_label *label, int family, int type,
+			int protocol);
+int aa_inet_bind_perm(struct socket *sock, struct sockaddr *address,
+		      int addrlen);
+int aa_inet_connect_perm(struct socket *sock, struct sockaddr *address,
+			 int addrlen);
+int aa_inet_listen_perm(struct socket *sock, int backlog);
+int aa_inet_accept_perm(struct socket *sock, struct socket *newsock);
+int aa_inet_msg_perm(const char *op, u32 request, struct socket *sock,
+		     struct msghdr *msg, int size);
+int aa_inet_opt_perm(const char *op, u32 request, struct socket *sock, int level,
+		     int optname);
+int aa_inet_file_perm(const struct cred *subj_cred,
+		      struct aa_label *label, const char *op, u32 request,
+		      struct socket *sock);
+
+#endif /* __AA_AF_INET_H */
diff --git a/security/apparmor/include/af_unix.h b/security/apparmor/include/af_unix.h
new file mode 100644
index 000000000..4a62e600d
--- /dev/null
+++ b/security/apparmor/include/af_unix.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor af_unix fine grained mediation
+ *
+ * Copyright 2023 Canonical Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation, version 2 of the
+ * License.
+ */
+#ifndef __AA_AF_UNIX_H
+
+#include <net/af_unix.h>
+
+#include "label.h"
+
+#define unix_addr(A) ((struct sockaddr_un *)(A))
+#define unix_addr_len(L) ((L) - sizeof(sa_family_t))
+#define unix_peer(sk) (unix_sk(sk)->peer)
+#define is_unix_addr_abstract_name(B) ((B)[0] == 0)
+#define is_unix_addr_anon(A, L) ((A) && unix_addr_len(L) <= 0)
+#define is_unix_addr_fs(A, L) (!is_unix_addr_anon(A, L) && \
+			    !is_unix_addr_abstract_name(unix_addr(A)->sun_path))
+
+#define is_unix_anonymous(U) (!unix_sk(U)->addr)
+#define is_unix_fs(U) (!is_unix_anonymous(U) &&			\
+		       unix_sk(U)->addr->name->sun_path[0])
+#define is_unix_connected(S) ((S)->state == SS_CONNECTED)
+
+
+struct sockaddr_un *aa_sunaddr(const struct unix_sock *u, int *addrlen);
+int aa_unix_peer_perm(const struct cred *subj_cred,
+		      struct aa_label *label, const char *op, u32 request,
+		      struct sock *sk, struct sock *peer_sk,
+		      struct aa_label *peer_label);
+int aa_unix_sock_perm(const char *op, u32 request, struct socket *sock);
+int aa_unix_create_perm(struct aa_label *label, int family, int type,
+			int protocol);
+int aa_unix_bind_perm(struct socket *sock, struct sockaddr *address,
+		      int addrlen);
+int aa_unix_connect_perm(struct socket *sock, struct sockaddr *address,
+			 int addrlen);
+int aa_unix_listen_perm(struct socket *sock, int backlog);
+int aa_unix_accept_perm(struct socket *sock, struct socket *newsock);
+int aa_unix_msg_perm(const char *op, u32 request, struct socket *sock,
+		     struct msghdr *msg, int size);
+int aa_unix_opt_perm(const char *op, u32 request, struct socket *sock, int level,
+		     int optname);
+int aa_unix_file_perm(const struct cred *subj_cred, struct aa_label *label,
+		      const char *op, u32 request, struct file *file);
+
+#endif /* __AA_AF_UNIX_H */
diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h
new file mode 100644
index 000000000..cb06b2f55
--- /dev/null
+++ b/security/apparmor/include/apparmor.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor basic global
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#ifndef __APPARMOR_H
+#define __APPARMOR_H
+
+#include <linux/types.h>
+
+/*
+ * Class of mediation types in the AppArmor policy db
+ */
+#define AA_CLASS_NONE		0
+#define AA_CLASS_UNKNOWN	1
+#define AA_CLASS_FILE		2
+#define AA_CLASS_CAP		3
+#define AA_CLASS_DEPRECATED	4
+#define AA_CLASS_RLIMITS	5
+#define AA_CLASS_DOMAIN		6
+#define AA_CLASS_MOUNT		7
+#define AA_CLASS_PTRACE		9
+#define AA_CLASS_SIGNAL		10
+#define AA_CLASS_XMATCH		11
+#define AA_CLASS_NET		14
+#define AA_CLASS_NETV9		15
+#define AA_CLASS_LABEL		16
+#define AA_CLASS_POSIX_MQUEUE	17
+#define AA_CLASS_MODULE		19
+#define AA_CLASS_DISPLAY_LSM	20
+#define AA_CLASS_NS		21
+#define AA_CLASS_IO_URING	22
+
+#define AA_CLASS_NETV9_SKB	30
+#define AA_CLASS_X		31
+#define AA_CLASS_DBUS		32
+
+/* NOTE: if AA_CLASS_LAST > 63 need to update label->mediates */
+#define AA_CLASS_LAST		AA_CLASS_DBUS
+
+/* Control parameters settable through module/boot flags */
+extern enum audit_mode aa_g_audit;
+extern bool aa_g_audit_header;
+extern int aa_g_debug;
+extern bool aa_g_hash_policy;
+extern bool aa_g_export_binary;
+extern int aa_g_rawdata_compression_level;
+extern bool aa_g_lock_policy;
+extern bool aa_g_logsyscall;
+extern bool aa_g_paranoid_load;
+extern unsigned int aa_g_path_max;
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+#define AA_MIN_CLEVEL zstd_min_clevel()
+#define AA_MAX_CLEVEL zstd_max_clevel()
+#define AA_DEFAULT_CLEVEL ZSTD_CLEVEL_DEFAULT
+#else
+#define AA_MIN_CLEVEL 0
+#define AA_MAX_CLEVEL 0
+#define AA_DEFAULT_CLEVEL 0
+#endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
+
+
+#endif /* __APPARMOR_H */
diff --git a/security/apparmor/include/apparmorfs.h b/security/apparmor/include/apparmorfs.h
new file mode 100644
index 000000000..c6c8fcde7
--- /dev/null
+++ b/security/apparmor/include/apparmorfs.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor filesystem definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_APPARMORFS_H
+#define __AA_APPARMORFS_H
+
+#include <linux/init.h>
+#include <linux/types.h>
+
+extern struct path aa_null;
+
+enum aa_sfs_type {
+	AA_SFS_TYPE_BOOLEAN,
+	AA_SFS_TYPE_STRING,
+	AA_SFS_TYPE_U64,
+	AA_SFS_TYPE_FOPS,
+	AA_SFS_TYPE_DIR,
+};
+
+struct aa_sfs_entry;
+
+struct aa_sfs_entry {
+	const char *name;
+	struct dentry *dentry;
+	umode_t mode;
+	enum aa_sfs_type v_type;
+	union {
+		bool boolean;
+		char *string;
+		unsigned long u64;
+		struct aa_sfs_entry *files;
+	} v;
+	const struct file_operations *file_ops;
+};
+
+extern const struct file_operations aa_sfs_seq_file_ops;
+
+#define AA_SFS_FILE_BOOLEAN(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_SFS_TYPE_BOOLEAN, .v.boolean = (_value), \
+	  .file_ops = &aa_sfs_seq_file_ops }
+#define AA_SFS_FILE_STRING(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_SFS_TYPE_STRING, .v.string = (_value), \
+	  .file_ops = &aa_sfs_seq_file_ops }
+#define AA_SFS_FILE_U64(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_SFS_TYPE_U64, .v.u64 = (_value), \
+	  .file_ops = &aa_sfs_seq_file_ops }
+#define AA_SFS_FILE_FOPS(_name, _mode, _fops) \
+	{ .name = (_name), .v_type = AA_SFS_TYPE_FOPS, \
+	  .mode = (_mode), .file_ops = (_fops) }
+#define AA_SFS_DIR(_name, _value) \
+	{ .name = (_name), .v_type = AA_SFS_TYPE_DIR, .v.files = (_value) }
+
+extern void __init aa_destroy_aafs(void);
+
+struct aa_profile;
+struct aa_ns;
+
+enum aafs_ns_type {
+	AAFS_NS_DIR,
+	AAFS_NS_PROFS,
+	AAFS_NS_NS,
+	AAFS_NS_RAW_DATA,
+	AAFS_NS_LOAD,
+	AAFS_NS_REPLACE,
+	AAFS_NS_REMOVE,
+	AAFS_NS_REVISION,
+	AAFS_NS_COUNT,
+	AAFS_NS_MAX_COUNT,
+	AAFS_NS_SIZE,
+	AAFS_NS_MAX_SIZE,
+	AAFS_NS_OWNER,
+	AAFS_NS_SIZEOF,
+};
+
+enum aafs_prof_type {
+	AAFS_PROF_DIR,
+	AAFS_PROF_PROFS,
+	AAFS_PROF_NAME,
+	AAFS_PROF_MODE,
+	AAFS_PROF_ATTACH,
+	AAFS_PROF_HASH,
+	AAFS_PROF_RAW_DATA,
+	AAFS_PROF_RAW_HASH,
+	AAFS_PROF_RAW_ABI,
+	AAFS_PROF_SIZEOF,
+};
+
+#define ns_dir(X) ((X)->dents[AAFS_NS_DIR])
+#define ns_subns_dir(X) ((X)->dents[AAFS_NS_NS])
+#define ns_subprofs_dir(X) ((X)->dents[AAFS_NS_PROFS])
+#define ns_subdata_dir(X) ((X)->dents[AAFS_NS_RAW_DATA])
+#define ns_subload(X) ((X)->dents[AAFS_NS_LOAD])
+#define ns_subreplace(X) ((X)->dents[AAFS_NS_REPLACE])
+#define ns_subremove(X) ((X)->dents[AAFS_NS_REMOVE])
+#define ns_subrevision(X) ((X)->dents[AAFS_NS_REVISION])
+
+#define prof_dir(X) ((X)->dents[AAFS_PROF_DIR])
+#define prof_child_dir(X) ((X)->dents[AAFS_PROF_PROFS])
+
+int aa_create_aafs(void);
+
+void __aa_bump_ns_revision(struct aa_ns *ns);
+void __aafs_profile_rmdir(struct aa_profile *profile);
+void __aafs_profile_migrate_dents(struct aa_profile *old,
+				   struct aa_profile *new);
+int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent);
+void __aafs_ns_rmdir(struct aa_ns *ns);
+int __aafs_ns_mkdir(struct aa_ns *ns, struct dentry *parent, const char *name,
+		     struct dentry *dent);
+
+struct aa_loaddata;
+
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+void __aa_fs_remove_rawdata(struct aa_loaddata *rawdata);
+int __aa_fs_create_rawdata(struct aa_ns *ns, struct aa_loaddata *rawdata);
+void __aa_remove_rawdata_symlink_dents(struct aa_profile *profile);
+int __aa_create_rawdata_symlink_dents(struct aa_profile *profile);
+#else
+static inline void __aa_fs_remove_rawdata(struct aa_loaddata *rawdata)
+{
+	/* empty stub */
+}
+
+static inline int __aa_fs_create_rawdata(struct aa_ns *ns,
+					 struct aa_loaddata *rawdata)
+{
+	return 0;
+}
+
+static inline void __aa_remove_rawdata_symlink_dents(struct aa_profile *profile)
+{
+	/* empty stub */
+}
+
+static inline int __aa_create_rawdata_symlink_dents(struct aa_profile *profile)
+{
+	return 0;
+}
+#endif /* CONFIG_SECURITY_APPARMOR_EXPORT_BINARY */
+
+#endif /* __AA_APPARMORFS_H */
diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h
new file mode 100644
index 000000000..987ed4441
--- /dev/null
+++ b/security/apparmor/include/audit.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor auditing function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_AUDIT_H
+#define __AA_AUDIT_H
+
+#include <linux/audit.h>
+#include <linux/fs.h>
+#include <linux/lsm_audit.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "file.h"
+#include "label.h"
+
+extern const char *const audit_mode_names[];
+enum audit_mode {
+	AUDIT_NORMAL,		/* follow normal auditing of accesses */
+	AUDIT_QUIET_DENIED,	/* quiet all denied access messages */
+	AUDIT_QUIET_ALLOWED,	/* quiet all allowed access messages */
+	AUDIT_QUIET,		/* quiet all messages */
+	AUDIT_NOQUIET,		/* do not quiet audit messages */
+	AUDIT_ALL,		/* audit all accesses */
+	AUDIT_MODE_NAMES_COUNT	/* Must be last entry */
+};
+
+enum audit_type {
+	AUDIT_APPARMOR_AUDIT,
+	AUDIT_APPARMOR_ALLOWED,
+	AUDIT_APPARMOR_DENIED,
+	AUDIT_APPARMOR_HINT,
+	AUDIT_APPARMOR_STATUS,
+	AUDIT_APPARMOR_ERROR,
+	AUDIT_APPARMOR_KILL,
+	AUDIT_APPARMOR_AUTO
+};
+
+#define OP_NULL NULL
+
+#define OP_SYSCTL "sysctl"
+#define OP_CAPABLE "capable"
+
+#define OP_UNLINK "unlink"
+#define OP_MKDIR "mkdir"
+#define OP_RMDIR "rmdir"
+#define OP_MKNOD "mknod"
+#define OP_TRUNC "truncate"
+#define OP_LINK "link"
+#define OP_SYMLINK "symlink"
+#define OP_RENAME_SRC "rename_src"
+#define OP_RENAME_DEST "rename_dest"
+#define OP_CHMOD "chmod"
+#define OP_CHOWN "chown"
+#define OP_GETATTR "getattr"
+#define OP_OPEN "open"
+
+#define OP_FRECEIVE "file_receive"
+#define OP_FPERM "file_perm"
+#define OP_FLOCK "file_lock"
+#define OP_FMMAP "file_mmap"
+#define OP_FMPROT "file_mprotect"
+#define OP_INHERIT "file_inherit"
+
+#define OP_PIVOTROOT "pivotroot"
+#define OP_MOUNT "mount"
+#define OP_UMOUNT "umount"
+
+#define OP_CREATE "create"
+#define OP_POST_CREATE "post_create"
+#define OP_BIND "bind"
+#define OP_CONNECT "connect"
+#define OP_LISTEN "listen"
+#define OP_ACCEPT "accept"
+#define OP_SENDMSG "sendmsg"
+#define OP_RECVMSG "recvmsg"
+#define OP_GETSOCKNAME "getsockname"
+#define OP_GETPEERNAME "getpeername"
+#define OP_GETSOCKOPT "getsockopt"
+#define OP_SETSOCKOPT "setsockopt"
+#define OP_SHUTDOWN "socket_shutdown"
+
+#define OP_PTRACE "ptrace"
+#define OP_SIGNAL "signal"
+
+#define OP_EXEC "exec"
+
+#define OP_CHANGE_HAT "change_hat"
+#define OP_CHANGE_PROFILE "change_profile"
+#define OP_CHANGE_ONEXEC "change_onexec"
+#define OP_STACK "stack"
+#define OP_STACK_ONEXEC "stack_onexec"
+
+#define OP_SETPROCATTR "setprocattr"
+#define OP_SETRLIMIT "setrlimit"
+
+#define OP_PROF_REPL "profile_replace"
+#define OP_PROF_LOAD "profile_load"
+#define OP_PROF_RM "profile_remove"
+
+#define OP_USERNS_CREATE "userns_create"
+
+#define OP_URING_OVERRIDE "uring_override"
+#define OP_URING_SQPOLL "uring_sqpoll"
+
+struct apparmor_audit_data {
+	int error;
+	int type;
+	u16 class;
+	const char *op;
+	const struct cred *subj_cred;
+	struct aa_label *subj_label;
+	const char *name;
+	const char *info;
+	u32 request;
+	u32 denied;
+	u32 tags;
+
+	union {
+		/* these entries require a custom callback fn */
+		struct {
+			struct aa_label *peer;
+			union {
+				struct {
+					const char *target;
+					kuid_t ouid;
+				} fs;
+				struct {
+					int rlim;
+					unsigned long max;
+				} rlim;
+				struct {
+					int signal;
+					int unmappedsig;
+				};
+				struct {
+					int type, protocol;
+					void *addr;
+					int addrlen;
+					struct {
+						void *addr;
+						int addrlen;
+					} peer;
+				} net;
+			};
+		};
+		struct {
+			struct aa_profile *profile;
+			const char *ns;
+			long pos;
+		} iface;
+		struct {
+			const char *src_name;
+			const char *type;
+			const char *trans;
+			const char *data;
+			unsigned long flags;
+		} mnt;
+		struct {
+			struct aa_label *target;
+		} uring;
+	};
+
+	struct common_audit_data common;
+};
+
+/* macros for dealing with  apparmor_audit_data structure */
+#define aad(SA) (container_of(SA, struct apparmor_audit_data, common))
+#define aad_of_va(VA) aad((struct common_audit_data *)(VA))
+
+#define DEFINE_AUDIT_DATA(NAME, T, C, X)				\
+	/* TODO: cleanup audit init so we don't need _aad = {0,} */	\
+	struct apparmor_audit_data NAME = {				\
+		.class = (C),						\
+		.op = (X),                                              \
+		.common.type = (T),					\
+		.common.u.tsk = NULL,					\
+		.common.apparmor_audit_data = &NAME,			\
+	};
+
+int aa_select_audit_type(u32 denied, const struct aa_perms *perms);
+
+void aa_audit_msg(int type, struct apparmor_audit_data *ad,
+		  void (*cb) (struct audit_buffer *, void *));
+int aa_audit(int type, struct aa_profile *profile,
+	     struct apparmor_audit_data *ad,
+	     void (*cb) (struct audit_buffer *, void *));
+
+#define aa_audit_error(ERROR, AD, CB)				\
+({								\
+	(AD)->error = (ERROR);					\
+	aa_audit_msg(AUDIT_APPARMOR_ERROR, (AD), (CB));		\
+	(AD)->error;					\
+})
+
+int aa_audit_perm_error(struct aa_label *label, u32 request, int error,
+			struct apparmor_audit_data *ad,
+			void (*cb)(struct audit_buffer *, void *));
+
+static inline int complain_error(int error)
+{
+	if (error == -EPERM || error == -EACCES)
+		return 0;
+	return error;
+}
+
+void aa_audit_rule_free(void *vrule);
+int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp);
+int aa_audit_rule_known(struct audit_krule *rule);
+int aa_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule);
+
+#endif /* __AA_AUDIT_H */
diff --git a/security/apparmor/include/capability.h b/security/apparmor/include/capability.h
new file mode 100644
index 000000000..89a9c75d8
--- /dev/null
+++ b/security/apparmor/include/capability.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor capability mediation definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2013 Canonical Ltd.
+ */
+
+#ifndef __AA_CAPABILITY_H
+#define __AA_CAPABILITY_H
+
+#include <linux/capability.h>
+#include <linux/sched.h>
+
+#include "apparmorfs.h"
+
+struct aa_label;
+
+/* aa_caps - confinement data for capabilities
+ * @allowed: capabilities mask
+ * @audit: caps that are to be audited
+ * @denied: caps that are explicitly denied
+ * @quiet: caps that should not be audited
+ * @kill: caps that when requested will result in the task being killed
+ * @extended: caps that are subject finer grained mediation
+ */
+struct aa_caps {
+	kernel_cap_t allow;
+	kernel_cap_t audit;
+	kernel_cap_t denied;
+	kernel_cap_t quiet;
+	kernel_cap_t kill;
+	kernel_cap_t extended;
+};
+
+extern struct aa_sfs_entry aa_sfs_entry_caps[];
+
+kernel_cap_t aa_profile_capget(const struct aa_profile *profile);
+int aa_capable(const struct cred *subj_cred, struct aa_label *label,
+	       int cap, unsigned int opts);
+
+static inline void aa_free_cap_rules(struct aa_caps *caps)
+{
+	/* NOP */
+}
+
+#endif /* __AA_CAPBILITY_H */
diff --git a/security/apparmor/include/cred.h b/security/apparmor/include/cred.h
new file mode 100644
index 000000000..056e031b7
--- /dev/null
+++ b/security/apparmor/include/cred.h
@@ -0,0 +1,246 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor contexts used to associate "labels" to objects.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_CONTEXT_H
+#define __AA_CONTEXT_H
+
+#include <linux/cred.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+#include "label.h"
+#include "policy_ns.h"
+#include "task.h"
+
+static inline struct aa_label *cred_label(const struct cred *cred)
+{
+	struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred;
+
+	AA_BUG(!blob);
+	return *blob;
+}
+
+static inline void set_cred_label(const struct cred *cred,
+				  struct aa_label *label)
+{
+	struct aa_label **blob = cred->security + apparmor_blob_sizes.lbs_cred;
+
+	AA_BUG(!blob);
+	*blob = label;
+}
+
+/**
+ * aa_get_newest_cred_label - obtain the newest label on a cred
+ * @cred: cred to obtain label from (NOT NULL)
+ *
+ * Returns: newest version of confining label
+ */
+static inline struct aa_label *aa_get_newest_cred_label(const struct cred *cred)
+{
+	return aa_get_newest_label(cred_label(cred));
+}
+
+static inline struct aa_label *aa_get_newest_cred_label_condref(const struct cred *cred,
+								bool *needput)
+{
+	struct aa_label *l = cred_label(cred);
+
+	if (unlikely(label_is_stale(l))) {
+		*needput = true;
+		return aa_get_newest_label(l);
+	}
+
+	*needput = false;
+	return l;
+}
+
+static inline void aa_put_label_condref(struct aa_label *l, bool needput)
+{
+	if (unlikely(needput))
+		aa_put_label(l);
+}
+
+/**
+ * aa_current_raw_label - find the current tasks confining label
+ *
+ * Returns: up to date confining label or the ns unconfined label (NOT NULL)
+ *
+ * This fn will not update the tasks cred to the most up to date version
+ * of the label so it is safe to call when inside of locks.
+ */
+static inline struct aa_label *aa_current_raw_label(void)
+{
+	return cred_label(current_cred());
+}
+
+/**
+ * aa_get_current_label - get the newest version of the current tasks label
+ *
+ * Returns: newest version of confining label (NOT NULL)
+ *
+ * This fn will not update the tasks cred, so it is safe inside of locks
+ *
+ * The returned reference must be put with aa_put_label()
+ */
+static inline struct aa_label *aa_get_current_label(void)
+{
+	struct aa_label *l = aa_current_raw_label();
+
+	if (label_is_stale(l))
+		return aa_get_newest_label(l);
+	return aa_get_label(l);
+}
+
+/**
+ * __end_cred_crit_section - end crit section begun with __begin_...
+ * @label: label obtained from __begin_cred_crit_section
+ * @needput: output: bool set by __begin_cred_crit_section
+ *
+ * While the cred passed to __begin is guaranteed to not change
+ * and the cred and label could be passed here instead of needput
+ * using needput with a local var makes it easier for the compiler
+ * and processor to optimize and speculatively execute the comparison
+ * than chasing a pointer in the cred struct.
+ */
+static inline void __end_cred_crit_section(struct aa_label *label,
+						    bool needput)
+{
+	if (unlikely(needput))
+		aa_put_label(label);
+}
+
+/**
+ * __begin_cred_crit_section - @cred's confining label
+ * @cred: current's cred to start a crit section on its label
+ * @needput: store whether the label needs to be put when ending crit section
+ *
+ * Returns: up to date confining label or the ns unconfined label (NOT NULL)
+ *
+ * safe to call inside locks
+ *
+ * The returned reference must be put with __end_cred_crit_section()
+ * This must NOT be used if the task cred could be updated within the
+ * critical section between
+ *   __begin_cred_crit_section() ..  __end_cred_crit_section()
+ *
+ * The crit section is an optimization to avoid having to get and put
+ * the newest version of the label. While the cred won't change and
+ * hence the label it contains won't change, the newest version of the
+ * label can. During the crit section the newest versions of the label
+ * will be used until the end of the crit section.
+ *
+ * If the label has not been updated at the start of the crit section
+ * no refcount is taken, the cred's refcount is enough to hold the
+ * label for the duration of the crit section.
+ *
+ * If the label has been updated then a refcount will be taken and the
+ * newest version of the label will be returned. While the cred label
+ * and the returned label could be compared at the end of the crit
+ * section, needput is used because it allows better optimization by
+ * the compiler and the processor's speculative execution.
+ */
+static inline struct aa_label *__begin_cred_crit_section(const struct cred *cred,
+							 bool *needput)
+{
+	struct aa_label *label = cred_label(cred);
+
+	if (label_is_stale(label)) {
+		*needput = true;
+		return aa_get_newest_label(label);
+	}
+
+	*needput = false;
+	return label;
+}
+
+/**
+ * __end_current_label_crit_section - end crit section begun with __begin_...
+ * @label: label obtained from __begin_current_label_crit_section
+ * @needput: output: bool set by __begin_current_label_crit_section
+ *
+ * wrapper around __end_cred_crit_section() to pair nicely with
+ * __begin_current_label_crit_section()
+ */
+static inline void __end_current_label_crit_section(struct aa_label *label,
+						    bool needput)
+{
+	__end_cred_crit_section(label, needput);
+}
+
+/**
+ * end_current_label_crit_section - put a reference found with begin_current_label..
+ * @label: label reference to put
+ * @needput: output: bool set by __begin_current_label_crit_section
+ *
+ * Should only be used with a reference obtained with
+ * begin_current_label_crit_section and never used in situations where the
+ * task cred may be updated
+ */
+static inline void end_current_label_crit_section(struct aa_label *label,
+						  bool needput)
+{
+	if (label != aa_current_raw_label())
+		aa_put_label(label);
+}
+
+/**
+ * __begin_current_label_crit_section - current's confining label
+ * @needput: store whether the label needs to be put when ending crit section
+ *
+ * Returns: up to date confining label or the ns unconfined label (NOT NULL)
+ *
+ * safe to call inside locks
+ *
+ * The returned reference must be put with __end_current_label_crit_section()
+ * This must NOT be used if the task cred could be updated within the
+ * critical section between __begin_current_label_crit_section() ..
+ * __end_current_label_crit_section()
+ */
+static inline struct aa_label *__begin_current_label_crit_section(bool *needput)
+{
+	return __begin_cred_crit_section(current_cred(), needput);
+}
+
+/**
+ * begin_current_label_crit_section - current's confining label and update it
+ * @needput: store whether the label needs to be put when ending crit section
+ *
+ * Returns: up to date confining label or the ns unconfined label (NOT NULL)
+ *
+ * The returned reference must be put with end_current_label_crit_section()
+ * This should NOT be used if the task cred could be updated within the
+ * critical section between begin_current_label_crit_section() ..
+ * end_current_label_crit_section()
+ */
+static inline struct aa_label *begin_current_label_crit_section(bool *needput)
+{
+	struct aa_label *label = aa_current_raw_label();
+
+	label = __begin_current_label_crit_section(needput);
+	if (*needput)
+		aa_schedule_stale_label_replacement();
+
+	return label;
+}
+
+static inline struct aa_ns *aa_get_current_ns(void)
+{
+	struct aa_label *label;
+	struct aa_ns *ns;
+	bool needput;
+
+	label  = __begin_current_label_crit_section(&needput);
+	ns = aa_get_ns(labels_ns(label));
+	__end_current_label_crit_section(label, needput);
+
+	return ns;
+}
+
+#endif /* __AA_CONTEXT_H */
diff --git a/security/apparmor/include/crypto.h b/security/apparmor/include/crypto.h
new file mode 100644
index 000000000..f3ffd388c
--- /dev/null
+++ b/security/apparmor/include/crypto.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright 2013 Canonical Ltd.
+ */
+
+#ifndef __APPARMOR_CRYPTO_H
+#define __APPARMOR_CRYPTO_H
+
+#include "policy.h"
+
+#ifdef CONFIG_SECURITY_APPARMOR_HASH
+int init_profile_hash(void);
+unsigned int aa_hash_size(void);
+char *aa_calc_hash(void *data, size_t len);
+int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start,
+			 size_t len);
+#else
+static inline char *aa_calc_hash(void *data, size_t len)
+{
+	return NULL;
+}
+static inline int aa_calc_profile_hash(struct aa_profile *profile, u32 version,
+				       void *start, size_t len)
+{
+	return 0;
+}
+
+static inline unsigned int aa_hash_size(void)
+{
+	return 0;
+}
+#endif
+
+#endif /* __APPARMOR_CRYPTO_H */
diff --git a/security/apparmor/include/domain.h b/security/apparmor/include/domain.h
new file mode 100644
index 000000000..77f9a0ed0
--- /dev/null
+++ b/security/apparmor/include/domain.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security domain transition function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/binfmts.h>
+#include <linux/types.h>
+
+#include "label.h"
+
+#ifndef __AA_DOMAIN_H
+#define __AA_DOMAIN_H
+
+#define AA_CHANGE_NOFLAGS 0
+#define AA_CHANGE_TEST 1
+#define AA_CHANGE_CHILD 2
+#define AA_CHANGE_ONEXEC  4
+#define AA_CHANGE_STACK 8
+
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+				const char **name);
+
+int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm);
+
+int aa_change_hat(const char *hats[], int count, u64 token, int flags);
+int aa_change_profile(const char *fqname, int flags);
+
+#endif /* __AA_DOMAIN_H */
diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h
new file mode 100644
index 000000000..1614c07fc
--- /dev/null
+++ b/security/apparmor/include/file.h
@@ -0,0 +1,133 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_FILE_H
+#define __AA_FILE_H
+
+#include <linux/spinlock.h>
+
+#include "domain.h"
+#include "match.h"
+#include "perms.h"
+
+struct aa_policydb;
+struct aa_profile;
+struct path;
+
+#define mask_mode_t(X) (X & (MAY_EXEC | MAY_WRITE | MAY_READ | MAY_APPEND))
+
+#define AA_AUDIT_FILE_MASK	(MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND |\
+				 AA_MAY_CREATE | AA_MAY_DELETE |	\
+				 AA_MAY_GETATTR | AA_MAY_SETATTR | \
+				 AA_MAY_CHMOD | AA_MAY_CHOWN | AA_MAY_LOCK | \
+				 AA_EXEC_MMAP | AA_MAY_LINK)
+
+static inline struct aa_file_ctx *file_ctx(struct file *file)
+{
+	return file->f_security + apparmor_blob_sizes.lbs_file;
+}
+
+/* struct aa_file_ctx - the AppArmor context the file was opened in
+ * @lock: lock to update the ctx
+ * @label: label currently cached on the ctx
+ * @perms: the permission the file was opened with
+ */
+struct aa_file_ctx {
+	spinlock_t lock;
+	struct aa_label __rcu *label;
+	u32 allow;
+};
+
+/*
+ * The xindex is broken into 3 parts
+ * - index - an index into either the exec name table or the variable table
+ * - exec type - which determines how the executable name and index are used
+ * - flags - which modify how the destination name is applied
+ */
+#define AA_X_INDEX_MASK		AA_INDEX_MASK
+
+#define AA_X_TYPE_MASK		0x0c000000
+#define AA_X_NONE		AA_INDEX_NONE
+#define AA_X_NAME		0x04000000 /* use executable name px */
+#define AA_X_TABLE		0x08000000 /* use a specified name ->n# */
+
+#define AA_X_UNSAFE		0x10000000
+#define AA_X_CHILD		0x20000000
+#define AA_X_INHERIT		0x40000000
+#define AA_X_UNCONFINED		0x80000000
+
+/* need to make conditional which ones are being set */
+struct path_cond {
+	kuid_t uid;
+	umode_t mode;
+};
+
+#define COMBINED_PERM_MASK(X) ((X).allow | (X).audit | (X).quiet | (X).kill)
+
+int aa_audit_file(const struct cred *cred,
+		  struct aa_profile *profile, const struct aa_perms *perms,
+		  const char *op, u32 request, const char *name,
+		  const char *target, struct aa_label *tlabel, kuid_t ouid,
+		  const char *info, int error);
+
+struct aa_perms *aa_lookup_condperms(kuid_t subj_uid,
+				     struct aa_policydb *file_rules,
+				     aa_state_t state, struct path_cond *cond);
+aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start,
+			const char *name, struct path_cond *cond,
+			struct aa_perms *perms);
+
+int __aa_path_perm(const char *op, const struct cred *subj_cred,
+		   struct aa_profile *profile, const char *name,
+		   u32 request, struct path_cond *cond, int flags,
+		   struct aa_perms *perms);
+int aa_path_perm(const char *op, const struct cred *subj_cred,
+		 struct aa_label *label, const struct path *path,
+		 int flags, u32 request, struct path_cond *cond);
+
+int aa_path_link(const struct cred *subj_cred, struct aa_label *label,
+		 struct dentry *old_dentry, const struct path *new_dir,
+		 struct dentry *new_dentry);
+
+int aa_file_perm(const char *op, const struct cred *subj_cred,
+		 struct aa_label *label, struct file *file,
+		 u32 request, bool in_atomic);
+
+void aa_inherit_files(const struct cred *cred, struct files_struct *files);
+
+
+/**
+ * aa_map_file_to_perms - map file flags to AppArmor permissions
+ * @file: open file to map flags to AppArmor permissions
+ *
+ * Returns: apparmor permission set for the file
+ */
+static inline u32 aa_map_file_to_perms(struct file *file)
+{
+	int flags = file->f_flags;
+	u32 perms = 0;
+
+	if (file->f_mode & FMODE_WRITE)
+		perms |= MAY_WRITE;
+	if (file->f_mode & FMODE_READ)
+		perms |= MAY_READ;
+
+	if ((flags & O_APPEND) && (perms & MAY_WRITE))
+		perms = (perms & ~MAY_WRITE) | MAY_APPEND;
+	/* trunc implies write permission */
+	if (flags & O_TRUNC)
+		perms |= MAY_WRITE;
+	if (flags & O_CREAT)
+		perms |= AA_MAY_CREATE;
+
+	return perms;
+}
+
+#endif /* __AA_FILE_H */
diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h
new file mode 100644
index 000000000..323dd071a
--- /dev/null
+++ b/security/apparmor/include/ipc.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor ipc mediation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#ifndef __AA_IPC_H
+#define __AA_IPC_H
+
+#include <linux/sched.h>
+
+#define SIGUNKNOWN 0
+#define MAXMAPPED_SIG 35
+
+int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender,
+		  const struct cred *target_cred, struct aa_label *target,
+		  int sig);
+
+#endif /* __AA_IPC_H */
diff --git a/security/apparmor/include/label.h b/security/apparmor/include/label.h
new file mode 100644
index 000000000..2c869b7de
--- /dev/null
+++ b/security/apparmor/include/label.h
@@ -0,0 +1,492 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor label definitions
+ *
+ * Copyright 2017 Canonical Ltd.
+ */
+
+#ifndef __AA_LABEL_H
+#define __AA_LABEL_H
+
+#include <linux/atomic.h>
+#include <linux/audit.h>
+#include <linux/rbtree.h>
+#include <linux/rcupdate.h>
+
+#include "apparmor.h"
+#include "lib.h"
+
+struct aa_ns;
+struct aa_ruleset;
+
+#define LOCAL_VEC_ENTRIES 8
+#define DEFINE_VEC(T, V)						\
+	struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES + 1];	\
+	struct aa_ ## T **(V)
+
+#define vec_setup(T, V, N, GFP)						\
+({									\
+	if ((N) <= LOCAL_VEC_ENTRIES) {					\
+		typeof(N) i;						\
+		(V) = (_ ## V ## _localtmp);				\
+		for (i = 0; i <= (N); i++)				\
+			(V)[i] = NULL;					\
+	} else								\
+		(V) = kzalloc_objs(struct aa_ ## T *, (N) + 1, (GFP));	\
+	(V) ? 0 : -ENOMEM;						\
+})
+
+#define vec_cleanup(T, V, N)						\
+do {									\
+	int i;								\
+	for (i = 0; i < (N); i++) {					\
+		if (!IS_ERR_OR_NULL((V)[i]))				\
+			aa_put_ ## T((V)[i]);				\
+	}								\
+	if ((V) != _ ## V ## _localtmp)					\
+		kfree(V);						\
+} while (0)
+
+#define vec_last(VEC, SIZE) ((VEC)[(SIZE) - 1])
+#define vec_ns(VEC, SIZE) (vec_last((VEC), (SIZE))->ns)
+#define vec_labelset(VEC, SIZE) (&vec_ns((VEC), (SIZE))->labels)
+#define cleanup_domain_vec(V, L) cleanup_label_vec((V), (L)->size)
+
+struct aa_profile;
+#define VEC_FLAG_TERMINATE 1
+int aa_vec_unique(struct aa_profile **vec, int n, int flags);
+struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len,
+					     gfp_t gfp);
+#define aa_sort_and_merge_vec(N, V) \
+	aa_sort_and_merge_profiles((N), (struct aa_profile **)(V))
+
+
+/* struct aa_labelset - set of labels for a namespace
+ *
+ * Labels are reference counted; aa_labelset does not contribute to label
+ * reference counts. Once a label's last refcount is put it is removed from
+ * the set.
+ */
+struct aa_labelset {
+	rwlock_t lock;
+
+	struct rb_root root;
+};
+
+#define __labelset_for_each(LS, N) \
+	for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N))
+
+enum label_flags {
+	FLAG_HAT = 1,			/* profile is a hat */
+	FLAG_UNCONFINED = 2,		/* label unconfined only if all */
+	FLAG_NULL = 4,			/* profile is null learning profile */
+	FLAG_IX_ON_NAME_ERROR = 8,	/* fallback to ix on name lookup fail */
+	FLAG_IMMUTIBLE = 0x10,		/* don't allow changes/replacement */
+	FLAG_USER_DEFINED = 0x20,	/* user based profile - lower privs */
+	FLAG_NO_LIST_REF = 0x40,	/* list doesn't keep profile ref */
+	FLAG_NS_COUNT = 0x80,		/* carries NS ref count */
+	FLAG_IN_TREE = 0x100,		/* label is in tree */
+	FLAG_PROFILE = 0x200,		/* label is a profile */
+	FLAG_EXPLICIT = 0x400,		/* explicit static label */
+	FLAG_STALE = 0x800,		/* replaced/removed */
+	FLAG_RENAMED = 0x1000,		/* label has renaming in it */
+	FLAG_REVOKED = 0x2000,		/* label has revocation in it */
+	FLAG_DEBUG1 = 0x4000,
+	FLAG_DEBUG2 = 0x8000,
+
+	/* These flags must correspond with PATH_flags */
+	/* TODO: add new path flags */
+};
+
+struct aa_label;
+struct aa_proxy {
+	struct aa_common_ref count;
+	struct aa_label __rcu *label;
+};
+
+struct label_it {
+	int i, j;
+};
+
+/* struct aa_label_base - base info of label
+ * @count: ref count of active users
+ * @node: rbtree position
+ * @rcu: rcu callback struct
+ * @proxy: is set to the label that replaced this label
+ * @hname: text representation of the label (MAYBE_NULL)
+ * @flags: stale and other flags - values may change under label set lock
+ * @secid: secid that references this label
+ * @size: number of entries in @ent[]
+ * @mediates: bitmask for label_mediates
+ * profile: label vec when embedded in a profile FLAG_PROFILE is set
+ * rules: variable length rules in a profile FLAG_PROFILE is set
+ * vec: vector of profiles comprising the compound label
+ */
+struct aa_label {
+	struct aa_common_ref count;
+	struct rb_node node;
+	struct rcu_head rcu;
+	struct aa_proxy *proxy;
+	__counted char *hname;
+	long flags;
+	u32 secid;
+	int size;
+	u64 mediates;
+	union {
+		struct {
+			/* only used is the label is a profile, size of
+			 * rules[] is determined by the profile
+			 * profile[1] is poison or null as guard
+			 */
+			struct aa_profile *profile[2];
+			DECLARE_FLEX_ARRAY(struct aa_ruleset *, rules);
+		};
+		DECLARE_FLEX_ARRAY(struct aa_profile *, vec);
+	};
+};
+
+#define last_error(E, FN)				\
+do {							\
+	int __subE = (FN);				\
+	if (__subE)					\
+		(E) = __subE;				\
+} while (0)
+
+#define label_isprofile(X) ((X)->flags & FLAG_PROFILE)
+#define label_unconfined(X) ((X)->flags & FLAG_UNCONFINED)
+#define unconfined(X) label_unconfined(X)
+#define label_is_stale(X) ((X)->flags & FLAG_STALE)
+#define __label_make_stale(X) ((X)->flags |= FLAG_STALE)
+#define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size))
+#define labels_set(X) (&labels_ns(X)->labels)
+#define labels_view(X) labels_ns(X)
+#define labels_profile(X) ((X)->vec[(X)->size - 1])
+
+
+int aa_label_next_confined(const struct aa_label *l, int i);
+
+/* for each profile in a label */
+#define label_for_each(I, L, P)						\
+	for ((I).i = 0; ((P) = (L)->vec[(I).i]); ++((I).i))
+
+/* assumes break/goto ended label_for_each */
+#define label_for_each_cont(I, L, P)					\
+	for (++((I).i); ((P) = (L)->vec[(I).i]); ++((I).i))
+
+
+
+/* for each profile that is enforcing confinement in a label */
+#define label_for_each_confined(I, L, P)				\
+	for ((I).i = aa_label_next_confined((L), 0);			\
+	     ((P) = (L)->vec[(I).i]);					\
+	     (I).i = aa_label_next_confined((L), (I).i + 1))
+
+#define label_for_each_in_merge(I, A, B, P)				\
+	for ((I).i = (I).j = 0;						\
+	     ((P) = aa_label_next_in_merge(&(I), (A), (B)));		\
+	     )
+
+#define label_for_each_not_in_set(I, SET, SUB, P)			\
+	for ((I).i = (I).j = 0;						\
+	     ((P) = __aa_label_next_not_in_set(&(I), (SET), (SUB)));	\
+	     )
+
+#define next_in_ns(i, NS, L)						\
+({									\
+	typeof(i) ___i = (i);						\
+	while ((L)->vec[___i] && (L)->vec[___i]->ns != (NS))		\
+		(___i)++;						\
+	(___i);								\
+})
+
+#define label_for_each_in_ns(I, NS, L, P)				\
+	for ((I).i = next_in_ns(0, (NS), (L));				\
+	     ((P) = (L)->vec[(I).i]);					\
+	     (I).i = next_in_ns((I).i + 1, (NS), (L)))
+
+#define fn_for_each_in_ns(L, P, FN)					\
+({									\
+	struct label_it __i;						\
+	struct aa_ns *__ns = labels_ns(L);				\
+	int __E = 0;							\
+	label_for_each_in_ns(__i, __ns, (L), (P)) {			\
+		last_error(__E, (FN));					\
+	}								\
+	__E;								\
+})
+
+
+#define fn_for_each_XXX(L, P, FN, ...)					\
+({									\
+	struct label_it i;						\
+	int __E = 0;							\
+	label_for_each ## __VA_ARGS__(i, (L), (P)) {			\
+		last_error(__E, (FN));					\
+	}								\
+	__E;								\
+})
+
+#define fn_for_each(L, P, FN) fn_for_each_XXX(L, P, FN)
+#define fn_for_each_confined(L, P, FN) fn_for_each_XXX(L, P, FN, _confined)
+
+#define fn_for_each2_XXX(L1, L2, P, FN, ...)				\
+({									\
+	struct label_it i;						\
+	int __E = 0;							\
+	label_for_each ## __VA_ARGS__(i, (L1), (L2), (P)) {		\
+		last_error(__E, (FN));					\
+	}								\
+	__E;								\
+})
+
+#define fn_for_each_in_merge(L1, L2, P, FN)				\
+	fn_for_each2_XXX((L1), (L2), P, FN, _in_merge)
+#define fn_for_each_not_in_set(L1, L2, P, FN)				\
+	fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set)
+
+static inline bool label_mediates(const struct aa_label *L, unsigned char C)
+{
+	return (L)->mediates & (((u64) 1) << (C));
+}
+
+static inline bool label_mediates_safe(const struct aa_label *L, unsigned char C)
+{
+	if (C > AA_CLASS_LAST)
+		return false;
+	return label_mediates(L, C);
+}
+
+void aa_labelset_destroy(struct aa_labelset *ls);
+void aa_labelset_init(struct aa_labelset *ls);
+void __aa_labelset_update_subtree(struct aa_ns *ns);
+
+void aa_label_destroy(struct aa_label *label);
+void aa_label_free(struct aa_label *label);
+void aa_label_kref(struct kref *kref);
+bool aa_label_init(struct aa_label *label, int size, gfp_t gfp);
+struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp);
+
+bool aa_label_is_subset(const struct aa_label *set, const struct aa_label *sub);
+bool aa_label_is_unconfined_subset(const struct aa_label *set,
+				   const struct aa_label *sub);
+struct aa_profile *__aa_label_next_not_in_set(struct label_it *I,
+					     const struct aa_label *set,
+					     const struct aa_label *sub);
+bool aa_label_remove(struct aa_label *label);
+struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *l);
+bool aa_label_replace(struct aa_label *old, struct aa_label *new);
+bool aa_label_make_newest(struct aa_labelset *ls, struct aa_label *old,
+			  struct aa_label *new);
+
+struct aa_profile *aa_label_next_in_merge(struct label_it *I,
+					  const struct aa_label *a,
+					  const struct aa_label *b);
+struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b);
+struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b,
+				gfp_t gfp);
+
+
+bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp);
+
+#define FLAGS_NONE 0
+#define FLAG_SHOW_MODE 1
+#define FLAG_VIEW_SUBNS 2
+#define FLAG_HIDDEN_UNCONFINED 4
+#define FLAG_ABS_ROOT 8
+int aa_label_snxprint(char *str, size_t size, struct aa_ns *view,
+		      struct aa_label *label, int flags);
+int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label,
+		      int flags, gfp_t gfp);
+int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns,
+			 struct aa_label *label, int flags, gfp_t gfp);
+void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns,
+		     struct aa_label *label, int flags, gfp_t gfp);
+void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns,
+			 struct aa_label *label, int flags, gfp_t gfp);
+void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags,
+		      gfp_t gfp);
+void aa_label_printk(struct aa_label *label, gfp_t gfp);
+
+struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str,
+				     size_t n, gfp_t gfp, bool create,
+				     bool force_stack);
+struct aa_label *aa_label_parse(struct aa_label *base, const char *str,
+				gfp_t gfp, bool create, bool force_stack);
+
+static inline const char *aa_label_strn_split(const char *str, int n)
+{
+	const char *pos;
+	aa_state_t state;
+
+	state = aa_dfa_matchn_until(stacksplitdfa, DFA_START, str, n, &pos);
+	if (!ACCEPT_TABLE(stacksplitdfa)[state])
+		return NULL;
+
+	return pos - 3;
+}
+
+static inline const char *aa_label_str_split(const char *str)
+{
+	const char *pos;
+	aa_state_t state;
+
+	state = aa_dfa_match_until(stacksplitdfa, DFA_START, str, &pos);
+	if (!ACCEPT_TABLE(stacksplitdfa)[state])
+		return NULL;
+
+	return pos - 3;
+}
+
+
+
+struct aa_perms;
+struct aa_ruleset;
+int aa_label_match(const struct aa_profile *profile, struct aa_ruleset *rules,
+		   struct aa_label *label, aa_state_t state, bool subns,
+		   u32 request, struct aa_perms *perms);
+
+
+/**
+ * __aa_get_label - get a reference count to uncounted label reference
+ * @l: reference to get a count on
+ *
+ * Returns: pointer to reference OR NULL if race is lost and reference is
+ *          being repeated.
+ * Requires: lock held, and the return code MUST be checked
+ */
+static inline struct aa_label *__aa_get_label(struct aa_label *l)
+{
+	if (l && kref_get_unless_zero(&l->count.count))
+		return l;
+
+	return NULL;
+}
+
+static inline struct aa_label *aa_get_label(struct aa_label *l)
+{
+	if (l)
+		kref_get(&(l->count.count));
+
+	return l;
+}
+
+
+/**
+ * aa_get_label_rcu - increment refcount on a label that can be replaced
+ * @l: pointer to label that can be replaced (NOT NULL)
+ *
+ * Returns: pointer to a refcounted label.
+ *     else NULL if no label
+ */
+static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l)
+{
+	struct aa_label *c;
+
+	rcu_read_lock();
+	do {
+		c = rcu_dereference(*l);
+	} while (c && !kref_get_unless_zero(&c->count.count));
+	rcu_read_unlock();
+
+	return c;
+}
+
+/**
+ * aa_get_newest_label - find the newest version of @l
+ * @l: the label to check for newer versions of
+ *
+ * Returns: refcounted newest version of @l taking into account
+ *          replacement, renames and removals
+ *          return @l.
+ */
+static inline struct aa_label *aa_get_newest_label(struct aa_label *l)
+{
+	if (!l)
+		return NULL;
+
+	if (label_is_stale(l)) {
+		struct aa_label *tmp;
+
+		AA_BUG(!l->proxy);
+		AA_BUG(!l->proxy->label);
+		/* BUG: only way this can happen is @l ref count and its
+		 * replacement count have gone to 0 and are on their way
+		 * to destruction. ie. we have a refcounting error
+		 */
+		tmp = aa_get_label_rcu(&l->proxy->label);
+		AA_BUG(!tmp);
+
+		return tmp;
+	}
+
+	return aa_get_label(l);
+}
+
+/**
+ * aa_get_newest_label_condref - find the newest version of @l
+ * @l: the label to check for newer versions of
+ * @needput: returns whether the reference needs put
+ *
+ * Returns: refcounted newest version of @l taking into account
+ *          replacement, renames and removals
+ *          return @l.
+ */
+static inline struct aa_label *aa_get_newest_label_condref(struct aa_label *l,
+							   bool *needput)
+{
+	if (l && unlikely(label_is_stale(l))) {
+		struct aa_label *tmp;
+
+		AA_BUG(!l->proxy);
+		AA_BUG(!l->proxy->label);
+		/* BUG: only way this can happen is @l ref count and its
+		 * replacement count have gone to 0 and are on their way
+		 * to destruction. ie. we have a refcounting error
+		 */
+		tmp = aa_get_label_rcu(&l->proxy->label);
+		AA_BUG(!tmp);
+
+		*needput = true;
+		return tmp;
+	}
+
+	*needput = false;
+	return l;
+}
+
+static inline void aa_put_label(struct aa_label *l)
+{
+	if (l)
+		kref_put(&l->count.count, aa_label_kref);
+}
+
+/* wrapper fn to indicate semantics of the check */
+static inline bool __aa_subj_label_is_cached(const struct aa_label *subj_label,
+					  const struct aa_label *obj_label)
+{
+	return aa_label_is_subset(obj_label, subj_label);
+}
+
+
+struct aa_proxy *aa_alloc_proxy(struct aa_label *l, gfp_t gfp);
+void aa_proxy_kref(struct kref *kref);
+
+static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy)
+{
+	if (proxy)
+		kref_get(&(proxy->count.count));
+
+	return proxy;
+}
+
+static inline void aa_put_proxy(struct aa_proxy *proxy)
+{
+	if (proxy)
+		kref_put(&proxy->count.count, aa_proxy_kref);
+}
+
+void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new);
+
+#endif /* __AA_LABEL_H */
diff --git a/security/apparmor/include/lib.h b/security/apparmor/include/lib.h
new file mode 100644
index 000000000..475dd71fb
--- /dev/null
+++ b/security/apparmor/include/lib.h
@@ -0,0 +1,363 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor lib definitions
+ *
+ * 2017 Canonical Ltd.
+ */
+
+#ifndef __AA_LIB_H
+#define __AA_LIB_H
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/lsm_hooks.h>
+
+#include "match.h"
+
+extern struct aa_dfa *stacksplitdfa;
+
+/*
+ * split individual debug cases out in preparation for finer grained
+ * debug controls in the future.
+ */
+#define dbg_printk(__fmt, __args...) pr_debug(__fmt, ##__args)
+
+#define DEBUG_NONE 0
+#define DEBUG_LABEL_ABS_ROOT 1
+#define DEBUG_LABEL 2
+#define DEBUG_DOMAIN 4
+#define DEBUG_POLICY 8
+#define DEBUG_INTERFACE 0x10
+#define DEBUG_UNPACK 0x20
+#define DEBUG_TAGS 0x40
+
+#define DEBUG_ALL 0x7f		/* update if new DEBUG_X added */
+#define DEBUG_PARSE_ERROR (-1)
+
+#define DEBUG_ON (aa_g_debug != DEBUG_NONE)
+#define DEBUG_ABS_ROOT (aa_g_debug & DEBUG_LABEL_ABS_ROOT)
+
+#define AA_DEBUG(opt, fmt, args...)					\
+	do {								\
+		if (aa_g_debug & opt)					\
+			pr_warn_ratelimited("%s: " fmt, __func__, ##args); \
+	} while (0)
+#define AA_DEBUG_LABEL(LAB, X, fmt, args...)				\
+do {									\
+	if ((LAB)->flags & FLAG_DEBUG1)					\
+		AA_DEBUG(X, fmt, ##args);				\
+} while (0)
+
+#define AA_DEBUG_PROFILE(PROF, X, fmt...) AA_DEBUG_LABEL(&(PROF)->label, X, ##fmt)
+
+#define AA_WARN(X) WARN((X), "APPARMOR WARN %s: %s\n", __func__, #X)
+
+#define AA_BUG(X, args...)						    \
+	do {								    \
+		_Pragma("GCC diagnostic ignored \"-Wformat-zero-length\""); \
+		AA_BUG_FMT((X), "" args);				    \
+		_Pragma("GCC diagnostic warning \"-Wformat-zero-length\""); \
+	} while (0)
+#ifdef CONFIG_SECURITY_APPARMOR_DEBUG_ASSERTS
+#define AA_BUG_FMT(X, fmt, args...)					\
+	WARN((X), "AppArmor WARN %s: (" #X "): " fmt, __func__, ##args)
+#else
+#define AA_BUG_FMT(X, fmt, args...)					\
+	do {								\
+		BUILD_BUG_ON_INVALID(X);				\
+		no_printk(fmt, ##args);					\
+	} while (0)
+#endif
+
+int aa_parse_debug_params(const char *str);
+int aa_print_debug_params(char *buffer);
+
+#define AA_ERROR(fmt, args...)						\
+	pr_err_ratelimited("AppArmor: " fmt, ##args)
+
+/* Flag indicating whether initialization completed */
+extern int apparmor_initialized;
+
+/* semantic split of scope and view */
+#define aa_in_scope(SUBJ, OBJ)						\
+	aa_ns_visible(SUBJ, OBJ, false)
+
+#define aa_in_view(SUBJ, OBJ)						\
+	aa_ns_visible(SUBJ, OBJ, true)
+
+#define label_for_each_in_scope(I, NS, L, P)				\
+	label_for_each_in_ns(I, NS, L, P)
+
+#define fn_for_each_in_scope(L, P, FN)					\
+	fn_for_each_in_ns(L, P, FN)
+
+/* fn's in lib */
+const char *skipn_spaces(const char *str, size_t n);
+const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name,
+			     size_t *ns_len);
+void aa_info_message(const char *str);
+
+/* Security blob offsets */
+extern struct lsm_blob_sizes apparmor_blob_sizes;
+
+enum reftype {
+	REF_NS,
+	REF_PROXY,
+	REF_RAWDATA,
+};
+
+/* common reference count used by data the shows up in aafs */
+struct aa_common_ref {
+	struct kref count;
+	enum reftype reftype;
+};
+
+/**
+ * aa_strneq - compare null terminated @str to a non null terminated substring
+ * @str: a null terminated string
+ * @sub: a substring, not necessarily null terminated
+ * @len: length of @sub to compare
+ *
+ * The @str string must be full consumed for this to be considered a match
+ */
+static inline bool aa_strneq(const char *str, const char *sub, int len)
+{
+	return !strncmp(str, sub, len) && !str[len];
+}
+
+/**
+ * aa_dfa_null_transition - step to next state after null character
+ * @dfa: the dfa to match against
+ * @start: the state of the dfa to start matching in
+ *
+ * aa_dfa_null_transition transitions to the next state after a null
+ * character which is not used in standard matching and is only
+ * used to separate pairs.
+ */
+static inline aa_state_t aa_dfa_null_transition(const struct aa_dfa *dfa,
+						aa_state_t start)
+{
+	/* the null transition only needs the string's null terminator byte */
+	return aa_dfa_next(dfa, start, 0);
+}
+
+static inline bool path_mediated_fs(struct dentry *dentry)
+{
+	return !(dentry->d_sb->s_flags & SB_NOUSER);
+}
+
+struct aa_str_table_ent {
+	int count;
+	int size;
+	char *strs;
+};
+
+struct aa_str_table {
+	int size;
+	struct aa_str_table_ent *table;
+};
+
+bool aa_resize_str_table(struct aa_str_table *t, int newsize, gfp_t gfp);
+void aa_destroy_str_table(struct aa_str_table *table);
+
+struct counted_str {
+	struct kref count;
+	char name[];
+};
+
+#define str_to_counted(str) \
+	((struct counted_str *)(str - offsetof(struct counted_str, name)))
+
+#define __counted	/* atm just a notation */
+
+void aa_str_kref(struct kref *kref);
+char *aa_str_alloc(int size, gfp_t gfp);
+
+
+static inline __counted char *aa_get_str(__counted char *str)
+{
+	if (str)
+		kref_get(&(str_to_counted(str)->count));
+
+	return str;
+}
+
+static inline void aa_put_str(__counted char *str)
+{
+	if (str)
+		kref_put(&str_to_counted(str)->count, aa_str_kref);
+}
+
+
+/* struct aa_policy - common part of both namespaces and profiles
+ * @name: name of the object
+ * @hname - The hierarchical name
+ * @list: list policy object is on
+ * @profiles: head of the profiles list contained in the object
+ */
+struct aa_policy {
+	const char *name;
+	__counted char *hname;
+	struct list_head list;
+	struct list_head profiles;
+};
+
+/**
+ * basename - find the last component of an hname
+ * @hname: hname to find the base profile name component of  (NOT NULL)
+ *
+ * Returns: the tail (base profile name) name component of an hname
+ */
+static inline const char *basename(const char *hname)
+{
+	char *split;
+
+	hname = strim((char *)hname);
+	for (split = strstr(hname, "//"); split; split = strstr(hname, "//"))
+		hname = split + 2;
+
+	return hname;
+}
+
+/**
+ * __policy_find - find a policy by @name on a policy list
+ * @head: list to search  (NOT NULL)
+ * @name: name to search for  (NOT NULL)
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted policy that match @name or NULL if not found
+ */
+static inline struct aa_policy *__policy_find(struct list_head *head,
+					      const char *name)
+{
+	struct aa_policy *policy;
+
+	list_for_each_entry_rcu(policy, head, list) {
+		if (!strcmp(policy->name, name))
+			return policy;
+	}
+	return NULL;
+}
+
+/**
+ * __policy_strn_find - find a policy that's name matches @len chars of @str
+ * @head: list to search  (NOT NULL)
+ * @str: string to search for  (NOT NULL)
+ * @len: length of match required
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted policy that match @str or NULL if not found
+ *
+ * if @len == strlen(@strlen) then this is equiv to __policy_find
+ * other wise it allows searching for policy by a partial match of name
+ */
+static inline struct aa_policy *__policy_strn_find(struct list_head *head,
+					    const char *str, int len)
+{
+	struct aa_policy *policy;
+
+	list_for_each_entry_rcu(policy, head, list) {
+		if (aa_strneq(policy->name, str, len))
+			return policy;
+	}
+
+	return NULL;
+}
+
+bool aa_policy_init(struct aa_policy *policy, const char *prefix,
+		    const char *name, gfp_t gfp);
+void aa_policy_destroy(struct aa_policy *policy);
+
+
+/*
+ * fn_label_build - abstract out the build of a label transition
+ * @L: label the transition is being computed for
+ * @P: profile parameter derived from L by this macro, can be passed to FN
+ * @GFP: memory allocation type to use
+ * @FN: fn to call for each profile transition. @P is set to the profile
+ *
+ * Returns: new label on success
+ *	    NULL if all callbacks decline to specify a transition
+ *          ERR_PTR if build @FN fails
+ *
+ * @FN must return a label or ERR_PTR on failure.
+ */
+#define fn_label_build(L, P, GFP, FN)					\
+({									\
+	__label__ __do_cleanup, __done;					\
+	struct aa_label *__new_ = NULL;					\
+									\
+	if ((L)->size > 1) {						\
+		/* TODO: add cache of transitions already done */	\
+		struct label_it __i;					\
+		int __j, __k, __count;					\
+		DEFINE_VEC(label, __lvec);				\
+		DEFINE_VEC(profile, __pvec);				\
+		if (vec_setup(label, __lvec, (L)->size, (GFP)))	{	\
+			__new_ = ERR_PTR(-ENOMEM);			\
+			goto __done;					\
+		}							\
+		__j = 0;						\
+		label_for_each(__i, (L), (P)) {				\
+			__new_ = (FN);					\
+			if (!__new_)					\
+				continue;				\
+			if (IS_ERR(__new_))				\
+				goto __do_cleanup;			\
+			__lvec[__j++] = __new_;				\
+		}							\
+		if (__j == 0)						\
+			/* no components adding to build */		\
+			goto __do_cleanup;				\
+		for (__j = __count = 0; __j < (L)->size; __j++)		\
+			__count += __lvec[__j]->size;			\
+		if (!vec_setup(profile, __pvec, __count, (GFP))) {	\
+			for (__j = __k = 0; __j < (L)->size; __j++) {	\
+				label_for_each(__i, __lvec[__j], (P))	\
+					__pvec[__k++] = aa_get_profile(P); \
+			}						\
+			__count -= aa_vec_unique(__pvec, __count, 0);	\
+			if (__count > 1) {				\
+				__new_ = aa_vec_find_or_create_label(__pvec,\
+						     __count, (GFP));	\
+				if (!__new_)				\
+					__new_ = ERR_PTR(-ENOMEM);	\
+			} else						\
+				__new_ = aa_get_label(&__pvec[0]->label); \
+			vec_cleanup(profile, __pvec, __count);		\
+		} else							\
+			__new_ = ERR_PTR(-ENOMEM);			\
+__do_cleanup:								\
+		vec_cleanup(label, __lvec, (L)->size);			\
+	} else {							\
+		(P) = labels_profile(L);				\
+		__new_ = (FN);						\
+	}								\
+__done:									\
+	if (IS_ERR(__new_))						\
+		AA_DEBUG(DEBUG_LABEL, "label build failed %ld\n", PTR_ERR(__new_)); \
+	(__new_);							\
+})
+
+
+#define __fn_build_in_scope(NS, P, NS_FN, OTHER_FN)			\
+({									\
+	struct aa_label *__new;						\
+	if ((P)->ns != (NS))						\
+		__new = (OTHER_FN);					\
+	else								\
+		__new = (NS_FN);					\
+	(__new);							\
+})
+
+#define fn_label_build_in_scope(L, P, GFP, NS_FN, OTHER_FN)		\
+({									\
+	fn_label_build((L), (P), (GFP),					\
+		__fn_build_in_scope(labels_ns(L), (P), (NS_FN), (OTHER_FN))); \
+})
+
+#endif /* __AA_LIB_H */
diff --git a/security/apparmor/include/match.h b/security/apparmor/include/match.h
new file mode 100644
index 000000000..f7bd7855f
--- /dev/null
+++ b/security/apparmor/include/match.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy dfa matching engine definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2012 Canonical Ltd.
+ */
+
+#ifndef __AA_MATCH_H
+#define __AA_MATCH_H
+
+#include <linux/kref.h>
+
+#define DFA_NOMATCH			0
+#define DFA_START			1
+
+
+/*
+ * The format used for transition tables is based on the GNU flex table
+ * file format (--tables-file option; see Table File Format in the flex
+ * info pages and the flex sources for documentation). The magic number
+ * used in the header is 0x1B5E783D instead of 0xF13C57B1 though, because
+ * new tables have been defined and others YY_ID_CHK (check) and YY_ID_DEF
+ * (default) tables are used slightly differently (see the apparmor-parser
+ * package).
+ *
+ *
+ * The data in the packed dfa is stored in network byte order, and the tables
+ * are arranged for flexibility.  We convert the table data to host native
+ * byte order.
+ *
+ * The dfa begins with a table set header, and is followed by the actual
+ * tables.
+ */
+
+#define YYTH_MAGIC	0x1B5E783D
+#define YYTH_FLAG_DIFF_ENCODE	1
+#define YYTH_FLAG_OOB_TRANS	2
+#define YYTH_FLAGS (YYTH_FLAG_DIFF_ENCODE | YYTH_FLAG_OOB_TRANS)
+
+#define MAX_OOB_SUPPORTED	1
+
+struct table_set_header {
+	u32 th_magic;		/* YYTH_MAGIC */
+	u32 th_hsize;
+	u32 th_ssize;
+	u16 th_flags;
+	char th_version[];
+};
+
+/* The YYTD_ID are one less than flex table mappings.  The flex id
+ * has 1 subtracted at table load time, this allows us to directly use the
+ * ID's as indexes.
+ */
+#define	YYTD_ID_ACCEPT	0
+#define YYTD_ID_BASE	1
+#define YYTD_ID_CHK	2
+#define YYTD_ID_DEF	3
+#define YYTD_ID_EC	4
+#define YYTD_ID_META	5
+#define YYTD_ID_ACCEPT2 6
+#define YYTD_ID_NXT	7
+#define YYTD_ID_TSIZE	8
+#define YYTD_ID_MAX	8
+
+#define YYTD_DATA8	1
+#define YYTD_DATA16	2
+#define YYTD_DATA32	4
+#define YYTD_DATA64	8
+
+/* ACCEPT & ACCEPT2 tables gets 6 dedicated flags, YYTD_DATAX define the
+ * first flags
+ */
+#define ACCEPT1_FLAGS(X) ((X) & 0x3f)
+#define ACCEPT2_FLAGS(X) ACCEPT1_FLAGS((X) >> YYTD_ID_ACCEPT2)
+#define TO_ACCEPT1_FLAG(X) ACCEPT1_FLAGS(X)
+#define TO_ACCEPT2_FLAG(X) (ACCEPT1_FLAGS(X) << YYTD_ID_ACCEPT2)
+#define DFA_FLAG_VERIFY_STATES 0x1000
+
+struct table_header {
+	u16 td_id;
+	u16 td_flags;
+	u32 td_hilen;
+	u32 td_lolen;
+	char td_data[];
+};
+
+#define TABLE_DATAU16(TABLE) ((u16 *)((TABLE)->td_data))
+#define TABLE_DATAU32(TABLE) ((u32 *)((TABLE)->td_data))
+#define DEFAULT_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_DEF]->td_data))
+#define BASE_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_BASE]->td_data))
+#define NEXT_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_NXT]->td_data))
+#define CHECK_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_CHK]->td_data))
+#define EQUIV_TABLE(DFA) ((u8 *)((DFA)->tables[YYTD_ID_EC]->td_data))
+#define ACCEPT_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_ACCEPT]->td_data))
+#define ACCEPT_TABLE2(DFA) ((u32 *)((DFA)->tables[YYTD_ID_ACCEPT2]->td_data))
+
+struct aa_dfa {
+	struct kref count;
+	u16 flags;
+	u32 max_oob;
+	struct table_header *tables[YYTD_ID_TSIZE];
+};
+
+#define UNPACK_ARRAY(TABLE, BLOB, LEN, TTYPE, BTYPE, NTOHX)	\
+	do { \
+		typeof(LEN) __i; \
+		TTYPE *__t = (TTYPE *) TABLE; \
+		BTYPE *__b = (BTYPE *) BLOB; \
+		BUILD_BUG_ON(sizeof(TTYPE) != sizeof(BTYPE)); \
+		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) \
+			memcpy(__t, __b, (LEN) * sizeof(BTYPE)); \
+		else /* copy & convert from big-endian */ \
+			for (__i = 0; __i < LEN; __i++) { \
+				__t[__i] = NTOHX(&__b[__i]); \
+			} \
+	} while (0)
+
+static inline size_t table_size(size_t len, size_t el_size)
+{
+	return ALIGN(sizeof(struct table_header) + len * el_size, 8);
+}
+
+#define aa_state_t unsigned int
+
+struct aa_dfa *aa_dfa_unpack(const void *blob, size_t size, int flags);
+aa_state_t aa_dfa_match_len(const struct aa_dfa *dfa, aa_state_t start,
+			    const char *str, int len);
+aa_state_t aa_dfa_match(const struct aa_dfa *dfa, aa_state_t start,
+			const char *str);
+aa_state_t aa_dfa_next(const struct aa_dfa *dfa, aa_state_t state,
+		       const char c);
+aa_state_t aa_dfa_outofband_transition(const struct aa_dfa *dfa,
+				       aa_state_t state);
+aa_state_t aa_dfa_match_until(const struct aa_dfa *dfa, aa_state_t start,
+			      const char *str, const char **retpos);
+aa_state_t aa_dfa_matchn_until(const struct aa_dfa *dfa, aa_state_t start,
+			       const char *str, int n, const char **retpos);
+
+void aa_dfa_free_kref(struct kref *kref);
+
+/* This needs to be a power of 2 */
+#define WB_HISTORY_SIZE 32
+struct match_workbuf {
+	unsigned int pos;
+	unsigned int len;
+	aa_state_t history[WB_HISTORY_SIZE];
+};
+#define DEFINE_MATCH_WB(N)		\
+struct match_workbuf N = {		\
+	.pos = 0,			\
+	.len = 0,			\
+}
+
+aa_state_t aa_dfa_leftmatch(const struct aa_dfa *dfa, aa_state_t start,
+			    const char *str, unsigned int *count);
+
+/**
+ * aa_get_dfa - increment refcount on dfa @p
+ * @dfa: dfa  (MAYBE NULL)
+ *
+ * Returns: pointer to @dfa if @dfa is NULL will return NULL
+ * Requires: @dfa must be held with valid refcount when called
+ */
+static inline struct aa_dfa *aa_get_dfa(struct aa_dfa *dfa)
+{
+	if (dfa)
+		kref_get(&(dfa->count));
+
+	return dfa;
+}
+
+/**
+ * aa_put_dfa - put a dfa refcount
+ * @dfa: dfa to put refcount   (MAYBE NULL)
+ *
+ * Requires: if @dfa != NULL that a valid refcount be held
+ */
+static inline void aa_put_dfa(struct aa_dfa *dfa)
+{
+	if (dfa)
+		kref_put(&dfa->count, aa_dfa_free_kref);
+}
+
+#define MATCH_FLAG_DIFF_ENCODE 0x80000000
+#define MARK_DIFF_ENCODE 0x40000000
+#define MATCH_FLAG_OOB_TRANSITION 0x20000000
+#define MARK_DIFF_ENCODE_VERIFIED 0x10000000
+#define MATCH_FLAGS_MASK 0xff000000
+#define MATCH_FLAGS_VALID (MATCH_FLAG_DIFF_ENCODE | MATCH_FLAG_OOB_TRANSITION)
+#define MATCH_FLAGS_INVALID (MATCH_FLAGS_MASK & ~MATCH_FLAGS_VALID)
+
+#endif /* __AA_MATCH_H */
diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h
new file mode 100644
index 000000000..46834f828
--- /dev/null
+++ b/security/apparmor/include/mount.h
@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright 2017 Canonical Ltd.
+ */
+
+#ifndef __AA_MOUNT_H
+#define __AA_MOUNT_H
+
+#include <linux/fs.h>
+#include <linux/path.h>
+
+#include "domain.h"
+#include "policy.h"
+
+/* mount perms */
+#define AA_MAY_PIVOTROOT	0x01
+#define AA_MAY_MOUNT		0x02
+#define AA_MAY_UMOUNT		0x04
+#define AA_AUDIT_DATA		0x40
+#define AA_MNT_CONT_MATCH	0x40
+
+#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN)
+
+int aa_remount(const struct cred *subj_cred,
+	       struct aa_label *label, const struct path *path,
+	       unsigned long flags, void *data);
+
+int aa_bind_mount(const struct cred *subj_cred,
+		  struct aa_label *label, const struct path *path,
+		  const char *old_name, unsigned long flags);
+
+
+int aa_mount_change_type(const struct cred *subj_cred,
+			 struct aa_label *label, const struct path *path,
+			 unsigned long flags);
+
+int aa_move_mount_old(const struct cred *subj_cred,
+		      struct aa_label *label, const struct path *path,
+		      const char *old_name);
+int aa_move_mount(const struct cred *subj_cred,
+		  struct aa_label *label, const struct path *from_path,
+		  const struct path *to_path);
+
+int aa_new_mount(const struct cred *subj_cred,
+		 struct aa_label *label, const char *dev_name,
+		 const struct path *path, const char *type, unsigned long flags,
+		 void *data);
+
+int aa_umount(const struct cred *subj_cred,
+	      struct aa_label *label, struct vfsmount *mnt, int flags);
+
+int aa_pivotroot(const struct cred *subj_cred,
+		 struct aa_label *label, const struct path *old_path,
+		 const struct path *new_path);
+
+#endif /* __AA_MOUNT_H */
diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h
new file mode 100644
index 000000000..375341929
--- /dev/null
+++ b/security/apparmor/include/net.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#ifndef __AA_NET_H
+#define __AA_NET_H
+
+#include <net/sock.h>
+#include <linux/path.h>
+
+#include "apparmorfs.h"
+#include "label.h"
+#include "perms.h"
+#include "policy.h"
+
+#define AA_MAY_SEND		AA_MAY_WRITE
+#define AA_MAY_RECEIVE		AA_MAY_READ
+
+#define AA_MAY_SHUTDOWN		AA_MAY_DELETE
+
+#define AA_MAY_CONNECT		AA_MAY_OPEN
+#define AA_MAY_ACCEPT		0x00100000
+
+#define AA_MAY_BIND		0x00200000
+#define AA_MAY_LISTEN		0x00400000
+
+#define AA_MAY_SETOPT		0x01000000
+#define AA_MAY_GETOPT		0x02000000
+
+#define NET_PERMS_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE |    \
+			AA_MAY_SHUTDOWN | AA_MAY_BIND | AA_MAY_LISTEN |	  \
+			AA_MAY_CONNECT | AA_MAY_ACCEPT | AA_MAY_SETATTR | \
+			AA_MAY_GETATTR | AA_MAY_SETOPT | AA_MAY_GETOPT)
+
+#define NET_FS_PERMS (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE |	\
+		      AA_MAY_SHUTDOWN | AA_MAY_CONNECT | AA_MAY_RENAME |\
+		      AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_CHMOD |	\
+		      AA_MAY_CHOWN | AA_MAY_CHGRP | AA_MAY_LOCK |	\
+		      AA_MAY_MPROT)
+
+#define NET_PEER_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CONNECT |	\
+		       AA_MAY_ACCEPT)
+struct aa_sk_ctx {
+	struct aa_label __rcu *label;
+	struct aa_label __rcu *peer;
+	struct aa_label __rcu *peer_lastupdate;	/* ptr cmp only, no deref */
+};
+
+static inline struct aa_sk_ctx *aa_sock(const struct sock *sk)
+{
+	return sk->sk_security + apparmor_blob_sizes.lbs_sock;
+}
+
+#define DEFINE_AUDIT_NET(NAME, OP, CRED, SK, F, T, P)			  \
+	struct lsm_network_audit NAME ## _net = { .sk = (SK),		  \
+						  .family = (F)};	  \
+	DEFINE_AUDIT_DATA(NAME,						  \
+			  ((SK) && (F) != AF_UNIX) ? LSM_AUDIT_DATA_NET : \
+						     LSM_AUDIT_DATA_NONE, \
+						     AA_CLASS_NET,        \
+			  OP);						  \
+	NAME.common.u.net = &(NAME ## _net);				  \
+	NAME.subj_cred = (CRED);					  \
+	NAME.net.type = (T);						  \
+	NAME.net.protocol = (P)
+
+#define DEFINE_AUDIT_SK(NAME, OP, CRED, SK)				     \
+	DEFINE_AUDIT_NET(NAME, OP, CRED, SK, (SK)->sk_family, (SK)->sk_type, \
+			 (SK)->sk_protocol)
+
+
+struct aa_secmark {
+	u8 audit;
+	u8 deny;
+	u32 secid;
+	char *label;
+};
+
+extern struct aa_sfs_entry aa_sfs_entry_network[];
+extern struct aa_sfs_entry aa_sfs_entry_networkv9[];
+
+int aa_do_perms(struct aa_profile *profile, struct aa_policydb *policy,
+		aa_state_t state, u32 request, const struct aa_perms *p,
+		struct apparmor_audit_data *ad);
+/* passing in state returned by XXX_mediates_AF() */
+aa_state_t aa_match_to_prot(struct aa_policydb *policy, aa_state_t state,
+			    u32 request, u16 af, int type, int protocol,
+			    struct aa_perms **p, const char **info);
+void audit_net_cb(struct audit_buffer *ab, void *va);
+int aa_profile_af_perm(struct aa_profile *profile,
+		       struct apparmor_audit_data *ad,
+		       u32 request, u16 family, int type, int protocol);
+int aa_af_perm(const struct cred *subj_cred, struct aa_label *label,
+	       const char *op, u32 request, u16 family,
+	       int type, int protocol);
+static inline int aa_profile_af_sk_perm(struct aa_profile *profile,
+					struct apparmor_audit_data *ad,
+					u32 request,
+					const struct sock *sk)
+{
+	return aa_profile_af_perm(profile, ad, request, sk->sk_family,
+				  sk->sk_type, sk->sk_protocol);
+}
+int aa_sk_perm(const char *op, u32 request, const struct sock *sk);
+int aa_label_sk_perm(const struct cred *subj_cred, struct aa_label *label,
+		     const char *op, u32 request, const struct sock *sk);
+int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label,
+		      const char *op, u32 request,
+		      struct file *file);
+
+int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
+			   u32 secid, const struct sock *sk);
+
+#endif /* __AA_NET_H */
diff --git a/security/apparmor/include/path.h b/security/apparmor/include/path.h
new file mode 100644
index 000000000..250812a77
--- /dev/null
+++ b/security/apparmor/include/path.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor basic path manipulation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_PATH_H
+#define __AA_PATH_H
+
+#include <linux/path.h>
+#include <linux/types.h>
+
+enum path_flags {
+	PATH_IS_DIR = 0x1,		/* path is a directory */
+	PATH_SOCK_COND = 0x2,
+	PATH_CONNECT_PATH = 0x4,	/* connect disconnected paths to / */
+	PATH_CHROOT_REL = 0x8,		/* do path lookup relative to chroot */
+	PATH_CHROOT_NSCONNECT = 0x10,	/* connect paths that are at ns root */
+
+	PATH_DELEGATE_DELETED = 0x10000, /* delegate deleted files */
+	PATH_MEDIATE_DELETED = 0x20000,	 /* mediate deleted paths */
+};
+
+int aa_path_name(const struct path *path, int flags, char *buffer,
+		 const char **name, const char **info,
+		 const char *disconnected);
+
+#define IN_ATOMIC true
+char *aa_get_buffer(bool in_atomic);
+void aa_put_buffer(char *buf);
+
+#endif /* __AA_PATH_H */
diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h
new file mode 100644
index 000000000..ee25eb8e7
--- /dev/null
+++ b/security/apparmor/include/perms.h
@@ -0,0 +1,220 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor basic permission sets definitions.
+ *
+ * Copyright 2017 Canonical Ltd.
+ */
+
+#ifndef __AA_PERM_H
+#define __AA_PERM_H
+
+#include <linux/fs.h>
+#include "label.h"
+
+#define AA_MAY_EXEC		MAY_EXEC
+#define AA_MAY_WRITE		MAY_WRITE
+#define AA_MAY_READ		MAY_READ
+#define AA_MAY_APPEND		MAY_APPEND
+
+#define AA_MAY_CREATE		0x0010
+#define AA_MAY_DELETE		0x0020
+#define AA_MAY_OPEN		0x0040
+#define AA_MAY_RENAME		0x0080		/* pair */
+
+#define AA_MAY_SETATTR		0x0100		/* meta write */
+#define AA_MAY_GETATTR		0x0200		/* meta read */
+#define AA_MAY_SETCRED		0x0400		/* security cred/attr */
+#define AA_MAY_GETCRED		0x0800
+
+#define AA_MAY_CHMOD		0x1000		/* pair */
+#define AA_MAY_CHOWN		0x2000		/* pair */
+#define AA_MAY_CHGRP		0x4000		/* pair */
+#define AA_MAY_LOCK		0x8000		/* LINK_SUBSET overlaid */
+
+#define AA_EXEC_MMAP		0x00010000
+#define AA_MAY_MPROT		0x00020000	/* extend conditions */
+#define AA_MAY_LINK		0x00040000	/* pair */
+#define AA_MAY_SNAPSHOT		0x00080000	/* pair */
+
+#define AA_MAY_DELEGATE
+#define AA_CONT_MATCH		0x08000000
+
+#define AA_MAY_STACK		0x10000000
+#define AA_MAY_ONEXEC		0x20000000 /* either stack or change_profile */
+#define AA_MAY_CHANGE_PROFILE	0x40000000
+#define AA_MAY_CHANGEHAT	0x80000000
+
+#define AA_LINK_SUBSET		AA_MAY_LOCK	/* overlaid */
+
+#define AA_MAY_CREATE_SQPOLL   AA_MAY_CREATE
+#define AA_MAY_OVERRIDE_CRED   AA_MAY_APPEND
+#define AA_URING_PERM_MASK     (AA_MAY_OVERRIDE_CRED | AA_MAY_CREATE_SQPOLL)
+
+#define PERMS_CHRS_MASK (MAY_READ | MAY_WRITE | AA_MAY_CREATE |		\
+			 AA_MAY_DELETE | AA_MAY_LINK | AA_MAY_LOCK |	\
+			 AA_MAY_EXEC | AA_EXEC_MMAP | AA_MAY_APPEND)
+
+#define PERMS_NAMES_MASK (PERMS_CHRS_MASK | AA_MAY_OPEN | AA_MAY_RENAME |     \
+			  AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_SETCRED | \
+			  AA_MAY_GETCRED | AA_MAY_CHMOD | AA_MAY_CHOWN | \
+			  AA_MAY_CHGRP | AA_MAY_MPROT | AA_MAY_SNAPSHOT | \
+			  AA_MAY_STACK | AA_MAY_ONEXEC |		\
+			  AA_MAY_CHANGE_PROFILE | AA_MAY_CHANGEHAT)
+
+extern const char aa_file_perm_chrs[];
+extern const char *aa_file_perm_names[];
+
+struct aa_perms {
+	u32 allow;
+	u32 deny;	/* explicit deny, or conflict if allow also set */
+
+	u32 subtree;	/* allow perm on full subtree only when allow is set */
+	u32 cond;	/* set only when ~allow and ~deny */
+
+	u32 kill;	/* set only when ~allow | deny */
+	u32 complain;	/* accumulates only used when ~allow & ~deny */
+	u32 prompt;	/* accumulates only used when ~allow & ~deny */
+
+	u32 audit;	/* set only when allow is set */
+	u32 quiet;	/* set only when ~allow | deny */
+	u32 hide;	/* set only when  ~allow | deny */
+
+
+	u32 xindex;
+	u32 tag;	/* tag string index, if present */
+	u32 label;	/* label string index, if present */
+};
+
+/*
+ * Indexes are broken into a 24 bit index and 8 bit flag.
+ * For the index to be valid there must be a value in the flag
+ */
+#define AA_INDEX_MASK			0x00ffffff
+#define AA_INDEX_FLAG_MASK		0xff000000
+#define AA_INDEX_NONE			0
+
+#define ALL_PERMS_MASK 0xffffffff
+extern const struct aa_perms nullperms;
+extern const struct aa_perms allperms;
+
+/**
+ * aa_perms_accum_raw - accumulate perms with out masking off overlapping perms
+ * @accum: perms struct to accumulate into
+ * @addend: perms struct to add to @accum
+ */
+static inline void aa_perms_accum_raw(struct aa_perms *accum,
+				      const struct aa_perms *addend)
+{
+	accum->deny |= addend->deny;
+	accum->allow &= addend->allow & ~addend->deny;
+	accum->audit |= addend->audit & addend->allow;
+	accum->quiet &= addend->quiet & ~addend->allow;
+	accum->kill |= addend->kill & ~addend->allow;
+	accum->complain |= addend->complain & ~addend->allow & ~addend->deny;
+	accum->cond |= addend->cond & ~addend->allow & ~addend->deny;
+	accum->hide &= addend->hide & ~addend->allow;
+	accum->prompt |= addend->prompt & ~addend->allow & ~addend->deny;
+	accum->subtree |= addend->subtree & ~addend->deny;
+
+	if (!accum->xindex)
+		accum->xindex = addend->xindex;
+	if (!accum->tag)
+		accum->tag = addend->tag;
+	if (!accum->label)
+		accum->label = addend->label;
+}
+
+/**
+ * aa_perms_accum - accumulate perms, masking off overlapping perms
+ * @accum: perms struct to accumulate into
+ * @addend: perms struct to add to @accum
+ */
+static inline void aa_perms_accum(struct aa_perms *accum,
+				  const struct aa_perms *addend)
+{
+	accum->deny |= addend->deny;
+	accum->allow &= addend->allow & ~accum->deny;
+	accum->audit |= addend->audit & accum->allow;
+	accum->quiet &= addend->quiet & ~accum->allow;
+	accum->kill |= addend->kill & ~accum->allow;
+	accum->complain |= addend->complain & ~accum->allow & ~accum->deny;
+	accum->cond |= addend->cond & ~accum->allow & ~accum->deny;
+	accum->hide &= addend->hide & ~accum->allow;
+	accum->prompt |= addend->prompt & ~accum->allow & ~accum->deny;
+	accum->subtree &= addend->subtree & ~accum->deny;
+
+	if (!accum->xindex)
+		accum->xindex = addend->xindex;
+	if (!accum->tag)
+		accum->tag = addend->tag;
+	if (!accum->label)
+		accum->label = addend->label;
+}
+
+#define xcheck(FN1, FN2)	\
+({				\
+	int e, error = FN1;	\
+	e = FN2;		\
+	if (e)			\
+		error = e;	\
+	error;			\
+})
+
+
+/*
+ * TODO: update for labels pointing to labels instead of profiles
+ * TODO: optimize the walk, currently does subwalk of L2 for each P in L1
+ * gah this doesn't allow for label compound check!!!!
+ */
+#define xcheck_ns_profile_profile(P1, P2, FN, args...)		\
+({								\
+	int ____e = 0;						\
+	if (P1->ns == P2->ns)					\
+		____e = FN((P1), (P2), args);			\
+	(____e);						\
+})
+
+#define xcheck_ns_profile_label(P, L, FN, args...)		\
+({								\
+	struct aa_profile *__p2;				\
+	fn_for_each((L), __p2,					\
+		    xcheck_ns_profile_profile((P), __p2, (FN), args));	\
+})
+
+#define xcheck_ns_labels(L1, L2, FN, args...)			\
+({								\
+	struct aa_profile *__p1;				\
+	fn_for_each((L1), __p1, FN(__p1, (L2), args));		\
+})
+
+/* Do the cross check but applying FN at the profiles level */
+#define xcheck_labels_profiles(L1, L2, FN, args...)		\
+	xcheck_ns_labels((L1), (L2), xcheck_ns_profile_label, (FN), args)
+
+#define xcheck_labels(L1, L2, P, FN1, FN2)			\
+	xcheck(fn_for_each((L1), (P), (FN1)), fn_for_each((L2), (P), (FN2)))
+
+
+extern struct aa_perms default_perms;
+
+
+void aa_perm_mask_to_str(char *str, size_t str_size, const char *chrs,
+			 u32 mask);
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+			 u32 mask);
+void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
+			u32 chrsmask, const char * const *names, u32 namesmask);
+void aa_apply_modes_to_perms(const struct aa_profile *profile,
+			     struct aa_perms *perms);
+void aa_perms_accum(struct aa_perms *accum, const struct aa_perms *addend);
+void aa_perms_accum_raw(struct aa_perms *accum, const struct aa_perms *addend);
+void aa_profile_match_label(const struct aa_profile *profile,
+			    struct aa_ruleset *rules, struct aa_label *label,
+			    int type, u32 request, struct aa_perms *perms);
+int aa_check_perms(struct aa_profile *profile, const struct aa_perms *perms,
+		   u32 request, struct apparmor_audit_data *ad,
+		   void (*cb)(struct audit_buffer *, void *));
+#endif /* __AA_PERM_H */
+
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
new file mode 100644
index 000000000..0dcbf8cf1
--- /dev/null
+++ b/security/apparmor/include/policy.h
@@ -0,0 +1,457 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_POLICY_H
+#define __AA_POLICY_H
+
+#include <linux/capability.h>
+#include <linux/cred.h>
+#include <linux/kref.h>
+#include <linux/rhashtable.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+
+#include "apparmor.h"
+#include "audit.h"
+#include "capability.h"
+#include "domain.h"
+#include "file.h"
+#include "lib.h"
+#include "label.h"
+#include "perms.h"
+#include "resource.h"
+
+
+struct aa_ns;
+
+extern int unprivileged_userns_apparmor_policy;
+extern int aa_unprivileged_unconfined_restricted;
+
+extern const char *const aa_profile_mode_names[];
+
+#define PROFILE_MODE(_profile, _mode)		\
+	((aa_g_profile_mode == (_mode)) ||	\
+	 ((_profile)->mode == (_mode)))
+
+#define COMPLAIN_MODE(_profile)	PROFILE_MODE((_profile), APPARMOR_COMPLAIN)
+
+#define USER_MODE(_profile)	PROFILE_MODE((_profile), APPARMOR_USER)
+
+#define KILL_MODE(_profile) PROFILE_MODE((_profile), APPARMOR_KILL)
+
+#define PROFILE_IS_HAT(_profile) ((_profile)->label.flags & FLAG_HAT)
+
+#define CHECK_DEBUG1(_profile) ((_profile)->label.flags & FLAG_DEBUG1)
+
+#define CHECK_DEBUG2(_profile) ((_profile)->label.flags & FLAG_DEBUG2)
+
+#define profile_is_stale(_profile) (label_is_stale(&(_profile)->label))
+
+#define on_list_rcu(X) (!list_empty(X) && (X)->prev != LIST_POISON2)
+
+/* flags in the dfa accept2 table */
+enum dfa_accept_flags {
+	ACCEPT_FLAG_OWNER = 1,
+};
+
+/*
+ * FIXME: currently need a clean way to replace and remove profiles as a
+ * set.  It should be done at the namespace level.
+ * Either, with a set of profiles loaded at the namespace level or via
+ * a mark and remove marked interface.
+ */
+enum profile_mode {
+	APPARMOR_ENFORCE,	/* enforce access rules */
+	APPARMOR_COMPLAIN,	/* allow and log access violations */
+	APPARMOR_KILL,		/* kill task on access violation */
+	APPARMOR_UNCONFINED,	/* profile set to unconfined */
+	APPARMOR_USER,		/* modified complain mode to userspace */
+	PROFILE_MODE_NAMES_COUNT	/* Must be last entry */
+};
+
+
+struct aa_tags_header {
+	u32 mask;	/* bit mask matching permissions */
+	u32 count;	/* number of strings per entry */
+	u32 size;	/* size of all strings covered by count */
+	u32 tags;	/* index into string table */
+};
+
+struct aa_tags_struct {
+	struct {
+		u32 size;		/* number of entries in tagsets */
+		u32 *table;		/* indexes into headers & strs */
+	} sets;
+	struct {
+		u32 size;		/* number of headers == num of strs */
+		struct aa_tags_header *table;
+	} hdrs;
+	struct aa_str_table strs;
+};
+
+/* struct aa_policydb - match engine for a policy
+ * @count: refcount for the pdb
+ * @dfa: dfa pattern match
+ * @perms: table of permissions
+ * @size: number of entries in @perms
+ * @trans: table of strings, index by x
+ * @tags: table of tags that perms->tag indexes
+ * @start:_states to start in for each class
+ * start: set of start states for the different classes of data
+ */
+struct aa_policydb {
+	struct kref count;
+	struct aa_dfa *dfa;
+	struct {
+		struct aa_perms *perms;
+		u32 size;
+	};
+	struct aa_str_table trans;
+	struct aa_tags_struct tags;
+	aa_state_t start[AA_CLASS_LAST + 1];
+};
+
+extern struct aa_policydb *nullpdb;
+
+void aa_destroy_tags(struct aa_tags_struct *tags);
+struct aa_policydb *aa_alloc_pdb(gfp_t gfp);
+void aa_pdb_free_kref(struct kref *kref);
+
+/**
+ * aa_get_pdb - increment refcount on @pdb
+ * @pdb: policydb  (MAYBE NULL)
+ *
+ * Returns: pointer to @pdb if @pdb is NULL will return NULL
+ * Requires: @pdb must be held with valid refcount when called
+ */
+static inline struct aa_policydb *aa_get_pdb(struct aa_policydb *pdb)
+{
+	if (pdb)
+		kref_get(&(pdb->count));
+
+	return pdb;
+}
+
+/**
+ * aa_put_pdb - put a pdb refcount
+ * @pdb: pdb to put refcount   (MAYBE NULL)
+ *
+ * Requires: if @pdb != NULL that a valid refcount be held
+ */
+static inline void aa_put_pdb(struct aa_policydb *pdb)
+{
+	if (pdb)
+		kref_put(&pdb->count, aa_pdb_free_kref);
+}
+
+/* lookup perm that doesn't have and object conditional */
+static inline struct aa_perms *aa_lookup_perms(struct aa_policydb *policy,
+					       aa_state_t state)
+{
+	unsigned int index = ACCEPT_TABLE(policy->dfa)[state];
+
+	if (!(policy->perms))
+		return &default_perms;
+
+	return &(policy->perms[index]);
+}
+
+/* struct aa_data - generic data structure
+ * key: name for retrieving this data
+ * size: size of data in bytes
+ * data: binary data
+ * head: reserved for rhashtable
+ */
+struct aa_data {
+	char *key;
+	u32 size;
+	char *data;
+	struct rhash_head head;
+};
+
+/* struct aa_ruleset - data covering mediation rules
+ * @list: list the rule is on
+ * @size: the memory consumed by this ruleset
+ * @policy: general match rules governing policy
+ * @file: The set of rules governing basic file access and domain transitions
+ * @caps: capabilities for the profile
+ * @rlimits: rlimits for the profile
+ * @secmark_count: number of secmark entries
+ * @secmark: secmark label match info
+ */
+struct aa_ruleset {
+	int size;
+
+	/* TODO: merge policy and file */
+	struct aa_policydb *policy;
+	struct aa_policydb *file;
+	struct aa_caps caps;
+
+	struct aa_rlimit rlimits;
+
+	int secmark_count;
+	struct aa_secmark *secmark;
+};
+
+
+/* struct aa_attachment - data and rules for a profiles attachment
+ * @list:
+ * @xmatch_str: human readable attachment string
+ * @xmatch: optional extended matching for unconfined executables names
+ * @xmatch_len: xmatch prefix len, used to determine xmatch priority
+ * @xattr_count: number of xattrs in table
+ * @xattrs: table of xattrs
+ */
+struct aa_attachment {
+	const char *xmatch_str;
+	struct aa_policydb *xmatch;
+	unsigned int xmatch_len;
+	int xattr_count;
+	char **xattrs;
+};
+
+/* struct aa_profile - basic confinement data
+ * @base - base components of the profile (name, refcount, lists, lock ...)
+ * @parent: parent of profile
+ * @ns: namespace the profile is in
+ * @rename: optional profile name that this profile renamed
+ *
+ * @audit: the auditing mode of the profile
+ * @mode: the enforcement mode of the profile
+ * @path_flags: flags controlling path generation behavior
+ * @signal: the signal that should be used when kill is used
+ * @disconnected: what to prepend if attach_disconnected is specified
+ * @attach: attachment rules for the profile
+ * @rules: rules to be enforced
+ *
+ * learning_cache: the accesses learned in complain mode
+ * raw_data: rawdata of the loaded profile policy
+ * hash: cryptographic hash of the profile
+ * @dents: dentries for the profiles file entries in apparmorfs
+ * @dirname: name of the profile dir in apparmorfs
+ * @dents: set of dentries associated with the profile
+ * @data: hashtable for free-form policy aa_data
+ * @label - label this profile is an extension of
+ * @rules - label with the rule vec on its end
+ *
+ * The AppArmor profile contains the basic confinement data.  Each profile
+ * has a name, and exists in a namespace.  The @name and @exec_match are
+ * used to determine profile attachment against unconfined tasks.  All other
+ * attachments are determined by profile X transition rules.
+ *
+ * Profiles have a hierarchy where hats and children profiles keep
+ * a reference to their parent.
+ *
+ * Profile names can not begin with a : and can not contain the \0
+ * character.  If a profile name begins with / it will be considered when
+ * determining profile attachment on "unconfined" tasks.
+ */
+struct aa_profile {
+	struct aa_policy base;
+	struct aa_profile __rcu *parent;
+
+	struct aa_ns *ns;
+	const char *rename;
+
+	enum audit_mode audit;
+	long mode;
+	u32 path_flags;
+	int signal;
+	const char *disconnected;
+
+	struct aa_attachment attach;
+
+	struct aa_loaddata *rawdata;
+	unsigned char *hash;
+	char *dirname;
+	struct dentry *dents[AAFS_PROF_SIZEOF];
+	struct rhashtable *data;
+
+	int n_rules;
+	/* special - variable length must be last entry in profile */
+	struct aa_label label;
+};
+
+extern enum profile_mode aa_g_profile_mode;
+
+#define AA_MAY_LOAD_POLICY	AA_MAY_APPEND
+#define AA_MAY_REPLACE_POLICY	AA_MAY_WRITE
+#define AA_MAY_REMOVE_POLICY	AA_MAY_DELETE
+
+#define profiles_ns(P) ((P)->ns)
+#define name_is_shared(A, B) ((A)->hname && (A)->hname == (B)->hname)
+
+struct aa_ruleset *aa_alloc_ruleset(gfp_t gfp);
+struct aa_profile *aa_alloc_profile(const char *name, struct aa_proxy *proxy,
+				    gfp_t gfp);
+struct aa_profile *aa_alloc_null(struct aa_profile *parent, const char *name,
+				 gfp_t gfp);
+struct aa_profile *__aa_new_learning_profile(struct aa_profile *parent,
+					     bool hat, const char *base,
+					     gfp_t gfp);
+struct aa_profile *aa_new_learning_profile(struct aa_profile *parent, bool hat,
+					   const char *base, gfp_t gfp);
+void aa_free_profile(struct aa_profile *profile);
+struct aa_profile *aa_find_child(struct aa_profile *parent, const char *name);
+struct aa_profile *aa_lookupn_profile(struct aa_ns *ns, const char *hname,
+				      size_t n);
+struct aa_profile *aa_fqlookupn_profile(struct aa_label *base,
+					const char *fqname, size_t n);
+
+ssize_t aa_replace_profiles(struct aa_ns *view, struct aa_label *label,
+			    u32 mask, struct aa_loaddata *udata,
+			    char *compressed_profile, size_t compressed_size);
+ssize_t aa_remove_profiles(struct aa_ns *view, struct aa_label *label,
+			   char *name, size_t size);
+void __aa_profile_list_release(struct list_head *head);
+
+#define profile_unconfined(X) ((X)->mode == APPARMOR_UNCONFINED)
+
+/**
+ * aa_get_newest_profile - simple wrapper fn to wrap the label version
+ * @p: profile (NOT NULL)
+ *
+ * Returns refcount to newest version of the profile (maybe @p)
+ *
+ * Requires: @p must be held with a valid refcount
+ */
+static inline struct aa_profile *aa_get_newest_profile(struct aa_profile *p)
+{
+	return labels_profile(aa_get_newest_label(&p->label));
+}
+
+static inline aa_state_t RULE_MEDIATES(struct aa_ruleset *rules,
+				       unsigned char class)
+{
+	if (class <= AA_CLASS_LAST)
+		return rules->policy->start[class];
+	else
+		return aa_dfa_match_len(rules->policy->dfa,
+					rules->policy->start[0], &class, 1);
+}
+
+static inline aa_state_t RULE_MEDIATES_v9NET(struct aa_ruleset *rules)
+{
+	return RULE_MEDIATES(rules, AA_CLASS_NETV9);
+}
+
+static inline aa_state_t RULE_MEDIATES_NET(struct aa_ruleset *rules)
+{
+	/* can not use RULE_MEDIATE_v9AF here, because AF match fail
+	 * can not be distiguished from class match fail, and we only
+	 * fallback to checking older class on class match failure
+	 */
+	aa_state_t state = RULE_MEDIATES(rules, AA_CLASS_NETV9);
+
+	/* fallback and check v7/8 if v9 is NOT mediated */
+	if (!state)
+		state = RULE_MEDIATES(rules, AA_CLASS_NET);
+	return state;
+}
+
+static inline aa_state_t RULE_MEDIATES_UNIX(struct aa_ruleset *rules)
+{
+	return RULE_MEDIATES_v9NET(rules);
+}
+
+
+void aa_compute_profile_mediates(struct aa_profile *profile);
+static inline bool profile_mediates(struct aa_profile *profile,
+				    unsigned char class)
+{
+	return label_mediates(&profile->label, class);
+}
+
+static inline bool profile_mediates_safe(struct aa_profile *profile,
+					 unsigned char class)
+{
+	return label_mediates_safe(&profile->label, class);
+}
+
+/**
+ * aa_get_profile - increment refcount on profile @p
+ * @p: profile  (MAYBE NULL)
+ *
+ * Returns: pointer to @p if @p is NULL will return NULL
+ * Requires: @p must be held with valid refcount when called
+ */
+static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
+{
+	if (p)
+		kref_get(&(p->label.count.count));
+
+	return p;
+}
+
+/**
+ * aa_get_profile_not0 - increment refcount on profile @p found via lookup
+ * @p: profile  (MAYBE NULL)
+ *
+ * Returns: pointer to @p if @p is NULL will return NULL
+ * Requires: @p must be held with valid refcount when called
+ */
+static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p)
+{
+	if (p && kref_get_unless_zero(&p->label.count.count))
+		return p;
+
+	return NULL;
+}
+
+/**
+ * aa_get_profile_rcu - increment a refcount profile that can be replaced
+ * @p: pointer to profile that can be replaced (NOT NULL)
+ *
+ * Returns: pointer to a refcounted profile.
+ *     else NULL if no profile
+ */
+static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
+{
+	struct aa_profile *c;
+
+	rcu_read_lock();
+	do {
+		c = rcu_dereference(*p);
+	} while (c && !kref_get_unless_zero(&c->label.count.count));
+	rcu_read_unlock();
+
+	return c;
+}
+
+/**
+ * aa_put_profile - decrement refcount on profile @p
+ * @p: profile  (MAYBE NULL)
+ */
+static inline void aa_put_profile(struct aa_profile *p)
+{
+	if (p)
+		kref_put(&p->label.count.count, aa_label_kref);
+}
+
+static inline int AUDIT_MODE(const struct aa_profile *profile)
+{
+	if (aa_g_audit != AUDIT_NORMAL)
+		return aa_g_audit;
+
+	return profile->audit;
+}
+
+bool aa_policy_view_capable(const struct cred *subj_cred,
+			    struct aa_label *label, struct aa_ns *ns);
+bool aa_policy_admin_capable(const struct cred *subj_cred,
+			     struct aa_label *label, struct aa_ns *ns);
+int aa_may_manage_policy(const struct cred *subj_cred,
+			 struct aa_label *label, struct aa_ns *ns,
+			 const struct cred *ocred, u32 mask);
+bool aa_current_policy_view_capable(struct aa_ns *ns);
+bool aa_current_policy_admin_capable(struct aa_ns *ns);
+
+#endif /* __AA_POLICY_H */
diff --git a/security/apparmor/include/policy_compat.h b/security/apparmor/include/policy_compat.h
new file mode 100644
index 000000000..af0e17433
--- /dev/null
+++ b/security/apparmor/include/policy_compat.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * Code to provide backwards compatibility with older policy versions,
+ * by converting/mapping older policy formats into the newer internal
+ * formats.
+ *
+ * Copyright 2022 Canonical Ltd.
+ */
+
+#ifndef __POLICY_COMPAT_H
+#define __POLICY_COMPAT_H
+
+#include "policy.h"
+
+#define K_ABI_MASK 0x3ff
+#define FORCE_COMPLAIN_FLAG 0x800
+#define VERSION_LT(X, Y) (((X) & K_ABI_MASK) < ((Y) & K_ABI_MASK))
+#define VERSION_LE(X, Y) (((X) & K_ABI_MASK) <= ((Y) & K_ABI_MASK))
+#define VERSION_GT(X, Y) (((X) & K_ABI_MASK) > ((Y) & K_ABI_MASK))
+
+#define v5	5	/* base version */
+#define v6	6	/* per entry policydb mediation check */
+#define v7	7
+#define v8	8	/* full network masking */
+#define v9	9	/* xbits are used as permission bits in policydb */
+
+int aa_compat_map_xmatch(struct aa_policydb *policy);
+int aa_compat_map_policy(struct aa_policydb *policy, u32 version);
+int aa_compat_map_file(struct aa_policydb *policy);
+
+#endif /* __POLICY_COMPAT_H */
diff --git a/security/apparmor/include/policy_ns.h b/security/apparmor/include/policy_ns.h
new file mode 100644
index 000000000..cc6e84151
--- /dev/null
+++ b/security/apparmor/include/policy_ns.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#ifndef __AA_NAMESPACE_H
+#define __AA_NAMESPACE_H
+
+#include <linux/kref.h>
+
+#include "apparmor.h"
+#include "apparmorfs.h"
+#include "label.h"
+#include "policy.h"
+
+/* Match max depth of user namespaces */
+#define MAX_NS_DEPTH 32
+
+/* struct aa_ns_acct - accounting of profiles in namespace
+ * @max_size: maximum space allowed for all profiles in namespace
+ * @max_count: maximum number of profiles that can be in this namespace
+ * @size: current size of profiles
+ * @count: current count of profiles (includes null profiles)
+ */
+struct aa_ns_acct {
+	int max_size;
+	int max_count;
+	int size;
+	int count;
+};
+
+/* struct aa_ns - namespace for a set of profiles
+ * @base: common policy
+ * @parent: parent of namespace
+ * @lock: lock for modifying the object
+ * @acct: accounting for the namespace
+ * @unconfined: special unconfined profile for the namespace
+ * @sub_ns: list of namespaces under the current namespace.
+ * @uniq_null: uniq value used for null learning profiles
+ * @uniq_id: a unique id count for the profiles in the namespace
+ * @level: level of ns within the tree hierarchy
+ * @dents: dentries for the namespaces file entries in apparmorfs
+ *
+ * An aa_ns defines the set profiles that are searched to determine which
+ * profile to attach to a task.  Profiles can not be shared between aa_ns
+ * and profile names within a namespace are guaranteed to be unique.  When
+ * profiles in separate namespaces have the same name they are NOT considered
+ * to be equivalent.
+ *
+ * Namespaces are hierarchical and only namespaces and profiles below the
+ * current namespace are visible.
+ *
+ * Namespace names must be unique and can not contain the characters :/\0
+ */
+struct aa_ns {
+	struct aa_policy base;
+	struct aa_ns *parent;
+	struct mutex lock;
+	struct aa_ns_acct acct;
+	struct aa_profile *unconfined;
+	struct list_head sub_ns;
+	atomic_t uniq_null;
+	long uniq_id;
+	int level;
+	long revision;
+	wait_queue_head_t wait;
+
+	struct aa_labelset labels;
+	struct list_head rawdata_list;
+
+	struct dentry *dents[AAFS_NS_SIZEOF];
+};
+
+extern struct aa_label *kernel_t;
+extern struct aa_ns *root_ns;
+
+extern const char *aa_hidden_ns_name;
+
+#define ns_unconfined(NS) (&(NS)->unconfined->label)
+
+bool aa_ns_visible(struct aa_ns *curr, struct aa_ns *view, bool subns);
+const char *aa_ns_name(struct aa_ns *parent, struct aa_ns *child, bool subns);
+void aa_free_ns(struct aa_ns *ns);
+int aa_alloc_root_ns(void);
+void aa_free_root_ns(void);
+
+struct aa_ns *__aa_lookupn_ns(struct aa_ns *view, const char *hname, size_t n);
+struct aa_ns *aa_lookupn_ns(struct aa_ns *view, const char *name, size_t n);
+struct aa_ns *__aa_find_or_create_ns(struct aa_ns *parent, const char *name,
+				     struct dentry *dir);
+struct aa_ns *aa_prepare_ns(struct aa_ns *root, const char *name);
+void __aa_remove_ns(struct aa_ns *ns);
+
+static inline struct aa_profile *aa_deref_parent(struct aa_profile *p)
+{
+	return rcu_dereference_protected(p->parent,
+					 mutex_is_locked(&p->ns->lock));
+}
+
+/**
+ * aa_get_ns - increment references count on @ns
+ * @ns: namespace to increment reference count of (MAYBE NULL)
+ *
+ * Returns: pointer to @ns, if @ns is NULL returns NULL
+ * Requires: @ns must be held with valid refcount when called
+ */
+static inline struct aa_ns *aa_get_ns(struct aa_ns *ns)
+{
+	if (ns)
+		aa_get_profile(ns->unconfined);
+
+	return ns;
+}
+
+/**
+ * aa_put_ns - decrement refcount on @ns
+ * @ns: namespace to put reference of
+ *
+ * Decrement reference count of @ns and if no longer in use free it
+ */
+static inline void aa_put_ns(struct aa_ns *ns)
+{
+	if (ns)
+		aa_put_profile(ns->unconfined);
+}
+
+/**
+ * __aa_findn_ns - find a namespace on a list by @name
+ * @head: list to search for namespace on  (NOT NULL)
+ * @name: name of namespace to look for  (NOT NULL)
+ * @n: length of @name
+ * Returns: unrefcounted namespace
+ *
+ * Requires: rcu_read_lock be held
+ */
+static inline struct aa_ns *__aa_findn_ns(struct list_head *head,
+					  const char *name, size_t n)
+{
+	return (struct aa_ns *)__policy_strn_find(head, name, n);
+}
+
+static inline struct aa_ns *__aa_find_ns(struct list_head *head,
+					 const char *name)
+{
+	return __aa_findn_ns(head, name, strlen(name));
+}
+
+#endif /* AA_NAMESPACE_H */
diff --git a/security/apparmor/include/policy_unpack.h b/security/apparmor/include/policy_unpack.h
new file mode 100644
index 000000000..c01f6885d
--- /dev/null
+++ b/security/apparmor/include/policy_unpack.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __POLICY_INTERFACE_H
+#define __POLICY_INTERFACE_H
+
+#include <linux/list.h>
+#include <linux/kref.h>
+#include <linux/dcache.h>
+#include <linux/workqueue.h>
+
+#include "lib.h"
+
+struct aa_load_ent {
+	struct list_head list;
+	struct aa_profile *new;
+	struct aa_profile *old;
+	struct aa_profile *rename;
+	const char *ns_name;
+};
+
+void aa_load_ent_free(struct aa_load_ent *ent);
+struct aa_load_ent *aa_load_ent_alloc(void);
+
+#define PACKED_FLAG_HAT		1
+#define PACKED_FLAG_DEBUG1	2
+#define PACKED_FLAG_DEBUG2	4
+
+#define PACKED_MODE_ENFORCE	0
+#define PACKED_MODE_COMPLAIN	1
+#define PACKED_MODE_KILL	2
+#define PACKED_MODE_UNCONFINED	3
+#define PACKED_MODE_USER	4
+
+struct aa_ns;
+
+enum {
+	AAFS_LOADDATA_ABI = 0,
+	AAFS_LOADDATA_REVISION,
+	AAFS_LOADDATA_HASH,
+	AAFS_LOADDATA_DATA,
+	AAFS_LOADDATA_COMPRESSED_SIZE,
+	AAFS_LOADDATA_DIR,		/* must be last actual entry */
+	AAFS_LOADDATA_NDENTS		/* count of entries */
+};
+
+/*
+ * The AppArmor interface treats data as a type byte followed by the
+ * actual data.  The interface has the notion of a named entry
+ * which has a name (AA_NAME typecode followed by name string) followed by
+ * the entries typecode and data.  Named types allow for optional
+ * elements and extensions to be added and tested for without breaking
+ * backwards compatibility.
+ */
+
+enum aa_code {
+	AA_U8,
+	AA_U16,
+	AA_U32,
+	AA_U64,
+	AA_NAME,		/* same as string except it is items name */
+	AA_STRING,
+	AA_BLOB,
+	AA_STRUCT,
+	AA_STRUCTEND,
+	AA_LIST,
+	AA_LISTEND,
+	AA_ARRAY,
+	AA_ARRAYEND,
+};
+
+/*
+ * aa_ext is the read of the buffer containing the serialized profile.  The
+ * data is copied into a kernel buffer in apparmorfs and then handed off to
+ * the unpack routines.
+ */
+struct aa_ext {
+	void *start;
+	void *end;
+	void *pos;		/* pointer to current position in the buffer */
+	u32 version;
+};
+
+/* struct aa_loaddata - buffer of policy raw_data set
+ * @count: inode/filesystem refcount - use aa_get_i_loaddata()
+ * @pcount: profile refcount - use aa_get_profile_loaddata()
+ * @list: list the loaddata is on
+ * @work: used to do a delayed cleanup
+ * @dents: refs to dents created in aafs
+ * @ns: the namespace this loaddata was loaded into
+ * @name:
+ * @size: the size of the data that was loaded
+ * @compressed_size: the size of the data when it is compressed
+ * @revision: unique revision count that this data was loaded as
+ * @abi: the abi number the loaddata uses
+ * @hash: a hash of the loaddata, used to help dedup data
+ *
+ * There is no loaddata ref for being on ns->rawdata_list, so
+ * @ns->lock must be held when walking the list. Dentries and
+ * inode opens hold refs on @count; profiles hold refs on @pcount.
+ * When the last @pcount drops, do_ploaddata_rmfs() removes the
+ * fs entries and drops the associated @count ref.
+ */
+struct aa_loaddata {
+	struct aa_common_ref count;
+	struct kref pcount;
+	struct list_head list;
+	struct work_struct work;
+	struct dentry *dents[AAFS_LOADDATA_NDENTS];
+	struct aa_ns *ns;
+	char *name;
+	size_t size;			/* the original size of the payload */
+	size_t compressed_size;		/* the compressed size of the payload */
+	long revision;			/* the ns policy revision this caused */
+	int abi;
+	unsigned char *hash;
+
+	/* Pointer to payload. If @compressed_size > 0, then this is the
+	 * compressed version of the payload, else it is the uncompressed
+	 * version (with the size indicated by @size).
+	 */
+	char *data;
+};
+
+int aa_unpack(struct aa_loaddata *udata, struct list_head *lh, const char **ns,
+	      char *compressed_data, size_t compressed_size);
+
+/**
+ * aa_get_i_loaddata - get a reference count from a counted data reference
+ * @data: reference to get a count on
+ *
+ * Returns: pointer to reference
+ * Requires: @data to have a valid reference count on it. It is a bug
+ *           if the race to reap can be encountered when it is used.
+ */
+static inline struct aa_loaddata *
+aa_get_i_loaddata(struct aa_loaddata *data)
+{
+
+	if (data)
+		kref_get(&(data->count.count));
+	return data;
+}
+
+
+/**
+ * aa_get_profile_loaddata - get a profile reference count on loaddata
+ * @data: reference to get a count on
+ *
+ * Returns: pointer to reference
+ * Requires: @data to have a valid reference count on it.
+ */
+static inline struct aa_loaddata *
+aa_get_profile_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_get(&(data->pcount));
+	return data;
+}
+
+/**
+ * aa_get_profile_loaddata_not0 - get a profile reference count if not zero
+ * @data: reference to get a count on
+ *
+ * Like aa_get_profile_loaddata(), but safe to call on an entry that may
+ * be on a list (e.g. ns->rawdata_list) where the last pcount has already
+ * dropped and the deferred cleanup has not yet run.
+ *
+ * Returns: pointer to reference, or %NULL if @data is NULL or its
+ *          profile refcount has already reached zero.
+ */
+static inline struct aa_loaddata *
+aa_get_profile_loaddata_not0(struct aa_loaddata *data)
+{
+	if (data && kref_get_unless_zero(&data->pcount))
+		return data;
+	return NULL;
+}
+
+void __aa_loaddata_update(struct aa_loaddata *data, long revision);
+bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r);
+void aa_loaddata_kref(struct kref *kref);
+void aa_ploaddata_kref(struct kref *kref);
+struct aa_loaddata *aa_loaddata_alloc(size_t size);
+static inline void aa_put_i_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_put(&data->count.count, aa_loaddata_kref);
+}
+
+static inline void aa_put_profile_loaddata(struct aa_loaddata *data)
+{
+	if (data)
+		kref_put(&data->pcount, aa_ploaddata_kref);
+}
+
+#if IS_ENABLED(CONFIG_KUNIT)
+bool aa_inbounds(struct aa_ext *e, size_t size);
+size_t aa_unpack_u16_chunk(struct aa_ext *e, char **chunk);
+bool aa_unpack_X(struct aa_ext *e, enum aa_code code);
+bool aa_unpack_nameX(struct aa_ext *e, enum aa_code code, const char *name);
+bool aa_unpack_u32(struct aa_ext *e, u32 *data, const char *name);
+bool aa_unpack_u64(struct aa_ext *e, u64 *data, const char *name);
+bool aa_unpack_array(struct aa_ext *e, const char *name, u16 *size);
+size_t aa_unpack_blob(struct aa_ext *e, char **blob, const char *name);
+int aa_unpack_str(struct aa_ext *e, const char **string, const char *name);
+int aa_unpack_strdup(struct aa_ext *e, char **string, const char *name);
+#endif
+
+#endif /* __POLICY_INTERFACE_H */
diff --git a/security/apparmor/include/procattr.h b/security/apparmor/include/procattr.h
new file mode 100644
index 000000000..56acd1bdb
--- /dev/null
+++ b/security/apparmor/include/procattr.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /proc/<pid>/attr/ interface function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_PROCATTR_H
+#define __AA_PROCATTR_H
+
+#include "label.h"
+
+int aa_getprocattr(struct aa_label *label, char **string, bool newline);
+int aa_setprocattr_changehat(char *args, size_t size, int flags);
+
+#endif /* __AA_PROCATTR_H */
diff --git a/security/apparmor/include/resource.h b/security/apparmor/include/resource.h
new file mode 100644
index 000000000..ad2c0da8e
--- /dev/null
+++ b/security/apparmor/include/resource.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor resource limits function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#ifndef __AA_RESOURCE_H
+#define __AA_RESOURCE_H
+
+#include <linux/resource.h>
+#include <linux/sched.h>
+
+#include "apparmorfs.h"
+
+struct aa_profile;
+
+/* struct aa_rlimit - rlimit settings for the profile
+ * @mask: which hard limits to set
+ * @limits: rlimit values that override task limits
+ *
+ * AppArmor rlimits are used to set confined task rlimits.  Only the
+ * limits specified in @mask will be controlled by apparmor.
+ */
+struct aa_rlimit {
+	unsigned int mask;
+	struct rlimit limits[RLIM_NLIMITS];
+};
+
+extern struct aa_sfs_entry aa_sfs_entry_rlimit[];
+
+int aa_map_resource(int resource);
+int aa_task_setrlimit(const struct cred *subj_cred, struct aa_label *label,
+		      struct task_struct *task,
+		      unsigned int resource, struct rlimit *new_rlim);
+
+void __aa_transition_rlimits(struct aa_label *old, struct aa_label *new);
+
+static inline void aa_free_rlimit_rules(struct aa_rlimit *rlims)
+{
+	/* NOP */
+}
+
+#endif /* __AA_RESOURCE_H */
diff --git a/security/apparmor/include/secid.h b/security/apparmor/include/secid.h
new file mode 100644
index 000000000..6025d3849
--- /dev/null
+++ b/security/apparmor/include/secid.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security identifier (secid) definitions
+ *
+ * Copyright 2009-2018 Canonical Ltd.
+ */
+
+#ifndef __AA_SECID_H
+#define __AA_SECID_H
+
+#include <linux/slab.h>
+#include <linux/types.h>
+
+struct aa_label;
+
+/* secid value that will not be allocated */
+#define AA_SECID_INVALID 0
+
+/* secid value that matches any other secid */
+#define AA_SECID_WILDCARD 1
+
+/* sysctl to enable displaying mode when converting secid to secctx */
+extern int apparmor_display_secid_mode;
+
+struct aa_label *aa_secid_to_label(u32 secid);
+int apparmor_secid_to_secctx(u32 secid, struct lsm_context *cp);
+int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp);
+int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid);
+void apparmor_release_secctx(struct lsm_context *cp);
+
+
+int aa_alloc_secid(struct aa_label *label, gfp_t gfp);
+void aa_free_secid(u32 secid);
+
+#endif /* __AA_SECID_H */
diff --git a/security/apparmor/include/sig_names.h b/security/apparmor/include/sig_names.h
new file mode 100644
index 000000000..c772668cd
--- /dev/null
+++ b/security/apparmor/include/sig_names.h
@@ -0,0 +1,97 @@
+#include <linux/signal.h>
+#include "signal.h"
+
+/* provide a mapping of arch signal to internal signal # for mediation
+ * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO
+ * map to the same entry those that may/or may not get a separate entry
+ */
+static const int sig_map[MAXMAPPED_SIG] = {
+	[0] = MAXMAPPED_SIG,	/* existence test */
+	[SIGHUP] = 1,
+	[SIGINT] = 2,
+	[SIGQUIT] = 3,
+	[SIGILL] = 4,
+	[SIGTRAP] = 5,		/* -, 5, - */
+	[SIGABRT] = 6,		/*  SIGIOT: -, 6, - */
+	[SIGBUS] = 7,		/* 10, 7, 10 */
+	[SIGFPE] = 8,
+	[SIGKILL] = 9,
+	[SIGUSR1] = 10,		/* 30, 10, 16 */
+	[SIGSEGV] = 11,
+	[SIGUSR2] = 12,		/* 31, 12, 17 */
+	[SIGPIPE] = 13,
+	[SIGALRM] = 14,
+	[SIGTERM] = 15,
+#ifdef SIGSTKFLT
+	[SIGSTKFLT] = 16,	/* -, 16, - */
+#endif
+	[SIGCHLD] = 17,		/* 20, 17, 18.  SIGCHLD -, -, 18 */
+	[SIGCONT] = 18,		/* 19, 18, 25 */
+	[SIGSTOP] = 19,		/* 17, 19, 23 */
+	[SIGTSTP] = 20,		/* 18, 20, 24 */
+	[SIGTTIN] = 21,		/* 21, 21, 26 */
+	[SIGTTOU] = 22,		/* 22, 22, 27 */
+	[SIGURG] = 23,		/* 16, 23, 21 */
+	[SIGXCPU] = 24,		/* 24, 24, 30 */
+	[SIGXFSZ] = 25,		/* 25, 25, 31 */
+	[SIGVTALRM] = 26,	/* 26, 26, 28 */
+	[SIGPROF] = 27,		/* 27, 27, 29 */
+	[SIGWINCH] = 28,	/* 28, 28, 20 */
+	[SIGIO] = 29,		/* SIGPOLL: 23, 29, 22 */
+	[SIGPWR] = 30,		/* 29, 30, 19.  SIGINFO 29, -, - */
+#ifdef SIGSYS
+	[SIGSYS] = 31,		/* 12, 31, 12. often SIG LOST/UNUSED */
+#endif
+#ifdef SIGEMT
+	[SIGEMT] = 32,		/* 7, - , 7 */
+#endif
+#if defined(SIGLOST) && SIGPWR != SIGLOST		/* sparc */
+	[SIGLOST] = 33,		/* unused on Linux */
+#endif
+#if defined(SIGUNUSED) && \
+    defined(SIGLOST) && defined(SIGSYS) && SIGLOST != SIGSYS
+	[SIGUNUSED] = 34,	/* -, 31, - */
+#endif
+};
+
+/* this table is ordered post sig_map[sig] mapping */
+static const char *const sig_names[MAXMAPPED_SIGNAME] = {
+	"unknown",
+	"hup",
+	"int",
+	"quit",
+	"ill",
+	"trap",
+	"abrt",
+	"bus",
+	"fpe",
+	"kill",
+	"usr1",
+	"segv",
+	"usr2",
+	"pipe",
+	"alrm",
+	"term",
+	"stkflt",
+	"chld",
+	"cont",
+	"stop",
+	"stp",
+	"ttin",
+	"ttou",
+	"urg",
+	"xcpu",
+	"xfsz",
+	"vtalrm",
+	"prof",
+	"winch",
+	"io",
+	"pwr",
+	"sys",
+	"emt",
+	"lost",
+	"unused",
+
+	"exists",	/* always last existence test mapped to MAXMAPPED_SIG */
+};
+
diff --git a/security/apparmor/include/signal.h b/security/apparmor/include/signal.h
new file mode 100644
index 000000000..729763fa7
--- /dev/null
+++ b/security/apparmor/include/signal.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor ipc mediation function definitions.
+ *
+ * Copyright 2023 Canonical Ltd.
+ */
+
+#ifndef __AA_SIGNAL_H
+#define __AA_SIGNAL_H
+
+#define SIGUNKNOWN 0
+#define MAXMAPPED_SIG 35
+
+#define MAXMAPPED_SIGNAME (MAXMAPPED_SIG + 1)
+#define SIGRT_BASE 128
+
+#endif /* __AA_SIGNAL_H */
diff --git a/security/apparmor/include/task.h b/security/apparmor/include/task.h
new file mode 100644
index 000000000..a8030ed78
--- /dev/null
+++ b/security/apparmor/include/task.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor task related definitions and mediation
+ *
+ * Copyright 2017 Canonical Ltd.
+ */
+
+#ifndef __AA_TASK_H
+#define __AA_TASK_H
+
+#include <linux/sched.h>
+
+#include "audit.h"
+#include "label.h"
+
+static inline struct aa_task_ctx *task_ctx(struct task_struct *task)
+{
+	return task->security + apparmor_blob_sizes.lbs_task;
+}
+
+/*
+ * struct aa_task_ctx - information for current task label change
+ * @nnp: snapshot of label at time of no_new_privs
+ * @onexec: profile to transition to on next exec  (MAY BE NULL)
+ * @previous: profile the task may return to     (MAY BE NULL)
+ * @token: magic value the task must know for returning to @previous_profile
+ * @label_replacement_tw: for aa_schedule_stale_label_replacement()
+ * @label_replacement_pending: is @label_replacement_tw pending?
+ *
+ * When changing this, check if aa_dup_task_ctx() needs to be updated.
+ */
+struct aa_task_ctx {
+	struct aa_label *nnp;
+	struct aa_label *onexec;
+	struct aa_label *previous;
+	u64 token;
+	struct callback_head label_replacement_tw;
+	bool label_replacement_pending;
+};
+
+int aa_replace_current_label(struct aa_label *label);
+void aa_schedule_stale_label_replacement(void);
+void aa_set_current_onexec(struct aa_label *label, bool stack);
+int aa_set_current_hat(struct aa_label *label, u64 token);
+int aa_restore_previous_label(u64 cookie);
+struct aa_label *aa_get_task_label(struct task_struct *task);
+
+/**
+ * aa_free_task_ctx - free a task_ctx
+ * @ctx: task_ctx to free (MAYBE NULL)
+ */
+static inline void aa_free_task_ctx(struct aa_task_ctx *ctx)
+{
+	if (ctx) {
+		aa_put_label(ctx->nnp);
+		aa_put_label(ctx->previous);
+		aa_put_label(ctx->onexec);
+	}
+}
+
+/**
+ * aa_dup_task_ctx - duplicate a task context, incrementing reference counts
+ * @new: a blank task context      (NOT NULL)
+ * @old: the task context to copy  (NOT NULL)
+ */
+static inline void aa_dup_task_ctx(struct aa_task_ctx *new,
+				   const struct aa_task_ctx *old)
+{
+	new->nnp = aa_get_label(old->nnp);
+	new->onexec = aa_get_label(old->onexec);
+	new->previous = aa_get_label(old->previous);
+	new->token = old->token;
+}
+
+/**
+ * aa_clear_task_ctx_trans - clear transition tracking info from the ctx
+ * @ctx: task context to clear (NOT NULL)
+ */
+static inline void aa_clear_task_ctx_trans(struct aa_task_ctx *ctx)
+{
+	AA_BUG(!ctx);
+
+	aa_put_label(ctx->previous);
+	aa_put_label(ctx->onexec);
+	ctx->previous = NULL;
+	ctx->onexec = NULL;
+	ctx->token = 0;
+}
+
+#define AA_PTRACE_TRACE		MAY_WRITE
+#define AA_PTRACE_READ		MAY_READ
+#define AA_MAY_BE_TRACED	AA_MAY_APPEND
+#define AA_MAY_BE_READ		AA_MAY_CREATE
+#define PTRACE_PERM_SHIFT	2
+
+#define AA_PTRACE_PERM_MASK (AA_PTRACE_READ | AA_PTRACE_TRACE | \
+			     AA_MAY_BE_READ | AA_MAY_BE_TRACED)
+#define AA_SIGNAL_PERM_MASK (MAY_READ | MAY_WRITE)
+
+#define AA_SFS_SIG_MASK "hup int quit ill trap abrt bus fpe kill usr1 " \
+	"segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \
+	"xcpu xfsz vtalrm prof winch io pwr sys emt lost"
+
+int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer,
+		  const struct cred *tracee_cred, struct aa_label *tracee,
+		  u32 request);
+
+
+
+#define AA_USERNS_CREATE	8
+
+int aa_profile_ns_perm(struct aa_profile *profile,
+		       struct apparmor_audit_data *ad, u32 request);
+
+#endif /* __AA_TASK_H */
diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c
new file mode 100644
index 000000000..df5712cea
--- /dev/null
+++ b/security/apparmor/ipc.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor ipc mediation
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#include <linux/gfp.h>
+
+#include "include/audit.h"
+#include "include/capability.h"
+#include "include/cred.h"
+#include "include/policy.h"
+#include "include/ipc.h"
+#include "include/sig_names.h"
+
+
+static inline int map_signal_num(int sig)
+{
+	if (sig > SIGRTMAX)
+		return SIGUNKNOWN;
+	else if (sig >= SIGRTMIN)
+		return sig - SIGRTMIN + SIGRT_BASE;
+	else if (sig < MAXMAPPED_SIG)
+		return sig_map[sig];
+	return SIGUNKNOWN;
+}
+
+/**
+ * audit_signal_mask - convert mask to permission string
+ * @mask: permission mask to convert
+ *
+ * Returns: pointer to static string
+ */
+static const char *audit_signal_mask(u32 mask)
+{
+	if (mask & MAY_READ)
+		return "receive";
+	if (mask & MAY_WRITE)
+		return "send";
+	return "";
+}
+
+/**
+ * audit_signal_cb() - call back for signal specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void audit_signal_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (ad->request & AA_SIGNAL_PERM_MASK) {
+		audit_log_format(ab, " requested_mask=\"%s\"",
+				 audit_signal_mask(ad->request));
+		if (ad->denied & AA_SIGNAL_PERM_MASK) {
+			audit_log_format(ab, " denied_mask=\"%s\"",
+					 audit_signal_mask(ad->denied));
+		}
+	}
+	if (ad->signal == SIGUNKNOWN)
+		audit_log_format(ab, "signal=unknown(%d)",
+				 ad->unmappedsig);
+	else if (ad->signal < MAXMAPPED_SIGNAME)
+		audit_log_format(ab, " signal=%s", sig_names[ad->signal]);
+	else
+		audit_log_format(ab, " signal=rtmin+%d",
+				 ad->signal - SIGRT_BASE);
+	audit_log_format(ab, " peer=");
+	aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+			FLAGS_NONE, GFP_ATOMIC);
+}
+
+static int profile_signal_perm(const struct cred *cred,
+			       struct aa_profile *profile,
+			       struct aa_label *peer, u32 request,
+			       struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms perms;
+	aa_state_t state;
+
+	if (profile_unconfined(profile))
+		return 0;
+
+	ad->subj_cred = cred;
+	ad->peer = peer;
+	/* TODO: secondary cache check <profile, profile, perm> */
+	state = RULE_MEDIATES(rules, AA_CLASS_SIGNAL);
+	if (!state)
+		return 0;
+	state = aa_dfa_next(rules->policy->dfa, state, ad->signal);
+	aa_label_match(profile, rules, peer, state, false, request, &perms);
+	aa_apply_modes_to_perms(profile, &perms);
+	return aa_check_perms(profile, &perms, request, ad, audit_signal_cb);
+}
+
+int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender,
+		  const struct cred *target_cred, struct aa_label *target,
+		  int sig)
+{
+	struct aa_profile *profile;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_SIGNAL, OP_SIGNAL);
+
+	ad.signal = map_signal_num(sig);
+	ad.unmappedsig = sig;
+	return xcheck_labels(sender, target, profile,
+			     profile_signal_perm(subj_cred, profile, target,
+						 MAY_WRITE, &ad),
+			     profile_signal_perm(target_cred, profile, sender,
+						 MAY_READ, &ad));
+}
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
new file mode 100644
index 000000000..82742a471
--- /dev/null
+++ b/security/apparmor/label.c
@@ -0,0 +1,2170 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor label definitions
+ *
+ * Copyright 2017 Canonical Ltd.
+ */
+
+#include <linux/audit.h>
+#include <linux/seq_file.h>
+#include <linux/sort.h>
+
+#include "include/apparmor.h"
+#include "include/cred.h"
+#include "include/label.h"
+#include "include/policy.h"
+#include "include/secid.h"
+
+
+/*
+ * the aa_label represents the set of profiles confining an object
+ *
+ * Labels maintain a reference count to the set of pointers they reference
+ * Labels are ref counted by
+ *   tasks and object via the security field/security context off the field
+ *   code - will take a ref count on a label if it needs the label
+ *          beyond what is possible with an rcu_read_lock.
+ *   profiles - each profile is a label
+ *   secids - a pinned secid will keep a refcount of the label it is
+ *          referencing
+ *   objects - inode, files, sockets, ...
+ *
+ * Labels are not ref counted by the label set, so they maybe removed and
+ * freed when no longer in use.
+ *
+ */
+
+#define PROXY_POISON 97
+#define LABEL_POISON 100
+
+static void free_proxy(struct aa_proxy *proxy)
+{
+	if (proxy) {
+		/* p->label will not updated any more as p is dead */
+		aa_put_label(rcu_dereference_protected(proxy->label, true));
+		memset(proxy, 0, sizeof(*proxy));
+		RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON);
+		kfree(proxy);
+	}
+}
+
+void aa_proxy_kref(struct kref *kref)
+{
+	struct aa_proxy *proxy = container_of(kref, struct aa_proxy,
+					      count.count);
+
+	free_proxy(proxy);
+}
+
+struct aa_proxy *aa_alloc_proxy(struct aa_label *label, gfp_t gfp)
+{
+	struct aa_proxy *new;
+
+	new = kzalloc_obj(struct aa_proxy, gfp);
+	if (new) {
+		kref_init(&new->count.count);
+		new->count.reftype = REF_PROXY;
+		rcu_assign_pointer(new->label, aa_get_label(label));
+	}
+	return new;
+}
+
+/* requires profile list write lock held */
+void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new)
+{
+	struct aa_label *tmp;
+
+	AA_BUG(!orig);
+	AA_BUG(!new);
+	lockdep_assert_held_write(&labels_set(orig)->lock);
+
+	tmp = rcu_dereference_protected(orig->proxy->label,
+					&labels_ns(orig)->lock);
+	rcu_assign_pointer(orig->proxy->label, aa_get_label(new));
+	__label_make_stale(orig);
+	aa_put_label(tmp);
+}
+
+static void __proxy_share(struct aa_label *old, struct aa_label *new)
+{
+	struct aa_proxy *proxy = new->proxy;
+
+	new->proxy = aa_get_proxy(old->proxy);
+	__aa_proxy_redirect(old, new);
+	aa_put_proxy(proxy);
+}
+
+
+/**
+ * ns_cmp - compare ns for label set ordering
+ * @a: ns to compare (NOT NULL)
+ * @b: ns to compare (NOT NULL)
+ *
+ * Returns: <0 if a < b
+ *          ==0 if a == b
+ *          >0  if a > b
+ */
+static int ns_cmp(struct aa_ns *a, struct aa_ns *b)
+{
+	int res;
+
+	AA_BUG(!a);
+	AA_BUG(!b);
+	AA_BUG(!a->base.hname);
+	AA_BUG(!b->base.hname);
+
+	if (a == b)
+		return 0;
+
+	res = a->level - b->level;
+	if (res)
+		return res;
+
+	return strcmp(a->base.hname, b->base.hname);
+}
+
+/**
+ * profile_cmp - profile comparison for set ordering
+ * @a: profile to compare (NOT NULL)
+ * @b: profile to compare (NOT NULL)
+ *
+ * Returns: <0  if a < b
+ *          ==0 if a == b
+ *          >0  if a > b
+ */
+static int profile_cmp(struct aa_profile *a, struct aa_profile *b)
+{
+	int res;
+
+	AA_BUG(!a);
+	AA_BUG(!b);
+	AA_BUG(!a->ns);
+	AA_BUG(!b->ns);
+	AA_BUG(!a->base.hname);
+	AA_BUG(!b->base.hname);
+
+	if (a == b || a->base.hname == b->base.hname)
+		return 0;
+	res = ns_cmp(a->ns, b->ns);
+	if (res)
+		return res;
+
+	return strcmp(a->base.hname, b->base.hname);
+}
+
+/**
+ * vec_cmp - label comparison for set ordering
+ * @a: aa_profile to compare (NOT NULL)
+ * @an: length of @a
+ * @b: aa_profile to compare (NOT NULL)
+ * @bn: length of @b
+ *
+ * Returns: <0  if @a < @b
+ *          ==0 if @a == @b
+ *          >0  if @a > @b
+ */
+static int vec_cmp(struct aa_profile * const *a, int an,
+		   struct aa_profile * const *b, int bn)
+{
+	int i;
+
+	AA_BUG(!a);
+	AA_BUG(!*a);
+	AA_BUG(!b);
+	AA_BUG(!*b);
+	AA_BUG(an <= 0);
+	AA_BUG(bn <= 0);
+
+	for (i = 0; i < an && i < bn; i++) {
+		int res = profile_cmp(a[i], b[i]);
+
+		if (res != 0)
+			return res;
+	}
+
+	return an - bn;
+}
+
+static bool vec_is_stale(struct aa_profile **vec, int n)
+{
+	int i;
+
+	AA_BUG(!vec);
+
+	for (i = 0; i < n; i++) {
+		if (profile_is_stale(vec[i]))
+			return true;
+	}
+
+	return false;
+}
+
+static void accum_label_info(struct aa_label *new)
+{
+	long u = FLAG_UNCONFINED;
+	int i;
+
+	AA_BUG(!new);
+
+	/* size == 1 is a profile and flags must be set as part of creation */
+	if (new->size == 1)
+		return;
+
+	for (i = 0; i < new->size; i++) {
+		u |= new->vec[i]->label.flags & (FLAG_DEBUG1 | FLAG_DEBUG2 |
+						 FLAG_STALE);
+		if (!(u & new->vec[i]->label.flags & FLAG_UNCONFINED))
+			u &= ~FLAG_UNCONFINED;
+		new->mediates |= new->vec[i]->label.mediates;
+	}
+	new->flags |= u;
+}
+
+static int sort_cmp(const void *a, const void *b)
+{
+	return profile_cmp(*(struct aa_profile **)a, *(struct aa_profile **)b);
+}
+
+/*
+ * assumes vec is sorted
+ * Assumes @vec has null terminator at vec[n], and will null terminate
+ * vec[n - dups]
+ */
+static inline int unique(struct aa_profile **vec, int n)
+{
+	int i, pos, dups = 0;
+
+	AA_BUG(n < 1);
+	AA_BUG(!vec);
+
+	pos = 0;
+	for (i = 1; i < n; i++) {
+		int res = profile_cmp(vec[pos], vec[i]);
+
+		AA_BUG(res > 0, "vec not sorted");
+		if (res == 0) {
+			/* drop duplicate */
+			aa_put_profile(vec[i]);
+			dups++;
+			continue;
+		}
+		pos++;
+		if (dups)
+			vec[pos] = vec[i];
+	}
+
+	AA_BUG(dups < 0);
+
+	return dups;
+}
+
+/**
+ * aa_vec_unique - canonical sort and unique a list of profiles
+ * @n: number of refcounted profiles in the list (@n > 0)
+ * @vec: list of profiles to sort and merge
+ * @flags: null terminator flags of @vec
+ *
+ * Returns: the number of duplicates eliminated == references put
+ *
+ * If @flags & VEC_FLAG_TERMINATE @vec has null terminator at vec[n], and will
+ * null terminate vec[n - dups]
+ */
+int aa_vec_unique(struct aa_profile **vec, int n, int flags)
+{
+	int i, dups = 0;
+
+	AA_BUG(n < 1);
+	AA_BUG(!vec);
+
+	/* vecs are usually small and inorder, have a fallback for larger */
+	if (n > 8) {
+		sort(vec, n, sizeof(struct aa_profile *), sort_cmp, NULL);
+		dups = unique(vec, n);
+		goto out;
+	}
+
+	/* insertion sort + unique in one */
+	for (i = 1; i < n; i++) {
+		struct aa_profile *tmp = vec[i];
+		int pos, j;
+
+		for (pos = i - 1 - dups; pos >= 0; pos--) {
+			int res = profile_cmp(vec[pos], tmp);
+
+			if (res == 0) {
+				/* drop duplicate entry */
+				aa_put_profile(tmp);
+				dups++;
+				goto continue_outer;
+			} else if (res < 0)
+				break;
+		}
+		/* pos is at entry < tmp, or index -1. Set to insert pos */
+		pos++;
+
+		for (j = i - dups; j > pos; j--)
+			vec[j] = vec[j - 1];
+		vec[pos] = tmp;
+continue_outer:
+		;
+	}
+
+	AA_BUG(dups < 0);
+
+out:
+	if (flags & VEC_FLAG_TERMINATE)
+		vec[n - dups] = NULL;
+
+	return dups;
+}
+
+
+void aa_label_destroy(struct aa_label *label)
+{
+	AA_BUG(!label);
+
+	if (!label_isprofile(label)) {
+		struct aa_profile *profile;
+		struct label_it i;
+
+		aa_put_str(label->hname);
+
+		label_for_each(i, label, profile) {
+			aa_put_profile(profile);
+			label->vec[i.i] = (struct aa_profile *)
+					   (LABEL_POISON + (long) i.i);
+		}
+	}
+
+	if (label->proxy) {
+		if (rcu_dereference_protected(label->proxy->label, true) == label)
+			rcu_assign_pointer(label->proxy->label, NULL);
+		aa_put_proxy(label->proxy);
+	}
+	aa_free_secid(label->secid);
+
+	label->proxy = (struct aa_proxy *) PROXY_POISON + 1;
+}
+
+void aa_label_free(struct aa_label *label)
+{
+	if (!label)
+		return;
+
+	aa_label_destroy(label);
+	kfree(label);
+}
+
+static void label_free_switch(struct aa_label *label)
+{
+	if (label->flags & FLAG_NS_COUNT)
+		aa_free_ns(labels_ns(label));
+	else if (label_isprofile(label))
+		aa_free_profile(labels_profile(label));
+	else
+		aa_label_free(label);
+}
+
+static void label_free_rcu(struct rcu_head *head)
+{
+	struct aa_label *label = container_of(head, struct aa_label, rcu);
+
+	if (label->flags & FLAG_IN_TREE)
+		(void) aa_label_remove(label);
+	label_free_switch(label);
+}
+
+void aa_label_kref(struct kref *kref)
+{
+	struct aa_label *label = container_of(kref, struct aa_label,
+					      count.count);
+	struct aa_ns *ns = labels_ns(label);
+
+	if (!ns) {
+		/* never live, no rcu callback needed, just using the fn */
+		label_free_switch(label);
+		return;
+	}
+	/* TODO: update labels_profile macro so it works here */
+	AA_BUG(label_isprofile(label) &&
+	       on_list_rcu(&label->vec[0]->base.profiles));
+	AA_BUG(label_isprofile(label) &&
+	       on_list_rcu(&label->vec[0]->base.list));
+
+	/* TODO: if compound label and not stale add to reclaim cache */
+	call_rcu(&label->rcu, label_free_rcu);
+}
+
+static void label_free_or_put_new(struct aa_label *label, struct aa_label *new)
+{
+	if (label != new)
+		/* need to free directly to break circular ref with proxy */
+		aa_label_free(new);
+	else
+		aa_put_label(new);
+}
+
+bool aa_label_init(struct aa_label *label, int size, gfp_t gfp)
+{
+	AA_BUG(!label);
+	AA_BUG(size < 1);
+
+	if (aa_alloc_secid(label, gfp) < 0)
+		return false;
+
+	label->size = size;			/* doesn't include null */
+	label->vec[size] = NULL;		/* null terminate */
+	kref_init(&label->count.count);
+	label->count.reftype = REF_NS;		/* for aafs purposes */
+	RB_CLEAR_NODE(&label->node);
+
+	return true;
+}
+
+/**
+ * aa_label_alloc - allocate a label with a profile vector of @size length
+ * @size: size of profile vector in the label
+ * @proxy: proxy to use OR null if to allocate a new one
+ * @gfp: memory allocation type
+ *
+ * Returns: new label
+ *     else NULL if failed
+ */
+struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp)
+{
+	struct aa_label *new;
+
+	AA_BUG(size < 1);
+
+	/*  + 1 for null terminator entry on vec */
+	new = kzalloc_flex(*new, vec, size + 1, gfp);
+	AA_DEBUG(DEBUG_LABEL, "%s (%p)\n", __func__, new);
+	if (!new)
+		goto fail;
+
+	if (!aa_label_init(new, size, gfp))
+		goto fail;
+
+	if (!proxy) {
+		proxy = aa_alloc_proxy(new, gfp);
+		if (!proxy)
+			goto fail;
+	} else
+		aa_get_proxy(proxy);
+	/* just set new's proxy, don't redirect proxy here if it was passed in*/
+	new->proxy = proxy;
+
+	return new;
+
+fail:
+	aa_label_free(new);
+
+	return NULL;
+}
+
+
+/**
+ * label_cmp - label comparison for set ordering
+ * @a: label to compare (NOT NULL)
+ * @b: label to compare (NOT NULL)
+ *
+ * Returns: <0  if a < b
+ *          ==0 if a == b
+ *          >0  if a > b
+ */
+static int label_cmp(const struct aa_label *a, const struct aa_label *b)
+{
+	AA_BUG(!b);
+
+	if (a == b)
+		return 0;
+
+	return vec_cmp(a->vec, a->size, b->vec, b->size);
+}
+
+/* helper fn for label_for_each_confined */
+int aa_label_next_confined(const struct aa_label *label, int i)
+{
+	AA_BUG(!label);
+	AA_BUG(i < 0);
+
+	for (; i < label->size; i++) {
+		if (!profile_unconfined(label->vec[i]))
+			return i;
+	}
+
+	return i;
+}
+
+/**
+ * __aa_label_next_not_in_set - return the next profile of @sub not in @set
+ * @I: label iterator
+ * @set: label to test against
+ * @sub: label to if is subset of @set
+ *
+ * Returns: profile in @sub that is not in @set, with iterator set pos after
+ *     else NULL if @sub is a subset of @set
+ */
+struct aa_profile *__aa_label_next_not_in_set(struct label_it *I,
+					      const struct aa_label *set,
+					      const struct aa_label *sub)
+{
+	AA_BUG(!set);
+	AA_BUG(!I);
+	AA_BUG(I->i < 0);
+	AA_BUG(I->i > set->size);
+	AA_BUG(!sub);
+	AA_BUG(I->j < 0);
+	AA_BUG(I->j > sub->size);
+
+	while (I->j < sub->size && I->i < set->size) {
+		int res = profile_cmp(sub->vec[I->j], set->vec[I->i]);
+
+		if (res == 0) {
+			(I->j)++;
+			(I->i)++;
+		} else if (res > 0)
+			(I->i)++;
+		else
+			return sub->vec[(I->j)++];
+	}
+
+	if (I->j < sub->size)
+		return sub->vec[(I->j)++];
+
+	return NULL;
+}
+
+/**
+ * aa_label_is_subset - test if @sub is a subset of @set
+ * @set: label to test against
+ * @sub: label to test if is subset of @set
+ *
+ * Returns: true if @sub is subset of @set
+ *     else false
+ */
+bool aa_label_is_subset(const struct aa_label *set, const struct aa_label *sub)
+{
+	struct label_it i = { };
+
+	AA_BUG(!set);
+	AA_BUG(!sub);
+
+	if (sub == set)
+		return true;
+
+	return __aa_label_next_not_in_set(&i, set, sub) == NULL;
+}
+
+/**
+ * aa_label_is_unconfined_subset - test if @sub is a subset of @set
+ * @set: label to test against
+ * @sub: label to test if is subset of @set
+ *
+ * This checks for subset but taking into account unconfined. IF
+ * @sub contains an unconfined profile that does not have a matching
+ * unconfined in @set then this will not cause the test to fail.
+ * Conversely we don't care about an unconfined in @set that is not in
+ * @sub
+ *
+ * Returns: true if @sub is special_subset of @set
+ *     else false
+ */
+bool aa_label_is_unconfined_subset(const struct aa_label *set,
+				   const struct aa_label *sub)
+{
+	struct label_it i = { };
+	struct aa_profile *p;
+
+	AA_BUG(!set);
+	AA_BUG(!sub);
+
+	if (sub == set)
+		return true;
+
+	do {
+		p = __aa_label_next_not_in_set(&i, set, sub);
+		if (p && !profile_unconfined(p))
+			break;
+	} while (p);
+
+	return p == NULL;
+}
+
+
+/**
+ * __label_remove - remove @label from the label set
+ * @label: label to remove
+ * @new: label to redirect to
+ *
+ * Requires: labels_set(@label)->lock write_lock
+ * Returns:  true if the label was in the tree and removed
+ */
+static bool __label_remove(struct aa_label *label, struct aa_label *new)
+{
+	struct aa_labelset *ls = labels_set(label);
+
+	AA_BUG(!ls);
+	AA_BUG(!label);
+	lockdep_assert_held_write(&ls->lock);
+
+	if (new)
+		__aa_proxy_redirect(label, new);
+
+	if (!label_is_stale(label))
+		__label_make_stale(label);
+
+	if (label->flags & FLAG_IN_TREE) {
+		rb_erase(&label->node, &ls->root);
+		label->flags &= ~FLAG_IN_TREE;
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * __label_replace - replace @old with @new in label set
+ * @old: label to remove from label set
+ * @new: label to replace @old with
+ *
+ * Requires: labels_set(@old)->lock write_lock
+ *           valid ref count be held on @new
+ * Returns: true if @old was in set and replaced by @new
+ *
+ * Note: current implementation requires label set be order in such a way
+ *       that @new directly replaces @old position in the set (ie.
+ *       using pointer comparison of the label address would not work)
+ */
+static bool __label_replace(struct aa_label *old, struct aa_label *new)
+{
+	struct aa_labelset *ls = labels_set(old);
+
+	AA_BUG(!ls);
+	AA_BUG(!old);
+	AA_BUG(!new);
+	lockdep_assert_held_write(&ls->lock);
+	AA_BUG(new->flags & FLAG_IN_TREE);
+
+	if (!label_is_stale(old))
+		__label_make_stale(old);
+
+	if (old->flags & FLAG_IN_TREE) {
+		rb_replace_node(&old->node, &new->node, &ls->root);
+		old->flags &= ~FLAG_IN_TREE;
+		new->flags |= FLAG_IN_TREE;
+		accum_label_info(new);
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * __label_insert - attempt to insert @l into a label set
+ * @ls: set of labels to insert @l into (NOT NULL)
+ * @label: new label to insert (NOT NULL)
+ * @replace: whether insertion should replace existing entry that is not stale
+ *
+ * Requires: @ls->lock
+ *           caller to hold a valid ref on l
+ *           if @replace is true l has a preallocated proxy associated
+ * Returns: @l if successful in inserting @l - with additional refcount
+ *          else ref counted equivalent label that is already in the set,
+ *          the else condition only happens if @replace is false
+ */
+static struct aa_label *__label_insert(struct aa_labelset *ls,
+				       struct aa_label *label, bool replace)
+{
+	struct rb_node **new, *parent = NULL;
+
+	AA_BUG(!ls);
+	AA_BUG(!label);
+	AA_BUG(labels_set(label) != ls);
+	lockdep_assert_held_write(&ls->lock);
+	AA_BUG(label->flags & FLAG_IN_TREE);
+
+	/* Figure out where to put new node */
+	new = &ls->root.rb_node;
+	while (*new) {
+		struct aa_label *this = rb_entry(*new, struct aa_label, node);
+		int result = label_cmp(label, this);
+
+		parent = *new;
+		if (result == 0) {
+			/* !__aa_get_label means queued for destruction,
+			 * so replace in place, however the label has
+			 * died before the replacement so do not share
+			 * the proxy
+			 */
+			if (!replace && !label_is_stale(this)) {
+				if (__aa_get_label(this))
+					return this;
+			} else
+				__proxy_share(this, label);
+			AA_BUG(!__label_replace(this, label));
+			return aa_get_label(label);
+		} else if (result < 0)
+			new = &((*new)->rb_left);
+		else /* (result > 0) */
+			new = &((*new)->rb_right);
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&label->node, parent, new);
+	rb_insert_color(&label->node, &ls->root);
+	label->flags |= FLAG_IN_TREE;
+	accum_label_info(label);
+
+	return aa_get_label(label);
+}
+
+/**
+ * __vec_find - find label that matches @vec in label set
+ * @vec: vec of profiles to find matching label for (NOT NULL)
+ * @n: length of @vec
+ *
+ * Requires: @vec_labelset(vec) lock held
+ *           caller to hold a valid ref on l
+ *
+ * Returns: ref counted @label if matching label is in tree
+ *          ref counted label that is equiv to @l in tree
+ *     else NULL if @vec equiv is not in tree
+ */
+static struct aa_label *__vec_find(struct aa_profile **vec, int n)
+{
+	struct rb_node *node;
+
+	AA_BUG(!vec);
+	AA_BUG(!*vec);
+	AA_BUG(n <= 0);
+
+	node = vec_labelset(vec, n)->root.rb_node;
+	while (node) {
+		struct aa_label *this = rb_entry(node, struct aa_label, node);
+		int result = vec_cmp(this->vec, this->size, vec, n);
+
+		if (result > 0)
+			node = node->rb_left;
+		else if (result < 0)
+			node = node->rb_right;
+		else
+			return __aa_get_label(this);
+	}
+
+	return NULL;
+}
+
+/**
+ * __label_find - find label @label in label set
+ * @label: label to find (NOT NULL)
+ *
+ * Requires: labels_set(@label)->lock held
+ *           caller to hold a valid ref on l
+ *
+ * Returns: ref counted @label if @label is in tree OR
+ *          ref counted label that is equiv to @label in tree
+ *     else NULL if @label or equiv is not in tree
+ */
+static struct aa_label *__label_find(struct aa_label *label)
+{
+	AA_BUG(!label);
+
+	return __vec_find(label->vec, label->size);
+}
+
+
+/**
+ * aa_label_remove - remove a label from the labelset
+ * @label: label to remove
+ *
+ * Returns: true if @label was removed from the tree
+ *     else @label was not in tree so it could not be removed
+ */
+bool aa_label_remove(struct aa_label *label)
+{
+	struct aa_labelset *ls = labels_set(label);
+	unsigned long flags;
+	bool res;
+
+	AA_BUG(!ls);
+
+	write_lock_irqsave(&ls->lock, flags);
+	res = __label_remove(label, ns_unconfined(labels_ns(label)));
+	write_unlock_irqrestore(&ls->lock, flags);
+
+	return res;
+}
+
+enum ls_lock_class {
+	AA_LS_LOCK_FIRST,
+	AA_LS_LOCK_SECOND,
+};
+
+#define write_lock_irqsave_nested(L, F, SC) write_lock_irqsave(L, F)
+
+static void ns_ls_double_lock(struct aa_ns *ns1, struct aa_ns *ns2,
+	unsigned long *flags)
+{
+	if (likely(ns1 == ns2)) {
+		write_lock_irqsave(&ns1->labels.lock, *flags);
+		return;
+	}
+
+	/* ordered by namespace hierarchy (walked in nesting order in
+	 * labels_update. If at the same level by address order
+	 */
+	if ((ns1->level > ns2->level) ||
+	    (ns1->level == ns2->level && ns1 > ns2))
+		swap(ns1, ns2);
+
+	write_lock_irqsave_nested(&ns1->labels.lock, *flags, AA_LS_LOCK_FIRST);
+	write_lock_nested(&ns2->labels.lock, AA_LS_LOCK_SECOND);
+}
+
+static void ns_ls_double_unlock(struct aa_ns *ns1, struct aa_ns *ns2,
+			     unsigned long flags)
+{
+	if (likely(ns1 == ns2)) {
+		write_unlock_irqrestore(&ns1->labels.lock, flags);
+		return;
+	}
+	/* order doesn't matter on unlock, except flags restore must be last */
+	write_unlock(&ns2->labels.lock);
+	write_unlock_irqrestore(&ns1->labels.lock, flags);
+}
+
+/**
+ * aa_label_replace - replace a label @old with a new version @new
+ * @old: label to replace
+ * @new: label replacing @old
+ *
+ * Returns: true if @old was in tree and replaced
+ *     else @old was not in tree, and @new was not inserted
+ *
+ * replacement can involve two different labelsets so has to be
+ * handled very careful, as a double lock may be required.
+ */
+bool aa_label_replace(struct aa_label *old, struct aa_label *new)
+{
+	struct aa_ns *ons = labels_ns(old);
+	struct aa_ns *nns = labels_ns(new);
+	unsigned long flags;
+	bool res;
+
+	ns_ls_double_lock(ons, nns, &flags);
+	if (ons == nns && name_is_shared(old, new)) {
+		if (old->proxy != new->proxy)
+			__proxy_share(old, new);
+		else
+			__aa_proxy_redirect(old, new);
+		res = __label_replace(old, new);
+	} else {
+		struct aa_label *l;
+
+		/* will redirect old proxy to new */
+		res = __label_remove(old, new);
+		l = __label_insert(&nns->labels, new, true);
+		res = (l == new);
+		aa_put_label(l);
+	}
+	ns_ls_double_unlock(ons, nns, flags);
+
+	return res;
+}
+
+/**
+ * vec_find - find label @l in label set
+ * @vec: array of profiles to find equiv label for (NOT NULL)
+ * @n: length of @vec
+ *
+ * Returns: refcounted label if @vec equiv is in tree
+ *     else NULL if @vec equiv is not in tree
+ */
+static struct aa_label *vec_find(struct aa_profile **vec, int n)
+{
+	struct aa_labelset *ls;
+	struct aa_label *label;
+	unsigned long flags;
+
+	AA_BUG(!vec);
+	AA_BUG(!*vec);
+	AA_BUG(n <= 0);
+
+	ls = vec_labelset(vec, n);
+	read_lock_irqsave(&ls->lock, flags);
+	label = __vec_find(vec, n);
+	read_unlock_irqrestore(&ls->lock, flags);
+
+	return label;
+}
+
+/* requires sort and merge done first */
+static struct aa_label *vec_create_and_insert_label(struct aa_profile **vec,
+						    int len, gfp_t gfp)
+{
+	struct aa_label *label = NULL;
+	struct aa_labelset *ls;
+	unsigned long flags;
+	struct aa_label *new;
+	int i;
+
+	AA_BUG(!vec);
+
+	if (len == 1)
+		return aa_get_label(&vec[0]->label);
+
+	ls = labels_set(&vec[len - 1]->label);
+
+	/* TODO: enable when read side is lockless
+	 * check if label exists before taking locks
+	 */
+	new = aa_label_alloc(len, NULL, gfp);
+	if (!new)
+		return NULL;
+
+	for (i = 0; i < len; i++)
+		new->vec[i] = aa_get_profile(vec[i]);
+
+	write_lock_irqsave(&ls->lock, flags);
+	label = __label_insert(ls, new, false);
+	write_unlock_irqrestore(&ls->lock, flags);
+	label_free_or_put_new(label, new);
+
+	return label;
+}
+
+struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len,
+					     gfp_t gfp)
+{
+	struct aa_label *label = vec_find(vec, len);
+
+	if (label)
+		return label;
+
+	return vec_create_and_insert_label(vec, len, gfp);
+}
+
+
+/**
+ * aa_label_insert - insert label @label into @ls or return existing label
+ * @ls: labelset to insert @label into
+ * @label: label to insert
+ *
+ * Requires: caller to hold a valid ref on @label
+ *
+ * Returns: ref counted @label if successful in inserting @label
+ *     else ref counted equivalent label that is already in the set
+ */
+struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *label)
+{
+	struct aa_label *l;
+	unsigned long flags;
+
+	AA_BUG(!ls);
+	AA_BUG(!label);
+
+	/* check if label exists before taking lock */
+	if (!label_is_stale(label)) {
+		read_lock_irqsave(&ls->lock, flags);
+		l = __label_find(label);
+		read_unlock_irqrestore(&ls->lock, flags);
+		if (l)
+			return l;
+	}
+
+	write_lock_irqsave(&ls->lock, flags);
+	l = __label_insert(ls, label, false);
+	write_unlock_irqrestore(&ls->lock, flags);
+
+	return l;
+}
+
+
+/**
+ * aa_label_next_in_merge - find the next profile when merging @a and @b
+ * @I: label iterator
+ * @a: label to merge
+ * @b: label to merge
+ *
+ * Returns: next profile
+ *     else null if no more profiles
+ */
+struct aa_profile *aa_label_next_in_merge(struct label_it *I,
+					  const struct aa_label *a,
+					  const struct aa_label *b)
+{
+	AA_BUG(!a);
+	AA_BUG(!b);
+	AA_BUG(!I);
+	AA_BUG(I->i < 0);
+	AA_BUG(I->i > a->size);
+	AA_BUG(I->j < 0);
+	AA_BUG(I->j > b->size);
+
+	if (I->i < a->size) {
+		if (I->j < b->size) {
+			int res = profile_cmp(a->vec[I->i], b->vec[I->j]);
+
+			if (res > 0)
+				return b->vec[(I->j)++];
+			if (res == 0)
+				(I->j)++;
+		}
+
+		return a->vec[(I->i)++];
+	}
+
+	if (I->j < b->size)
+		return b->vec[(I->j)++];
+
+	return NULL;
+}
+
+/**
+ * label_merge_cmp - cmp of @a merging with @b against @z for set ordering
+ * @a: label to merge then compare (NOT NULL)
+ * @b: label to merge then compare (NOT NULL)
+ * @z: label to compare merge against (NOT NULL)
+ *
+ * Assumes: using the most recent versions of @a, @b, and @z
+ *
+ * Returns: <0  if a < b
+ *          ==0 if a == b
+ *          >0  if a > b
+ */
+static int label_merge_cmp(struct aa_label *a, struct aa_label *b,
+			   struct aa_label *z)
+{
+	struct aa_profile *p = NULL;
+	struct label_it i = { };
+	int k;
+
+	AA_BUG(!a);
+	AA_BUG(!b);
+	AA_BUG(!z);
+
+	for (k = 0;
+	     k < z->size && (p = aa_label_next_in_merge(&i, a, b));
+	     k++) {
+		int res = profile_cmp(p, z->vec[k]);
+
+		if (res != 0)
+			return res;
+	}
+
+	if (p)
+		return 1;
+	else if (k < z->size)
+		return -1;
+	return 0;
+}
+
+/**
+ * label_merge_insert - create a new label by merging @a and @b
+ * @new: preallocated label to merge into (NOT NULL)
+ * @a: label to merge with @b  (NOT NULL)
+ * @b: label to merge with @a  (NOT NULL)
+ *
+ * Requires: preallocated proxy
+ *
+ * Returns: ref counted label either @new if merge is unique
+ *          @a if @b is a subset of @a
+ *          @b if @a is a subset of @b
+ *
+ * NOTE: will not use @new if the merge results in @new == @a or @b
+ *
+ *       Must be used within labelset write lock to avoid racing with
+ *       setting labels stale.
+ */
+static struct aa_label *label_merge_insert(struct aa_label *new,
+					   struct aa_label *a,
+					   struct aa_label *b)
+{
+	struct aa_label *label;
+	struct aa_labelset *ls;
+	struct aa_profile *next;
+	struct label_it i;
+	unsigned long flags;
+	int k = 0, invcount = 0;
+	bool stale = false;
+
+	AA_BUG(!a);
+	AA_BUG(a->size < 0);
+	AA_BUG(!b);
+	AA_BUG(b->size < 0);
+	AA_BUG(!new);
+	AA_BUG(new->size < a->size + b->size);
+
+	label_for_each_in_merge(i, a, b, next) {
+		AA_BUG(!next);
+		if (profile_is_stale(next)) {
+			new->vec[k] = aa_get_newest_profile(next);
+			AA_BUG(!new->vec[k]->label.proxy);
+			AA_BUG(!new->vec[k]->label.proxy->label);
+			if (next->label.proxy != new->vec[k]->label.proxy)
+				invcount++;
+			k++;
+			stale = true;
+		} else
+			new->vec[k++] = aa_get_profile(next);
+	}
+	/* set to actual size which is <= allocated len */
+	new->size = k;
+	new->vec[k] = NULL;
+
+	if (invcount) {
+		new->size -= aa_vec_unique(&new->vec[0], new->size,
+					   VEC_FLAG_TERMINATE);
+		/* TODO: deal with reference labels */
+		if (new->size == 1) {
+			label = aa_get_label(&new->vec[0]->label);
+			return label;
+		}
+	} else if (!stale) {
+		/*
+		 * merge could be same as a || b, note: it is not possible
+		 * for new->size == a->size == b->size unless a == b
+		 */
+		if (k == a->size)
+			return aa_get_label(a);
+		else if (k == b->size)
+			return aa_get_label(b);
+	}
+	ls = labels_set(new);
+	write_lock_irqsave(&ls->lock, flags);
+	label = __label_insert(labels_set(new), new, false);
+	write_unlock_irqrestore(&ls->lock, flags);
+
+	return label;
+}
+
+/**
+ * labelset_of_merge - find which labelset a merged label should be inserted
+ * @a: label to merge and insert
+ * @b: label to merge and insert
+ *
+ * Returns: labelset that the merged label should be inserted into
+ */
+static struct aa_labelset *labelset_of_merge(struct aa_label *a,
+					     struct aa_label *b)
+{
+	struct aa_ns *nsa = labels_ns(a);
+	struct aa_ns *nsb = labels_ns(b);
+
+	if (ns_cmp(nsa, nsb) <= 0)
+		return &nsa->labels;
+	return &nsb->labels;
+}
+
+/**
+ * __label_find_merge - find label that is equiv to merge of @a and @b
+ * @ls: set of labels to search (NOT NULL)
+ * @a: label to merge with @b  (NOT NULL)
+ * @b: label to merge with @a  (NOT NULL)
+ *
+ * Requires: ls->lock read_lock held
+ *
+ * Returns: ref counted label that is equiv to merge of @a and @b
+ *     else NULL if merge of @a and @b is not in set
+ */
+static struct aa_label *__label_find_merge(struct aa_labelset *ls,
+					   struct aa_label *a,
+					   struct aa_label *b)
+{
+	struct rb_node *node;
+
+	AA_BUG(!ls);
+	AA_BUG(!a);
+	AA_BUG(!b);
+
+	if (a == b)
+		return __label_find(a);
+
+	node  = ls->root.rb_node;
+	while (node) {
+		struct aa_label *this = container_of(node, struct aa_label,
+						     node);
+		int result = label_merge_cmp(a, b, this);
+
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return __aa_get_label(this);
+	}
+
+	return NULL;
+}
+
+
+/**
+ * aa_label_find_merge - find label that is equiv to merge of @a and @b
+ * @a: label to merge with @b  (NOT NULL)
+ * @b: label to merge with @a  (NOT NULL)
+ *
+ * Requires: labels be fully constructed with a valid ns
+ *
+ * Returns: ref counted label that is equiv to merge of @a and @b
+ *     else NULL if merge of @a and @b is not in set
+ */
+struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b)
+{
+	struct aa_labelset *ls;
+	struct aa_label *label;
+	unsigned long flags;
+	bool a_needput, b_needput;
+
+	AA_BUG(!a);
+	AA_BUG(!b);
+
+	a = aa_get_newest_label_condref(a, &a_needput);
+	b = aa_get_newest_label_condref(b, &b_needput);
+	ls = labelset_of_merge(a, b);
+	read_lock_irqsave(&ls->lock, flags);
+	label = __label_find_merge(ls, a, b);
+	read_unlock_irqrestore(&ls->lock, flags);
+	aa_put_label_condref(a, a_needput);
+	aa_put_label_condref(b, b_needput);
+
+	return label;
+}
+
+/**
+ * aa_label_merge - attempt to insert new merged label of @a and @b
+ * @a: label to merge with @b  (NOT NULL)
+ * @b: label to merge with @a  (NOT NULL)
+ * @gfp: memory allocation type
+ *
+ * Requires: caller to hold valid refs on @a and @b
+ *           labels be fully constructed with a valid ns
+ *
+ * Returns: ref counted new label if successful in inserting merge of a & b
+ *     else ref counted equivalent label that is already in the set.
+ *     else NULL if could not create label (-ENOMEM)
+ */
+struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b,
+				gfp_t gfp)
+{
+	struct aa_label *label = NULL;
+
+	AA_BUG(!a);
+	AA_BUG(!b);
+
+	if (a == b)
+		return aa_get_newest_label(a);
+
+	/* TODO: enable when read side is lockless
+	 * check if label exists before taking locks
+	if (!label_is_stale(a) && !label_is_stale(b))
+		label = aa_label_find_merge(a, b);
+	*/
+
+	if (!label) {
+		struct aa_label *new;
+		bool a_needput, b_needput;
+
+		a = aa_get_newest_label_condref(a, &a_needput);
+		b = aa_get_newest_label_condref(b, &b_needput);
+
+		/* could use label_merge_len(a, b), but requires double
+		 * comparison for small savings
+		 */
+		new = aa_label_alloc(a->size + b->size, NULL, gfp);
+		if (!new)
+			goto out;
+
+		label = label_merge_insert(new, a, b);
+		label_free_or_put_new(label, new);
+out:
+		aa_put_label_condref(a, a_needput);
+		aa_put_label_condref(b, b_needput);
+	}
+
+	return label;
+}
+
+/* match a profile and its associated ns component if needed
+ * Assumes visibility test has already been done.
+ * If a subns profile is not to be matched should be prescreened with
+ * visibility test.
+ */
+static inline aa_state_t match_component(const struct aa_profile *profile,
+					 struct aa_ruleset *rules,
+					 const struct aa_profile *tp,
+					 aa_state_t state)
+{
+	const char *ns_name;
+
+	if (profile->ns == tp->ns)
+		return aa_dfa_match(rules->policy->dfa, state, tp->base.hname);
+
+	/* try matching with namespace name and then profile */
+	ns_name = aa_ns_name(profile->ns, tp->ns, true);
+	state = aa_dfa_match_len(rules->policy->dfa, state, ":", 1);
+	state = aa_dfa_match(rules->policy->dfa, state, ns_name);
+	state = aa_dfa_match_len(rules->policy->dfa, state, ":", 1);
+	return aa_dfa_match(rules->policy->dfa, state, tp->base.hname);
+}
+
+/**
+ * label_compound_match - find perms for full compound label
+ * @profile: profile to find perms for
+ * @rules: ruleset to search
+ * @label: label to check access permissions for
+ * @state: state to start match in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permissions to request
+ * @perms: perms struct to set
+ *
+ * Returns: state match stopped at or DFA_NOMATCH if aborted early
+ *
+ * For the label A//&B//&C this does the perm match for A//&B//&C
+ * @perms should be preinitialized with allperms OR a previous permission
+ *        check to be stacked.
+ */
+static int label_compound_match(const struct aa_profile *profile,
+				struct aa_ruleset *rules,
+				struct aa_label *label,
+				aa_state_t state, bool inview, u32 request,
+				struct aa_perms *perms)
+{
+	struct aa_profile *tp;
+	struct label_it i;
+
+	/* find first subcomponent that is visible */
+	label_for_each(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, rules, tp, state);
+		if (!state)
+			goto fail;
+		goto next;
+	}
+
+	/* no component visible */
+	*perms = allperms;
+	return state;
+
+next:
+	label_for_each_cont(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = aa_dfa_match(rules->policy->dfa, state, "//&");
+		state = match_component(profile, rules, tp, state);
+		if (!state)
+			goto fail;
+	}
+	*perms = *aa_lookup_perms(rules->policy, state);
+	return state;
+
+fail:
+	*perms = nullperms;
+	return DFA_NOMATCH;
+}
+
+/**
+ * label_components_match - find perms for all subcomponents of a label
+ * @profile: profile to find perms for
+ * @rules: ruleset to search
+ * @label: label to check access permissions for
+ * @start: state to start match in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permissions to request
+ * @perms: an initialized perms struct to add accumulation to
+ *
+ * Returns: the state the match finished in, may be the none matching state
+ *
+ * For the label A//&B//&C this does the perm match for each of A and B and C
+ * @perms should be preinitialized with allperms OR a previous permission
+ *        check to be stacked.
+ */
+static int label_components_match(const struct aa_profile *profile,
+				  struct aa_ruleset *rules,
+				  struct aa_label *label, aa_state_t start,
+				  bool inview, u32 request,
+				  struct aa_perms *perms)
+{
+	struct aa_profile *tp;
+	struct label_it i;
+	struct aa_perms tmp;
+	aa_state_t state = 0;
+
+	/* find first subcomponent to test */
+	label_for_each(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, rules, tp, start);
+		if (!state)
+			goto fail;
+		goto next;
+	}
+
+	/* no subcomponents visible - no change in perms */
+	return state;
+
+next:
+	tmp = *aa_lookup_perms(rules->policy, state);
+	aa_perms_accum(perms, &tmp);
+	label_for_each_cont(i, label, tp) {
+		if (!aa_ns_visible(profile->ns, tp->ns, inview))
+			continue;
+		state = match_component(profile, rules, tp, start);
+		if (!state)
+			goto fail;
+		tmp = *aa_lookup_perms(rules->policy, state);
+		aa_perms_accum(perms, &tmp);
+	}
+
+	if ((perms->allow & request) != request)
+		return DFA_NOMATCH;
+
+	return state;
+
+fail:
+	*perms = nullperms;
+	return DFA_NOMATCH;
+}
+
+/**
+ * aa_label_match - do a multi-component label match
+ * @profile: profile to match against (NOT NULL)
+ * @rules: ruleset to search
+ * @label: label to match (NOT NULL)
+ * @state: state to start in
+ * @inview: whether to match labels in view or only in scope
+ * @request: permission request
+ * @perms: Returns computed perms (NOT NULL)
+ *
+ * Returns: the state the match finished in, may be the none matching state
+ */
+int aa_label_match(const struct aa_profile *profile, struct aa_ruleset *rules,
+		   struct aa_label *label, aa_state_t state, bool inview,
+		   u32 request, struct aa_perms *perms)
+{
+	aa_state_t tmp = label_compound_match(profile, rules, label, state,
+					      inview, request, perms);
+	if ((perms->allow & request) == request)
+		return tmp;
+
+	/* failed compound_match try component matches */
+	*perms = allperms;
+	return label_components_match(profile, rules, label, state, inview,
+				      request, perms);
+}
+
+
+/**
+ * aa_update_label_name - update a label to have a stored name
+ * @ns: ns being viewed from (NOT NULL)
+ * @label: label to update (NOT NULL)
+ * @gfp: type of memory allocation
+ *
+ * Requires: labels_set(label) not locked in caller
+ *
+ * note: only updates the label name if it does not have a name already
+ *       and if it is in the labelset
+ */
+bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp)
+{
+	struct aa_labelset *ls;
+	unsigned long flags;
+	char __counted *name;
+	bool res = false;
+
+	AA_BUG(!ns);
+	AA_BUG(!label);
+
+	if (label->hname || labels_ns(label) != ns)
+		return res;
+
+	if (aa_label_acntsxprint(&name, ns, label, FLAGS_NONE, gfp) < 0)
+		return res;
+
+	ls = labels_set(label);
+	write_lock_irqsave(&ls->lock, flags);
+	if (!label->hname && label->flags & FLAG_IN_TREE) {
+		label->hname = name;
+		res = true;
+	} else
+		aa_put_str(name);
+	write_unlock_irqrestore(&ls->lock, flags);
+
+	return res;
+}
+
+/*
+ * cached label name is present and visible
+ * @label->hname only exists if label is namespace hierarchical
+ */
+static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label,
+				   int flags)
+{
+	if (label->hname && (!ns || labels_ns(label) == ns) &&
+	    !(flags & ~FLAG_SHOW_MODE))
+		return true;
+
+	return false;
+}
+
+/* helper macro for snprint routines */
+#define update_for_len(total, len, size, str)	\
+do {					\
+	size_t ulen = len;		\
+					\
+	AA_BUG(len < 0);		\
+	total += ulen;			\
+	ulen = min(ulen, size);		\
+	size -= ulen;			\
+	str += ulen;			\
+} while (0)
+
+/**
+ * aa_profile_snxprint - print a profile name to a buffer
+ * @str: buffer to write to. (MAY BE NULL if @size == 0)
+ * @size: size of buffer
+ * @view: namespace profile is being viewed from
+ * @profile: profile to view (NOT NULL)
+ * @flags: whether to include the mode string
+ * @prev_ns: last ns printed when used in compound print
+ *
+ * Returns: size of name written or would be written if larger than
+ *          available buffer
+ *
+ * Note: will not print anything if the profile is not visible
+ */
+static int aa_profile_snxprint(char *str, size_t size, struct aa_ns *view,
+			       struct aa_profile *profile, int flags,
+			       struct aa_ns **prev_ns)
+{
+	const char *ns_name = NULL;
+
+	AA_BUG(!str && size != 0);
+	AA_BUG(!profile);
+
+	if (!view)
+		view = profiles_ns(profile);
+
+	if (view != profile->ns &&
+	    (!prev_ns || (*prev_ns != profile->ns))) {
+		if (prev_ns)
+			*prev_ns = profile->ns;
+		ns_name = aa_ns_name(view, profile->ns,
+				     flags & FLAG_VIEW_SUBNS);
+		if (ns_name == aa_hidden_ns_name) {
+			if (flags & FLAG_HIDDEN_UNCONFINED)
+				return snprintf(str, size, "%s", "unconfined");
+			return snprintf(str, size, "%s", ns_name);
+		}
+	}
+
+	if ((flags & FLAG_SHOW_MODE) && profile != profile->ns->unconfined) {
+		const char *modestr = aa_profile_mode_names[profile->mode];
+
+		if (ns_name)
+			return snprintf(str, size, ":%s:%s (%s)", ns_name,
+					profile->base.hname, modestr);
+		return snprintf(str, size, "%s (%s)", profile->base.hname,
+				modestr);
+	}
+
+	if (ns_name)
+		return snprintf(str, size, ":%s:%s", ns_name,
+				profile->base.hname);
+	return snprintf(str, size, "%s", profile->base.hname);
+}
+
+static const char *label_modename(struct aa_ns *ns, struct aa_label *label,
+				  int flags)
+{
+	struct aa_profile *profile;
+	struct label_it i;
+	int mode = -1, count = 0;
+
+	label_for_each(i, label, profile) {
+		if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
+			count++;
+			if (profile == profile->ns->unconfined)
+				/* special case unconfined so stacks with
+				 * unconfined don't report as mixed. ie.
+				 * profile_foo//&:ns1:unconfined (mixed)
+				 */
+				continue;
+			if (mode == -1)
+				mode = profile->mode;
+			else if (mode != profile->mode)
+				return "mixed";
+		}
+	}
+
+	if (count == 0)
+		return "-";
+	if (mode == -1)
+		/* everything was unconfined */
+		mode = APPARMOR_UNCONFINED;
+
+	return aa_profile_mode_names[mode];
+}
+
+/* if any visible label is not unconfined the display_mode returns true */
+static inline bool display_mode(struct aa_ns *ns, struct aa_label *label,
+				int flags)
+{
+	if ((flags & FLAG_SHOW_MODE)) {
+		struct aa_profile *profile;
+		struct label_it i;
+
+		label_for_each(i, label, profile) {
+			if (aa_ns_visible(ns, profile->ns,
+					  flags & FLAG_VIEW_SUBNS) &&
+			    profile != profile->ns->unconfined)
+				return true;
+		}
+		/* only ns->unconfined in set of profiles in ns */
+		return false;
+	}
+
+	return false;
+}
+
+/**
+ * aa_label_snxprint - print a label name to a string buffer
+ * @str: buffer to write to. (MAY BE NULL if @size == 0)
+ * @size: size of buffer
+ * @ns: namespace profile is being viewed from
+ * @label: label to view (NOT NULL)
+ * @flags: whether to include the mode string
+ *
+ * Returns: size of name written or would be written if larger than
+ *          available buffer
+ *
+ * Note: labels do not have to be strictly hierarchical to the ns as
+ *       objects may be shared across different namespaces and thus
+ *       pickup labeling from each ns.  If a particular part of the
+ *       label is not visible it will just be excluded.  And if none
+ *       of the label is visible "---" will be used.
+ */
+int aa_label_snxprint(char *str, size_t size, struct aa_ns *ns,
+		      struct aa_label *label, int flags)
+{
+	struct aa_profile *profile;
+	struct aa_ns *prev_ns = NULL;
+	struct label_it i;
+	int count = 0, total = 0;
+	ssize_t len;
+
+	AA_BUG(!str && size != 0);
+	AA_BUG(!label);
+
+	if (DEBUG_ABS_ROOT && (flags & FLAG_ABS_ROOT)) {
+		ns = root_ns;
+		len = snprintf(str, size, "_");
+		update_for_len(total, len, size, str);
+	} else if (!ns) {
+		ns = labels_ns(label);
+	}
+
+	label_for_each(i, label, profile) {
+		if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
+			if (count > 0) {
+				len = snprintf(str, size, "//&");
+				update_for_len(total, len, size, str);
+			}
+			len = aa_profile_snxprint(str, size, ns, profile,
+						  flags & FLAG_VIEW_SUBNS,
+						  &prev_ns);
+			update_for_len(total, len, size, str);
+			count++;
+		}
+	}
+
+	if (count == 0) {
+		if (flags & FLAG_HIDDEN_UNCONFINED)
+			return snprintf(str, size, "%s", "unconfined");
+		return snprintf(str, size, "%s", aa_hidden_ns_name);
+	}
+
+	/* count == 1 && ... is for backwards compat where the mode
+	 * is not displayed for 'unconfined' in the current ns
+	 */
+	if (display_mode(ns, label, flags)) {
+		len = snprintf(str, size, " (%s)",
+			       label_modename(ns, label, flags));
+		update_for_len(total, len, size, str);
+	}
+
+	return total;
+}
+#undef update_for_len
+
+/**
+ * aa_label_asxprint - allocate a string buffer and print label into it
+ * @strp: Returns - the allocated buffer with the label name. (NOT NULL)
+ * @ns: namespace profile is being viewed from
+ * @label: label to view (NOT NULL)
+ * @flags: flags controlling what label info is printed
+ * @gfp: kernel memory allocation type
+ *
+ * Returns: size of name written or would be written if larger than
+ *          available buffer
+ */
+int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label,
+		      int flags, gfp_t gfp)
+{
+	int size;
+
+	AA_BUG(!strp);
+	AA_BUG(!label);
+
+	size = aa_label_snxprint(NULL, 0, ns, label, flags);
+	if (size < 0)
+		return size;
+
+	*strp = kmalloc(size + 1, gfp);
+	if (!*strp)
+		return -ENOMEM;
+	return aa_label_snxprint(*strp, size + 1, ns, label, flags);
+}
+
+/**
+ * aa_label_acntsxprint - allocate a __counted string buffer and print label
+ * @strp: buffer to write to.
+ * @ns: namespace profile is being viewed from
+ * @label: label to view (NOT NULL)
+ * @flags: flags controlling what label info is printed
+ * @gfp: kernel memory allocation type
+ *
+ * Returns: size of name written or would be written if larger than
+ *          available buffer
+ */
+int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns,
+			 struct aa_label *label, int flags, gfp_t gfp)
+{
+	int size;
+
+	AA_BUG(!strp);
+	AA_BUG(!label);
+
+	size = aa_label_snxprint(NULL, 0, ns, label, flags);
+	if (size < 0)
+		return size;
+
+	*strp = aa_str_alloc(size + 1, gfp);
+	if (!*strp)
+		return -ENOMEM;
+	return aa_label_snxprint(*strp, size + 1, ns, label, flags);
+}
+
+
+void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns,
+		     struct aa_label *label, int flags, gfp_t gfp)
+{
+	const char *str;
+	char *name = NULL;
+	int len;
+
+	AA_BUG(!ab);
+	AA_BUG(!label);
+
+	if (!use_label_hname(ns, label, flags) ||
+	    display_mode(ns, label, flags)) {
+		len  = aa_label_asxprint(&name, ns, label, flags, gfp);
+		if (len < 0) {
+			AA_DEBUG(DEBUG_LABEL, "label print error");
+			return;
+		}
+		str = name;
+	} else {
+		str = (char *) label->hname;
+		len = strlen(str);
+	}
+	audit_log_n_untrustedstring(ab, str, len);
+
+	kfree(name);
+}
+
+void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns,
+			 struct aa_label *label, int flags, gfp_t gfp)
+{
+	AA_BUG(!f);
+	AA_BUG(!label);
+
+	if (!use_label_hname(ns, label, flags)) {
+		char *str;
+		int len;
+
+		len = aa_label_asxprint(&str, ns, label, flags, gfp);
+		if (len < 0) {
+			AA_DEBUG(DEBUG_LABEL, "label print error");
+			return;
+		}
+		seq_puts(f, str);
+		kfree(str);
+	} else if (display_mode(ns, label, flags))
+		seq_printf(f, "%s (%s)", label->hname,
+			   label_modename(ns, label, flags));
+	else
+		seq_puts(f, label->hname);
+}
+
+void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags,
+		      gfp_t gfp)
+{
+	AA_BUG(!label);
+
+	if (!use_label_hname(ns, label, flags)) {
+		char *str;
+		int len;
+
+		len = aa_label_asxprint(&str, ns, label, flags, gfp);
+		if (len < 0) {
+			AA_DEBUG(DEBUG_LABEL, "label print error");
+			return;
+		}
+		pr_info("%s", str);
+		kfree(str);
+	} else if (display_mode(ns, label, flags))
+		pr_info("%s (%s)", label->hname,
+		       label_modename(ns, label, flags));
+	else
+		pr_info("%s", label->hname);
+}
+
+void aa_label_printk(struct aa_label *label, gfp_t gfp)
+{
+	struct aa_ns *ns = aa_get_current_ns();
+
+	aa_label_xprintk(ns, label, FLAG_VIEW_SUBNS, gfp);
+	aa_put_ns(ns);
+}
+
+static int label_count_strn_entries(const char *str, size_t n)
+{
+	const char *end = str + n;
+	const char *split;
+	int count = 1;
+
+	AA_BUG(!str);
+
+	for (split = aa_label_strn_split(str, end - str);
+	     split;
+	     split = aa_label_strn_split(str, end - str)) {
+		count++;
+		str = split + 3;
+	}
+
+	return count;
+}
+
+/*
+ * ensure stacks with components like
+ *   :ns:A//&B
+ * have :ns: applied to both 'A' and 'B' by making the lookup relative
+ * to the base if the lookup specifies an ns, else making the stacked lookup
+ * relative to the last embedded ns in the string.
+ */
+static struct aa_profile *fqlookupn_profile(struct aa_label *base,
+					    struct aa_label *currentbase,
+					    const char *str, size_t n)
+{
+	const char *first = skipn_spaces(str, n);
+
+	if (first && *first == ':')
+		return aa_fqlookupn_profile(base, str, n);
+
+	return aa_fqlookupn_profile(currentbase, str, n);
+}
+
+/**
+ * aa_label_strn_parse - parse, validate and convert a text string to a label
+ * @base: base label to use for lookups (NOT NULL)
+ * @str: null terminated text string (NOT NULL)
+ * @n: length of str to parse, will stop at \0 if encountered before n
+ * @gfp: allocation type
+ * @create: true if should create compound labels if they don't exist
+ * @force_stack: true if should stack even if no leading &
+ *
+ * Returns: the matching refcounted label if present
+ *     else ERRPTR
+ */
+struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str,
+				     size_t n, gfp_t gfp, bool create,
+				     bool force_stack)
+{
+	DEFINE_VEC(profile, vec);
+	struct aa_label *label, *currbase = base;
+	int i, len, stack = 0, error;
+	const char *end = str + n;
+	const char *split;
+
+	AA_BUG(!base);
+	AA_BUG(!str);
+
+	str = skipn_spaces(str, n);
+	if (str == NULL || (DEBUG_ABS_ROOT && *str == '_' &&
+			    base != &root_ns->unconfined->label))
+		return ERR_PTR(-EINVAL);
+
+	len = label_count_strn_entries(str, end - str);
+	if (*str == '&' || force_stack) {
+		/* stack on top of base */
+		stack = base->size;
+		len += stack;
+		if (*str == '&')
+			str++;
+	}
+
+	error = vec_setup(profile, vec, len, gfp);
+	if (error)
+		return ERR_PTR(error);
+
+	for (i = 0; i < stack; i++)
+		vec[i] = aa_get_profile(base->vec[i]);
+
+	for (split = aa_label_strn_split(str, end - str), i = stack;
+	     split && i < len; i++) {
+		vec[i] = fqlookupn_profile(base, currbase, str, split - str);
+		if (!vec[i])
+			goto fail;
+		/*
+		 * if component specified a new ns it becomes the new base
+		 * so that subsequent lookups are relative to it
+		 */
+		if (vec[i]->ns != labels_ns(currbase))
+			currbase = &vec[i]->label;
+		str = split + 3;
+		split = aa_label_strn_split(str, end - str);
+	}
+	/* last element doesn't have a split */
+	if (i < len) {
+		vec[i] = fqlookupn_profile(base, currbase, str, end - str);
+		if (!vec[i])
+			goto fail;
+	}
+	if (len == 1)
+		/* no need to free vec as len < LOCAL_VEC_ENTRIES */
+		return &vec[0]->label;
+
+	len -= aa_vec_unique(vec, len, VEC_FLAG_TERMINATE);
+	/* TODO: deal with reference labels */
+	if (len == 1) {
+		label = aa_get_label(&vec[0]->label);
+		goto out;
+	}
+
+	if (create)
+		label = aa_vec_find_or_create_label(vec, len, gfp);
+	else
+		label = vec_find(vec, len);
+	if (!label)
+		goto fail;
+
+out:
+	/* use adjusted len from after vec_unique, not original */
+	vec_cleanup(profile, vec, len);
+	return label;
+
+fail:
+	label = ERR_PTR(-ENOENT);
+	goto out;
+}
+
+struct aa_label *aa_label_parse(struct aa_label *base, const char *str,
+				gfp_t gfp, bool create, bool force_stack)
+{
+	return aa_label_strn_parse(base, str, strlen(str), gfp, create,
+				   force_stack);
+}
+
+/**
+ * aa_labelset_destroy - remove all labels from the label set
+ * @ls: label set to cleanup (NOT NULL)
+ *
+ * Labels that are removed from the set may still exist beyond the set
+ * being destroyed depending on their reference counting
+ */
+void aa_labelset_destroy(struct aa_labelset *ls)
+{
+	struct rb_node *node;
+	unsigned long flags;
+
+	AA_BUG(!ls);
+
+	write_lock_irqsave(&ls->lock, flags);
+	for (node = rb_first(&ls->root); node; node = rb_first(&ls->root)) {
+		struct aa_label *this = rb_entry(node, struct aa_label, node);
+
+		if (labels_ns(this) != root_ns)
+			__label_remove(this,
+				       ns_unconfined(labels_ns(this)->parent));
+		else
+			__label_remove(this, NULL);
+	}
+	write_unlock_irqrestore(&ls->lock, flags);
+}
+
+/*
+ * @ls: labelset to init (NOT NULL)
+ */
+void aa_labelset_init(struct aa_labelset *ls)
+{
+	AA_BUG(!ls);
+
+	rwlock_init(&ls->lock);
+	ls->root = RB_ROOT;
+}
+
+static struct aa_label *labelset_next_stale(struct aa_labelset *ls)
+{
+	struct aa_label *label;
+	struct rb_node *node;
+	unsigned long flags;
+
+	AA_BUG(!ls);
+
+	read_lock_irqsave(&ls->lock, flags);
+
+	__labelset_for_each(ls, node) {
+		label = rb_entry(node, struct aa_label, node);
+		if ((label_is_stale(label) ||
+		     vec_is_stale(label->vec, label->size)) &&
+		    __aa_get_label(label))
+			goto out;
+
+	}
+	label = NULL;
+
+out:
+	read_unlock_irqrestore(&ls->lock, flags);
+
+	return label;
+}
+
+/**
+ * __label_update - insert updated version of @label into labelset
+ * @label: the label to update/replace
+ *
+ * Returns: new label that is up to date
+ *     else NULL on failure
+ *
+ * Requires: @ns lock be held
+ *
+ * Note: worst case is the stale @label does not get updated and has
+ *       to be updated at a later time.
+ */
+static struct aa_label *__label_update(struct aa_label *label)
+{
+	struct aa_label *new, *tmp;
+	struct aa_labelset *ls;
+	unsigned long flags;
+	int i, invcount = 0;
+
+	AA_BUG(!label);
+	AA_BUG(!mutex_is_locked(&labels_ns(label)->lock));
+
+	new = aa_label_alloc(label->size, label->proxy, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	/*
+	 * while holding the ns_lock will stop profile replacement, removal,
+	 * and label updates, label merging and removal can be occurring
+	 */
+	ls = labels_set(label);
+	write_lock_irqsave(&ls->lock, flags);
+	for (i = 0; i < label->size; i++) {
+		AA_BUG(!label->vec[i]);
+		new->vec[i] = aa_get_newest_profile(label->vec[i]);
+		AA_BUG(!new->vec[i]);
+		AA_BUG(!new->vec[i]->label.proxy);
+		AA_BUG(!new->vec[i]->label.proxy->label);
+		if (new->vec[i]->label.proxy != label->vec[i]->label.proxy)
+			invcount++;
+	}
+
+	/* updated stale label by being removed/renamed from labelset */
+	if (invcount) {
+		new->size -= aa_vec_unique(&new->vec[0], new->size,
+					   VEC_FLAG_TERMINATE);
+		/* TODO: deal with reference labels */
+		if (new->size == 1) {
+			tmp = aa_get_label(&new->vec[0]->label);
+			AA_BUG(tmp == label);
+			goto remove;
+		}
+		if (labels_set(label) != labels_set(new)) {
+			write_unlock_irqrestore(&ls->lock, flags);
+			tmp = aa_label_insert(labels_set(new), new);
+			write_lock_irqsave(&ls->lock, flags);
+			goto remove;
+		}
+	} else
+		AA_BUG(labels_ns(label) != labels_ns(new));
+
+	tmp = __label_insert(labels_set(label), new, true);
+remove:
+	/* ensure label is removed, and redirected correctly */
+	__label_remove(label, tmp);
+	write_unlock_irqrestore(&ls->lock, flags);
+	label_free_or_put_new(tmp, new);
+
+	return tmp;
+}
+
+/**
+ * __labelset_update - update labels in @ns
+ * @ns: namespace to update labels in  (NOT NULL)
+ *
+ * Requires: @ns lock be held
+ *
+ * Walk the labelset ensuring that all labels are up to date and valid
+ * Any label that has a stale component is marked stale and replaced and
+ * by an updated version.
+ *
+ * If failures happen due to memory pressures then stale labels will
+ * be left in place until the next pass.
+ */
+static void __labelset_update(struct aa_ns *ns)
+{
+	struct aa_label *label;
+
+	AA_BUG(!ns);
+	AA_BUG(!mutex_is_locked(&ns->lock));
+
+	do {
+		label = labelset_next_stale(&ns->labels);
+		if (label) {
+			struct aa_label *l = __label_update(label);
+
+			aa_put_label(l);
+			aa_put_label(label);
+		}
+	} while (label);
+}
+
+/**
+ * __aa_labelset_update_subtree - update all labels with a stale component
+ * @ns: ns to start update at (NOT NULL)
+ *
+ * Requires: @ns lock be held
+ *
+ * Invalidates labels based on @p in @ns and any children namespaces.
+ */
+void __aa_labelset_update_subtree(struct aa_ns *ns)
+{
+	struct aa_ns *child;
+
+	AA_BUG(!ns);
+	AA_BUG(!mutex_is_locked(&ns->lock));
+
+	__labelset_update(ns);
+
+	list_for_each_entry(child, &ns->sub_ns, base.list) {
+		mutex_lock_nested(&child->lock, child->level);
+		__aa_labelset_update_subtree(child);
+		mutex_unlock(&child->lock);
+	}
+}
diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c
new file mode 100644
index 000000000..73b88bde4
--- /dev/null
+++ b/security/apparmor/lib.c
@@ -0,0 +1,514 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains basic common functions used in AppArmor
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/ctype.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include "include/audit.h"
+#include "include/apparmor.h"
+#include "include/lib.h"
+#include "include/perms.h"
+#include "include/policy.h"
+
+const struct aa_perms nullperms;
+const struct aa_perms allperms = { .allow = ALL_PERMS_MASK,
+			     .quiet = ALL_PERMS_MASK,
+			     .hide = ALL_PERMS_MASK };
+
+struct val_table_ent {
+	const char *str;
+	int value;
+};
+
+static const struct val_table_ent debug_values_table[] = {
+	{ "N", DEBUG_NONE },
+	{ "none", DEBUG_NONE },
+	{ "n", DEBUG_NONE },
+	{ "0", DEBUG_NONE },
+	{ "all", DEBUG_ALL },
+	{ "Y", DEBUG_ALL },
+	{ "y", DEBUG_ALL },
+	{ "1", DEBUG_ALL },
+	{ "abs_root", DEBUG_LABEL_ABS_ROOT },
+	{ "label", DEBUG_LABEL },
+	{ "domain", DEBUG_DOMAIN },
+	{ "policy", DEBUG_POLICY },
+	{ "interface", DEBUG_INTERFACE },
+	{ "unpack", DEBUG_UNPACK },
+	{ "tags", DEBUG_TAGS },
+	{ NULL, 0 }
+};
+
+static const struct val_table_ent *
+val_table_find_ent(const struct val_table_ent *table,
+		   const char *name, size_t len)
+{
+	const struct val_table_ent *entry;
+
+	for (entry = table; entry->str != NULL; entry++) {
+		if (strncmp(entry->str, name, len) == 0 &&
+		    strlen(entry->str) == len)
+			return entry;
+	}
+	return NULL;
+}
+
+int aa_parse_debug_params(const char *str)
+{
+	const struct val_table_ent *ent;
+	const char *next;
+	int val = 0;
+
+	do {
+		size_t n = strcspn(str, "\r\n,");
+
+		next = str + n;
+		ent = val_table_find_ent(debug_values_table, str, next - str);
+		if (ent)
+			val |= ent->value;
+		else
+			AA_DEBUG(DEBUG_INTERFACE, "unknown debug type '%.*s'",
+				 (int)(next - str), str);
+		str = next + 1;
+	} while (*next != 0);
+	return val;
+}
+
+/**
+ * val_mask_to_str - convert a perm mask to its short string
+ * @str: character buffer to store string in (at least 10 characters)
+ * @size: size of the @str buffer
+ * @table: NUL-terminated character buffer of permission characters (NOT NULL)
+ * @mask: permission mask to convert
+ */
+static int val_mask_to_str(char *str, size_t size,
+			   const struct val_table_ent *table, u32 mask)
+{
+	const struct val_table_ent *ent;
+	int total = 0;
+
+	for (ent = table; ent->str; ent++) {
+		if (ent->value && (ent->value & mask) == ent->value) {
+			int len = scnprintf(str, size, "%s%s", total ? "," : "",
+					    ent->str);
+			size -= len;
+			str += len;
+			total += len;
+			mask &= ~ent->value;
+		}
+	}
+
+	return total;
+}
+
+int aa_print_debug_params(char *buffer)
+{
+	if (!aa_g_debug)
+		return sprintf(buffer, "N");
+	return val_mask_to_str(buffer, PAGE_SIZE, debug_values_table,
+			       aa_g_debug);
+}
+
+bool aa_resize_str_table(struct aa_str_table *t, int newsize, gfp_t gfp)
+{
+	struct aa_str_table_ent *n;
+	int i;
+
+	if (t->size == newsize)
+		return true;
+	n = kzalloc_objs(*n, newsize, gfp);
+	if (!n)
+		return false;
+	for (i = 0; i < min(t->size, newsize); i++)
+		n[i] = t->table[i];
+	for (; i < t->size; i++)
+		kfree_sensitive(t->table[i].strs);
+	if (newsize > t->size)
+		memset(&n[t->size], 0, (newsize-t->size)*sizeof(*n));
+	kfree_sensitive(t->table);
+	t->table = n;
+	t->size = newsize;
+
+	return true;
+}
+
+/**
+ * aa_destroy_str_table - free entries str table
+ * @t: the string table to free  (MAYBE NULL)
+ */
+void aa_destroy_str_table(struct aa_str_table *t)
+{
+	int i;
+
+	if (t) {
+		if (!t->table)
+			return;
+
+		for (i = 0; i < t->size; i++)
+			kfree_sensitive(t->table[i].strs);
+		kfree_sensitive(t->table);
+		t->table = NULL;
+		t->size = 0;
+	}
+}
+
+/**
+ * skipn_spaces - Removes leading whitespace from @str.
+ * @str: The string to be stripped.
+ * @n: length of str to parse, will stop at \0 if encountered before n
+ *
+ * Returns a pointer to the first non-whitespace character in @str.
+ * if all whitespace will return NULL
+ */
+
+const char *skipn_spaces(const char *str, size_t n)
+{
+	for (; n && isspace(*str); --n)
+		++str;
+	if (n)
+		return (char *)str;
+	return NULL;
+}
+
+const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name,
+			     size_t *ns_len)
+{
+	const char *end = fqname + n;
+	const char *name = skipn_spaces(fqname, n);
+
+	*ns_name = NULL;
+	*ns_len = 0;
+
+	if (!name)
+		return NULL;
+
+	if (name[0] == ':') {
+		char *split = strnchr(&name[1], end - &name[1], ':');
+		*ns_name = skipn_spaces(&name[1], end - &name[1]);
+		if (!*ns_name)
+			return NULL;
+		if (split) {
+			*ns_len = split - *ns_name;
+			if (*ns_len == 0)
+				*ns_name = NULL;
+			split++;
+			if (end - split > 1 && strncmp(split, "//", 2) == 0)
+				split += 2;
+			name = skipn_spaces(split, end - split);
+		} else {
+			/* a ns name without a following profile is allowed */
+			name = NULL;
+			*ns_len = end - *ns_name;
+		}
+	}
+	if (name && *name == 0)
+		name = NULL;
+
+	return name;
+}
+
+/**
+ * aa_info_message - log a none profile related status message
+ * @str: message to log
+ */
+void aa_info_message(const char *str)
+{
+	if (audit_enabled) {
+		DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL);
+
+		ad.info = str;
+		aa_audit_msg(AUDIT_APPARMOR_STATUS, &ad, NULL);
+	}
+	printk(KERN_INFO "AppArmor: %s\n", str);
+}
+
+__counted char *aa_str_alloc(int size, gfp_t gfp)
+{
+	struct counted_str *str;
+
+	str = kmalloc_flex(*str, name, size, gfp);
+	if (!str)
+		return NULL;
+
+	kref_init(&str->count);
+	return str->name;
+}
+
+void aa_str_kref(struct kref *kref)
+{
+	kfree(container_of(kref, struct counted_str, count));
+}
+
+
+const char aa_file_perm_chrs[] = "xwracd         km l     ";
+const char *aa_file_perm_names[] = {
+	"exec",
+	"write",
+	"read",
+	"append",
+
+	"create",
+	"delete",
+	"open",
+	"rename",
+
+	"setattr",
+	"getattr",
+	"setcred",
+	"getcred",
+
+	"chmod",
+	"chown",
+	"chgrp",
+	"lock",
+
+	"mmap",
+	"mprot",
+	"link",
+	"snapshot",
+
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+
+	"stack",
+	"change_onexec",
+	"change_profile",
+	"change_hat",
+};
+
+/**
+ * aa_perm_mask_to_str - convert a perm mask to its short string
+ * @str: character buffer to store string in (at least 10 characters)
+ * @str_size: size of the @str buffer
+ * @chrs: NUL-terminated character buffer of permission characters
+ * @mask: permission mask to convert
+ */
+void aa_perm_mask_to_str(char *str, size_t str_size, const char *chrs, u32 mask)
+{
+	unsigned int i, perm = 1;
+	size_t num_chrs = strlen(chrs);
+
+	for (i = 0; i < num_chrs; perm <<= 1, i++) {
+		if (mask & perm) {
+			/* Ensure that one byte is left for NUL-termination */
+			if (WARN_ON_ONCE(str_size <= 1))
+				break;
+
+			*str++ = chrs[i];
+			str_size--;
+		}
+	}
+	*str = '\0';
+}
+
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+			 u32 mask)
+{
+	const char *fmt = "%s";
+	unsigned int i, perm = 1;
+	bool prev = false;
+
+	for (i = 0; i < 32; perm <<= 1, i++) {
+		if (mask & perm) {
+			audit_log_format(ab, fmt, names[i]);
+			if (!prev) {
+				prev = true;
+				fmt = " %s";
+			}
+		}
+	}
+}
+
+void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
+			u32 chrsmask, const char * const *names, u32 namesmask)
+{
+	char str[33];
+
+	audit_log_format(ab, "\"");
+	if ((mask & chrsmask) && chrs) {
+		aa_perm_mask_to_str(str, sizeof(str), chrs, mask & chrsmask);
+		mask &= ~chrsmask;
+		audit_log_format(ab, "%s", str);
+		if (mask & namesmask)
+			audit_log_format(ab, " ");
+	}
+	if ((mask & namesmask) && names)
+		aa_audit_perm_names(ab, names, mask & namesmask);
+	audit_log_format(ab, "\"");
+}
+
+/**
+ * aa_apply_modes_to_perms - apply namespace and profile flags to perms
+ * @profile: that perms where computed from
+ * @perms: perms to apply mode modifiers to
+ *
+ * TODO: split into profile and ns based flags for when accumulating perms
+ */
+void aa_apply_modes_to_perms(const struct aa_profile *profile,
+			     struct aa_perms *perms)
+{
+	if (KILL_MODE(profile))
+		perms->kill = ~perms->allow;
+	else if (COMPLAIN_MODE(profile))
+		perms->complain |= ~(perms->allow | perms->deny);
+	else if (USER_MODE(profile))
+		perms->prompt |= ~(perms->allow | perms->deny);
+
+	switch (AUDIT_MODE(profile)) {
+	case AUDIT_ALL:
+		perms->audit = ALL_PERMS_MASK;
+		fallthrough;
+	case AUDIT_NOQUIET:
+		perms->quiet = 0;
+		break;
+	case AUDIT_QUIET:
+		perms->audit = 0;
+		fallthrough;
+	case AUDIT_QUIET_DENIED:
+		perms->quiet |= ~perms->allow;
+		break;
+	case AUDIT_QUIET_ALLOWED:
+		perms->quiet |= perms->complain | perms->allow;
+		break;
+	}
+}
+
+void aa_profile_match_label(const struct aa_profile *profile,
+			    struct aa_ruleset *rules,
+			    struct aa_label *label,
+			    int type, u32 request, struct aa_perms *perms)
+{
+	/* TODO: doesn't yet handle extended types */
+	aa_state_t state;
+
+	state = aa_dfa_next(rules->policy->dfa,
+			    rules->policy->start[AA_CLASS_LABEL],
+			    type);
+	aa_label_match(profile, rules, label, state, false, request, perms);
+}
+
+
+/**
+ * aa_check_perms - do audit mode selection based on perms set
+ * @profile: profile being checked
+ * @perms: perms computed for the request
+ * @request: requested perms
+ * @ad: initialized audit structure (MAY BE NULL if not auditing)
+ * @cb: callback fn for type specific fields (MAY BE NULL)
+ *
+ * Returns: 0 if permission else error code
+ *
+ * Note: profile audit modes need to be set before calling by setting the
+ *       perm masks appropriately.
+ *
+ *       If not auditing then complain mode is not enabled and the
+ *       error code will indicate whether there was an explicit deny
+ *	 with a positive value.
+ */
+int aa_check_perms(struct aa_profile *profile, const struct aa_perms *perms,
+		   u32 request, struct apparmor_audit_data *ad,
+		   void (*cb)(struct audit_buffer *, void *))
+{
+	int error;
+	u32 denied = request & (~perms->allow | perms->deny);
+
+	if (likely(!denied)) {
+		/* mask off perms that are not being force audited */
+		request &= perms->audit;
+		if (!request || !ad)
+			return 0;
+
+		error = 0;
+	} else {
+		error = -EACCES;
+
+		if (denied == (denied & perms->hide))
+			error = -ENOENT;
+
+		denied &= ~perms->quiet;
+		if (!ad || !denied)
+			return error;
+	}
+
+	int type = aa_select_audit_type(denied, perms);
+
+	if (ad) {
+		ad->subj_label = &profile->label;
+		ad->request = request;
+		ad->denied = denied;
+		ad->error = error;
+		aa_audit_msg(type, ad, cb);
+	}
+
+	if (type == AUDIT_APPARMOR_ALLOWED)
+		error = 0;
+
+	return error;
+}
+
+
+/**
+ * aa_policy_init - initialize a policy structure
+ * @policy: policy to initialize  (NOT NULL)
+ * @prefix: prefix name if any is required.  (MAYBE NULL)
+ * @name: name of the policy, init will make a copy of it  (NOT NULL)
+ * @gfp: allocation mode
+ *
+ * Note: this fn creates a copy of strings passed in
+ *
+ * Returns: true if policy init successful
+ */
+bool aa_policy_init(struct aa_policy *policy, const char *prefix,
+		    const char *name, gfp_t gfp)
+{
+	char *hname;
+	size_t hname_sz;
+
+	INIT_LIST_HEAD(&policy->list);
+	INIT_LIST_HEAD(&policy->profiles);
+	hname_sz = (prefix ? strlen(prefix) + 2 : 0) + strlen(name) + 1;
+	/* freed by policy_free */
+	hname = aa_str_alloc(hname_sz, gfp);
+	if (!hname)
+		return false;
+	if (prefix)
+		scnprintf(hname, hname_sz, "%s//%s", prefix, name);
+	else
+		strscpy(hname, name, hname_sz);
+	policy->hname = hname;
+	/* base.name is a substring of fqname */
+	policy->name = basename(policy->hname);
+
+	return true;
+}
+
+/**
+ * aa_policy_destroy - free the elements referenced by @policy
+ * @policy: policy that is to have its elements freed  (NOT NULL)
+ */
+void aa_policy_destroy(struct aa_policy *policy)
+{
+	AA_BUG(on_list_rcu(&policy->profiles));
+	AA_BUG(on_list_rcu(&policy->list));
+
+	/* don't free name as its a subset of hname */
+	aa_put_str(policy->hname);
+}
+
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
new file mode 100644
index 000000000..d502ad0ac
--- /dev/null
+++ b/security/apparmor/lsm.c
@@ -0,0 +1,2642 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor LSM hooks.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/lsm_hooks.h>
+#include <linux/moduleparam.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/ptrace.h>
+#include <linux/ctype.h>
+#include <linux/sysctl.h>
+#include <linux/sysfs.h>
+#include <linux/audit.h>
+#include <linux/user_namespace.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/zstd.h>
+#include <net/sock.h>
+#include <uapi/linux/mount.h>
+#include <uapi/linux/lsm.h>
+
+#include "include/af_unix.h"
+#include "include/af_inet.h"
+#include "include/apparmor.h"
+#include "include/apparmorfs.h"
+#include "include/audit.h"
+#include "include/capability.h"
+#include "include/cred.h"
+#include "include/crypto.h"
+#include "include/file.h"
+#include "include/ipc.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/label.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+#include "include/procattr.h"
+#include "include/mount.h"
+#include "include/secid.h"
+
+/* Flag indicating whether initialization completed */
+int apparmor_initialized;
+
+union aa_buffer {
+	struct list_head list;
+	DECLARE_FLEX_ARRAY(char, buffer);
+};
+
+struct aa_local_cache {
+	unsigned int hold;
+	unsigned int count;
+	struct list_head head;
+};
+
+#define RESERVE_COUNT 2
+static int reserve_count = RESERVE_COUNT;
+static int buffer_count;
+
+static LIST_HEAD(aa_global_buffers);
+static DEFINE_SPINLOCK(aa_buffers_lock);
+static DEFINE_PER_CPU(struct aa_local_cache, aa_local_buffers);
+
+/*
+ * LSM hook functions
+ */
+
+/*
+ * put the associated labels
+ */
+static void apparmor_cred_free(struct cred *cred)
+{
+	aa_put_label(cred_label(cred));
+	set_cred_label(cred, NULL);
+}
+
+/*
+ * allocate the apparmor part of blank credentials
+ */
+static int apparmor_cred_alloc_blank(struct cred *cred, gfp_t gfp)
+{
+	set_cred_label(cred, NULL);
+	return 0;
+}
+
+/*
+ * prepare new cred label for modification by prepare_cred block
+ */
+static int apparmor_cred_prepare(struct cred *new, const struct cred *old,
+				 gfp_t gfp)
+{
+	set_cred_label(new, aa_get_newest_label(cred_label(old)));
+	return 0;
+}
+
+/*
+ * transfer the apparmor data to a blank set of creds
+ */
+static void apparmor_cred_transfer(struct cred *new, const struct cred *old)
+{
+	set_cred_label(new, aa_get_newest_label(cred_label(old)));
+}
+
+static void apparmor_task_free(struct task_struct *task)
+{
+
+	aa_free_task_ctx(task_ctx(task));
+}
+
+static int apparmor_task_alloc(struct task_struct *task,
+			       u64 clone_flags)
+{
+	struct aa_task_ctx *new = task_ctx(task);
+
+	aa_dup_task_ctx(new, task_ctx(current));
+
+	return 0;
+}
+
+static int apparmor_ptrace_access_check(struct task_struct *child,
+					unsigned int mode)
+{
+	struct aa_label *tracer, *tracee;
+	const struct cred *cred;
+	int error;
+	bool needput;
+
+	cred = get_task_cred(child);
+	tracee = cred_label(cred);	/* ref count on cred */
+	tracer = __begin_current_label_crit_section(&needput);
+	error = aa_may_ptrace(current_cred(), tracer, cred, tracee,
+			(mode & PTRACE_MODE_READ) ? AA_PTRACE_READ
+						  : AA_PTRACE_TRACE);
+	__end_current_label_crit_section(tracer, needput);
+	put_cred(cred);
+
+	return error;
+}
+
+static int apparmor_ptrace_traceme(struct task_struct *parent)
+{
+	struct aa_label *tracer, *tracee;
+	const struct cred *cred;
+	int error;
+	bool needput;
+
+	tracee = __begin_current_label_crit_section(&needput);
+	cred = get_task_cred(parent);
+	tracer = cred_label(cred);	/* ref count on cred */
+	error = aa_may_ptrace(cred, tracer, current_cred(), tracee,
+			      AA_PTRACE_TRACE);
+	put_cred(cred);
+	__end_current_label_crit_section(tracee, needput);
+
+	return error;
+}
+
+/* Derived from security/commoncap.c:cap_capget */
+static int apparmor_capget(const struct task_struct *target, kernel_cap_t *effective,
+			   kernel_cap_t *inheritable, kernel_cap_t *permitted)
+{
+	struct aa_label *label;
+	const struct cred *cred;
+
+	rcu_read_lock();
+	cred = __task_cred(target);
+	label = aa_get_newest_cred_label(cred);
+
+	/*
+	 * cap_capget is stacked ahead of this and will
+	 * initialize effective and permitted.
+	 */
+	if (!unconfined(label)) {
+		struct aa_profile *profile;
+		struct label_it i;
+
+		label_for_each_confined(i, label, profile) {
+			kernel_cap_t allowed;
+
+			allowed = aa_profile_capget(profile);
+			*effective = cap_intersect(*effective, allowed);
+			*permitted = cap_intersect(*permitted, allowed);
+		}
+	}
+	rcu_read_unlock();
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int apparmor_capable(const struct cred *cred, struct user_namespace *ns,
+			    int cap, unsigned int opts)
+{
+	struct aa_label *label;
+	int error = 0;
+
+	label = aa_get_newest_cred_label(cred);
+	if (!unconfined(label))
+		error = aa_capable(cred, label, cap, opts);
+	aa_put_label(label);
+
+	return error;
+}
+
+/**
+ * common_perm - basic common permission check wrapper fn for paths
+ * @op: operation being checked
+ * @path: path to check permission of  (NOT NULL)
+ * @mask: requested permissions mask
+ * @cond: conditional info for the permission request  (NOT NULL)
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm(const char *op, const struct path *path, u32 mask,
+		       struct path_cond *cond)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	if (!unconfined(label))
+		error = aa_path_perm(op, current_cred(), label, path, 0, mask,
+				     cond);
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+/**
+ * common_perm_cond - common permission wrapper around inode cond
+ * @op: operation being checked
+ * @path: location to check (NOT NULL)
+ * @mask: requested permissions mask
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_cond(const char *op, const struct path *path, u32 mask)
+{
+	vfsuid_t vfsuid = i_uid_into_vfsuid(mnt_idmap(path->mnt),
+					    d_backing_inode(path->dentry));
+	struct path_cond cond = {
+		vfsuid_into_kuid(vfsuid),
+		d_backing_inode(path->dentry)->i_mode
+	};
+
+	if (!path_mediated_fs(path->dentry))
+		return 0;
+
+	return common_perm(op, path, mask, &cond);
+}
+
+/**
+ * common_perm_dir_dentry - common permission wrapper when path is dir, dentry
+ * @op: operation being checked
+ * @dir: directory of the dentry  (NOT NULL)
+ * @dentry: dentry to check  (NOT NULL)
+ * @mask: requested permissions mask
+ * @cond: conditional info for the permission request  (NOT NULL)
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_dir_dentry(const char *op, const struct path *dir,
+				  struct dentry *dentry, u32 mask,
+				  struct path_cond *cond)
+{
+	struct path path = { .mnt = dir->mnt, .dentry = dentry };
+
+	return common_perm(op, &path, mask, cond);
+}
+
+/**
+ * common_perm_rm - common permission wrapper for operations doing rm
+ * @op: operation being checked
+ * @dir: directory that the dentry is in  (NOT NULL)
+ * @dentry: dentry being rm'd  (NOT NULL)
+ * @mask: requested permission mask
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_rm(const char *op, const struct path *dir,
+			  struct dentry *dentry, u32 mask)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct path_cond cond = { };
+	vfsuid_t vfsuid;
+
+	if (!inode || !path_mediated_fs(dentry))
+		return 0;
+
+	vfsuid = i_uid_into_vfsuid(mnt_idmap(dir->mnt), inode);
+	cond.uid = vfsuid_into_kuid(vfsuid);
+	cond.mode = inode->i_mode;
+
+	return common_perm_dir_dentry(op, dir, dentry, mask, &cond);
+}
+
+/**
+ * common_perm_create - common permission wrapper for operations doing create
+ * @op: operation being checked
+ * @dir: directory that dentry will be created in  (NOT NULL)
+ * @dentry: dentry to create   (NOT NULL)
+ * @mask: request permission mask
+ * @mode: created file mode
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_create(const char *op, const struct path *dir,
+			      struct dentry *dentry, u32 mask, umode_t mode)
+{
+	struct path_cond cond = { current_fsuid(), mode };
+
+	if (!path_mediated_fs(dir->dentry))
+		return 0;
+
+	return common_perm_dir_dentry(op, dir, dentry, mask, &cond);
+}
+
+static int apparmor_path_unlink(const struct path *dir, struct dentry *dentry)
+{
+	return common_perm_rm(OP_UNLINK, dir, dentry, AA_MAY_DELETE);
+}
+
+static int apparmor_path_mkdir(const struct path *dir, struct dentry *dentry,
+			       umode_t mode)
+{
+	return common_perm_create(OP_MKDIR, dir, dentry, AA_MAY_CREATE,
+				  S_IFDIR);
+}
+
+static int apparmor_path_rmdir(const struct path *dir, struct dentry *dentry)
+{
+	return common_perm_rm(OP_RMDIR, dir, dentry, AA_MAY_DELETE);
+}
+
+static int apparmor_path_mknod(const struct path *dir, struct dentry *dentry,
+			       umode_t mode, unsigned int dev)
+{
+	return common_perm_create(OP_MKNOD, dir, dentry, AA_MAY_CREATE, mode);
+}
+
+static int apparmor_path_truncate(const struct path *path)
+{
+	return common_perm_cond(OP_TRUNC, path, MAY_WRITE | AA_MAY_SETATTR);
+}
+
+static int apparmor_file_truncate(struct file *file)
+{
+	return apparmor_path_truncate(&file->f_path);
+}
+
+static int apparmor_path_symlink(const struct path *dir, struct dentry *dentry,
+				 const char *old_name)
+{
+	return common_perm_create(OP_SYMLINK, dir, dentry, AA_MAY_CREATE,
+				  S_IFLNK);
+}
+
+static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_dir,
+			      struct dentry *new_dentry)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	if (!path_mediated_fs(old_dentry))
+		return 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label))
+		error = aa_path_link(current_cred(), label, old_dentry, new_dir,
+				     new_dentry);
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_dentry,
+				const struct path *new_dir, struct dentry *new_dentry,
+				const unsigned int flags)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	if (!path_mediated_fs(old_dentry))
+		return 0;
+	if ((flags & RENAME_EXCHANGE) && !path_mediated_fs(new_dentry))
+		return 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		struct mnt_idmap *idmap = mnt_idmap(old_dir->mnt);
+		vfsuid_t vfsuid;
+		struct path old_path = { .mnt = old_dir->mnt,
+					 .dentry = old_dentry };
+		struct path new_path = { .mnt = new_dir->mnt,
+					 .dentry = new_dentry };
+		struct path_cond cond = {
+			.mode = d_backing_inode(old_dentry)->i_mode
+		};
+		vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry));
+		cond.uid = vfsuid_into_kuid(vfsuid);
+
+		if (flags & RENAME_EXCHANGE) {
+			struct path_cond cond_exchange = {
+				.mode = d_backing_inode(new_dentry)->i_mode,
+			};
+			vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(new_dentry));
+			cond_exchange.uid = vfsuid_into_kuid(vfsuid);
+
+			error = aa_path_perm(OP_RENAME_SRC, current_cred(),
+					     label, &new_path, 0,
+					     MAY_READ | AA_MAY_GETATTR | MAY_WRITE |
+					     AA_MAY_SETATTR | AA_MAY_DELETE,
+					     &cond_exchange);
+			if (!error)
+				error = aa_path_perm(OP_RENAME_DEST, current_cred(),
+						     label, &old_path,
+						     0, MAY_WRITE | AA_MAY_SETATTR |
+						     AA_MAY_CREATE, &cond_exchange);
+		}
+
+		if (!error)
+			error = aa_path_perm(OP_RENAME_SRC, current_cred(),
+					     label, &old_path, 0,
+					     MAY_READ | AA_MAY_GETATTR | MAY_WRITE |
+					     AA_MAY_SETATTR | AA_MAY_DELETE,
+					     &cond);
+		if (!error)
+			error = aa_path_perm(OP_RENAME_DEST, current_cred(),
+					     label, &new_path,
+					     0, MAY_WRITE | AA_MAY_SETATTR |
+					     AA_MAY_CREATE, &cond);
+
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_path_chmod(const struct path *path, umode_t mode)
+{
+	return common_perm_cond(OP_CHMOD, path, AA_MAY_CHMOD);
+}
+
+static int apparmor_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
+{
+	return common_perm_cond(OP_CHOWN, path, AA_MAY_CHOWN);
+}
+
+static int apparmor_inode_getattr(const struct path *path)
+{
+	return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR);
+}
+
+static int apparmor_file_open(struct file *file)
+{
+	struct aa_file_ctx *fctx = file_ctx(file);
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	if (!path_mediated_fs(file->f_path.dentry))
+		return 0;
+
+	/* If in exec, permission is handled by bprm hooks.
+	 * Cache permissions granted by the previous exec check, with
+	 * implicit read and executable mmap which are required to
+	 * actually execute the image.
+	 *
+	 * Illogically, FMODE_EXEC is in f_flags, not f_mode.
+	 */
+	if (file->f_flags & __FMODE_EXEC) {
+		fctx->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
+		return 0;
+	}
+
+	label = aa_get_newest_cred_label_condref(file->f_cred, &needput);
+	if (!unconfined(label)) {
+		struct mnt_idmap *idmap = file_mnt_idmap(file);
+		struct inode *inode = file_inode(file);
+		vfsuid_t vfsuid;
+		struct path_cond cond = {
+			.mode = inode->i_mode,
+		};
+		vfsuid = i_uid_into_vfsuid(idmap, inode);
+		cond.uid = vfsuid_into_kuid(vfsuid);
+
+		error = aa_path_perm(OP_OPEN, file->f_cred,
+				     label, &file->f_path, 0,
+				     aa_map_file_to_perms(file), &cond);
+		/* todo cache full allowed permissions set and state */
+		fctx->allow = aa_map_file_to_perms(file);
+	}
+	aa_put_label_condref(label, needput);
+
+	return error;
+}
+
+static int apparmor_file_alloc_security(struct file *file)
+{
+	struct aa_file_ctx *ctx = file_ctx(file);
+	bool needput;
+	struct aa_label *label = begin_current_label_crit_section(&needput);
+
+	spin_lock_init(&ctx->lock);
+	rcu_assign_pointer(ctx->label, aa_get_label(label));
+	end_current_label_crit_section(label, needput);
+	return 0;
+}
+
+static void apparmor_file_free_security(struct file *file)
+{
+	struct aa_file_ctx *ctx = file_ctx(file);
+
+	if (ctx)
+		aa_put_label(rcu_access_pointer(ctx->label));
+}
+
+static int common_file_perm(const char *op, struct file *file, u32 mask)
+{
+	struct aa_label *label;
+	bool needput;
+	int error = 0;
+
+	label = begin_current_label_crit_section(&needput);
+	error = aa_file_perm(op, current_cred(), label, file, mask, false);
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_file_receive(struct file *file)
+{
+	return common_file_perm(OP_FRECEIVE, file, aa_map_file_to_perms(file));
+}
+
+static int apparmor_file_permission(struct file *file, int mask)
+{
+	return common_file_perm(OP_FPERM, file, mask);
+}
+
+static int apparmor_file_lock(struct file *file, unsigned int cmd)
+{
+	u32 mask = AA_MAY_LOCK;
+
+	if (cmd == F_WRLCK)
+		mask |= MAY_WRITE;
+
+	return common_file_perm(OP_FLOCK, file, mask);
+}
+
+static int common_mmap(const char *op, struct file *file, unsigned long prot,
+		       unsigned long flags)
+{
+	int mask = 0;
+
+	if (!file || !file_ctx(file))
+		return 0;
+
+	if (prot & PROT_READ)
+		mask |= MAY_READ;
+	/*
+	 * Private mappings don't require write perms since they don't
+	 * write back to the files
+	 */
+	if ((prot & PROT_WRITE) && !(flags & MAP_PRIVATE))
+		mask |= MAY_WRITE;
+	if (prot & PROT_EXEC)
+		mask |= AA_EXEC_MMAP;
+
+	return common_file_perm(op, file, mask);
+}
+
+static int apparmor_mmap_file(struct file *file, unsigned long reqprot,
+			      unsigned long prot, unsigned long flags)
+{
+	return common_mmap(OP_FMMAP, file, prot, flags);
+}
+
+static int apparmor_file_mprotect(struct vm_area_struct *vma,
+				  unsigned long reqprot, unsigned long prot)
+{
+	return common_mmap(OP_FMPROT, vma->vm_file, prot,
+			   !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0);
+}
+
+#ifdef CONFIG_IO_URING
+static const char *audit_uring_mask(u32 mask)
+{
+	if (mask & AA_MAY_CREATE_SQPOLL)
+		return "sqpoll";
+	if (mask & AA_MAY_OVERRIDE_CRED)
+		return "override_creds";
+	return "";
+}
+
+static void audit_uring_cb(struct audit_buffer *ab, void *va)
+{
+	struct apparmor_audit_data *ad = aad_of_va(va);
+
+	if (ad->request & AA_URING_PERM_MASK) {
+		audit_log_format(ab, " requested=\"%s\"",
+				 audit_uring_mask(ad->request));
+		if (ad->denied & AA_URING_PERM_MASK) {
+			audit_log_format(ab, " denied=\"%s\"",
+					 audit_uring_mask(ad->denied));
+		}
+	}
+	if (ad->uring.target) {
+		audit_log_format(ab, " tcontext=");
+		aa_label_xaudit(ab, labels_ns(ad->subj_label),
+				ad->uring.target,
+				FLAGS_NONE, GFP_ATOMIC);
+	}
+}
+
+static int profile_uring(struct aa_profile *profile, u32 request,
+			 struct aa_label *new, int cap,
+			 struct apparmor_audit_data *ad)
+{
+	unsigned int state;
+	struct aa_ruleset *rules;
+	int error = 0;
+
+	AA_BUG(!profile);
+
+	rules = profile->label.rules[0];
+	state = RULE_MEDIATES(rules, AA_CLASS_IO_URING);
+	if (state) {
+		struct aa_perms perms = { };
+
+		if (new) {
+			aa_label_match(profile, rules, new, state,
+				       false, request, &perms);
+		} else {
+			perms = *aa_lookup_perms(rules->policy, state);
+		}
+		aa_apply_modes_to_perms(profile, &perms);
+		error = aa_check_perms(profile, &perms, request, ad,
+				       audit_uring_cb);
+	}
+
+	return error;
+}
+
+/**
+ * apparmor_uring_override_creds - check the requested cred override
+ * @new: the target creds
+ *
+ * Check to see if the current task is allowed to override it's credentials
+ * to service an io_uring operation.
+ */
+static int apparmor_uring_override_creds(const struct cred *new)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	int error;
+	bool needput;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING,
+			  OP_URING_OVERRIDE);
+
+	ad.uring.target = cred_label(new);
+	label = __begin_current_label_crit_section(&needput);
+	error = fn_for_each(label, profile,
+			profile_uring(profile, AA_MAY_OVERRIDE_CRED,
+				      cred_label(new), CAP_SYS_ADMIN, &ad));
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+/**
+ * apparmor_uring_sqpoll - check if a io_uring polling thread can be created
+ *
+ * Check to see if the current task is allowed to create a new io_uring
+ * kernel polling thread.
+ */
+static int apparmor_uring_sqpoll(void)
+{
+	struct aa_profile *profile;
+	struct aa_label *label;
+	int error;
+	bool needput;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_IO_URING,
+			  OP_URING_SQPOLL);
+
+	label = __begin_current_label_crit_section(&needput);
+	error = fn_for_each(label, profile,
+			profile_uring(profile, AA_MAY_CREATE_SQPOLL,
+				      NULL, CAP_SYS_ADMIN, &ad));
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+#endif /* CONFIG_IO_URING */
+
+static int apparmor_sb_mount(const char *dev_name, const struct path *path,
+			     const char *type, unsigned long flags, void *data)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	/* Discard magic */
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+
+	flags &= ~AA_MS_IGNORE_MASK;
+
+	label = __begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		if (flags & MS_REMOUNT)
+			error = aa_remount(current_cred(), label, path, flags,
+					   data);
+		else if (flags & MS_BIND)
+			error = aa_bind_mount(current_cred(), label, path,
+					      dev_name, flags);
+		else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE |
+				  MS_UNBINDABLE))
+			error = aa_mount_change_type(current_cred(), label,
+						     path, flags);
+		else if (flags & MS_MOVE)
+			error = aa_move_mount_old(current_cred(), label, path,
+						  dev_name);
+		else
+			error = aa_new_mount(current_cred(), label, dev_name,
+					     path, type, flags, data);
+	}
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_move_mount(const struct path *from_path,
+			       const struct path *to_path)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	if (!unconfined(label))
+		error = aa_move_mount(current_cred(), label, from_path,
+				      to_path);
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_sb_umount(struct vfsmount *mnt, int flags)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	if (!unconfined(label))
+		error = aa_umount(current_cred(), label, mnt, flags);
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_sb_pivotroot(const struct path *old_path,
+				 const struct path *new_path)
+{
+	struct aa_label *label;
+	int error = 0;
+
+	label = aa_get_current_label();
+	if (!unconfined(label))
+		error = aa_pivotroot(current_cred(), label, old_path, new_path);
+	aa_put_label(label);
+
+	return error;
+}
+
+static int apparmor_getselfattr(unsigned int attr, struct lsm_ctx __user *lx,
+				u32 *size, u32 flags)
+{
+	int error = -ENOENT;
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct aa_label *label = NULL;
+	char *value = NULL;
+
+	switch (attr) {
+	case LSM_ATTR_CURRENT:
+		label = aa_get_newest_label(cred_label(current_cred()));
+		break;
+	case LSM_ATTR_PREV:
+		if (ctx->previous)
+			label = aa_get_newest_label(ctx->previous);
+		break;
+	case LSM_ATTR_EXEC:
+		if (ctx->onexec)
+			label = aa_get_newest_label(ctx->onexec);
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		break;
+	}
+
+	if (label) {
+		error = aa_getprocattr(label, &value, false);
+		if (error > 0)
+			error = lsm_fill_user_ctx(lx, size, value, error,
+						  LSM_ID_APPARMOR, 0);
+		kfree(value);
+	}
+
+	aa_put_label(label);
+
+	if (error < 0)
+		return error;
+	return 1;
+}
+
+static int apparmor_getprocattr(struct task_struct *task, const char *name,
+				char **value)
+{
+	int error = -ENOENT;
+	struct aa_label *label = NULL;
+
+	rcu_read_lock();
+	if (strcmp(name, "current") == 0)
+		label = aa_get_newest_cred_label(__task_cred(task));
+	else if (strcmp(name, "prev") == 0  && task_ctx(task)->previous)
+		label = aa_get_newest_label(task_ctx(task)->previous);
+	else if (strcmp(name, "exec") == 0 && task_ctx(task)->onexec)
+		label = aa_get_newest_label(task_ctx(task)->onexec);
+	else
+		error = -EINVAL;
+	rcu_read_unlock();
+
+	if (label)
+		error = aa_getprocattr(label, value, true);
+
+	aa_put_label(label);
+
+	return error;
+}
+
+static int do_setattr(u64 attr, void *value, size_t size)
+{
+	char *command, *largs = NULL, *args = value;
+	size_t arg_size;
+	int error;
+	bool needput;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE,
+			  OP_SETPROCATTR);
+
+	if (size == 0)
+		return -EINVAL;
+
+	/* AppArmor requires that the buffer must be null terminated atm */
+	if (args[size - 1] != '\0') {
+		largs = args = kmemdup_nul(value, size, GFP_KERNEL);
+		if (!args)
+			return -ENOMEM;
+	}
+
+	error = -EINVAL;
+	args = strim(args);
+	command = strsep(&args, " ");
+	if (!args)
+		goto out;
+	args = skip_spaces(args);
+	if (!*args)
+		goto out;
+
+	arg_size = size - (args - (largs ? largs : (char *) value));
+	if (attr == LSM_ATTR_CURRENT) {
+		if (strcmp(command, "changehat") == 0) {
+			error = aa_setprocattr_changehat(args, arg_size,
+							 AA_CHANGE_NOFLAGS);
+		} else if (strcmp(command, "permhat") == 0) {
+			error = aa_setprocattr_changehat(args, arg_size,
+							 AA_CHANGE_TEST);
+		} else if (strcmp(command, "changeprofile") == 0) {
+			error = aa_change_profile(args, AA_CHANGE_NOFLAGS);
+		} else if (strcmp(command, "permprofile") == 0) {
+			error = aa_change_profile(args, AA_CHANGE_TEST);
+		} else if (strcmp(command, "stack") == 0) {
+			error = aa_change_profile(args, AA_CHANGE_STACK);
+		} else
+			goto fail;
+	} else if (attr == LSM_ATTR_EXEC) {
+		if (strcmp(command, "exec") == 0)
+			error = aa_change_profile(args, AA_CHANGE_ONEXEC);
+		else if (strcmp(command, "stack") == 0)
+			error = aa_change_profile(args, (AA_CHANGE_ONEXEC |
+							 AA_CHANGE_STACK));
+		else
+			goto fail;
+	} else
+		/* only support the "current" and "exec" process attributes */
+		goto fail;
+
+	if (!error)
+		error = size;
+out:
+	kfree(largs);
+	return error;
+
+fail:
+	ad.subj_label = begin_current_label_crit_section(&needput);
+	if (attr == LSM_ATTR_CURRENT)
+		ad.info = "current";
+	else if (attr == LSM_ATTR_EXEC)
+		ad.info = "exec";
+	else
+		ad.info = "invalid";
+	ad.error = error = -EINVAL;
+	aa_audit_msg(AUDIT_APPARMOR_DENIED, &ad, NULL);
+	end_current_label_crit_section(ad.subj_label, needput);
+	goto out;
+}
+
+static int apparmor_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+				u32 size, u32 flags)
+{
+	int rc;
+
+	if (attr != LSM_ATTR_CURRENT && attr != LSM_ATTR_EXEC)
+		return -EOPNOTSUPP;
+
+	rc = do_setattr(attr, ctx->ctx, ctx->ctx_len);
+	if (rc > 0)
+		return 0;
+	return rc;
+}
+
+static int apparmor_setprocattr(const char *name, void *value,
+				size_t size)
+{
+	int attr = lsm_name_to_attr(name);
+
+	if (attr)
+		return do_setattr(attr, value, size);
+	return -EINVAL;
+}
+
+/**
+ * apparmor_bprm_committing_creds - do task cleanup on committing new creds
+ * @bprm: binprm for the exec  (NOT NULL)
+ */
+static void apparmor_bprm_committing_creds(const struct linux_binprm *bprm)
+{
+	struct aa_label *label = aa_current_raw_label();
+	struct aa_label *new_label = cred_label(bprm->cred);
+
+	/* bail out if unconfined or not changing profile */
+	if ((new_label->proxy == label->proxy) ||
+	    (unconfined(new_label)))
+		return;
+
+	aa_inherit_files(bprm->cred, current->files);
+
+	current->pdeath_signal = 0;
+
+	/* reset soft limits and set hard limits for the new label */
+	__aa_transition_rlimits(label, new_label);
+}
+
+/**
+ * apparmor_bprm_committed_creds() - do cleanup after new creds committed
+ * @bprm: binprm for the exec  (NOT NULL)
+ */
+static void apparmor_bprm_committed_creds(const struct linux_binprm *bprm)
+{
+	/* clear out temporary/transitional state from the context */
+	aa_clear_task_ctx_trans(task_ctx(current));
+
+	return;
+}
+
+static void apparmor_current_getlsmprop_subj(struct lsm_prop *prop)
+{
+	struct aa_label *label;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	prop->apparmor.label = label;
+	__end_current_label_crit_section(label, needput);
+}
+
+static void apparmor_task_getlsmprop_obj(struct task_struct *p,
+					  struct lsm_prop *prop)
+{
+	struct aa_label *label = aa_get_task_label(p);
+
+	prop->apparmor.label = label;
+	aa_put_label(label);
+}
+
+static int apparmor_task_setrlimit(struct task_struct *task,
+		unsigned int resource, struct rlimit *new_rlim)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+
+	if (!unconfined(label))
+		error = aa_task_setrlimit(current_cred(), label, task,
+					  resource, new_rlim);
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo *info,
+			      int sig, const struct cred *cred)
+{
+	const struct cred *tc;
+	struct aa_label *cl, *tl;
+	int error;
+	bool needput;
+
+	tc = get_task_cred(target);
+	tl = aa_get_newest_cred_label(tc);
+	if (cred) {
+		/*
+		 * Dealing with USB IO specific behavior
+		 */
+		cl = aa_get_newest_cred_label(cred);
+		error = aa_may_signal(cred, cl, tc, tl, sig);
+		aa_put_label(cl);
+	} else {
+		cl = __begin_current_label_crit_section(&needput);
+		error = aa_may_signal(current_cred(), cl, tc, tl, sig);
+		__end_current_label_crit_section(cl, needput);
+	}
+	aa_put_label(tl);
+	put_cred(tc);
+
+	return error;
+}
+
+static int apparmor_userns_create(const struct cred *cred)
+{
+	struct aa_label *label;
+	struct aa_profile *profile;
+	int error = 0;
+	bool needput;
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_NS,
+			  OP_USERNS_CREATE);
+
+	ad.subj_cred = current_cred();
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		error = fn_for_each(label, profile,
+				    aa_profile_ns_perm(profile, &ad,
+						       AA_USERNS_CREATE));
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t gfp)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	struct aa_label *label;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	//spin_lock_init(&ctx->lock);
+	rcu_assign_pointer(ctx->label, aa_get_label(label));
+	rcu_assign_pointer(ctx->peer, NULL);
+	rcu_assign_pointer(ctx->peer_lastupdate, NULL);
+	__end_current_label_crit_section(label, needput);
+	return 0;
+}
+
+static void apparmor_sk_free_security(struct sock *sk)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+
+	/* dead these won't be updated any more */
+	aa_put_label(rcu_dereference_protected(ctx->label, true));
+	aa_put_label(rcu_dereference_protected(ctx->peer, true));
+	aa_put_label(rcu_dereference_protected(ctx->peer_lastupdate, true));
+}
+
+/**
+ * apparmor_sk_clone_security - clone the sk_security field
+ * @sk: sock to have security cloned
+ * @newsk: sock getting clone
+ */
+static void apparmor_sk_clone_security(const struct sock *sk,
+				       struct sock *newsk)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	struct aa_sk_ctx *new = aa_sock(newsk);
+
+	/* not actually in use yet */
+	if (rcu_access_pointer(ctx->label) != rcu_access_pointer(new->label)) {
+		aa_put_label(rcu_dereference_protected(new->label, true));
+		rcu_assign_pointer(new->label, aa_get_label_rcu(&ctx->label));
+	}
+
+	if (rcu_access_pointer(ctx->peer) != rcu_access_pointer(new->peer)) {
+		aa_put_label(rcu_dereference_protected(new->peer, true));
+		rcu_assign_pointer(new->peer, aa_get_label_rcu(&ctx->peer));
+	}
+
+	if (rcu_access_pointer(ctx->peer_lastupdate) != rcu_access_pointer(new->peer_lastupdate)) {
+		aa_put_label(rcu_dereference_protected(new->peer_lastupdate, true));
+		rcu_assign_pointer(new->peer_lastupdate,
+				   aa_get_label_rcu(&ctx->peer_lastupdate));
+	}
+}
+
+static int unix_connect_perm(const struct cred *cred, struct aa_label *label,
+			     struct sock *sk, struct sock *peer_sk)
+{
+	struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk);
+	int error;
+
+	error = aa_unix_peer_perm(cred, label, OP_CONNECT,
+				(AA_MAY_CONNECT | AA_MAY_SEND | AA_MAY_RECEIVE),
+				  sk, peer_sk,
+				  rcu_dereference_protected(peer_ctx->label,
+				     lockdep_is_held(&unix_sk(peer_sk)->lock)));
+	if (!is_unix_fs(peer_sk)) {
+		last_error(error,
+			   aa_unix_peer_perm(cred,
+				rcu_dereference_protected(peer_ctx->label,
+				     lockdep_is_held(&unix_sk(peer_sk)->lock)),
+				OP_CONNECT,
+				(AA_MAY_ACCEPT | AA_MAY_SEND | AA_MAY_RECEIVE),
+							  peer_sk, sk, label));
+	}
+
+	return error;
+}
+
+/* lockdep check in unix_connect_perm - push sks here to check */
+static void unix_connect_peers(struct aa_sk_ctx *sk_ctx,
+			       struct aa_sk_ctx *peer_ctx)
+{
+	/* Cross reference the peer labels for SO_PEERSEC */
+	struct aa_label *label = rcu_dereference_protected(sk_ctx->label, true);
+
+	aa_get_label(label);
+	aa_put_label(rcu_dereference_protected(peer_ctx->peer,
+					     true));
+	rcu_assign_pointer(peer_ctx->peer, label);	/* transfer cnt */
+
+	label = aa_get_label(rcu_dereference_protected(peer_ctx->label,
+					     true));
+	//spin_unlock(&peer_ctx->lock);
+
+	//spin_lock(&sk_ctx->lock);
+	aa_put_label(rcu_dereference_protected(sk_ctx->peer,
+					       true));
+	aa_put_label(rcu_dereference_protected(sk_ctx->peer_lastupdate,
+					       true));
+
+	rcu_assign_pointer(sk_ctx->peer, aa_get_label(label));
+	rcu_assign_pointer(sk_ctx->peer_lastupdate, label);     /* transfer cnt */
+	//spin_unlock(&sk_ctx->lock);
+}
+
+/**
+ * apparmor_unix_stream_connect - check perms before making unix domain conn
+ * @sk: sk attempting to connect
+ * @peer_sk: sk that is accepting the connection
+ * @newsk: new sk created for this connection
+ * peer is locked when this hook is called
+ *
+ * Return:
+ *   0 if connection is permitted
+ *   error code on denial or failure
+ */
+static int apparmor_unix_stream_connect(struct sock *sk, struct sock *peer_sk,
+					struct sock *newsk)
+{
+	struct aa_sk_ctx *sk_ctx = aa_sock(sk);
+	struct aa_sk_ctx *peer_ctx = aa_sock(peer_sk);
+	struct aa_sk_ctx *new_ctx = aa_sock(newsk);
+	struct aa_label *label;
+	int error;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	error = unix_connect_perm(current_cred(), label, sk, peer_sk);
+	__end_current_label_crit_section(label, needput);
+
+	if (error)
+		return error;
+
+	/* newsk doesn't go through post_create, but does go through
+	 * security_sk_alloc()
+	 */
+	rcu_assign_pointer(new_ctx->label,
+			   aa_get_label(rcu_dereference_protected(peer_ctx->label,
+								  true)));
+
+	/* Cross reference the peer labels for SO_PEERSEC */
+	unix_connect_peers(sk_ctx, new_ctx);
+
+	return 0;
+}
+
+/**
+ * apparmor_unix_may_send - check perms before conn or sending unix dgrams
+ * @sock: socket sending the message
+ * @peer: socket message is being send to
+ *
+ * Performs bidirectional permission checks for Unix domain socket communication:
+ * 1. Verifies sender has AA_MAY_SEND to target socket
+ * 2. Verifies receiver has AA_MAY_RECEIVE from source socket
+ *
+ * sock and peer are locked when this hook is called
+ * called by: dgram_connect peer setup but path not copied to newsk
+ *
+ * Return:
+ *   0 if transmission is permitted
+ *   error code on denial or failure
+ */
+static int apparmor_unix_may_send(struct socket *sock, struct socket *peer)
+{
+	struct aa_sk_ctx *peer_ctx = aa_sock(peer->sk);
+	struct aa_label *label;
+	int error;
+	bool needput;
+
+	label = __begin_current_label_crit_section(&needput);
+	error = xcheck(aa_unix_peer_perm(current_cred(),
+				label, OP_SENDMSG, AA_MAY_SEND,
+				sock->sk, peer->sk,
+				rcu_dereference_protected(peer_ctx->label,
+							  true)),
+		       aa_unix_peer_perm(peer->file ? peer->file->f_cred : NULL,
+				rcu_dereference_protected(peer_ctx->label,
+							  true),
+				OP_SENDMSG, AA_MAY_RECEIVE, peer->sk,
+				sock->sk, label));
+	__end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+static int apparmor_socket_create(int family, int type, int protocol, int kern)
+{
+	struct aa_label *label;
+	int error = 0;
+	bool needput;
+
+	AA_BUG(in_interrupt());
+
+	if (kern)
+		return 0;
+
+	label = begin_current_label_crit_section(&needput);
+	if (!unconfined(label)) {
+		switch (family) {
+		case PF_UNIX:
+			error = aa_unix_create_perm(label, family, type,
+						    protocol);
+			break;
+		case PF_INET:
+		case PF_INET6:
+			error = aa_inet_create_perm(label, family, type,
+						    protocol);
+			break;
+		default:
+			error = aa_af_perm(current_cred(), label, OP_CREATE,
+					   AA_MAY_CREATE, family, type,
+					   protocol);
+		}
+	}
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+/**
+ * apparmor_socket_post_create - setup the per-socket security struct
+ * @sock: socket that is being setup
+ * @family: family of socket being created
+ * @type: type of the socket
+ * @protocol: protocol of the socket
+ * @kern: socket is a special kernel socket
+ *
+ * Note:
+ * -   kernel sockets labeled kernel_t used to use unconfined
+ * -   socket may not have sk here if created with sock_create_lite or
+ *     sock_alloc. These should be accept cases which will be handled in
+ *     sock_graft.
+ */
+static int apparmor_socket_post_create(struct socket *sock, int family,
+				       int type, int protocol, int kern)
+{
+	struct aa_label *label;
+
+	if (kern) {
+		label = aa_get_label(kernel_t);
+	} else
+		label = aa_get_current_label();
+
+	if (sock->sk) {
+		struct aa_sk_ctx *ctx = aa_sock(sock->sk);
+
+		/* still not live */
+		aa_put_label(rcu_dereference_protected(ctx->label, true));
+		rcu_assign_pointer(ctx->label, aa_get_label(label));
+	}
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int apparmor_socket_socketpair(struct socket *socka,
+				      struct socket *sockb)
+{
+	struct aa_sk_ctx *a_ctx = aa_sock(socka->sk);
+	struct aa_sk_ctx *b_ctx = aa_sock(sockb->sk);
+	struct aa_label *label;
+	bool needput;
+
+	/* socks not live yet - initial values set in sk_alloc */
+	label = begin_current_label_crit_section(&needput);
+	if (rcu_access_pointer(a_ctx->label) != label) {
+		AA_BUG("a_ctx != label");
+		aa_put_label(rcu_dereference_protected(a_ctx->label, true));
+		rcu_assign_pointer(a_ctx->label, aa_get_label(label));
+	}
+	if (rcu_access_pointer(b_ctx->label) != label) {
+		AA_BUG("b_ctx != label");
+		aa_put_label(rcu_dereference_protected(b_ctx->label, true));
+		rcu_assign_pointer(b_ctx->label, aa_get_label(label));
+	}
+
+	if (socka->sk->sk_family == PF_UNIX) {
+		/* unix socket pairs by-pass unix_stream_connect */
+		unix_connect_peers(a_ctx, b_ctx);
+	}
+	end_current_label_crit_section(label, needput);
+
+	return 0;
+}
+
+/**
+ * apparmor_socket_bind - check perms before bind addr to socket
+ * @sock: socket to bind the address to (must be non-NULL)
+ * @address: address that is being bound (must be non-NULL)
+ * @addrlen: length of @address
+ *
+ * Performs security checks before allowing a socket to bind to an address.
+ * Handles Unix domain sockets specially through aa_unix_bind_perm().
+ * For other socket families, uses generic permission check via aa_sk_perm().
+ *
+ * Return:
+ *   0 if binding is permitted
+ *   error code on denial or invalid parameters
+ */
+static int apparmor_socket_bind(struct socket *sock,
+				struct sockaddr *address, int addrlen)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(!address);
+	AA_BUG(in_interrupt());
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_bind_perm(sock, address, addrlen);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_bind_perm(sock, address, addrlen);
+	}
+	return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk);
+}
+
+static int apparmor_socket_connect(struct socket *sock,
+				   struct sockaddr *address, int addrlen)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(!address);
+	AA_BUG(in_interrupt());
+
+	/* PF_UNIX goes through unix_stream_connect && unix_may_send */
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return 0;
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_connect_perm(sock, address, addrlen);
+	}
+	return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk);
+}
+
+static int apparmor_socket_listen(struct socket *sock, int backlog)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(in_interrupt());
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_listen_perm(sock, backlog);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_listen_perm(sock, backlog);
+	}
+	return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk);
+}
+
+/*
+ * Note: while @newsock is created and has some information, the accept
+ *       has not been done.
+ */
+static int apparmor_socket_accept(struct socket *sock, struct socket *newsock)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(!newsock);
+	AA_BUG(in_interrupt());
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_accept_perm(sock, newsock);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_accept_perm(sock, newsock);
+	}
+	return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk);
+}
+
+static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
+			    struct msghdr *msg, int size)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(!msg);
+	AA_BUG(in_interrupt());
+
+	/* PF_UNIX goes through unix_may_send */
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return 0;
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_msg_perm(op, request, sock, msg, size);
+	}
+
+	return aa_sk_perm(op, request, sock->sk);
+}
+
+static int apparmor_socket_sendmsg(struct socket *sock,
+				   struct msghdr *msg, int size)
+{
+	int error = aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
+
+	if (error)
+		return error;
+
+	/* TCP fast open carries connect() semantics in sendmsg(); mediate
+	 * the implicit connect so it cannot bypass the connect permission.
+	 */
+	if ((msg->msg_flags & MSG_FASTOPEN) && msg->msg_name &&
+	    (sk_is_tcp(sock->sk) ||
+	     (sk_is_inet(sock->sk) && sock->sk->sk_type == SOCK_STREAM &&
+	      sock->sk->sk_protocol == IPPROTO_MPTCP)))
+		error = aa_sock_msg_perm(OP_CONNECT, AA_MAY_CONNECT, sock,
+					 msg, size);
+
+	return error;
+}
+
+static int apparmor_socket_recvmsg(struct socket *sock,
+				   struct msghdr *msg, int size, int flags)
+{
+	return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size);
+}
+
+/* revaliation, get/set attr, shutdown */
+static int aa_sock_perm(const char *op, u32 request, struct socket *sock)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(in_interrupt());
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_sock_perm(op, request, sock);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_sock_perm(op, request, sock);
+	}
+	return aa_sk_perm(op, request, sock->sk);
+}
+
+static int apparmor_socket_getsockname(struct socket *sock)
+{
+	return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock);
+}
+
+static int apparmor_socket_getpeername(struct socket *sock)
+{
+	return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock);
+}
+
+/* revaliation, get/set attr, opt */
+static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock,
+			    int level, int optname)
+{
+	AA_BUG(!sock);
+	AA_BUG(!sock->sk);
+	AA_BUG(in_interrupt());
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_opt_perm(op, request, sock, level, optname);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_opt_perm(op, request, sock, level, optname);
+	}
+	return aa_sk_perm(op, request, sock->sk);
+}
+
+static int apparmor_socket_getsockopt(struct socket *sock, int level,
+				      int optname)
+{
+	return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock,
+				level, optname);
+}
+
+static int apparmor_socket_setsockopt(struct socket *sock, int level,
+				      int optname)
+{
+	return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock,
+				level, optname);
+}
+
+static int apparmor_socket_shutdown(struct socket *sock, int how)
+{
+	return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock);
+}
+
+static struct aa_label *sk_peer_get_label(struct sock *sk)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+
+	if (rcu_access_pointer(ctx->peer))
+		return aa_get_label_rcu(&ctx->peer);
+
+	return ERR_PTR(-ENOPROTOOPT);
+}
+
+/**
+ * apparmor_socket_getpeersec_stream - get security context of peer
+ * @sock: socket that we are trying to get the peer context of
+ * @optval: output - buffer to copy peer name to
+ * @optlen: output - size of copied name in @optval
+ * @len: size of @optval buffer
+ * Returns: 0 on success, -errno of failure
+ *
+ * Note: for tcp only valid if using ipsec or cipso on lan
+ */
+static int apparmor_socket_getpeersec_stream(struct socket *sock,
+					     sockptr_t optval, sockptr_t optlen,
+					     unsigned int len)
+{
+	char *name = NULL;
+	int slen, error = 0;
+	struct aa_label *label;
+	struct aa_label *peer;
+	bool needput;
+
+	peer = sk_peer_get_label(sock->sk);
+	if (IS_ERR(peer)) {
+		error = PTR_ERR(peer);
+		goto done;
+	}
+	label = begin_current_label_crit_section(&needput);
+	slen = aa_label_asxprint(&name, labels_ns(label), peer,
+				 FLAG_SHOW_MODE | FLAG_VIEW_SUBNS |
+				 FLAG_HIDDEN_UNCONFINED, GFP_KERNEL);
+	/* don't include terminating \0 in slen, it breaks some apps */
+	if (slen < 0) {
+		error = -ENOMEM;
+		goto done_put;
+	}
+	if (slen > len) {
+		error = -ERANGE;
+		goto done_len;
+	}
+
+	if (copy_to_sockptr(optval, name, slen))
+		error = -EFAULT;
+done_len:
+	if (copy_to_sockptr(optlen, &slen, sizeof(slen)))
+		error = -EFAULT;
+
+done_put:
+	end_current_label_crit_section(label, needput);
+	aa_put_label(peer);
+done:
+	kfree(name);
+	return error;
+}
+
+/**
+ * apparmor_socket_getpeersec_dgram - get security label of packet
+ * @sock: the peer socket
+ * @skb: packet data
+ * @secid: pointer to where to put the secid of the packet
+ *
+ * Sets the netlabel socket state on sk from parent
+ */
+static int apparmor_socket_getpeersec_dgram(struct socket *sock,
+					    struct sk_buff *skb, u32 *secid)
+
+{
+	/* TODO: requires secid support */
+	return -ENOPROTOOPT;
+}
+
+/**
+ * apparmor_sock_graft - Initialize newly created socket
+ * @sk: child sock
+ * @parent: parent socket
+ *
+ * Note: could set off of SOCK_CTX(parent) but need to track inode and we can
+ *       just set sk security information off of current creating process label
+ *       Labeling of sk for accept case - probably should be sock based
+ *       instead of task, because of the case where an implicitly labeled
+ *       socket is shared by different tasks.
+ */
+static void apparmor_sock_graft(struct sock *sk, struct socket *parent)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+
+	/* setup - not live */
+	if (!rcu_access_pointer(ctx->label))
+		rcu_assign_pointer(ctx->label, aa_get_current_label());
+}
+
+#ifdef CONFIG_NETWORK_SECMARK
+/**
+ * apparmor_socket_sock_rcv_skb - check perms before associating skb to sk
+ * @sk: sk to associate @skb with
+ * @skb: skb to check for perms
+ *
+ * Note: can not sleep may be called with locks held
+ *
+ * don't want protocol specific in __skb_recv_datagram()
+ * to deny an incoming connection  socket_sock_rcv_skb()
+ */
+static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	int error;
+
+	if (!skb->secmark)
+		return 0;
+
+	/*
+	 * If reach here before socket_post_create hook is called, in which
+	 * case label is null, drop the packet.
+	 */
+	if (!rcu_access_pointer(ctx->label))
+		return -EACCES;
+
+	rcu_read_lock();
+	error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_RECVMSG,
+				       AA_MAY_RECEIVE, skb->secmark, sk);
+	rcu_read_unlock();
+
+	return error;
+}
+
+static int apparmor_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+				      struct request_sock *req)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	int error;
+
+	if (!skb->secmark)
+		return 0;
+
+	rcu_read_lock();
+	error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_CONNECT,
+				       AA_MAY_CONNECT, skb->secmark, sk);
+	rcu_read_unlock();
+
+	return error;
+}
+#endif
+
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK)
+static unsigned int apparmor_ip_postroute(void *priv,
+					  struct sk_buff *skb,
+					  const struct nf_hook_state *state)
+{
+	struct aa_sk_ctx *ctx;
+	struct sock *sk;
+	int error;
+
+	if (!skb->secmark)
+		return NF_ACCEPT;
+
+	sk = skb_to_full_sk(skb);
+	if (sk == NULL)
+		return NF_ACCEPT;
+
+	ctx = aa_sock(sk);
+	rcu_read_lock();
+	error = apparmor_secmark_check(rcu_dereference(ctx->label), OP_SENDMSG,
+				       AA_MAY_SEND, skb->secmark, sk);
+	rcu_read_unlock();
+	if (!error)
+		return NF_ACCEPT;
+
+	return NF_DROP_ERR(-ECONNREFUSED);
+}
+
+static const struct nf_hook_ops apparmor_nf_ops[] = {
+	{
+		.hook =         apparmor_ip_postroute,
+		.pf =           NFPROTO_IPV4,
+		.hooknum =      NF_INET_POST_ROUTING,
+		.priority =     NF_IP_PRI_SELINUX_FIRST,
+	},
+#if IS_ENABLED(CONFIG_IPV6)
+	{
+		.hook =         apparmor_ip_postroute,
+		.pf =           NFPROTO_IPV6,
+		.hooknum =      NF_INET_POST_ROUTING,
+		.priority =     NF_IP6_PRI_SELINUX_FIRST,
+	},
+#endif
+};
+#endif
+
+/*
+ * The cred blob is a pointer to, not an instance of, an aa_label.
+ */
+struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = {
+	.lbs_cred = sizeof(struct aa_label *),
+	.lbs_file = sizeof(struct aa_file_ctx),
+	.lbs_task = sizeof(struct aa_task_ctx),
+	.lbs_sock = sizeof(struct aa_sk_ctx),
+};
+
+static const struct lsm_id apparmor_lsmid = {
+	.name = "apparmor",
+	.id = LSM_ID_APPARMOR,
+};
+
+static struct security_hook_list apparmor_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme),
+	LSM_HOOK_INIT(capget, apparmor_capget),
+	LSM_HOOK_INIT(capable, apparmor_capable),
+
+	LSM_HOOK_INIT(move_mount, apparmor_move_mount),
+	LSM_HOOK_INIT(sb_mount, apparmor_sb_mount),
+	LSM_HOOK_INIT(sb_umount, apparmor_sb_umount),
+	LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot),
+
+	LSM_HOOK_INIT(path_link, apparmor_path_link),
+	LSM_HOOK_INIT(path_unlink, apparmor_path_unlink),
+	LSM_HOOK_INIT(path_symlink, apparmor_path_symlink),
+	LSM_HOOK_INIT(path_mkdir, apparmor_path_mkdir),
+	LSM_HOOK_INIT(path_rmdir, apparmor_path_rmdir),
+	LSM_HOOK_INIT(path_mknod, apparmor_path_mknod),
+	LSM_HOOK_INIT(path_rename, apparmor_path_rename),
+	LSM_HOOK_INIT(path_chmod, apparmor_path_chmod),
+	LSM_HOOK_INIT(path_chown, apparmor_path_chown),
+	LSM_HOOK_INIT(path_truncate, apparmor_path_truncate),
+	LSM_HOOK_INIT(inode_getattr, apparmor_inode_getattr),
+
+	LSM_HOOK_INIT(file_open, apparmor_file_open),
+	LSM_HOOK_INIT(file_receive, apparmor_file_receive),
+	LSM_HOOK_INIT(file_permission, apparmor_file_permission),
+	LSM_HOOK_INIT(file_alloc_security, apparmor_file_alloc_security),
+	LSM_HOOK_INIT(file_free_security, apparmor_file_free_security),
+	LSM_HOOK_INIT(mmap_file, apparmor_mmap_file),
+	LSM_HOOK_INIT(file_mprotect, apparmor_file_mprotect),
+	LSM_HOOK_INIT(file_lock, apparmor_file_lock),
+	LSM_HOOK_INIT(file_truncate, apparmor_file_truncate),
+
+	LSM_HOOK_INIT(getselfattr, apparmor_getselfattr),
+	LSM_HOOK_INIT(setselfattr, apparmor_setselfattr),
+	LSM_HOOK_INIT(getprocattr, apparmor_getprocattr),
+	LSM_HOOK_INIT(setprocattr, apparmor_setprocattr),
+
+	LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security),
+	LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security),
+	LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security),
+
+	LSM_HOOK_INIT(unix_stream_connect, apparmor_unix_stream_connect),
+	LSM_HOOK_INIT(unix_may_send, apparmor_unix_may_send),
+
+	LSM_HOOK_INIT(socket_create, apparmor_socket_create),
+	LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create),
+	LSM_HOOK_INIT(socket_socketpair, apparmor_socket_socketpair),
+	LSM_HOOK_INIT(socket_bind, apparmor_socket_bind),
+	LSM_HOOK_INIT(socket_connect, apparmor_socket_connect),
+	LSM_HOOK_INIT(socket_listen, apparmor_socket_listen),
+	LSM_HOOK_INIT(socket_accept, apparmor_socket_accept),
+	LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg),
+	LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg),
+	LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname),
+	LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername),
+	LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt),
+	LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt),
+	LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown),
+#ifdef CONFIG_NETWORK_SECMARK
+	LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb),
+#endif
+	LSM_HOOK_INIT(socket_getpeersec_stream,
+		      apparmor_socket_getpeersec_stream),
+	LSM_HOOK_INIT(socket_getpeersec_dgram,
+		      apparmor_socket_getpeersec_dgram),
+	LSM_HOOK_INIT(sock_graft, apparmor_sock_graft),
+#ifdef CONFIG_NETWORK_SECMARK
+	LSM_HOOK_INIT(inet_conn_request, apparmor_inet_conn_request),
+#endif
+
+	LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank),
+	LSM_HOOK_INIT(cred_free, apparmor_cred_free),
+	LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare),
+	LSM_HOOK_INIT(cred_transfer, apparmor_cred_transfer),
+
+	LSM_HOOK_INIT(bprm_creds_for_exec, apparmor_bprm_creds_for_exec),
+	LSM_HOOK_INIT(bprm_committing_creds, apparmor_bprm_committing_creds),
+	LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds),
+
+	LSM_HOOK_INIT(task_free, apparmor_task_free),
+	LSM_HOOK_INIT(task_alloc, apparmor_task_alloc),
+	LSM_HOOK_INIT(current_getlsmprop_subj,
+		      apparmor_current_getlsmprop_subj),
+	LSM_HOOK_INIT(task_getlsmprop_obj, apparmor_task_getlsmprop_obj),
+	LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit),
+	LSM_HOOK_INIT(task_kill, apparmor_task_kill),
+	LSM_HOOK_INIT(userns_create, apparmor_userns_create),
+
+#ifdef CONFIG_AUDIT
+	LSM_HOOK_INIT(audit_rule_init, aa_audit_rule_init),
+	LSM_HOOK_INIT(audit_rule_known, aa_audit_rule_known),
+	LSM_HOOK_INIT(audit_rule_match, aa_audit_rule_match),
+	LSM_HOOK_INIT(audit_rule_free, aa_audit_rule_free),
+#endif
+
+	LSM_HOOK_INIT(secid_to_secctx, apparmor_secid_to_secctx),
+	LSM_HOOK_INIT(lsmprop_to_secctx, apparmor_lsmprop_to_secctx),
+	LSM_HOOK_INIT(secctx_to_secid, apparmor_secctx_to_secid),
+	LSM_HOOK_INIT(release_secctx, apparmor_release_secctx),
+
+#ifdef CONFIG_IO_URING
+	LSM_HOOK_INIT(uring_override_creds, apparmor_uring_override_creds),
+	LSM_HOOK_INIT(uring_sqpoll, apparmor_uring_sqpoll),
+#endif
+};
+
+/*
+ * AppArmor sysfs module parameters
+ */
+
+static int param_set_aabool(const char *val, const struct kernel_param *kp);
+static int param_get_aabool(char *buffer, const struct kernel_param *kp);
+#define param_check_aabool param_check_bool
+static const struct kernel_param_ops param_ops_aabool = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = param_set_aabool,
+	.get = param_get_aabool
+};
+
+static int param_set_aauint(const char *val, const struct kernel_param *kp);
+static int param_get_aauint(char *buffer, const struct kernel_param *kp);
+#define param_check_aauint param_check_uint
+static const struct kernel_param_ops param_ops_aauint = {
+	.set = param_set_aauint,
+	.get = param_get_aauint
+};
+
+static int param_set_aacompressionlevel(const char *val,
+					const struct kernel_param *kp);
+static int param_get_aacompressionlevel(char *buffer,
+					const struct kernel_param *kp);
+#define param_check_aacompressionlevel param_check_int
+static const struct kernel_param_ops param_ops_aacompressionlevel = {
+	.set = param_set_aacompressionlevel,
+	.get = param_get_aacompressionlevel
+};
+
+static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp);
+static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp);
+#define param_check_aalockpolicy param_check_bool
+static const struct kernel_param_ops param_ops_aalockpolicy = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = param_set_aalockpolicy,
+	.get = param_get_aalockpolicy
+};
+
+static int param_set_debug(const char *val, const struct kernel_param *kp);
+static int param_get_debug(char *buffer, const struct kernel_param *kp);
+
+static int param_set_audit(const char *val, const struct kernel_param *kp);
+static int param_get_audit(char *buffer, const struct kernel_param *kp);
+
+static int param_set_mode(const char *val, const struct kernel_param *kp);
+static int param_get_mode(char *buffer, const struct kernel_param *kp);
+
+/* Flag values, also controllable via /sys/module/apparmor/parameters
+ * We define special types as we want to do additional mediation.
+ */
+
+/* AppArmor global enforcement switch - complain, enforce, kill */
+enum profile_mode aa_g_profile_mode = APPARMOR_ENFORCE;
+module_param_call(mode, param_set_mode, param_get_mode,
+		  &aa_g_profile_mode, S_IRUSR | S_IWUSR);
+
+/* whether policy verification hashing is enabled */
+bool aa_g_hash_policy = IS_ENABLED(CONFIG_SECURITY_APPARMOR_HASH_DEFAULT);
+#ifdef CONFIG_SECURITY_APPARMOR_HASH
+module_param_named(hash_policy, aa_g_hash_policy, aabool, S_IRUSR | S_IWUSR);
+#endif
+
+/* whether policy exactly as loaded is retained for debug and checkpointing */
+bool aa_g_export_binary = IS_ENABLED(CONFIG_SECURITY_APPARMOR_EXPORT_BINARY);
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+module_param_named(export_binary, aa_g_export_binary, aabool, 0600);
+#endif
+
+/* policy loaddata compression level */
+int aa_g_rawdata_compression_level = AA_DEFAULT_CLEVEL;
+module_param_named(rawdata_compression_level, aa_g_rawdata_compression_level,
+		   aacompressionlevel, 0400);
+
+/* Debug mode */
+int aa_g_debug;
+module_param_call(debug, param_set_debug, param_get_debug,
+		  &aa_g_debug, 0600);
+
+/* Audit mode */
+enum audit_mode aa_g_audit;
+module_param_call(audit, param_set_audit, param_get_audit,
+		  &aa_g_audit, S_IRUSR | S_IWUSR);
+
+/* Determines if audit header is included in audited messages.  This
+ * provides more context if the audit daemon is not running
+ */
+bool aa_g_audit_header = true;
+module_param_named(audit_header, aa_g_audit_header, aabool,
+		   S_IRUSR | S_IWUSR);
+
+/* lock out loading/removal of policy
+ * TODO: add in at boot loading of policy, which is the only way to
+ *       load policy, if lock_policy is set
+ */
+bool aa_g_lock_policy;
+module_param_named(lock_policy, aa_g_lock_policy, aalockpolicy,
+		   S_IRUSR | S_IWUSR);
+
+/* Syscall logging mode */
+bool aa_g_logsyscall;
+module_param_named(logsyscall, aa_g_logsyscall, aabool, S_IRUSR | S_IWUSR);
+
+/* Maximum pathname length before accesses will start getting rejected */
+unsigned int aa_g_path_max = 2 * PATH_MAX;
+module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR);
+
+/* Determines how paranoid loading of policy is and how much verification
+ * on the loaded policy is done.
+ * DEPRECATED: read only as strict checking of load is always done now
+ * that none root users (user namespaces) can load policy.
+ */
+bool aa_g_paranoid_load = IS_ENABLED(CONFIG_SECURITY_APPARMOR_PARANOID_LOAD);
+module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO);
+
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp);
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp);
+#define param_check_aaintbool param_check_int
+static const struct kernel_param_ops param_ops_aaintbool = {
+	.set = param_set_aaintbool,
+	.get = param_get_aaintbool
+};
+/* Boot time disable flag */
+static int apparmor_enabled __ro_after_init = 1;
+module_param_named(enabled, apparmor_enabled, aaintbool, 0444);
+
+static int __init apparmor_enabled_setup(char *str)
+{
+	unsigned long enabled;
+	int error = kstrtoul(str, 0, &enabled);
+	if (!error)
+		apparmor_enabled = enabled ? 1 : 0;
+	return 1;
+}
+
+__setup("apparmor=", apparmor_enabled_setup);
+
+/* set global flag turning off the ability to load policy */
+static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+	return param_set_bool(val, kp);
+}
+
+static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return param_get_bool(buffer, kp);
+}
+
+static int param_set_aabool(const char *val, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+	return param_set_bool(val, kp);
+}
+
+static int param_get_aabool(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return param_get_bool(buffer, kp);
+}
+
+static int param_set_aauint(const char *val, const struct kernel_param *kp)
+{
+	int error;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+	/* file is ro but enforce 2nd line check */
+	if (apparmor_initialized)
+		return -EPERM;
+
+	error = param_set_uint(val, kp);
+	aa_g_path_max = max_t(uint32_t, aa_g_path_max, sizeof(union aa_buffer));
+	pr_info("AppArmor: buffer size set to %d bytes\n", aa_g_path_max);
+
+	return error;
+}
+
+static int param_get_aauint(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return param_get_uint(buffer, kp);
+}
+
+/* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp)
+{
+	struct kernel_param kp_local;
+	bool value;
+	int error;
+
+	if (apparmor_initialized)
+		return -EPERM;
+
+	/* Create local copy, with arg pointing to bool type. */
+	value = !!*((int *)kp->arg);
+	memcpy(&kp_local, kp, sizeof(kp_local));
+	kp_local.arg = &value;
+
+	error = param_set_bool(val, &kp_local);
+	if (!error)
+		*((int *)kp->arg) = *((bool *)kp_local.arg);
+	return error;
+}
+
+/*
+ * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to
+ * 1/0, this converts the "int that is actually bool" back to bool for
+ * display in the /sys filesystem, while keeping it "int" for the LSM
+ * infrastructure.
+ */
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp)
+{
+	struct kernel_param kp_local;
+	bool value;
+
+	/* Create local copy, with arg pointing to bool type. */
+	value = !!*((int *)kp->arg);
+	memcpy(&kp_local, kp, sizeof(kp_local));
+	kp_local.arg = &value;
+
+	return param_get_bool(buffer, &kp_local);
+}
+
+static int param_set_aacompressionlevel(const char *val,
+					const struct kernel_param *kp)
+{
+	int error;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized)
+		return -EPERM;
+
+	error = param_set_int(val, kp);
+
+	aa_g_rawdata_compression_level = clamp(aa_g_rawdata_compression_level,
+					       AA_MIN_CLEVEL, AA_MAX_CLEVEL);
+	pr_info("AppArmor: policy rawdata compression level set to %d\n",
+		aa_g_rawdata_compression_level);
+
+	return error;
+}
+
+static int param_get_aacompressionlevel(char *buffer,
+					const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return param_get_int(buffer, kp);
+}
+
+static int param_get_debug(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return aa_print_debug_params(buffer);
+}
+
+static int param_set_debug(const char *val, const struct kernel_param *kp)
+{
+	int i;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (!val)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+
+	i = aa_parse_debug_params(val);
+	if (i == DEBUG_PARSE_ERROR)
+		return -EINVAL;
+
+	aa_g_debug = i;
+	return 0;
+}
+
+static int param_get_audit(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return sysfs_emit(buffer, "%s\n", audit_mode_names[aa_g_audit]);
+}
+
+static int param_set_audit(const char *val, const struct kernel_param *kp)
+{
+	int i;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (!val)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+
+	i = match_string(audit_mode_names, AUDIT_MODE_NAMES_COUNT, val);
+	if (i < 0)
+		return -EINVAL;
+
+	aa_g_audit = i;
+	return 0;
+}
+
+static int param_get_mode(char *buffer, const struct kernel_param *kp)
+{
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_view_capable(NULL))
+		return -EPERM;
+	return sysfs_emit(buffer, "%s\n", aa_profile_mode_names[aa_g_profile_mode]);
+}
+
+static int param_set_mode(const char *val, const struct kernel_param *kp)
+{
+	int i;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+	if (!val)
+		return -EINVAL;
+	if (apparmor_initialized && !aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+
+	i = match_string(aa_profile_mode_names, PROFILE_MODE_NAMES_COUNT,
+			 val);
+	if (i < 0)
+		return -EINVAL;
+
+	aa_g_profile_mode = i;
+	return 0;
+}
+
+/* arbitrary cap on how long to hold buffer because contention was
+ * encountered before trying to put it back into the global pool
+ */
+#define MAX_HOLD_COUNT 64
+
+/* the hold count is a heuristic for lock contention, and can be
+ * incremented async to actual buffer alloc/free.  Because buffers
+ * may be put back onto a percpu cache different than the ->hold was
+ * added to the counts can be out of sync. Guard against underflow
+ * and overflow
+ */
+static void cache_hold_inc(unsigned int *hold)
+{
+	if (*hold < MAX_HOLD_COUNT)
+		(*hold)++;
+}
+
+char *aa_get_buffer(bool in_atomic)
+{
+	union aa_buffer *aa_buf;
+	struct aa_local_cache *cache;
+	bool try_again = true;
+	gfp_t flags = (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+
+	/* use per cpu cached buffers first */
+	cache = get_cpu_ptr(&aa_local_buffers);
+	if (!list_empty(&cache->head)) {
+		aa_buf = list_first_entry(&cache->head, union aa_buffer, list);
+		list_del(&aa_buf->list);
+		if (cache->hold)
+			cache->hold--;
+		cache->count--;
+		put_cpu_ptr(&aa_local_buffers);
+		return &aa_buf->buffer[0];
+	}
+	/* exit percpu as spinlocks may sleep on realtime kernels */
+	put_cpu_ptr(&aa_local_buffers);
+
+	if (!spin_trylock(&aa_buffers_lock)) {
+		/* had contention on lock so increase hold count. Doesn't
+		 * really matter if recorded before or after the spin lock
+		 * as there is no way to guarantee the buffer will be put
+		 * back on the same percpu cache. Instead rely on holds
+		 * roughly averaging out over time.
+		 */
+		cache = get_cpu_ptr(&aa_local_buffers);
+		cache_hold_inc(&cache->hold);
+		put_cpu_ptr(&aa_local_buffers);
+		spin_lock(&aa_buffers_lock);
+	}
+retry:
+	if (buffer_count > reserve_count ||
+	    (in_atomic && !list_empty(&aa_global_buffers))) {
+		aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer,
+					  list);
+		list_del(&aa_buf->list);
+		buffer_count--;
+		spin_unlock(&aa_buffers_lock);
+		return aa_buf->buffer;
+	}
+	if (in_atomic) {
+		/*
+		 * out of reserve buffers and in atomic context so increase
+		 * how many buffers to keep in reserve
+		 */
+		reserve_count++;
+		flags = GFP_ATOMIC;
+	}
+	spin_unlock(&aa_buffers_lock);
+
+	if (!in_atomic)
+		might_sleep();
+	aa_buf = kmalloc(aa_g_path_max, flags);
+	if (!aa_buf) {
+		if (try_again) {
+			try_again = false;
+			spin_lock(&aa_buffers_lock);
+			goto retry;
+		}
+		pr_warn_once("AppArmor: Failed to allocate a memory buffer.\n");
+		return NULL;
+	}
+	return aa_buf->buffer;
+}
+
+void aa_put_buffer(char *buf)
+{
+	union aa_buffer *aa_buf;
+	struct aa_local_cache *cache;
+
+	if (!buf)
+		return;
+	aa_buf = container_of(buf, union aa_buffer, buffer[0]);
+
+	cache = get_cpu_ptr(&aa_local_buffers);
+	if (!cache->hold) {
+		put_cpu_ptr(&aa_local_buffers);
+
+		if (spin_trylock(&aa_buffers_lock)) {
+			/* put back on global list */
+			list_add(&aa_buf->list, &aa_global_buffers);
+			buffer_count++;
+			spin_unlock(&aa_buffers_lock);
+			return;
+		}
+		/* contention on global list, fallback to percpu */
+		cache = get_cpu_ptr(&aa_local_buffers);
+		cache_hold_inc(&cache->hold);
+	}
+
+	/* cache in percpu list */
+	list_add(&aa_buf->list, &cache->head);
+	cache->count++;
+	put_cpu_ptr(&aa_local_buffers);
+}
+
+/*
+ * AppArmor init functions
+ */
+
+/**
+ * set_init_ctx - set a task context and profile on the first task.
+ *
+ * TODO: allow setting an alternate profile than unconfined
+ */
+static int __init set_init_ctx(void)
+{
+	struct cred *cred = (__force struct cred *)current->real_cred;
+
+	set_cred_label(cred, aa_get_label(ns_unconfined(root_ns)));
+
+	return 0;
+}
+
+static void destroy_buffers(void)
+{
+	union aa_buffer *aa_buf;
+
+	spin_lock(&aa_buffers_lock);
+	while (!list_empty(&aa_global_buffers)) {
+		aa_buf = list_first_entry(&aa_global_buffers, union aa_buffer,
+					 list);
+		list_del(&aa_buf->list);
+		spin_unlock(&aa_buffers_lock);
+		kfree(aa_buf);
+		spin_lock(&aa_buffers_lock);
+	}
+	spin_unlock(&aa_buffers_lock);
+}
+
+static int __init alloc_buffers(void)
+{
+	union aa_buffer *aa_buf;
+	int i, num;
+
+	/*
+	 * per cpu set of cached allocated buffers used to help reduce
+	 * lock contention
+	 */
+	for_each_possible_cpu(i) {
+		per_cpu(aa_local_buffers, i).hold = 0;
+		per_cpu(aa_local_buffers, i).count = 0;
+		INIT_LIST_HEAD(&per_cpu(aa_local_buffers, i).head);
+	}
+	/*
+	 * A function may require two buffers at once. Usually the buffers are
+	 * used for a short period of time and are shared. On UP kernel buffers
+	 * two should be enough, with more CPUs it is possible that more
+	 * buffers will be used simultaneously. The preallocated pool may grow.
+	 * This preallocation has also the side-effect that AppArmor will be
+	 * disabled early at boot if aa_g_path_max is extremely high.
+	 */
+	if (num_online_cpus() > 1)
+		num = 4 + RESERVE_COUNT;
+	else
+		num = 2 + RESERVE_COUNT;
+
+	for (i = 0; i < num; i++) {
+
+		aa_buf = kmalloc(aa_g_path_max, GFP_KERNEL |
+				 __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+		if (!aa_buf) {
+			destroy_buffers();
+			return -ENOMEM;
+		}
+		aa_put_buffer(aa_buf->buffer);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_SYSCTL
+static int apparmor_dointvec(const struct ctl_table *table, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (!aa_current_policy_admin_capable(NULL))
+		return -EPERM;
+	if (!apparmor_enabled)
+		return -EINVAL;
+
+	return proc_dointvec(table, write, buffer, lenp, ppos);
+}
+
+static const struct ctl_table apparmor_sysctl_table[] = {
+#ifdef CONFIG_USER_NS
+	{
+		.procname       = "unprivileged_userns_apparmor_policy",
+		.data           = &unprivileged_userns_apparmor_policy,
+		.maxlen         = sizeof(int),
+		.mode           = 0600,
+		.proc_handler   = apparmor_dointvec,
+	},
+#endif /* CONFIG_USER_NS */
+	{
+		.procname       = "apparmor_display_secid_mode",
+		.data           = &apparmor_display_secid_mode,
+		.maxlen         = sizeof(int),
+		.mode           = 0600,
+		.proc_handler   = apparmor_dointvec,
+	},
+	{
+		.procname       = "apparmor_restrict_unprivileged_unconfined",
+		.data           = &aa_unprivileged_unconfined_restricted,
+		.maxlen         = sizeof(int),
+		.mode           = 0600,
+		.proc_handler   = apparmor_dointvec,
+	},
+};
+
+static int __init apparmor_init_sysctl(void)
+{
+	return register_sysctl("kernel", apparmor_sysctl_table) ? 0 : -ENOMEM;
+}
+#else
+static inline int apparmor_init_sysctl(void)
+{
+	return 0;
+}
+#endif /* CONFIG_SYSCTL */
+
+
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK)
+static int __net_init apparmor_nf_register(struct net *net)
+{
+	return nf_register_net_hooks(net, apparmor_nf_ops,
+				    ARRAY_SIZE(apparmor_nf_ops));
+}
+
+static void __net_exit apparmor_nf_unregister(struct net *net)
+{
+	nf_unregister_net_hooks(net, apparmor_nf_ops,
+				ARRAY_SIZE(apparmor_nf_ops));
+}
+
+static struct pernet_operations apparmor_net_ops = {
+	.init = apparmor_nf_register,
+	.exit = apparmor_nf_unregister,
+};
+
+static int __init apparmor_nf_ip_init(void)
+{
+	int err;
+
+	if (!apparmor_enabled)
+		return 0;
+
+	err = register_pernet_subsys(&apparmor_net_ops);
+	if (err)
+		panic("Apparmor: register_pernet_subsys: error %d\n", err);
+
+	return 0;
+}
+#endif
+
+static const char nulldfa_src[] __aligned(8) = {
+	#include "nulldfa.in"
+};
+static struct aa_dfa *nulldfa __ro_after_init;
+
+static char stacksplitdfa_src[] __aligned(8) = {
+	#include "stacksplitdfa.in"
+};
+struct aa_dfa *stacksplitdfa __ro_after_init;
+struct aa_policydb *nullpdb __ro_after_init;
+
+static int __init aa_setup_dfa_engine(void)
+{
+	int error = -ENOMEM;
+
+	nullpdb = aa_alloc_pdb(GFP_KERNEL);
+	if (!nullpdb)
+		return -ENOMEM;
+
+	nulldfa = aa_dfa_unpack(nulldfa_src, sizeof(nulldfa_src),
+			    TO_ACCEPT1_FLAG(YYTD_DATA32) |
+			    TO_ACCEPT2_FLAG(YYTD_DATA32));
+	if (IS_ERR(nulldfa)) {
+		error = PTR_ERR(nulldfa);
+		nulldfa = NULL;
+		goto fail;
+	}
+	nullpdb->dfa = aa_get_dfa(nulldfa);
+	nullpdb->perms = kzalloc_objs(struct aa_perms, 2);
+	if (!nullpdb->perms)
+		goto fail;
+	nullpdb->size = 2;
+
+	stacksplitdfa = aa_dfa_unpack(stacksplitdfa_src,
+				      sizeof(stacksplitdfa_src),
+				      TO_ACCEPT1_FLAG(YYTD_DATA32) |
+				      TO_ACCEPT2_FLAG(YYTD_DATA32));
+	if (IS_ERR(stacksplitdfa)) {
+		error = PTR_ERR(stacksplitdfa);
+		goto fail;
+	}
+
+	return 0;
+
+fail:
+	aa_put_pdb(nullpdb);
+	aa_put_dfa(nulldfa);
+	nullpdb = NULL;
+	nulldfa = NULL;
+	stacksplitdfa = NULL;
+
+	return error;
+}
+
+static void __init aa_teardown_dfa_engine(void)
+{
+	aa_put_dfa(stacksplitdfa);
+	aa_put_dfa(nulldfa);
+	aa_put_pdb(nullpdb);
+	nullpdb = NULL;
+	stacksplitdfa = NULL;
+	nulldfa = NULL;
+}
+
+static int __init apparmor_init(void)
+{
+	int error;
+
+	error = aa_setup_dfa_engine();
+	if (error) {
+		AA_ERROR("Unable to setup dfa engine\n");
+		goto alloc_out;
+	}
+
+	error = aa_alloc_root_ns();
+	if (error) {
+		AA_ERROR("Unable to allocate default profile namespace\n");
+		goto alloc_out;
+	}
+
+	error = apparmor_init_sysctl();
+	if (error) {
+		AA_ERROR("Unable to register sysctls\n");
+		goto alloc_out;
+
+	}
+
+	error = alloc_buffers();
+	if (error) {
+		AA_ERROR("Unable to allocate work buffers\n");
+		goto alloc_out;
+	}
+
+	error = set_init_ctx();
+	if (error) {
+		AA_ERROR("Failed to set context on init task\n");
+		aa_free_root_ns();
+		goto buffers_out;
+	}
+	security_add_hooks(apparmor_hooks, ARRAY_SIZE(apparmor_hooks),
+				&apparmor_lsmid);
+
+	/* Inform the audit system that secctx is used */
+	audit_cfg_lsm(&apparmor_lsmid, AUDIT_CFG_LSM_SECCTX_SUBJECT);
+
+	/* Report that AppArmor successfully initialized */
+	apparmor_initialized = 1;
+	if (aa_g_profile_mode == APPARMOR_COMPLAIN)
+		aa_info_message("AppArmor initialized: complain mode enabled");
+	else if (aa_g_profile_mode == APPARMOR_KILL)
+		aa_info_message("AppArmor initialized: kill mode enabled");
+	else
+		aa_info_message("AppArmor initialized");
+
+	return error;
+
+buffers_out:
+	destroy_buffers();
+alloc_out:
+	aa_destroy_aafs();
+	aa_teardown_dfa_engine();
+
+	apparmor_enabled = false;
+	return error;
+}
+
+DEFINE_LSM(apparmor) = {
+	.id = &apparmor_lsmid,
+	.flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE,
+	.enabled = &apparmor_enabled,
+	.blobs = &apparmor_blob_sizes,
+	.init = apparmor_init,
+	.initcall_fs = aa_create_aafs,
+#if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK)
+	.initcall_device = apparmor_nf_ip_init,
+#endif
+#ifdef CONFIG_SECURITY_APPARMOR_HASH
+	.initcall_late = init_profile_hash,
+#endif
+};
diff --git a/security/apparmor/match.c b/security/apparmor/match.c
new file mode 100644
index 000000000..7713484f6
--- /dev/null
+++ b/security/apparmor/match.c
@@ -0,0 +1,835 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor dfa based regular expression matching engine
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2012 Canonical Ltd.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/err.h>
+#include <linux/kref.h>
+#include <linux/unaligned.h>
+
+#include "include/lib.h"
+#include "include/match.h"
+
+#define base_idx(X) ((X) & 0xffffff)
+
+/**
+ * unpack_table - unpack a dfa table (one of accept, default, base, next check)
+ * @blob: data to unpack (NOT NULL)
+ * @bsize: size of blob
+ *
+ * Returns: pointer to table else ERR_PTR on failure
+ *
+ * NOTE: must be freed by kvfree (not kfree)
+ */
+static struct table_header *unpack_table(const char *blob, size_t bsize)
+{
+	struct table_header *table = ERR_PTR(-EPROTO);
+	struct table_header th;
+	size_t tsize;
+
+	if (bsize < sizeof(struct table_header))
+		goto out;
+
+	/* loaded td_id's start at 1, subtract 1 now to avoid doing
+	 * it every time we use td_id as an index
+	 */
+	th.td_id = get_unaligned_be16(blob) - 1;
+	if (th.td_id > YYTD_ID_MAX)
+		goto out;
+	th.td_flags = get_unaligned_be16(blob + 2);
+	th.td_lolen = get_unaligned_be32(blob + 8);
+	blob += sizeof(struct table_header);
+
+	if (!(th.td_flags == YYTD_DATA16 || th.td_flags == YYTD_DATA32 ||
+	      th.td_flags == YYTD_DATA8))
+		goto out;
+
+	/* if we have a table it must have some entries */
+	if (th.td_lolen == 0)
+		goto out;
+	tsize = table_size(th.td_lolen, th.td_flags);
+	if (bsize < tsize)
+		goto out;
+
+	table = kvzalloc(tsize, GFP_KERNEL);
+	if (table) {
+		table->td_id = th.td_id;
+		table->td_flags = th.td_flags;
+		table->td_lolen = th.td_lolen;
+		if (th.td_flags == YYTD_DATA8)
+			memcpy(table->td_data, blob, th.td_lolen);
+		else if (th.td_flags == YYTD_DATA16)
+			UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
+				     u16, __be16, get_unaligned_be16);
+		else if (th.td_flags == YYTD_DATA32)
+			UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
+				     u32, __be32, get_unaligned_be32);
+		else {
+			kvfree(table);
+			table = ERR_PTR(-EPROTO);
+			goto out;
+		}
+		/* if table was vmalloced make sure the page tables are synced
+		 * before it is used, as it goes live to all cpus.
+		 */
+		if (is_vmalloc_addr(table))
+			vm_unmap_aliases();
+	} else
+		table = ERR_PTR(-ENOMEM);
+
+out:
+	return table;
+}
+
+/**
+ * verify_table_headers - verify that the tables headers are as expected
+ * @tables: array of dfa tables to check (NOT NULL)
+ * @flags: flags controlling what type of accept table are acceptable
+ *
+ * Assumes dfa has gone through the first pass verification done by unpacking
+ * NOTE: this does not valid accept table values
+ *
+ * Returns: %0 else error code on failure to verify
+ */
+static int verify_table_headers(struct table_header **tables, int flags)
+{
+	size_t state_count, trans_count;
+	int error = -EPROTO;
+
+	/* check that required tables exist */
+	if (!(tables[YYTD_ID_DEF] && tables[YYTD_ID_BASE] &&
+	      tables[YYTD_ID_NXT] && tables[YYTD_ID_CHK]))
+		goto out;
+
+	/* accept.size == default.size == base.size */
+	state_count = tables[YYTD_ID_BASE]->td_lolen;
+	if (ACCEPT1_FLAGS(flags)) {
+		if (!tables[YYTD_ID_ACCEPT])
+			goto out;
+		if (state_count != tables[YYTD_ID_ACCEPT]->td_lolen)
+			goto out;
+	}
+	if (ACCEPT2_FLAGS(flags)) {
+		if (!tables[YYTD_ID_ACCEPT2])
+			goto out;
+		if (state_count != tables[YYTD_ID_ACCEPT2]->td_lolen)
+			goto out;
+	}
+	if (state_count != tables[YYTD_ID_DEF]->td_lolen)
+		goto out;
+
+	/* next.size == chk.size */
+	trans_count = tables[YYTD_ID_NXT]->td_lolen;
+	if (trans_count != tables[YYTD_ID_CHK]->td_lolen)
+		goto out;
+
+	/* if equivalence classes then its table size must be 256 */
+	if (tables[YYTD_ID_EC] && tables[YYTD_ID_EC]->td_lolen != 256)
+		goto out;
+
+	error = 0;
+out:
+	return error;
+}
+
+/**
+ * verify_dfa - verify that transitions and states in the tables are in bounds.
+ * @dfa: dfa to test  (NOT NULL)
+ *
+ * Assumes dfa has gone through the first pass verification done by unpacking
+ * NOTE: this does not valid accept table values
+ *
+ * Returns: %0 else error code on failure to verify
+ */
+static int verify_dfa(const struct aa_dfa *dfa)
+{
+	size_t i, state_count, trans_count;
+	int error = -EPROTO;
+
+	state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
+	trans_count = dfa->tables[YYTD_ID_NXT]->td_lolen;
+	if (state_count < 2)
+		goto out;
+	for (i = 0; i < state_count; i++) {
+		if (DEFAULT_TABLE(dfa)[i] >= state_count) {
+			pr_err("AppArmor DFA default state out of bounds");
+			goto out;
+		}
+		if (BASE_TABLE(dfa)[i] & MATCH_FLAGS_INVALID) {
+			pr_err("AppArmor DFA state with invalid match flags");
+			goto out;
+		}
+		if ((BASE_TABLE(dfa)[i] & MATCH_FLAG_DIFF_ENCODE)) {
+			if (!(dfa->flags & YYTH_FLAG_DIFF_ENCODE)) {
+				pr_err("AppArmor DFA diff encoded transition state without header flag");
+				goto out;
+			}
+		}
+		if ((BASE_TABLE(dfa)[i] & MATCH_FLAG_OOB_TRANSITION)) {
+			if (base_idx(BASE_TABLE(dfa)[i]) < dfa->max_oob) {
+				pr_err("AppArmor DFA out of bad transition out of range");
+				goto out;
+			}
+			if (!(dfa->flags & YYTH_FLAG_OOB_TRANS)) {
+				pr_err("AppArmor DFA out of bad transition state without header flag");
+				goto out;
+			}
+		}
+		if (base_idx(BASE_TABLE(dfa)[i]) + 255 >= trans_count) {
+			pr_err("AppArmor DFA next/check upper bounds error\n");
+			goto out;
+		}
+	}
+
+	for (i = 0; i < trans_count; i++) {
+		if (NEXT_TABLE(dfa)[i] >= state_count)
+			goto out;
+		if (CHECK_TABLE(dfa)[i] >= state_count)
+			goto out;
+	}
+
+	/* Now that all the other tables are verified, verify diffencoding */
+	for (i = 0; i < state_count; i++) {
+		size_t j, k;
+
+		for (j = i;
+		     ((BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE) &&
+		      !(BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE_VERIFIED));
+		     j = k) {
+			if (BASE_TABLE(dfa)[j] & MARK_DIFF_ENCODE)
+				/* loop in current chain */
+				goto out;
+			k = DEFAULT_TABLE(dfa)[j];
+			if (j == k)
+				/* self loop */
+				goto out;
+			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE;
+		}
+		/* move mark to verified */
+		for (j = i;
+		     (BASE_TABLE(dfa)[j] & MATCH_FLAG_DIFF_ENCODE);
+		     j = k) {
+			k = DEFAULT_TABLE(dfa)[j];
+			if (j < i)
+				/* jumps to state/chain that has been
+				 * verified
+				 */
+				break;
+			BASE_TABLE(dfa)[j] &= ~MARK_DIFF_ENCODE;
+			BASE_TABLE(dfa)[j] |= MARK_DIFF_ENCODE_VERIFIED;
+		}
+	}
+	error = 0;
+
+out:
+	return error;
+}
+
+/**
+ * dfa_free - free a dfa allocated by aa_dfa_unpack
+ * @dfa: the dfa to free  (MAYBE NULL)
+ *
+ * Requires: reference count to dfa == 0
+ */
+static void dfa_free(struct aa_dfa *dfa)
+{
+	if (dfa) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(dfa->tables); i++) {
+			kvfree(dfa->tables[i]);
+			dfa->tables[i] = NULL;
+		}
+		kfree(dfa);
+	}
+}
+
+/**
+ * aa_dfa_free_kref - free aa_dfa by kref (called by aa_put_dfa)
+ * @kref: kref callback for freeing of a dfa  (NOT NULL)
+ */
+void aa_dfa_free_kref(struct kref *kref)
+{
+	struct aa_dfa *dfa = container_of(kref, struct aa_dfa, count);
+	dfa_free(dfa);
+}
+
+
+
+/**
+ * remap_data16_to_data32 - remap u16 @old table to a u32 based table
+ * @old: table to remap
+ *
+ * Returns: new table with u32 entries instead of u16.
+ *
+ * Note: will free @old so caller does not have to
+ */
+static struct table_header *remap_data16_to_data32(struct table_header *old)
+{
+	struct table_header *new;
+	size_t tsize;
+	u32 i;
+
+	tsize = table_size(old->td_lolen, YYTD_DATA32);
+	new = kvzalloc(tsize, GFP_KERNEL);
+	if (!new) {
+		kvfree(old);
+		return NULL;
+	}
+	new->td_id = old->td_id;
+	new->td_flags = YYTD_DATA32;
+	new->td_lolen = old->td_lolen;
+
+	for (i = 0; i < old->td_lolen; i++)
+		TABLE_DATAU32(new)[i] = (u32) TABLE_DATAU16(old)[i];
+
+	kvfree(old);
+	if (is_vmalloc_addr(new))
+		vm_unmap_aliases();
+
+	return new;
+}
+
+/**
+ * aa_dfa_unpack - unpack the binary tables of a serialized dfa
+ * @blob: aligned serialized stream of data to unpack  (NOT NULL)
+ * @size: size of data to unpack
+ * @flags: flags controlling what type of accept tables are acceptable
+ *
+ * Unpack a dfa that has been serialized.  To find information on the dfa
+ * format look in Documentation/admin-guide/LSM/apparmor.rst
+ * Assumes the dfa @blob stream has been aligned on a 8 byte boundary
+ *
+ * Returns: an unpacked dfa ready for matching or ERR_PTR on failure
+ */
+struct aa_dfa *aa_dfa_unpack(const void *blob, size_t size, int flags)
+{
+	int hsize;
+	int error = -ENOMEM;
+	const char *data = blob;
+	struct table_header *table = NULL;
+	struct aa_dfa *dfa = kzalloc_obj(struct aa_dfa);
+	if (!dfa)
+		goto fail;
+
+	kref_init(&dfa->count);
+
+	error = -EPROTO;
+
+	/* get dfa table set header */
+	if (size < sizeof(struct table_set_header))
+		goto fail;
+
+	if (get_unaligned_be32(data) != YYTH_MAGIC)
+		goto fail;
+
+	hsize = get_unaligned_be32(data + 4);
+	if (size < hsize)
+		goto fail;
+
+	dfa->flags = get_unaligned_be16(data + 12);
+	if (dfa->flags & ~(YYTH_FLAGS))
+		goto fail;
+
+	/*
+	 * TODO: needed for dfa to support more than 1 oob
+	 * if (dfa->flags & YYTH_FLAGS_OOB_TRANS) {
+	 *	if (hsize < 16 + 4)
+	 *		goto fail;
+	 *	dfa->max_oob = get_unaligned_be32(data + 16);
+	 *	if (dfa->max <= MAX_OOB_SUPPORTED) {
+	 *		pr_err("AppArmor DFA OOB greater than supported\n");
+	 *		goto fail;
+	 *	}
+	 * }
+	 */
+	dfa->max_oob = 1;
+
+	data += hsize;
+	size -= hsize;
+
+	while (size > 0) {
+		table = unpack_table(data, size);
+		if (IS_ERR(table)) {
+			error = PTR_ERR(table);
+			table = NULL;
+			goto fail;
+		}
+
+		switch (table->td_id) {
+		case YYTD_ID_ACCEPT:
+			if (!(table->td_flags & ACCEPT1_FLAGS(flags)))
+				goto fail;
+			break;
+		case YYTD_ID_ACCEPT2:
+			if (!(table->td_flags & ACCEPT2_FLAGS(flags)))
+				goto fail;
+			break;
+		case YYTD_ID_BASE:
+			if (table->td_flags != YYTD_DATA32)
+				goto fail;
+			break;
+		case YYTD_ID_DEF:
+		case YYTD_ID_NXT:
+		case YYTD_ID_CHK:
+			if (!(table->td_flags == YYTD_DATA16 ||
+			      table->td_flags == YYTD_DATA32)) {
+				goto fail;
+			}
+			break;
+		case YYTD_ID_EC:
+			if (table->td_flags != YYTD_DATA8)
+				goto fail;
+			break;
+		default:
+			goto fail;
+		}
+		/* check for duplicate table entry */
+		if (dfa->tables[table->td_id])
+			goto fail;
+		dfa->tables[table->td_id] = table;
+		data += table_size(table->td_lolen, table->td_flags);
+		size -= table_size(table->td_lolen, table->td_flags);
+
+		/*
+		 * this remapping has to be done after incrementing data above
+		 * for now straight remap, later have dfa support both
+		 */
+		switch (table->td_id) {
+		case YYTD_ID_DEF:
+		case YYTD_ID_NXT:
+		case YYTD_ID_CHK:
+			if (table->td_flags == YYTD_DATA16) {
+				table = remap_data16_to_data32(table);
+				if (!table)
+					goto fail;
+			}
+			dfa->tables[table->td_id] = table;
+			break;
+		}
+		table = NULL;
+	}
+	error = verify_table_headers(dfa->tables, flags);
+	if (error)
+		goto fail;
+
+	if (flags & DFA_FLAG_VERIFY_STATES) {
+		error = verify_dfa(dfa);
+		if (error)
+			goto fail;
+	}
+
+	return dfa;
+
+fail:
+	kvfree(table);
+	dfa_free(dfa);
+	return ERR_PTR(error);
+}
+
+#define match_char(state, def, base, next, check, C)	\
+do {							\
+	u32 b = (base)[(state)];			\
+	unsigned int pos = base_idx(b) + (C);		\
+	if ((check)[pos] != (state)) {			\
+		(state) = (def)[(state)];		\
+		if (b & MATCH_FLAG_DIFF_ENCODE)		\
+			continue;			\
+		break;					\
+	}						\
+	(state) = (next)[pos];				\
+	break;						\
+} while (1)
+
+/**
+ * aa_dfa_match_len - traverse @dfa to find state @str stops at
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the string of bytes to match against the dfa  (NOT NULL)
+ * @len: length of the string of bytes to match
+ *
+ * aa_dfa_match_len will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * This function will happily match again the 0 byte and only finishes
+ * when @len input is consumed.
+ *
+ * Returns: final state reached after input is consumed
+ */
+aa_state_t aa_dfa_match_len(const struct aa_dfa *dfa, aa_state_t start,
+			    const char *str, int len)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	aa_state_t state = start;
+
+	if (state == DFA_NOMATCH)
+		return DFA_NOMATCH;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		for (; len; len--) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
+	} else {
+		/* default is direct to next state */
+		for (; len; len--) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
+	}
+
+	return state;
+}
+
+/**
+ * aa_dfa_match - traverse @dfa to find state @str stops at
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the null terminated string of bytes to match against the dfa (NOT NULL)
+ *
+ * aa_dfa_match will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * Returns: final state reached after input is consumed
+ */
+aa_state_t aa_dfa_match(const struct aa_dfa *dfa, aa_state_t start,
+			const char *str)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	aa_state_t state = start;
+
+	if (state == DFA_NOMATCH)
+		return DFA_NOMATCH;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		while (*str) {
+			u8 c = equiv[(u8) *str];
+
+			match_char(state, def, base, next, check, c);
+			str++;
+		}
+	} else {
+		/* default is direct to next state */
+		while (*str) {
+			match_char(state, def, base, next, check, (u8) *str);
+			str++;
+		}
+	}
+
+	return state;
+}
+
+/**
+ * aa_dfa_next - step one character to the next state in the dfa
+ * @dfa: the dfa to traverse (NOT NULL)
+ * @state: the state to start in
+ * @c: the input character to transition on
+ *
+ * aa_dfa_match will step through the dfa by one input character @c
+ *
+ * Returns: state reach after input @c
+ */
+aa_state_t aa_dfa_next(const struct aa_dfa *dfa, aa_state_t state,
+		       const char c)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		match_char(state, def, base, next, check, equiv[(u8) c]);
+	} else
+		match_char(state, def, base, next, check, (u8) c);
+
+	return state;
+}
+
+aa_state_t aa_dfa_outofband_transition(const struct aa_dfa *dfa,
+				       aa_state_t state)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	u32 b = (base)[(state)];
+
+	if (!(b & MATCH_FLAG_OOB_TRANSITION))
+		return DFA_NOMATCH;
+
+	/* No Equivalence class remapping for outofband transitions */
+	match_char(state, def, base, next, check, -1);
+
+	return state;
+}
+
+/**
+ * aa_dfa_match_until - traverse @dfa until accept state or end of input
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the null terminated string of bytes to match against the dfa (NOT NULL)
+ * @retpos: first character in str after match OR end of string
+ *
+ * aa_dfa_match will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * Returns: final state reached after input is consumed
+ */
+aa_state_t aa_dfa_match_until(const struct aa_dfa *dfa, aa_state_t start,
+			      const char *str, const char **retpos)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	u32 *accept = ACCEPT_TABLE(dfa);
+	aa_state_t state = start, pos;
+
+	if (state == DFA_NOMATCH)
+		return DFA_NOMATCH;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		while (*str) {
+			pos = base_idx(base[state]) + equiv[(u8) *str++];
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (accept[state])
+				break;
+		}
+	} else {
+		/* default is direct to next state */
+		while (*str) {
+			pos = base_idx(base[state]) + (u8) *str++;
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (accept[state])
+				break;
+		}
+	}
+
+	*retpos = str;
+	return state;
+}
+
+/**
+ * aa_dfa_matchn_until - traverse @dfa until accept or @n bytes consumed
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the string of bytes to match against the dfa  (NOT NULL)
+ * @n: length of the string of bytes to match
+ * @retpos: first character in str after match OR str + n
+ *
+ * aa_dfa_match_len will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * This function will happily match again the 0 byte and only finishes
+ * when @n input is consumed.
+ *
+ * Returns: final state reached after input is consumed
+ */
+aa_state_t aa_dfa_matchn_until(const struct aa_dfa *dfa, aa_state_t start,
+			       const char *str, int n, const char **retpos)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	u32 *accept = ACCEPT_TABLE(dfa);
+	aa_state_t state = start, pos;
+
+	*retpos = NULL;
+	if (state == DFA_NOMATCH)
+		return DFA_NOMATCH;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		for (; n; n--) {
+			pos = base_idx(base[state]) + equiv[(u8) *str++];
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (accept[state])
+				break;
+		}
+	} else {
+		/* default is direct to next state */
+		for (; n; n--) {
+			pos = base_idx(base[state]) + (u8) *str++;
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (accept[state])
+				break;
+		}
+	}
+
+	*retpos = str;
+	return state;
+}
+
+#define inc_wb_pos(wb)							\
+do {									\
+	BUILD_BUG_ON_NOT_POWER_OF_2(WB_HISTORY_SIZE);			\
+	wb->pos = (wb->pos + 1) & (WB_HISTORY_SIZE - 1);		\
+	wb->len = (wb->len + 1) > WB_HISTORY_SIZE ? WB_HISTORY_SIZE :	\
+				wb->len + 1;				\
+} while (0)
+
+/* For DFAs that don't support extended tagging of states */
+/* adjust is only set if is_loop returns true */
+static bool is_loop(struct match_workbuf *wb, aa_state_t state,
+		    unsigned int *adjust)
+{
+	int pos = wb->pos;
+	int i;
+
+	if (wb->history[pos] < state)
+		return false;
+
+	for (i = 0; i < wb->len; i++) {
+		if (wb->history[pos] == state) {
+			*adjust = i;
+			return true;
+		}
+		/* -1 wraps to WB_HISTORY_SIZE - 1 */
+		pos = (pos - 1) & (WB_HISTORY_SIZE - 1);
+	}
+
+	return false;
+}
+
+static aa_state_t leftmatch_fb(const struct aa_dfa *dfa, aa_state_t start,
+			       const char *str, struct match_workbuf *wb,
+			       unsigned int *count)
+{
+	u32 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u32 *next = NEXT_TABLE(dfa);
+	u32 *check = CHECK_TABLE(dfa);
+	aa_state_t state = start, pos;
+
+	AA_BUG(!dfa);
+	AA_BUG(!str);
+	AA_BUG(!wb);
+	AA_BUG(!count);
+
+	*count = 0;
+	if (state == DFA_NOMATCH)
+		return DFA_NOMATCH;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		while (*str) {
+			unsigned int adjust;
+
+			wb->history[wb->pos] = state;
+			pos = base_idx(base[state]) + equiv[(u8) *str++];
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (is_loop(wb, state, &adjust)) {
+				state = aa_dfa_match(dfa, state, str);
+				*count -= adjust;
+				goto out;
+			}
+			inc_wb_pos(wb);
+			(*count)++;
+		}
+	} else {
+		/* default is direct to next state */
+		while (*str) {
+			unsigned int adjust;
+
+			wb->history[wb->pos] = state;
+			pos = base_idx(base[state]) + (u8) *str++;
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+			if (is_loop(wb, state, &adjust)) {
+				state = aa_dfa_match(dfa, state, str);
+				*count -= adjust;
+				goto out;
+			}
+			inc_wb_pos(wb);
+			(*count)++;
+		}
+	}
+
+out:
+	if (!state)
+		*count = 0;
+	return state;
+}
+
+/**
+ * aa_dfa_leftmatch - traverse @dfa to find state @str stops at
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the null terminated string of bytes to match against the dfa (NOT NULL)
+ * @count: current count of longest left.
+ *
+ * aa_dfa_match will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * Returns: final state reached after input is consumed
+ */
+aa_state_t aa_dfa_leftmatch(const struct aa_dfa *dfa, aa_state_t start,
+			    const char *str, unsigned int *count)
+{
+	DEFINE_MATCH_WB(wb);
+
+	/* TODO: match for extended state dfas */
+
+	return leftmatch_fb(dfa, start, str, &wb, count);
+}
diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c
new file mode 100644
index 000000000..4ed7b9136
--- /dev/null
+++ b/security/apparmor/mount.c
@@ -0,0 +1,709 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <uapi/linux/mount.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/mount.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+
+#define DEFINE_AUDIT_MOUNT(NAME, OP, CRED)				\
+	DEFINE_AUDIT_DATA(NAME, LSM_AUDIT_DATA_NONE, AA_CLASS_MOUNT, OP);\
+	NAME.subj_cred = (CRED)
+
+static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags)
+{
+	if (flags & MS_RDONLY)
+		audit_log_format(ab, "ro");
+	else
+		audit_log_format(ab, "rw");
+	if (flags & MS_NOSUID)
+		audit_log_format(ab, ", nosuid");
+	if (flags & MS_NODEV)
+		audit_log_format(ab, ", nodev");
+	if (flags & MS_NOEXEC)
+		audit_log_format(ab, ", noexec");
+	if (flags & MS_SYNCHRONOUS)
+		audit_log_format(ab, ", sync");
+	if (flags & MS_REMOUNT)
+		audit_log_format(ab, ", remount");
+	if (flags & MS_MANDLOCK)
+		audit_log_format(ab, ", mand");
+	if (flags & MS_DIRSYNC)
+		audit_log_format(ab, ", dirsync");
+	if (flags & MS_NOSYMFOLLOW)
+		audit_log_format(ab, ", nosymfollow");
+	if (flags & MS_NOATIME)
+		audit_log_format(ab, ", noatime");
+	if (flags & MS_NODIRATIME)
+		audit_log_format(ab, ", nodiratime");
+	if (flags & MS_BIND)
+		audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind");
+	if (flags & MS_MOVE)
+		audit_log_format(ab, ", move");
+	if (flags & MS_SILENT)
+		audit_log_format(ab, ", silent");
+	if (flags & MS_POSIXACL)
+		audit_log_format(ab, ", acl");
+	if (flags & MS_UNBINDABLE)
+		audit_log_format(ab, flags & MS_REC ? ", runbindable" :
+				 ", unbindable");
+	if (flags & MS_PRIVATE)
+		audit_log_format(ab, flags & MS_REC ? ", rprivate" :
+				 ", private");
+	if (flags & MS_SLAVE)
+		audit_log_format(ab, flags & MS_REC ? ", rslave" :
+				 ", slave");
+	if (flags & MS_SHARED)
+		audit_log_format(ab, flags & MS_REC ? ", rshared" :
+				 ", shared");
+	if (flags & MS_RELATIME)
+		audit_log_format(ab, ", relatime");
+	if (flags & MS_I_VERSION)
+		audit_log_format(ab, ", iversion");
+	if (flags & MS_STRICTATIME)
+		audit_log_format(ab, ", strictatime");
+	if (flags & MS_NOUSER)
+		audit_log_format(ab, ", nouser");
+}
+
+/**
+ * audit_cb - call back for mount specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (ad->mnt.type) {
+		audit_log_format(ab, " fstype=");
+		audit_log_untrustedstring(ab, ad->mnt.type);
+	}
+	if (ad->mnt.src_name) {
+		audit_log_format(ab, " srcname=");
+		audit_log_untrustedstring(ab, ad->mnt.src_name);
+	}
+	if (ad->mnt.trans) {
+		audit_log_format(ab, " trans=");
+		audit_log_untrustedstring(ab, ad->mnt.trans);
+	}
+	if (ad->mnt.flags) {
+		audit_log_format(ab, " flags=\"");
+		audit_mnt_flags(ab, ad->mnt.flags);
+		audit_log_format(ab, "\"");
+	}
+	if (ad->mnt.data) {
+		audit_log_format(ab, " options=");
+		audit_log_untrustedstring(ab, ad->mnt.data);
+	}
+}
+
+/**
+ * match_mnt_flags - Do an ordered match on mount flags
+ * @dfa: dfa to match against
+ * @state: state to start in
+ * @flags: mount flags to match against
+ *
+ * Mount flags are encoded as an ordered match. This is done instead of
+ * checking against a simple bitmask, to allow for logical operations
+ * on the flags.
+ *
+ * Returns: next state after flags match
+ */
+static aa_state_t match_mnt_flags(const struct aa_dfa *dfa, aa_state_t state,
+				    unsigned long flags)
+{
+	unsigned int i;
+
+	for (i = 0; i <= 31 ; ++i) {
+		if ((1 << i) & flags)
+			state = aa_dfa_next(dfa, state, i + 1);
+	}
+
+	return state;
+}
+
+static const char * const mnt_info_table[] = {
+	"match succeeded",
+	"failed mntpnt match",
+	"failed srcname match",
+	"failed type match",
+	"failed flags match",
+	"failed data match",
+	"failed perms check"
+};
+
+/*
+ * Returns 0 on success else element that match failed in, this is the
+ * index into the mnt_info_table above
+ */
+static int do_match_mnt(struct aa_policydb *policy, aa_state_t start,
+			const char *mntpnt, const char *devname,
+			const char *type, unsigned long flags,
+			void *data, bool binary, struct aa_perms *perms)
+{
+	aa_state_t state;
+
+	AA_BUG(!policy);
+	AA_BUG(!policy->dfa);
+	AA_BUG(!policy->perms);
+	AA_BUG(!perms);
+
+	state = aa_dfa_match(policy->dfa, start, mntpnt);
+	state = aa_dfa_null_transition(policy->dfa, state);
+	if (!state)
+		return 1;
+
+	if (devname)
+		state = aa_dfa_match(policy->dfa, state, devname);
+	state = aa_dfa_null_transition(policy->dfa, state);
+	if (!state)
+		return 2;
+
+	if (type)
+		state = aa_dfa_match(policy->dfa, state, type);
+	state = aa_dfa_null_transition(policy->dfa, state);
+	if (!state)
+		return 3;
+
+	state = match_mnt_flags(policy->dfa, state, flags);
+	if (!state)
+		return 4;
+	*perms = *aa_lookup_perms(policy, state);
+	if (perms->allow & AA_MAY_MOUNT)
+		return 0;
+
+	/* only match data if not binary and the DFA flags data is expected */
+	if (data && !binary && (perms->allow & AA_MNT_CONT_MATCH)) {
+		state = aa_dfa_null_transition(policy->dfa, state);
+		if (!state)
+			return 4;
+
+		state = aa_dfa_match(policy->dfa, state, data);
+		if (!state)
+			return 5;
+		*perms = *aa_lookup_perms(policy, state);
+		if (perms->allow & AA_MAY_MOUNT)
+			return 0;
+	}
+
+	/* failed at perms check, don't confuse with flags match */
+	return 6;
+}
+
+
+static int path_flags(const struct aa_profile *profile, const struct path *path)
+{
+	AA_BUG(!profile);
+	AA_BUG(!path);
+
+	return profile->path_flags |
+		(S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0);
+}
+
+/**
+ * match_mnt_path_str - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devname: string for the devname/src_name (MAY BE NULL OR ERRPTR)
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ * @devinfo: error str if (IS_ERR(@devname))
+ * @ad: apparmor audit data structure
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt_path_str(struct aa_profile *profile,
+			      const struct path *mntpath, char *buffer,
+			      const char *devname, const char *type,
+			      unsigned long flags, void *data, bool binary,
+			      const char *devinfo,
+			      struct apparmor_audit_data *ad)
+{
+	struct aa_perms perms = { };
+	const char *mntpnt = NULL;
+	struct aa_ruleset *rules = profile->label.rules[0];
+	int pos, error;
+
+	AA_BUG(!profile);
+	AA_BUG(!mntpath);
+	AA_BUG(!buffer);
+
+	if (!RULE_MEDIATES(rules, AA_CLASS_MOUNT))
+		return 0;
+
+	ad->mnt.type = type;
+
+	error = aa_path_name(mntpath, path_flags(profile, mntpath), buffer,
+			     &mntpnt, &ad->info, profile->disconnected);
+	if (error)
+		return aa_audit_perm_error(&profile->label, AA_MAY_MOUNT,
+					   error, ad, audit_cb);
+	ad->name = mntpnt;
+
+	if (IS_ERR(devname)) {
+		error = PTR_ERR(devname);
+		ad->info = devinfo;
+		return aa_audit_perm_error(&profile->label, AA_MAY_MOUNT,
+					   error, ad, audit_cb);
+	}
+	ad->mnt.src_name = devname;
+
+	pos = do_match_mnt(rules->policy,
+			   rules->policy->start[AA_CLASS_MOUNT],
+			   mntpnt, devname, type, flags, data, binary, &perms);
+	if (pos)
+		ad->info = mnt_info_table[pos];
+
+	aa_apply_modes_to_perms(profile, &perms);
+	if (data && !binary && (perms.audit & AA_AUDIT_DATA))
+		ad->mnt.data = data;
+	return aa_check_perms(profile, &perms, AA_MAY_MOUNT, ad, audit_cb);
+}
+
+/**
+ * match_mnt - handle path matching for mount
+ * @profile: the confining profile
+ * @path: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devpath: path devname/src_name (MAYBE NULL)
+ * @devbuffer: buffer to be used to lookup devname/src_name
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ * @ad: apparmor audit data structure
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt(struct aa_profile *profile, const struct path *path,
+		     char *buffer, const struct path *devpath, char *devbuffer,
+		     const char *type, unsigned long flags, void *data,
+		     bool binary, struct apparmor_audit_data *ad)
+{
+	const char *devname = NULL, *info = NULL;
+	struct aa_ruleset *rules = profile->label.rules[0];
+	int error = -EACCES;
+
+	AA_BUG(!profile);
+	AA_BUG(devpath && !devbuffer);
+
+	if (!RULE_MEDIATES(rules, AA_CLASS_MOUNT))
+		return 0;
+
+	if (devpath) {
+		error = aa_path_name(devpath, path_flags(profile, devpath),
+				     devbuffer, &devname, &info,
+				     profile->disconnected);
+		if (error)
+			devname = ERR_PTR(error);
+	}
+
+	return match_mnt_path_str(profile, path, buffer, devname,
+				  type, flags, data, binary, info, ad);
+}
+
+int aa_remount(const struct cred *subj_cred,
+	       struct aa_label *label, const struct path *path,
+	       unsigned long flags, void *data)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	bool binary;
+	int error;
+	DEFINE_AUDIT_MOUNT(ad, OP_MOUNT, subj_cred);
+	ad.mnt.flags = flags;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA;
+
+	buffer = aa_get_buffer(false);
+	if (!buffer)
+		return -ENOMEM;
+	error = fn_for_each(label, profile,
+			match_mnt(profile, path, buffer, NULL, NULL, NULL,
+				  flags, data, binary, &ad));
+	aa_put_buffer(buffer);
+
+	return error;
+}
+
+int aa_bind_mount(const struct cred *subj_cred,
+		  struct aa_label *label, const struct path *path,
+		  const char *dev_name, unsigned long flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL, *old_buffer = NULL;
+	struct path old_path;
+	int error;
+	DEFINE_AUDIT_MOUNT(ad, OP_MOUNT, subj_cred);
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (!dev_name || !*dev_name)
+		return -EINVAL;
+
+	flags &= MS_REC | MS_BIND;
+	ad.mnt.flags = flags;
+
+	error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
+	if (error)
+		return aa_audit_perm_error(label, AA_MAY_MOUNT, error, &ad,
+			audit_cb);
+
+	buffer = aa_get_buffer(false);
+	old_buffer = aa_get_buffer(false);
+	error = -ENOMEM;
+	if (!buffer || !old_buffer)
+		goto out;
+
+	error = fn_for_each(label, profile,
+			match_mnt(profile, path, buffer, &old_path,
+				  old_buffer, NULL, flags, NULL, false, &ad));
+out:
+	aa_put_buffer(buffer);
+	aa_put_buffer(old_buffer);
+	path_put(&old_path);
+
+	return error;
+}
+
+int aa_mount_change_type(const struct cred *subj_cred,
+			 struct aa_label *label, const struct path *path,
+			 unsigned long flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	int error;
+	DEFINE_AUDIT_MOUNT(ad, OP_MOUNT, subj_cred);
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	/* These are the flags allowed by do_change_type() */
+	flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE |
+		  MS_UNBINDABLE);
+	ad.mnt.flags = flags;
+
+	buffer = aa_get_buffer(false);
+	if (!buffer)
+		return -ENOMEM;
+	error = fn_for_each(label, profile,
+			match_mnt(profile, path, buffer, NULL, NULL, NULL,
+				  flags, NULL, false, &ad));
+	aa_put_buffer(buffer);
+
+	return error;
+}
+
+int aa_move_mount(const struct cred *subj_cred,
+		  struct aa_label *label, const struct path *from_path,
+		  const struct path *to_path)
+{
+	struct aa_profile *profile;
+	char *to_buffer = NULL, *from_buffer = NULL;
+	int error;
+	DEFINE_AUDIT_MOUNT(ad, OP_MOUNT, subj_cred);
+	ad.mnt.flags = MS_MOVE;
+
+	AA_BUG(!label);
+	AA_BUG(!from_path);
+	AA_BUG(!to_path);
+
+	to_buffer = aa_get_buffer(false);
+	from_buffer = aa_get_buffer(false);
+	error = -ENOMEM;
+	if (!to_buffer || !from_buffer)
+		goto out;
+
+	if (!our_mnt(from_path->mnt))
+		/* moving a mount detached from the namespace */
+		from_path = NULL;
+	error = fn_for_each(label, profile,
+			match_mnt(profile, to_path, to_buffer, from_path,
+				  from_buffer, NULL, MS_MOVE, NULL, false,
+				  &ad));
+out:
+	aa_put_buffer(to_buffer);
+	aa_put_buffer(from_buffer);
+
+	return error;
+}
+
+int aa_move_mount_old(const struct cred *subj_cred, struct aa_label *label,
+		      const struct path *path, const char *orig_name)
+{
+	struct path old_path;
+	int error;
+
+	if (!orig_name || !*orig_name)
+		return -EINVAL;
+	error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path);
+	if (error)
+		return error;
+
+	error = aa_move_mount(subj_cred, label, &old_path, path);
+	path_put(&old_path);
+
+	return error;
+}
+
+int aa_new_mount(const struct cred *subj_cred, struct aa_label *label,
+		 const char *dev_name, const struct path *path,
+		 const char *type, unsigned long flags, void *data)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL, *dev_buffer = NULL;
+	bool binary = true;
+	int error;
+	int requires_dev = 0;
+	struct path tmp_path, *dev_path = NULL;
+	DEFINE_AUDIT_MOUNT(ad, OP_MOUNT, subj_cred);
+	ad.mnt.flags = flags;
+
+	AA_BUG(!label);
+	AA_BUG(!path);
+
+	if (type) {
+		struct file_system_type *fstype;
+
+		fstype = get_fs_type(type);
+		if (!fstype)
+			return -ENODEV;
+		binary = fstype->fs_flags & FS_BINARY_MOUNTDATA;
+		requires_dev = fstype->fs_flags & FS_REQUIRES_DEV;
+		put_filesystem(fstype);
+
+		if (requires_dev) {
+			if (!dev_name || !*dev_name)
+				return -ENOENT;
+
+			error = kern_path(dev_name, LOOKUP_FOLLOW, &tmp_path);
+			if (error)
+				return error;
+			dev_path = &tmp_path;
+		}
+	}
+
+	buffer = aa_get_buffer(false);
+	if (!buffer) {
+		error = -ENOMEM;
+		goto out;
+	}
+	if (dev_path) {
+		dev_buffer = aa_get_buffer(false);
+		if (!dev_buffer) {
+			error = -ENOMEM;
+			goto out;
+		}
+		error = fn_for_each(label, profile,
+				match_mnt(profile, path, buffer, dev_path,
+					  dev_buffer, type, flags, data,
+					  binary, &ad));
+	} else {
+		error = fn_for_each(label, profile,
+				match_mnt_path_str(profile, path, buffer,
+						   dev_name, type, flags, data,
+						   binary, NULL, &ad));
+	}
+
+out:
+	aa_put_buffer(buffer);
+	aa_put_buffer(dev_buffer);
+	if (dev_path)
+		path_put(dev_path);
+
+	return error;
+}
+
+static int profile_umount(struct aa_profile *profile, const struct path *path,
+			  char *buffer, struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms perms = { };
+	const char *name = NULL;
+	aa_state_t state;
+	int error;
+
+	AA_BUG(!profile);
+	AA_BUG(!path);
+
+	if (!RULE_MEDIATES(rules, AA_CLASS_MOUNT))
+		return 0;
+
+	/* TODO: lift path_name, need to separate profile path_flags from
+	 * the lookup
+	 */
+	error = aa_path_name(path, path_flags(profile, path), buffer, &name,
+			     &ad->info, profile->disconnected);
+	if (error)
+		return aa_audit_perm_error(&profile->label, AA_MAY_UMOUNT,
+					   error, ad, audit_cb);
+
+	ad->name = name;
+	state = aa_dfa_match(rules->policy->dfa,
+			     rules->policy->start[AA_CLASS_MOUNT],
+			     name);
+	perms = *aa_lookup_perms(rules->policy, state);
+
+	aa_apply_modes_to_perms(profile, &perms);
+	return aa_check_perms(profile, &perms, AA_MAY_UMOUNT, ad, audit_cb);
+}
+
+int aa_umount(const struct cred *subj_cred, struct aa_label *label,
+	      struct vfsmount *mnt, int flags)
+{
+	struct aa_profile *profile;
+	char *buffer = NULL;
+	int error;
+	struct path path = { .mnt = mnt, .dentry = mnt->mnt_root };
+	DEFINE_AUDIT_MOUNT(ad, OP_UMOUNT, subj_cred);
+
+	AA_BUG(!label);
+	AA_BUG(!mnt);
+
+	buffer = aa_get_buffer(false);
+	if (!buffer)
+		return -ENOMEM;
+
+	error = fn_for_each(label, profile,
+			profile_umount(profile, &path, buffer, &ad));
+	aa_put_buffer(buffer);
+
+	return error;
+}
+
+/* helper fn for transition on pivotroot
+ *
+ * Returns: label for transition or ERR_PTR. Does not return NULL
+ */
+static struct aa_label *build_pivotroot(struct aa_profile *profile,
+					const struct path *new_path,
+					char *new_buffer,
+					const struct path *old_path,
+					char *old_buffer,
+					struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	const char *old_name, *new_name = NULL;
+	struct aa_perms perms = { };
+	aa_state_t state;
+	int error;
+
+	AA_BUG(!profile);
+	AA_BUG(!new_path);
+	AA_BUG(!old_path);
+
+	if (profile_unconfined(profile) ||
+	    !RULE_MEDIATES(rules, AA_CLASS_MOUNT))
+		return aa_get_newest_label(&profile->label);
+
+	error = aa_path_name(old_path, path_flags(profile, old_path),
+			     old_buffer, &old_name, &ad->info,
+			     profile->disconnected);
+	if (error)
+		goto err;
+	ad->mnt.src_name = old_name;
+	error = aa_path_name(new_path, path_flags(profile, new_path),
+			     new_buffer, &new_name, &ad->info,
+			     profile->disconnected);
+	if (error)
+		goto err;
+	ad->name = new_name;
+
+	state = aa_dfa_match(rules->policy->dfa,
+			     rules->policy->start[AA_CLASS_MOUNT],
+			     new_name);
+	state = aa_dfa_null_transition(rules->policy->dfa, state);
+	state = aa_dfa_match(rules->policy->dfa, state, old_name);
+	perms = *aa_lookup_perms(rules->policy, state);
+	/* todo: allow pivotroot to specify a transition other than profile */
+	ad->mnt.trans = profile->label.hname;
+
+	aa_apply_modes_to_perms(profile, &perms);
+	error = aa_check_perms(profile, &perms, AA_MAY_PIVOTROOT, ad, audit_cb);
+
+out:
+	if (error)
+		return ERR_PTR(error);
+
+	return aa_get_newest_label(&profile->label);
+
+err:
+	error = aa_audit_perm_error(&profile->label, AA_MAY_PIVOTROOT, error,
+				    ad, audit_cb);
+	goto out;
+}
+
+int aa_pivotroot(const struct cred *subj_cred, struct aa_label *label,
+		 const struct path *old_path,
+		 const struct path *new_path)
+{
+	struct aa_profile *profile;
+	struct aa_label *target = NULL;
+	char *old_buffer = NULL, *new_buffer = NULL;
+	int error;
+	DEFINE_AUDIT_MOUNT(ad, OP_PIVOTROOT, subj_cred);
+
+	AA_BUG(!label);
+	AA_BUG(!old_path);
+	AA_BUG(!new_path);
+
+	old_buffer = aa_get_buffer(false);
+	new_buffer = aa_get_buffer(false);
+	error = -ENOMEM;
+	if (!old_buffer || !new_buffer)
+		goto out;
+	target = fn_label_build(label, profile, GFP_KERNEL,
+			build_pivotroot(profile, new_path, new_buffer,
+					old_path, old_buffer, &ad));
+	AA_BUG(!target);
+	if (!IS_ERR(target)) {
+		error = aa_replace_current_label(target);
+		if (error)
+			goto fail;
+		aa_put_label(target);
+	} else
+		/* already audited error in build_pivotroot */
+		error = PTR_ERR(target);
+out:
+	aa_put_buffer(old_buffer);
+	aa_put_buffer(new_buffer);
+
+	return error;
+
+fail:
+	/* TODO: add back in auditing of new_name and old_name,
+	 * needs lifting of name lookup out of profile cb
+	 */
+	ad.mnt.trans = target->hname;
+	error = aa_audit_perm_error(label, AA_MAY_PIVOTROOT, error, &ad,
+				    audit_cb);
+	aa_put_label(target);
+	goto out;
+}
diff --git a/security/apparmor/net.c b/security/apparmor/net.c
new file mode 100644
index 000000000..a333e6aff
--- /dev/null
+++ b/security/apparmor/net.c
@@ -0,0 +1,415 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ */
+
+#include "include/af_unix.h"
+#include "include/af_inet.h"
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/policy.h"
+#include "include/secid.h"
+
+#include "net_names.h"
+
+
+struct aa_sfs_entry aa_sfs_entry_network[] = {
+	AA_SFS_FILE_STRING("af_mask",	AA_SFS_AF_MASK),
+	AA_SFS_FILE_BOOLEAN("tcp-fast-open",		1),
+	{ }
+};
+
+struct aa_sfs_entry aa_sfs_entry_networkv9[] = {
+	AA_SFS_FILE_STRING("af_mask",	AA_SFS_AF_MASK),
+	AA_SFS_FILE_BOOLEAN("af_unix",	1),
+	AA_SFS_FILE_BOOLEAN("tcp-fast-open",		1),
+	{ }
+};
+
+static const char * const net_mask_names[] = {
+	"unknown",
+	"send",
+	"receive",
+	"unknown",
+
+	"create",
+	"shutdown",
+	"connect",
+	"unknown",
+
+	"setattr",
+	"getattr",
+	"setcred",
+	"getcred",
+
+	"chmod",
+	"chown",
+	"chgrp",
+	"lock",
+
+	"mmap",
+	"mprot",
+	"unknown",
+	"unknown",
+
+	"accept",
+	"bind",
+	"listen",
+	"unknown",
+
+	"setopt",
+	"getopt",
+	"unknown",
+	"unknown",
+
+	"unknown",
+	"unknown",
+	"unknown",
+	"unknown",
+};
+
+static void audit_unix_addr(struct audit_buffer *ab, const char *str,
+			    struct sockaddr_un *addr, int addrlen)
+{
+	int len = unix_addr_len(addrlen);
+
+	if (!addr || len <= 0) {
+		audit_log_format(ab, " %s=none", str);
+	} else if (addr->sun_path[0]) {
+		audit_log_format(ab, " %s=", str);
+		audit_log_untrustedstring(ab, addr->sun_path);
+	} else {
+		audit_log_format(ab, " %s=\"@", str);
+		if (audit_string_contains_control(&addr->sun_path[1], len - 1))
+			audit_log_n_hex(ab, &addr->sun_path[1], len - 1);
+		else
+			audit_log_format(ab, "%.*s", len - 1,
+					 &addr->sun_path[1]);
+		audit_log_format(ab, "\"");
+	}
+}
+
+static void audit_unix_sk_addr(struct audit_buffer *ab, const char *str,
+			       const struct sock *sk)
+{
+	const struct unix_sock *u = unix_sk(sk);
+
+	if (u && u->addr) {
+		int addrlen;
+		struct sockaddr_un *addr = aa_sunaddr(u, &addrlen);
+
+		audit_unix_addr(ab, str, addr, addrlen);
+	} else {
+		audit_unix_addr(ab, str, NULL, 0);
+
+	}
+}
+
+/* audit callback for net specific fields */
+void audit_net_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (address_family_names[ad->common.u.net->family])
+		audit_log_format(ab, " family=\"%s\"",
+				 address_family_names[ad->common.u.net->family]);
+	else
+		audit_log_format(ab, " family=\"unknown(%d)\"",
+				 ad->common.u.net->family);
+	if (sock_type_names[ad->net.type])
+		audit_log_format(ab, " sock_type=\"%s\"",
+				 sock_type_names[ad->net.type]);
+	else
+		audit_log_format(ab, " sock_type=\"unknown(%d)\"",
+				 ad->net.type);
+	audit_log_format(ab, " protocol=%d", ad->net.protocol);
+
+	if (ad->request & NET_PERMS_MASK) {
+		audit_log_format(ab, " requested=");
+		aa_audit_perm_mask(ab, ad->request, NULL, 0,
+				   net_mask_names, NET_PERMS_MASK);
+
+		if (ad->denied & NET_PERMS_MASK) {
+			audit_log_format(ab, " denied=");
+			aa_audit_perm_mask(ab, ad->denied, NULL, 0,
+					   net_mask_names, NET_PERMS_MASK);
+		}
+	}
+	if (ad->common.u.net->family == PF_UNIX) {
+		if (ad->net.addr || !ad->common.u.net->sk)
+			audit_unix_addr(ab, "addr",
+					unix_addr(ad->net.addr),
+					ad->net.addrlen);
+		else
+			audit_unix_sk_addr(ab, "addr", ad->common.u.net->sk);
+		if (ad->request & NET_PEER_MASK) {
+			audit_unix_addr(ab, "peer_addr",
+					unix_addr(ad->net.peer.addr),
+					ad->net.peer.addrlen);
+		}
+	}
+	if (ad->peer) {
+		audit_log_format(ab, " peer=");
+		aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+				FLAGS_NONE, GFP_ATOMIC);
+	}
+}
+
+/* standard permission lookup pattern - supports early bailout */
+int aa_do_perms(struct aa_profile *profile, struct aa_policydb *policy,
+		aa_state_t state, u32 request,
+		const struct aa_perms *p, struct apparmor_audit_data *ad)
+{
+	struct aa_perms perms;
+
+	AA_BUG(!profile);
+	AA_BUG(!policy);
+
+
+	if (state || !p)
+		p = aa_lookup_perms(policy, state);
+	perms = *p;
+	aa_apply_modes_to_perms(profile, &perms);
+	return aa_check_perms(profile, &perms, request, ad,
+			      audit_net_cb);
+}
+
+/* only continue match if
+ *   insufficient current perms at current state
+ *   indicates there are more perms in later state
+ * Returns: perms struct if early match
+ */
+static struct aa_perms *early_match(struct aa_policydb *policy,
+				    aa_state_t state, u32 request)
+{
+	struct aa_perms *p;
+
+	p = aa_lookup_perms(policy, state);
+	if (((p->allow & request) != request) && (p->allow & AA_CONT_MATCH))
+		return NULL;
+	return p;
+}
+
+static aa_state_t aa_dfa_match_be16(const struct aa_dfa *dfa, aa_state_t state,
+					  u16 data)
+{
+	__be16 buffer = cpu_to_be16(data);
+
+	return aa_dfa_match_len(dfa, state, (char *) &buffer, 2);
+}
+
+/**
+ * aa_match_to_prot - match the af, type, protocol triplet
+ * @policy: policy being matched
+ * @state: state to start in
+ * @request: permissions being requested, ignored if @p == NULL
+ * @af: socket address family
+ * @type: socket type
+ * @protocol: socket protocol
+ * @p: output - pointer to permission associated with match
+ * @info: output - pointer to string describing failure
+ *
+ * RETURNS: state match stopped in.
+ *
+ * If @(p) is assigned a value the returned state will be the
+ * corresponding state. Will not set @p on failure or if match completes
+ * only if an early match occurs
+ */
+aa_state_t aa_match_to_prot(struct aa_policydb *policy, aa_state_t state,
+			    u32 request, u16 af, int type, int protocol,
+			    struct aa_perms **p, const char **info)
+{
+	state = aa_dfa_match_be16(policy->dfa, state, (u16)af);
+	if (!state) {
+		*info = "failed af match";
+		return state;
+	}
+	state = aa_dfa_match_be16(policy->dfa, state, (u16)type);
+	if (state) {
+		if (p)
+			*p = early_match(policy, state, request);
+		if (!p || !*p) {
+			state = aa_dfa_match_be16(policy->dfa, state, (u16)protocol);
+			if (!state)
+				*info = "failed protocol match";
+		}
+	} else {
+		*info = "failed type match";
+	}
+
+	return state;
+}
+
+/* Generic af perm */
+int aa_profile_af_perm(struct aa_profile *profile,
+		       struct apparmor_audit_data *ad, u32 request, u16 family,
+		       int type, int protocol)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms *p = NULL;
+	aa_state_t state;
+
+	AA_BUG(family >= AF_MAX);
+	AA_BUG(type < 0 || type >= SOCK_MAX);
+	AA_BUG(profile_unconfined(profile));
+
+	state = RULE_MEDIATES_NET(rules);
+	if (state) {
+		state = aa_match_to_prot(rules->policy, state, request, family,
+					 type, protocol, &p, &ad->info);
+		return aa_do_perms(profile, rules->policy, state, request, p,
+				   ad);
+	} /* else */
+
+	return 0;
+}
+
+int aa_af_perm(const struct cred *subj_cred, struct aa_label *label,
+	       const char *op, u32 request, u16 family, int type, int protocol)
+{
+	struct aa_profile *profile;
+	DEFINE_AUDIT_NET(ad, op, subj_cred, NULL, family, type, protocol);
+
+	return fn_for_each_confined(label, profile,
+			aa_profile_af_perm(profile, &ad, request, family,
+					   type, protocol));
+}
+
+int aa_label_sk_perm(const struct cred *subj_cred, struct aa_label *label,
+		     const char *op, u32 request, const struct sock *sk)
+{
+	struct aa_sk_ctx *ctx = aa_sock(sk);
+	int error = 0;
+
+	AA_BUG(!label);
+	AA_BUG(!sk);
+
+	if (rcu_access_pointer(ctx->label) != kernel_t && !unconfined(label)) {
+		struct aa_profile *profile;
+		DEFINE_AUDIT_SK(ad, op, subj_cred, sk);
+
+		ad.subj_cred = subj_cred;
+		error = fn_for_each_confined(label, profile,
+			    aa_profile_af_perm(profile, &ad, request, sk->sk_family,
+					    sk->sk_type, sk->sk_protocol));
+	}
+
+	return error;
+}
+
+int aa_sk_perm(const char *op, u32 request, const struct sock *sk)
+{
+	struct aa_label *label;
+	bool needput;
+	int error;
+
+	AA_BUG(!sk);
+	AA_BUG(in_interrupt());
+
+	/* TODO: switch to begin_current_label ???? */
+	label = begin_current_label_crit_section(&needput);
+	error = aa_label_sk_perm(current_cred(), label, op, request, sk);
+	end_current_label_crit_section(label, needput);
+
+	return error;
+}
+
+
+int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label,
+		      const char *op, u32 request, struct file *file)
+{
+	struct socket *sock = (struct socket *) file->private_data;
+
+	AA_BUG(!label);
+
+	/* sock && sock->sk can be NULL for sockets being set up or torn down */
+	if (!sock || !sock->sk)
+		return 0;
+
+	switch (sock->sk->sk_family) {
+	case PF_UNIX:
+		return aa_unix_file_perm(subj_cred, label, op, request, file);
+	case PF_INET:
+	case PF_INET6:
+		return aa_inet_file_perm(subj_cred, label, op, request, sock);
+	}
+	return aa_label_sk_perm(subj_cred, label, op, request, sock->sk);
+}
+
+#ifdef CONFIG_NETWORK_SECMARK
+static int apparmor_secmark_init(struct aa_secmark *secmark)
+{
+	struct aa_label *label;
+
+	if (secmark->label[0] == '*') {
+		secmark->secid = AA_SECID_WILDCARD;
+		return 0;
+	}
+
+	label = aa_label_strn_parse(&root_ns->unconfined->label,
+				    secmark->label, strlen(secmark->label),
+				    GFP_ATOMIC, false, false);
+
+	if (IS_ERR(label))
+		return PTR_ERR(label);
+
+	secmark->secid = label->secid;
+	aa_put_label(label);
+
+	return 0;
+}
+
+static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid,
+			   struct apparmor_audit_data *ad)
+{
+	int i, ret;
+	struct aa_perms perms = { };
+	struct aa_ruleset *rules = profile->label.rules[0];
+
+	if (rules->secmark_count == 0)
+		return 0;
+
+	for (i = 0; i < rules->secmark_count; i++) {
+		if (!rules->secmark[i].secid) {
+			ret = apparmor_secmark_init(&rules->secmark[i]);
+			if (ret)
+				return ret;
+		}
+
+		if (rules->secmark[i].secid == secid ||
+		    rules->secmark[i].secid == AA_SECID_WILDCARD) {
+			if (rules->secmark[i].deny)
+				perms.deny = ALL_PERMS_MASK;
+			else
+				perms.allow = ALL_PERMS_MASK;
+
+			if (rules->secmark[i].audit)
+				perms.audit = ALL_PERMS_MASK;
+		}
+	}
+
+	aa_apply_modes_to_perms(profile, &perms);
+
+	return aa_check_perms(profile, &perms, request, ad, audit_net_cb);
+}
+
+int apparmor_secmark_check(struct aa_label *label, char *op, u32 request,
+			   u32 secid, const struct sock *sk)
+{
+	struct aa_profile *profile;
+	DEFINE_AUDIT_SK(ad, op, NULL, sk);
+
+	return fn_for_each_confined(label, profile,
+				    aa_secmark_perm(profile, request, secid,
+						    &ad));
+}
+#endif
diff --git a/security/apparmor/nulldfa.in b/security/apparmor/nulldfa.in
new file mode 100644
index 000000000..095f42a24
--- /dev/null
+++ b/security/apparmor/nulldfa.in
@@ -0,0 +1,107 @@
+0x1B, 0x5E, 0x78, 0x3D, 0x00, 0x00, 0x00, 0x18, 0x00, 0x00, 0x04,
+0x90, 0x00, 0x00, 0x6E, 0x6F, 0x74, 0x66, 0x6C, 0x65, 0x78, 0x00,
+0x00, 0x00, 0x00, 0x01, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x07, 0x00, 0x04, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x04, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00,
+0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x08, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x03, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00
diff --git a/security/apparmor/path.c b/security/apparmor/path.c
new file mode 100644
index 000000000..2494e8101
--- /dev/null
+++ b/security/apparmor/path.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor function for pathnames
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/nsproxy.h>
+#include <linux/path.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/fs_struct.h>
+
+#include "include/apparmor.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+/* modified from dcache.c */
+static int prepend(char **buffer, int buflen, const char *str, int namelen)
+{
+	buflen -= namelen;
+	if (buflen < 0)
+		return -ENAMETOOLONG;
+	*buffer -= namelen;
+	memcpy(*buffer, str, namelen);
+	return 0;
+}
+
+#define CHROOT_NSCONNECT (PATH_CHROOT_REL | PATH_CHROOT_NSCONNECT)
+
+/* If the path is not connected to the expected root,
+ * check if it is a sysctl and handle specially else remove any
+ * leading / that __d_path may have returned.
+ * Unless
+ *     specifically directed to connect the path,
+ * OR
+ *     if in a chroot and doing chroot relative paths and the path
+ *     resolves to the namespace root (would be connected outside
+ *     of chroot) and specifically directed to connect paths to
+ *     namespace root.
+ */
+static int disconnect(const struct path *path, char *buf, char **name,
+		      int flags, const char *disconnected)
+{
+	int error = 0;
+
+	if (!(flags & PATH_CONNECT_PATH) &&
+	    !(((flags & CHROOT_NSCONNECT) == CHROOT_NSCONNECT) &&
+	      our_mnt(path->mnt))) {
+		/* disconnected path, don't return pathname starting
+		 * with '/'
+		 */
+		error = -EACCES;
+		if (**name == '/')
+			*name = *name + 1;
+	} else {
+		if (**name != '/')
+			/* CONNECT_PATH with missing root */
+			error = prepend(name, *name - buf, "/", 1);
+		if (!error && disconnected)
+			error = prepend(name, *name - buf, disconnected,
+					strlen(disconnected));
+	}
+
+	return error;
+}
+
+/**
+ * d_namespace_path - lookup a name associated with a given path
+ * @path: path to lookup  (NOT NULL)
+ * @buf:  buffer to store path to  (NOT NULL)
+ * @name: Returns - pointer for start of path name with in @buf (NOT NULL)
+ * @flags: flags controlling path lookup
+ * @disconnected: string to prefix to disconnected paths
+ *
+ * Handle path name lookup.
+ *
+ * Returns: %0 else error code if path lookup fails
+ *          When no error the path name is returned in @name which points to
+ *          a position in @buf
+ */
+static int d_namespace_path(const struct path *path, char *buf, char **name,
+			    int flags, const char *disconnected)
+{
+	char *res;
+	int error = 0;
+	int connected = 1;
+	int isdir = (flags & PATH_IS_DIR) ? 1 : 0;
+	int buflen = aa_g_path_max - isdir;
+
+	if (path->mnt->mnt_flags & MNT_INTERNAL) {
+		/* it's not mounted anywhere */
+		res = dentry_path(path->dentry, buf, buflen);
+		*name = res;
+		if (IS_ERR(res)) {
+			*name = buf;
+			return PTR_ERR(res);
+		}
+		if (path->dentry->d_sb->s_magic == PROC_SUPER_MAGIC &&
+		    strncmp(*name, "/sys/", 5) == 0) {
+			/* TODO: convert over to using a per namespace
+			 * control instead of hard coded /proc
+			 */
+			error = prepend(name, *name - buf, "/proc", 5);
+			goto out;
+		} else
+			error = disconnect(path, buf, name, flags,
+					   disconnected);
+		goto out;
+	}
+
+	/* resolve paths relative to chroot?*/
+	if (flags & PATH_CHROOT_REL) {
+		struct path root;
+		get_fs_root(current->fs, &root);
+		res = __d_path(path, &root, buf, buflen);
+		path_put(&root);
+	} else {
+		res = d_absolute_path(path, buf, buflen);
+		if (!our_mnt(path->mnt))
+			connected = 0;
+	}
+
+	/* handle error conditions - and still allow a partial path to
+	 * be returned.
+	 */
+	if (IS_ERR_OR_NULL(res)) {
+		if (PTR_ERR(res) == -ENAMETOOLONG) {
+			error = -ENAMETOOLONG;
+			*name = buf;
+			goto out;
+		}
+		connected = 0;
+		res = dentry_path_raw(path->dentry, buf, buflen);
+		if (IS_ERR(res)) {
+			error = PTR_ERR(res);
+			*name = buf;
+			goto out;
+		}
+	} else if (!our_mnt(path->mnt))
+		connected = 0;
+
+	*name = res;
+
+	if (!connected)
+		error = disconnect(path, buf, name, flags, disconnected);
+
+	/* Handle two cases:
+	 * 1. A deleted dentry && profile is not allowing mediation of deleted
+	 * 2. On some filesystems, newly allocated dentries appear to the
+	 *    security_path hooks as a deleted dentry except without an inode
+	 *    allocated.
+	 */
+	if (d_unlinked(path->dentry) && d_is_positive(path->dentry) &&
+	    !(flags & (PATH_MEDIATE_DELETED | PATH_DELEGATE_DELETED))) {
+			error = -ENOENT;
+			goto out;
+	}
+
+out:
+	/* Append "/" to directory paths and reterminate string, except for
+	 * root "/" which already ends in a slash.
+	 */
+	if (!error && isdir) {
+		bool is_root = (*name)[0] == '/' && (*name)[1] == '\0';
+
+		if (!is_root) {
+			buf[aa_g_path_max - 2] = '/';
+			buf[aa_g_path_max - 1] = '\0';
+		}
+	}
+
+	return error;
+}
+
+/**
+ * aa_path_name - get the pathname to a buffer ensure dir / is appended
+ * @path: path the file  (NOT NULL)
+ * @flags: flags controlling path name generation
+ * @buffer: buffer to put name in (NOT NULL)
+ * @name: Returns - the generated path name if !error (NOT NULL)
+ * @info: Returns - information on why the path lookup failed (MAYBE NULL)
+ * @disconnected: string to prepend to disconnected paths
+ *
+ * @name is a pointer to the beginning of the pathname (which usually differs
+ * from the beginning of the buffer), or NULL.  If there is an error @name
+ * may contain a partial or invalid name that can be used for audit purposes,
+ * but it can not be used for mediation.
+ *
+ * We need PATH_IS_DIR to indicate whether the file is a directory or not
+ * because the file may not yet exist, and so we cannot check the inode's
+ * file type.
+ *
+ * Returns: %0 else error code if could retrieve name
+ */
+int aa_path_name(const struct path *path, int flags, char *buffer,
+		 const char **name, const char **info, const char *disconnected)
+{
+	char *str = NULL;
+	int error = d_namespace_path(path, buffer, &str, flags, disconnected);
+
+	if (info && error) {
+		if (error == -ENOENT)
+			*info = "Failed name lookup - deleted entry";
+		else if (error == -EACCES)
+			*info = "Failed name lookup - disconnected path";
+		else if (error == -ENAMETOOLONG)
+			*info = "Failed name lookup - name too long";
+		else
+			*info = "Failed name lookup";
+	}
+
+	*name = str;
+
+	return error;
+}
diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
new file mode 100644
index 000000000..397f9ff78
--- /dev/null
+++ b/security/apparmor/policy.c
@@ -0,0 +1,1537 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy manipulation functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * AppArmor policy is based around profiles, which contain the rules a
+ * task is confined by.  Every task in the system has a profile attached
+ * to it determined either by matching "unconfined" tasks against the
+ * visible set of profiles or by following a profiles attachment rules.
+ *
+ * Each profile exists in a profile namespace which is a container of
+ * visible profiles.  Each namespace contains a special "unconfined" profile,
+ * which doesn't enforce any confinement on a task beyond DAC.
+ *
+ * Namespace and profile names can be written together in either
+ * of two syntaxes.
+ *	:namespace:profile - used by kernel interfaces for easy detection
+ *	namespace://profile - used by policy
+ *
+ * Profile names can not start with : or @ or ^ and may not contain \0
+ *
+ * Reserved profile names
+ *	unconfined - special automatically generated unconfined profile
+ *	inherit - special name to indicate profile inheritance
+ *	null-XXXX-YYYY - special automatically generated learning profiles
+ *
+ * Namespace names may not start with / or @ and may not contain \0 or :
+ * Reserved namespace names
+ *	user-XXXX - user defined profiles
+ *
+ * a // in a profile or namespace name indicates a hierarchical name with the
+ * name before the // being the parent and the name after the child.
+ *
+ * Profile and namespace hierarchies serve two different but similar purposes.
+ * The namespace contains the set of visible profiles that are considered
+ * for attachment.  The hierarchy of namespaces allows for virtualizing
+ * the namespace so that for example a chroot can have its own set of profiles
+ * which may define some local user namespaces.
+ * The profile hierarchy severs two distinct purposes,
+ * -  it allows for sub profiles or hats, which allows an application to run
+ *    subprograms under its own profile with different restriction than it
+ *    self, and not have it use the system profile.
+ *    eg. if a mail program starts an editor, the policy might make the
+ *        restrictions tighter on the editor tighter than the mail program,
+ *        and definitely different than general editor restrictions
+ * - it allows for binary hierarchy of profiles, so that execution history
+ *   is preserved.  This feature isn't exploited by AppArmor reference policy
+ *   but is allowed.  NOTE: this is currently suboptimal because profile
+ *   aliasing is not currently implemented so that a profile for each
+ *   level must be defined.
+ *   eg. /bin/bash///bin/ls as a name would indicate /bin/ls was started
+ *       from /bin/bash
+ *
+ *   A profile or namespace name that can contain one or more // separators
+ *   is referred to as an hname (hierarchical).
+ *   eg.  /bin/bash//bin/ls
+ *
+ *   An fqname is a name that may contain both namespace and profile hnames.
+ *   eg. :ns:/bin/bash//bin/ls
+ *
+ * NOTES:
+ *   - locking of profile lists is currently fairly coarse.  All profile
+ *     lists within a namespace use the namespace lock.
+ * FIXME: move profile lists to using rcu_lists
+ */
+
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/cred.h>
+#include <linux/rculist.h>
+#include <linux/user_namespace.h>
+
+#include "include/apparmor.h"
+#include "include/capability.h"
+#include "include/cred.h"
+#include "include/file.h"
+#include "include/ipc.h"
+#include "include/match.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+#include "include/policy_unpack.h"
+#include "include/resource.h"
+
+int unprivileged_userns_apparmor_policy = 1;
+int aa_unprivileged_unconfined_restricted;
+
+const char *const aa_profile_mode_names[] = {
+	"enforce",
+	"complain",
+	"kill",
+	"unconfined",
+	"user",
+};
+
+void aa_destroy_tags(struct aa_tags_struct *tags)
+{
+	kfree_sensitive(tags->hdrs.table);
+	kfree_sensitive(tags->sets.table);
+	aa_destroy_str_table(&tags->strs);
+	memset(tags, 0, sizeof(*tags));
+}
+
+static void aa_free_pdb(struct aa_policydb *pdb)
+{
+	if (pdb) {
+		aa_put_dfa(pdb->dfa);
+		kvfree(pdb->perms);
+		aa_destroy_str_table(&pdb->trans);
+		aa_destroy_tags(&pdb->tags);
+		kfree(pdb);
+	}
+}
+
+/**
+ * aa_pdb_free_kref - free aa_policydb by kref (called by aa_put_pdb)
+ * @kref: kref callback for freeing of a dfa  (NOT NULL)
+ */
+void aa_pdb_free_kref(struct kref *kref)
+{
+	struct aa_policydb *pdb = container_of(kref, struct aa_policydb, count);
+
+	aa_free_pdb(pdb);
+}
+
+
+struct aa_policydb *aa_alloc_pdb(gfp_t gfp)
+{
+	struct aa_policydb *pdb = kzalloc_obj(struct aa_policydb, gfp);
+
+	if (!pdb)
+		return NULL;
+
+	kref_init(&pdb->count);
+
+	return pdb;
+}
+
+
+/**
+ * __add_profile - add a profiles to list and label tree
+ * @list: list to add it to  (NOT NULL)
+ * @profile: the profile to add  (NOT NULL)
+ *
+ * refcount @profile, should be put by __list_remove_profile
+ *
+ * Requires: namespace lock be held, or list not be shared
+ */
+static void __add_profile(struct list_head *list, struct aa_profile *profile)
+{
+	struct aa_label *l;
+
+	AA_BUG(!list);
+	AA_BUG(!profile);
+	AA_BUG(!profile->ns);
+	AA_BUG(!mutex_is_locked(&profile->ns->lock));
+
+	list_add_rcu(&profile->base.list, list);
+	/* get list reference */
+	aa_get_profile(profile);
+	l = aa_label_insert(&profile->ns->labels, &profile->label);
+	AA_BUG(l != &profile->label);
+	aa_put_label(l);
+}
+
+/**
+ * __list_remove_profile - remove a profile from the list it is on
+ * @profile: the profile to remove  (NOT NULL)
+ *
+ * remove a profile from the list, warning generally removal should
+ * be done with __replace_profile as most profile removals are
+ * replacements to the unconfined profile.
+ *
+ * put @profile list refcount
+ *
+ * Requires: namespace lock be held, or list not have been live
+ */
+static void __list_remove_profile(struct aa_profile *profile)
+{
+	AA_BUG(!profile);
+	AA_BUG(!profile->ns);
+	AA_BUG(!mutex_is_locked(&profile->ns->lock));
+
+	list_del_rcu(&profile->base.list);
+	aa_put_profile(profile);
+}
+
+/**
+ * __remove_profile - remove profile, and children
+ * @profile: profile to be removed  (NOT NULL)
+ *
+ * Requires: namespace list lock be held, or list not be shared
+ */
+static void __remove_profile(struct aa_profile *profile)
+{
+	struct aa_profile *curr, *to_remove;
+
+	AA_BUG(!profile);
+	AA_BUG(!profile->ns);
+	AA_BUG(!mutex_is_locked(&profile->ns->lock));
+
+	/* release any children lists first */
+	if (!list_empty(&profile->base.profiles)) {
+		curr = list_first_entry(&profile->base.profiles, struct aa_profile, base.list);
+
+		while (curr != profile) {
+
+			while (!list_empty(&curr->base.profiles))
+				curr = list_first_entry(&curr->base.profiles,
+							struct aa_profile, base.list);
+
+			to_remove = curr;
+			if (!list_is_last(&to_remove->base.list,
+					  &aa_deref_parent(curr)->base.profiles))
+				curr = list_next_entry(to_remove, base.list);
+			else
+				curr = aa_deref_parent(curr);
+
+			/* released by free_profile */
+			aa_label_remove(&to_remove->label);
+			__aafs_profile_rmdir(to_remove);
+			__list_remove_profile(to_remove);
+		}
+	}
+
+	/* released by free_profile */
+	aa_label_remove(&profile->label);
+	__aafs_profile_rmdir(profile);
+	__list_remove_profile(profile);
+	/* rawdata is only ever referenced by fs lookup, that is no
+	 * longer possible here, so put the reference to it. This will
+	 * enable the rawdata to be freed if for some reason the profile
+	 * is pinned and going to live for a while.
+	 */
+	aa_put_profile_loaddata(profile->rawdata);
+	profile->rawdata = NULL;
+}
+
+/**
+ * __aa_profile_list_release - remove all profiles on the list and put refs
+ * @head: list of profiles  (NOT NULL)
+ *
+ * Requires: namespace lock be held
+ */
+void __aa_profile_list_release(struct list_head *head)
+{
+	struct aa_profile *profile, *tmp;
+	list_for_each_entry_safe(profile, tmp, head, base.list)
+		__remove_profile(profile);
+}
+
+/**
+ * aa_free_data - free a data blob
+ * @ptr: data to free
+ * @arg: unused
+ */
+static void aa_free_data(void *ptr, void *arg)
+{
+	struct aa_data *data = ptr;
+
+	if (!ptr)
+		return;
+
+	kvfree_sensitive(data->data, data->size);
+	kfree_sensitive(data->key);
+	kfree_sensitive(data);
+}
+
+static void free_attachment(struct aa_attachment *attach)
+{
+	int i;
+
+	if (!attach)
+		return;
+
+	for (i = 0; i < attach->xattr_count; i++)
+		kfree_sensitive(attach->xattrs[i]);
+	kfree_sensitive(attach->xattrs);
+	aa_put_pdb(attach->xmatch);
+}
+
+static void free_ruleset(struct aa_ruleset *rules)
+{
+	int i;
+
+	if (!rules)
+	  return;
+
+	aa_put_pdb(rules->file);
+	aa_put_pdb(rules->policy);
+	aa_free_cap_rules(&rules->caps);
+	aa_free_rlimit_rules(&rules->rlimits);
+
+	for (i = 0; i < rules->secmark_count; i++)
+		kfree_sensitive(rules->secmark[i].label);
+	kfree_sensitive(rules->secmark);
+	kfree_sensitive(rules);
+}
+
+struct aa_ruleset *aa_alloc_ruleset(gfp_t gfp)
+{
+	struct aa_ruleset *rules;
+
+	rules = kzalloc_obj(*rules, gfp);
+
+	return rules;
+}
+
+/**
+ * aa_free_profile - free a profile
+ * @profile: the profile to free  (MAYBE NULL)
+ *
+ * Free a profile, its hats and null_profile. All references to the profile,
+ * its hats and null_profile must have been put.
+ *
+ * If the profile was referenced from a task context, free_profile() will
+ * be called from an rcu callback routine, so we must not sleep here.
+ */
+void aa_free_profile(struct aa_profile *profile)
+{
+	struct rhashtable *rht;
+
+	AA_DEBUG(DEBUG_POLICY, "%s(%p)\n", __func__, profile);
+
+	if (!profile)
+		return;
+
+	/* free children profiles */
+	aa_policy_destroy(&profile->base);
+	aa_put_profile(rcu_access_pointer(profile->parent));
+
+	aa_put_ns(profile->ns);
+	kfree_sensitive(profile->rename);
+	kfree_sensitive(profile->disconnected);
+
+	free_attachment(&profile->attach);
+
+	/*
+	 * at this point there are no tasks that can have a reference
+	 * to rules
+	 */
+	for (int i = 0; i < profile->n_rules; i++)
+		free_ruleset(profile->label.rules[i]);
+
+	kfree_sensitive(profile->dirname);
+
+	if (profile->data) {
+		rht = profile->data;
+		profile->data = NULL;
+		rhashtable_free_and_destroy(rht, aa_free_data, NULL);
+		kfree_sensitive(rht);
+	}
+
+	kfree_sensitive(profile->hash);
+	aa_put_profile_loaddata(profile->rawdata);
+	aa_label_destroy(&profile->label);
+
+	kfree_sensitive(profile);
+}
+
+/**
+ * aa_alloc_profile - allocate, initialize and return a new profile
+ * @hname: name of the profile  (NOT NULL)
+ * @proxy: proxy to use OR null if to allocate a new one
+ * @gfp: allocation type
+ *
+ * Returns: refcount profile or NULL on failure
+ */
+struct aa_profile *aa_alloc_profile(const char *hname, struct aa_proxy *proxy,
+				    gfp_t gfp)
+{
+	struct aa_profile *profile;
+
+	/* freed by free_profile - usually through aa_put_profile
+	 * this adds space for a single ruleset in the rules section of the
+	 * label
+	 */
+	profile = kzalloc_flex(*profile, label.rules, 1, gfp);
+	if (!profile)
+		return NULL;
+
+	if (!aa_policy_init(&profile->base, NULL, hname, gfp))
+		goto fail;
+	if (!aa_label_init(&profile->label, 1, gfp))
+		goto fail;
+
+	/* allocate the first ruleset, but leave it empty */
+	profile->label.rules[0] = aa_alloc_ruleset(gfp);
+	if (!profile->label.rules[0])
+		goto fail;
+	profile->n_rules = 1;
+
+	/* update being set needed by fs interface */
+	if (!proxy) {
+		proxy = aa_alloc_proxy(&profile->label, gfp);
+		if (!proxy)
+			goto fail;
+	} else
+		aa_get_proxy(proxy);
+	profile->label.proxy = proxy;
+
+	profile->label.hname = profile->base.hname;
+	profile->label.flags |= FLAG_PROFILE;
+	profile->label.vec[0] = profile;
+
+	profile->signal = SIGKILL;
+	/* refcount released by caller */
+	return profile;
+
+fail:
+	aa_free_profile(profile);
+
+	return NULL;
+}
+
+static inline bool ANY_RULE_MEDIATES(struct aa_profile *profile,
+				     unsigned char class)
+{
+	int i;
+
+	for (i = 0; i < profile->n_rules; i++) {
+		if (RULE_MEDIATES(profile->label.rules[i], class))
+			return true;
+	}
+	return false;
+}
+
+/* set of rules that are mediated by unconfined */
+static int unconfined_mediates[] = { AA_CLASS_NS, AA_CLASS_IO_URING, 0 };
+
+/* must be called after profile rulesets and start information is setup */
+void aa_compute_profile_mediates(struct aa_profile *profile)
+{
+	int c;
+
+	if (profile_unconfined(profile)) {
+		int *pos;
+
+		for (pos = unconfined_mediates; *pos; pos++) {
+			if (ANY_RULE_MEDIATES(profile, *pos))
+				profile->label.mediates |= ((u64) 1) << AA_CLASS_NS;
+		}
+		return;
+	}
+	for (c = 0; c <= AA_CLASS_LAST; c++) {
+		if (ANY_RULE_MEDIATES(profile, c))
+			profile->label.mediates |= ((u64) 1) << c;
+	}
+}
+
+/* TODO: profile accounting - setup in remove */
+
+/**
+ * __strn_find_child - find a profile on @head list using substring of @name
+ * @head: list to search  (NOT NULL)
+ * @name: name of profile (NOT NULL)
+ * @len: length of @name substring to match
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted profile ptr, or NULL if not found
+ */
+static struct aa_profile *__strn_find_child(struct list_head *head,
+					    const char *name, int len)
+{
+	return (struct aa_profile *)__policy_strn_find(head, name, len);
+}
+
+/**
+ * __find_child - find a profile on @head list with a name matching @name
+ * @head: list to search  (NOT NULL)
+ * @name: name of profile (NOT NULL)
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted profile ptr, or NULL if not found
+ */
+static struct aa_profile *__find_child(struct list_head *head, const char *name)
+{
+	return __strn_find_child(head, name, strlen(name));
+}
+
+/**
+ * aa_find_child - find a profile by @name in @parent
+ * @parent: profile to search  (NOT NULL)
+ * @name: profile name to search for  (NOT NULL)
+ *
+ * Returns: a refcounted profile or NULL if not found
+ */
+struct aa_profile *aa_find_child(struct aa_profile *parent, const char *name)
+{
+	struct aa_profile *profile;
+
+	rcu_read_lock();
+	do {
+		profile = __find_child(&parent->base.profiles, name);
+	} while (profile && !aa_get_profile_not0(profile));
+	rcu_read_unlock();
+
+	/* refcount released by caller */
+	return profile;
+}
+
+/**
+ * __lookup_parent - lookup the parent of a profile of name @hname
+ * @ns: namespace to lookup profile in  (NOT NULL)
+ * @hname: hierarchical profile name to find parent of  (NOT NULL)
+ *
+ * Lookups up the parent of a fully qualified profile name, the profile
+ * that matches hname does not need to exist, in general this
+ * is used to load a new profile.
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted policy or NULL if not found
+ */
+static struct aa_policy *__lookup_parent(struct aa_ns *ns,
+					 const char *hname)
+{
+	struct aa_policy *policy;
+	struct aa_profile *profile = NULL;
+	char *split;
+
+	policy = &ns->base;
+
+	for (split = strstr(hname, "//"); split;) {
+		profile = __strn_find_child(&policy->profiles, hname,
+					    split - hname);
+		if (!profile)
+			return NULL;
+		policy = &profile->base;
+		hname = split + 2;
+		split = strstr(hname, "//");
+	}
+	if (!profile)
+		return &ns->base;
+	return &profile->base;
+}
+
+/**
+ * __create_missing_ancestors - create place holders for missing ancestors
+ * @ns: namespace to lookup profile in (NOT NULL)
+ * @hname: hierarchical profile name to find parent of (NOT NULL)
+ * @gfp: type of allocation.
+ *
+ * Requires: ns mutex lock held
+ *
+ * Return: unrefcounted parent policy on success or %NULL if error creating
+ *          place holder profiles.
+ */
+static struct aa_policy *__create_missing_ancestors(struct aa_ns *ns,
+						    const char *hname,
+						    gfp_t gfp)
+{
+	struct aa_policy *policy;
+	struct aa_profile *parent, *profile = NULL;
+	char *split;
+
+	AA_BUG(!ns);
+	AA_BUG(!hname);
+
+	policy = &ns->base;
+
+	for (split = strstr(hname, "//"); split;) {
+		parent = profile;
+		profile = __strn_find_child(&policy->profiles, hname,
+					    split - hname);
+		if (!profile) {
+			const char *name = kstrndup(hname, split - hname,
+						    gfp);
+			if (!name)
+				return NULL;
+			profile = aa_alloc_null(parent, name, gfp);
+			kfree(name);
+			if (!profile)
+				return NULL;
+			if (!parent)
+				profile->ns = aa_get_ns(ns);
+		}
+		policy = &profile->base;
+		hname = split + 2;
+		split = strstr(hname, "//");
+	}
+	if (!profile)
+		return &ns->base;
+	return &profile->base;
+}
+
+/**
+ * __lookupn_profile - lookup the profile matching @hname
+ * @base: base list to start looking up profile name from  (NOT NULL)
+ * @hname: hierarchical profile name  (NOT NULL)
+ * @n: length of @hname
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted profile pointer or NULL if not found
+ *
+ * Do a relative name lookup, recursing through profile tree.
+ */
+static struct aa_profile *__lookupn_profile(struct aa_policy *base,
+					    const char *hname, size_t n)
+{
+	struct aa_profile *profile = NULL;
+	const char *split;
+
+	for (split = strnstr(hname, "//", n); split;
+	     split = strnstr(hname, "//", n)) {
+		profile = __strn_find_child(&base->profiles, hname,
+					    split - hname);
+		if (!profile)
+			return NULL;
+
+		base = &profile->base;
+		n -= split + 2 - hname;
+		hname = split + 2;
+	}
+
+	if (n)
+		return __strn_find_child(&base->profiles, hname, n);
+	return NULL;
+}
+
+static struct aa_profile *__lookup_profile(struct aa_policy *base,
+					   const char *hname)
+{
+	return __lookupn_profile(base, hname, strlen(hname));
+}
+
+/**
+ * aa_lookupn_profile - find a profile by its full or partial name
+ * @ns: the namespace to start from (NOT NULL)
+ * @hname: name to do lookup on.  Does not contain namespace prefix (NOT NULL)
+ * @n: size of @hname
+ *
+ * Returns: refcounted profile or NULL if not found
+ */
+struct aa_profile *aa_lookupn_profile(struct aa_ns *ns, const char *hname,
+				      size_t n)
+{
+	struct aa_profile *profile;
+
+	rcu_read_lock();
+	do {
+		profile = __lookupn_profile(&ns->base, hname, n);
+	} while (profile && !aa_get_profile_not0(profile));
+	rcu_read_unlock();
+
+	/* the unconfined profile is not in the regular profile list */
+	if (!profile && strncmp(hname, "unconfined", n) == 0)
+		profile = aa_get_newest_profile(ns->unconfined);
+
+	/* refcount released by caller */
+	return profile;
+}
+
+struct aa_profile *aa_fqlookupn_profile(struct aa_label *base,
+					const char *fqname, size_t n)
+{
+	struct aa_profile *profile;
+	struct aa_ns *ns;
+	const char *name, *ns_name;
+	size_t ns_len;
+
+	name = aa_splitn_fqname(fqname, n, &ns_name, &ns_len);
+	if (ns_name) {
+		ns = aa_lookupn_ns(labels_ns(base), ns_name, ns_len);
+		if (!ns)
+			return NULL;
+	} else
+		ns = aa_get_ns(labels_ns(base));
+
+	if (name)
+		profile = aa_lookupn_profile(ns, name, n - (name - fqname));
+	else if (ns)
+		/* default profile for ns, currently unconfined */
+		profile = aa_get_newest_profile(ns->unconfined);
+	else
+		profile = NULL;
+	aa_put_ns(ns);
+
+	return profile;
+}
+
+
+struct aa_profile *aa_alloc_null(struct aa_profile *parent, const char *name,
+				 gfp_t gfp)
+{
+	struct aa_profile *profile;
+	struct aa_ruleset *rules;
+
+	profile = aa_alloc_profile(name, NULL, gfp);
+	if (!profile)
+		return NULL;
+
+	/* TODO: ideally we should inherit abi from parent */
+	profile->label.flags |= FLAG_NULL;
+	profile->attach.xmatch = aa_get_pdb(nullpdb);
+	rules = profile->label.rules[0];
+	rules->file = aa_get_pdb(nullpdb);
+	rules->policy = aa_get_pdb(nullpdb);
+	aa_compute_profile_mediates(profile);
+
+	if (parent) {
+		profile->path_flags = parent->path_flags;
+		/* override/inherit what is mediated from parent */
+		profile->label.mediates = parent->label.mediates;
+		/* released on free_profile */
+		rcu_assign_pointer(profile->parent, aa_get_profile(parent));
+		profile->ns = aa_get_ns(parent->ns);
+	}
+
+	return profile;
+}
+
+/**
+ * __aa_new_learning_profile - create or find a null-X learning profile
+ * @parent: profile that caused this profile to be created (NOT NULL)
+ * @hat: true if the null- learning profile is a hat
+ * @base: name to base the null profile off of
+ * @gfp: type of allocation
+ *
+ * Find/Create a null- complain mode profile used in learning mode.  The
+ * name of the profile is unique and follows the format of parent//null-XXX.
+ * where XXX is based on the @name or if that fails or is not supplied
+ * a unique number
+ *
+ * null profiles are added to the profile list but the list does not
+ * hold a count on them so that they are automatically released when
+ * not in use.
+ *
+ * Returns: new refcounted profile else NULL on failure
+ */
+struct aa_profile *__aa_new_learning_profile(struct aa_profile *parent,
+					     bool hat, const char *base,
+					     gfp_t gfp)
+{
+	struct aa_profile *p, *profile;
+	const char *bname;
+	char *name = NULL;
+	size_t name_sz;
+
+	AA_BUG(!parent);
+	AA_BUG(!mutex_is_locked(&parent->ns->lock));
+
+	if (base) {
+		name_sz = strlen(parent->base.hname) + 8 + strlen(base);
+		name = kmalloc(name_sz, gfp);
+		if (name) {
+			snprintf(name, name_sz, "%s//null-%s",
+				 parent->base.hname, base);
+			goto name;
+		}
+		/* fall through to try shorter uniq */
+	}
+
+	name_sz = strlen(parent->base.hname) + 2 + 7 + 8;
+	name = kmalloc(name_sz, gfp);
+	if (!name)
+		return NULL;
+	snprintf(name, name_sz, "%s//null-%x", parent->base.hname,
+		 atomic_inc_return(&parent->ns->uniq_null));
+
+name:
+	/* lookup to see if this is a dup creation */
+	bname = basename(name);
+	profile = aa_find_child(parent, bname);
+	if (profile)
+		goto out;
+
+	profile = aa_alloc_null(parent, name, gfp);
+	if (!profile)
+		goto fail;
+	profile->mode = APPARMOR_COMPLAIN;
+	if (hat)
+		profile->label.flags |= FLAG_HAT;
+
+	p = __find_child(&parent->base.profiles, bname);
+	if (p) {
+		aa_free_profile(profile);
+		profile = aa_get_profile(p);
+	} else {
+		__add_profile(&parent->base.profiles, profile);
+	}
+
+	/* refcount released by caller */
+out:
+	kfree(name);
+
+	return profile;
+
+fail:
+	kfree(name);
+	aa_free_profile(profile);
+	return NULL;
+}
+
+struct aa_profile *aa_new_learning_profile(struct aa_profile *parent, bool hat,
+					   const char *base, gfp_t gfp)
+{
+	struct aa_profile *profile;
+
+	mutex_lock_nested(&parent->ns->lock, parent->ns->level);
+	profile = __aa_new_learning_profile(parent, hat, base, gfp);
+	mutex_unlock(&parent->ns->lock);
+
+	return profile;
+}
+
+/**
+ * replacement_allowed - test to see if replacement is allowed
+ * @profile: profile to test if it can be replaced  (MAYBE NULL)
+ * @noreplace: true if replacement shouldn't be allowed but addition is okay
+ * @info: Returns - info about why replacement failed (NOT NULL)
+ *
+ * Returns: %0 if replacement allowed else error code
+ */
+static int replacement_allowed(struct aa_profile *profile, int noreplace,
+			       const char **info)
+{
+	if (profile) {
+		if (profile->label.flags & FLAG_IMMUTIBLE) {
+			*info = "cannot replace immutable profile";
+			return -EPERM;
+		} else if (noreplace) {
+			*info = "profile already exists";
+			return -EEXIST;
+		}
+	}
+	return 0;
+}
+
+/* audit callback for net specific fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (ad->iface.ns) {
+		audit_log_format(ab, " ns=");
+		audit_log_untrustedstring(ab, ad->iface.ns);
+	}
+}
+
+/**
+ * audit_policy - Do auditing of policy changes
+ * @subj_label: label to check if it can manage policy
+ * @op: policy operation being performed
+ * @ns_name: name of namespace being manipulated
+ * @name: name of profile being manipulated (NOT NULL)
+ * @info: any extra information to be audited (MAYBE NULL)
+ * @error: error code
+ *
+ * Returns: the error to be returned after audit is done
+ */
+static int audit_policy(struct aa_label *subj_label, const char *op,
+			const char *ns_name, const char *name,
+			const char *info, int error)
+{
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, op);
+
+	ad.iface.ns = ns_name;
+	ad.name = name;
+	ad.info = info;
+	ad.error = error;
+	ad.subj_label = subj_label;
+
+	aa_audit_msg(AUDIT_APPARMOR_STATUS, &ad, audit_cb);
+
+	return error;
+}
+
+/* don't call out to other LSMs in the stack for apparmor policy admin
+ * permissions
+ */
+static int policy_ns_capable(const struct cred *subj_cred,
+			     struct aa_label *label,
+			     struct user_namespace *userns, int cap)
+{
+	int err;
+
+	/* check for MAC_ADMIN cap in cred */
+	err = cap_capable(subj_cred, userns, cap, CAP_OPT_NONE);
+	if (!err)
+		err = aa_capable(subj_cred, label, cap, CAP_OPT_NONE);
+
+	return err;
+}
+
+/**
+ * aa_policy_view_capable - check if viewing policy in at @ns is allowed
+ * @subj_cred: cred of subject
+ * @label: label that is trying to view policy in ns
+ * @ns: namespace being viewed by @label (may be NULL if @label's ns)
+ *
+ * Returns: true if viewing policy is allowed
+ *
+ * If @ns is NULL then the namespace being viewed is assumed to be the
+ * tasks current namespace.
+ */
+bool aa_policy_view_capable(const struct cred *subj_cred,
+			     struct aa_label *label, struct aa_ns *ns)
+{
+	struct user_namespace *user_ns = subj_cred->user_ns;
+	struct aa_ns *view_ns = labels_view(label);
+	bool root_in_user_ns = uid_eq(current_euid(), make_kuid(user_ns, 0)) ||
+			       in_egroup_p(make_kgid(user_ns, 0));
+	bool response = false;
+	if (!ns)
+		ns = view_ns;
+
+	if (root_in_user_ns && aa_ns_visible(view_ns, ns, true) &&
+	    (user_ns == &init_user_ns ||
+	     (unprivileged_userns_apparmor_policy != 0 &&
+	      user_ns->level == view_ns->level)))
+		response = true;
+
+	return response;
+}
+
+bool aa_policy_admin_capable(const struct cred *subj_cred,
+			     struct aa_label *label, struct aa_ns *ns)
+{
+	struct user_namespace *user_ns = subj_cred->user_ns;
+	bool capable = policy_ns_capable(subj_cred, label, user_ns,
+					 CAP_MAC_ADMIN) == 0;
+
+	AA_DEBUG(DEBUG_POLICY, "cap_mac_admin? %d\n", capable);
+	AA_DEBUG(DEBUG_POLICY, "policy locked? %d\n", aa_g_lock_policy);
+
+	return aa_policy_view_capable(subj_cred, label, ns) && capable &&
+		!aa_g_lock_policy;
+}
+
+bool aa_current_policy_view_capable(struct aa_ns *ns)
+{
+	struct aa_label *label;
+	bool needput, res;
+
+	label = __begin_current_label_crit_section(&needput);
+	res = aa_policy_view_capable(current_cred(), label, ns);
+	__end_current_label_crit_section(label, needput);
+
+	return res;
+}
+
+bool aa_current_policy_admin_capable(struct aa_ns *ns)
+{
+	struct aa_label *label;
+	bool needput, res;
+
+	label = __begin_current_label_crit_section(&needput);
+	res = aa_policy_admin_capable(current_cred(), label, ns);
+	__end_current_label_crit_section(label, needput);
+
+	return res;
+}
+
+static bool is_subset_of_obj_privilege(const struct cred *cred,
+				       struct aa_label *label,
+				       const struct cred *ocred)
+{
+	if (cred == ocred)
+		return true;
+
+	if (!aa_label_is_subset(label, cred_label(ocred)))
+		return false;
+	/* don't allow crossing userns for now */
+	if (cred->user_ns != ocred->user_ns)
+		return false;
+	if (!cap_issubset(cred->cap_inheritable, ocred->cap_inheritable))
+		return false;
+	if (!cap_issubset(cred->cap_permitted, ocred->cap_permitted))
+		return false;
+	if (!cap_issubset(cred->cap_effective, ocred->cap_effective))
+		return false;
+	if (!cap_issubset(cred->cap_bset, ocred->cap_bset))
+		return false;
+	if (!cap_issubset(cred->cap_ambient, ocred->cap_ambient))
+		return false;
+	return true;
+}
+
+
+/**
+ * aa_may_manage_policy - can the current task manage policy
+ * @subj_cred: subjects cred
+ * @label: label to check if it can manage policy
+ * @ns: namespace being managed by @label (may be NULL if @label's ns)
+ * @ocred: object cred if request is coming from an open object
+ * @mask: contains the policy manipulation operation being done
+ *
+ * Returns: 0 if the task is allowed to manipulate policy else error
+ */
+int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label,
+			 struct aa_ns *ns, const struct cred *ocred, u32 mask)
+{
+	const char *op;
+
+	if (mask & AA_MAY_REMOVE_POLICY)
+		op = OP_PROF_RM;
+	else if (mask & AA_MAY_REPLACE_POLICY)
+		op = OP_PROF_REPL;
+	else
+		op = OP_PROF_LOAD;
+
+	/* check if loading policy is locked out */
+	if (aa_g_lock_policy)
+		return audit_policy(label, op, NULL, NULL, "policy_locked",
+				    -EACCES);
+
+	if (ocred && !is_subset_of_obj_privilege(subj_cred, label, ocred))
+		return audit_policy(label, op, NULL, NULL,
+				    "not privileged for target profile",
+				    -EACCES);
+
+	if (!aa_policy_admin_capable(subj_cred, label, ns))
+		return audit_policy(label, op, NULL, NULL, "not policy admin",
+				    -EACCES);
+
+	/* TODO: add fine grained mediation of policy loads */
+	return 0;
+}
+
+static struct aa_profile *__list_lookup_parent(struct list_head *lh,
+					       struct aa_profile *profile)
+{
+	const char *base = basename(profile->base.hname);
+	long len = base - profile->base.hname;
+	struct aa_load_ent *ent;
+
+	/* parent won't have trailing // so remove from len */
+	if (len <= 2)
+		return NULL;
+	len -= 2;
+
+	list_for_each_entry(ent, lh, list) {
+		if (ent->new == profile)
+			continue;
+		if (strncmp(ent->new->base.hname, profile->base.hname, len) ==
+		    0 && ent->new->base.hname[len] == 0)
+			return ent->new;
+	}
+
+	return NULL;
+}
+
+/**
+ * __replace_profile - replace @old with @new on a list
+ * @old: profile to be replaced  (NOT NULL)
+ * @new: profile to replace @old with  (NOT NULL)
+ *
+ * Will duplicate and refcount elements that @new inherits from @old
+ * and will inherit @old children.
+ *
+ * refcount @new for list, put @old list refcount
+ *
+ * Requires: namespace list lock be held, or list not be shared
+ */
+static void __replace_profile(struct aa_profile *old, struct aa_profile *new)
+{
+	struct aa_profile *child, *tmp;
+
+	if (!list_empty(&old->base.profiles)) {
+		LIST_HEAD(lh);
+		list_splice_init_rcu(&old->base.profiles, &lh, synchronize_rcu);
+
+		list_for_each_entry_safe(child, tmp, &lh, base.list) {
+			struct aa_profile *p;
+
+			list_del_init(&child->base.list);
+			p = __find_child(&new->base.profiles, child->base.name);
+			if (p) {
+				/* @p replaces @child  */
+				__replace_profile(child, p);
+				continue;
+			}
+
+			/* inherit @child and its children */
+			/* TODO: update hname of inherited children */
+			/* list refcount transferred to @new */
+			p = aa_deref_parent(child);
+			rcu_assign_pointer(child->parent, aa_get_profile(new));
+			list_add_rcu(&child->base.list, &new->base.profiles);
+			aa_put_profile(p);
+		}
+	}
+
+	if (!rcu_access_pointer(new->parent)) {
+		struct aa_profile *parent = aa_deref_parent(old);
+		rcu_assign_pointer(new->parent, aa_get_profile(parent));
+	}
+	aa_label_replace(&old->label, &new->label);
+	/* migrate dents must come after label replacement b/c update */
+	__aafs_profile_migrate_dents(old, new);
+
+	if (list_empty(&new->base.list)) {
+		/* new is not on a list already */
+		list_replace_rcu(&old->base.list, &new->base.list);
+		aa_get_profile(new);
+		aa_put_profile(old);
+	} else
+		__list_remove_profile(old);
+}
+
+/**
+ * __lookup_replace - lookup replacement information for a profile
+ * @ns: namespace the lookup occurs in
+ * @hname: name of profile to lookup
+ * @noreplace: true if not replacing an existing profile
+ * @p: Returns - profile to be replaced
+ * @info: Returns - info string on why lookup failed
+ *
+ * Returns: profile to replace (no ref) on success else ptr error
+ */
+static int __lookup_replace(struct aa_ns *ns, const char *hname,
+			    bool noreplace, struct aa_profile **p,
+			    const char **info)
+{
+	*p = aa_get_profile(__lookup_profile(&ns->base, hname));
+	if (*p) {
+		int error = replacement_allowed(*p, noreplace, info);
+		if (error) {
+			*info = "profile can not be replaced";
+			return error;
+		}
+	}
+
+	return 0;
+}
+
+static void share_name(struct aa_profile *old, struct aa_profile *new)
+{
+	aa_put_str(new->base.hname);
+	aa_get_str(old->base.hname);
+	new->base.hname = old->base.hname;
+	new->base.name = old->base.name;
+	new->label.hname = old->label.hname;
+}
+
+/* Update to newest version of parent after previous replacements
+ * Returns: unrefcount newest version of parent
+ */
+static struct aa_profile *update_to_newest_parent(struct aa_profile *new)
+{
+	struct aa_profile *parent, *newest;
+
+	parent = rcu_dereference_protected(new->parent,
+					   mutex_is_locked(&new->ns->lock));
+	newest = aa_get_newest_profile(parent);
+
+	/* parent replaced in this atomic set? */
+	if (newest != parent) {
+		aa_put_profile(parent);
+		rcu_assign_pointer(new->parent, newest);
+	} else
+		aa_put_profile(newest);
+
+	return newest;
+}
+
+/**
+ * aa_replace_profiles - replace profile(s) on the profile list
+ * @policy_ns: namespace load is occurring on
+ * @label: label that is attempting to load/replace policy
+ * @mask: permission mask
+ * @udata: serialized data stream  (NOT NULL)
+ * @compressed_profile: The userspace-provided compressed profile. May be NULL
+ * @compressed_size: If compressed_data is not NULL, the compressed data size
+ *
+ * unpack and replace a profile on the profile list and uses of that profile
+ * by any task creds via invalidating the old version of the profile, which
+ * tasks will notice to update their own cred.  If the profile does not exist
+ * on the profile list it is added.
+ *
+ * Returns: size of data consumed else error code on failure.
+ */
+ssize_t aa_replace_profiles(struct aa_ns *policy_ns, struct aa_label *label,
+			    u32 mask, struct aa_loaddata *udata,
+			    char *compressed_profile, size_t compressed_size)
+{
+	const char *ns_name = NULL, *info = NULL;
+	struct aa_ns *ns = NULL;
+	struct aa_load_ent *ent, *tmp;
+	struct aa_loaddata *rawdata_ent;
+	const char *op;
+	ssize_t count, error;
+	LIST_HEAD(lh);
+
+	op = mask & AA_MAY_REPLACE_POLICY ? OP_PROF_REPL : OP_PROF_LOAD;
+	aa_get_profile_loaddata(udata);
+	/* released below */
+	error = aa_unpack(udata, &lh, &ns_name, compressed_profile, compressed_size);
+	if (error)
+		goto out;
+
+	/* ensure that profiles are all for the same ns
+	 * TODO: update locking to remove this constraint. All profiles in
+	 *       the load set must succeed as a set or the load will
+	 *       fail. Sort ent list and take ns locks in hierarchy order
+	 */
+	count = 0;
+	list_for_each_entry(ent, &lh, list) {
+		if (ns_name) {
+			if (ent->ns_name &&
+			    strcmp(ent->ns_name, ns_name) != 0) {
+				info = "policy load has mixed namespaces";
+				error = -EACCES;
+				goto fail;
+			}
+		} else if (ent->ns_name) {
+			if (count) {
+				info = "policy load has mixed namespaces";
+				error = -EACCES;
+				goto fail;
+			}
+			ns_name = ent->ns_name;
+			ent->ns_name = NULL;
+		} else
+			count++;
+	}
+	if (ns_name) {
+		ns = aa_prepare_ns(policy_ns ? policy_ns : labels_ns(label),
+				   ns_name);
+		if (IS_ERR(ns)) {
+			op = OP_PROF_LOAD;
+			info = "failed to prepare namespace";
+			error = PTR_ERR(ns);
+			ns = NULL;
+			ent = NULL;
+			goto fail;
+		}
+	} else
+		ns = aa_get_ns(policy_ns ? policy_ns : labels_ns(label));
+
+	mutex_lock_nested(&ns->lock, ns->level);
+	/* check for duplicate rawdata blobs: space and file dedup */
+	if (!list_empty(&ns->rawdata_list)) {
+		list_for_each_entry(rawdata_ent, &ns->rawdata_list, list) {
+			if (aa_rawdata_eq(rawdata_ent, udata)) {
+				struct aa_loaddata *tmp;
+
+				/*
+				 * Entries remain on rawdata_list with
+				 * pcount == 0 until do_ploaddata_rmfs()
+				 * runs; only take a live profile ref.
+				 */
+				tmp = aa_get_profile_loaddata_not0(rawdata_ent);
+				if (tmp) {
+					aa_put_profile_loaddata(udata);
+					udata = tmp;
+					break;
+				}
+			}
+		}
+	}
+	/* setup parent and ns info */
+	list_for_each_entry(ent, &lh, list) {
+		struct aa_policy *policy;
+		struct aa_profile *p;
+
+		if (aa_g_export_binary)
+			ent->new->rawdata = aa_get_profile_loaddata(udata);
+		error = __lookup_replace(ns, ent->new->base.hname,
+					 !(mask & AA_MAY_REPLACE_POLICY),
+					 &ent->old, &info);
+		if (error)
+			goto fail_lock;
+
+		if (ent->new->rename) {
+			error = __lookup_replace(ns, ent->new->rename,
+						!(mask & AA_MAY_REPLACE_POLICY),
+						&ent->rename, &info);
+			if (error)
+				goto fail_lock;
+		}
+
+		/* released when @new is freed */
+		ent->new->ns = aa_get_ns(ns);
+
+		if (ent->old || ent->rename)
+			continue;
+
+		/* no ref on policy only use inside lock */
+		p = NULL;
+		policy = __lookup_parent(ns, ent->new->base.hname);
+		if (!policy) {
+			/* first check for parent in the load set */
+			p = __list_lookup_parent(&lh, ent->new);
+			if (!p) {
+				/*
+				 * fill in missing parent with null
+				 * profile that doesn't have
+				 * permissions. This allows for
+				 * individual profile loading where
+				 * the child is loaded before the
+				 * parent, and outside of the current
+				 * atomic set. This unfortunately can
+				 * happen with some userspaces.  The
+				 * null profile will be replaced once
+				 * the parent is loaded.
+				 */
+				policy = __create_missing_ancestors(ns,
+							ent->new->base.hname,
+							GFP_KERNEL);
+				if (!policy) {
+					error = -ENOENT;
+					info = "parent does not exist";
+					goto fail_lock;
+				}
+			}
+		}
+		if (!p && policy != &ns->base)
+			/* released on profile replacement or free_profile */
+			p = (struct aa_profile *) policy;
+		rcu_assign_pointer(ent->new->parent, aa_get_profile(p));
+	}
+
+	/* create new fs entries for introspection if needed */
+	if (!udata->dents[AAFS_LOADDATA_DIR] && aa_g_export_binary) {
+		error = __aa_fs_create_rawdata(ns, udata);
+		if (error) {
+			info = "failed to create raw_data dir and files";
+			ent = NULL;
+			goto fail_lock;
+		}
+	}
+	list_for_each_entry(ent, &lh, list) {
+		if (!ent->old) {
+			struct dentry *parent;
+			if (rcu_access_pointer(ent->new->parent)) {
+				struct aa_profile *p;
+				p = aa_deref_parent(ent->new);
+				parent = prof_child_dir(p);
+			} else
+				parent = ns_subprofs_dir(ent->new->ns);
+			error = __aafs_profile_mkdir(ent->new, parent);
+		}
+
+		if (error) {
+			info = "failed to create";
+			goto fail_lock;
+		}
+	}
+
+	/* Done with checks that may fail - do actual replacement */
+	__aa_bump_ns_revision(ns);
+	if (aa_g_export_binary)
+		__aa_loaddata_update(udata, ns->revision);
+	list_for_each_entry_safe(ent, tmp, &lh, list) {
+		list_del_init(&ent->list);
+		op = (!ent->old && !ent->rename) ? OP_PROF_LOAD : OP_PROF_REPL;
+
+		if (ent->old && ent->old->rawdata == ent->new->rawdata &&
+		    ent->new->rawdata) {
+			/* dedup actual profile replacement */
+			audit_policy(label, op, ns_name, ent->new->base.hname,
+				     "same as current profile, skipping",
+				     error);
+			/* break refcount cycle with proxy. */
+			aa_put_proxy(ent->new->label.proxy);
+			ent->new->label.proxy = NULL;
+			goto skip;
+		}
+
+		if (!aa_g_export_binary) {
+			if (ent->old && ent->old->rawdata &&
+			    ent->old->dents[AAFS_LOADDATA_DIR]) {
+				/* remove rawdata symlinks because the symlink
+				 * target will be removed
+				 */
+				__aa_remove_rawdata_symlink_dents(ent->old);
+			}
+		}
+
+		/*
+		 * TODO: finer dedup based on profile range in data. Load set
+		 * can differ but profile may remain unchanged
+		 */
+		audit_policy(label, op, ns_name, ent->new->base.hname, NULL,
+			     error);
+
+		if (ent->old) {
+			share_name(ent->old, ent->new);
+			__replace_profile(ent->old, ent->new);
+			if (aa_g_export_binary) {
+				/* recreate rawdata symlinks */
+				if (!ent->old->rawdata)
+					__aa_create_rawdata_symlink_dents(ent->new);
+			}
+		} else {
+			struct list_head *lh;
+
+			if (rcu_access_pointer(ent->new->parent)) {
+				struct aa_profile *parent;
+
+				parent = update_to_newest_parent(ent->new);
+				lh = &parent->base.profiles;
+			} else
+				lh = &ns->base.profiles;
+			__add_profile(lh, ent->new);
+		}
+	skip:
+		aa_load_ent_free(ent);
+	}
+	__aa_labelset_update_subtree(ns);
+	mutex_unlock(&ns->lock);
+
+out:
+	aa_put_ns(ns);
+
+	ssize_t udata_sz = udata->size;
+
+	aa_put_profile_loaddata(udata);
+	kfree(ns_name);
+
+	if (error)
+		return error;
+	return udata_sz;
+
+fail_lock:
+	mutex_unlock(&ns->lock);
+
+	/* audit cause of failure */
+	op = (ent && !ent->old) ? OP_PROF_LOAD : OP_PROF_REPL;
+fail:
+	  audit_policy(label, op, ns_name, ent ? ent->new->base.hname : NULL,
+		       info, error);
+	/* audit status that rest of profiles in the atomic set failed too */
+	info = "valid profile in failed atomic policy load";
+	list_for_each_entry(tmp, &lh, list) {
+		if (tmp == ent) {
+			info = "unchecked profile in failed atomic policy load";
+			/* skip entry that caused failure */
+			continue;
+		}
+		op = (!tmp->old) ? OP_PROF_LOAD : OP_PROF_REPL;
+		audit_policy(label, op, ns_name, tmp->new->base.hname, info,
+			     error);
+	}
+	list_for_each_entry_safe(ent, tmp, &lh, list) {
+		list_del_init(&ent->list);
+		aa_load_ent_free(ent);
+	}
+
+	goto out;
+}
+
+/**
+ * aa_remove_profiles - remove profile(s) from the system
+ * @policy_ns: namespace the remove is being done from
+ * @subj: label attempting to remove policy
+ * @fqname: name of the profile or namespace to remove  (NOT NULL)
+ * @size: size of the name
+ *
+ * Remove a profile or sub namespace from the current namespace, so that
+ * they can not be found anymore and mark them as replaced by unconfined
+ *
+ * NOTE: removing confinement does not restore rlimits to preconfinement values
+ *
+ * Returns: size of data consume else error code if fails
+ */
+ssize_t aa_remove_profiles(struct aa_ns *policy_ns, struct aa_label *subj,
+			   char *fqname, size_t size)
+{
+	struct aa_ns *ns = NULL;
+	struct aa_profile *profile = NULL;
+	const char *name = fqname, *info = NULL;
+	const char *ns_name = NULL;
+	ssize_t error = 0;
+
+	if (*fqname == 0) {
+		info = "no profile specified";
+		error = -ENOENT;
+		goto fail;
+	}
+
+	if (fqname[0] == ':') {
+		size_t ns_len;
+
+		name = aa_splitn_fqname(fqname, size, &ns_name, &ns_len);
+		/* released below */
+		ns = aa_lookupn_ns(policy_ns ? policy_ns : labels_ns(subj),
+				   ns_name, ns_len);
+		if (!ns) {
+			info = "namespace does not exist";
+			error = -ENOENT;
+			goto fail;
+		}
+	} else
+		/* released below */
+		ns = aa_get_ns(policy_ns ? policy_ns : labels_ns(subj));
+
+	if (!name) {
+		/* remove namespace - can only happen if fqname[0] == ':' */
+		mutex_lock_nested(&ns->parent->lock, ns->parent->level);
+		__aa_bump_ns_revision(ns);
+		__aa_remove_ns(ns);
+		mutex_unlock(&ns->parent->lock);
+	} else {
+		/* remove profile */
+		mutex_lock_nested(&ns->lock, ns->level);
+		profile = aa_get_profile(__lookup_profile(&ns->base, name));
+		if (!profile) {
+			error = -ENOENT;
+			info = "profile does not exist";
+			goto fail_ns_lock;
+		}
+		name = profile->base.hname;
+		__aa_bump_ns_revision(ns);
+		__remove_profile(profile);
+		__aa_labelset_update_subtree(ns);
+		mutex_unlock(&ns->lock);
+	}
+
+	/* don't fail removal if audit fails */
+	(void) audit_policy(subj, OP_PROF_RM, ns_name, name, info,
+			    error);
+	aa_put_ns(ns);
+	aa_put_profile(profile);
+	return size;
+
+fail_ns_lock:
+	mutex_unlock(&ns->lock);
+	aa_put_ns(ns);
+
+fail:
+	(void) audit_policy(subj, OP_PROF_RM, ns_name, name, info,
+			    error);
+	return error;
+}
diff --git a/security/apparmor/policy_compat.c b/security/apparmor/policy_compat.c
new file mode 100644
index 000000000..94e4b781d
--- /dev/null
+++ b/security/apparmor/policy_compat.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor functions for unpacking policy loaded
+ * from userspace.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2022 Canonical Ltd.
+ *
+ * Code to provide backwards compatibility with older policy versions,
+ * by converting/mapping older policy formats into the newer internal
+ * formats.
+ */
+
+#include <linux/ctype.h>
+#include <linux/errno.h>
+
+#include "include/lib.h"
+#include "include/policy_unpack.h"
+#include "include/policy_compat.h"
+
+/* remap old accept table embedded permissions to separate permission table */
+static u32 dfa_map_xindex(u16 mask)
+{
+	u16 old_index = (mask >> 10) & 0xf;
+	u32 index = 0;
+
+	if (mask & 0x100)
+		index |= AA_X_UNSAFE;
+	if (mask & 0x200)
+		index |= AA_X_INHERIT;
+	if (mask & 0x80)
+		index |= AA_X_UNCONFINED;
+
+	if (old_index == 1) {
+		index |= AA_X_UNCONFINED;
+	} else if (old_index == 2) {
+		index |= AA_X_NAME;
+	} else if (old_index == 3) {
+		index |= AA_X_NAME | AA_X_CHILD;
+	} else if (old_index) {
+		index |= AA_X_TABLE;
+		index |= old_index - 4;
+	}
+
+	return index;
+}
+
+/*
+ * map old dfa inline permissions to new format
+ */
+#define dfa_user_allow(dfa, state) (((ACCEPT_TABLE(dfa)[state]) & 0x7f) | \
+				    ((ACCEPT_TABLE(dfa)[state]) & 0x80000000))
+#define dfa_user_xbits(dfa, state) (((ACCEPT_TABLE(dfa)[state]) >> 7) & 0x7f)
+#define dfa_user_audit(dfa, state) ((ACCEPT_TABLE2(dfa)[state]) & 0x7f)
+#define dfa_user_quiet(dfa, state) (((ACCEPT_TABLE2(dfa)[state]) >> 7) & 0x7f)
+#define dfa_user_xindex(dfa, state) \
+	(dfa_map_xindex(ACCEPT_TABLE(dfa)[state] & 0x3fff))
+
+#define dfa_other_allow(dfa, state) ((((ACCEPT_TABLE(dfa)[state]) >> 14) & \
+				      0x7f) |				\
+				     ((ACCEPT_TABLE(dfa)[state]) & 0x80000000))
+#define dfa_other_xbits(dfa, state) \
+	((((ACCEPT_TABLE(dfa)[state]) >> 7) >> 14) & 0x7f)
+#define dfa_other_audit(dfa, state) (((ACCEPT_TABLE2(dfa)[state]) >> 14) & 0x7f)
+#define dfa_other_quiet(dfa, state) \
+	((((ACCEPT_TABLE2(dfa)[state]) >> 7) >> 14) & 0x7f)
+#define dfa_other_xindex(dfa, state) \
+	dfa_map_xindex((ACCEPT_TABLE(dfa)[state] >> 14) & 0x3fff)
+
+/**
+ * map_old_perms - map old file perms layout to the new layout
+ * @old: permission set in old mapping
+ *
+ * Returns: new permission mapping
+ */
+static u32 map_old_perms(u32 old)
+{
+	u32 new = old & 0xf;
+
+	if (old & MAY_READ)
+		new |= AA_MAY_GETATTR | AA_MAY_OPEN;
+	if (old & MAY_WRITE)
+		new |= AA_MAY_SETATTR | AA_MAY_CREATE | AA_MAY_DELETE |
+		       AA_MAY_CHMOD | AA_MAY_CHOWN | AA_MAY_OPEN;
+	if (old & 0x10)
+		new |= AA_MAY_LINK;
+	/* the old mapping lock and link_subset flags where overlaid
+	 * and use was determined by part of a pair that they were in
+	 */
+	if (old & 0x20)
+		new |= AA_MAY_LOCK | AA_LINK_SUBSET;
+	if (old & 0x40)	/* AA_EXEC_MMAP */
+		new |= AA_EXEC_MMAP;
+
+	return new;
+}
+
+static void compute_fperms_allow(struct aa_perms *perms, const struct aa_dfa *dfa,
+				 aa_state_t state)
+{
+	perms->allow |= AA_MAY_GETATTR;
+
+	/* change_profile wasn't determined by ownership in old mapping */
+	if (ACCEPT_TABLE(dfa)[state] & 0x80000000)
+		perms->allow |= AA_MAY_CHANGE_PROFILE;
+	if (ACCEPT_TABLE(dfa)[state] & 0x40000000)
+		perms->allow |= AA_MAY_ONEXEC;
+}
+
+static struct aa_perms compute_fperms_user(const struct aa_dfa *dfa,
+					   aa_state_t state)
+{
+	struct aa_perms perms = { };
+
+	perms.allow = map_old_perms(dfa_user_allow(dfa, state));
+	perms.audit = map_old_perms(dfa_user_audit(dfa, state));
+	perms.quiet = map_old_perms(dfa_user_quiet(dfa, state));
+	perms.xindex = dfa_user_xindex(dfa, state);
+
+	compute_fperms_allow(&perms, dfa, state);
+
+	return perms;
+}
+
+static struct aa_perms compute_fperms_other(const struct aa_dfa *dfa,
+					    aa_state_t state)
+{
+	struct aa_perms perms = { };
+
+	perms.allow = map_old_perms(dfa_other_allow(dfa, state));
+	perms.audit = map_old_perms(dfa_other_audit(dfa, state));
+	perms.quiet = map_old_perms(dfa_other_quiet(dfa, state));
+	perms.xindex = dfa_other_xindex(dfa, state);
+
+	compute_fperms_allow(&perms, dfa, state);
+
+	return perms;
+}
+
+/**
+ * compute_fperms - convert dfa compressed perms to internal perms and store
+ *		    them so they can be retrieved later.
+ * @dfa: a dfa using fperms to remap to internal permissions
+ * @size: Returns the permission table size
+ *
+ * Returns: remapped perm table
+ */
+static struct aa_perms *compute_fperms(const struct aa_dfa *dfa,
+				       u32 *size)
+{
+	aa_state_t state;
+	unsigned int state_count;
+	struct aa_perms *table;
+
+	AA_BUG(!dfa);
+
+	state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
+	/* DFAs are restricted from having a state_count of less than 2 */
+	table = kvzalloc_objs(struct aa_perms, state_count * 2);
+	if (!table)
+		return NULL;
+	*size = state_count * 2;
+
+	for (state = 0; state < state_count; state++) {
+		table[state * 2] = compute_fperms_user(dfa, state);
+		table[state * 2 + 1] = compute_fperms_other(dfa, state);
+	}
+
+	return table;
+}
+
+static struct aa_perms *compute_xmatch_perms(const struct aa_dfa *xmatch,
+				      u32 *size)
+{
+	struct aa_perms *perms;
+	int state;
+	int state_count;
+
+	AA_BUG(!xmatch);
+
+	state_count = xmatch->tables[YYTD_ID_BASE]->td_lolen;
+	/* DFAs are restricted from having a state_count of less than 2 */
+	perms = kvzalloc_objs(struct aa_perms, state_count);
+	if (!perms)
+		return NULL;
+	*size = state_count;
+
+	/* zero init so skip the trap state (state == 0) */
+	for (state = 1; state < state_count; state++)
+		perms[state].allow = dfa_user_allow(xmatch, state);
+
+	return perms;
+}
+
+static u32 map_other(u32 x)
+{
+	return ((x & 0x3) << 8) |	/* SETATTR/GETATTR */
+		((x & 0x1c) << 18) |	/* ACCEPT/BIND/LISTEN */
+		((x & 0x60) << 19);	/* SETOPT/GETOPT */
+}
+
+static u32 map_xbits(u32 x)
+{
+	return ((x & 0x1) << 7) |
+		((x & 0x7e) << 9);
+}
+
+static struct aa_perms compute_perms_entry(const struct aa_dfa *dfa,
+					   aa_state_t state,
+					   u32 version)
+{
+	struct aa_perms perms = { };
+
+	perms.allow = dfa_user_allow(dfa, state);
+	perms.audit = dfa_user_audit(dfa, state);
+	perms.quiet = dfa_user_quiet(dfa, state);
+
+	/*
+	 * This mapping is convulated due to history.
+	 * v1-v4: only file perms, which are handled by compute_fperms
+	 * v5: added policydb which dropped user conditional to gain new
+	 *     perm bits, but had to map around the xbits because the
+	 *     userspace compiler was still munging them.
+	 * v9: adds using the xbits in policydb because the compiler now
+	 *     supports treating policydb permission bits different.
+	 *     Unfortunately there is no way to force auditing on the
+	 *     perms represented by the xbits
+	 */
+	perms.allow |= map_other(dfa_other_allow(dfa, state));
+	if (VERSION_LE(version, v8))
+		perms.allow |= AA_MAY_LOCK;
+	else
+		perms.allow |= map_xbits(dfa_user_xbits(dfa, state));
+
+	/*
+	 * for v5-v9 perm mapping in the policydb, the other set is used
+	 * to extend the general perm set
+	 */
+	perms.audit |= map_other(dfa_other_audit(dfa, state));
+	perms.quiet |= map_other(dfa_other_quiet(dfa, state));
+	if (VERSION_GT(version, v8))
+		perms.quiet |= map_xbits(dfa_other_xbits(dfa, state));
+
+	return perms;
+}
+
+static struct aa_perms *compute_perms(const struct aa_dfa *dfa, u32 version,
+				      u32 *size)
+{
+	unsigned int state;
+	unsigned int state_count;
+	struct aa_perms *table;
+
+	AA_BUG(!dfa);
+
+	state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
+	/* DFAs are restricted from having a state_count of less than 2 */
+	table = kvzalloc_objs(struct aa_perms, state_count);
+	if (!table)
+		return NULL;
+	*size = state_count;
+
+	/* zero init so skip the trap state (state == 0) */
+	for (state = 1; state < state_count; state++) {
+		table[state] = compute_perms_entry(dfa, state, version);
+		AA_DEBUG(DEBUG_UNPACK,
+			 "[%d]: (0x%x/0x%x/0x%x//0x%x/0x%x//0x%x), converted from accept1: 0x%x, accept2: 0x%x",
+			 state, table[state].allow, table[state].deny,
+			 table[state].prompt, table[state].audit,
+			 table[state].quiet, table[state].xindex,
+			 ACCEPT_TABLE(dfa)[state], ACCEPT_TABLE2(dfa)[state]);
+	}
+	return table;
+}
+
+/**
+ * remap_dfa_accept - remap old dfa accept table to be an index
+ * @dfa: dfa to do the remapping on
+ * @factor: scaling factor for the index conversion.
+ *
+ * Used in conjunction with compute_Xperms, it converts old style perms
+ * that are encoded in the dfa accept tables to the new style where
+ * there is a permission table and the accept table is an index into
+ * the permission table.
+ */
+static void remap_dfa_accept(struct aa_dfa *dfa, unsigned int factor)
+{
+	unsigned int state;
+	unsigned int state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
+
+	AA_BUG(!dfa);
+
+	for (state = 0; state < state_count; state++) {
+		ACCEPT_TABLE(dfa)[state] = state * factor;
+		ACCEPT_TABLE2(dfa)[state] = factor > 1 ? ACCEPT_FLAG_OWNER : 0;
+	}
+}
+
+/* TODO: merge different dfa mappings into single map_policy fn */
+int aa_compat_map_xmatch(struct aa_policydb *policy)
+{
+	policy->perms = compute_xmatch_perms(policy->dfa, &policy->size);
+	if (!policy->perms)
+		return -ENOMEM;
+
+	remap_dfa_accept(policy->dfa, 1);
+
+	return 0;
+}
+
+int aa_compat_map_policy(struct aa_policydb *policy, u32 version)
+{
+	policy->perms = compute_perms(policy->dfa, version, &policy->size);
+	if (!policy->perms)
+		return -ENOMEM;
+
+	remap_dfa_accept(policy->dfa, 1);
+
+	return 0;
+}
+
+int aa_compat_map_file(struct aa_policydb *policy)
+{
+	policy->perms = compute_fperms(policy->dfa, &policy->size);
+	if (!policy->perms)
+		return -ENOMEM;
+
+	remap_dfa_accept(policy->dfa, 2);
+
+	return 0;
+}
diff --git a/security/apparmor/policy_ns.c b/security/apparmor/policy_ns.c
new file mode 100644
index 000000000..5a907a875
--- /dev/null
+++ b/security/apparmor/policy_ns.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy manipulation functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * AppArmor policy namespaces, allow for different sets of policies
+ * to be loaded for tasks within the namespace.
+ */
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "include/apparmor.h"
+#include "include/cred.h"
+#include "include/policy_ns.h"
+#include "include/label.h"
+#include "include/policy.h"
+
+/* kernel label */
+struct aa_label *kernel_t;
+
+/* root profile namespace */
+struct aa_ns *root_ns;
+const char *aa_hidden_ns_name = "---";
+
+/**
+ * aa_ns_visible - test if @view is visible from @curr
+ * @curr: namespace to treat as the parent (NOT NULL)
+ * @view: namespace to test if visible from @curr (NOT NULL)
+ * @subns: whether view of a subns is allowed
+ *
+ * Returns: true if @view is visible from @curr else false
+ */
+bool aa_ns_visible(struct aa_ns *curr, struct aa_ns *view, bool subns)
+{
+	if (curr == view)
+		return true;
+
+	if (!subns)
+		return false;
+
+	for ( ; view; view = view->parent) {
+		if (view->parent == curr)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * aa_ns_name - Find the ns name to display for @view from @curr
+ * @curr: current namespace (NOT NULL)
+ * @view: namespace attempting to view (NOT NULL)
+ * @subns: are subns visible
+ *
+ * Returns: name of @view visible from @curr
+ */
+const char *aa_ns_name(struct aa_ns *curr, struct aa_ns *view, bool subns)
+{
+	/* if view == curr then the namespace name isn't displayed */
+	if (curr == view)
+		return "";
+
+	if (aa_ns_visible(curr, view, subns)) {
+		/* at this point if a ns is visible it is in a view ns
+		 * thus the curr ns.hname is a prefix of its name.
+		 * Only output the virtualized portion of the name
+		 * Add + 2 to skip over // separating curr hname prefix
+		 * from the visible tail of the views hname
+		 */
+		return view->base.hname + strlen(curr->base.hname) + 2;
+	}
+
+	return aa_hidden_ns_name;
+}
+
+static struct aa_profile *alloc_unconfined(const char *name)
+{
+	struct aa_profile *profile;
+
+	profile = aa_alloc_null(NULL, name, GFP_KERNEL);
+	if (!profile)
+		return NULL;
+
+	profile->label.flags |= FLAG_IX_ON_NAME_ERROR |
+		FLAG_IMMUTIBLE | FLAG_NS_COUNT | FLAG_UNCONFINED;
+	profile->mode = APPARMOR_UNCONFINED;
+
+	return profile;
+}
+
+/**
+ * alloc_ns - allocate, initialize and return a new namespace
+ * @prefix: parent namespace name (MAYBE NULL)
+ * @name: a preallocated name  (NOT NULL)
+ *
+ * Returns: refcounted namespace or NULL on failure.
+ */
+static struct aa_ns *alloc_ns(const char *prefix, const char *name)
+{
+	struct aa_ns *ns;
+
+	ns = kzalloc_obj(*ns);
+	AA_DEBUG(DEBUG_POLICY, "%s(%p)\n", __func__, ns);
+	if (!ns)
+		return NULL;
+	if (!aa_policy_init(&ns->base, prefix, name, GFP_KERNEL))
+		goto fail_ns;
+
+	INIT_LIST_HEAD(&ns->sub_ns);
+	INIT_LIST_HEAD(&ns->rawdata_list);
+	mutex_init(&ns->lock);
+	init_waitqueue_head(&ns->wait);
+
+	/* released by aa_free_ns() */
+	ns->unconfined = alloc_unconfined("unconfined");
+	if (!ns->unconfined)
+		goto fail_unconfined;
+	/* ns and ns->unconfined share ns->unconfined refcount */
+	ns->unconfined->ns = ns;
+
+	atomic_set(&ns->uniq_null, 0);
+
+	aa_labelset_init(&ns->labels);
+
+	return ns;
+
+fail_unconfined:
+	aa_policy_destroy(&ns->base);
+fail_ns:
+	kfree_sensitive(ns);
+	return NULL;
+}
+
+/**
+ * aa_free_ns - free a profile namespace
+ * @ns: the namespace to free  (MAYBE NULL)
+ *
+ * Requires: All references to the namespace must have been put, if the
+ *           namespace was referenced by a profile confining a task,
+ */
+void aa_free_ns(struct aa_ns *ns)
+{
+	if (!ns)
+		return;
+
+	aa_policy_destroy(&ns->base);
+	aa_labelset_destroy(&ns->labels);
+	aa_put_ns(ns->parent);
+
+	ns->unconfined->ns = NULL;
+	aa_free_profile(ns->unconfined);
+	kfree_sensitive(ns);
+}
+
+/**
+ * __aa_lookupn_ns - lookup the namespace matching @hname
+ * @view: namespace to search in  (NOT NULL)
+ * @hname: hierarchical ns name  (NOT NULL)
+ * @n: length of @hname
+ *
+ * Requires: rcu_read_lock be held
+ *
+ * Returns: unrefcounted ns pointer or NULL if not found
+ *
+ * Do a relative name lookup, recursing through profile tree.
+ */
+struct aa_ns *__aa_lookupn_ns(struct aa_ns *view, const char *hname, size_t n)
+{
+	struct aa_ns *ns = view;
+	const char *split;
+
+	for (split = strnstr(hname, "//", n); split;
+	     split = strnstr(hname, "//", n)) {
+		ns = __aa_findn_ns(&ns->sub_ns, hname, split - hname);
+		if (!ns)
+			return NULL;
+
+		n -= split + 2 - hname;
+		hname = split + 2;
+	}
+
+	if (n)
+		return __aa_findn_ns(&ns->sub_ns, hname, n);
+	return NULL;
+}
+
+/**
+ * aa_lookupn_ns  -  look up a policy namespace relative to @view
+ * @view: namespace to search in  (NOT NULL)
+ * @name: name of namespace to find  (NOT NULL)
+ * @n: length of @name
+ *
+ * Returns: a refcounted namespace on the list, or NULL if no namespace
+ *          called @name exists.
+ *
+ * refcount released by caller
+ */
+struct aa_ns *aa_lookupn_ns(struct aa_ns *view, const char *name, size_t n)
+{
+	struct aa_ns *ns = NULL;
+
+	rcu_read_lock();
+	ns = aa_get_ns(__aa_lookupn_ns(view, name, n));
+	rcu_read_unlock();
+
+	return ns;
+}
+
+static struct aa_ns *__aa_create_ns(struct aa_ns *parent, const char *name,
+				    struct dentry *dir)
+{
+	struct aa_ns *ns;
+	int error;
+
+	AA_BUG(!parent);
+	AA_BUG(!name);
+	AA_BUG(!mutex_is_locked(&parent->lock));
+
+	if (parent->level > MAX_NS_DEPTH)
+		return ERR_PTR(-ENOSPC);
+	ns = alloc_ns(parent->base.hname, name);
+	if (!ns)
+		return ERR_PTR(-ENOMEM);
+	ns->level = parent->level + 1;
+	mutex_lock_nested(&ns->lock, ns->level);
+	error = __aafs_ns_mkdir(ns, ns_subns_dir(parent), name, dir);
+	if (error) {
+		AA_ERROR("Failed to create interface for ns %s\n",
+			 ns->base.name);
+		mutex_unlock(&ns->lock);
+		aa_free_ns(ns);
+		return ERR_PTR(error);
+	}
+	ns->parent = aa_get_ns(parent);
+	list_add_rcu(&ns->base.list, &parent->sub_ns);
+	/* add list ref */
+	aa_get_ns(ns);
+	mutex_unlock(&ns->lock);
+
+	return ns;
+}
+
+/**
+ * __aa_find_or_create_ns - create an ns, fail if it already exists
+ * @parent: the parent of the namespace being created
+ * @name: the name of the namespace
+ * @dir: if not null the dir to put the ns entries in
+ *
+ * Returns: the a refcounted ns that has been add or an ERR_PTR
+ */
+struct aa_ns *__aa_find_or_create_ns(struct aa_ns *parent, const char *name,
+				     struct dentry *dir)
+{
+	struct aa_ns *ns;
+
+	AA_BUG(!mutex_is_locked(&parent->lock));
+
+	/* try and find the specified ns */
+	/* released by caller */
+	ns = aa_get_ns(__aa_find_ns(&parent->sub_ns, name));
+	if (!ns)
+		ns = __aa_create_ns(parent, name, dir);
+	else
+		ns = ERR_PTR(-EEXIST);
+
+	/* return ref */
+	return ns;
+}
+
+/**
+ * aa_prepare_ns - find an existing or create a new namespace of @name
+ * @parent: ns to treat as parent
+ * @name: the namespace to find or add  (NOT NULL)
+ *
+ * Returns: refcounted namespace or PTR_ERR if failed to create one
+ */
+struct aa_ns *aa_prepare_ns(struct aa_ns *parent, const char *name)
+{
+	struct aa_ns *ns;
+
+	mutex_lock_nested(&parent->lock, parent->level);
+	/* try and find the specified ns and if it doesn't exist create it */
+	/* released by caller */
+	ns = aa_get_ns(__aa_find_ns(&parent->sub_ns, name));
+	if (!ns)
+		ns = __aa_create_ns(parent, name, NULL);
+	mutex_unlock(&parent->lock);
+
+	/* return ref */
+	return ns;
+}
+
+static void __ns_list_release(struct list_head *head);
+
+/**
+ * destroy_ns - remove everything contained by @ns
+ * @ns: namespace to have it contents removed  (NOT NULL)
+ */
+static void destroy_ns(struct aa_ns *ns)
+{
+	if (!ns)
+		return;
+
+	mutex_lock_nested(&ns->lock, ns->level);
+	/* release all profiles in this namespace */
+	__aa_profile_list_release(&ns->base.profiles);
+
+	/* release all sub namespaces */
+	__ns_list_release(&ns->sub_ns);
+
+	if (ns->parent) {
+		unsigned long flags;
+
+		write_lock_irqsave(&ns->labels.lock, flags);
+		__aa_proxy_redirect(ns_unconfined(ns),
+				    ns_unconfined(ns->parent));
+		write_unlock_irqrestore(&ns->labels.lock, flags);
+	}
+	__aafs_ns_rmdir(ns);
+	mutex_unlock(&ns->lock);
+}
+
+/**
+ * __aa_remove_ns - remove a namespace and all its children
+ * @ns: namespace to be removed  (NOT NULL)
+ *
+ * Requires: ns->parent->lock be held and ns removed from parent.
+ */
+void __aa_remove_ns(struct aa_ns *ns)
+{
+	/* remove ns from namespace list */
+	list_del_rcu(&ns->base.list);
+	destroy_ns(ns);
+	aa_put_ns(ns);
+}
+
+/**
+ * __ns_list_release - remove all profile namespaces on the list put refs
+ * @head: list of profile namespaces  (NOT NULL)
+ *
+ * Requires: namespace lock be held
+ */
+static void __ns_list_release(struct list_head *head)
+{
+	struct aa_ns *ns, *tmp;
+
+	list_for_each_entry_safe(ns, tmp, head, base.list)
+		__aa_remove_ns(ns);
+
+}
+
+/**
+ * aa_alloc_root_ns - allocate the root profile namespace
+ *
+ * Returns: %0 on success else error
+ *
+ */
+int __init aa_alloc_root_ns(void)
+{
+	struct aa_profile *kernel_p;
+
+	/* released by aa_free_root_ns - used as list ref*/
+	root_ns = alloc_ns(NULL, "root");
+	if (!root_ns)
+		return -ENOMEM;
+
+	kernel_p = alloc_unconfined("kernel_t");
+	if (!kernel_p) {
+		destroy_ns(root_ns);
+		aa_free_ns(root_ns);
+		return -ENOMEM;
+	}
+	kernel_t = &kernel_p->label;
+	root_ns->unconfined->ns = aa_get_ns(root_ns);
+
+	return 0;
+}
+
+ /**
+  * aa_free_root_ns - free the root profile namespace
+  */
+void __init aa_free_root_ns(void)
+{
+	 struct aa_ns *ns = root_ns;
+
+	 root_ns = NULL;
+
+	 aa_label_free(kernel_t);
+	 destroy_ns(ns);
+	 aa_put_ns(ns);
+}
diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
new file mode 100644
index 000000000..f1fc48e72
--- /dev/null
+++ b/security/apparmor/policy_unpack.c
@@ -0,0 +1,1821 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor functions for unpacking policy loaded from
+ * userspace.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * AppArmor uses a serialized binary format for loading policy. To find
+ * policy format documentation see Documentation/admin-guide/LSM/apparmor.rst
+ * All policy is validated before it is used.
+ */
+
+#include <linux/unaligned.h>
+#include <kunit/visibility.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/zstd.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/crypto.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/net.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/policy_unpack.h"
+#include "include/policy_compat.h"
+#include "include/signal.h"
+
+/* audit callback for unpack fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (ad->iface.ns) {
+		audit_log_format(ab, " ns=");
+		audit_log_untrustedstring(ab, ad->iface.ns);
+	}
+	if (ad->name) {
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, ad->name);
+	}
+	if (ad->iface.pos)
+		audit_log_format(ab, " offset=%ld", ad->iface.pos);
+}
+
+/**
+ * audit_iface - do audit message for policy unpacking/load/replace/remove
+ * @new: profile if it has been allocated (MAYBE NULL)
+ * @ns_name: name of the ns the profile is to be loaded to (MAY BE NULL)
+ * @name: name of the profile being manipulated (MAYBE NULL)
+ * @info: any extra info about the failure (MAYBE NULL)
+ * @e: buffer position info
+ * @error: error code
+ *
+ * Returns: %0 or error
+ */
+static int audit_iface(struct aa_profile *new, const char *ns_name,
+		       const char *name, const char *info, struct aa_ext *e,
+		       int error)
+{
+	struct aa_profile *profile = labels_profile(aa_current_raw_label());
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL);
+	if (e)
+		ad.iface.pos = e->pos - e->start;
+	ad.iface.ns = ns_name;
+	if (new)
+		ad.name = new->base.hname;
+	else
+		ad.name = name;
+	ad.info = info;
+	ad.error = error;
+
+	return aa_audit(AUDIT_APPARMOR_STATUS, profile, &ad, audit_cb);
+}
+
+void __aa_loaddata_update(struct aa_loaddata *data, long revision)
+{
+	AA_BUG(!data);
+	AA_BUG(!data->ns);
+	AA_BUG(!mutex_is_locked(&data->ns->lock));
+	AA_BUG(data->revision > revision);
+
+	data->revision = revision;
+	if ((data->dents[AAFS_LOADDATA_REVISION])) {
+		struct inode *inode;
+
+		inode = d_inode(data->dents[AAFS_LOADDATA_DIR]);
+		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+
+		inode = d_inode(data->dents[AAFS_LOADDATA_REVISION]);
+		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+	}
+}
+
+bool aa_rawdata_eq(struct aa_loaddata *l, struct aa_loaddata *r)
+{
+	if (l->size != r->size)
+		return false;
+	if (l->compressed_size != r->compressed_size)
+		return false;
+	if (aa_g_hash_policy && memcmp(l->hash, r->hash, aa_hash_size()) != 0)
+		return false;
+	return memcmp(l->data, r->data, r->compressed_size ?: r->size) == 0;
+}
+
+static void do_loaddata_free(struct aa_loaddata *d)
+{
+	kfree_sensitive(d->hash);
+	kfree_sensitive(d->name);
+	kvfree(d->data);
+	kfree_sensitive(d);
+}
+
+void aa_loaddata_kref(struct kref *kref)
+{
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata,
+					     count.count);
+
+	do_loaddata_free(d);
+}
+
+/*
+ * need to take the ns mutex lock which is NOT safe most places that
+ * put_loaddata is called, so we have to delay freeing it
+ */
+static void do_ploaddata_rmfs(struct work_struct *work)
+{
+	struct aa_loaddata *d = container_of(work, struct aa_loaddata, work);
+	struct aa_ns *ns = aa_get_ns(d->ns);
+
+	if (ns) {
+		mutex_lock_nested(&ns->lock, ns->level);
+		/* remove fs ref to loaddata */
+		__aa_fs_remove_rawdata(d);
+		mutex_unlock(&ns->lock);
+		aa_put_ns(ns);
+	}
+	/* called by dropping last pcount, so drop its associated icount */
+	aa_put_i_loaddata(d);
+}
+
+void aa_ploaddata_kref(struct kref *kref)
+{
+	struct aa_loaddata *d = container_of(kref, struct aa_loaddata, pcount);
+
+	if (d) {
+		INIT_WORK(&d->work, do_ploaddata_rmfs);
+		schedule_work(&d->work);
+	}
+}
+
+struct aa_loaddata *aa_loaddata_alloc(size_t size)
+{
+	struct aa_loaddata *d;
+
+	d = kzalloc_obj(*d);
+	if (d == NULL)
+		return ERR_PTR(-ENOMEM);
+	d->data = kvzalloc(size, GFP_KERNEL);
+	if (!d->data) {
+		kfree(d);
+		return ERR_PTR(-ENOMEM);
+	}
+	kref_init(&d->count.count);
+	d->count.reftype = REF_RAWDATA;
+	kref_init(&d->pcount);
+	INIT_LIST_HEAD(&d->list);
+
+	return d;
+}
+
+/* test if read will be in packed data bounds */
+VISIBLE_IF_KUNIT bool aa_inbounds(struct aa_ext *e, size_t size)
+{
+	return (size <= e->end - e->pos);
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_inbounds);
+
+/**
+ * aa_unpack_u16_chunk - test and do bounds checking for a u16 size based chunk
+ * @e: serialized data read head (NOT NULL)
+ * @chunk: start address for chunk of data (NOT NULL)
+ *
+ * Returns: the size of chunk found with the read head at the end of the chunk.
+ */
+VISIBLE_IF_KUNIT size_t aa_unpack_u16_chunk(struct aa_ext *e, char **chunk)
+{
+	size_t size = 0;
+	void *pos = e->pos;
+
+	if (!aa_inbounds(e, sizeof(u16)))
+		goto fail;
+	size = le16_to_cpu(get_unaligned((__le16 *) e->pos));
+	e->pos += sizeof(__le16);
+	if (!aa_inbounds(e, size))
+		goto fail;
+	*chunk = e->pos;
+	e->pos += size;
+	return size;
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_u16_chunk);
+
+/* unpack control byte */
+VISIBLE_IF_KUNIT bool aa_unpack_X(struct aa_ext *e, enum aa_code code)
+{
+	if (!aa_inbounds(e, 1))
+		return false;
+	if (*(u8 *) e->pos != code)
+		return false;
+	e->pos++;
+	return true;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_X);
+
+/**
+ * aa_unpack_nameX - check is the next element is of type X with a name of @name
+ * @e: serialized data extent information  (NOT NULL)
+ * @code: type code
+ * @name: name to match to the serialized element.  (MAYBE NULL)
+ *
+ * check that the next serialized data element is of type X and has a tag
+ * name @name.  If @name is specified then there must be a matching
+ * name element in the stream.  If @name is NULL any name element will be
+ * skipped and only the typecode will be tested.
+ *
+ * Returns true on success (both type code and name tests match) and the read
+ * head is advanced past the headers
+ *
+ * Returns: false if either match fails, the read head does not move
+ */
+VISIBLE_IF_KUNIT bool aa_unpack_nameX(struct aa_ext *e, enum aa_code code, const char *name)
+{
+	/*
+	 * May need to reset pos if name or type doesn't match
+	 */
+	void *pos = e->pos;
+	/*
+	 * Check for presence of a tagname, and if present name size
+	 * AA_NAME tag value is a u16.
+	 */
+	if (aa_unpack_X(e, AA_NAME)) {
+		char *tag = NULL;
+		size_t size = aa_unpack_u16_chunk(e, &tag);
+		/* if a name is specified it must match. otherwise skip tag */
+		if (name && (!size || tag[size-1] != '\0' || strcmp(name, tag)))
+			goto fail;
+	} else if (name) {
+		/* if a name is specified and there is no name tag fail */
+		goto fail;
+	}
+
+	/* now check if type code matches */
+	if (aa_unpack_X(e, code))
+		return true;
+
+fail:
+	e->pos = pos;
+	return false;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_nameX);
+
+static bool unpack_u8(struct aa_ext *e, u8 *data, const char *name)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_U8, name)) {
+		if (!aa_inbounds(e, sizeof(u8)))
+			goto fail;
+		if (data)
+			*data = *((u8 *)e->pos);
+		e->pos += sizeof(u8);
+		return true;
+	}
+
+fail:
+	e->pos = pos;
+	return false;
+}
+
+VISIBLE_IF_KUNIT bool aa_unpack_u32(struct aa_ext *e, u32 *data, const char *name)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_U32, name)) {
+		if (!aa_inbounds(e, sizeof(u32)))
+			goto fail;
+		if (data)
+			*data = le32_to_cpu(get_unaligned((__le32 *) e->pos));
+		e->pos += sizeof(u32);
+		return true;
+	}
+
+fail:
+	e->pos = pos;
+	return false;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_u32);
+
+VISIBLE_IF_KUNIT bool aa_unpack_u64(struct aa_ext *e, u64 *data, const char *name)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_U64, name)) {
+		if (!aa_inbounds(e, sizeof(u64)))
+			goto fail;
+		if (data)
+			*data = le64_to_cpu(get_unaligned((__le64 *) e->pos));
+		e->pos += sizeof(u64);
+		return true;
+	}
+
+fail:
+	e->pos = pos;
+	return false;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_u64);
+
+static bool aa_unpack_cap_low(struct aa_ext *e, kernel_cap_t *data, const char *name)
+{
+	u32 val;
+
+	if (!aa_unpack_u32(e, &val, name))
+		return false;
+	data->val = val;
+	return true;
+}
+
+static bool aa_unpack_cap_high(struct aa_ext *e, kernel_cap_t *data, const char *name)
+{
+	u32 val;
+
+	if (!aa_unpack_u32(e, &val, name))
+		return false;
+	data->val = (u32)data->val | ((u64)val << 32);
+	return true;
+}
+
+VISIBLE_IF_KUNIT bool aa_unpack_array(struct aa_ext *e, const char *name, u16 *size)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_ARRAY, name)) {
+		if (!aa_inbounds(e, sizeof(u16)))
+			goto fail;
+		*size = le16_to_cpu(get_unaligned((__le16 *) e->pos));
+		e->pos += sizeof(u16);
+		return true;
+	}
+
+fail:
+	e->pos = pos;
+	return false;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_array);
+
+VISIBLE_IF_KUNIT size_t aa_unpack_blob(struct aa_ext *e, char **blob, const char *name)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_BLOB, name)) {
+		u32 size;
+		if (!aa_inbounds(e, sizeof(u32)))
+			goto fail;
+		size = le32_to_cpu(get_unaligned((__le32 *) e->pos));
+		e->pos += sizeof(u32);
+		if (aa_inbounds(e, (size_t) size)) {
+			*blob = e->pos;
+			e->pos += size;
+			return size;
+		}
+	}
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_blob);
+
+VISIBLE_IF_KUNIT int aa_unpack_str(struct aa_ext *e, const char **string, const char *name)
+{
+	char *src_str;
+	size_t size = 0;
+	void *pos = e->pos;
+	*string = NULL;
+	if (aa_unpack_nameX(e, AA_STRING, name)) {
+		size = aa_unpack_u16_chunk(e, &src_str);
+		if (size) {
+			/* strings are null terminated, length is size - 1 */
+			if (src_str[size - 1] != 0)
+				goto fail;
+			*string = src_str;
+
+			return size;
+		}
+	}
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_str);
+
+VISIBLE_IF_KUNIT int aa_unpack_strdup(struct aa_ext *e, char **string, const char *name)
+{
+	const char *tmp;
+	void *pos = e->pos;
+	int res = aa_unpack_str(e, &tmp, name);
+	*string = NULL;
+
+	if (!res)
+		return 0;
+
+	*string = kmemdup(tmp, res, GFP_KERNEL);
+	if (!*string) {
+		e->pos = pos;
+		return 0;
+	}
+
+	return res;
+}
+EXPORT_SYMBOL_IF_KUNIT(aa_unpack_strdup);
+
+
+/**
+ * unpack_dfa - unpack a file rule dfa
+ * @e: serialized data extent information (NOT NULL)
+ * @flags: dfa flags to check
+ *
+ * returns dfa or ERR_PTR or NULL if no dfa
+ */
+static struct aa_dfa *unpack_dfa(struct aa_ext *e, int flags)
+{
+	char *blob = NULL;
+	size_t size;
+	struct aa_dfa *dfa = NULL;
+
+	size = aa_unpack_blob(e, &blob, "aadfa");
+	if (size) {
+		/*
+		 * The dfa is aligned with in the blob to 8 bytes
+		 * from the beginning of the stream.
+		 * alignment adjust needed by dfa unpack
+		 */
+		size_t sz = blob - (char *) e->start -
+			((e->pos - e->start) & 7);
+		size_t pad = ALIGN(sz, 8) - sz;
+		if (aa_g_paranoid_load)
+			flags |= DFA_FLAG_VERIFY_STATES;
+		dfa = aa_dfa_unpack(blob + pad, size - pad, flags);
+
+		if (IS_ERR(dfa))
+			return dfa;
+
+	}
+
+	return dfa;
+}
+
+static int process_strs_entry(char *str, int size, bool multi)
+{
+	int c = 1;
+
+	if (size <= 0)
+		return -1;
+	if (multi) {
+		if (size < 2)
+			return -2;
+		/* multi ends with double \0 */
+		if (str[size - 2])
+			return -3;
+	}
+
+	char *save = str;
+	char *pos = str;
+	char *end = multi ? str + size - 2 : str + size - 1;
+	/* count # of internal \0 */
+	while (str < end) {
+		if (str == pos) {
+			/* starts with ... */
+			if (!*str) {
+				AA_DEBUG(DEBUG_UNPACK,
+					 "starting with null save=%lu size %d c=%d",
+					 (unsigned long)(str - save), size, c);
+				return -4;
+			}
+			if (isspace(*str))
+				return -5;
+			if (*str == ':') {
+				/* :ns_str\0str\0
+				 * first character after : must be valid
+				 */
+				if (!str[1])
+					return -6;
+			}
+		} else if (!*str) {
+			if (*pos == ':')
+				*str = ':';
+			else
+				c++;
+			pos = str +  1;
+		}
+		str++;
+	} /* while */
+
+	return c;
+}
+
+/**
+ * unpack_strs_table - unpack a profile transition table
+ * @e: serialized data extent information  (NOT NULL)
+ * @name: name of table (MAY BE NULL)
+ * @multi: allow multiple strings on a single entry
+ * @strs: str table to unpack to (NOT NULL)
+ *
+ * Returns: 0 if table successfully unpacked or not present, else error
+ */
+static int unpack_strs_table(struct aa_ext *e, const char *name, bool multi,
+			      struct aa_str_table *strs)
+{
+	void *saved_pos = e->pos;
+	struct aa_str_table_ent *table = NULL;
+	int error = -EPROTO;
+
+	/* exec table is optional */
+	if (aa_unpack_nameX(e, AA_STRUCT, name)) {
+		u16 size;
+		int i;
+
+		if (!aa_unpack_array(e, NULL, &size))
+			/*
+			 * Note: index into trans table array is a max
+			 * of 2^24, but unpack array can only unpack
+			 * an array of 2^16 in size atm so no need
+			 * for size check here
+			 */
+			goto fail;
+		table = kzalloc_objs(struct aa_str_table_ent, size);
+		if (!table) {
+			error = -ENOMEM;
+			goto fail;
+		}
+		strs->table = table;
+		strs->size = size;
+		for (i = 0; i < size; i++) {
+			char *str;
+			int c, size2 = aa_unpack_strdup(e, &str, NULL);
+			/* aa_unpack_strdup verifies that the last character is
+			 * null termination byte.
+			 */
+			c = process_strs_entry(str, size2, multi);
+			if (c <= 0) {
+				AA_DEBUG(DEBUG_UNPACK, "process_strs %d i %d pos %ld",
+					 c, i,
+					 (unsigned long)(e->pos - saved_pos));
+				goto fail;
+			}
+			if (!multi && c > 1) {
+				AA_DEBUG(DEBUG_UNPACK, "!multi && c > 1");
+				/* fail - all other cases with embedded \0 */
+				goto fail;
+			}
+			table[i].strs = str;
+			table[i].count = c;
+			table[i].size = size2;
+		}
+		if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+	return 0;
+
+fail:
+	aa_destroy_str_table(strs);
+	e->pos = saved_pos;
+	return error;
+}
+
+static bool unpack_xattrs(struct aa_ext *e, struct aa_profile *profile)
+{
+	void *pos = e->pos;
+
+	if (aa_unpack_nameX(e, AA_STRUCT, "xattrs")) {
+		u16 size;
+		int i;
+
+		if (!aa_unpack_array(e, NULL, &size))
+			goto fail;
+		profile->attach.xattr_count = size;
+		profile->attach.xattrs = kcalloc(size, sizeof(char *), GFP_KERNEL);
+		if (!profile->attach.xattrs)
+			goto fail;
+		for (i = 0; i < size; i++) {
+			if (!aa_unpack_strdup(e, &profile->attach.xattrs[i], NULL))
+				goto fail;
+		}
+		if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	return true;
+
+fail:
+	e->pos = pos;
+	return false;
+}
+
+static bool unpack_secmark(struct aa_ext *e, struct aa_ruleset *rules)
+{
+	void *pos = e->pos;
+	u16 size;
+	int i;
+
+	if (aa_unpack_nameX(e, AA_STRUCT, "secmark")) {
+		if (!aa_unpack_array(e, NULL, &size))
+			goto fail;
+
+		rules->secmark = kzalloc_objs(struct aa_secmark, size);
+		if (!rules->secmark)
+			goto fail;
+
+		rules->secmark_count = size;
+
+		for (i = 0; i < size; i++) {
+			if (!unpack_u8(e, &rules->secmark[i].audit, NULL))
+				goto fail;
+			if (!unpack_u8(e, &rules->secmark[i].deny, NULL))
+				goto fail;
+			if (!aa_unpack_strdup(e, &rules->secmark[i].label, NULL))
+				goto fail;
+		}
+		if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	return true;
+
+fail:
+	if (rules->secmark) {
+		for (i = 0; i < size; i++)
+			kfree_sensitive(rules->secmark[i].label);
+		kfree_sensitive(rules->secmark);
+		rules->secmark_count = 0;
+		rules->secmark = NULL;
+	}
+
+	e->pos = pos;
+	return false;
+}
+
+static bool unpack_rlimits(struct aa_ext *e, struct aa_ruleset *rules)
+{
+	void *pos = e->pos;
+
+	/* rlimits are optional */
+	if (aa_unpack_nameX(e, AA_STRUCT, "rlimits")) {
+		u16 size;
+		int i;
+		u32 tmp = 0;
+		if (!aa_unpack_u32(e, &tmp, NULL))
+			goto fail;
+		rules->rlimits.mask = tmp;
+
+		if (!aa_unpack_array(e, NULL, &size) ||
+		    size > RLIM_NLIMITS)
+			goto fail;
+		for (i = 0; i < size; i++) {
+			u64 tmp2 = 0;
+			int a = aa_map_resource(i);
+			if (!aa_unpack_u64(e, &tmp2, NULL))
+				goto fail;
+			rules->rlimits.limits[a].rlim_max = tmp2;
+		}
+		if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+	return true;
+
+fail:
+	e->pos = pos;
+	return false;
+}
+
+
+static bool verify_tags(struct aa_tags_struct *tags, const char **info)
+{
+	if ((tags->hdrs.size && !tags->hdrs.table) ||
+	    (!tags->hdrs.size && tags->hdrs.table)) {
+		*info = "failed verification tag.hdrs disagree";
+		return false;
+	}
+	if ((tags->sets.size && !tags->sets.table) ||
+	    (!tags->sets.size && tags->sets.table)) {
+		*info = "failed verification tag.sets disagree";
+		return false;
+	}
+	if ((tags->strs.size && !tags->strs.table) ||
+	    (!tags->strs.size && tags->strs.table)) {
+		*info = "failed verification tags->strs disagree";
+		return false;
+	}
+	/* no data present */
+	if (!tags->sets.size && !tags->hdrs.size && !tags->strs.size) {
+		return true;
+	} else if (!(tags->sets.size && tags->hdrs.size && tags->strs.size)) {
+		/* some data present but not all */
+		*info = "failed verification tags partial data present";
+		return false;
+	}
+
+	u32 i;
+
+	for (i = 0; i < tags->sets.size; i++) {
+		/* count followed by count indexes into hdrs */
+		u32 cnt = tags->sets.table[i];
+
+		if ((u64)i + cnt >= tags->sets.size) {
+			AA_DEBUG(DEBUG_UNPACK,
+				 "tagset too large %d+%d > sets.table[%d]",
+				 i, cnt, tags->sets.size);
+			*info = "failed verification tagset too large";
+			return false;
+		}
+		for (; cnt; cnt--) {
+			if (tags->sets.table[++i] >= tags->hdrs.size) {
+				AA_DEBUG(DEBUG_UNPACK,
+					 "tagsets idx out of bounds cnt %d sets.table[%d] >= %d",
+					 cnt, i-1, tags->hdrs.size);
+				*info = "failed verification tagsets idx out of bounds";
+				return false;
+			}
+		}
+	}
+	for (i = 0; i < tags->hdrs.size; i++) {
+		u32 idx = tags->hdrs.table[i].tags;
+
+		if (idx >= tags->strs.size) {
+			AA_DEBUG(DEBUG_UNPACK,
+				 "tag.hdrs idx oob idx %d > tags->strs.size=%d",
+				 idx, tags->strs.size);
+			*info = "failed verification tags.hdrs idx out of bounds";
+			return false;
+		}
+		if (tags->hdrs.table[i].count != tags->strs.table[idx].count) {
+			AA_DEBUG(DEBUG_UNPACK, "hdrs.table[%d].count=%d != tags->strs.table[%d]=%d",
+				 i, tags->hdrs.table[i].count, idx, tags->strs.table[idx].count);
+			*info = "failed verification tagd.hdrs[idx].count";
+			return false;
+		}
+		if (tags->hdrs.table[i].size != tags->strs.table[idx].size) {
+			AA_DEBUG(DEBUG_UNPACK, "hdrs.table[%d].size=%d != strs.table[%d].size=%d",
+				 i, tags->hdrs.table[i].size, idx, tags->strs.table[idx].size);
+			*info = "failed verification tagd.hdrs[idx].size";
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int unpack_tagsets(struct aa_ext *e, struct aa_tags_struct *tags)
+{
+	u32 *sets;
+	u16 i, size;
+	int error = -EPROTO;
+	void *pos = e->pos;
+
+	if (!aa_unpack_array(e, "sets", &size))
+		goto fail_reset;
+	sets = kcalloc(size, sizeof(u32), GFP_KERNEL);
+	if (!sets) {
+		error = -ENOMEM;
+		goto fail_reset;
+	}
+	for (i = 0; i < size; i++) {
+		if (!aa_unpack_u32(e, &sets[i], NULL))
+			goto fail;
+	}
+	if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+		goto fail;
+
+	tags->sets.size = size;
+	tags->sets.table = sets;
+
+	return 0;
+
+fail:
+	kfree_sensitive(sets);
+fail_reset:
+	e->pos = pos;
+	return error;
+}
+
+static bool unpack_tag_header_ent(struct aa_ext *e, struct aa_tags_header *h)
+{
+	return aa_unpack_u32(e, &h->mask, NULL) &&
+		aa_unpack_u32(e, &h->count, NULL) &&
+		aa_unpack_u32(e, &h->size, NULL) &&
+		aa_unpack_u32(e, &h->tags, NULL);
+}
+
+static int unpack_tag_headers(struct aa_ext *e, struct aa_tags_struct *tags)
+{
+	struct aa_tags_header *hdrs;
+	u16 i, size;
+	int error = -EPROTO;
+	void *pos = e->pos;
+
+	if (!aa_unpack_array(e, "hdrs", &size))
+		goto fail_reset;
+	hdrs = kzalloc_objs(struct aa_tags_header, size);
+	if (!hdrs) {
+		error = -ENOMEM;
+		goto fail_reset;
+	}
+	for (i = 0; i < size; i++) {
+		if (!unpack_tag_header_ent(e, &hdrs[i]))
+			goto fail;
+	}
+	if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+		goto fail;
+
+	tags->hdrs.size = size;
+	tags->hdrs.table = hdrs;
+	AA_DEBUG(DEBUG_UNPACK, "headers %ld size %d", (long) hdrs, size);
+	return true;
+
+fail:
+	kfree_sensitive(hdrs);
+fail_reset:
+	e->pos = pos;
+	return error;
+}
+
+
+static int unpack_tags(struct aa_ext *e, struct aa_tags_struct *tags,
+	const char **info)
+{
+	int error = -EPROTO;
+	void *pos = e->pos;
+
+	AA_BUG(!tags);
+	/* policy tags are optional */
+	if (aa_unpack_nameX(e, AA_STRUCT, "tags")) {
+		u32 version;
+
+		if (!aa_unpack_u32(e, &version, "version") || version != 1) {
+			*info = "invalid tags version";
+			goto fail_reset;
+		}
+		error = unpack_strs_table(e, "strs", true, &tags->strs);
+		if (error) {
+			*info = "failed to unpack profile tag.strs";
+			goto fail;
+		}
+		error = unpack_tag_headers(e, tags);
+		if (error) {
+			*info = "failed to unpack profile tag.headers";
+			goto fail;
+		}
+		error = unpack_tagsets(e, tags);
+		if (error) {
+			*info = "failed to unpack profile tag.sets";
+			goto fail;
+		}
+		error = -EPROTO;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+
+		if (!verify_tags(tags, info))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	aa_destroy_tags(tags);
+fail_reset:
+	e->pos = pos;
+	return error;
+}
+
+static bool unpack_perm(struct aa_ext *e, u32 version, struct aa_perms *perm)
+{
+	u32 reserved;
+
+	if (version != 1)
+		return false;
+
+	/* reserved entry is for later expansion, discard for now */
+	return	aa_unpack_u32(e, &reserved, NULL) &&
+		aa_unpack_u32(e, &perm->allow, NULL) &&
+		aa_unpack_u32(e, &perm->deny, NULL) &&
+		aa_unpack_u32(e, &perm->subtree, NULL) &&
+		aa_unpack_u32(e, &perm->cond, NULL) &&
+		aa_unpack_u32(e, &perm->kill, NULL) &&
+		aa_unpack_u32(e, &perm->complain, NULL) &&
+		aa_unpack_u32(e, &perm->prompt, NULL) &&
+		aa_unpack_u32(e, &perm->audit, NULL) &&
+		aa_unpack_u32(e, &perm->quiet, NULL) &&
+		aa_unpack_u32(e, &perm->hide, NULL) &&
+		aa_unpack_u32(e, &perm->xindex, NULL) &&
+		aa_unpack_u32(e, &perm->tag, NULL) &&
+		aa_unpack_u32(e, &perm->label, NULL);
+}
+
+static ssize_t unpack_perms_table(struct aa_ext *e, struct aa_perms **perms)
+{
+	void *pos = e->pos;
+	u16 size = 0;
+
+	AA_BUG(!perms);
+	/*
+	 * policy perms are optional, in which case perms are embedded
+	 * in the dfa accept table
+	 */
+	if (aa_unpack_nameX(e, AA_STRUCT, "perms")) {
+		int i;
+		u32 version;
+
+		if (!aa_unpack_u32(e, &version, "version"))
+			goto fail_reset;
+		if (!aa_unpack_array(e, NULL, &size))
+			goto fail_reset;
+		*perms = kzalloc_objs(struct aa_perms, size);
+		if (!*perms) {
+			e->pos = pos;
+			return -ENOMEM;
+		}
+		for (i = 0; i < size; i++) {
+			if (!unpack_perm(e, version, &(*perms)[i]))
+				goto fail;
+		}
+		if (!aa_unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	} else
+		*perms = NULL;
+
+	return size;
+
+fail:
+	kfree(*perms);
+fail_reset:
+	e->pos = pos;
+	return -EPROTO;
+}
+
+static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy,
+		      bool required_dfa, bool required_trans,
+		      const char **info)
+{
+	struct aa_policydb *pdb;
+	void *pos = e->pos;
+	int i, flags, error = -EPROTO;
+	ssize_t size;
+	u32 version = 0;
+
+	pdb = aa_alloc_pdb(GFP_KERNEL);
+	if (!pdb)
+		return -ENOMEM;
+
+	AA_DEBUG(DEBUG_UNPACK, "unpacking tags");
+	if (unpack_tags(e, &pdb->tags, info) < 0)
+		goto fail;
+	AA_DEBUG(DEBUG_UNPACK, "done unpacking tags");
+
+	size = unpack_perms_table(e, &pdb->perms);
+	if (size < 0) {
+		error = size;
+		pdb->perms = NULL;
+		*info = "failed to unpack - perms";
+		goto fail;
+	}
+	pdb->size = size;
+
+	if (pdb->perms) {
+		/* perms table present accept is index */
+		flags = TO_ACCEPT1_FLAG(YYTD_DATA32);
+		if (aa_unpack_u32(e, &version, "permsv") && version > 2)
+			/* accept2 used for dfa flags */
+			flags |= TO_ACCEPT2_FLAG(YYTD_DATA32);
+	} else {
+		/* packed perms in accept1 and accept2 */
+		flags = TO_ACCEPT1_FLAG(YYTD_DATA32) |
+			TO_ACCEPT2_FLAG(YYTD_DATA32);
+	}
+
+	pdb->dfa = unpack_dfa(e, flags);
+	if (IS_ERR(pdb->dfa)) {
+		error = PTR_ERR(pdb->dfa);
+		pdb->dfa = NULL;
+		*info = "failed to unpack - dfa";
+		goto fail;
+	} else if (!pdb->dfa) {
+		if (required_dfa) {
+			*info = "missing required dfa";
+			goto fail;
+		}
+	} else {
+		/*
+		 * only unpack the following if a dfa is present
+		 *
+		 * sadly start was given different names for file and policydb
+		 * but since it is optional we can try both
+		 */
+		if (!aa_unpack_u32(e, &pdb->start[0], "start"))
+			/* default start state */
+			pdb->start[0] = DFA_START;
+		if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
+			/* default start state for xmatch and file dfa */
+			pdb->start[AA_CLASS_FILE] = DFA_START;
+		}
+
+		size_t state_count = pdb->dfa->tables[YYTD_ID_BASE]->td_lolen;
+
+		if (pdb->start[0] >= state_count ||
+		    pdb->start[AA_CLASS_FILE] >= state_count) {
+			*info = "invalid dfa start state";
+			goto fail;
+		}
+
+		/* setup class index */
+		for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
+			pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
+						    i);
+		}
+	}
+
+	/* accept2 is in some cases being allocated, even with perms */
+	if (pdb->dfa && pdb->perms && !pdb->dfa->tables[YYTD_ID_ACCEPT2]) {
+		/* add dfa flags table missing in v2 */
+		u32 noents = pdb->dfa->tables[YYTD_ID_ACCEPT]->td_lolen;
+		u16 tdflags = pdb->dfa->tables[YYTD_ID_ACCEPT]->td_flags;
+		size_t tsize = table_size(noents, tdflags);
+
+		pdb->dfa->tables[YYTD_ID_ACCEPT2] = kvzalloc(tsize, GFP_KERNEL);
+		if (!pdb->dfa->tables[YYTD_ID_ACCEPT2]) {
+			*info = "failed to alloc dfa flags table";
+			error = -ENOMEM;
+			goto fail;
+		}
+		pdb->dfa->tables[YYTD_ID_ACCEPT2]->td_lolen = noents;
+		pdb->dfa->tables[YYTD_ID_ACCEPT2]->td_flags = tdflags;
+	}
+	/*
+	 * Unfortunately due to a bug in earlier userspaces, a
+	 * transition table may be present even when the dfa is
+	 * not. For compatibility reasons unpack and discard.
+	 */
+	error = unpack_strs_table(e, "xtable", false, &pdb->trans);
+	if (error && required_trans) {
+		*info = "failed to unpack profile transition table";
+		goto fail;
+	}
+
+	if (!pdb->dfa && pdb->trans.table)
+		aa_destroy_str_table(&pdb->trans);
+
+	/* TODO:
+	 * - move compat mapping here, requires dfa merging first
+	 * - move verify here, it has to be done after compat mappings
+	 * - move free of unneeded trans table here, has to be done
+	 *   after perm mapping.
+	 */
+	*policy = pdb;
+	return 0;
+
+fail:
+	aa_put_pdb(pdb);
+	e->pos = pos;
+	return error;
+}
+
+static u32 strhash(const void *data, u32 len, u32 seed)
+{
+	const char * const *key = data;
+
+	return jhash(*key, strlen(*key), seed);
+}
+
+static int datacmp(struct rhashtable_compare_arg *arg, const void *obj)
+{
+	const struct aa_data *data = obj;
+	const char * const *key = arg->key;
+
+	return strcmp(data->key, *key);
+}
+
+/**
+ * unpack_profile - unpack a serialized profile
+ * @e: serialized data extent information (NOT NULL)
+ * @ns_name: pointer of newly allocated copy of %NULL in case of error
+ *
+ * NOTE: unpack profile sets audit struct if there is a failure
+ */
+static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
+{
+	struct aa_ruleset *rules;
+	struct aa_profile *profile = NULL;
+	const char *tmpname, *tmpns = NULL, *name = NULL;
+	const char *info = "failed to unpack profile";
+	size_t ns_len;
+	struct rhashtable_params params = { 0 };
+	char *key = NULL, *disconnected = NULL;
+	struct aa_data *data;
+	int error = -EPROTO;
+	kernel_cap_t tmpcap;
+	u32 tmp;
+
+	*ns_name = NULL;
+
+	/* check that we have the right struct being passed */
+	if (!aa_unpack_nameX(e, AA_STRUCT, "profile"))
+		goto fail;
+	if (!aa_unpack_str(e, &name, NULL))
+		goto fail;
+	if (*name == '\0')
+		goto fail;
+
+	tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
+	if (tmpns) {
+		if (!tmpname) {
+			info = "empty profile name";
+			goto fail;
+		}
+		*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
+		if (!*ns_name) {
+			info = "out of memory";
+			error = -ENOMEM;
+			goto fail;
+		}
+		name = tmpname;
+	}
+
+	profile = aa_alloc_profile(name, NULL, GFP_KERNEL);
+	if (!profile) {
+		info = "out of memory";
+		error = -ENOMEM;
+		goto fail;
+	}
+	rules = profile->label.rules[0];
+
+	/* profile renaming is optional */
+	(void) aa_unpack_str(e, &profile->rename, "rename");
+
+	/* attachment string is optional */
+	(void) aa_unpack_str(e, &profile->attach.xmatch_str, "attach");
+
+	/* xmatch is optional and may be NULL */
+	error = unpack_pdb(e, &profile->attach.xmatch, false, false, &info);
+	if (error) {
+		info = "bad xmatch";
+		goto fail;
+	}
+
+	/* neither xmatch_len not xmatch_perms are optional if xmatch is set */
+	if (profile->attach.xmatch->dfa) {
+		if (!aa_unpack_u32(e, &tmp, NULL)) {
+			info = "missing xmatch len";
+			goto fail;
+		}
+		profile->attach.xmatch_len = tmp;
+		profile->attach.xmatch->start[AA_CLASS_XMATCH] = DFA_START;
+		if (!profile->attach.xmatch->perms) {
+			error = aa_compat_map_xmatch(profile->attach.xmatch);
+			if (error) {
+				info = "failed to convert xmatch permission table";
+				goto fail;
+			}
+		}
+	}
+
+	/* disconnected attachment string is optional */
+	(void) aa_unpack_strdup(e, &disconnected, "disconnected");
+	profile->disconnected = disconnected;
+
+	/* optional */
+	(void) aa_unpack_u32(e, &profile->signal, "kill");
+	if (profile->signal < 1 || profile->signal > MAXMAPPED_SIG) {
+		info = "profile kill.signal invalid value";
+		goto fail;
+	}
+	/* per profile debug flags (complain, audit) */
+	if (!aa_unpack_nameX(e, AA_STRUCT, "flags")) {
+		info = "profile missing flags";
+		goto fail;
+	}
+	info = "failed to unpack profile flags";
+	if (!aa_unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp & PACKED_FLAG_HAT)
+		profile->label.flags |= FLAG_HAT;
+	if (tmp & PACKED_FLAG_DEBUG1)
+		profile->label.flags |= FLAG_DEBUG1;
+	if (tmp & PACKED_FLAG_DEBUG2)
+		profile->label.flags |= FLAG_DEBUG2;
+	if (!aa_unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp == PACKED_MODE_COMPLAIN || (e->version & FORCE_COMPLAIN_FLAG)) {
+		profile->mode = APPARMOR_COMPLAIN;
+	} else if (tmp == PACKED_MODE_ENFORCE) {
+		profile->mode = APPARMOR_ENFORCE;
+	} else if (tmp == PACKED_MODE_KILL) {
+		profile->mode = APPARMOR_KILL;
+	} else if (tmp == PACKED_MODE_UNCONFINED) {
+		profile->mode = APPARMOR_UNCONFINED;
+		profile->label.flags |= FLAG_UNCONFINED;
+	} else if (tmp == PACKED_MODE_USER) {
+		profile->mode = APPARMOR_USER;
+	} else {
+		goto fail;
+	}
+	if (!aa_unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp)
+		profile->audit = AUDIT_ALL;
+
+	if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+		goto fail;
+
+	/* path_flags is optional */
+	if (aa_unpack_u32(e, &profile->path_flags, "path_flags"))
+		profile->path_flags |= profile->label.flags &
+			PATH_MEDIATE_DELETED;
+	else
+		/* set a default value if path_flags field is not present */
+		profile->path_flags = PATH_MEDIATE_DELETED;
+
+	info = "failed to unpack profile capabilities";
+	if (!aa_unpack_cap_low(e, &rules->caps.allow, NULL))
+		goto fail;
+	if (!aa_unpack_cap_low(e, &rules->caps.audit, NULL))
+		goto fail;
+	if (!aa_unpack_cap_low(e, &rules->caps.quiet, NULL))
+		goto fail;
+	if (!aa_unpack_cap_low(e, &tmpcap, NULL))
+		goto fail;
+
+	info = "failed to unpack upper profile capabilities";
+	if (aa_unpack_nameX(e, AA_STRUCT, "caps64")) {
+		/* optional upper half of 64 bit caps */
+		if (!aa_unpack_cap_high(e, &rules->caps.allow, NULL))
+			goto fail;
+		if (!aa_unpack_cap_high(e, &rules->caps.audit, NULL))
+			goto fail;
+		if (!aa_unpack_cap_high(e, &rules->caps.quiet, NULL))
+			goto fail;
+		if (!aa_unpack_cap_high(e, &tmpcap, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	info = "failed to unpack extended profile capabilities";
+	if (aa_unpack_nameX(e, AA_STRUCT, "capsx")) {
+		/* optional extended caps mediation mask */
+		if (!aa_unpack_cap_low(e, &rules->caps.extended, NULL))
+			goto fail;
+		if (!aa_unpack_cap_high(e, &rules->caps.extended, NULL))
+			goto fail;
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	if (!unpack_xattrs(e, profile)) {
+		info = "failed to unpack profile xattrs";
+		goto fail;
+	}
+
+	if (!unpack_rlimits(e, rules)) {
+		info = "failed to unpack profile rlimits";
+		goto fail;
+	}
+
+	if (!unpack_secmark(e, rules)) {
+		info = "failed to unpack profile secmark rules";
+		goto fail;
+	}
+
+	if (aa_unpack_nameX(e, AA_STRUCT, "policydb")) {
+		/* generic policy dfa - optional and may be NULL */
+		info = "failed to unpack policydb";
+		error = unpack_pdb(e, &rules->policy, true, false,
+				   &info);
+		if (error)
+			goto fail;
+		/* Fixup: drop when we get rid of start array */
+		if (aa_dfa_next(rules->policy->dfa, rules->policy->start[0],
+				AA_CLASS_FILE))
+			rules->policy->start[AA_CLASS_FILE] =
+			  aa_dfa_next(rules->policy->dfa,
+				      rules->policy->start[0],
+				      AA_CLASS_FILE);
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+		if (!rules->policy->perms) {
+			error = aa_compat_map_policy(rules->policy,
+						     e->version);
+			if (error) {
+				info = "failed to remap policydb permission table";
+				goto fail;
+			}
+		}
+	} else {
+		rules->policy = aa_get_pdb(nullpdb);
+	}
+	/* get file rules */
+	error = unpack_pdb(e, &rules->file, false, true, &info);
+	if (error) {
+		goto fail;
+	} else if (rules->file->dfa) {
+		if (!rules->file->perms) {
+			AA_DEBUG(DEBUG_UNPACK, "compat mapping perms");
+			error = aa_compat_map_file(rules->file);
+			if (error) {
+				info = "failed to remap file permission table";
+				goto fail;
+			}
+		}
+	} else if (rules->policy->dfa &&
+		   rules->policy->start[AA_CLASS_FILE]) {
+		aa_put_pdb(rules->file);
+		rules->file = aa_get_pdb(rules->policy);
+	} else {
+		aa_put_pdb(rules->file);
+		rules->file = aa_get_pdb(nullpdb);
+	}
+	error = -EPROTO;
+	if (aa_unpack_nameX(e, AA_STRUCT, "data")) {
+		info = "out of memory";
+		profile->data = kzalloc_obj(*profile->data);
+		if (!profile->data) {
+			error = -ENOMEM;
+			goto fail;
+		}
+		params.nelem_hint = 3;
+		params.key_len = sizeof(void *);
+		params.key_offset = offsetof(struct aa_data, key);
+		params.head_offset = offsetof(struct aa_data, head);
+		params.hashfn = strhash;
+		params.obj_cmpfn = datacmp;
+
+		if (rhashtable_init(profile->data, &params)) {
+			info = "failed to init key, value hash table";
+			goto fail;
+		}
+
+		while (aa_unpack_strdup(e, &key, NULL)) {
+			data = kzalloc_obj(*data);
+			if (!data) {
+				kfree_sensitive(key);
+				error = -ENOMEM;
+				goto fail;
+			}
+
+			data->key = key;
+			data->size = aa_unpack_blob(e, &data->data, NULL);
+			data->data = kvmemdup(data->data, data->size, GFP_KERNEL);
+			if (data->size && !data->data) {
+				kfree_sensitive(data->key);
+				kfree_sensitive(data);
+				error = -ENOMEM;
+				goto fail;
+			}
+
+			if (rhashtable_insert_fast(profile->data, &data->head,
+						   profile->data->p)) {
+				kvfree_sensitive(data->data, data->size);
+				kfree_sensitive(data->key);
+				kfree_sensitive(data);
+				info = "failed to insert data to table";
+				goto fail;
+			}
+		}
+
+		if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL)) {
+			info = "failed to unpack end of key, value data table";
+			goto fail;
+		}
+	}
+
+	if (!aa_unpack_nameX(e, AA_STRUCTEND, NULL)) {
+		info = "failed to unpack end of profile";
+		goto fail;
+	}
+
+	aa_compute_profile_mediates(profile);
+
+	return profile;
+
+fail:
+	if (error == 0)
+		/* default error covers most cases */
+		error = -EPROTO;
+	if (*ns_name) {
+		kfree(*ns_name);
+		*ns_name = NULL;
+	}
+	if (profile)
+		name = NULL;
+	else if (!name)
+		name = "unknown";
+	audit_iface(profile, NULL, name, info, e, error);
+	aa_free_profile(profile);
+
+	return ERR_PTR(error);
+}
+
+/**
+ * verify_header - unpack serialized stream header
+ * @e: serialized data read head (NOT NULL)
+ * @required: whether the header is required or optional
+ * @ns: Returns - namespace if one is specified else NULL (NOT NULL)
+ *
+ * Returns: error or 0 if header is good
+ */
+static int verify_header(struct aa_ext *e, int required, const char **ns)
+{
+	int error = -EPROTONOSUPPORT;
+	const char *name = NULL;
+
+	/* get the interface version */
+	if (!aa_unpack_u32(e, &e->version, "version")) {
+		if (required) {
+			audit_iface(NULL, NULL, NULL, "invalid profile format",
+				    e, error);
+			return error;
+		}
+	}
+
+	/* Check that the interface version is currently supported.
+	 * if not specified use previous version
+	 * Mask off everything that is not kernel abi version
+	 */
+	if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v9)) {
+		audit_iface(NULL, NULL, NULL, "unsupported interface version",
+			    e, error);
+		return error;
+	}
+
+	/* read the namespace if present */
+	if (aa_unpack_str(e, &name, "namespace")) {
+		if (*name == '\0') {
+			audit_iface(NULL, NULL, NULL, "invalid namespace name",
+				    e, error);
+			return error;
+		}
+		if (*ns && strcmp(*ns, name)) {
+			audit_iface(NULL, NULL, NULL, "invalid ns change", e,
+				    error);
+			return error;
+		} else if (!*ns) {
+			*ns = kstrdup(name, GFP_KERNEL);
+			if (!*ns)
+				return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * verify_dfa_accept_index - verify accept indexes are in range of perms table
+ * @dfa: the dfa to check accept indexes are in range
+ * @table_size: the permission table size the indexes should be within
+ */
+static bool verify_dfa_accept_index(const struct aa_dfa *dfa, int table_size)
+{
+	int i;
+	for (i = 0; i < dfa->tables[YYTD_ID_ACCEPT]->td_lolen; i++) {
+		if (ACCEPT_TABLE(dfa)[i] >= table_size)
+			return false;
+	}
+	return true;
+}
+
+static bool verify_perm(const struct aa_perms *perm)
+{
+	/* TODO: allow option to just force the perms into a valid state */
+	if (perm->allow & perm->deny)
+		return false;
+	if (perm->subtree & ~perm->allow)
+		return false;
+	if (perm->cond & (perm->allow | perm->deny))
+		return false;
+	if (perm->kill & perm->allow)
+		return false;
+	if (perm->complain & (perm->allow | perm->deny))
+		return false;
+	if (perm->prompt & (perm->allow | perm->deny))
+		return false;
+	if (perm->complain & perm->prompt)
+		return false;
+	if (perm->hide & perm->allow)
+		return false;
+
+	return true;
+}
+
+static bool verify_perms(struct aa_policydb *pdb)
+{
+	int i;
+	int xidx, xmax = -1;
+
+	for (i = 0; i < pdb->size; i++) {
+		if (!verify_perm(&pdb->perms[i]))
+			return false;
+		/* verify indexes into str table */
+		if ((pdb->perms[i].xindex & AA_X_TYPE_MASK) == AA_X_TABLE) {
+			xidx = pdb->perms[i].xindex & AA_X_INDEX_MASK;
+			if (xidx >= pdb->trans.size)
+				return false;
+			if (xmax < xidx)
+				xmax = xidx;
+		}
+		if (pdb->perms[i].tag && pdb->perms[i].tag >= pdb->tags.sets.size)
+			return false;
+		if (pdb->perms[i].label &&
+		    pdb->perms[i].label >= pdb->trans.size)
+			return false;
+	}
+	/* deal with incorrectly constructed string tables */
+	if (xmax == -1) {
+		aa_destroy_str_table(&pdb->trans);
+	} else if (pdb->trans.size > xmax + 1) {
+		if (!aa_resize_str_table(&pdb->trans, xmax + 1, GFP_KERNEL))
+			return false;
+	}
+	return true;
+}
+
+/**
+ * verify_profile - Do post unpack analysis to verify profile consistency
+ * @profile: profile to verify (NOT NULL)
+ *
+ * Returns: 0 if passes verification else error
+ *
+ * This verification is post any unpack mapping or changes
+ */
+static int verify_profile(struct aa_profile *profile)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+
+	if (!rules)
+		return 0;
+
+	if (rules->file->dfa && !verify_dfa_accept_index(rules->file->dfa,
+							rules->file->size)) {
+		audit_iface(profile, NULL, NULL,
+			    "Unpack: file Invalid named transition", NULL,
+			    -EPROTO);
+		return -EPROTO;
+	}
+	if (rules->policy->dfa &&
+	    !verify_dfa_accept_index(rules->policy->dfa, rules->policy->size)) {
+		audit_iface(profile, NULL, NULL,
+			    "Unpack: policy Invalid named transition", NULL,
+			    -EPROTO);
+		return -EPROTO;
+	}
+
+	if (!verify_perms(rules->file)) {
+		audit_iface(profile, NULL, NULL,
+			    "Unpack: Invalid perm index", NULL, -EPROTO);
+		return -EPROTO;
+	}
+	if (!verify_perms(rules->policy)) {
+		audit_iface(profile, NULL, NULL,
+			    "Unpack: Invalid perm index", NULL, -EPROTO);
+		return -EPROTO;
+	}
+	if (!verify_perms(profile->attach.xmatch)) {
+		audit_iface(profile, NULL, NULL,
+			    "Unpack: Invalid perm index", NULL, -EPROTO);
+		return -EPROTO;
+	}
+
+	return 0;
+}
+
+void aa_load_ent_free(struct aa_load_ent *ent)
+{
+	if (ent) {
+		aa_put_profile(ent->rename);
+		aa_put_profile(ent->old);
+		aa_put_profile(ent->new);
+		kfree(ent->ns_name);
+		kfree_sensitive(ent);
+	}
+}
+
+struct aa_load_ent *aa_load_ent_alloc(void)
+{
+	struct aa_load_ent *ent = kzalloc_obj(*ent);
+	if (ent)
+		INIT_LIST_HEAD(&ent->list);
+	return ent;
+}
+
+static int compress_zstd(const char *src, size_t slen, char **dst, size_t *dlen)
+{
+#ifdef CONFIG_SECURITY_APPARMOR_EXPORT_BINARY
+	const zstd_parameters params =
+		zstd_get_params(aa_g_rawdata_compression_level, slen);
+	const size_t wksp_len = zstd_cctx_workspace_bound(&params.cParams);
+	void *wksp = NULL;
+	zstd_cctx *ctx = NULL;
+	size_t out_len = zstd_compress_bound(slen);
+	void *out = NULL;
+	int ret = 0;
+
+	out = kvzalloc(out_len, GFP_KERNEL);
+	if (!out) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	wksp = kvzalloc(wksp_len, GFP_KERNEL);
+	if (!wksp) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	ctx = zstd_init_cctx(wksp, wksp_len);
+	if (!ctx) {
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
+	out_len = zstd_compress_cctx(ctx, out, out_len, src, slen, &params);
+	if (zstd_is_error(out_len) || out_len >= slen) {
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
+	if (is_vmalloc_addr(out)) {
+		*dst = kvzalloc(out_len, GFP_KERNEL);
+		if (*dst) {
+			memcpy(*dst, out, out_len);
+			kvfree(out);
+			out = NULL;
+		}
+	} else {
+		/*
+		 * If the staging buffer was kmalloc'd, then using krealloc is
+		 * probably going to be faster. The destination buffer will
+		 * always be smaller, so it's just shrunk, avoiding a memcpy
+		 */
+		*dst = krealloc(out, out_len, GFP_KERNEL);
+	}
+
+	if (!*dst) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	*dlen = out_len;
+
+cleanup:
+	if (ret) {
+		kvfree(out);
+		*dst = NULL;
+	}
+
+	kvfree(wksp);
+	return ret;
+#else
+	*dlen = slen;
+	return 0;
+#endif
+}
+
+static int compress_loaddata(struct aa_loaddata *data)
+{
+	AA_BUG(data->compressed_size > 0);
+
+	/*
+	 * Shortcut the no compression case, else we increase the amount of
+	 * storage required by a small amount
+	 */
+	if (aa_g_rawdata_compression_level != 0) {
+		void *udata = data->data;
+		int error = compress_zstd(udata, data->size, &data->data,
+					  &data->compressed_size);
+		if (error) {
+			data->compressed_size = data->size;
+			return error;
+		}
+		if (udata != data->data)
+			kvfree(udata);
+	} else
+		data->compressed_size = data->size;
+
+	return 0;
+}
+
+/**
+ * aa_unpack - unpack packed binary profile(s) data loaded from user space
+ * @udata: user data copied to kmem  (NOT NULL)
+ * @lh: list to place unpacked profiles in a aa_repl_ws
+ * @ns: Returns namespace profile is in if specified else NULL (NOT NULL)
+ * @compressed_data: The userspace-provided compressed data. May be NULL
+ * @compressed_size: If compressed_data is not NULL, the compressed data size
+ *
+ * Unpack user data and return refcounted allocated profile(s) stored in
+ * @lh in order of discovery, with the list chain stored in base.list
+ * or error
+ *
+ * Returns: profile(s) on @lh else error pointer if fails to unpack
+ */
+int aa_unpack(struct aa_loaddata *udata, struct list_head *lh,
+	      const char **ns, char *compressed_data, size_t compressed_size)
+{
+	struct aa_load_ent *tmp, *ent;
+	struct aa_profile *profile = NULL;
+	char *ns_name = NULL;
+	int error = 0;
+	struct aa_ext e = {
+		.start = udata->data,
+		.end = udata->data + udata->size,
+		.pos = udata->data,
+	};
+
+	*ns = NULL;
+	while (e.pos < e.end) {
+		void *start;
+		error = verify_header(&e, e.pos == e.start, ns);
+		if (error)
+			goto fail;
+
+		start = e.pos;
+		profile = unpack_profile(&e, &ns_name);
+		if (IS_ERR(profile)) {
+			error = PTR_ERR(profile);
+			goto fail;
+		}
+
+		error = verify_profile(profile);
+		if (error)
+			goto fail_profile;
+
+		if (aa_g_hash_policy)
+			error = aa_calc_profile_hash(profile, e.version, start,
+						     e.pos - start);
+		if (error)
+			goto fail_profile;
+
+		ent = aa_load_ent_alloc();
+		if (!ent) {
+			error = -ENOMEM;
+			goto fail_profile;
+		}
+
+		ent->new = profile;
+		ent->ns_name = ns_name;
+		ns_name = NULL;
+		list_add_tail(&ent->list, lh);
+	}
+	udata->abi = e.version & K_ABI_MASK;
+	if (aa_g_hash_policy) {
+		udata->hash = aa_calc_hash(udata->data, udata->size);
+		if (IS_ERR(udata->hash)) {
+			error = PTR_ERR(udata->hash);
+			udata->hash = NULL;
+			goto fail;
+		}
+	}
+
+	if (aa_g_export_binary) {
+		/* Do we have userspace-compressed data? */
+		if (compressed_data) {
+			kvfree(udata->data);
+			udata->data = compressed_data;
+			udata->compressed_size = compressed_size;
+			compressed_data = NULL; /* consumed */
+
+		} else
+			error = compress_loaddata(udata);
+
+		if (error)
+			goto fail;
+	} else if (compressed_data) {
+		kvfree(compressed_data);
+		compressed_data = NULL;
+	}
+
+	return 0;
+
+fail_profile:
+	kfree(ns_name);
+	aa_put_profile(profile);
+
+fail:
+	if (compressed_data)
+		kvfree(compressed_data);
+	list_for_each_entry_safe(ent, tmp, lh, list) {
+		list_del_init(&ent->list);
+		aa_load_ent_free(ent);
+	}
+
+	return error;
+}
diff --git a/security/apparmor/policy_unpack_test.c b/security/apparmor/policy_unpack_test.c
new file mode 100644
index 000000000..cf18744da
--- /dev/null
+++ b/security/apparmor/policy_unpack_test.c
@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for AppArmor's policy unpack.
+ */
+
+#include <kunit/test.h>
+#include <kunit/visibility.h>
+
+#include "include/policy.h"
+#include "include/policy_unpack.h"
+
+#include <linux/unaligned.h>
+
+#define TEST_STRING_NAME "TEST_STRING"
+#define TEST_STRING_DATA "testing"
+#define TEST_STRING_BUF_OFFSET \
+	(3 + strlen(TEST_STRING_NAME) + 1)
+
+#define TEST_U32_NAME "U32_TEST"
+#define TEST_U32_DATA ((u32)0x01020304)
+#define TEST_NAMED_U32_BUF_OFFSET \
+	(TEST_STRING_BUF_OFFSET + 3 + strlen(TEST_STRING_DATA) + 1)
+#define TEST_U32_BUF_OFFSET \
+	(TEST_NAMED_U32_BUF_OFFSET + 3 + strlen(TEST_U32_NAME) + 1)
+
+#define TEST_U16_OFFSET (TEST_U32_BUF_OFFSET + 3)
+#define TEST_U16_DATA ((u16)(TEST_U32_DATA >> 16))
+
+#define TEST_U64_NAME "U64_TEST"
+#define TEST_U64_DATA ((u64)0x0102030405060708)
+#define TEST_NAMED_U64_BUF_OFFSET (TEST_U32_BUF_OFFSET + sizeof(u32) + 1)
+#define TEST_U64_BUF_OFFSET \
+	(TEST_NAMED_U64_BUF_OFFSET + 3 + strlen(TEST_U64_NAME) + 1)
+
+#define TEST_BLOB_NAME "BLOB_TEST"
+#define TEST_BLOB_DATA "\xde\xad\x00\xbe\xef"
+#define TEST_BLOB_DATA_SIZE (ARRAY_SIZE(TEST_BLOB_DATA))
+#define TEST_NAMED_BLOB_BUF_OFFSET (TEST_U64_BUF_OFFSET + sizeof(u64) + 1)
+#define TEST_BLOB_BUF_OFFSET \
+	(TEST_NAMED_BLOB_BUF_OFFSET + 3 + strlen(TEST_BLOB_NAME) + 1)
+
+#define TEST_ARRAY_NAME "ARRAY_TEST"
+#define TEST_ARRAY_SIZE 16
+#define TEST_NAMED_ARRAY_BUF_OFFSET \
+	(TEST_BLOB_BUF_OFFSET + 5 + TEST_BLOB_DATA_SIZE)
+#define TEST_ARRAY_BUF_OFFSET \
+	(TEST_NAMED_ARRAY_BUF_OFFSET + 3 + strlen(TEST_ARRAY_NAME) + 1)
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+struct policy_unpack_fixture {
+	struct aa_ext *e;
+	size_t e_size;
+};
+
+static struct aa_ext *build_aa_ext_struct(struct policy_unpack_fixture *puf,
+					  struct kunit *test, size_t buf_size)
+{
+	char *buf;
+	struct aa_ext *e;
+
+	buf = kunit_kzalloc(test, buf_size, GFP_USER);
+	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, buf);
+
+	e = kunit_kmalloc(test, sizeof(*e), GFP_USER);
+	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, e);
+
+	e->start = buf;
+	e->end = e->start + buf_size;
+	e->pos = e->start;
+
+	*buf = AA_NAME;
+	*(buf + 1) = strlen(TEST_STRING_NAME) + 1;
+	strscpy(buf + 3, TEST_STRING_NAME, e->end - (void *)(buf + 3));
+
+	buf = e->start + TEST_STRING_BUF_OFFSET;
+	*buf = AA_STRING;
+	*(buf + 1) = strlen(TEST_STRING_DATA) + 1;
+	strscpy(buf + 3, TEST_STRING_DATA, e->end - (void *)(buf + 3));
+	buf = e->start + TEST_NAMED_U32_BUF_OFFSET;
+	*buf = AA_NAME;
+	*(buf + 1) = strlen(TEST_U32_NAME) + 1;
+	strscpy(buf + 3, TEST_U32_NAME, e->end - (void *)(buf + 3));
+	*(buf + 3 + strlen(TEST_U32_NAME) + 1) = AA_U32;
+	put_unaligned_le32(TEST_U32_DATA, buf + 3 + strlen(TEST_U32_NAME) + 2);
+
+	buf = e->start + TEST_NAMED_U64_BUF_OFFSET;
+	*buf = AA_NAME;
+	*(buf + 1) = strlen(TEST_U64_NAME) + 1;
+	strscpy(buf + 3, TEST_U64_NAME, e->end - (void *)(buf + 3));
+	*(buf + 3 + strlen(TEST_U64_NAME) + 1) = AA_U64;
+	*((__le64 *)(buf + 3 + strlen(TEST_U64_NAME) + 2)) = cpu_to_le64(TEST_U64_DATA);
+
+	buf = e->start + TEST_NAMED_BLOB_BUF_OFFSET;
+	*buf = AA_NAME;
+	*(buf + 1) = strlen(TEST_BLOB_NAME) + 1;
+	strscpy(buf + 3, TEST_BLOB_NAME, e->end - (void *)(buf + 3));
+	*(buf + 3 + strlen(TEST_BLOB_NAME) + 1) = AA_BLOB;
+	*(buf + 3 + strlen(TEST_BLOB_NAME) + 2) = TEST_BLOB_DATA_SIZE;
+	memcpy(buf + 3 + strlen(TEST_BLOB_NAME) + 6,
+		TEST_BLOB_DATA, TEST_BLOB_DATA_SIZE);
+
+	buf = e->start + TEST_NAMED_ARRAY_BUF_OFFSET;
+	*buf = AA_NAME;
+	*(buf + 1) = strlen(TEST_ARRAY_NAME) + 1;
+	strscpy(buf + 3, TEST_ARRAY_NAME, e->end - (void *)(buf + 3));
+	*(buf + 3 + strlen(TEST_ARRAY_NAME) + 1) = AA_ARRAY;
+	put_unaligned_le16(TEST_ARRAY_SIZE, buf + 3 + strlen(TEST_ARRAY_NAME) + 2);
+
+	return e;
+}
+
+static int policy_unpack_test_init(struct kunit *test)
+{
+	size_t e_size = TEST_ARRAY_BUF_OFFSET + sizeof(u16) + 1;
+	struct policy_unpack_fixture *puf;
+
+	puf = kunit_kmalloc(test, sizeof(*puf), GFP_USER);
+	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, puf);
+
+	puf->e_size = e_size;
+	puf->e = build_aa_ext_struct(puf, test, e_size);
+
+	test->priv = puf;
+	return 0;
+}
+
+static void policy_unpack_test_inbounds_when_inbounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+
+	KUNIT_EXPECT_TRUE(test, aa_inbounds(puf->e, 0));
+	KUNIT_EXPECT_TRUE(test, aa_inbounds(puf->e, puf->e_size / 2));
+	KUNIT_EXPECT_TRUE(test, aa_inbounds(puf->e, puf->e_size));
+}
+
+static void policy_unpack_test_inbounds_when_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+
+	KUNIT_EXPECT_FALSE(test, aa_inbounds(puf->e, puf->e_size + 1));
+}
+
+static void policy_unpack_test_unpack_array_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	u16 array_size = 0;
+
+	puf->e->pos += TEST_ARRAY_BUF_OFFSET;
+
+	KUNIT_EXPECT_TRUE(test, aa_unpack_array(puf->e, NULL, &array_size));
+	KUNIT_EXPECT_EQ(test, array_size, (u16)TEST_ARRAY_SIZE);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+		puf->e->start + TEST_ARRAY_BUF_OFFSET + sizeof(u16) + 1);
+}
+
+static void policy_unpack_test_unpack_array_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_ARRAY_NAME;
+	u16 array_size = 0;
+
+	puf->e->pos += TEST_NAMED_ARRAY_BUF_OFFSET;
+
+	KUNIT_EXPECT_TRUE(test, aa_unpack_array(puf->e, name, &array_size));
+	KUNIT_EXPECT_EQ(test, array_size, (u16)TEST_ARRAY_SIZE);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+		puf->e->start + TEST_ARRAY_BUF_OFFSET + sizeof(u16) + 1);
+}
+
+static void policy_unpack_test_unpack_array_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_ARRAY_NAME;
+	u16 array_size;
+
+	puf->e->pos += TEST_NAMED_ARRAY_BUF_OFFSET;
+	puf->e->end = puf->e->start + TEST_ARRAY_BUF_OFFSET + sizeof(u16);
+
+	KUNIT_EXPECT_FALSE(test, aa_unpack_array(puf->e, name, &array_size));
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+		puf->e->start + TEST_NAMED_ARRAY_BUF_OFFSET);
+}
+
+static void policy_unpack_test_unpack_blob_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *blob = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_BLOB_BUF_OFFSET;
+	size = aa_unpack_blob(puf->e, &blob, NULL);
+
+	KUNIT_ASSERT_EQ(test, size, TEST_BLOB_DATA_SIZE);
+	KUNIT_EXPECT_TRUE(test,
+		memcmp(blob, TEST_BLOB_DATA, TEST_BLOB_DATA_SIZE) == 0);
+}
+
+static void policy_unpack_test_unpack_blob_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *blob = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_NAMED_BLOB_BUF_OFFSET;
+	size = aa_unpack_blob(puf->e, &blob, TEST_BLOB_NAME);
+
+	KUNIT_ASSERT_EQ(test, size, TEST_BLOB_DATA_SIZE);
+	KUNIT_EXPECT_TRUE(test,
+		memcmp(blob, TEST_BLOB_DATA, TEST_BLOB_DATA_SIZE) == 0);
+}
+
+static void policy_unpack_test_unpack_blob_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *blob = NULL;
+	void *start;
+	int size;
+
+	puf->e->pos += TEST_NAMED_BLOB_BUF_OFFSET;
+	start = puf->e->pos;
+	puf->e->end = puf->e->start + TEST_BLOB_BUF_OFFSET
+		+ TEST_BLOB_DATA_SIZE - 1;
+
+	size = aa_unpack_blob(puf->e, &blob, TEST_BLOB_NAME);
+
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, start);
+}
+
+static void policy_unpack_test_unpack_str_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char *string = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_STRING_BUF_OFFSET;
+	size = aa_unpack_str(puf->e, &string, NULL);
+
+	KUNIT_EXPECT_EQ(test, size, strlen(TEST_STRING_DATA) + 1);
+	KUNIT_EXPECT_STREQ(test, string, TEST_STRING_DATA);
+}
+
+static void policy_unpack_test_unpack_str_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char *string = NULL;
+	size_t size;
+
+	size = aa_unpack_str(puf->e, &string, TEST_STRING_NAME);
+
+	KUNIT_EXPECT_EQ(test, size, strlen(TEST_STRING_DATA) + 1);
+	KUNIT_EXPECT_STREQ(test, string, TEST_STRING_DATA);
+}
+
+static void policy_unpack_test_unpack_str_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char *string = NULL;
+	void *start = puf->e->pos;
+	int size;
+
+	puf->e->end = puf->e->pos + TEST_STRING_BUF_OFFSET
+		+ strlen(TEST_STRING_DATA) - 1;
+
+	size = aa_unpack_str(puf->e, &string, TEST_STRING_NAME);
+
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, start);
+}
+
+static void policy_unpack_test_unpack_strdup_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *string = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_STRING_BUF_OFFSET;
+	size = aa_unpack_strdup(puf->e, &string, NULL);
+
+	KUNIT_EXPECT_EQ(test, size, strlen(TEST_STRING_DATA) + 1);
+	KUNIT_EXPECT_FALSE(test,
+			   ((uintptr_t)puf->e->start <= (uintptr_t)string)
+			   && ((uintptr_t)string <= (uintptr_t)puf->e->end));
+	KUNIT_EXPECT_STREQ(test, string, TEST_STRING_DATA);
+
+	kfree(string);
+}
+
+static void policy_unpack_test_unpack_strdup_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *string = NULL;
+	size_t size;
+
+	size = aa_unpack_strdup(puf->e, &string, TEST_STRING_NAME);
+
+	KUNIT_EXPECT_EQ(test, size, strlen(TEST_STRING_DATA) + 1);
+	KUNIT_EXPECT_FALSE(test,
+			   ((uintptr_t)puf->e->start <= (uintptr_t)string)
+			   && ((uintptr_t)string <= (uintptr_t)puf->e->end));
+	KUNIT_EXPECT_STREQ(test, string, TEST_STRING_DATA);
+
+	kfree(string);
+}
+
+static void policy_unpack_test_unpack_strdup_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	void *start = puf->e->pos;
+	char *string = NULL;
+	int size;
+
+	puf->e->end = puf->e->pos + TEST_STRING_BUF_OFFSET
+		+ strlen(TEST_STRING_DATA) - 1;
+
+	size = aa_unpack_strdup(puf->e, &string, TEST_STRING_NAME);
+
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_NULL(test, string);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, start);
+
+	kfree(string);
+}
+
+static void policy_unpack_test_unpack_nameX_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success;
+
+	puf->e->pos += TEST_U32_BUF_OFFSET;
+
+	success = aa_unpack_nameX(puf->e, AA_U32, NULL);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			    puf->e->start + TEST_U32_BUF_OFFSET + 1);
+}
+
+static void policy_unpack_test_unpack_nameX_with_wrong_code(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success;
+
+	puf->e->pos += TEST_U32_BUF_OFFSET;
+
+	success = aa_unpack_nameX(puf->e, AA_BLOB, NULL);
+
+	KUNIT_EXPECT_FALSE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			    puf->e->start + TEST_U32_BUF_OFFSET);
+}
+
+static void policy_unpack_test_unpack_nameX_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_U32_NAME;
+	bool success;
+
+	puf->e->pos += TEST_NAMED_U32_BUF_OFFSET;
+
+	success = aa_unpack_nameX(puf->e, AA_U32, name);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			    puf->e->start + TEST_U32_BUF_OFFSET + 1);
+}
+
+static void policy_unpack_test_unpack_nameX_with_wrong_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	static const char name[] = "12345678";
+	bool success;
+
+	puf->e->pos += TEST_NAMED_U32_BUF_OFFSET;
+
+	success = aa_unpack_nameX(puf->e, AA_U32, name);
+
+	KUNIT_EXPECT_FALSE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			    puf->e->start + TEST_NAMED_U32_BUF_OFFSET);
+}
+
+static void policy_unpack_test_unpack_u16_chunk_basic(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *chunk = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_U16_OFFSET;
+	/*
+	 * WARNING: For unit testing purposes, we're pushing puf->e->end past
+	 * the end of the allocated memory. Doing anything other than comparing
+	 * memory addresses is dangerous.
+	 */
+	puf->e->end += TEST_U16_DATA;
+
+	size = aa_unpack_u16_chunk(puf->e, &chunk);
+
+	KUNIT_EXPECT_PTR_EQ(test, chunk,
+			    puf->e->start + TEST_U16_OFFSET + 2);
+	KUNIT_EXPECT_EQ(test, size, TEST_U16_DATA);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, (chunk + TEST_U16_DATA));
+}
+
+static void policy_unpack_test_unpack_u16_chunk_out_of_bounds_1(
+		struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *chunk = NULL;
+	size_t size;
+
+	puf->e->pos = puf->e->end - 1;
+
+	size = aa_unpack_u16_chunk(puf->e, &chunk);
+
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_NULL(test, chunk);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, puf->e->end - 1);
+}
+
+static void policy_unpack_test_unpack_u16_chunk_out_of_bounds_2(
+		struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	char *chunk = NULL;
+	size_t size;
+
+	puf->e->pos += TEST_U16_OFFSET;
+	/*
+	 * WARNING: For unit testing purposes, we're pushing puf->e->end past
+	 * the end of the allocated memory. Doing anything other than comparing
+	 * memory addresses is dangerous.
+	 */
+	puf->e->end = puf->e->pos + TEST_U16_DATA - 1;
+
+	size = aa_unpack_u16_chunk(puf->e, &chunk);
+
+	KUNIT_EXPECT_EQ(test, size, 0);
+	KUNIT_EXPECT_NULL(test, chunk);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos, puf->e->start + TEST_U16_OFFSET);
+}
+
+static void policy_unpack_test_unpack_u32_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success;
+	u32 data = 0;
+
+	puf->e->pos += TEST_U32_BUF_OFFSET;
+
+	success = aa_unpack_u32(puf->e, &data, NULL);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_EQ(test, data, TEST_U32_DATA);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_U32_BUF_OFFSET + sizeof(u32) + 1);
+}
+
+static void policy_unpack_test_unpack_u32_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_U32_NAME;
+	bool success;
+	u32 data = 0;
+
+	puf->e->pos += TEST_NAMED_U32_BUF_OFFSET;
+
+	success = aa_unpack_u32(puf->e, &data, name);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_EQ(test, data, TEST_U32_DATA);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_U32_BUF_OFFSET + sizeof(u32) + 1);
+}
+
+static void policy_unpack_test_unpack_u32_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_U32_NAME;
+	bool success;
+	u32 data = 0;
+
+	puf->e->pos += TEST_NAMED_U32_BUF_OFFSET;
+	puf->e->end = puf->e->start + TEST_U32_BUF_OFFSET + sizeof(u32);
+
+	success = aa_unpack_u32(puf->e, &data, name);
+
+	KUNIT_EXPECT_FALSE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_NAMED_U32_BUF_OFFSET);
+}
+
+static void policy_unpack_test_unpack_u64_with_null_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success;
+	u64 data = 0;
+
+	puf->e->pos += TEST_U64_BUF_OFFSET;
+
+	success = aa_unpack_u64(puf->e, &data, NULL);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_EQ(test, data, TEST_U64_DATA);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_U64_BUF_OFFSET + sizeof(u64) + 1);
+}
+
+static void policy_unpack_test_unpack_u64_with_name(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_U64_NAME;
+	bool success;
+	u64 data = 0;
+
+	puf->e->pos += TEST_NAMED_U64_BUF_OFFSET;
+
+	success = aa_unpack_u64(puf->e, &data, name);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_EQ(test, data, TEST_U64_DATA);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_U64_BUF_OFFSET + sizeof(u64) + 1);
+}
+
+static void policy_unpack_test_unpack_u64_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	const char name[] = TEST_U64_NAME;
+	bool success;
+	u64 data = 0;
+
+	puf->e->pos += TEST_NAMED_U64_BUF_OFFSET;
+	puf->e->end = puf->e->start + TEST_U64_BUF_OFFSET + sizeof(u64);
+
+	success = aa_unpack_u64(puf->e, &data, name);
+
+	KUNIT_EXPECT_FALSE(test, success);
+	KUNIT_EXPECT_PTR_EQ(test, puf->e->pos,
+			puf->e->start + TEST_NAMED_U64_BUF_OFFSET);
+}
+
+static void policy_unpack_test_unpack_X_code_match(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success = aa_unpack_X(puf->e, AA_NAME);
+
+	KUNIT_EXPECT_TRUE(test, success);
+	KUNIT_EXPECT_TRUE(test, puf->e->pos == puf->e->start + 1);
+}
+
+static void policy_unpack_test_unpack_X_code_mismatch(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success = aa_unpack_X(puf->e, AA_STRING);
+
+	KUNIT_EXPECT_FALSE(test, success);
+	KUNIT_EXPECT_TRUE(test, puf->e->pos == puf->e->start);
+}
+
+static void policy_unpack_test_unpack_X_out_of_bounds(struct kunit *test)
+{
+	struct policy_unpack_fixture *puf = test->priv;
+	bool success;
+
+	puf->e->pos = puf->e->end;
+	success = aa_unpack_X(puf->e, AA_NAME);
+
+	KUNIT_EXPECT_FALSE(test, success);
+}
+
+static struct kunit_case apparmor_policy_unpack_test_cases[] = {
+	KUNIT_CASE(policy_unpack_test_inbounds_when_inbounds),
+	KUNIT_CASE(policy_unpack_test_inbounds_when_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_array_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_array_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_array_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_blob_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_blob_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_blob_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_nameX_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_nameX_with_wrong_code),
+	KUNIT_CASE(policy_unpack_test_unpack_nameX_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_nameX_with_wrong_name),
+	KUNIT_CASE(policy_unpack_test_unpack_str_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_str_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_str_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_strdup_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_strdup_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_strdup_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_u16_chunk_basic),
+	KUNIT_CASE(policy_unpack_test_unpack_u16_chunk_out_of_bounds_1),
+	KUNIT_CASE(policy_unpack_test_unpack_u16_chunk_out_of_bounds_2),
+	KUNIT_CASE(policy_unpack_test_unpack_u32_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_u32_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_u32_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_u64_with_null_name),
+	KUNIT_CASE(policy_unpack_test_unpack_u64_with_name),
+	KUNIT_CASE(policy_unpack_test_unpack_u64_out_of_bounds),
+	KUNIT_CASE(policy_unpack_test_unpack_X_code_match),
+	KUNIT_CASE(policy_unpack_test_unpack_X_code_mismatch),
+	KUNIT_CASE(policy_unpack_test_unpack_X_out_of_bounds),
+	{},
+};
+
+static struct kunit_suite apparmor_policy_unpack_test_module = {
+	.name = "apparmor_policy_unpack",
+	.init = policy_unpack_test_init,
+	.test_cases = apparmor_policy_unpack_test_cases,
+};
+
+kunit_test_suite(apparmor_policy_unpack_test_module);
+
+MODULE_DESCRIPTION("KUnit tests for AppArmor's policy unpack");
+MODULE_LICENSE("GPL");
diff --git a/security/apparmor/procattr.c b/security/apparmor/procattr.c
new file mode 100644
index 000000000..c07b6e8fd
--- /dev/null
+++ b/security/apparmor/procattr.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /proc/<pid>/attr/ interface functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include "include/apparmor.h"
+#include "include/cred.h"
+#include "include/policy.h"
+#include "include/policy_ns.h"
+#include "include/domain.h"
+#include "include/procattr.h"
+
+
+/**
+ * aa_getprocattr - Return the label information for @label
+ * @label: the label to print label info about  (NOT NULL)
+ * @string: Returns - string containing the label info (NOT NULL)
+ * @newline: indicates that a newline should be added
+ *
+ * Requires: label != NULL && string != NULL
+ *
+ * Creates a string containing the label information for @label.
+ *
+ * Returns: size of string placed in @string else error code on failure
+ */
+int aa_getprocattr(struct aa_label *label, char **string, bool newline)
+{
+	struct aa_ns *ns = labels_ns(label);
+	struct aa_ns *current_ns = aa_get_current_ns();
+	int len;
+
+	if (!aa_ns_visible(current_ns, ns, true)) {
+		aa_put_ns(current_ns);
+		return -EACCES;
+	}
+
+	len = aa_label_snxprint(NULL, 0, current_ns, label,
+				FLAG_SHOW_MODE | FLAG_VIEW_SUBNS |
+				FLAG_HIDDEN_UNCONFINED);
+	AA_BUG(len < 0);
+
+	*string = kmalloc(len + 2, GFP_KERNEL);
+	if (!*string) {
+		aa_put_ns(current_ns);
+		return -ENOMEM;
+	}
+
+	len = aa_label_snxprint(*string, len + 2, current_ns, label,
+				FLAG_SHOW_MODE | FLAG_VIEW_SUBNS |
+				FLAG_HIDDEN_UNCONFINED);
+	if (len < 0) {
+		kfree(*string);
+		*string = NULL;
+		aa_put_ns(current_ns);
+		return len;
+	}
+
+	if (newline)
+		(*string)[len++] = '\n';
+	(*string)[len] = 0;
+
+	aa_put_ns(current_ns);
+	return len;
+}
+
+/**
+ * split_token_from_name - separate a string of form  <token>^<name>
+ * @op: operation being checked
+ * @args: string to parse  (NOT NULL)
+ * @token: stores returned parsed token value  (NOT NULL)
+ *
+ * Returns: start position of name after token else NULL on failure
+ */
+static char *split_token_from_name(const char *op, char *args, u64 *token)
+{
+	char *name;
+
+	*token = simple_strtoull(args, &name, 16);
+	if ((name == args) || *name != '^') {
+		AA_ERROR("%s: Invalid input '%s'", op, args);
+		return ERR_PTR(-EINVAL);
+	}
+
+	name++;			/* skip ^ */
+	if (!*name)
+		name = NULL;
+	return name;
+}
+
+/**
+ * aa_setprocattr_changehat - handle procattr interface to change_hat
+ * @args: args received from writing to /proc/<pid>/attr/current (NOT NULL)
+ * @size: size of the args
+ * @flags: set of flags governing behavior
+ *
+ * Returns: %0 or error code if change_hat fails
+ */
+int aa_setprocattr_changehat(char *args, size_t size, int flags)
+{
+	char *hat;
+	u64 token;
+	const char *hats[16];		/* current hard limit on # of names */
+	int count = 0;
+
+	hat = split_token_from_name(OP_CHANGE_HAT, args, &token);
+	if (IS_ERR(hat))
+		return PTR_ERR(hat);
+
+	if (!hat && !token) {
+		AA_ERROR("change_hat: Invalid input, NULL hat and NULL magic");
+		return -EINVAL;
+	}
+
+	if (hat) {
+		/* set up hat name vector, args guaranteed null terminated
+		 * at args[size] by setprocattr.
+		 *
+		 * If there are multiple hat names in the buffer each is
+		 * separated by a \0.  Ie. userspace writes them pre tokenized
+		 */
+		char *end = args + size;
+		for (count = 0; (hat < end) && count < 16; ++count) {
+			char *next = hat + strlen(hat) + 1;
+			hats[count] = hat;
+			AA_DEBUG(DEBUG_DOMAIN,
+				 "%s: (pid %d) Magic 0x%llx count %d hat '%s'\n"
+				 , __func__, current->pid, token, count, hat);
+			hat = next;
+		}
+	} else
+		AA_DEBUG(DEBUG_DOMAIN,
+			 "%s: (pid %d) Magic 0x%llx count %d Hat '%s'\n",
+			 __func__, current->pid, token, count, "<NULL>");
+
+	return aa_change_hat(hats, count, token, flags);
+}
diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c
new file mode 100644
index 000000000..64212b39b
--- /dev/null
+++ b/security/apparmor/resource.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor resource mediation and attachment
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ */
+
+#include <linux/audit.h>
+#include <linux/security.h>
+
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/resource.h"
+#include "include/policy.h"
+
+/*
+ * Table of rlimit names: we generate it from resource.h.
+ */
+#include "rlim_names.h"
+
+struct aa_sfs_entry aa_sfs_entry_rlimit[] = {
+	AA_SFS_FILE_STRING("mask", AA_SFS_RLIMIT_MASK),
+	{ }
+};
+
+/* audit callback for resource specific fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	audit_log_format(ab, " rlimit=%s value=%lu",
+			 rlim_names[ad->rlim.rlim], ad->rlim.max);
+	if (ad->peer) {
+		audit_log_format(ab, " peer=");
+		aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+				FLAGS_NONE, GFP_ATOMIC);
+	}
+}
+
+/**
+ * audit_resource - audit setting resource limit
+ * @subj_cred: cred setting the resource
+ * @profile: profile being enforced  (NOT NULL)
+ * @resource: rlimit being auditing
+ * @value: value being set
+ * @peer: aa_albel of the task being set
+ * @info: info being auditing
+ * @error: error value
+ *
+ * Returns: 0 or ad->error else other error code on failure
+ */
+static int audit_resource(const struct cred *subj_cred,
+			  struct aa_profile *profile, unsigned int resource,
+			  unsigned long value, struct aa_label *peer,
+			  const char *info, int error)
+{
+	DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_RLIMITS,
+			  OP_SETRLIMIT);
+
+	ad.subj_cred = subj_cred;
+	ad.rlim.rlim = resource;
+	ad.rlim.max = value;
+	ad.peer = peer;
+	ad.info = info;
+	ad.error = error;
+
+	return aa_audit(AUDIT_APPARMOR_AUTO, profile, &ad, audit_cb);
+}
+
+/**
+ * aa_map_resource - map compiled policy resource to internal #
+ * @resource: flattened policy resource number
+ *
+ * Returns: resource # for the current architecture.
+ *
+ * rlimit resource can vary based on architecture, map the compiled policy
+ * resource # to the internal representation for the architecture.
+ */
+int aa_map_resource(int resource)
+{
+	return rlim_map[resource];
+}
+
+static int profile_setrlimit(const struct cred *subj_cred,
+			     struct aa_profile *profile, unsigned int resource,
+			     struct rlimit *new_rlim)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	int e = 0;
+
+	if (rules->rlimits.mask & (1 << resource) && new_rlim->rlim_max >
+	    rules->rlimits.limits[resource].rlim_max)
+		e = -EACCES;
+	return audit_resource(subj_cred, profile, resource, new_rlim->rlim_max,
+			      NULL, NULL, e);
+}
+
+/**
+ * aa_task_setrlimit - test permission to set an rlimit
+ * @subj_cred: cred setting the limit
+ * @label: label confining the task  (NOT NULL)
+ * @task: task the resource is being set on
+ * @resource: the resource being set
+ * @new_rlim: the new resource limit  (NOT NULL)
+ *
+ * Control raising the processes hard limit.
+ *
+ * Returns: 0 or error code if setting resource failed
+ */
+int aa_task_setrlimit(const struct cred *subj_cred, struct aa_label *label,
+		      struct task_struct *task,
+		      unsigned int resource, struct rlimit *new_rlim)
+{
+	struct aa_profile *profile;
+	struct aa_label *peer;
+	int error = 0;
+
+	rcu_read_lock();
+	peer = aa_get_newest_cred_label(__task_cred(task));
+	rcu_read_unlock();
+
+	/* TODO: extend resource control to handle other (non current)
+	 * profiles.  AppArmor rules currently have the implicit assumption
+	 * that the task is setting the resource of a task confined with
+	 * the same profile or that the task setting the resource of another
+	 * task has CAP_SYS_RESOURCE.
+	 */
+
+	if (label != peer &&
+	    aa_capable(subj_cred, label, CAP_SYS_RESOURCE, CAP_OPT_NOAUDIT) != 0)
+		error = fn_for_each(label, profile,
+				audit_resource(subj_cred, profile, resource,
+					       new_rlim->rlim_max, peer,
+					       "cap_sys_resource", -EACCES));
+	else
+		error = fn_for_each_confined(label, profile,
+				profile_setrlimit(subj_cred, profile, resource,
+						  new_rlim));
+	aa_put_label(peer);
+
+	return error;
+}
+
+/**
+ * __aa_transition_rlimits - apply new profile rlimits
+ * @old_l: old label on task  (NOT NULL)
+ * @new_l: new label with rlimits to apply  (NOT NULL)
+ */
+void __aa_transition_rlimits(struct aa_label *old_l, struct aa_label *new_l)
+{
+	unsigned int mask = 0;
+	struct rlimit *rlim, *initrlim;
+	struct aa_profile *old, *new;
+	struct label_it i;
+
+	old = labels_profile(old_l);
+	new = labels_profile(new_l);
+
+	/* for any rlimits the profile controlled, reset the soft limit
+	 * to the lesser of the tasks hard limit and the init tasks soft limit
+	 */
+	label_for_each_confined(i, old_l, old) {
+		struct aa_ruleset *rules = old->label.rules[0];
+		if (rules->rlimits.mask) {
+			int j;
+
+			for (j = 0, mask = 1; j < RLIM_NLIMITS; j++,
+				     mask <<= 1) {
+				if (rules->rlimits.mask & mask) {
+					rlim = current->signal->rlim + j;
+					initrlim = init_task.signal->rlim + j;
+					rlim->rlim_cur = min(rlim->rlim_max,
+							    initrlim->rlim_cur);
+				}
+			}
+		}
+	}
+
+	/* set any new hard limits as dictated by the new profile */
+	label_for_each_confined(i, new_l, new) {
+		struct aa_ruleset *rules = new->label.rules[0];
+		int j;
+
+		if (!rules->rlimits.mask)
+			continue;
+		for (j = 0, mask = 1; j < RLIM_NLIMITS; j++, mask <<= 1) {
+			if (!(rules->rlimits.mask & mask))
+				continue;
+
+			rlim = current->signal->rlim + j;
+			rlim->rlim_max = min(rlim->rlim_max,
+					     rules->rlimits.limits[j].rlim_max);
+			/* soft limit should not exceed hard limit */
+			rlim->rlim_cur = min(rlim->rlim_cur, rlim->rlim_max);
+			if (j == RLIMIT_CPU &&
+			    rlim->rlim_cur != RLIM_INFINITY &&
+			    IS_ENABLED(CONFIG_POSIX_TIMERS))
+				(void) update_rlimit_cpu(current->group_leader,
+							 rlim->rlim_cur);
+		}
+	}
+}
diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c
new file mode 100644
index 000000000..28caf66b9
--- /dev/null
+++ b/security/apparmor/secid.c
@@ -0,0 +1,155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security identifier (secid) manipulation fns
+ *
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * AppArmor allocates a unique secid for every label used. If a label
+ * is replaced it receives the secid of the label it is replacing.
+ */
+
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/xarray.h>
+
+#include "include/cred.h"
+#include "include/lib.h"
+#include "include/secid.h"
+#include "include/label.h"
+#include "include/policy_ns.h"
+
+/*
+ * secids - do not pin labels with a refcount. They rely on the label
+ * properly updating/freeing them
+ */
+#define AA_FIRST_SECID 2
+
+static DEFINE_XARRAY_FLAGS(aa_secids, XA_FLAGS_LOCK_IRQ | XA_FLAGS_TRACK_FREE);
+
+int apparmor_display_secid_mode;
+
+/*
+ * TODO: allow policy to reserve a secid range?
+ * TODO: add secid pinning
+ * TODO: use secid_update in label replace
+ */
+
+/*
+ * see label for inverse aa_label_to_secid
+ */
+struct aa_label *aa_secid_to_label(u32 secid)
+{
+	return xa_load(&aa_secids, secid);
+}
+
+static int apparmor_label_to_secctx(struct aa_label *label,
+				    struct lsm_context *cp)
+{
+	/* TODO: cache secctx and ref count so we don't have to recreate */
+	int flags = FLAG_VIEW_SUBNS | FLAG_HIDDEN_UNCONFINED | FLAG_ABS_ROOT;
+	int len;
+
+	if (!label)
+		return -EINVAL;
+
+	if (apparmor_display_secid_mode)
+		flags |= FLAG_SHOW_MODE;
+
+	if (cp)
+		len = aa_label_asxprint(&cp->context, root_ns, label,
+					flags, GFP_ATOMIC);
+	else
+		len = aa_label_snxprint(NULL, 0, root_ns, label, flags);
+
+	if (len < 0)
+		return -ENOMEM;
+
+	if (cp) {
+		cp->len = len;
+		cp->id = LSM_ID_APPARMOR;
+	}
+
+	return len;
+}
+
+int apparmor_secid_to_secctx(u32 secid, struct lsm_context *cp)
+{
+	struct aa_label *label = aa_secid_to_label(secid);
+
+	return apparmor_label_to_secctx(label, cp);
+}
+
+int apparmor_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp)
+{
+	struct aa_label *label;
+
+	label = prop->apparmor.label;
+
+	return apparmor_label_to_secctx(label, cp);
+}
+
+int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
+{
+	struct aa_label *label;
+
+	label = aa_label_strn_parse(&root_ns->unconfined->label, secdata,
+				    seclen, GFP_KERNEL, false, false);
+	if (IS_ERR(label))
+		return PTR_ERR(label);
+	*secid = label->secid;
+
+	return 0;
+}
+
+void apparmor_release_secctx(struct lsm_context *cp)
+{
+	if (cp->id == LSM_ID_APPARMOR) {
+		kfree(cp->context);
+		cp->context = NULL;
+		cp->id = LSM_ID_UNDEF;
+	}
+}
+
+/**
+ * aa_alloc_secid - allocate a new secid for a profile
+ * @label: the label to allocate a secid for
+ * @gfp: memory allocation flags
+ *
+ * Returns: 0 with @label->secid initialized
+ *          <0 returns error with @label->secid set to AA_SECID_INVALID
+ */
+int aa_alloc_secid(struct aa_label *label, gfp_t gfp)
+{
+	unsigned long flags;
+	int ret;
+
+	xa_lock_irqsave(&aa_secids, flags);
+	ret = __xa_alloc(&aa_secids, &label->secid, label,
+			XA_LIMIT(AA_FIRST_SECID, INT_MAX), gfp);
+	xa_unlock_irqrestore(&aa_secids, flags);
+
+	if (ret < 0) {
+		label->secid = AA_SECID_INVALID;
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * aa_free_secid - free a secid
+ * @secid: secid to free
+ */
+void aa_free_secid(u32 secid)
+{
+	unsigned long flags;
+
+	xa_lock_irqsave(&aa_secids, flags);
+	__xa_erase(&aa_secids, secid);
+	xa_unlock_irqrestore(&aa_secids, flags);
+}
diff --git a/security/apparmor/stacksplitdfa.in b/security/apparmor/stacksplitdfa.in
new file mode 100644
index 000000000..4bddd10b6
--- /dev/null
+++ b/security/apparmor/stacksplitdfa.in
@@ -0,0 +1,114 @@
+/* 0x1 [^\000]*[^/\000]//& */ 0x1B, 0x5E, 0x78, 0x3D, 0x00, 0x00,
+0x00, 0x18, 0x00, 0x00, 0x04, 0xD8, 0x00, 0x00, 0x6E, 0x6F, 0x74,
+0x66, 0x6C, 0x65, 0x78, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x04,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x07, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x02, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00,
+0x02, 0x00, 0x00, 0x00, 0x03, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00,
+0x00, 0x05, 0x00, 0x00, 0x00, 0x00, 0x00, 0x04, 0x00, 0x02, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x02,
+0x00, 0x02, 0x00, 0x02, 0x00, 0x02, 0x00, 0x02, 0x00, 0x08, 0x00,
+0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x05, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x05, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x03, 0x00,
+0x04, 0x00, 0x01, 0x00, 0x03, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x03, 0x00, 0x02, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x01, 0x05, 0x00, 0x00, 0x00, 0x01, 0x00,
+0x02, 0x00, 0x03, 0x00, 0x04, 0x00, 0x05, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x02, 0x00, 0x03, 0x00, 0x04,
+0x00, 0x05, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+0x00, 0x00
diff --git a/security/apparmor/task.c b/security/apparmor/task.c
new file mode 100644
index 000000000..e16ff4130
--- /dev/null
+++ b/security/apparmor/task.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor task related definitions and mediation
+ *
+ * Copyright 2017 Canonical Ltd.
+ *
+ * TODO
+ * If a task uses change_hat it currently does not return to the old
+ * cred or task context but instead creates a new one.  Ideally the task
+ * should return to the previous cred if it has not been modified.
+ */
+
+#include <linux/gfp.h>
+#include <linux/ptrace.h>
+#include <linux/task_work.h>
+
+#include "include/path.h"
+#include "include/audit.h"
+#include "include/cred.h"
+#include "include/policy.h"
+#include "include/task.h"
+
+/**
+ * aa_get_task_label - Get another task's label
+ * @task: task to query  (NOT NULL)
+ *
+ * Returns: counted reference to @task's label
+ */
+struct aa_label *aa_get_task_label(struct task_struct *task)
+{
+	struct aa_label *p;
+
+	rcu_read_lock();
+	p = aa_get_newest_cred_label(__task_cred(task));
+	rcu_read_unlock();
+
+	return p;
+}
+
+/**
+ * aa_replace_current_label - replace the current tasks label
+ * @label: new label  (NOT NULL)
+ *
+ * Returns: 0 or error on failure
+ */
+int aa_replace_current_label(struct aa_label *label)
+{
+	struct aa_label *old = aa_current_raw_label();
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct cred *new;
+
+	AA_BUG(!label);
+
+	if (old == label)
+		return 0;
+
+	if (current_cred() != current_real_cred())
+		return -EBUSY;
+
+	new  = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	if (ctx->nnp && label_is_stale(ctx->nnp)) {
+		struct aa_label *tmp = ctx->nnp;
+
+		ctx->nnp = aa_get_newest_label(tmp);
+		aa_put_label(tmp);
+	}
+	if (unconfined(label) || (labels_ns(old) != labels_ns(label)))
+		/*
+		 * if switching to unconfined or a different label namespace
+		 * clear out context state
+		 */
+		aa_clear_task_ctx_trans(task_ctx(current));
+
+	/*
+	 * be careful switching cred label, when racing replacement it
+	 * is possible that the cred labels's->proxy->label is the reference
+	 * keeping @label valid, so make sure to get its reference before
+	 * dropping the reference on the cred's label
+	 */
+	aa_get_label(label);
+	aa_put_label(cred_label(new));
+	set_cred_label(new, label);
+
+	commit_creds(new);
+	return 0;
+}
+
+static void aa_replace_stale_label_tw_func(struct callback_head *tw)
+{
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct aa_label *label;
+
+	ctx->label_replacement_pending = false;
+	label = aa_current_raw_label();
+	if (!label_is_stale(label))
+		return;
+	label = aa_get_newest_label(label);
+	aa_replace_current_label(label);
+	aa_put_label(label);
+}
+
+/* replace the current task's stale label on syscall return */
+void aa_schedule_stale_label_replacement(void)
+{
+	struct aa_task_ctx *ctx = task_ctx(current);
+
+	if (ctx->label_replacement_pending)
+		return;
+	init_task_work(&ctx->label_replacement_tw, aa_replace_stale_label_tw_func);
+	if (task_work_add(current, &ctx->label_replacement_tw, TWA_RESUME) == 0)
+		ctx->label_replacement_pending = true;
+}
+
+
+/**
+ * aa_set_current_onexec - set the tasks change_profile to happen onexec
+ * @label: system label to set at exec  (MAYBE NULL to clear value)
+ * @stack: whether stacking should be done
+ */
+void aa_set_current_onexec(struct aa_label *label, bool stack)
+{
+	struct aa_task_ctx *ctx = task_ctx(current);
+
+	aa_get_label(label);
+	aa_put_label(ctx->onexec);
+	ctx->onexec = label;
+	ctx->token = stack;
+}
+
+/**
+ * aa_set_current_hat - set the current tasks hat
+ * @label: label to set as the current hat  (NOT NULL)
+ * @token: token value that must be specified to change from the hat
+ *
+ * Do switch of tasks hat.  If the task is currently in a hat
+ * validate the token to match.
+ *
+ * Returns: 0 or error on failure
+ */
+int aa_set_current_hat(struct aa_label *label, u64 token)
+{
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct cred *new;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	AA_BUG(!label);
+
+	if (!ctx->previous) {
+		/* transfer refcount */
+		ctx->previous = cred_label(new);
+		ctx->token = token;
+	} else if (ctx->token == token) {
+		aa_put_label(cred_label(new));
+	} else {
+		/* previous_profile && ctx->token != token */
+		abort_creds(new);
+		return -EACCES;
+	}
+
+	set_cred_label(new, aa_get_newest_label(label));
+	/* clear exec on switching context */
+	aa_put_label(ctx->onexec);
+	ctx->onexec = NULL;
+
+	commit_creds(new);
+	return 0;
+}
+
+/**
+ * aa_restore_previous_label - exit from hat context restoring previous label
+ * @token: the token that must be matched to exit hat context
+ *
+ * Attempt to return out of a hat to the previous label.  The token
+ * must match the stored token value.
+ *
+ * Returns: 0 or error of failure
+ */
+int aa_restore_previous_label(u64 token)
+{
+	struct aa_task_ctx *ctx = task_ctx(current);
+	struct cred *new;
+
+	if (ctx->token != token)
+		return -EACCES;
+	/* ignore restores when there is no saved label */
+	if (!ctx->previous)
+		return 0;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	aa_put_label(cred_label(new));
+	set_cred_label(new, aa_get_newest_label(ctx->previous));
+	AA_BUG(!cred_label(new));
+	/* clear exec && prev information when restoring to previous context */
+	aa_clear_task_ctx_trans(ctx);
+
+	commit_creds(new);
+
+	return 0;
+}
+
+/**
+ * audit_ptrace_mask - convert mask to permission string
+ * @mask: permission mask to convert
+ *
+ * Returns: pointer to static string
+ */
+static const char *audit_ptrace_mask(u32 mask)
+{
+	switch (mask) {
+	case MAY_READ:
+		return "read";
+	case MAY_WRITE:
+		return "trace";
+	case AA_MAY_BE_READ:
+		return "readby";
+	case AA_MAY_BE_TRACED:
+		return "tracedby";
+	}
+	return "";
+}
+
+/* call back to audit ptrace fields */
+static void audit_ptrace_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	struct apparmor_audit_data *ad = aad(sa);
+
+	if (ad->request & AA_PTRACE_PERM_MASK) {
+		audit_log_format(ab, " requested_mask=\"%s\"",
+				 audit_ptrace_mask(ad->request));
+
+		if (ad->denied & AA_PTRACE_PERM_MASK) {
+			audit_log_format(ab, " denied_mask=\"%s\"",
+					 audit_ptrace_mask(ad->denied));
+		}
+	}
+	audit_log_format(ab, " peer=");
+	aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer,
+			FLAGS_NONE, GFP_ATOMIC);
+}
+
+/* assumes check for RULE_MEDIATES is already done */
+/* TODO: conditionals */
+static int profile_ptrace_perm(const struct cred *cred,
+			       struct aa_profile *profile,
+			       struct aa_label *peer, u32 request,
+			       struct apparmor_audit_data *ad)
+{
+	struct aa_ruleset *rules = profile->label.rules[0];
+	struct aa_perms perms = { };
+
+	ad->subj_cred = cred;
+	ad->peer = peer;
+	aa_profile_match_label(profile, rules, peer, AA_CLASS_PTRACE, request,
+			       &perms);
+	aa_apply_modes_to_perms(profile, &perms);
+	return aa_check_perms(profile, &perms, request, ad, audit_ptrace_cb);
+}
+
+static int profile_tracee_perm(const struct cred *cred,
+			       struct aa_profile *tracee,
+			       struct aa_label *tracer, u32 request,
+			       struct apparmor_audit_data *ad)
+{
+	if (profile_unconfined(tracee) || unconfined(tracer) ||
+	    !label_mediates(&tracee->label, AA_CLASS_PTRACE))
+		return 0;
+
+	return profile_ptrace_perm(cred, tracee, tracer, request, ad);
+}
+
+static int profile_tracer_perm(const struct cred *cred,
+			       struct aa_profile *tracer,
+			       struct aa_label *tracee, u32 request,
+			       struct apparmor_audit_data *ad)
+{
+	if (profile_unconfined(tracer))
+		return 0;
+
+	if (label_mediates(&tracer->label, AA_CLASS_PTRACE))
+		return profile_ptrace_perm(cred, tracer, tracee, request, ad);
+
+	/* profile uses the old style capability check for ptrace */
+	if (&tracer->label == tracee)
+		return 0;
+
+	ad->subj_label = &tracer->label;
+	ad->peer = tracee;
+	ad->request = 0;
+	ad->error = aa_capable(cred, &tracer->label, CAP_SYS_PTRACE,
+			       CAP_OPT_NONE);
+
+	return aa_audit(AUDIT_APPARMOR_AUTO, tracer, ad, audit_ptrace_cb);
+}
+
+/**
+ * aa_may_ptrace - test if tracer task can trace the tracee
+ * @tracer_cred: cred of task doing the tracing  (NOT NULL)
+ * @tracer: label of the task doing the tracing  (NOT NULL)
+ * @tracee_cred: cred of task to be traced
+ * @tracee: task label to be traced
+ * @request: permission request
+ *
+ * Returns: %0 else error code if permission denied or error
+ */
+int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer,
+		  const struct cred *tracee_cred, struct aa_label *tracee,
+		  u32 request)
+{
+	struct aa_profile *profile;
+	u32 xrequest = request << PTRACE_PERM_SHIFT;
+	DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_PTRACE, OP_PTRACE);
+
+	return xcheck_labels(tracer, tracee, profile,
+			profile_tracer_perm(tracer_cred, profile, tracee,
+					    request, &sa),
+			profile_tracee_perm(tracee_cred, profile, tracer,
+					    xrequest, &sa));
+}
+
+static const char *get_current_exe_path(char *buffer, int buffer_size)
+{
+	struct file *exe_file;
+	struct path p;
+	const char *path_str;
+
+	exe_file = get_task_exe_file(current);
+	if (!exe_file)
+		return ERR_PTR(-ENOENT);
+	p = exe_file->f_path;
+	path_get(&p);
+
+	if (aa_path_name(&p, FLAG_VIEW_SUBNS, buffer, &path_str, NULL, NULL))
+		path_str = ERR_PTR(-ENOMEM);
+
+	fput(exe_file);
+	path_put(&p);
+
+	return path_str;
+}
+
+/* call back to audit ptrace fields */
+static void audit_ns_cb(struct audit_buffer *ab, void *va)
+{
+	struct apparmor_audit_data *ad = aad_of_va(va);
+	char *buffer;
+	const char *path;
+
+	if (ad->request & AA_USERNS_CREATE)
+		audit_log_format(ab, " requested=\"userns_create\"");
+
+	if (ad->denied & AA_USERNS_CREATE)
+		audit_log_format(ab, " denied=\"userns_create\"");
+
+	buffer = aa_get_buffer(false);
+	if (!buffer)
+		return; // OOM
+	path = get_current_exe_path(buffer, aa_g_path_max);
+	if (!IS_ERR(path))
+		audit_log_format(ab, " execpath=\"%s\"", path);
+	aa_put_buffer(buffer);
+}
+
+int aa_profile_ns_perm(struct aa_profile *profile,
+		       struct apparmor_audit_data *ad,
+		       u32 request)
+{
+	struct aa_perms perms = { };
+	int error = 0;
+
+	ad->subj_label = &profile->label;
+	ad->request = request;
+
+	if (!profile_unconfined(profile)) {
+		struct aa_ruleset *rules = profile->label.rules[0];
+		aa_state_t state;
+
+		state = RULE_MEDIATES(rules, ad->class);
+		if (!state)
+			/* TODO: add flag to complain about unmediated */
+			return 0;
+		perms = *aa_lookup_perms(rules->policy, state);
+		aa_apply_modes_to_perms(profile, &perms);
+		error = aa_check_perms(profile, &perms, request, ad,
+				       audit_ns_cb);
+	}
+
+	return error;
+}
diff --git a/security/bpf/Makefile b/security/bpf/Makefile
new file mode 100644
index 000000000..c7a89a962
--- /dev/null
+++ b/security/bpf/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2020 Google LLC.
+
+obj-$(CONFIG_BPF_LSM) := hooks.o
diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
new file mode 100644
index 000000000..7b98f5d1e
--- /dev/null
+++ b/security/bpf/hooks.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+#include <linux/lsm_hooks.h>
+#include <linux/bpf_lsm.h>
+#include <uapi/linux/lsm.h>
+
+bool bpf_lsm_initialized __ro_after_init;
+
+static struct security_hook_list bpf_lsm_hooks[] __ro_after_init = {
+	#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
+	LSM_HOOK_INIT(NAME, bpf_lsm_##NAME),
+	#include <linux/lsm_hook_defs.h>
+	#undef LSM_HOOK
+	LSM_HOOK_INIT(inode_free_security, bpf_inode_storage_free),
+};
+
+static const struct lsm_id bpf_lsmid = {
+	.name = "bpf",
+	.id = LSM_ID_BPF,
+};
+
+static int __init bpf_lsm_init(void)
+{
+	security_add_hooks(bpf_lsm_hooks, ARRAY_SIZE(bpf_lsm_hooks),
+			   &bpf_lsmid);
+	bpf_lsm_initialized = true;
+	pr_info("LSM support for eBPF active\n");
+	return 0;
+}
+
+struct lsm_blob_sizes bpf_lsm_blob_sizes __ro_after_init = {
+	.lbs_inode = sizeof(struct bpf_storage_blob),
+};
+
+DEFINE_LSM(bpf) = {
+	.id = &bpf_lsmid,
+	.init = bpf_lsm_init,
+	.blobs = &bpf_lsm_blob_sizes
+};
diff --git a/security/commoncap.c b/security/commoncap.c
new file mode 100644
index 000000000..339953580
--- /dev/null
+++ b/security/commoncap.c
@@ -0,0 +1,1527 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Common capabilities, needed by capability.o.
+ */
+
+#include <linux/capability.h>
+#include <linux/audit.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/lsm_hooks.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/ptrace.h>
+#include <linux/xattr.h>
+#include <linux/hugetlb.h>
+#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/securebits.h>
+#include <linux/user_namespace.h>
+#include <linux/binfmts.h>
+#include <linux/personality.h>
+#include <linux/mnt_idmapping.h>
+#include <uapi/linux/lsm.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/capability.h>
+
+/*
+ * If a non-root user executes a setuid-root binary in
+ * !secure(SECURE_NOROOT) mode, then we raise capabilities.
+ * However if fE is also set, then the intent is for only
+ * the file capabilities to be applied, and the setuid-root
+ * bit is left on either to change the uid (plausible) or
+ * to get full privilege on a kernel without file capabilities
+ * support.  So in that case we do not raise capabilities.
+ *
+ * Warn if that happens, once per boot.
+ */
+static void warn_setuid_and_fcaps_mixed(const char *fname)
+{
+	static int warned;
+	if (!warned) {
+		printk(KERN_INFO "warning: `%s' has both setuid-root and"
+			" effective capabilities. Therefore not raising all"
+			" capabilities.\n", fname);
+		warned = 1;
+	}
+}
+
+/**
+ * cap_capable_helper - Determine whether a task has a particular effective
+ * capability.
+ * @cred: The credentials to use
+ * @target_ns:  The user namespace of the resource being accessed
+ * @cred_ns:  The user namespace of the credentials
+ * @cap: The capability to check for
+ *
+ * Determine whether the nominated task has the specified capability amongst
+ * its effective set, returning 0 if it does, -ve if it does not.
+ *
+ * See cap_capable for more details.
+ */
+static inline int cap_capable_helper(const struct cred *cred,
+				     struct user_namespace *target_ns,
+				     const struct user_namespace *cred_ns,
+				     int cap)
+{
+	struct user_namespace *ns = target_ns;
+
+	/* See if cred has the capability in the target user namespace
+	 * by examining the target user namespace and all of the target
+	 * user namespace's parents.
+	 */
+	for (;;) {
+		/* Do we have the necessary capabilities? */
+		if (likely(ns == cred_ns))
+			return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+
+		/*
+		 * If we're already at a lower level than we're looking for,
+		 * we're done searching.
+		 */
+		if (ns->level <= cred_ns->level)
+			return -EPERM;
+
+		/* 
+		 * The owner of the user namespace in the parent of the
+		 * user namespace has all caps.
+		 */
+		if ((ns->parent == cred_ns) && uid_eq(ns->owner, cred->euid))
+			return 0;
+
+		/*
+		 * If you have a capability in a parent user ns, then you have
+		 * it over all children user namespaces as well.
+		 */
+		ns = ns->parent;
+	}
+
+	/* We never get here */
+}
+
+/**
+ * cap_capable - Determine whether a task has a particular effective capability
+ * @cred: The credentials to use
+ * @target_ns:  The user namespace of the resource being accessed
+ * @cap: The capability to check for
+ * @opts: Bitmask of options defined in include/linux/security.h (unused)
+ *
+ * Determine whether the nominated task has the specified capability amongst
+ * its effective set, returning 0 if it does, -ve if it does not.
+ *
+ * NOTE WELL: cap_capable() has reverse semantics to the capable() call
+ * and friends. That is cap_capable() returns an int 0 when a task has
+ * a capability, while the kernel's capable(), has_ns_capability(),
+ * has_ns_capability_noaudit(), and has_capability_noaudit() return a
+ * bool true (1) for this case.
+ */
+int cap_capable(const struct cred *cred, struct user_namespace *target_ns,
+		int cap, unsigned int opts)
+{
+	const struct user_namespace *cred_ns = cred->user_ns;
+	int ret = cap_capable_helper(cred, target_ns, cred_ns, cap);
+
+	trace_cap_capable(cred, target_ns, cred_ns, cap, ret);
+	return ret;
+}
+
+/**
+ * cap_settime - Determine whether the current process may set the system clock
+ * @ts: The time to set
+ * @tz: The timezone to set
+ *
+ * Determine whether the current process may set the system clock and timezone
+ * information, returning 0 if permission granted, -ve if denied.
+ */
+int cap_settime(const struct timespec64 *ts, const struct timezone *tz)
+{
+	if (!capable(CAP_SYS_TIME))
+		return -EPERM;
+	return 0;
+}
+
+/**
+ * cap_ptrace_access_check - Determine whether the current process may access
+ *			   another
+ * @child: The process to be accessed
+ * @mode: The mode of attachment.
+ *
+ * If we are in the same or an ancestor user_ns and have all the target
+ * task's capabilities, then ptrace access is allowed.
+ * If we have the ptrace capability to the target user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
+ * Determine whether a process may access another, returning 0 if permission
+ * granted, -ve if denied.
+ */
+int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
+{
+	int ret = 0;
+	const struct cred *cred, *child_cred;
+	const kernel_cap_t *caller_caps;
+
+	rcu_read_lock();
+	cred = current_cred();
+	child_cred = __task_cred(child);
+	if (mode & PTRACE_MODE_FSCREDS)
+		caller_caps = &cred->cap_effective;
+	else
+		caller_caps = &cred->cap_permitted;
+	if (cred->user_ns == child_cred->user_ns &&
+	    cap_issubset(child_cred->cap_permitted, *caller_caps))
+		goto out;
+	if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * cap_ptrace_traceme - Determine whether another process may trace the current
+ * @parent: The task proposed to be the tracer
+ *
+ * If parent is in the same or an ancestor user_ns and has all current's
+ * capabilities, then ptrace access is allowed.
+ * If parent has the ptrace capability to current's user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
+ * Determine whether the nominated task is permitted to trace the current
+ * process, returning 0 if permission is granted, -ve if denied.
+ */
+int cap_ptrace_traceme(struct task_struct *parent)
+{
+	int ret = 0;
+	const struct cred *cred, *child_cred;
+
+	rcu_read_lock();
+	cred = __task_cred(parent);
+	child_cred = current_cred();
+	if (cred->user_ns == child_cred->user_ns &&
+	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+		goto out;
+	if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * cap_capget - Retrieve a task's capability sets
+ * @target: The task from which to retrieve the capability sets
+ * @effective: The place to record the effective set
+ * @inheritable: The place to record the inheritable set
+ * @permitted: The place to record the permitted set
+ *
+ * This function retrieves the capabilities of the nominated task and returns
+ * them to the caller.
+ */
+int cap_capget(const struct task_struct *target, kernel_cap_t *effective,
+	       kernel_cap_t *inheritable, kernel_cap_t *permitted)
+{
+	const struct cred *cred;
+
+	/* Derived from kernel/capability.c:sys_capget. */
+	rcu_read_lock();
+	cred = __task_cred(target);
+	*effective   = cred->cap_effective;
+	*inheritable = cred->cap_inheritable;
+	*permitted   = cred->cap_permitted;
+	rcu_read_unlock();
+	return 0;
+}
+
+/*
+ * Determine whether the inheritable capabilities are limited to the old
+ * permitted set.  Returns 1 if they are limited, 0 if they are not.
+ */
+static inline int cap_inh_is_capped(void)
+{
+	/* they are so limited unless the current task has the CAP_SETPCAP
+	 * capability
+	 */
+	if (cap_capable(current_cred(), current_cred()->user_ns,
+			CAP_SETPCAP, CAP_OPT_NONE) == 0)
+		return 0;
+	return 1;
+}
+
+/**
+ * cap_capset - Validate and apply proposed changes to current's capabilities
+ * @new: The proposed new credentials; alterations should be made here
+ * @old: The current task's current credentials
+ * @effective: A pointer to the proposed new effective capabilities set
+ * @inheritable: A pointer to the proposed new inheritable capabilities set
+ * @permitted: A pointer to the proposed new permitted capabilities set
+ *
+ * This function validates and applies a proposed mass change to the current
+ * process's capability sets.  The changes are made to the proposed new
+ * credentials, and assuming no error, will be committed by the caller of LSM.
+ */
+int cap_capset(struct cred *new,
+	       const struct cred *old,
+	       const kernel_cap_t *effective,
+	       const kernel_cap_t *inheritable,
+	       const kernel_cap_t *permitted)
+{
+	if (cap_inh_is_capped() &&
+	    !cap_issubset(*inheritable,
+			  cap_combine(old->cap_inheritable,
+				      old->cap_permitted)))
+		/* incapable of using this inheritable set */
+		return -EPERM;
+
+	if (!cap_issubset(*inheritable,
+			  cap_combine(old->cap_inheritable,
+				      old->cap_bset)))
+		/* no new pI capabilities outside bounding set */
+		return -EPERM;
+
+	/* verify restrictions on target's new Permitted set */
+	if (!cap_issubset(*permitted, old->cap_permitted))
+		return -EPERM;
+
+	/* verify the _new_Effective_ is a subset of the _new_Permitted_ */
+	if (!cap_issubset(*effective, *permitted))
+		return -EPERM;
+
+	new->cap_effective   = *effective;
+	new->cap_inheritable = *inheritable;
+	new->cap_permitted   = *permitted;
+
+	/*
+	 * Mask off ambient bits that are no longer both permitted and
+	 * inheritable.
+	 */
+	new->cap_ambient = cap_intersect(new->cap_ambient,
+					 cap_intersect(*permitted,
+						       *inheritable));
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * cap_inode_need_killpriv - Determine if inode change affects privileges
+ * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV
+ *
+ * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
+ * affects the security markings on that inode, and if it is, should
+ * inode_killpriv() be invoked or the change rejected.
+ *
+ * Return: 1 if security.capability has a value, meaning inode_killpriv()
+ * is required, 0 otherwise, meaning inode_killpriv() is not required.
+ */
+int cap_inode_need_killpriv(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	int error;
+
+	error = __vfs_getxattr(dentry, inode, XATTR_NAME_CAPS, NULL, 0);
+	return error > 0;
+}
+
+/**
+ * cap_inode_killpriv - Erase the security markings on an inode
+ *
+ * @idmap:	idmap of the mount the inode was found from
+ * @dentry:	The inode/dentry to alter
+ *
+ * Erase the privilege-enhancing security markings on an inode.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply pass @nop_mnt_idmap.
+ *
+ * Return: 0 if successful, -ve on error.
+ */
+int cap_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry)
+{
+	int error;
+
+	error = __vfs_removexattr(idmap, dentry, XATTR_NAME_CAPS);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+	return error;
+}
+
+/**
+ * kuid_root_in_ns - check whether the given kuid is root in the given ns
+ * @kuid: the kuid to be tested
+ * @ns: the user namespace to test against
+ *
+ * Returns true if @kuid represents the root user in @ns, false otherwise.
+ */
+static bool kuid_root_in_ns(kuid_t kuid, struct user_namespace *ns)
+{
+	for (;; ns = ns->parent) {
+		if (from_kuid(ns, kuid) == 0)
+			return true;
+		if (ns == &init_user_ns)
+			break;
+	}
+
+	return false;
+}
+
+static bool vfsuid_root_in_currentns(vfsuid_t vfsuid)
+{
+	kuid_t kuid;
+
+	if (!vfsuid_valid(vfsuid))
+		return false;
+	kuid = vfsuid_into_kuid(vfsuid);
+	return kuid_root_in_ns(kuid, current_user_ns());
+}
+
+static __u32 sansflags(__u32 m)
+{
+	return m & ~VFS_CAP_FLAGS_EFFECTIVE;
+}
+
+static bool is_v2header(int size, const struct vfs_cap_data *cap)
+{
+	if (size != XATTR_CAPS_SZ_2)
+		return false;
+	return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_2;
+}
+
+static bool is_v3header(int size, const struct vfs_cap_data *cap)
+{
+	if (size != XATTR_CAPS_SZ_3)
+		return false;
+	return sansflags(le32_to_cpu(cap->magic_etc)) == VFS_CAP_REVISION_3;
+}
+
+/*
+ * getsecurity: We are called for security.* before any attempt to read the
+ * xattr from the inode itself.
+ *
+ * This gives us a chance to read the on-disk value and convert it.  If we
+ * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler.
+ *
+ * Note we are not called by vfs_getxattr_alloc(), but that is only called
+ * by the integrity subsystem, which really wants the unconverted values -
+ * so that's good.
+ */
+int cap_inode_getsecurity(struct mnt_idmap *idmap,
+			  struct inode *inode, const char *name, void **buffer,
+			  bool alloc)
+{
+	int size;
+	kuid_t kroot;
+	vfsuid_t vfsroot;
+	u32 nsmagic, magic;
+	uid_t root, mappedroot;
+	char *tmpbuf = NULL;
+	struct vfs_cap_data *cap;
+	struct vfs_ns_cap_data *nscap = NULL;
+	struct dentry *dentry;
+	struct user_namespace *fs_ns;
+
+	if (strcmp(name, "capability") != 0)
+		return -EOPNOTSUPP;
+
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return -EINVAL;
+	size = vfs_getxattr_alloc(idmap, dentry, XATTR_NAME_CAPS, &tmpbuf,
+				  sizeof(struct vfs_ns_cap_data), GFP_NOFS);
+	dput(dentry);
+	/* gcc11 complains if we don't check for !tmpbuf */
+	if (size < 0 || !tmpbuf)
+		goto out_free;
+
+	fs_ns = inode->i_sb->s_user_ns;
+	cap = (struct vfs_cap_data *) tmpbuf;
+	if (is_v2header(size, cap)) {
+		root = 0;
+	} else if (is_v3header(size, cap)) {
+		nscap = (struct vfs_ns_cap_data *) tmpbuf;
+		root = le32_to_cpu(nscap->rootid);
+	} else {
+		size = -EINVAL;
+		goto out_free;
+	}
+
+	kroot = make_kuid(fs_ns, root);
+
+	/* If this is an idmapped mount shift the kuid. */
+	vfsroot = make_vfsuid(idmap, fs_ns, kroot);
+
+	/* If the root kuid maps to a valid uid in current ns, then return
+	 * this as a nscap. */
+	mappedroot = from_kuid(current_user_ns(), vfsuid_into_kuid(vfsroot));
+	if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) {
+		size = sizeof(struct vfs_ns_cap_data);
+		if (alloc) {
+			if (!nscap) {
+				/* v2 -> v3 conversion */
+				nscap = kzalloc(size, GFP_ATOMIC);
+				if (!nscap) {
+					size = -ENOMEM;
+					goto out_free;
+				}
+				nsmagic = VFS_CAP_REVISION_3;
+				magic = le32_to_cpu(cap->magic_etc);
+				if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+					nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+				memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+				nscap->magic_etc = cpu_to_le32(nsmagic);
+			} else {
+				/* use allocated v3 buffer */
+				tmpbuf = NULL;
+			}
+			nscap->rootid = cpu_to_le32(mappedroot);
+			*buffer = nscap;
+		}
+		goto out_free;
+	}
+
+	if (!vfsuid_root_in_currentns(vfsroot)) {
+		size = -EOVERFLOW;
+		goto out_free;
+	}
+
+	/* This comes from a parent namespace.  Return as a v2 capability */
+	size = sizeof(struct vfs_cap_data);
+	if (alloc) {
+		if (nscap) {
+			/* v3 -> v2 conversion */
+			cap = kzalloc(size, GFP_ATOMIC);
+			if (!cap) {
+				size = -ENOMEM;
+				goto out_free;
+			}
+			magic = VFS_CAP_REVISION_2;
+			nsmagic = le32_to_cpu(nscap->magic_etc);
+			if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE)
+				magic |= VFS_CAP_FLAGS_EFFECTIVE;
+			memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+			cap->magic_etc = cpu_to_le32(magic);
+		} else {
+			/* use unconverted v2 */
+			tmpbuf = NULL;
+		}
+		*buffer = cap;
+	}
+out_free:
+	kfree(tmpbuf);
+	return size;
+}
+
+/**
+ * rootid_from_xattr - translate root uid of vfs caps
+ *
+ * @value:	vfs caps value which may be modified by this function
+ * @size:	size of @ivalue
+ * @task_ns:	user namespace of the caller
+ */
+static vfsuid_t rootid_from_xattr(const void *value, size_t size,
+				  struct user_namespace *task_ns)
+{
+	const struct vfs_ns_cap_data *nscap = value;
+	uid_t rootid = 0;
+
+	if (size == XATTR_CAPS_SZ_3)
+		rootid = le32_to_cpu(nscap->rootid);
+
+	return VFSUIDT_INIT(make_kuid(task_ns, rootid));
+}
+
+static bool validheader(size_t size, const struct vfs_cap_data *cap)
+{
+	return is_v2header(size, cap) || is_v3header(size, cap);
+}
+
+/**
+ * cap_convert_nscap - check vfs caps
+ *
+ * @idmap:	idmap of the mount the inode was found from
+ * @dentry:	used to retrieve inode to check permissions on
+ * @ivalue:	vfs caps value which may be modified by this function
+ * @size:	size of @ivalue
+ *
+ * User requested a write of security.capability.  If needed, update the
+ * xattr to change from v2 to v3, or to fixup the v3 rootid.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply pass @nop_mnt_idmap.
+ *
+ * Return: On success, return the new size; on error, return < 0.
+ */
+int cap_convert_nscap(struct mnt_idmap *idmap, struct dentry *dentry,
+		      const void **ivalue, size_t size)
+{
+	struct vfs_ns_cap_data *nscap;
+	uid_t nsrootid;
+	const struct vfs_cap_data *cap = *ivalue;
+	__u32 magic, nsmagic;
+	struct inode *inode = d_backing_inode(dentry);
+	struct user_namespace *task_ns = current_user_ns(),
+		*fs_ns = inode->i_sb->s_user_ns;
+	kuid_t rootid;
+	vfsuid_t vfsrootid;
+	size_t newsize;
+
+	if (!*ivalue)
+		return -EINVAL;
+	if (!validheader(size, cap))
+		return -EINVAL;
+	if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
+		return -EPERM;
+	if (size == XATTR_CAPS_SZ_2 && (idmap == &nop_mnt_idmap))
+		if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
+			/* user is privileged, just write the v2 */
+			return size;
+
+	vfsrootid = rootid_from_xattr(*ivalue, size, task_ns);
+	if (!vfsuid_valid(vfsrootid))
+		return -EINVAL;
+
+	rootid = from_vfsuid(idmap, fs_ns, vfsrootid);
+	if (!uid_valid(rootid))
+		return -EINVAL;
+
+	nsrootid = from_kuid(fs_ns, rootid);
+	if (nsrootid == -1)
+		return -EINVAL;
+
+	newsize = sizeof(struct vfs_ns_cap_data);
+	nscap = kmalloc(newsize, GFP_ATOMIC);
+	if (!nscap)
+		return -ENOMEM;
+	nscap->rootid = cpu_to_le32(nsrootid);
+	nsmagic = VFS_CAP_REVISION_3;
+	magic = le32_to_cpu(cap->magic_etc);
+	if (magic & VFS_CAP_FLAGS_EFFECTIVE)
+		nsmagic |= VFS_CAP_FLAGS_EFFECTIVE;
+	nscap->magic_etc = cpu_to_le32(nsmagic);
+	memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32);
+
+	*ivalue = nscap;
+	return newsize;
+}
+
+/*
+ * Calculate the new process capability sets from the capability sets attached
+ * to a file.
+ */
+static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
+					  struct linux_binprm *bprm,
+					  bool *effective,
+					  bool *has_fcap)
+{
+	struct cred *new = bprm->cred;
+	int ret = 0;
+
+	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
+		*effective = true;
+
+	if (caps->magic_etc & VFS_CAP_REVISION_MASK)
+		*has_fcap = true;
+
+	/*
+	 * pP' = (X & fP) | (pI & fI)
+	 * The addition of pA' is handled later.
+	 */
+	new->cap_permitted.val =
+		(new->cap_bset.val & caps->permitted.val) |
+		(new->cap_inheritable.val & caps->inheritable.val);
+
+	if (caps->permitted.val & ~new->cap_permitted.val)
+		/* insufficient to execute correctly */
+		ret = -EPERM;
+
+	/*
+	 * For legacy apps, with no internal support for recognizing they
+	 * do not have enough capabilities, we return an error if they are
+	 * missing some "forced" (aka file-permitted) capabilities.
+	 */
+	return *effective ? ret : 0;
+}
+
+/**
+ * get_vfs_caps_from_disk - retrieve vfs caps from disk
+ *
+ * @idmap:	idmap of the mount the inode was found from
+ * @dentry:	dentry from which @inode is retrieved
+ * @cpu_caps:	vfs capabilities
+ *
+ * Extract the on-exec-apply capability sets for an executable file.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply pass @nop_mnt_idmap.
+ */
+int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
+			   const struct dentry *dentry,
+			   struct cpu_vfs_cap_data *cpu_caps)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	__u32 magic_etc;
+	int size;
+	struct vfs_ns_cap_data data, *nscaps = &data;
+	struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
+	kuid_t rootkuid;
+	vfsuid_t rootvfsuid;
+	struct user_namespace *fs_ns;
+
+	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
+
+	if (!inode)
+		return -ENODATA;
+
+	fs_ns = inode->i_sb->s_user_ns;
+	size = __vfs_getxattr((struct dentry *)dentry, inode,
+			      XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ);
+	if (size == -ENODATA || size == -EOPNOTSUPP)
+		/* no data, that's ok */
+		return -ENODATA;
+
+	if (size < 0)
+		return size;
+
+	if (size < sizeof(magic_etc))
+		return -EINVAL;
+
+	cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc);
+
+	rootkuid = make_kuid(fs_ns, 0);
+	switch (magic_etc & VFS_CAP_REVISION_MASK) {
+	case VFS_CAP_REVISION_1:
+		if (size != XATTR_CAPS_SZ_1)
+			return -EINVAL;
+		break;
+	case VFS_CAP_REVISION_2:
+		if (size != XATTR_CAPS_SZ_2)
+			return -EINVAL;
+		break;
+	case VFS_CAP_REVISION_3:
+		if (size != XATTR_CAPS_SZ_3)
+			return -EINVAL;
+		rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	rootvfsuid = make_vfsuid(idmap, fs_ns, rootkuid);
+	if (!vfsuid_valid(rootvfsuid))
+		return -ENODATA;
+
+	/* Limit the caps to the mounter of the filesystem
+	 * or the more limited uid specified in the xattr.
+	 */
+	if (!vfsuid_root_in_currentns(rootvfsuid))
+		return -ENODATA;
+
+	cpu_caps->permitted.val = le32_to_cpu(caps->data[0].permitted);
+	cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable);
+
+	/*
+	 * Rev1 had just a single 32-bit word, later expanded
+	 * to a second one for the high bits
+	 */
+	if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) {
+		cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32;
+		cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32;
+	}
+
+	cpu_caps->permitted.val &= CAP_VALID_MASK;
+	cpu_caps->inheritable.val &= CAP_VALID_MASK;
+
+	cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid);
+
+	return 0;
+}
+
+/*
+ * Attempt to get the on-exec apply capability sets for an executable file from
+ * its xattrs and, if present, apply them to the proposed credentials being
+ * constructed by execve().
+ */
+static int get_file_caps(struct linux_binprm *bprm, const struct file *file,
+			 bool *effective, bool *has_fcap)
+{
+	int rc = 0;
+	struct cpu_vfs_cap_data vcaps;
+
+	cap_clear(bprm->cred->cap_permitted);
+
+	if (!file_caps_enabled)
+		return 0;
+
+	if (!mnt_may_suid(file->f_path.mnt))
+		return 0;
+
+	/*
+	 * This check is redundant with mnt_may_suid() but is kept to make
+	 * explicit that capability bits are limited to s_user_ns and its
+	 * descendants.
+	 */
+	if (!current_in_userns(file->f_path.mnt->mnt_sb->s_user_ns))
+		return 0;
+
+	rc = get_vfs_caps_from_disk(file_mnt_idmap(file),
+				    file->f_path.dentry, &vcaps);
+	if (rc < 0) {
+		if (rc == -EINVAL)
+			printk(KERN_NOTICE "Invalid argument reading file caps for %s\n",
+					bprm->filename);
+		else if (rc == -ENODATA)
+			rc = 0;
+		goto out;
+	}
+
+	rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_fcap);
+
+out:
+	if (rc)
+		cap_clear(bprm->cred->cap_permitted);
+
+	return rc;
+}
+
+static inline bool root_privileged(void) { return !issecure(SECURE_NOROOT); }
+
+static inline bool __is_real(kuid_t uid, struct cred *cred)
+{ return uid_eq(cred->uid, uid); }
+
+static inline bool __is_eff(kuid_t uid, struct cred *cred)
+{ return uid_eq(cred->euid, uid); }
+
+static inline bool __is_suid(kuid_t uid, struct cred *cred)
+{ return !__is_real(uid, cred) && __is_eff(uid, cred); }
+
+/*
+ * handle_privileged_root - Handle case of privileged root
+ * @bprm: The execution parameters, including the proposed creds
+ * @has_fcap: Are any file capabilities set?
+ * @effective: Do we have effective root privilege?
+ * @root_uid: This namespace' root UID WRT initial USER namespace
+ *
+ * Handle the case where root is privileged and hasn't been neutered by
+ * SECURE_NOROOT.  If file capabilities are set, they won't be combined with
+ * set UID root and nothing is changed.  If we are root, cap_permitted is
+ * updated.  If we have become set UID root, the effective bit is set.
+ */
+static void handle_privileged_root(struct linux_binprm *bprm, bool has_fcap,
+				   bool *effective, kuid_t root_uid)
+{
+	const struct cred *old = current_cred();
+	struct cred *new = bprm->cred;
+
+	if (!root_privileged())
+		return;
+	/*
+	 * If the legacy file capability is set, then don't set privs
+	 * for a setuid root binary run by a non-root user.  Do set it
+	 * for a root user just to cause least surprise to an admin.
+	 */
+	if (has_fcap && __is_suid(root_uid, new)) {
+		warn_setuid_and_fcaps_mixed(bprm->filename);
+		return;
+	}
+	/*
+	 * To support inheritance of root-permissions and suid-root
+	 * executables under compatibility mode, we override the
+	 * capability sets for the file.
+	 */
+	if (__is_eff(root_uid, new) || __is_real(root_uid, new)) {
+		/* pP' = (cap_bset & ~0) | (pI & ~0) */
+		new->cap_permitted = cap_combine(old->cap_bset,
+						 old->cap_inheritable);
+	}
+	/*
+	 * If only the real uid is 0, we do not set the effective bit.
+	 */
+	if (__is_eff(root_uid, new))
+		*effective = true;
+}
+
+#define __cap_gained(field, target, source) \
+	!cap_issubset(target->cap_##field, source->cap_##field)
+#define __cap_grew(target, source, cred) \
+	!cap_issubset(cred->cap_##target, cred->cap_##source)
+#define __cap_full(field, cred) \
+	cap_issubset(CAP_FULL_SET, cred->cap_##field)
+
+/*
+ * 1) Audit candidate if current->cap_effective is set
+ *
+ * We do not bother to audit if 3 things are true:
+ *   1) cap_effective has all caps
+ *   2) we became root *OR* are were already root
+ *   3) root is supposed to have all caps (SECURE_NOROOT)
+ * Since this is just a normal root execing a process.
+ *
+ * Number 1 above might fail if you don't have a full bset, but I think
+ * that is interesting information to audit.
+ *
+ * A number of other conditions require logging:
+ * 2) something prevented setuid root getting all caps
+ * 3) non-setuid root gets fcaps
+ * 4) non-setuid root gets ambient
+ */
+static inline bool nonroot_raised_pE(struct cred *new, const struct cred *old,
+				     kuid_t root, bool has_fcap)
+{
+	bool ret = false;
+
+	if ((__cap_grew(effective, ambient, new) &&
+	     !(__cap_full(effective, new) &&
+	       (__is_eff(root, new) || __is_real(root, new)) &&
+	       root_privileged())) ||
+	    (root_privileged() &&
+	     __is_suid(root, new) &&
+	     !__cap_full(effective, new)) ||
+	    (uid_eq(new->euid, old->euid) &&
+	     ((has_fcap &&
+	       __cap_gained(permitted, new, old)) ||
+	      __cap_gained(ambient, new, old))))
+
+		ret = true;
+
+	return ret;
+}
+
+/**
+ * cap_bprm_creds_from_file - Set up the proposed credentials for execve().
+ * @bprm: The execution parameters, including the proposed creds
+ * @file: The file to pull the credentials from
+ *
+ * Set up the proposed credentials for a new execution context being
+ * constructed by execve().  The proposed creds in @bprm->cred is altered,
+ * which won't take effect immediately.
+ *
+ * Return: 0 if successful, -ve on error.
+ */
+int cap_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file)
+{
+	/* Process setpcap binaries and capabilities for uid 0 */
+	const struct cred *old = current_cred();
+	struct cred *new = bprm->cred;
+	bool effective = false, has_fcap = false, id_changed;
+	int ret;
+	kuid_t root_uid;
+
+	if (WARN_ON(!cap_ambient_invariant_ok(old)))
+		return -EPERM;
+
+	ret = get_file_caps(bprm, file, &effective, &has_fcap);
+	if (ret < 0)
+		return ret;
+
+	root_uid = make_kuid(new->user_ns, 0);
+
+	handle_privileged_root(bprm, has_fcap, &effective, root_uid);
+
+	/* if we have fs caps, clear dangerous personality flags */
+	if (__cap_gained(permitted, new, old))
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
+	 * credentials unless they have the appropriate permit.
+	 *
+	 * In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
+	 */
+	id_changed = !uid_eq(new->euid, old->euid) || !in_group_p(new->egid);
+
+	if ((id_changed || __cap_gained(permitted, new, old)) &&
+	    ((bprm->unsafe & ~LSM_UNSAFE_PTRACE) ||
+	     !ptracer_capable(current, new->user_ns))) {
+		/* downgrade; they get no more than they had, and maybe less */
+		if (!ns_capable(new->user_ns, CAP_SETUID) ||
+		    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) {
+			new->euid = new->uid;
+			new->egid = new->gid;
+		}
+		new->cap_permitted = cap_intersect(new->cap_permitted,
+						   old->cap_permitted);
+	}
+
+	new->suid = new->fsuid = new->euid;
+	new->sgid = new->fsgid = new->egid;
+
+	/* File caps or setid cancels ambient. */
+	if (has_fcap || id_changed)
+		cap_clear(new->cap_ambient);
+
+	/*
+	 * Now that we've computed pA', update pP' to give:
+	 *   pP' = (X & fP) | (pI & fI) | pA'
+	 */
+	new->cap_permitted = cap_combine(new->cap_permitted, new->cap_ambient);
+
+	/*
+	 * Set pE' = (fE ? pP' : pA').  Because pA' is zero if fE is set,
+	 * this is the same as pE' = (fE ? pP' : 0) | pA'.
+	 */
+	if (effective)
+		new->cap_effective = new->cap_permitted;
+	else
+		new->cap_effective = new->cap_ambient;
+
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EPERM;
+
+	if (nonroot_raised_pE(new, old, root_uid, has_fcap)) {
+		ret = audit_log_bprm_fcaps(bprm, new, old);
+		if (ret < 0)
+			return ret;
+	}
+
+	new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+
+	if (WARN_ON(!cap_ambient_invariant_ok(new)))
+		return -EPERM;
+
+	/* Check for privilege-elevated exec. */
+	if (id_changed ||
+	    !uid_eq(new->euid, old->uid) ||
+	    !gid_eq(new->egid, old->gid) ||
+	    (!__is_real(root_uid, new) &&
+	     (effective ||
+	      __cap_grew(permitted, ambient, new))))
+		bprm->secureexec = 1;
+
+	return 0;
+}
+
+/**
+ * cap_inode_setxattr - Determine whether an xattr may be altered
+ * @dentry: The inode/dentry being altered
+ * @name: The name of the xattr to be changed
+ * @value: The value that the xattr will be changed to
+ * @size: The size of value
+ * @flags: The replacement flag
+ *
+ * Determine whether an xattr may be altered or set on an inode, returning 0 if
+ * permission is granted, -ve if denied.
+ *
+ * This is used to make sure security xattrs don't get updated or set by those
+ * who aren't privileged to do so.
+ */
+int cap_inode_setxattr(struct dentry *dentry, const char *name,
+		       const void *value, size_t size, int flags)
+{
+	struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
+	/* Ignore non-security xattrs */
+	if (strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN) != 0)
+		return 0;
+
+	/*
+	 * For XATTR_NAME_CAPS the check will be done in
+	 * cap_convert_nscap(), called by setxattr()
+	 */
+	if (strcmp(name, XATTR_NAME_CAPS) == 0)
+		return 0;
+
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+	return 0;
+}
+
+/**
+ * cap_inode_removexattr - Determine whether an xattr may be removed
+ *
+ * @idmap:	idmap of the mount the inode was found from
+ * @dentry:	The inode/dentry being altered
+ * @name:	The name of the xattr to be changed
+ *
+ * Determine whether an xattr may be removed from an inode, returning 0 if
+ * permission is granted, -ve if denied.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply pass @nop_mnt_idmap.
+ *
+ * This is used to make sure security xattrs don't get removed by those who
+ * aren't privileged to remove them.
+ */
+int cap_inode_removexattr(struct mnt_idmap *idmap,
+			  struct dentry *dentry, const char *name)
+{
+	struct user_namespace *user_ns = dentry->d_sb->s_user_ns;
+
+	/* Ignore non-security xattrs */
+	if (strncmp(name, XATTR_SECURITY_PREFIX,
+			XATTR_SECURITY_PREFIX_LEN) != 0)
+		return 0;
+
+	if (strcmp(name, XATTR_NAME_CAPS) == 0) {
+		/* security.capability gets namespaced */
+		struct inode *inode = d_backing_inode(dentry);
+		if (!inode)
+			return -EINVAL;
+		if (!capable_wrt_inode_uidgid(idmap, inode, CAP_SETFCAP))
+			return -EPERM;
+		return 0;
+	}
+
+	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
+		return -EPERM;
+	return 0;
+}
+
+/*
+ * cap_emulate_setxuid() fixes the effective / permitted capabilities of
+ * a process after a call to setuid, setreuid, or setresuid.
+ *
+ *  1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
+ *  {r,e,s}uid != 0, the permitted and effective capabilities are
+ *  cleared.
+ *
+ *  2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
+ *  capabilities of the process are cleared.
+ *
+ *  3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
+ *  capabilities are set to the permitted capabilities.
+ *
+ *  fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should
+ *  never happen.
+ *
+ *  -astor
+ *
+ * cevans - New behaviour, Oct '99
+ * A process may, via prctl(), elect to keep its capabilities when it
+ * calls setuid() and switches away from uid==0. Both permitted and
+ * effective sets will be retained.
+ * Without this change, it was impossible for a daemon to drop only some
+ * of its privilege. The call to setuid(!=0) would drop all privileges!
+ * Keeping uid 0 is not an option because uid 0 owns too many vital
+ * files..
+ * Thanks to Olaf Kirch and Peter Benie for spotting this.
+ */
+static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old)
+{
+	kuid_t root_uid = make_kuid(old->user_ns, 0);
+
+	if ((uid_eq(old->uid, root_uid) ||
+	     uid_eq(old->euid, root_uid) ||
+	     uid_eq(old->suid, root_uid)) &&
+	    (!uid_eq(new->uid, root_uid) &&
+	     !uid_eq(new->euid, root_uid) &&
+	     !uid_eq(new->suid, root_uid))) {
+		if (!issecure(SECURE_KEEP_CAPS)) {
+			cap_clear(new->cap_permitted);
+			cap_clear(new->cap_effective);
+		}
+
+		/*
+		 * Pre-ambient programs expect setresuid to nonroot followed
+		 * by exec to drop capabilities.  We should make sure that
+		 * this remains the case.
+		 */
+		cap_clear(new->cap_ambient);
+	}
+	if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid))
+		cap_clear(new->cap_effective);
+	if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid))
+		new->cap_effective = new->cap_permitted;
+}
+
+/**
+ * cap_task_fix_setuid - Fix up the results of setuid() call
+ * @new: The proposed credentials
+ * @old: The current task's current credentials
+ * @flags: Indications of what has changed
+ *
+ * Fix up the results of setuid() call before the credential changes are
+ * actually applied.
+ *
+ * Return: 0 to grant the changes, -ve to deny them.
+ */
+int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
+{
+	switch (flags) {
+	case LSM_SETID_RE:
+	case LSM_SETID_ID:
+	case LSM_SETID_RES:
+		/* juggle the capabilities to follow [RES]UID changes unless
+		 * otherwise suppressed */
+		if (!issecure(SECURE_NO_SETUID_FIXUP))
+			cap_emulate_setxuid(new, old);
+		break;
+
+	case LSM_SETID_FS:
+		/* juggle the capabilities to follow FSUID changes, unless
+		 * otherwise suppressed
+		 *
+		 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
+		 *          if not, we might be a bit too harsh here.
+		 */
+		if (!issecure(SECURE_NO_SETUID_FIXUP)) {
+			kuid_t root_uid = make_kuid(old->user_ns, 0);
+			if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid))
+				new->cap_effective =
+					cap_drop_fs_set(new->cap_effective);
+
+			if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid))
+				new->cap_effective =
+					cap_raise_fs_set(new->cap_effective,
+							 new->cap_permitted);
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Rationale: code calling task_setscheduler, task_setioprio, and
+ * task_setnice, assumes that
+ *   . if capable(cap_sys_nice), then those actions should be allowed
+ *   . if not capable(cap_sys_nice), but acting on your own processes,
+ *   	then those actions should be allowed
+ * This is insufficient now since you can call code without suid, but
+ * yet with increased caps.
+ * So we check for increased caps on the target process.
+ */
+static int cap_safe_nice(struct task_struct *p)
+{
+	int is_subset, ret = 0;
+
+	rcu_read_lock();
+	is_subset = cap_issubset(__task_cred(p)->cap_permitted,
+				 current_cred()->cap_permitted);
+	if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+		ret = -EPERM;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * cap_task_setscheduler - Determine if scheduler policy change is permitted
+ * @p: The task to affect
+ *
+ * Determine if the requested scheduler policy change is permitted for the
+ * specified task.
+ *
+ * Return: 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setscheduler(struct task_struct *p)
+{
+	return cap_safe_nice(p);
+}
+
+/**
+ * cap_task_setioprio - Determine if I/O priority change is permitted
+ * @p: The task to affect
+ * @ioprio: The I/O priority to set
+ *
+ * Determine if the requested I/O priority change is permitted for the specified
+ * task.
+ *
+ * Return: 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setioprio(struct task_struct *p, int ioprio)
+{
+	return cap_safe_nice(p);
+}
+
+/**
+ * cap_task_setnice - Determine if task priority change is permitted
+ * @p: The task to affect
+ * @nice: The nice value to set
+ *
+ * Determine if the requested task priority change is permitted for the
+ * specified task.
+ *
+ * Return: 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setnice(struct task_struct *p, int nice)
+{
+	return cap_safe_nice(p);
+}
+
+/*
+ * Implement PR_CAPBSET_DROP.  Attempt to remove the specified capability from
+ * the current task's bounding set.  Returns 0 on success, -ve on error.
+ */
+static int cap_prctl_drop(unsigned long cap)
+{
+	struct cred *new;
+
+	if (!ns_capable(current_user_ns(), CAP_SETPCAP))
+		return -EPERM;
+	if (!cap_valid(cap))
+		return -EINVAL;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	cap_lower(new->cap_bset, cap);
+	return commit_creds(new);
+}
+
+/**
+ * cap_task_prctl - Implement process control functions for this security module
+ * @option: The process control function requested
+ * @arg2: The argument data for this function
+ * @arg3: The argument data for this function
+ * @arg4: The argument data for this function
+ * @arg5: The argument data for this function
+ *
+ * Allow process control functions (sys_prctl()) to alter capabilities; may
+ * also deny access to other functions not otherwise implemented here.
+ *
+ * Return: 0 or +ve on success, -ENOSYS if this function is not implemented
+ * here, other -ve on error.  If -ENOSYS is returned, sys_prctl() and other LSM
+ * modules will consider performing the function.
+ */
+int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+		   unsigned long arg4, unsigned long arg5)
+{
+	const struct cred *old = current_cred();
+	struct cred *new;
+
+	switch (option) {
+	case PR_CAPBSET_READ:
+		if (!cap_valid(arg2))
+			return -EINVAL;
+		return !!cap_raised(old->cap_bset, arg2);
+
+	case PR_CAPBSET_DROP:
+		return cap_prctl_drop(arg2);
+
+	/*
+	 * The next four prctl's remain to assist with transitioning a
+	 * system from legacy UID=0 based privilege (when filesystem
+	 * capabilities are not in use) to a system using filesystem
+	 * capabilities only - as the POSIX.1e draft intended.
+	 *
+	 * Note:
+	 *
+	 *  PR_SET_SECUREBITS =
+	 *      issecure_mask(SECURE_KEEP_CAPS_LOCKED)
+	 *    | issecure_mask(SECURE_NOROOT)
+	 *    | issecure_mask(SECURE_NOROOT_LOCKED)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
+	 *
+	 * will ensure that the current process and all of its
+	 * children will be locked into a pure
+	 * capability-based-privilege environment.
+	 */
+	case PR_SET_SECUREBITS:
+		if ((((old->securebits & SECURE_ALL_LOCKS) >> 1)
+		     & (old->securebits ^ arg2))			/*[1]*/
+		    || ((old->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
+		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
+			/*
+			 * [1] no changing of bits that are locked
+			 * [2] no unlocking of locks
+			 * [3] no setting of unsupported bits
+			 */
+		    )
+			/* cannot change a locked bit */
+			return -EPERM;
+
+		/*
+		 * Doing anything requires privilege (go read about the
+		 * "sendmail capabilities bug"), except for unprivileged bits.
+		 * Indeed, the SECURE_ALL_UNPRIVILEGED bits are not
+		 * restrictions enforced by the kernel but by user space on
+		 * itself.
+		 */
+		if (cap_capable(current_cred(), current_cred()->user_ns,
+				CAP_SETPCAP, CAP_OPT_NONE) != 0) {
+			const unsigned long unpriv_and_locks =
+				SECURE_ALL_UNPRIVILEGED |
+				SECURE_ALL_UNPRIVILEGED << 1;
+			const unsigned long changed = old->securebits ^ arg2;
+
+			/* For legacy reason, denies non-change. */
+			if (!changed)
+				return -EPERM;
+
+			/* Denies privileged changes. */
+			if (changed & ~unpriv_and_locks)
+				return -EPERM;
+		}
+
+		new = prepare_creds();
+		if (!new)
+			return -ENOMEM;
+		new->securebits = arg2;
+		return commit_creds(new);
+
+	case PR_GET_SECUREBITS:
+		return old->securebits;
+
+	case PR_GET_KEEPCAPS:
+		return !!issecure(SECURE_KEEP_CAPS);
+
+	case PR_SET_KEEPCAPS:
+		if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
+			return -EINVAL;
+		if (issecure(SECURE_KEEP_CAPS_LOCKED))
+			return -EPERM;
+
+		new = prepare_creds();
+		if (!new)
+			return -ENOMEM;
+		if (arg2)
+			new->securebits |= issecure_mask(SECURE_KEEP_CAPS);
+		else
+			new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+		return commit_creds(new);
+
+	case PR_CAP_AMBIENT:
+		if (arg2 == PR_CAP_AMBIENT_CLEAR_ALL) {
+			if (arg3 | arg4 | arg5)
+				return -EINVAL;
+
+			new = prepare_creds();
+			if (!new)
+				return -ENOMEM;
+			cap_clear(new->cap_ambient);
+			return commit_creds(new);
+		}
+
+		if (((!cap_valid(arg3)) | arg4 | arg5))
+			return -EINVAL;
+
+		if (arg2 == PR_CAP_AMBIENT_IS_SET) {
+			return !!cap_raised(current_cred()->cap_ambient, arg3);
+		} else if (arg2 != PR_CAP_AMBIENT_RAISE &&
+			   arg2 != PR_CAP_AMBIENT_LOWER) {
+			return -EINVAL;
+		} else {
+			if (arg2 == PR_CAP_AMBIENT_RAISE &&
+			    (!cap_raised(current_cred()->cap_permitted, arg3) ||
+			     !cap_raised(current_cred()->cap_inheritable,
+					 arg3) ||
+			     issecure(SECURE_NO_CAP_AMBIENT_RAISE)))
+				return -EPERM;
+
+			new = prepare_creds();
+			if (!new)
+				return -ENOMEM;
+			if (arg2 == PR_CAP_AMBIENT_RAISE)
+				cap_raise(new->cap_ambient, arg3);
+			else
+				cap_lower(new->cap_ambient, arg3);
+			return commit_creds(new);
+		}
+
+	default:
+		/* No functionality available - continue with default */
+		return -ENOSYS;
+	}
+}
+
+/**
+ * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted
+ * @mm: The VM space in which the new mapping is to be made
+ * @pages: The size of the mapping
+ *
+ * Determine whether the allocation of a new virtual mapping by the current
+ * task is permitted.
+ *
+ * Return: 0 if permission granted, negative error code if not.
+ */
+int cap_vm_enough_memory(struct mm_struct *mm, long pages)
+{
+	return cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN,
+			   CAP_OPT_NOAUDIT);
+}
+
+/**
+ * cap_mmap_addr - check if able to map given addr
+ * @addr: address attempting to be mapped
+ *
+ * If the process is attempting to map memory below dac_mmap_min_addr they need
+ * CAP_SYS_RAWIO.  The other parameters to this function are unused by the
+ * capability security module.
+ *
+ * Return: 0 if this mapping should be allowed or -EPERM if not.
+ */
+int cap_mmap_addr(unsigned long addr)
+{
+	int ret = 0;
+
+	if (addr < dac_mmap_min_addr) {
+		ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO,
+				  CAP_OPT_NONE);
+		/* set PF_SUPERPRIV if it turns out we allow the low mmap */
+		if (ret == 0)
+			current->flags |= PF_SUPERPRIV;
+	}
+	return ret;
+}
+
+#ifdef CONFIG_SECURITY
+
+static const struct lsm_id capability_lsmid = {
+	.name = "capability",
+	.id = LSM_ID_CAPABILITY,
+};
+
+static struct security_hook_list capability_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(capable, cap_capable),
+	LSM_HOOK_INIT(settime, cap_settime),
+	LSM_HOOK_INIT(ptrace_access_check, cap_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, cap_ptrace_traceme),
+	LSM_HOOK_INIT(capget, cap_capget),
+	LSM_HOOK_INIT(capset, cap_capset),
+	LSM_HOOK_INIT(bprm_creds_from_file, cap_bprm_creds_from_file),
+	LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv),
+	LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv),
+	LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity),
+	LSM_HOOK_INIT(mmap_addr, cap_mmap_addr),
+	LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid),
+	LSM_HOOK_INIT(task_prctl, cap_task_prctl),
+	LSM_HOOK_INIT(task_setscheduler, cap_task_setscheduler),
+	LSM_HOOK_INIT(task_setioprio, cap_task_setioprio),
+	LSM_HOOK_INIT(task_setnice, cap_task_setnice),
+	LSM_HOOK_INIT(vm_enough_memory, cap_vm_enough_memory),
+};
+
+static int __init capability_init(void)
+{
+	security_add_hooks(capability_hooks, ARRAY_SIZE(capability_hooks),
+			   &capability_lsmid);
+	return 0;
+}
+
+DEFINE_LSM(capability) = {
+	.id = &capability_lsmid,
+	.order = LSM_ORDER_FIRST,
+	.init = capability_init,
+};
+
+#endif /* CONFIG_SECURITY */
+
+#ifdef CONFIG_SECURITY_COMMONCAP_KUNIT_TEST
+#include "commoncap_test.c"
+#endif
diff --git a/security/commoncap_test.c b/security/commoncap_test.c
new file mode 100644
index 000000000..e9b278be3
--- /dev/null
+++ b/security/commoncap_test.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * KUnit tests for commoncap.c security functions
+ *
+ * Tests for security-critical functions in the capability subsystem,
+ * particularly namespace-related capability checks.
+ */
+
+#include <kunit/test.h>
+#include <linux/user_namespace.h>
+#include <linux/uidgid.h>
+#include <linux/cred.h>
+#include <linux/mnt_idmapping.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/refcount.h>
+
+#ifdef CONFIG_SECURITY_COMMONCAP_KUNIT_TEST
+
+/* Functions are static in commoncap.c, but we can call them since we're
+ * included in the same compilation unit when tests are enabled.
+ */
+
+/**
+ * test_vfsuid_root_in_currentns_init_ns - Test vfsuid_root_in_currentns with init ns
+ *
+ * Verifies that UID 0 in the init namespace correctly owns the current
+ * namespace when running in init_user_ns.
+ *
+ * @test: KUnit test context
+ */
+static void test_vfsuid_root_in_currentns_init_ns(struct kunit *test)
+{
+	vfsuid_t vfsuid;
+	kuid_t kuid;
+
+	/* Create UID 0 in init namespace */
+	kuid = KUIDT_INIT(0);
+	vfsuid = VFSUIDT_INIT(kuid);
+
+	/* In init namespace, UID 0 should own current namespace */
+	KUNIT_EXPECT_TRUE(test, vfsuid_root_in_currentns(vfsuid));
+}
+
+/**
+ * test_vfsuid_root_in_currentns_invalid - Test vfsuid_root_in_currentns with invalid vfsuid
+ *
+ * Verifies that an invalid vfsuid correctly returns false.
+ *
+ * @test: KUnit test context
+ */
+static void test_vfsuid_root_in_currentns_invalid(struct kunit *test)
+{
+	vfsuid_t invalid_vfsuid;
+
+	/* Use the predefined invalid vfsuid */
+	invalid_vfsuid = INVALID_VFSUID;
+
+	/* Invalid vfsuid should return false */
+	KUNIT_EXPECT_FALSE(test, vfsuid_root_in_currentns(invalid_vfsuid));
+}
+
+/**
+ * test_vfsuid_root_in_currentns_nonzero - Test vfsuid_root_in_currentns with non-zero UID
+ *
+ * Verifies that a non-zero UID correctly returns false.
+ *
+ * @test: KUnit test context
+ */
+static void test_vfsuid_root_in_currentns_nonzero(struct kunit *test)
+{
+	vfsuid_t vfsuid;
+	kuid_t kuid;
+
+	/* Create a non-zero UID */
+	kuid = KUIDT_INIT(1000);
+	vfsuid = VFSUIDT_INIT(kuid);
+
+	/* Non-zero UID should return false */
+	KUNIT_EXPECT_FALSE(test, vfsuid_root_in_currentns(vfsuid));
+}
+
+/**
+ * test_kuid_root_in_ns_init_ns_uid0 - Test kuid_root_in_ns with init namespace and UID 0
+ *
+ * Verifies that kuid_root_in_ns correctly identifies UID 0 in init namespace.
+ * This tests the core namespace traversal logic. In init namespace, UID 0
+ * maps to itself, so it should own the namespace.
+ *
+ * @test: KUnit test context
+ */
+static void test_kuid_root_in_ns_init_ns_uid0(struct kunit *test)
+{
+	kuid_t kuid;
+	struct user_namespace *init_ns;
+
+	kuid = KUIDT_INIT(0);
+	init_ns = &init_user_ns;
+
+	/* UID 0 should own init namespace */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(kuid, init_ns));
+}
+
+/**
+ * test_kuid_root_in_ns_init_ns_nonzero - Test kuid_root_in_ns with init namespace and non-zero UID
+ *
+ * Verifies that kuid_root_in_ns correctly rejects non-zero UIDs in init namespace.
+ * Only UID 0 should own a namespace.
+ *
+ * @test: KUnit test context
+ */
+static void test_kuid_root_in_ns_init_ns_nonzero(struct kunit *test)
+{
+	kuid_t kuid;
+	struct user_namespace *init_ns;
+
+	kuid = KUIDT_INIT(1000);
+	init_ns = &init_user_ns;
+
+	/* Non-zero UID should not own namespace */
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(kuid, init_ns));
+}
+
+/**
+ * create_test_user_ns_with_mapping - Create a mock user namespace with UID mapping
+ *
+ * Creates a minimal user namespace structure for testing where uid 0 in the
+ * namespace maps to a specific kuid in the parent namespace.
+ *
+ * @test: KUnit test context
+ * @parent_ns: Parent namespace (typically init_user_ns)
+ * @mapped_kuid: The kuid that uid 0 in this namespace maps to in parent
+ *
+ * Returns: Pointer to allocated namespace, or NULL on failure
+ */
+static struct user_namespace *create_test_user_ns_with_mapping(struct kunit *test,
+								 struct user_namespace *parent_ns,
+								 kuid_t mapped_kuid)
+{
+	struct user_namespace *ns;
+	struct uid_gid_extent extent;
+
+	/* Allocate a test namespace - use kzalloc to zero all fields */
+	ns = kunit_kzalloc(test, sizeof(*ns), GFP_KERNEL);
+	if (!ns)
+		return NULL;
+
+	/* Initialize basic namespace structure fields */
+	ns->parent = parent_ns;
+	ns->level = parent_ns ? parent_ns->level + 1 : 0;
+	ns->owner = mapped_kuid;
+	ns->group = KGIDT_INIT(0);
+
+	/* Initialize ns_common structure */
+	refcount_set(&ns->ns.__ns_ref, 1);
+	ns->ns.inum = 0; /* Mock inum */
+
+	/* Set up uid mapping: uid 0 in this namespace maps to mapped_kuid in parent
+	 * Format: first (uid in ns) : lower_first (kuid in parent) : count
+	 * So: uid 0 in ns -> kuid mapped_kuid in parent
+	 * This means from_kuid(ns, mapped_kuid) returns 0
+	 */
+	extent.first = 0;                              /* uid 0 in this namespace */
+	extent.lower_first = __kuid_val(mapped_kuid);  /* maps to this kuid in parent */
+	extent.count = 1;
+
+	ns->uid_map.extent[0] = extent;
+	ns->uid_map.nr_extents = 1;
+
+	/* Set up gid mapping: gid 0 maps to gid 0 in parent (simplified) */
+	extent.first = 0;
+	extent.lower_first = 0;
+	extent.count = 1;
+
+	ns->gid_map.extent[0] = extent;
+	ns->gid_map.nr_extents = 1;
+
+	return ns;
+}
+
+/**
+ * test_kuid_root_in_ns_with_mapping - Test kuid_root_in_ns with namespace where uid 0
+ *				       maps to different kuid
+ *
+ * Creates a user namespace where uid 0 maps to kuid 1000 in the parent namespace.
+ * Verifies that kuid_root_in_ns correctly identifies kuid 1000 as owning the namespace.
+ *
+ * Note: kuid_root_in_ns walks up the namespace hierarchy, so it checks the current
+ * namespace first, then parent, then parent's parent, etc. So:
+ * - kuid 1000 owns test_ns because from_kuid(test_ns, 1000) == 0
+ * - kuid 0 also owns test_ns because from_kuid(init_user_ns, 0) == 0
+ *   (checked in parent)
+ *
+ * This tests the actual functionality as requested: creating namespaces with
+ * different values for the namespace's uid 0.
+ *
+ * @test: KUnit test context
+ */
+static void test_kuid_root_in_ns_with_mapping(struct kunit *test)
+{
+	struct user_namespace *test_ns;
+	struct user_namespace *parent_ns;
+	kuid_t mapped_kuid, other_kuid;
+
+	parent_ns = &init_user_ns;
+	mapped_kuid = KUIDT_INIT(1000);
+	other_kuid = KUIDT_INIT(2000);
+
+	test_ns = create_test_user_ns_with_mapping(test, parent_ns, mapped_kuid);
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_ns);
+
+	/* kuid 1000 should own test_ns because it maps to uid 0 in test_ns */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(mapped_kuid, test_ns));
+
+	/* kuid 0 should also own test_ns (checked via parent init_user_ns) */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(0), test_ns));
+
+	/* Other kuids should not own test_ns */
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(other_kuid, test_ns));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(500), test_ns));
+}
+
+/**
+ * test_kuid_root_in_ns_with_different_mappings - Test with multiple namespaces
+ *
+ * Creates multiple user namespaces with different UID mappings to verify
+ * that kuid_root_in_ns correctly distinguishes between namespaces.
+ *
+ * Each namespace maps uid 0 to a different kuid, and we verify that each
+ * kuid only owns its corresponding namespace (plus kuid 0 owns all via
+ * init_user_ns parent).
+ *
+ * @test: KUnit test context
+ */
+static void test_kuid_root_in_ns_with_different_mappings(struct kunit *test)
+{
+	struct user_namespace *ns1, *ns2, *ns3;
+
+	/* Create three independent namespaces, each mapping uid 0 to different kuids */
+	ns1 = create_test_user_ns_with_mapping(test, &init_user_ns, KUIDT_INIT(1000));
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ns1);
+
+	ns2 = create_test_user_ns_with_mapping(test, &init_user_ns, KUIDT_INIT(2000));
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ns2);
+
+	ns3 = create_test_user_ns_with_mapping(test, &init_user_ns, KUIDT_INIT(3000));
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ns3);
+
+	/* Test ns1: kuid 1000 owns it, kuid 0 owns it (via parent), others do not */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(1000), ns1));
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(0), ns1));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(2000), ns1));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(3000), ns1));
+
+	/* Test ns2: kuid 2000 owns it, kuid 0 owns it (via parent), others do not */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(2000), ns2));
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(0), ns2));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(1000), ns2));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(3000), ns2));
+
+	/* Test ns3: kuid 3000 owns it, kuid 0 owns it (via parent), others do not */
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(3000), ns3));
+	KUNIT_EXPECT_TRUE(test, kuid_root_in_ns(KUIDT_INIT(0), ns3));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(1000), ns3));
+	KUNIT_EXPECT_FALSE(test, kuid_root_in_ns(KUIDT_INIT(2000), ns3));
+}
+
+static struct kunit_case commoncap_test_cases[] = {
+	KUNIT_CASE(test_vfsuid_root_in_currentns_init_ns),
+	KUNIT_CASE(test_vfsuid_root_in_currentns_invalid),
+	KUNIT_CASE(test_vfsuid_root_in_currentns_nonzero),
+	KUNIT_CASE(test_kuid_root_in_ns_init_ns_uid0),
+	KUNIT_CASE(test_kuid_root_in_ns_init_ns_nonzero),
+	KUNIT_CASE(test_kuid_root_in_ns_with_mapping),
+	KUNIT_CASE(test_kuid_root_in_ns_with_different_mappings),
+	{}
+};
+
+static struct kunit_suite commoncap_test_suite = {
+	.name = "commoncap",
+	.test_cases = commoncap_test_cases,
+};
+
+kunit_test_suite(commoncap_test_suite);
+
+MODULE_LICENSE("GPL");
+
+#endif /* CONFIG_SECURITY_COMMONCAP_KUNIT_TEST */
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
new file mode 100644
index 000000000..cd166dee6
--- /dev/null
+++ b/security/device_cgroup.c
@@ -0,0 +1,870 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * device_cgroup.c - device cgroup subsystem
+ *
+ * Copyright 2007 IBM Corp
+ */
+
+#include <linux/bpf-cgroup.h>
+#include <linux/device_cgroup.h>
+#include <linux/cgroup.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
+
+#ifdef CONFIG_CGROUP_DEVICE
+
+static DEFINE_MUTEX(devcgroup_mutex);
+
+enum devcg_behavior {
+	DEVCG_DEFAULT_NONE,
+	DEVCG_DEFAULT_ALLOW,
+	DEVCG_DEFAULT_DENY,
+};
+
+/*
+ * exception list locking rules:
+ * hold devcgroup_mutex for update/read.
+ * hold rcu_read_lock() for read.
+ */
+
+struct dev_exception_item {
+	u32 major, minor;
+	short type;
+	short access;
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+struct dev_cgroup {
+	struct cgroup_subsys_state css;
+	struct list_head exceptions;
+	enum devcg_behavior behavior;
+};
+
+static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
+{
+	return s ? container_of(s, struct dev_cgroup, css) : NULL;
+}
+
+static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
+{
+	return css_to_devcgroup(task_css(task, devices_cgrp_id));
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig)
+{
+	struct dev_exception_item *ex, *tmp, *new;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry(ex, orig, list) {
+		new = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
+		if (!new)
+			goto free_and_exit;
+		list_add_tail(&new->list, dest);
+	}
+
+	return 0;
+
+free_and_exit:
+	list_for_each_entry_safe(ex, tmp, dest, list) {
+		list_del(&ex->list);
+		kfree(ex);
+	}
+	return -ENOMEM;
+}
+
+static void dev_exceptions_move(struct list_head *dest, struct list_head *orig)
+{
+	struct dev_exception_item *ex, *tmp;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry_safe(ex, tmp, orig, list) {
+		list_move_tail(&ex->list, dest);
+	}
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static int dev_exception_add(struct dev_cgroup *dev_cgroup,
+			     struct dev_exception_item *ex)
+{
+	struct dev_exception_item *excopy, *walk;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
+	if (!excopy)
+		return -ENOMEM;
+
+	list_for_each_entry(walk, &dev_cgroup->exceptions, list) {
+		if (walk->type != ex->type)
+			continue;
+		if (walk->major != ex->major)
+			continue;
+		if (walk->minor != ex->minor)
+			continue;
+
+		walk->access |= ex->access;
+		kfree(excopy);
+		excopy = NULL;
+	}
+
+	if (excopy != NULL)
+		list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions);
+	return 0;
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static void dev_exception_rm(struct dev_cgroup *dev_cgroup,
+			     struct dev_exception_item *ex)
+{
+	struct dev_exception_item *walk, *tmp;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) {
+		if (walk->type != ex->type)
+			continue;
+		if (walk->major != ex->major)
+			continue;
+		if (walk->minor != ex->minor)
+			continue;
+
+		walk->access &= ~ex->access;
+		if (!walk->access) {
+			list_del_rcu(&walk->list);
+			kfree_rcu(walk, rcu);
+		}
+	}
+}
+
+static void __dev_exception_clean(struct dev_cgroup *dev_cgroup)
+{
+	struct dev_exception_item *ex, *tmp;
+
+	list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) {
+		list_del_rcu(&ex->list);
+		kfree_rcu(ex, rcu);
+	}
+}
+
+/**
+ * dev_exception_clean - frees all entries of the exception list
+ * @dev_cgroup: dev_cgroup with the exception list to be cleaned
+ *
+ * called under devcgroup_mutex
+ */
+static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
+{
+	lockdep_assert_held(&devcgroup_mutex);
+
+	__dev_exception_clean(dev_cgroup);
+}
+
+static inline bool is_devcg_online(const struct dev_cgroup *devcg)
+{
+	return (devcg->behavior != DEVCG_DEFAULT_NONE);
+}
+
+/**
+ * devcgroup_online - initializes devcgroup's behavior and exceptions based on
+ * 		      parent's
+ * @css: css getting online
+ * returns 0 in case of success, error code otherwise
+ */
+static int devcgroup_online(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
+	int ret = 0;
+
+	mutex_lock(&devcgroup_mutex);
+
+	if (parent_dev_cgroup == NULL)
+		dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW;
+	else {
+		ret = dev_exceptions_copy(&dev_cgroup->exceptions,
+					  &parent_dev_cgroup->exceptions);
+		if (!ret)
+			dev_cgroup->behavior = parent_dev_cgroup->behavior;
+	}
+	mutex_unlock(&devcgroup_mutex);
+
+	return ret;
+}
+
+static void devcgroup_offline(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+
+	mutex_lock(&devcgroup_mutex);
+	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
+	mutex_unlock(&devcgroup_mutex);
+}
+
+/*
+ * called from kernel/cgroup/cgroup.c with cgroup_lock() held.
+ */
+static struct cgroup_subsys_state *
+devcgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct dev_cgroup *dev_cgroup;
+
+	dev_cgroup = kzalloc_obj(*dev_cgroup);
+	if (!dev_cgroup)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&dev_cgroup->exceptions);
+	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
+
+	return &dev_cgroup->css;
+}
+
+static void devcgroup_css_free(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+
+	__dev_exception_clean(dev_cgroup);
+	kfree(dev_cgroup);
+}
+
+#define DEVCG_ALLOW 1
+#define DEVCG_DENY 2
+#define DEVCG_LIST 3
+
+static void seq_putaccess(struct seq_file *m, short access)
+{
+	if (access & DEVCG_ACC_READ)
+		seq_putc(m, 'r');
+	if (access & DEVCG_ACC_WRITE)
+		seq_putc(m, 'w');
+	if (access & DEVCG_ACC_MKNOD)
+		seq_putc(m, 'm');
+}
+
+static void seq_puttype(struct seq_file *m, short type)
+{
+	if (type == DEVCG_DEV_ALL)
+		seq_putc(m, 'a');
+	else if (type == DEVCG_DEV_CHAR)
+		seq_putc(m, 'c');
+	else if (type == DEVCG_DEV_BLOCK)
+		seq_putc(m, 'b');
+	else
+		seq_putc(m, 'X');
+}
+
+static void seq_putversion(struct seq_file *m, unsigned int version)
+{
+	if (version == ~0)
+		seq_putc(m, '*');
+	else
+		seq_printf(m, "%u", version);
+}
+
+static int devcgroup_seq_show(struct seq_file *m, void *v)
+{
+	struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m));
+	struct dev_exception_item *ex;
+
+	rcu_read_lock();
+	/*
+	 * To preserve the compatibility:
+	 * - Only show the "all devices" when the default policy is to allow
+	 * - List the exceptions in case the default policy is to deny
+	 * This way, the file remains as a "whitelist of devices"
+	 */
+	if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+		seq_puts(m, "a *:* rwm\n");
+	} else {
+		list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
+			seq_puttype(m, ex->type);
+			seq_putc(m, ' ');
+			seq_putversion(m, ex->major);
+			seq_putc(m, ':');
+			seq_putversion(m, ex->minor);
+			seq_putc(m, ' ');
+			seq_putaccess(m, ex->access);
+			seq_putc(m, '\n');
+		}
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+/**
+ * match_exception	- iterates the exception list trying to find a complete match
+ * @exceptions: list of exceptions
+ * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
+ *
+ * It is considered a complete match if an exception is found that will
+ * contain the entire range of provided parameters.
+ *
+ * Return: true in case it matches an exception completely
+ */
+static bool match_exception(struct list_head *exceptions, short type,
+			    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
+
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
+			continue;
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
+			continue;
+		if (ex->major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && ex->minor != minor)
+			continue;
+		/* provided access cannot have more than the exception rule */
+		if (access & (~ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * match_exception_partial - iterates the exception list trying to find a partial match
+ * @exceptions: list of exceptions
+ * @type: device type (DEVCG_DEV_BLOCK or DEVCG_DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (DEVCG_ACC_READ, DEVCG_ACC_WRITE, DEVCG_ACC_MKNOD)
+ *
+ * It is considered a partial match if an exception's range is found to
+ * contain *any* of the devices specified by provided parameters. This is
+ * used to make sure no extra access is being granted that is forbidden by
+ * any of the exception list.
+ *
+ * Return: true in case the provided range mat matches an exception completely
+ */
+static bool match_exception_partial(struct list_head *exceptions, short type,
+				    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
+
+	list_for_each_entry_rcu(ex, exceptions, list,
+				lockdep_is_held(&devcgroup_mutex)) {
+		if ((type & DEVCG_DEV_BLOCK) && !(ex->type & DEVCG_DEV_BLOCK))
+			continue;
+		if ((type & DEVCG_DEV_CHAR) && !(ex->type & DEVCG_DEV_CHAR))
+			continue;
+		/*
+		 * We must be sure that both the exception and the provided
+		 * range aren't masking all devices
+		 */
+		if (ex->major != ~0 && major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
+			continue;
+		/*
+		 * In order to make sure the provided range isn't matching
+		 * an exception, all its access bits shouldn't match the
+		 * exception's access bits
+		 */
+		if (!(access & ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions
+ * @dev_cgroup: dev cgroup to be tested against
+ * @refex: new exception
+ * @behavior: behavior of the exception's dev_cgroup
+ *
+ * This is used to make sure a child cgroup won't have more privileges
+ * than its parent
+ */
+static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
+		          struct dev_exception_item *refex,
+		          enum devcg_behavior behavior)
+{
+	bool match = false;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
+			 !lockdep_is_held(&devcgroup_mutex),
+			 "device_cgroup:verify_new_ex called without proper synchronization");
+
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+		if (behavior == DEVCG_DEFAULT_ALLOW) {
+			/*
+			 * new exception in the child doesn't matter, only
+			 * adding extra restrictions
+			 */ 
+			return true;
+		} else {
+			/*
+			 * new exception in the child will add more devices
+			 * that can be accessed, so it can't match any of
+			 * parent's exceptions, even slightly
+			 */ 
+			match = match_exception_partial(&dev_cgroup->exceptions,
+							refex->type,
+							refex->major,
+							refex->minor,
+							refex->access);
+
+			if (match)
+				return false;
+			return true;
+		}
+	} else {
+		/*
+		 * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
+		 * the new exception will add access to more devices and must
+		 * be contained completely in an parent's exception to be
+		 * allowed
+		 */
+		match = match_exception(&dev_cgroup->exceptions, refex->type,
+					refex->major, refex->minor,
+					refex->access);
+
+		if (match)
+			/* parent has an exception that matches the proposed */
+			return true;
+		else
+			return false;
+	}
+	return false;
+}
+
+/*
+ * parent_has_perm:
+ * when adding a new allow rule to a device exception list, the rule
+ * must be allowed in the parent device
+ */
+static int parent_has_perm(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
+
+	if (!parent)
+		return 1;
+	return verify_new_ex(parent, ex, childcg->behavior);
+}
+
+/**
+ * parent_allows_removal - verify if it's ok to remove an exception
+ * @childcg: child cgroup from where the exception will be removed
+ * @ex: exception being removed
+ *
+ * When removing an exception in cgroups with default ALLOW policy, it must
+ * be checked if removing it will give the child cgroup more access than the
+ * parent.
+ *
+ * Return: true if it's ok to remove exception, false otherwise
+ */
+static bool parent_allows_removal(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
+
+	if (!parent)
+		return true;
+
+	/* It's always allowed to remove access to devices */
+	if (childcg->behavior == DEVCG_DEFAULT_DENY)
+		return true;
+
+	/*
+	 * Make sure you're not removing part or a whole exception existing in
+	 * the parent cgroup
+	 */
+	return !match_exception_partial(&parent->exceptions, ex->type,
+					ex->major, ex->minor, ex->access);
+}
+
+/**
+ * may_allow_all - checks if it's possible to change the behavior to
+ *		   allow based on parent's rules.
+ * @parent: device cgroup's parent
+ * returns: != 0 in case it's allowed, 0 otherwise
+ */
+static inline int may_allow_all(struct dev_cgroup *parent)
+{
+	if (!parent)
+		return 1;
+	return parent->behavior == DEVCG_DEFAULT_ALLOW;
+}
+
+/**
+ * revalidate_active_exceptions - walks through the active exception list and
+ * 				  revalidates the exceptions based on parent's
+ * 				  behavior and exceptions. The exceptions that
+ * 				  are no longer valid will be removed.
+ * 				  Called with devcgroup_mutex held.
+ * @devcg: cgroup which exceptions will be checked
+ *
+ * This is one of the three key functions for hierarchy implementation.
+ * This function is responsible for re-evaluating all the cgroup's active
+ * exceptions due to a parent's exception change.
+ * Refer to Documentation/admin-guide/cgroup-v1/devices.rst for more details.
+ */
+static void revalidate_active_exceptions(struct dev_cgroup *devcg)
+{
+	struct dev_exception_item *ex;
+	struct list_head *this, *tmp;
+
+	list_for_each_safe(this, tmp, &devcg->exceptions) {
+		ex = container_of(this, struct dev_exception_item, list);
+		if (!parent_has_perm(devcg, ex))
+			dev_exception_rm(devcg, ex);
+	}
+}
+
+/**
+ * propagate_exception - propagates a new exception to the children
+ * @devcg_root: device cgroup that added a new exception
+ * @ex: new exception to be propagated
+ *
+ * returns: 0 in case of success, != 0 in case of error
+ */
+static int propagate_exception(struct dev_cgroup *devcg_root,
+			       struct dev_exception_item *ex)
+{
+	struct cgroup_subsys_state *pos;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	css_for_each_descendant_pre(pos, &devcg_root->css) {
+		struct dev_cgroup *devcg = css_to_devcgroup(pos);
+
+		/*
+		 * Because devcgroup_mutex is held, no devcg will become
+		 * online or offline during the tree walk (see on/offline
+		 * methods), and online ones are safe to access outside RCU
+		 * read lock without bumping refcnt.
+		 */
+		if (pos == &devcg_root->css || !is_devcg_online(devcg))
+			continue;
+
+		rcu_read_unlock();
+
+		/*
+		 * in case both root's behavior and devcg is allow, a new
+		 * restriction means adding to the exception list
+		 */
+		if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW &&
+		    devcg->behavior == DEVCG_DEFAULT_ALLOW) {
+			rc = dev_exception_add(devcg, ex);
+			if (rc)
+				return rc;
+		} else {
+			/*
+			 * in the other possible cases:
+			 * root's behavior: allow, devcg's: deny
+			 * root's behavior: deny, devcg's: deny
+			 * the exception will be removed
+			 */
+			dev_exception_rm(devcg, ex);
+		}
+		revalidate_active_exceptions(devcg);
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+	return rc;
+}
+
+/*
+ * Modify the exception list using allow/deny rules.
+ * CAP_SYS_ADMIN is needed for this.  It's at least separate from CAP_MKNOD
+ * so we can give a container CAP_MKNOD to let it create devices but not
+ * modify the exception list.
+ * It seems likely we'll want to add a CAP_CONTAINER capability to allow
+ * us to also grant CAP_SYS_ADMIN to containers without giving away the
+ * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN
+ *
+ * Taking rules away is always allowed (given CAP_SYS_ADMIN).  Granting
+ * new access is only allowed if you're in the top-level cgroup, or your
+ * parent cgroup has the access you're asking for.
+ */
+static int devcgroup_update_access(struct dev_cgroup *devcgroup,
+				   int filetype, char *buffer)
+{
+	const char *b;
+	char temp[12];		/* 11 + 1 characters needed for a u32 */
+	int count, rc = 0;
+	struct dev_exception_item ex;
+	struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
+	struct dev_cgroup tmp_devcgrp;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	memset(&ex, 0, sizeof(ex));
+	memset(&tmp_devcgrp, 0, sizeof(tmp_devcgrp));
+	b = buffer;
+
+	switch (*b) {
+	case 'a':
+		switch (filetype) {
+		case DEVCG_ALLOW:
+			if (css_has_online_children(&devcgroup->css))
+				return -EINVAL;
+
+			if (!may_allow_all(parent))
+				return -EPERM;
+			if (!parent) {
+				devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
+				dev_exception_clean(devcgroup);
+				break;
+			}
+
+			INIT_LIST_HEAD(&tmp_devcgrp.exceptions);
+			rc = dev_exceptions_copy(&tmp_devcgrp.exceptions,
+						 &devcgroup->exceptions);
+			if (rc)
+				return rc;
+			dev_exception_clean(devcgroup);
+			rc = dev_exceptions_copy(&devcgroup->exceptions,
+						 &parent->exceptions);
+			if (rc) {
+				dev_exceptions_move(&devcgroup->exceptions,
+						    &tmp_devcgrp.exceptions);
+				return rc;
+			}
+			devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
+			dev_exception_clean(&tmp_devcgrp);
+			break;
+		case DEVCG_DENY:
+			if (css_has_online_children(&devcgroup->css))
+				return -EINVAL;
+
+			dev_exception_clean(devcgroup);
+			devcgroup->behavior = DEVCG_DEFAULT_DENY;
+			break;
+		default:
+			return -EINVAL;
+		}
+		return 0;
+	case 'b':
+		ex.type = DEVCG_DEV_BLOCK;
+		break;
+	case 'c':
+		ex.type = DEVCG_DEV_CHAR;
+		break;
+	default:
+		return -EINVAL;
+	}
+	b++;
+	if (!isspace(*b))
+		return -EINVAL;
+	b++;
+	if (*b == '*') {
+		ex.major = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		memset(temp, 0, sizeof(temp));
+		for (count = 0; count < sizeof(temp) - 1; count++) {
+			temp[count] = *b;
+			b++;
+			if (!isdigit(*b))
+				break;
+		}
+		rc = kstrtou32(temp, 10, &ex.major);
+		if (rc)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+	if (*b != ':')
+		return -EINVAL;
+	b++;
+
+	/* read minor */
+	if (*b == '*') {
+		ex.minor = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		memset(temp, 0, sizeof(temp));
+		for (count = 0; count < sizeof(temp) - 1; count++) {
+			temp[count] = *b;
+			b++;
+			if (!isdigit(*b))
+				break;
+		}
+		rc = kstrtou32(temp, 10, &ex.minor);
+		if (rc)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+	if (!isspace(*b))
+		return -EINVAL;
+	for (b++, count = 0; count < 3; count++, b++) {
+		switch (*b) {
+		case 'r':
+			ex.access |= DEVCG_ACC_READ;
+			break;
+		case 'w':
+			ex.access |= DEVCG_ACC_WRITE;
+			break;
+		case 'm':
+			ex.access |= DEVCG_ACC_MKNOD;
+			break;
+		case '\n':
+		case '\0':
+			count = 3;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	switch (filetype) {
+	case DEVCG_ALLOW:
+		/*
+		 * If the default policy is to allow by default, try to remove
+		 * an matching exception instead. And be silent about it: we
+		 * don't want to break compatibility
+		 */
+		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+			/* Check if the parent allows removing it first */
+			if (!parent_allows_removal(devcgroup, &ex))
+				return -EPERM;
+			dev_exception_rm(devcgroup, &ex);
+			break;
+		}
+
+		if (!parent_has_perm(devcgroup, &ex))
+			return -EPERM;
+		rc = dev_exception_add(devcgroup, &ex);
+		break;
+	case DEVCG_DENY:
+		/*
+		 * If the default policy is to deny by default, try to remove
+		 * an matching exception instead. And be silent about it: we
+		 * don't want to break compatibility
+		 */
+		if (devcgroup->behavior == DEVCG_DEFAULT_DENY)
+			dev_exception_rm(devcgroup, &ex);
+		else
+			rc = dev_exception_add(devcgroup, &ex);
+
+		if (rc)
+			break;
+		/* we only propagate new restrictions */
+		rc = propagate_exception(devcgroup, &ex);
+		break;
+	default:
+		rc = -EINVAL;
+	}
+	return rc;
+}
+
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	int retval;
+
+	mutex_lock(&devcgroup_mutex);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
+	mutex_unlock(&devcgroup_mutex);
+	return retval ?: nbytes;
+}
+
+static struct cftype dev_cgroup_files[] = {
+	{
+		.name = "allow",
+		.write = devcgroup_access_write,
+		.private = DEVCG_ALLOW,
+	},
+	{
+		.name = "deny",
+		.write = devcgroup_access_write,
+		.private = DEVCG_DENY,
+	},
+	{
+		.name = "list",
+		.seq_show = devcgroup_seq_show,
+		.private = DEVCG_LIST,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys devices_cgrp_subsys = {
+	.css_alloc = devcgroup_css_alloc,
+	.css_free = devcgroup_css_free,
+	.css_online = devcgroup_online,
+	.css_offline = devcgroup_offline,
+	.legacy_cftypes = dev_cgroup_files,
+};
+
+/**
+ * devcgroup_legacy_check_permission - checks if an inode operation is permitted
+ * @type: device type
+ * @major: device major number
+ * @minor: device minor number
+ * @access: combination of DEVCG_ACC_WRITE, DEVCG_ACC_READ and DEVCG_ACC_MKNOD
+ *
+ * returns 0 on success, -EPERM case the operation is not permitted
+ */
+static int devcgroup_legacy_check_permission(short type, u32 major, u32 minor,
+					short access)
+{
+	struct dev_cgroup *dev_cgroup;
+	bool rc;
+
+	rcu_read_lock();
+	dev_cgroup = task_devcgroup(current);
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
+		/* Can't match any of the exceptions, even partially */
+		rc = !match_exception_partial(&dev_cgroup->exceptions,
+					      type, major, minor, access);
+	else
+		/* Need to match completely one exception to be allowed */
+		rc = match_exception(&dev_cgroup->exceptions, type, major,
+				     minor, access);
+	rcu_read_unlock();
+
+	if (!rc)
+		return -EPERM;
+
+	return 0;
+}
+
+#endif /* CONFIG_CGROUP_DEVICE */
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+
+int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
+{
+	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
+
+	if (rc)
+		return rc;
+
+	#ifdef CONFIG_CGROUP_DEVICE
+	return devcgroup_legacy_check_permission(type, major, minor, access);
+
+	#else /* CONFIG_CGROUP_DEVICE */
+	return 0;
+
+	#endif /* CONFIG_CGROUP_DEVICE */
+}
+EXPORT_SYMBOL(devcgroup_check_permission);
+#endif /* defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) */
diff --git a/security/inode.c b/security/inode.c
new file mode 100644
index 000000000..080402367
--- /dev/null
+++ b/security/inode.c
@@ -0,0 +1,380 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  inode.c - securityfs
+ *
+ *  Copyright (C) 2005 Greg Kroah-Hartman <gregkh@suse.de>
+ *
+ *  Based on fs/debugfs/inode.c which had the following copyright notice:
+ *    Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
+ *    Copyright (C) 2004 IBM Inc.
+ */
+
+/* #define DEBUG */
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include <linux/lsm_hooks.h>
+#include <linux/magic.h>
+
+#include "lsm.h"
+
+static struct vfsmount *mount;
+static int mount_count;
+
+static void securityfs_free_inode(struct inode *inode)
+{
+	if (S_ISLNK(inode->i_mode))
+		kfree_const(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static const struct super_operations securityfs_super_operations = {
+	.statfs		= simple_statfs,
+	.free_inode	= securityfs_free_inode,
+};
+
+static int securityfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	static const struct tree_descr files[] = {{""}};
+	int error;
+
+	error = simple_fill_super(sb, SECURITYFS_MAGIC, files);
+	if (error)
+		return error;
+
+	sb->s_op = &securityfs_super_operations;
+
+	return 0;
+}
+
+static int securityfs_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, securityfs_fill_super);
+}
+
+static const struct fs_context_operations securityfs_context_ops = {
+	.get_tree	= securityfs_get_tree,
+};
+
+static int securityfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &securityfs_context_ops;
+	return 0;
+}
+
+static struct file_system_type fs_type = {
+	.owner =	THIS_MODULE,
+	.name =		"securityfs",
+	.init_fs_context = securityfs_init_fs_context,
+	.kill_sb =	kill_anon_super,
+};
+
+/**
+ * securityfs_create_dentry - create a dentry in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the securityfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ *        on.  The inode.i_private pointer will point to this value on
+ *        the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ *        this file.
+ * @iops: a point to a struct of inode_operations that should be used for
+ *        this file/dir
+ *
+ * This is the basic "create a file/dir/symlink" function for
+ * securityfs.  It allows for a wide range of flexibility in creating
+ * a file, or a directory (if you want to create a directory, the
+ * securityfs_create_dir() function is recommended to be used
+ * instead).
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the
+ * file is to be removed (no automatic cleanup happens if your module
+ * is unloaded, you are responsible here).  If an error occurs, the
+ * function will return the error value (via ERR_PTR).
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.
+ */
+static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const struct file_operations *fops,
+					const struct inode_operations *iops)
+{
+	struct dentry *dentry;
+	struct inode *dir, *inode;
+	int error;
+	bool pinned = false;
+
+	if (!(mode & S_IFMT))
+		mode = (mode & S_IALLUGO) | S_IFREG;
+
+	pr_debug("securityfs: creating file '%s'\n",name);
+
+	if (!parent) {
+		error = simple_pin_fs(&fs_type, &mount, &mount_count);
+		if (error)
+			return ERR_PTR(error);
+		pinned = true;
+		parent = mount->mnt_root;
+	}
+
+	inode = new_inode(parent->d_sb);
+	if (unlikely(!inode)) {
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	dir = d_inode(parent);
+
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry)) {
+		iput(inode);
+		goto out;
+	}
+	inode->i_ino = get_next_ino();
+	inode->i_mode = mode;
+	simple_inode_init_ts(inode);
+	inode->i_private = data;
+	if (S_ISDIR(mode)) {
+		inode->i_op = &simple_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		inc_nlink(inode);
+		inc_nlink(dir);
+	} else if (S_ISLNK(mode)) {
+		inode->i_op = iops ? iops : &simple_symlink_inode_operations;
+		inode->i_link = data;
+	} else {
+		inode->i_fop = fops;
+	}
+	d_make_persistent(dentry, inode);
+	simple_done_creating(dentry);
+	return dentry; // borrowed
+
+out:
+	if (pinned)
+		simple_release_fs(&mount, &mount_count);
+	return dentry;
+}
+
+/**
+ * securityfs_create_file - create a file in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the securityfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ *        on.  The inode.i_private pointer will point to this value on
+ *        the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ *        this file.
+ *
+ * This function creates a file in securityfs with the given @name.
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here).  If an error occurs, the function will return
+ * the error value (via ERR_PTR).
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.
+ */
+struct dentry *securityfs_create_file(const char *name, umode_t mode,
+				      struct dentry *parent, void *data,
+				      const struct file_operations *fops)
+{
+	return securityfs_create_dentry(name, mode, parent, data, fops, NULL);
+}
+EXPORT_SYMBOL_GPL(securityfs_create_file);
+
+/**
+ * securityfs_create_dir - create a directory in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the directory to
+ *        create.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          directory will be created in the root of the securityfs filesystem.
+ *
+ * This function creates a directory in securityfs with the given @name.
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here).  If an error occurs, the function will return
+ * the error value (via ERR_PTR).
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.
+ */
+struct dentry *securityfs_create_dir(const char *name, struct dentry *parent)
+{
+	return securityfs_create_file(name, S_IFDIR | 0755, parent, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(securityfs_create_dir);
+
+/**
+ * securityfs_create_symlink - create a symlink in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the symlink to
+ *        create.
+ * @parent: a pointer to the parent dentry for the symlink.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          directory will be created in the root of the securityfs filesystem.
+ * @target: a pointer to a string containing the name of the symlink's target.
+ *          If this parameter is %NULL, then the @iops parameter needs to be
+ *          setup to handle .readlink and .get_link inode_operations.
+ * @iops: a pointer to the struct inode_operations to use for the symlink. If
+ *        this parameter is %NULL, then the default simple_symlink_inode
+ *        operations will be used.
+ *
+ * This function creates a symlink in securityfs with the given @name.
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here).  If an error occurs, the function will return
+ * the error value (via ERR_PTR).
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.
+ */
+struct dentry *securityfs_create_symlink(const char *name,
+					 struct dentry *parent,
+					 const char *target,
+					 const struct inode_operations *iops)
+{
+	struct dentry *dent;
+	const char *link = NULL;
+
+	if (target) {
+		link = kstrdup_const(target, GFP_KERNEL);
+		if (!link)
+			return ERR_PTR(-ENOMEM);
+	}
+	dent = securityfs_create_dentry(name, S_IFLNK | 0444, parent,
+					(void *)link, NULL, iops);
+	if (IS_ERR(dent))
+		kfree_const(link);
+
+	return dent;
+}
+EXPORT_SYMBOL_GPL(securityfs_create_symlink);
+
+static void remove_one(struct dentry *victim)
+{
+	if (victim->d_parent == victim->d_sb->s_root)
+		simple_release_fs(&mount, &mount_count);
+}
+
+/**
+ * securityfs_remove - removes a file or directory from the securityfs filesystem
+ *
+ * @dentry: a pointer to a the dentry of the file or directory to be removed.
+ *
+ * This function removes a file or directory in securityfs that was previously
+ * created with a call to another securityfs function (like
+ * securityfs_create_file() or variants thereof.)
+ *
+ * This function is required to be called in order for the file to be
+ * removed. No automatic cleanup of files will happen when a module is
+ * removed; you are responsible here.
+ *
+ * AV: when applied to directory it will take all children out; no need to call
+ * it for descendents if ancestor is getting killed.
+ */
+void securityfs_remove(struct dentry *dentry)
+{
+	if (IS_ERR_OR_NULL(dentry))
+		return;
+
+	simple_pin_fs(&fs_type, &mount, &mount_count);
+	simple_recursive_removal(dentry, remove_one);
+	simple_release_fs(&mount, &mount_count);
+}
+EXPORT_SYMBOL_GPL(securityfs_remove);
+
+#ifdef CONFIG_SECURITY
+#include <linux/spinlock.h>
+
+static struct dentry *lsm_dentry;
+
+static ssize_t lsm_read(struct file *filp, char __user *buf, size_t count,
+			loff_t *ppos)
+{
+	int i;
+	static char *str;
+	static size_t len;
+	static DEFINE_SPINLOCK(lock);
+
+	/* NOTE: we never free or modify the string once it is set */
+
+	if (unlikely(!str || !len)) {
+		char *str_tmp;
+		size_t len_tmp = 0;
+
+		for (i = 0; i < lsm_active_cnt; i++)
+			/* the '+ 1' accounts for either a comma or a NUL */
+			len_tmp += strlen(lsm_idlist[i]->name) + 1;
+
+		str_tmp = kmalloc(len_tmp, GFP_KERNEL);
+		if (!str_tmp)
+			return -ENOMEM;
+		str_tmp[0] = '\0';
+
+		for (i = 0; i < lsm_active_cnt; i++) {
+			if (i > 0)
+				strcat(str_tmp, ",");
+			strcat(str_tmp, lsm_idlist[i]->name);
+		}
+
+		spin_lock(&lock);
+		if (!str) {
+			str = str_tmp;
+			len = len_tmp - 1;
+		} else
+			kfree(str_tmp);
+		spin_unlock(&lock);
+	}
+
+	return simple_read_from_buffer(buf, count, ppos, str, len);
+}
+
+static const struct file_operations lsm_ops = {
+	.read = lsm_read,
+	.llseek = generic_file_llseek,
+};
+#endif
+
+int __init securityfs_init(void)
+{
+	int retval;
+
+	retval = sysfs_create_mount_point(kernel_kobj, "security");
+	if (retval)
+		return retval;
+
+	retval = register_filesystem(&fs_type);
+	if (retval) {
+		sysfs_remove_mount_point(kernel_kobj, "security");
+		return retval;
+	}
+#ifdef CONFIG_SECURITY
+	lsm_dentry = securityfs_create_file("lsm", 0444, NULL, NULL,
+						&lsm_ops);
+#endif
+	return 0;
+}
diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig
new file mode 100644
index 000000000..916d4f2bf
--- /dev/null
+++ b/security/integrity/Kconfig
@@ -0,0 +1,137 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config INTEGRITY
+	bool "Integrity subsystem"
+	depends on SECURITY
+	default y
+	help
+	  This option enables the integrity subsystem, which is comprised
+	  of a number of different components including the Integrity
+	  Measurement Architecture (IMA), Extended Verification Module
+	  (EVM), IMA-appraisal extension, digital signature verification
+	  extension and audit measurement log support.
+
+	  Each of these components can be enabled/disabled separately.
+	  Refer to the individual components for additional details.
+
+if INTEGRITY
+
+config INTEGRITY_SIGNATURE
+	bool "Digital signature verification using multiple keyrings"
+	default n
+	select KEYS
+	select SIGNATURE
+	help
+	  This option enables digital signature verification support
+	  using multiple keyrings. It defines separate keyrings for each
+	  of the different use cases - evm, ima, and modules.
+	  Different keyrings improves search performance, but also allow
+	  to "lock" certain keyring to prevent adding new keys.
+	  This is useful for evm and module keyrings, when keys are
+	  usually only added from initramfs.
+
+config INTEGRITY_ASYMMETRIC_KEYS
+	bool "Enable asymmetric keys support"
+	depends on INTEGRITY_SIGNATURE
+	default n
+	select ASYMMETRIC_KEY_TYPE
+	select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+	select CRYPTO
+	select CRYPTO_RSA
+	select X509_CERTIFICATE_PARSER
+	help
+	  This option enables digital signature verification using
+	  asymmetric keys.
+
+config INTEGRITY_TRUSTED_KEYRING
+	bool "Require all keys on the integrity keyrings be signed"
+	depends on SYSTEM_TRUSTED_KEYRING
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	default y
+	help
+	   This option requires that all keys added to the .ima and
+	   .evm keyrings be signed by a key on the system trusted
+	   keyring.
+
+config INTEGRITY_PLATFORM_KEYRING
+	bool "Provide keyring for platform/firmware trusted keys"
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	depends on SYSTEM_BLACKLIST_KEYRING
+	help
+	  Provide a separate, distinct keyring for platform trusted keys, which
+	  the kernel automatically populates during initialization from values
+	  provided by the platform for verifying the kexec'ed kerned image
+	  and, possibly, the initramfs signature.
+
+config INTEGRITY_MACHINE_KEYRING
+	bool "Provide a keyring to which Machine Owner Keys may be added"
+	depends on SECONDARY_TRUSTED_KEYRING
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	depends on SYSTEM_BLACKLIST_KEYRING
+	depends on LOAD_UEFI_KEYS || LOAD_PPC_KEYS
+	help
+	  If set, provide a keyring to which Machine Owner Keys (MOK) may
+	  be added. This keyring shall contain just MOK keys.  Unlike keys
+	  in the platform keyring, keys contained in the .machine keyring will
+	  be trusted within the kernel.
+
+config INTEGRITY_CA_MACHINE_KEYRING
+	bool "Enforce Machine Keyring CA Restrictions"
+	depends on INTEGRITY_MACHINE_KEYRING
+	default n
+	help
+	  The .machine keyring can be configured to enforce CA restriction
+	  on any key added to it.  By default no restrictions are in place
+	  and all Machine Owner Keys (MOK) are added to the machine keyring.
+	  If enabled only CA keys are added to the machine keyring, all
+	  other MOK keys load into the platform keyring.
+
+config INTEGRITY_CA_MACHINE_KEYRING_MAX
+	bool "Only CA keys without DigitialSignature usage set"
+	depends on INTEGRITY_CA_MACHINE_KEYRING
+	default n
+	help
+	  When selected, only load CA keys are loaded into the machine
+	  keyring that contain the CA bit set along with the keyCertSign
+	  Usage field.  Keys containing the digitialSignature Usage field
+	  will not be loaded. The remaining MOK keys are loaded into the
+	  .platform keyring.
+
+config LOAD_UEFI_KEYS
+	depends on INTEGRITY_PLATFORM_KEYRING
+	depends on EFI
+	def_bool y
+
+config LOAD_IPL_KEYS
+	depends on INTEGRITY_PLATFORM_KEYRING
+	depends on S390
+	def_bool y
+
+config LOAD_PPC_KEYS
+	bool "Enable loading of platform and blacklisted keys for POWER"
+	depends on INTEGRITY_PLATFORM_KEYRING
+	depends on PPC_SECURE_BOOT
+	default y
+	help
+	  Enable loading of keys to the .platform keyring and blacklisted
+	  hashes to the .blacklist keyring for powerpc based platforms.
+
+config INTEGRITY_AUDIT
+	bool "Enables integrity auditing support "
+	depends on AUDIT
+	default y
+	help
+	  In addition to enabling integrity auditing support, this
+	  option adds a kernel parameter 'integrity_audit', which
+	  controls the level of integrity auditing messages.
+	  0 - basic integrity auditing messages (default)
+	  1 - additional integrity auditing messages
+
+	  Additional informational integrity auditing messages would
+	  be enabled by specifying 'integrity_audit=1' on the kernel
+	  command line.
+
+source "security/integrity/ima/Kconfig"
+source "security/integrity/evm/Kconfig"
+
+endif   # if INTEGRITY
diff --git a/security/integrity/Makefile b/security/integrity/Makefile
new file mode 100644
index 000000000..45dfdedbd
--- /dev/null
+++ b/security/integrity/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for caching inode integrity data (iint)
+#
+
+obj-$(CONFIG_INTEGRITY) += integrity.o
+
+integrity-y := iint.o
+integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
+integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
+integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
+integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o
+integrity-$(CONFIG_INTEGRITY_MACHINE_KEYRING) += platform_certs/machine_keyring.o
+integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \
+				      platform_certs/load_uefi.o \
+				      platform_certs/keyring_handler.o
+integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o
+integrity-$(CONFIG_LOAD_PPC_KEYS) += platform_certs/efi_parser.o \
+                                     platform_certs/load_powerpc.o \
+                                     platform_certs/keyring_handler.o
+integrity-$(CONFIG_EFI) += efi_secureboot.o
+# The relative order of the 'ima' and 'evm' LSMs depends on the order below.
+obj-$(CONFIG_IMA)			+= ima/
+obj-$(CONFIG_EVM)			+= evm/
diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c
new file mode 100644
index 000000000..1ed686154
--- /dev/null
+++ b/security/integrity/digsig.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011 Intel Corporation
+ *
+ * Author:
+ * Dmitry Kasatkin <dmitry.kasatkin@intel.com>
+ */
+
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/kernel_read_file.h>
+#include <linux/key-type.h>
+#include <linux/digsig.h>
+#include <linux/vmalloc.h>
+#include <crypto/public_key.h>
+#include <keys/system_keyring.h>
+
+#include "integrity.h"
+
+static struct key *keyring[INTEGRITY_KEYRING_MAX];
+
+static const char * const keyring_name[INTEGRITY_KEYRING_MAX] = {
+#ifndef CONFIG_INTEGRITY_TRUSTED_KEYRING
+	"_evm",
+	"_ima",
+#else
+	".evm",
+	".ima",
+#endif
+	".platform",
+	".machine",
+};
+
+#ifdef CONFIG_IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY
+#define restrict_link_to_ima restrict_link_by_digsig_builtin_and_secondary
+#else
+#define restrict_link_to_ima restrict_link_by_digsig_builtin
+#endif
+
+static struct key *integrity_keyring_from_id(const unsigned int id)
+{
+	if (id >= INTEGRITY_KEYRING_MAX)
+		return ERR_PTR(-EINVAL);
+
+	if (!keyring[id]) {
+		keyring[id] =
+			request_key(&key_type_keyring, keyring_name[id], NULL);
+		if (IS_ERR(keyring[id])) {
+			int err = PTR_ERR(keyring[id]);
+			pr_err("no %s keyring: %d\n", keyring_name[id], err);
+			keyring[id] = NULL;
+			return ERR_PTR(err);
+		}
+	}
+
+	return keyring[id];
+}
+
+int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
+			    const char *digest, int digestlen, u8 algo)
+{
+	struct key *keyring;
+
+	if (siglen < 2)
+		return -EINVAL;
+
+	keyring = integrity_keyring_from_id(id);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	switch (sig[1]) {
+	case 1:
+		/* v1 API expect signature without xattr type */
+		return digsig_verify(keyring, sig + 1, siglen - 1, digest,
+				     digestlen);
+	case 2: /* regular file data hash based signature */
+		return asymmetric_verify(keyring, sig, siglen, digest,
+					    digestlen);
+	case 3: /* struct ima_file_id data based signature */
+		return asymmetric_verify_v3(keyring, sig, siglen, digest,
+					    digestlen, algo);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+int integrity_modsig_verify(const unsigned int id, const struct modsig *modsig)
+{
+	struct key *keyring;
+
+	keyring = integrity_keyring_from_id(id);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	return ima_modsig_verify(keyring, modsig);
+}
+
+static int __init __integrity_init_keyring(const unsigned int id,
+					   key_perm_t perm,
+					   struct key_restriction *restriction)
+{
+	const struct cred *cred = current_cred();
+	int err = 0;
+
+	keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0),
+				    KGIDT_INIT(0), cred, perm,
+				    KEY_ALLOC_NOT_IN_QUOTA, restriction, NULL);
+	if (IS_ERR(keyring[id])) {
+		err = PTR_ERR(keyring[id]);
+		pr_info("Can't allocate %s keyring (%d)\n",
+			keyring_name[id], err);
+		keyring[id] = NULL;
+	} else {
+		if (id == INTEGRITY_KEYRING_PLATFORM)
+			set_platform_trusted_keys(keyring[id]);
+		if (id == INTEGRITY_KEYRING_MACHINE && imputed_trust_enabled())
+			set_machine_trusted_keys(keyring[id]);
+		if (id == INTEGRITY_KEYRING_IMA)
+			load_module_cert(keyring[id]);
+	}
+
+	return err;
+}
+
+int __init integrity_init_keyring(const unsigned int id)
+{
+	struct key_restriction *restriction;
+	key_perm_t perm;
+	int ret;
+
+	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW
+		| KEY_USR_READ | KEY_USR_SEARCH;
+
+	if (id == INTEGRITY_KEYRING_PLATFORM ||
+	    (id == INTEGRITY_KEYRING_MACHINE &&
+	    !IS_ENABLED(CONFIG_INTEGRITY_CA_MACHINE_KEYRING))) {
+		restriction = NULL;
+		goto out;
+	}
+
+	if (!IS_ENABLED(CONFIG_INTEGRITY_TRUSTED_KEYRING))
+		return 0;
+
+	restriction = kzalloc_obj(struct key_restriction);
+	if (!restriction)
+		return -ENOMEM;
+
+	if (id == INTEGRITY_KEYRING_MACHINE)
+		restriction->check = restrict_link_by_ca;
+	else
+		restriction->check = restrict_link_to_ima;
+
+	/*
+	 * MOK keys can only be added through a read-only runtime services
+	 * UEFI variable during boot. No additional keys shall be allowed to
+	 * load into the machine keyring following init from userspace.
+	 */
+	if (id != INTEGRITY_KEYRING_MACHINE)
+		perm |= KEY_USR_WRITE;
+
+out:
+	ret = __integrity_init_keyring(id, perm, restriction);
+	if (ret)
+		kfree(restriction);
+	return ret;
+}
+
+static int __init integrity_add_key(const unsigned int id, const void *data,
+				    off_t size, key_perm_t perm)
+{
+	key_ref_t key;
+	int rc = 0;
+
+	if (!keyring[id])
+		return -EINVAL;
+
+	key = key_create_or_update(make_key_ref(keyring[id], 1), "asymmetric",
+				   NULL, data, size, perm,
+				   KEY_ALLOC_NOT_IN_QUOTA);
+	if (IS_ERR(key)) {
+		rc = PTR_ERR(key);
+		if (id != INTEGRITY_KEYRING_MACHINE)
+			pr_err("Problem loading X.509 certificate %d\n", rc);
+	} else {
+		pr_notice("Loaded X.509 cert '%s'\n",
+			  key_ref_to_ptr(key)->description);
+		key_ref_put(key);
+	}
+
+	return rc;
+
+}
+
+int __init integrity_load_x509(const unsigned int id, const char *path)
+{
+	void *data = NULL;
+	size_t size;
+	int rc;
+	key_perm_t perm;
+
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
+					READING_X509_CERTIFICATE);
+	if (rc < 0) {
+		pr_err("Unable to open file: %s (%d)", path, rc);
+		return rc;
+	}
+	size = rc;
+
+	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ;
+
+	pr_info("Loading X.509 certificate: %s\n", path);
+	rc = integrity_add_key(id, (const void *)data, size, perm);
+
+	vfree(data);
+	return rc;
+}
+
+int __init integrity_load_cert(const unsigned int id, const char *source,
+			       const void *data, size_t len, key_perm_t perm)
+{
+	if (!data)
+		return -EINVAL;
+
+	pr_info("Loading X.509 certificate: %s\n", source);
+	return integrity_add_key(id, data, len, perm);
+}
diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c
new file mode 100644
index 000000000..b4c23a0ed
--- /dev/null
+++ b/security/integrity/digsig_asymmetric.c
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Intel Corporation
+ *
+ * Author:
+ * Dmitry Kasatkin <dmitry.kasatkin@intel.com>
+ */
+
+#include <linux/err.h>
+#include <linux/ratelimit.h>
+#include <linux/key-type.h>
+#include <crypto/public_key.h>
+#include <crypto/hash_info.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+
+#include "integrity.h"
+
+/*
+ * Request an asymmetric key.
+ */
+static struct key *request_asymmetric_key(struct key *keyring, uint32_t keyid)
+{
+	struct key *key;
+	char name[12];
+
+	sprintf(name, "id:%08x", keyid);
+
+	pr_debug("key search: \"%s\"\n", name);
+
+	key = get_ima_blacklist_keyring();
+	if (key) {
+		key_ref_t kref;
+
+		kref = keyring_search(make_key_ref(key, 1),
+				      &key_type_asymmetric, name, true);
+		if (!IS_ERR(kref)) {
+			pr_err("Key '%s' is in ima_blacklist_keyring\n", name);
+			return ERR_PTR(-EKEYREJECTED);
+		}
+	}
+
+	if (keyring) {
+		/* search in specific keyring */
+		key_ref_t kref;
+
+		kref = keyring_search(make_key_ref(keyring, 1),
+				      &key_type_asymmetric, name, true);
+		if (IS_ERR(kref))
+			key = ERR_CAST(kref);
+		else
+			key = key_ref_to_ptr(kref);
+	} else {
+		key = request_key(&key_type_asymmetric, name, NULL);
+	}
+
+	if (IS_ERR(key)) {
+		if (keyring)
+			pr_err_ratelimited("Request for unknown key '%s' in '%s' keyring. err %ld\n",
+					   name, keyring->description,
+					   PTR_ERR(key));
+		else
+			pr_err_ratelimited("Request for unknown key '%s' err %ld\n",
+					   name, PTR_ERR(key));
+
+		switch (PTR_ERR(key)) {
+			/* Hide some search errors */
+		case -EACCES:
+		case -ENOTDIR:
+		case -EAGAIN:
+			return ERR_PTR(-ENOKEY);
+		default:
+			return key;
+		}
+	}
+
+	pr_debug("%s() = 0 [%x]\n", __func__, key_serial(key));
+
+	return key;
+}
+
+/**
+ * asymmetric_verify_common -- sigv2 and sigv3 common verify function
+ * @key: The key to use for signature verification; caller must free it
+ * @pk: The associated public key; must not be NULL
+ * @sig: The xattr signature
+ * @siglen: The length of the xattr signature; must be at least
+ *          sizeof(struct signature_v2_hdr)
+ * @data: The data to verify the signature on
+ * @datalen: Length of @data
+ */
+static int asymmetric_verify_common(const struct key *key,
+				    const struct public_key *pk,
+				    const char *sig, int siglen,
+				    const char *data, int datalen)
+{
+	struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+	struct public_key_signature pks;
+	int ret;
+
+	siglen -= sizeof(*hdr);
+
+	if (siglen != be16_to_cpu(hdr->sig_size))
+		return -EBADMSG;
+
+	if (hdr->hash_algo >= HASH_ALGO__LAST)
+		return -ENOPKG;
+
+	memset(&pks, 0, sizeof(pks));
+
+	pks.hash_algo = hash_algo_name[hdr->hash_algo];
+	pks.pkey_algo = pk->pkey_algo;
+	if (!strcmp(pk->pkey_algo, "rsa")) {
+		pks.encoding = "pkcs1";
+	} else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) {
+		/* edcsa-nist-p192 etc. */
+		pks.encoding = "x962";
+	} else if (!strcmp(pk->pkey_algo, "ecrdsa")) {
+		pks.encoding = "raw";
+	} else {
+		ret = -ENOPKG;
+		goto out;
+	}
+
+	pks.m = (u8 *)data;
+	pks.m_size = datalen;
+	pks.s = hdr->sig;
+	pks.s_size = siglen;
+	ret = verify_signature(key, &pks);
+out:
+	pr_debug("%s() = %d\n", __func__, ret);
+	return ret;
+}
+
+int asymmetric_verify(struct key *keyring, const char *sig,
+		      int siglen, const char *data, int datalen)
+{
+	struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+	const struct public_key *pk;
+	struct key *key;
+	int ret;
+
+	if (siglen <= sizeof(*hdr))
+		return -EBADMSG;
+
+	key = request_asymmetric_key(keyring, be32_to_cpu(hdr->keyid));
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+	pk = asymmetric_key_public_key(key);
+	if (!pk) {
+		ret = -ENOKEY;
+		goto out;
+	}
+
+	ret = asymmetric_verify_common(key, pk, sig, siglen, data, datalen);
+
+out:
+	key_put(key);
+
+	return ret;
+}
+
+/*
+ * calc_file_id_hash - calculate the hash of the ima_file_id struct data
+ * @type: xattr type [enum evm_ima_xattr_type]
+ * @algo: hash algorithm [enum hash_algo]; caller must ensure valid value
+ * @digest: pointer to the digest to be hashed
+ * @hash: (out) pointer to the hash
+ *
+ * IMA signature version 3 disambiguates the data that is signed by
+ * indirectly signing the hash of the ima_file_id structure data.
+ *
+ * Return 0 on success, error code otherwise.
+ */
+static int calc_file_id_hash(enum evm_ima_xattr_type type,
+			     enum hash_algo algo, const u8 *digest,
+			     struct ima_max_digest_data *hash)
+{
+	struct ima_file_id file_id = {.hash_type = type, .hash_algorithm = algo};
+	size_t digest_size = hash_digest_size[algo];
+	struct crypto_shash *tfm;
+	size_t file_id_size;
+	int rc;
+
+	if (type != IMA_VERITY_DIGSIG && type != EVM_IMA_XATTR_DIGSIG &&
+	    type != EVM_XATTR_PORTABLE_DIGSIG)
+		return -EINVAL;
+
+	tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	memcpy(file_id.hash, digest, digest_size);
+
+	/* Calculate the ima_file_id struct hash on the portion used. */
+	file_id_size = sizeof(file_id) - (HASH_MAX_DIGESTSIZE - digest_size);
+
+	hash->hdr.algo = algo;
+	hash->hdr.length = digest_size;
+	rc = crypto_shash_tfm_digest(tfm, (const u8 *)&file_id, file_id_size,
+				     hash->digest);
+
+	crypto_free_shash(tfm);
+	return rc;
+}
+
+/**
+ * asymmetric_verify_v3_hashless - Use hashless signature verification on sigv3
+ * @key: The key to use for signature verification; caller must free it
+ * @pk: The associated public key; must not be NULL
+ * @encoding: The encoding the key type uses
+ * @sig: The xattr signature
+ * @siglen: The length of the xattr signature; must be at least
+ *          sizeof(struct signature_v2_hdr)
+ * @algo: hash algorithm [enum hash_algo]; caller must ensure valid value
+ * @digest: The file digest
+ *
+ * Create an ima_file_id structure and use it for signature verification
+ * directly. This can be used for ML-DSA in pure mode for example.
+ */
+static int asymmetric_verify_v3_hashless(struct key *key,
+					 const struct public_key *pk,
+					 const char *encoding,
+					 const char *sig, int siglen,
+					 u8 algo,
+					 const u8 *digest)
+{
+	struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+	struct ima_file_id file_id = {
+		.hash_type = hdr->type,
+		.hash_algorithm = algo,
+	};
+	size_t digest_size = hash_digest_size[algo];
+	struct public_key_signature pks = {
+		.m = (u8 *)&file_id,
+		.m_size = sizeof(file_id) - (HASH_MAX_DIGESTSIZE - digest_size),
+		.s = hdr->sig,
+		.s_size = siglen - sizeof(*hdr),
+		.pkey_algo = pk->pkey_algo,
+		.hash_algo = "none",
+		.encoding = encoding,
+	};
+	int ret;
+
+	if (hdr->type != IMA_VERITY_DIGSIG &&
+	    hdr->type != EVM_IMA_XATTR_DIGSIG &&
+	    hdr->type != EVM_XATTR_PORTABLE_DIGSIG)
+		return -EINVAL;
+
+	if (pks.s_size != be16_to_cpu(hdr->sig_size))
+		return -EBADMSG;
+
+	memcpy(file_id.hash, digest, digest_size);
+
+	ret = verify_signature(key, &pks);
+	pr_debug("%s() = %d\n", __func__, ret);
+	return ret;
+}
+
+int asymmetric_verify_v3(struct key *keyring, const char *sig, int siglen,
+			 const char *data, int datalen, u8 algo)
+{
+	struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+	struct ima_max_digest_data hash;
+	const struct public_key *pk;
+	struct key *key;
+	int rc;
+
+	if (algo >= HASH_ALGO__LAST)
+		return -ENOPKG;
+
+	if (siglen <= sizeof(*hdr))
+		return -EBADMSG;
+
+	key = request_asymmetric_key(keyring, be32_to_cpu(hdr->keyid));
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+
+	pk = asymmetric_key_public_key(key);
+	if (!pk) {
+		rc = -ENOKEY;
+		goto out;
+	}
+	if (!strncmp(pk->pkey_algo, "mldsa", 5)) {
+		rc = asymmetric_verify_v3_hashless(key, pk, "raw",
+						   sig, siglen, algo, data);
+	} else {
+		rc = calc_file_id_hash(hdr->type, algo, data, &hash);
+		if (rc) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		rc = asymmetric_verify_common(key, pk, sig, siglen, hash.digest,
+					      hash.hdr.length);
+	}
+
+out:
+	key_put(key);
+
+	return rc;
+}
diff --git a/security/integrity/efi_secureboot.c b/security/integrity/efi_secureboot.c
new file mode 100644
index 000000000..bfd4260a8
--- /dev/null
+++ b/security/integrity/efi_secureboot.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-1.0+
+/*
+ * Copyright (C) 2018 IBM Corporation
+ */
+#include <linux/efi.h>
+#include <linux/secure_boot.h>
+#include <asm/efi.h>
+
+#ifndef arch_efi_boot_mode
+#define arch_efi_boot_mode efi_secureboot_mode_unset
+#endif
+
+static enum efi_secureboot_mode get_sb_mode(void)
+{
+	enum efi_secureboot_mode mode;
+
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) {
+		pr_info("integrity: secureboot mode unknown, no efi\n");
+		return efi_secureboot_mode_unknown;
+	}
+
+	mode = efi_get_secureboot_mode(efi.get_variable);
+	if (mode == efi_secureboot_mode_disabled)
+		pr_info("integrity: secureboot mode disabled\n");
+	else if (mode == efi_secureboot_mode_unknown)
+		pr_info("integrity: secureboot mode unknown\n");
+	else
+		pr_info("integrity: secureboot mode enabled\n");
+	return mode;
+}
+
+/*
+ * Query secure boot status
+ *
+ * Note don't call this function too early e.g. in __setup hook otherwise the
+ * kernel may hang when calling efi_get_secureboot_mode.
+ *
+ */
+bool arch_get_secureboot(void)
+{
+	static enum efi_secureboot_mode sb_mode;
+	static bool initialized;
+
+	if (!initialized && efi_enabled(EFI_BOOT)) {
+		sb_mode = arch_efi_boot_mode;
+
+		if (sb_mode == efi_secureboot_mode_unset)
+			sb_mode = get_sb_mode();
+		initialized = true;
+	}
+
+	if (sb_mode == efi_secureboot_mode_enabled)
+		return true;
+	else
+		return false;
+}
diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig
new file mode 100644
index 000000000..861b3baca
--- /dev/null
+++ b/security/integrity/evm/Kconfig
@@ -0,0 +1,76 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config EVM
+	bool "EVM support"
+	select KEYS
+	select ENCRYPTED_KEYS
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	select CRYPTO_HASH_INFO
+	select SECURITY_PATH
+	default n
+	help
+	  EVM protects a file's security extended attributes against
+	  integrity attacks.
+
+	  If you are unsure how to answer this question, answer N.
+
+config EVM_ATTR_FSUUID
+	bool "FSUUID (version 2)"
+	default y
+	depends on EVM
+	help
+	  Include filesystem UUID for HMAC calculation.
+
+	  Default value is 'selected', which is former version 2.
+	  if 'not selected', it is former version 1
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+
+config EVM_EXTRA_SMACK_XATTRS
+	bool "Additional SMACK xattrs"
+	depends on EVM && SECURITY_SMACK
+	default n
+	help
+	  Include additional SMACK xattrs for HMAC calculation.
+
+	  In addition to the original security xattrs (eg. security.selinux,
+	  security.SMACK64, security.capability, and security.ima) included
+	  in the HMAC calculation, enabling this option includes newly defined
+	  Smack xattrs: security.SMACK64EXEC, security.SMACK64TRANSMUTE and
+	  security.SMACK64MMAP.
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+
+config EVM_ADD_XATTRS
+	bool "Add additional EVM extended attributes at runtime"
+	depends on EVM
+	default n
+	help
+	  Allow userland to provide additional xattrs for HMAC calculation.
+
+	  When this option is enabled, root can add additional xattrs to the
+	  list used by EVM by writing them into
+	  /sys/kernel/security/integrity/evm/evm_xattrs.
+
+config EVM_LOAD_X509
+	bool "Load an X509 certificate onto the '.evm' trusted keyring"
+	depends on EVM && INTEGRITY_TRUSTED_KEYRING
+	default n
+	help
+	   Load an X509 certificate onto the '.evm' trusted keyring.
+
+	   This option enables X509 certificate loading from the kernel
+	   onto the '.evm' trusted keyring.  A public key can be used to
+	   verify EVM integrity starting from the 'init' process. The
+	   key must have digitalSignature usage set.
+
+config EVM_X509_PATH
+	string "EVM X509 certificate path"
+	depends on EVM_LOAD_X509
+	default "/etc/keys/x509_evm.der"
+	help
+	   This option defines X509 certificate path.
diff --git a/security/integrity/evm/Makefile b/security/integrity/evm/Makefile
new file mode 100644
index 000000000..a56f5613b
--- /dev/null
+++ b/security/integrity/evm/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for building the Extended Verification Module(EVM)
+#
+obj-$(CONFIG_EVM) += evm.o
+
+evm-y := evm_main.o evm_crypto.o evm_secfs.o
+evm-$(CONFIG_FS_POSIX_ACL) += evm_posix_acl.o
diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h
new file mode 100644
index 000000000..694552ace
--- /dev/null
+++ b/security/integrity/evm/evm.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * File: evm.h
+ */
+
+#ifndef __INTEGRITY_EVM_H
+#define __INTEGRITY_EVM_H
+
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "../integrity.h"
+
+#define EVM_INIT_HMAC	0x0001
+#define EVM_INIT_X509	0x0002
+#define EVM_ALLOW_METADATA_WRITES	0x0004
+#define EVM_SIGV3_REQUIRED		0x0008
+#define EVM_SETUP_COMPLETE 0x80000000 /* userland has signaled key load */
+
+#define EVM_KEY_MASK (EVM_INIT_HMAC | EVM_INIT_X509)
+#define EVM_INIT_MASK (EVM_INIT_HMAC | EVM_INIT_X509 | EVM_SETUP_COMPLETE | \
+		       EVM_ALLOW_METADATA_WRITES | EVM_SIGV3_REQUIRED)
+
+struct xattr_list {
+	struct list_head list;
+	char *name;
+	bool enabled;
+};
+
+#define EVM_NEW_FILE			0x00000001
+#define EVM_IMMUTABLE_DIGSIG		0x00000002
+
+/* EVM integrity metadata associated with an inode */
+struct evm_iint_cache {
+	unsigned long flags;
+	enum integrity_status evm_status:4;
+	struct integrity_inode_attributes metadata_inode;
+};
+
+extern struct lsm_blob_sizes evm_blob_sizes;
+
+static inline struct evm_iint_cache *evm_iint_inode(const struct inode *inode)
+{
+	if (unlikely(!inode->i_security))
+		return NULL;
+
+	return inode->i_security + evm_blob_sizes.lbs_inode;
+}
+
+extern int evm_initialized;
+
+#define EVM_ATTR_FSUUID		0x0001
+
+extern int evm_hmac_attrs;
+
+/* List of EVM protected security xattrs */
+extern struct list_head evm_config_xattrnames;
+
+struct evm_digest {
+	struct ima_digest_data_hdr hdr;
+	char digest[IMA_MAX_DIGEST_SIZE];
+} __packed;
+
+int evm_protected_xattr(const char *req_xattr_name);
+
+int evm_init_key(void);
+int evm_update_evmxattr(struct dentry *dentry,
+			const char *req_xattr_name,
+			const char *req_xattr_value,
+			size_t req_xattr_value_len);
+int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value,
+		  size_t req_xattr_value_len, struct evm_digest *data,
+		  struct evm_iint_cache *iint);
+int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value,
+		  size_t req_xattr_value_len, char type,
+		  struct evm_digest *data, struct evm_iint_cache *iint);
+int evm_init_hmac(struct inode *inode, const struct xattr *xattrs,
+		  char *hmac_val);
+int evm_init_secfs(void);
+
+#endif
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
new file mode 100644
index 000000000..1c41af2f9
--- /dev/null
+++ b/security/integrity/evm/evm_crypto.c
@@ -0,0 +1,459 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * File: evm_crypto.c
+ *	 Using root's kernel master key (kmk), calculate the HMAC
+ */
+
+#define pr_fmt(fmt) "EVM: "fmt
+
+#include <linux/export.h>
+#include <linux/hex.h>
+#include <linux/crypto.h>
+#include <linux/xattr.h>
+#include <linux/evm.h>
+#include <keys/encrypted-type.h>
+#include <crypto/hash.h>
+#include <crypto/hash_info.h>
+#include "evm.h"
+
+#define EVMKEY "evm-key"
+#define MAX_KEY_SIZE 128
+static unsigned char evmkey[MAX_KEY_SIZE];
+static const int evmkey_len = MAX_KEY_SIZE;
+
+static struct crypto_shash *hmac_tfm;
+static struct crypto_shash *evm_tfm[HASH_ALGO__LAST];
+
+static DEFINE_MUTEX(mutex);
+
+#define EVM_SET_KEY_BUSY 0
+
+static unsigned long evm_set_key_flags;
+
+static const char evm_hmac[] = "hmac(sha1)";
+
+/**
+ * evm_set_key() - set EVM HMAC key from the kernel
+ * @key: pointer to a buffer with the key data
+ * @keylen: length of the key data
+ *
+ * This function allows setting the EVM HMAC key from the kernel
+ * without using the "encrypted" key subsystem keys. It can be used
+ * by the crypto HW kernel module which has its own way of managing
+ * keys.
+ *
+ * key length should be between 32 and 128 bytes long
+ */
+int evm_set_key(void *key, size_t keylen)
+{
+	int rc;
+
+	rc = -EBUSY;
+	if (test_and_set_bit(EVM_SET_KEY_BUSY, &evm_set_key_flags))
+		goto busy;
+	rc = -EINVAL;
+	if (keylen > MAX_KEY_SIZE)
+		goto inval;
+	memcpy(evmkey, key, keylen);
+	evm_initialized |= EVM_INIT_HMAC;
+	pr_info("key initialized\n");
+	return 0;
+inval:
+	clear_bit(EVM_SET_KEY_BUSY, &evm_set_key_flags);
+busy:
+	pr_err("key initialization failed\n");
+	return rc;
+}
+EXPORT_SYMBOL_GPL(evm_set_key);
+
+static struct shash_desc *init_desc(char type, uint8_t hash_algo)
+{
+	long rc;
+	const char *algo;
+	struct crypto_shash **tfm, *tmp_tfm;
+	struct shash_desc *desc;
+
+	if (type == EVM_XATTR_HMAC) {
+		if (!(evm_initialized & EVM_INIT_HMAC)) {
+			pr_err_once("HMAC key is not set\n");
+			return ERR_PTR(-ENOKEY);
+		}
+		tfm = &hmac_tfm;
+		algo = evm_hmac;
+	} else {
+		if (hash_algo >= HASH_ALGO__LAST)
+			return ERR_PTR(-EINVAL);
+
+		tfm = &evm_tfm[hash_algo];
+		algo = hash_algo_name[hash_algo];
+	}
+
+	if (*tfm)
+		goto alloc;
+	mutex_lock(&mutex);
+	if (*tfm)
+		goto unlock;
+
+	tmp_tfm = crypto_alloc_shash(algo, 0, CRYPTO_NOLOAD);
+	if (IS_ERR(tmp_tfm)) {
+		pr_err("Can not allocate %s (reason: %ld)\n", algo,
+		       PTR_ERR(tmp_tfm));
+		mutex_unlock(&mutex);
+		return ERR_CAST(tmp_tfm);
+	}
+	if (type == EVM_XATTR_HMAC) {
+		rc = crypto_shash_setkey(tmp_tfm, evmkey, evmkey_len);
+		if (rc) {
+			crypto_free_shash(tmp_tfm);
+			mutex_unlock(&mutex);
+			return ERR_PTR(rc);
+		}
+	}
+	*tfm = tmp_tfm;
+unlock:
+	mutex_unlock(&mutex);
+alloc:
+	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm),
+			GFP_KERNEL);
+	if (!desc)
+		return ERR_PTR(-ENOMEM);
+
+	desc->tfm = *tfm;
+
+	rc = crypto_shash_init(desc);
+	if (rc) {
+		kfree(desc);
+		return ERR_PTR(rc);
+	}
+	return desc;
+}
+
+/* Protect against 'cutting & pasting' security.evm xattr, include inode
+ * specific info.
+ *
+ * (Additional directory/file metadata needs to be added for more complete
+ * protection.)
+ */
+static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
+			  char type, char *digest)
+{
+	struct h_misc {
+		/*
+		 * Although inode->i_ino is now u64, this field remains
+		 * unsigned long to allow existing HMAC and signatures from
+		 * 32-bit hosts to continue working when i_ino hasn't changed
+		 * and fits in a u32.
+		 */
+		unsigned long ino;
+		__u32 generation;
+		uid_t uid;
+		gid_t gid;
+		umode_t mode;
+	} hmac_misc;
+
+	memset(&hmac_misc, 0, sizeof(hmac_misc));
+	/* Don't include the inode or generation number in portable
+	 * signatures
+	 */
+	if (type != EVM_XATTR_PORTABLE_DIGSIG) {
+		hmac_misc.ino = inode->i_ino;
+		hmac_misc.generation = inode->i_generation;
+	}
+	/* The hmac uid and gid must be encoded in the initial user
+	 * namespace (not the filesystems user namespace) as encoding
+	 * them in the filesystems user namespace allows an attack
+	 * where first they are written in an unprivileged fuse mount
+	 * of a filesystem and then the system is tricked to mount the
+	 * filesystem for real on next boot and trust it because
+	 * everything is signed.
+	 */
+	hmac_misc.uid = from_kuid(&init_user_ns, inode->i_uid);
+	hmac_misc.gid = from_kgid(&init_user_ns, inode->i_gid);
+	hmac_misc.mode = inode->i_mode;
+	crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof(hmac_misc));
+	if ((evm_hmac_attrs & EVM_ATTR_FSUUID) &&
+	    type != EVM_XATTR_PORTABLE_DIGSIG)
+		crypto_shash_update(desc, (u8 *)&inode->i_sb->s_uuid, UUID_SIZE);
+	crypto_shash_final(desc, digest);
+
+	pr_debug("hmac_misc: (%zu) [%*phN]\n", sizeof(struct h_misc),
+		 (int)sizeof(struct h_misc), &hmac_misc);
+}
+
+/*
+ * Dump large security xattr values as a continuous ascii hexadecimal string.
+ * (pr_debug is limited to 64 bytes.)
+ */
+static void dump_security_xattr_l(const char *prefix, const void *src,
+				  size_t count)
+{
+#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
+	char *asciihex, *p;
+
+	p = asciihex = kmalloc(count * 2 + 1, GFP_KERNEL);
+	if (!asciihex)
+		return;
+
+	p = bin2hex(p, src, count);
+	*p = 0;
+	pr_debug("%s: (%zu) %.*s\n", prefix, count, (int)count * 2, asciihex);
+	kfree(asciihex);
+#endif
+}
+
+static void dump_security_xattr(const char *name, const char *value,
+				size_t value_len)
+{
+	if (value_len < 64)
+		pr_debug("%s: (%zu) [%*phN]\n", name, value_len,
+			 (int)value_len, value);
+	else
+		dump_security_xattr_l(name, value, value_len);
+}
+
+/*
+ * Calculate the HMAC value across the set of protected security xattrs.
+ *
+ * Instead of retrieving the requested xattr, for performance, calculate
+ * the hmac using the requested xattr value. Don't alloc/free memory for
+ * each xattr, but attempt to re-use the previously allocated memory.
+ */
+static int evm_calc_hmac_or_hash(struct dentry *dentry,
+				 const char *req_xattr_name,
+				 const char *req_xattr_value,
+				 size_t req_xattr_value_len,
+				 uint8_t type, struct evm_digest *data,
+				 struct evm_iint_cache *iint)
+{
+	struct inode *inode = d_inode(d_real(dentry, D_REAL_METADATA));
+	struct xattr_list *xattr;
+	struct shash_desc *desc;
+	size_t xattr_size = 0;
+	char *xattr_value = NULL;
+	int error;
+	int size, user_space_size;
+	bool ima_present = false;
+	u64 i_version = 0;
+
+	if (!(inode->i_opflags & IOP_XATTR) ||
+	    inode->i_sb->s_user_ns != &init_user_ns)
+		return -EOPNOTSUPP;
+
+	desc = init_desc(type, data->hdr.algo);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	data->hdr.length = crypto_shash_digestsize(desc->tfm);
+
+	error = -ENODATA;
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
+		bool is_ima = false;
+
+		if (strcmp(xattr->name, XATTR_NAME_IMA) == 0)
+			is_ima = true;
+
+		/*
+		 * Skip non-enabled xattrs for locally calculated
+		 * signatures/HMACs.
+		 */
+		if (type != EVM_XATTR_PORTABLE_DIGSIG && !xattr->enabled)
+			continue;
+
+		if ((req_xattr_name && req_xattr_value)
+		    && !strcmp(xattr->name, req_xattr_name)) {
+			error = 0;
+			crypto_shash_update(desc, (const u8 *)req_xattr_value,
+					     req_xattr_value_len);
+			if (is_ima)
+				ima_present = true;
+
+			dump_security_xattr(req_xattr_name,
+					    req_xattr_value,
+					    req_xattr_value_len);
+			continue;
+		}
+		size = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr->name,
+					  &xattr_value, xattr_size, GFP_NOFS);
+		if (size == -ENOMEM) {
+			error = -ENOMEM;
+			goto out;
+		}
+		if (size < 0)
+			continue;
+
+		user_space_size = vfs_getxattr(&nop_mnt_idmap, dentry,
+					       xattr->name, NULL, 0);
+		if (user_space_size != size)
+			pr_debug("file %s: xattr %s size mismatch (kernel: %d, user: %d)\n",
+				 dentry->d_name.name, xattr->name, size,
+				 user_space_size);
+		error = 0;
+		xattr_size = size;
+		crypto_shash_update(desc, (const u8 *)xattr_value, xattr_size);
+		if (is_ima)
+			ima_present = true;
+
+		dump_security_xattr(xattr->name, xattr_value, xattr_size);
+	}
+	hmac_add_misc(desc, inode, type, data->digest);
+
+	if (inode != d_backing_inode(dentry) && iint) {
+		if (IS_I_VERSION(inode))
+			i_version = inode_query_iversion(inode);
+		integrity_inode_attrs_store(&iint->metadata_inode, i_version,
+					    inode);
+	}
+
+	/* Portable EVM signatures must include an IMA hash */
+	if (type == EVM_XATTR_PORTABLE_DIGSIG && !ima_present)
+		error = -EPERM;
+out:
+	kfree(xattr_value);
+	kfree(desc);
+	return error;
+}
+
+int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value, size_t req_xattr_value_len,
+		  struct evm_digest *data, struct evm_iint_cache *iint)
+{
+	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
+				    req_xattr_value_len, EVM_XATTR_HMAC, data,
+				    iint);
+}
+
+int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value, size_t req_xattr_value_len,
+		  char type, struct evm_digest *data, struct evm_iint_cache *iint)
+{
+	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
+				     req_xattr_value_len, type, data, iint);
+}
+
+static int evm_is_immutable(struct dentry *dentry, struct inode *inode)
+{
+	const struct evm_ima_xattr_data *xattr_data = NULL;
+	struct evm_iint_cache *iint;
+	int rc = 0;
+
+	iint = evm_iint_inode(inode);
+	if (iint && (iint->flags & EVM_IMMUTABLE_DIGSIG))
+		return 1;
+
+	/* Do this the hard way */
+	rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM,
+				(char **)&xattr_data, 0, GFP_NOFS);
+	if (rc <= 0) {
+		if (rc == -ENODATA)
+			rc = 0;
+		goto out;
+	}
+	if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG)
+		rc = 1;
+	else
+		rc = 0;
+
+out:
+	kfree(xattr_data);
+	return rc;
+}
+
+
+/*
+ * Calculate the hmac and update security.evm xattr
+ *
+ * Expects to be called with i_mutex locked.
+ */
+int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name,
+			const char *xattr_value, size_t xattr_value_len)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+	struct evm_digest data;
+	int rc = 0;
+
+	/*
+	 * Don't permit any transformation of the EVM xattr if the signature
+	 * is of an immutable type
+	 */
+	rc = evm_is_immutable(dentry, inode);
+	if (rc < 0)
+		return rc;
+	if (rc)
+		return -EPERM;
+
+	data.hdr.algo = HASH_ALGO_SHA1;
+	rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
+			   xattr_value_len, &data, iint);
+	if (rc == 0) {
+		data.hdr.xattr.sha1.type = EVM_XATTR_HMAC;
+		rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry,
+					   XATTR_NAME_EVM,
+					   &data.hdr.xattr.data[1],
+					   SHA1_DIGEST_SIZE + 1, 0);
+	} else if (rc == -ENODATA && (inode->i_opflags & IOP_XATTR)) {
+		rc = __vfs_removexattr(&nop_mnt_idmap, dentry, XATTR_NAME_EVM);
+	}
+	return rc;
+}
+
+int evm_init_hmac(struct inode *inode, const struct xattr *xattrs,
+		  char *hmac_val)
+{
+	struct shash_desc *desc;
+	const struct xattr *xattr;
+	struct xattr_list *xattr_entry;
+
+	desc = init_desc(EVM_XATTR_HMAC, HASH_ALGO_SHA1);
+	if (IS_ERR(desc)) {
+		pr_info("init_desc failed\n");
+		return PTR_ERR(desc);
+	}
+
+	list_for_each_entry_lockless(xattr_entry, &evm_config_xattrnames,
+				     list) {
+		for (xattr = xattrs; xattr->name; xattr++) {
+			if (strcmp(xattr_entry->name +
+				   XATTR_SECURITY_PREFIX_LEN, xattr->name) != 0)
+				continue;
+
+			crypto_shash_update(desc, xattr->value,
+					    xattr->value_len);
+		}
+	}
+
+	hmac_add_misc(desc, inode, EVM_XATTR_HMAC, hmac_val);
+	kfree(desc);
+	return 0;
+}
+
+/*
+ * Get the key from the TPM for the SHA1-HMAC
+ */
+int evm_init_key(void)
+{
+	struct key *evm_key;
+	struct encrypted_key_payload *ekp;
+	int rc;
+
+	evm_key = request_key(&key_type_encrypted, EVMKEY, NULL);
+	if (IS_ERR(evm_key))
+		return -ENOENT;
+
+	down_read(&evm_key->sem);
+	ekp = evm_key->payload.data[0];
+
+	rc = evm_set_key(ekp->decrypted_data, ekp->decrypted_datalen);
+
+	/* burn the original key contents */
+	memset(ekp->decrypted_data, 0, ekp->decrypted_datalen);
+	up_read(&evm_key->sem);
+	key_put(evm_key);
+	return rc;
+}
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
new file mode 100644
index 000000000..b59e3f121
--- /dev/null
+++ b/security/integrity/evm/evm_main.c
@@ -0,0 +1,1236 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * File: evm_main.c
+ *	implements evm_inode_setxattr, evm_inode_post_setxattr,
+ *	evm_inode_removexattr, evm_verifyxattr, and evm_inode_set_acl.
+ */
+
+#define pr_fmt(fmt) "EVM: "fmt
+
+#include <linux/init.h>
+#include <linux/audit.h>
+#include <linux/xattr.h>
+#include <linux/integrity.h>
+#include <linux/evm.h>
+#include <linux/magic.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/lsm_hooks.h>
+
+#include <crypto/hash.h>
+#include <crypto/hash_info.h>
+#include <crypto/utils.h>
+#include "evm.h"
+
+int evm_initialized;
+
+static const char * const integrity_status_msg[] = {
+	"pass", "pass_immutable", "fail", "fail_immutable", "no_label",
+	"no_xattrs", "unknown"
+};
+int evm_hmac_attrs;
+
+static struct xattr_list evm_config_default_xattrnames[] = {
+	{
+	 .name = XATTR_NAME_SELINUX,
+	 .enabled = IS_ENABLED(CONFIG_SECURITY_SELINUX)
+	},
+	{
+	 .name = XATTR_NAME_SMACK,
+	 .enabled = IS_ENABLED(CONFIG_SECURITY_SMACK)
+	},
+	{
+	 .name = XATTR_NAME_SMACKEXEC,
+	 .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS)
+	},
+	{
+	 .name = XATTR_NAME_SMACKTRANSMUTE,
+	 .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS)
+	},
+	{
+	 .name = XATTR_NAME_SMACKMMAP,
+	 .enabled = IS_ENABLED(CONFIG_EVM_EXTRA_SMACK_XATTRS)
+	},
+	{
+	 .name = XATTR_NAME_APPARMOR,
+	 .enabled = IS_ENABLED(CONFIG_SECURITY_APPARMOR)
+	},
+	{
+	 .name = XATTR_NAME_IMA,
+	 .enabled = IS_ENABLED(CONFIG_IMA_APPRAISE)
+	},
+	{
+	 .name = XATTR_NAME_CAPS,
+	 .enabled = true
+	},
+};
+
+LIST_HEAD(evm_config_xattrnames);
+
+static char *evm_cmdline __initdata;
+core_param(evm, evm_cmdline, charp, 0);
+
+static int evm_fixmode __ro_after_init;
+static void __init evm_set_fixmode(void)
+{
+	if (!evm_cmdline)
+		return;
+
+	if (strncmp(evm_cmdline, "fix", 3) == 0) {
+		if (arch_get_secureboot()) {
+			pr_info("Secure boot enabled: ignoring evm=fix");
+			return;
+		}
+		evm_fixmode = 1;
+	} else {
+		pr_err("invalid \"%s\" mode", evm_cmdline);
+	}
+}
+
+static void __init evm_init_config(void)
+{
+	int i, xattrs;
+
+	xattrs = ARRAY_SIZE(evm_config_default_xattrnames);
+
+	pr_info("Initialising EVM extended attributes:\n");
+	for (i = 0; i < xattrs; i++) {
+		pr_info("%s%s\n", evm_config_default_xattrnames[i].name,
+			!evm_config_default_xattrnames[i].enabled ?
+			" (disabled)" : "");
+		list_add_tail(&evm_config_default_xattrnames[i].list,
+			      &evm_config_xattrnames);
+	}
+
+#ifdef CONFIG_EVM_ATTR_FSUUID
+	evm_hmac_attrs |= EVM_ATTR_FSUUID;
+#endif
+	pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs);
+}
+
+static bool evm_key_loaded(void)
+{
+	return (bool)(evm_initialized & EVM_KEY_MASK);
+}
+
+/*
+ * This function determines whether or not it is safe to ignore verification
+ * errors, based on the ability of EVM to calculate HMACs. If the HMAC key
+ * is not loaded, and it cannot be loaded in the future due to the
+ * EVM_SETUP_COMPLETE initialization flag, allowing an operation despite the
+ * attrs/xattrs being found invalid will not make them valid.
+ */
+static bool evm_hmac_disabled(void)
+{
+	if (evm_initialized & EVM_INIT_HMAC)
+		return false;
+
+	if (!(evm_initialized & EVM_SETUP_COMPLETE))
+		return false;
+
+	return true;
+}
+
+static bool evm_sigv3_required(void)
+{
+	if (evm_initialized & EVM_SIGV3_REQUIRED)
+		return true;
+
+	return false;
+}
+
+static int evm_find_protected_xattrs(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct xattr_list *xattr;
+	int error;
+	int count = 0;
+
+	if (!(inode->i_opflags & IOP_XATTR))
+		return -EOPNOTSUPP;
+
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
+		error = __vfs_getxattr(dentry, inode, xattr->name, NULL, 0);
+		if (error < 0) {
+			if (error == -ENODATA)
+				continue;
+			return error;
+		}
+		count++;
+	}
+
+	return count;
+}
+
+static int is_unsupported_hmac_fs(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+
+	if (inode->i_sb->s_iflags & SB_I_EVM_HMAC_UNSUPPORTED) {
+		pr_info_once("%s not supported\n", inode->i_sb->s_type->name);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr
+ *
+ * Compute the HMAC on the dentry's protected set of extended attributes
+ * and compare it against the stored security.evm xattr.
+ *
+ * For performance:
+ * - use the previously retrieved xattr value and length to calculate the
+ *   HMAC.)
+ * - cache the verification result in the iint, when available.
+ *
+ * Returns integrity status
+ */
+static enum integrity_status evm_verify_hmac(struct dentry *dentry,
+					     const char *xattr_name,
+					     char *xattr_value,
+					     size_t xattr_value_len)
+{
+	struct evm_ima_xattr_data *xattr_data = NULL;
+	struct signature_v2_hdr *hdr;
+	enum integrity_status evm_status = INTEGRITY_PASS;
+	struct evm_digest digest;
+	struct inode *inode = d_backing_inode(dentry);
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+	int rc, xattr_len, evm_immutable = 0;
+
+	if (iint && (iint->evm_status == INTEGRITY_PASS ||
+		     iint->evm_status == INTEGRITY_PASS_IMMUTABLE))
+		return iint->evm_status;
+
+	/*
+	 * On unsupported filesystems without EVM_INIT_X509 enabled, skip
+	 * signature verification.
+	 */
+	if (!(evm_initialized & EVM_INIT_X509) &&
+	    is_unsupported_hmac_fs(dentry))
+		return INTEGRITY_UNKNOWN;
+
+	/* if status is not PASS, try to check again - against -ENOMEM */
+
+	/* first need to know the sig type */
+	rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_EVM,
+				(char **)&xattr_data, 0, GFP_NOFS);
+	if (rc <= 0) {
+		evm_status = INTEGRITY_FAIL;
+		if (rc == -ENODATA) {
+			rc = evm_find_protected_xattrs(dentry);
+			if (rc > 0)
+				evm_status = INTEGRITY_NOLABEL;
+			else if (rc == 0)
+				evm_status = INTEGRITY_NOXATTRS; /* new file */
+		} else if (rc == -EOPNOTSUPP) {
+			evm_status = INTEGRITY_UNKNOWN;
+		}
+		goto out;
+	}
+
+	xattr_len = rc;
+
+	/* check value type */
+	switch (xattr_data->type) {
+	case EVM_XATTR_HMAC:
+		if (xattr_len != sizeof(struct evm_xattr)) {
+			evm_status = INTEGRITY_FAIL;
+			goto out;
+		}
+
+		digest.hdr.algo = HASH_ALGO_SHA1;
+		rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
+				   xattr_value_len, &digest, iint);
+		if (rc)
+			break;
+		rc = crypto_memneq(xattr_data->data, digest.digest,
+				   SHA1_DIGEST_SIZE);
+		if (rc)
+			rc = -EINVAL;
+		break;
+	case EVM_XATTR_PORTABLE_DIGSIG:
+		evm_immutable = 1;
+		fallthrough;
+	case EVM_IMA_XATTR_DIGSIG:
+		/* accept xattr with non-empty signature field */
+		if (xattr_len <= sizeof(struct signature_v2_hdr)) {
+			evm_status = INTEGRITY_FAIL;
+			goto out;
+		}
+
+		hdr = (struct signature_v2_hdr *)xattr_data;
+
+		if (evm_sigv3_required() && hdr->version != 3) {
+			evm_status = INTEGRITY_FAIL;
+			goto out;
+		}
+
+		digest.hdr.algo = hdr->hash_algo;
+		rc = evm_calc_hash(dentry, xattr_name, xattr_value,
+				   xattr_value_len, xattr_data->type, &digest,
+				   iint);
+		if (rc)
+			break;
+		rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM,
+					(const char *)xattr_data, xattr_len,
+					digest.digest, digest.hdr.length,
+					digest.hdr.algo);
+		if (!rc) {
+			if (xattr_data->type == EVM_XATTR_PORTABLE_DIGSIG) {
+				if (iint)
+					iint->flags |= EVM_IMMUTABLE_DIGSIG;
+				evm_status = INTEGRITY_PASS_IMMUTABLE;
+			} else if (!IS_RDONLY(inode) &&
+				   !(inode->i_sb->s_readonly_remount) &&
+				   !IS_IMMUTABLE(inode) &&
+				   !is_unsupported_hmac_fs(dentry)) {
+				evm_update_evmxattr(dentry, xattr_name,
+						    xattr_value,
+						    xattr_value_len);
+			}
+		}
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
+
+	if (rc) {
+		if (rc == -ENODATA)
+			evm_status = INTEGRITY_NOXATTRS;
+		else if (evm_immutable)
+			evm_status = INTEGRITY_FAIL_IMMUTABLE;
+		else
+			evm_status = INTEGRITY_FAIL;
+	}
+	pr_debug("digest: (%d) [%*phN]\n", digest.hdr.length, digest.hdr.length,
+		  digest.digest);
+out:
+	if (iint)
+		iint->evm_status = evm_status;
+	kfree(xattr_data);
+	return evm_status;
+}
+
+static int evm_protected_xattr_common(const char *req_xattr_name,
+				      bool all_xattrs)
+{
+	int namelen;
+	int found = 0;
+	struct xattr_list *xattr;
+
+	namelen = strlen(req_xattr_name);
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
+		if (!all_xattrs && !xattr->enabled)
+			continue;
+
+		if ((strlen(xattr->name) == namelen)
+		    && (strncmp(req_xattr_name, xattr->name, namelen) == 0)) {
+			found = 1;
+			break;
+		}
+		if (strncmp(req_xattr_name,
+			    xattr->name + XATTR_SECURITY_PREFIX_LEN,
+			    strlen(req_xattr_name)) == 0) {
+			found = 1;
+			break;
+		}
+	}
+
+	return found;
+}
+
+int evm_protected_xattr(const char *req_xattr_name)
+{
+	return evm_protected_xattr_common(req_xattr_name, false);
+}
+
+int evm_protected_xattr_if_enabled(const char *req_xattr_name)
+{
+	return evm_protected_xattr_common(req_xattr_name, true);
+}
+
+/**
+ * evm_read_protected_xattrs - read EVM protected xattr names, lengths, values
+ * @dentry: dentry of the read xattrs
+ * @buffer: buffer xattr names, lengths or values are copied to
+ * @buffer_size: size of buffer
+ * @type: n: names, l: lengths, v: values
+ * @canonical_fmt: data format (true: little endian, false: native format)
+ *
+ * Read protected xattr names (separated by |), lengths (u32) or values for a
+ * given dentry and return the total size of copied data. If buffer is NULL,
+ * just return the total size.
+ *
+ * Returns the total size on success, a negative value on error.
+ */
+int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer,
+			      int buffer_size, char type, bool canonical_fmt)
+{
+	struct xattr_list *xattr;
+	int rc, size, total_size = 0;
+
+	list_for_each_entry_lockless(xattr, &evm_config_xattrnames, list) {
+		rc = __vfs_getxattr(dentry, d_backing_inode(dentry),
+				    xattr->name, NULL, 0);
+		if (rc < 0 && rc == -ENODATA)
+			continue;
+		else if (rc < 0)
+			return rc;
+
+		switch (type) {
+		case 'n':
+			size = strlen(xattr->name) + 1;
+			if (buffer) {
+				if (total_size)
+					*(buffer + total_size - 1) = '|';
+
+				memcpy(buffer + total_size, xattr->name, size);
+			}
+			break;
+		case 'l':
+			size = sizeof(u32);
+			if (buffer) {
+				if (canonical_fmt)
+					rc = (__force int)cpu_to_le32(rc);
+
+				*(u32 *)(buffer + total_size) = rc;
+			}
+			break;
+		case 'v':
+			size = rc;
+			if (buffer) {
+				rc = __vfs_getxattr(dentry,
+					d_backing_inode(dentry), xattr->name,
+					buffer + total_size,
+					buffer_size - total_size);
+				if (rc < 0)
+					return rc;
+			}
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		total_size += size;
+	}
+
+	return total_size;
+}
+
+/**
+ * evm_verifyxattr - verify the integrity of the requested xattr
+ * @dentry: object of the verify xattr
+ * @xattr_name: requested xattr
+ * @xattr_value: requested xattr value
+ * @xattr_value_len: requested xattr value length
+ *
+ * Calculate the HMAC for the given dentry and verify it against the stored
+ * security.evm xattr. For performance, use the xattr value and length
+ * previously retrieved to calculate the HMAC.
+ *
+ * Returns the xattr integrity status.
+ *
+ * This function requires the caller to lock the inode's i_mutex before it
+ * is executed.
+ */
+enum integrity_status evm_verifyxattr(struct dentry *dentry,
+				      const char *xattr_name,
+				      void *xattr_value, size_t xattr_value_len)
+{
+	if (!evm_key_loaded() || !evm_protected_xattr(xattr_name))
+		return INTEGRITY_UNKNOWN;
+
+	return evm_verify_hmac(dentry, xattr_name, xattr_value,
+				 xattr_value_len);
+}
+EXPORT_SYMBOL_GPL(evm_verifyxattr);
+
+/*
+ * evm_verify_current_integrity - verify the dentry's metadata integrity
+ * @dentry: pointer to the affected dentry
+ *
+ * Verify and return the dentry's metadata integrity. The exceptions are
+ * before EVM is initialized or in 'fix' mode.
+ */
+static enum integrity_status evm_verify_current_integrity(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+
+	if (!evm_key_loaded() || !S_ISREG(inode->i_mode) || evm_fixmode)
+		return INTEGRITY_PASS;
+	return evm_verify_hmac(dentry, NULL, NULL, 0);
+}
+
+/*
+ * evm_xattr_change - check if passed xattr value differs from current value
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: requested xattr
+ * @xattr_value: requested xattr value
+ * @xattr_value_len: requested xattr value length
+ *
+ * Check if passed xattr value differs from current value.
+ *
+ * Returns 1 if passed xattr value differs from current value, 0 otherwise.
+ */
+static int evm_xattr_change(struct mnt_idmap *idmap,
+			    struct dentry *dentry, const char *xattr_name,
+			    const void *xattr_value, size_t xattr_value_len)
+{
+	char *xattr_data = NULL;
+	int rc = 0;
+
+	rc = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, xattr_name, &xattr_data,
+				0, GFP_NOFS);
+	if (rc < 0) {
+		rc = 1;
+		goto out;
+	}
+
+	if (rc == xattr_value_len)
+		rc = !!memcmp(xattr_value, xattr_data, rc);
+	else
+		rc = 1;
+
+out:
+	kfree(xattr_data);
+	return rc;
+}
+
+/*
+ * evm_protect_xattr - protect the EVM extended attribute
+ *
+ * Prevent security.evm from being modified or removed without the
+ * necessary permissions or when the existing value is invalid.
+ *
+ * The posix xattr acls are 'system' prefixed, which normally would not
+ * affect security.evm.  An interesting side affect of writing posix xattr
+ * acls is their modifying of the i_mode, which is included in security.evm.
+ * For posix xattr acls only, permit security.evm, even if it currently
+ * doesn't exist, to be updated unless the EVM signature is immutable.
+ */
+static int evm_protect_xattr(struct mnt_idmap *idmap,
+			     struct dentry *dentry, const char *xattr_name,
+			     const void *xattr_value, size_t xattr_value_len)
+{
+	enum integrity_status evm_status;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (is_unsupported_hmac_fs(dentry))
+			return -EPERM;
+	} else if (!evm_protected_xattr(xattr_name)) {
+		if (!posix_xattr_acl(xattr_name))
+			return 0;
+		if (is_unsupported_hmac_fs(dentry))
+			return 0;
+
+		evm_status = evm_verify_current_integrity(dentry);
+		if ((evm_status == INTEGRITY_PASS) ||
+		    (evm_status == INTEGRITY_NOXATTRS))
+			return 0;
+		goto out;
+	} else if (is_unsupported_hmac_fs(dentry))
+		return 0;
+
+	evm_status = evm_verify_current_integrity(dentry);
+	if (evm_status == INTEGRITY_NOXATTRS) {
+		struct evm_iint_cache *iint;
+
+		/* Exception if the HMAC is not going to be calculated. */
+		if (evm_hmac_disabled())
+			return 0;
+
+		iint = evm_iint_inode(d_backing_inode(dentry));
+		if (iint && (iint->flags & EVM_NEW_FILE))
+			return 0;
+
+		/* exception for pseudo filesystems */
+		if (dentry->d_sb->s_magic == TMPFS_MAGIC
+		    || dentry->d_sb->s_magic == SYSFS_MAGIC)
+			return 0;
+
+		integrity_audit_msg(AUDIT_INTEGRITY_METADATA,
+				    dentry->d_inode, dentry->d_name.name,
+				    "update_metadata",
+				    integrity_status_msg[evm_status],
+				    -EPERM, 0);
+	}
+out:
+	/* Exception if the HMAC is not going to be calculated. */
+	if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL ||
+	    evm_status == INTEGRITY_UNKNOWN))
+		return 0;
+
+	/*
+	 * Writing other xattrs is safe for portable signatures, as portable
+	 * signatures are immutable and can never be updated.
+	 */
+	if (evm_status == INTEGRITY_FAIL_IMMUTABLE)
+		return 0;
+
+	if (evm_status == INTEGRITY_PASS_IMMUTABLE &&
+	    !evm_xattr_change(idmap, dentry, xattr_name, xattr_value,
+			      xattr_value_len))
+		return 0;
+
+	if (evm_status != INTEGRITY_PASS &&
+	    evm_status != INTEGRITY_PASS_IMMUTABLE)
+		integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry),
+				    dentry->d_name.name, "appraise_metadata",
+				    integrity_status_msg[evm_status],
+				    -EPERM, 0);
+	return evm_status == INTEGRITY_PASS ? 0 : -EPERM;
+}
+
+/**
+ * evm_inode_setxattr - protect the EVM extended attribute
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ * @xattr_value: pointer to the new extended attribute value
+ * @xattr_value_len: pointer to the new extended attribute value length
+ * @flags: flags to pass into filesystem operations
+ *
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
+ */
+static int evm_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			      const char *xattr_name, const void *xattr_value,
+			      size_t xattr_value_len, int flags)
+{
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	/* Policy permits modification of the protected xattrs even though
+	 * there's no HMAC key loaded
+	 */
+	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
+		return 0;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!xattr_value_len)
+			return -EINVAL;
+		if (xattr_data->type != EVM_IMA_XATTR_DIGSIG &&
+		    xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG)
+			return -EPERM;
+	}
+	return evm_protect_xattr(idmap, dentry, xattr_name, xattr_value,
+				 xattr_value_len);
+}
+
+/**
+ * evm_inode_removexattr - protect the EVM extended attribute
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ *
+ * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that
+ * the current value is valid.
+ */
+static int evm_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
+				 const char *xattr_name)
+{
+	/* Policy permits modification of the protected xattrs even though
+	 * there's no HMAC key loaded
+	 */
+	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
+		return 0;
+
+	return evm_protect_xattr(idmap, dentry, xattr_name, NULL, 0);
+}
+
+#ifdef CONFIG_FS_POSIX_ACL
+static int evm_inode_set_acl_change(struct mnt_idmap *idmap,
+				    struct dentry *dentry, const char *name,
+				    struct posix_acl *kacl)
+{
+	int rc;
+
+	umode_t mode;
+	struct inode *inode = d_backing_inode(dentry);
+
+	if (!kacl)
+		return 1;
+
+	rc = posix_acl_update_mode(idmap, inode, &mode, &kacl);
+	if (rc || (inode->i_mode != mode))
+		return 1;
+
+	return 0;
+}
+#else
+static inline int evm_inode_set_acl_change(struct mnt_idmap *idmap,
+					   struct dentry *dentry,
+					   const char *name,
+					   struct posix_acl *kacl)
+{
+	return 0;
+}
+#endif
+
+/**
+ * evm_inode_set_acl - protect the EVM extended attribute from posix acls
+ * @idmap: idmap of the idmapped mount
+ * @dentry: pointer to the affected dentry
+ * @acl_name: name of the posix acl
+ * @kacl: pointer to the posix acls
+ *
+ * Prevent modifying posix acls causing the EVM HMAC to be re-calculated
+ * and 'security.evm' xattr updated, unless the existing 'security.evm' is
+ * valid.
+ *
+ * Return: zero on success, -EPERM on failure.
+ */
+static int evm_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+			     const char *acl_name, struct posix_acl *kacl)
+{
+	enum integrity_status evm_status;
+
+	/* Policy permits modification of the protected xattrs even though
+	 * there's no HMAC key loaded
+	 */
+	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
+		return 0;
+
+	evm_status = evm_verify_current_integrity(dentry);
+	if ((evm_status == INTEGRITY_PASS) ||
+	    (evm_status == INTEGRITY_NOXATTRS))
+		return 0;
+
+	/* Exception if the HMAC is not going to be calculated. */
+	if (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL ||
+	    evm_status == INTEGRITY_UNKNOWN))
+		return 0;
+
+	/*
+	 * Writing other xattrs is safe for portable signatures, as portable
+	 * signatures are immutable and can never be updated.
+	 */
+	if (evm_status == INTEGRITY_FAIL_IMMUTABLE)
+		return 0;
+
+	if (evm_status == INTEGRITY_PASS_IMMUTABLE &&
+	    !evm_inode_set_acl_change(idmap, dentry, acl_name, kacl))
+		return 0;
+
+	if (evm_status != INTEGRITY_PASS_IMMUTABLE)
+		integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry),
+				    dentry->d_name.name, "appraise_metadata",
+				    integrity_status_msg[evm_status],
+				    -EPERM, 0);
+	return -EPERM;
+}
+
+/**
+ * evm_inode_remove_acl - Protect the EVM extended attribute from posix acls
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @acl_name: name of the posix acl
+ *
+ * Prevent removing posix acls causing the EVM HMAC to be re-calculated
+ * and 'security.evm' xattr updated, unless the existing 'security.evm' is
+ * valid.
+ *
+ * Return: zero on success, -EPERM on failure.
+ */
+static int evm_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+				const char *acl_name)
+{
+	return evm_inode_set_acl(idmap, dentry, acl_name, NULL);
+}
+
+static void evm_reset_status(struct inode *inode)
+{
+	struct evm_iint_cache *iint;
+
+	iint = evm_iint_inode(inode);
+	if (iint)
+		iint->evm_status = INTEGRITY_UNKNOWN;
+}
+
+/**
+ * evm_metadata_changed: Detect changes to the metadata
+ * @inode: a file's inode
+ * @metadata_inode: metadata inode
+ *
+ * On a stacked filesystem detect whether the metadata has changed. If this is
+ * the case reset the evm_status associated with the inode that represents the
+ * file.
+ */
+bool evm_metadata_changed(struct inode *inode, struct inode *metadata_inode)
+{
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+	bool ret = false;
+
+	if (iint) {
+		ret = (!IS_I_VERSION(metadata_inode) ||
+		       integrity_inode_attrs_changed(&iint->metadata_inode,
+						     metadata_inode));
+		if (ret)
+			iint->evm_status = INTEGRITY_UNKNOWN;
+	}
+
+	return ret;
+}
+
+/**
+ * evm_revalidate_status - report whether EVM status re-validation is necessary
+ * @xattr_name: pointer to the affected extended attribute name
+ *
+ * Report whether callers of evm_verifyxattr() should re-validate the
+ * EVM status.
+ *
+ * Return true if re-validation is necessary, false otherwise.
+ */
+bool evm_revalidate_status(const char *xattr_name)
+{
+	if (!evm_key_loaded())
+		return false;
+
+	/* evm_inode_post_setattr() passes NULL */
+	if (!xattr_name)
+		return true;
+
+	if (!evm_protected_xattr(xattr_name) && !posix_xattr_acl(xattr_name) &&
+	    strcmp(xattr_name, XATTR_NAME_EVM))
+		return false;
+
+	return true;
+}
+
+/**
+ * evm_fix_hmac - Calculate the HMAC and add it to security.evm for fix mode
+ * @dentry: pointer to the affected dentry which doesn't yet have security.evm
+ *          xattr
+ * @xattr_name: pointer to the affected extended attribute name
+ * @xattr_value: pointer to the new extended attribute value
+ * @xattr_value_len: pointer to the new extended attribute value length
+ *
+ * Expects to be called with i_mutex locked.
+ *
+ * Return: 0 on success, -EPERM/-ENOMEM/-EOPNOTSUPP on failure
+ */
+int evm_fix_hmac(struct dentry *dentry, const char *xattr_name,
+		 const char *xattr_value, size_t xattr_value_len)
+
+{
+	if (!evm_fixmode || !evm_revalidate_status((xattr_name)))
+		return -EPERM;
+
+	if (!(evm_initialized & EVM_INIT_HMAC))
+		return -EPERM;
+
+	if (is_unsupported_hmac_fs(dentry))
+		return -EOPNOTSUPP;
+
+	return evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
+}
+
+/**
+ * evm_inode_post_setxattr - update 'security.evm' to reflect the changes
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ * @xattr_value: pointer to the new extended attribute value
+ * @xattr_value_len: pointer to the new extended attribute value length
+ * @flags: flags to pass into filesystem operations
+ *
+ * Update the HMAC stored in 'security.evm' to reflect the change.
+ *
+ * No need to take the i_mutex lock here, as this function is called from
+ * __vfs_setxattr_noperm().  The caller of which has taken the inode's
+ * i_mutex lock.
+ */
+static void evm_inode_post_setxattr(struct dentry *dentry,
+				    const char *xattr_name,
+				    const void *xattr_value,
+				    size_t xattr_value_len,
+				    int flags)
+{
+	if (!evm_revalidate_status(xattr_name))
+		return;
+
+	evm_reset_status(dentry->d_inode);
+
+	if (!strcmp(xattr_name, XATTR_NAME_EVM))
+		return;
+
+	if (!(evm_initialized & EVM_INIT_HMAC))
+		return;
+
+	if (is_unsupported_hmac_fs(dentry))
+		return;
+
+	evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
+}
+
+/**
+ * evm_inode_post_set_acl - Update the EVM extended attribute from posix acls
+ * @dentry: pointer to the affected dentry
+ * @acl_name: name of the posix acl
+ * @kacl: pointer to the posix acls
+ *
+ * Update the 'security.evm' xattr with the EVM HMAC re-calculated after setting
+ * posix acls.
+ */
+static void evm_inode_post_set_acl(struct dentry *dentry, const char *acl_name,
+				   struct posix_acl *kacl)
+{
+	return evm_inode_post_setxattr(dentry, acl_name, NULL, 0, 0);
+}
+
+/**
+ * evm_inode_post_removexattr - update 'security.evm' after removing the xattr
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ *
+ * Update the HMAC stored in 'security.evm' to reflect removal of the xattr.
+ *
+ * No need to take the i_mutex lock here, as this function is called from
+ * vfs_removexattr() which takes the i_mutex.
+ */
+static void evm_inode_post_removexattr(struct dentry *dentry,
+				       const char *xattr_name)
+{
+	if (!evm_revalidate_status(xattr_name))
+		return;
+
+	evm_reset_status(dentry->d_inode);
+
+	if (!strcmp(xattr_name, XATTR_NAME_EVM))
+		return;
+
+	if (!(evm_initialized & EVM_INIT_HMAC))
+		return;
+
+	evm_update_evmxattr(dentry, xattr_name, NULL, 0);
+}
+
+/**
+ * evm_inode_post_remove_acl - Update the EVM extended attribute from posix acls
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @acl_name: name of the posix acl
+ *
+ * Update the 'security.evm' xattr with the EVM HMAC re-calculated after
+ * removing posix acls.
+ */
+static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap,
+					     struct dentry *dentry,
+					     const char *acl_name)
+{
+	evm_inode_post_removexattr(dentry, acl_name);
+}
+
+static int evm_attr_change(struct mnt_idmap *idmap,
+			   struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	unsigned int ia_valid = attr->ia_valid;
+
+	if (!i_uid_needs_update(idmap, attr, inode) &&
+	    !i_gid_needs_update(idmap, attr, inode) &&
+	    (!(ia_valid & ATTR_MODE) || attr->ia_mode == inode->i_mode))
+		return 0;
+
+	return 1;
+}
+
+/**
+ * evm_inode_setattr - prevent updating an invalid EVM extended attribute
+ * @idmap: idmap of the mount
+ * @dentry: pointer to the affected dentry
+ * @attr: iattr structure containing the new file attributes
+ *
+ * Permit update of file attributes when files have a valid EVM signature,
+ * except in the case of them having an immutable portable signature.
+ */
+static int evm_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			     struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	enum integrity_status evm_status;
+
+	/* Policy permits modification of the protected attrs even though
+	 * there's no HMAC key loaded
+	 */
+	if (evm_initialized & EVM_ALLOW_METADATA_WRITES)
+		return 0;
+
+	if (is_unsupported_hmac_fs(dentry))
+		return 0;
+
+	if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
+		return 0;
+
+	evm_status = evm_verify_current_integrity(dentry);
+	/*
+	 * Writing attrs is safe for portable signatures, as portable signatures
+	 * are immutable and can never be updated.
+	 */
+	if ((evm_status == INTEGRITY_PASS) ||
+	    (evm_status == INTEGRITY_NOXATTRS) ||
+	    (evm_status == INTEGRITY_FAIL_IMMUTABLE) ||
+	    (evm_hmac_disabled() && (evm_status == INTEGRITY_NOLABEL ||
+	     evm_status == INTEGRITY_UNKNOWN)))
+		return 0;
+
+	if (evm_status == INTEGRITY_PASS_IMMUTABLE &&
+	    !evm_attr_change(idmap, dentry, attr))
+		return 0;
+
+	integrity_audit_msg(AUDIT_INTEGRITY_METADATA, d_backing_inode(dentry),
+			    dentry->d_name.name, "appraise_metadata",
+			    integrity_status_msg[evm_status], -EPERM, 0);
+	return -EPERM;
+}
+
+/**
+ * evm_inode_post_setattr - update 'security.evm' after modifying metadata
+ * @idmap: idmap of the idmapped mount
+ * @dentry: pointer to the affected dentry
+ * @ia_valid: for the UID and GID status
+ *
+ * For now, update the HMAC stored in 'security.evm' to reflect UID/GID
+ * changes.
+ *
+ * This function is called from notify_change(), which expects the caller
+ * to lock the inode's i_mutex.
+ */
+static void evm_inode_post_setattr(struct mnt_idmap *idmap,
+				   struct dentry *dentry, int ia_valid)
+{
+	if (!evm_revalidate_status(NULL))
+		return;
+
+	evm_reset_status(dentry->d_inode);
+
+	if (!(evm_initialized & EVM_INIT_HMAC))
+		return;
+
+	if (is_unsupported_hmac_fs(dentry))
+		return;
+
+	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+		evm_update_evmxattr(dentry, NULL, NULL, 0);
+}
+
+static int evm_inode_copy_up_xattr(struct dentry *src, const char *name)
+{
+	struct evm_ima_xattr_data *xattr_data = NULL;
+	int rc;
+
+	if (strcmp(name, XATTR_NAME_EVM) != 0)
+		return -EOPNOTSUPP;
+
+	/* first need to know the sig type */
+	rc = vfs_getxattr_alloc(&nop_mnt_idmap, src, XATTR_NAME_EVM,
+				(char **)&xattr_data, 0, GFP_NOFS);
+	if (rc <= 0)
+		return -EPERM;
+
+	if (rc < offsetof(struct evm_ima_xattr_data, type) +
+		 sizeof(xattr_data->type))
+		return -EPERM;
+
+	switch (xattr_data->type) {
+	case EVM_XATTR_PORTABLE_DIGSIG:
+		rc = 0; /* allow copy-up */
+		break;
+	case EVM_XATTR_HMAC:
+	case EVM_IMA_XATTR_DIGSIG:
+	default:
+		rc = -ECANCELED; /* discard */
+	}
+
+	kfree(xattr_data);
+	return rc;
+}
+
+/*
+ * evm_inode_init_security - initializes security.evm HMAC value
+ */
+int evm_inode_init_security(struct inode *inode, struct inode *dir,
+			    const struct qstr *qstr, struct xattr *xattrs,
+			    int *xattr_count)
+{
+	struct evm_xattr *xattr_data;
+	struct xattr *xattr, *evm_xattr;
+	bool evm_protected_xattrs = false;
+	int rc;
+
+	if (!(evm_initialized & EVM_INIT_HMAC) || !xattrs)
+		return 0;
+
+	/*
+	 * security_inode_init_security() makes sure that the xattrs array is
+	 * contiguous, there is enough space for security.evm, and that there is
+	 * a terminator at the end of the array.
+	 */
+	for (xattr = xattrs; xattr->name; xattr++) {
+		if (evm_protected_xattr(xattr->name))
+			evm_protected_xattrs = true;
+	}
+
+	/* EVM xattr not needed. */
+	if (!evm_protected_xattrs)
+		return 0;
+
+	evm_xattr = lsm_get_xattr_slot(xattrs, xattr_count);
+	/*
+	 * Array terminator (xattr name = NULL) must be the first non-filled
+	 * xattr slot.
+	 */
+	WARN_ONCE(evm_xattr != xattr,
+		  "%s: xattrs terminator is not the first non-filled slot\n",
+		  __func__);
+
+	xattr_data = kzalloc_obj(*xattr_data, GFP_NOFS);
+	if (!xattr_data)
+		return -ENOMEM;
+
+	xattr_data->data.type = EVM_XATTR_HMAC;
+	rc = evm_init_hmac(inode, xattrs, xattr_data->digest);
+	if (rc < 0)
+		goto out;
+
+	evm_xattr->value = xattr_data;
+	evm_xattr->value_len = sizeof(*xattr_data);
+	evm_xattr->name = XATTR_EVM_SUFFIX;
+	return 0;
+out:
+	kfree(xattr_data);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(evm_inode_init_security);
+
+static int evm_inode_alloc_security(struct inode *inode)
+{
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+
+	/* Called by security_inode_alloc(), it cannot be NULL. */
+	iint->flags = 0UL;
+	iint->evm_status = INTEGRITY_UNKNOWN;
+
+	return 0;
+}
+
+static void evm_file_release(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+	fmode_t mode = file->f_mode;
+
+	if (!S_ISREG(inode->i_mode) || !(mode & FMODE_WRITE))
+		return;
+
+	if (iint && iint->flags & EVM_NEW_FILE &&
+	    atomic_read(&inode->i_writecount) == 1)
+		iint->flags &= ~EVM_NEW_FILE;
+}
+
+static void evm_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct evm_iint_cache *iint = evm_iint_inode(inode);
+
+	if (!S_ISREG(inode->i_mode))
+		return;
+
+	if (iint)
+		iint->flags |= EVM_NEW_FILE;
+}
+
+#ifdef CONFIG_EVM_LOAD_X509
+void __init evm_load_x509(void)
+{
+	int rc;
+
+	rc = integrity_load_x509(INTEGRITY_KEYRING_EVM, CONFIG_EVM_X509_PATH);
+	if (!rc)
+		evm_initialized |= EVM_INIT_X509;
+}
+#endif
+
+static int __init init_evm(void)
+{
+	int error;
+	struct list_head *pos, *q;
+
+	evm_init_config();
+
+	evm_set_fixmode();
+
+	error = integrity_init_keyring(INTEGRITY_KEYRING_EVM);
+	if (error)
+		goto error;
+
+	error = evm_init_secfs();
+	if (error < 0) {
+		pr_info("Error registering secfs\n");
+		goto error;
+	}
+
+error:
+	if (error != 0) {
+		if (!list_empty(&evm_config_xattrnames)) {
+			list_for_each_safe(pos, q, &evm_config_xattrnames)
+				list_del(pos);
+		}
+	}
+
+	return error;
+}
+
+static struct security_hook_list evm_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(inode_setattr, evm_inode_setattr),
+	LSM_HOOK_INIT(inode_post_setattr, evm_inode_post_setattr),
+	LSM_HOOK_INIT(inode_copy_up_xattr, evm_inode_copy_up_xattr),
+	LSM_HOOK_INIT(inode_setxattr, evm_inode_setxattr),
+	LSM_HOOK_INIT(inode_post_setxattr, evm_inode_post_setxattr),
+	LSM_HOOK_INIT(inode_set_acl, evm_inode_set_acl),
+	LSM_HOOK_INIT(inode_post_set_acl, evm_inode_post_set_acl),
+	LSM_HOOK_INIT(inode_remove_acl, evm_inode_remove_acl),
+	LSM_HOOK_INIT(inode_post_remove_acl, evm_inode_post_remove_acl),
+	LSM_HOOK_INIT(inode_removexattr, evm_inode_removexattr),
+	LSM_HOOK_INIT(inode_post_removexattr, evm_inode_post_removexattr),
+	LSM_HOOK_INIT(inode_init_security, evm_inode_init_security),
+	LSM_HOOK_INIT(inode_alloc_security, evm_inode_alloc_security),
+	LSM_HOOK_INIT(file_release, evm_file_release),
+	LSM_HOOK_INIT(path_post_mknod, evm_post_path_mknod),
+};
+
+static const struct lsm_id evm_lsmid = {
+	.name = "evm",
+	.id = LSM_ID_EVM,
+};
+
+static int __init init_evm_lsm(void)
+{
+	security_add_hooks(evm_hooks, ARRAY_SIZE(evm_hooks), &evm_lsmid);
+	return 0;
+}
+
+struct lsm_blob_sizes evm_blob_sizes __ro_after_init = {
+	.lbs_inode = sizeof(struct evm_iint_cache),
+	.lbs_xattr_count = 1,
+};
+
+DEFINE_LSM(evm) = {
+	.id = &evm_lsmid,
+	.init = init_evm_lsm,
+	.order = LSM_ORDER_LAST,
+	.blobs = &evm_blob_sizes,
+	.initcall_late = init_evm,
+};
diff --git a/security/integrity/evm/evm_posix_acl.c b/security/integrity/evm/evm_posix_acl.c
new file mode 100644
index 000000000..37275800c
--- /dev/null
+++ b/security/integrity/evm/evm_posix_acl.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ */
+
+#include <linux/xattr.h>
+#include <linux/evm.h>
+
+int posix_xattr_acl(const char *xattr)
+{
+	int xattr_len = strlen(xattr);
+
+	if ((strlen(XATTR_NAME_POSIX_ACL_ACCESS) == xattr_len)
+	     && (strncmp(XATTR_NAME_POSIX_ACL_ACCESS, xattr, xattr_len) == 0))
+		return 1;
+	if ((strlen(XATTR_NAME_POSIX_ACL_DEFAULT) == xattr_len)
+	     && (strncmp(XATTR_NAME_POSIX_ACL_DEFAULT, xattr, xattr_len) == 0))
+		return 1;
+	return 0;
+}
diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c
new file mode 100644
index 000000000..4baf5e23b
--- /dev/null
+++ b/security/integrity/evm/evm_secfs.c
@@ -0,0 +1,346 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: evm_secfs.c
+ *	- Used to signal when key is on keyring
+ *	- Get the key and enable EVM
+ */
+
+#include <linux/audit.h>
+#include <linux/uaccess.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include "evm.h"
+
+static struct dentry *evm_dir;
+static struct dentry *evm_symlink;
+
+#ifdef CONFIG_EVM_ADD_XATTRS
+static struct dentry *evm_xattrs;
+static DEFINE_MUTEX(xattr_list_mutex);
+static int evm_xattrs_locked;
+#endif
+
+/**
+ * evm_read_key - read() for <securityfs>/evm
+ *
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t evm_read_key(struct file *filp, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	char temp[80];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d", (evm_initialized & ~EVM_SETUP_COMPLETE));
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+
+	return rc;
+}
+
+/**
+ * evm_write_key - write() for <securityfs>/evm
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Used to signal that key is on the kernel key ring.
+ * - get the integrity hmac key from the kernel key ring
+ * - create list of hmac protected extended attributes
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t evm_write_key(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	unsigned int i;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN) || (evm_initialized & EVM_SETUP_COMPLETE))
+		return -EPERM;
+
+	ret = kstrtouint_from_user(buf, count, 0, &i);
+
+	if (ret)
+		return ret;
+
+	/* Reject invalid values */
+	if (!i || (i & ~EVM_INIT_MASK) != 0)
+		return -EINVAL;
+
+	/*
+	 * Don't allow a request to enable metadata writes if
+	 * an HMAC key is loaded.
+	 */
+	if ((i & EVM_ALLOW_METADATA_WRITES) &&
+	    (evm_initialized & EVM_INIT_HMAC) != 0)
+		return -EPERM;
+
+	if (i & EVM_INIT_HMAC) {
+		ret = evm_init_key();
+		if (ret != 0)
+			return ret;
+		/* Forbid further writes after the symmetric key is loaded */
+		i |= EVM_SETUP_COMPLETE;
+	}
+
+	evm_initialized |= i;
+
+	/* Don't allow protected metadata modification if a symmetric key
+	 * is loaded
+	 */
+	if (evm_initialized & EVM_INIT_HMAC)
+		evm_initialized &= ~(EVM_ALLOW_METADATA_WRITES);
+
+	return count;
+}
+
+static const struct file_operations evm_key_ops = {
+	.read		= evm_read_key,
+	.write		= evm_write_key,
+};
+
+#ifdef CONFIG_EVM_ADD_XATTRS
+/**
+ * evm_read_xattrs - read() for <securityfs>/evm_xattrs
+ *
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t evm_read_xattrs(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	char *temp;
+	size_t offset = 0, size = 0;
+	ssize_t rc;
+	struct xattr_list *xattr;
+
+	if (*ppos != 0)
+		return 0;
+
+	rc = mutex_lock_interruptible(&xattr_list_mutex);
+	if (rc)
+		return -ERESTARTSYS;
+
+	list_for_each_entry(xattr, &evm_config_xattrnames, list) {
+		if (!xattr->enabled)
+			continue;
+
+		size += strlen(xattr->name) + 1;
+	}
+
+	temp = kmalloc(size + 1, GFP_KERNEL);
+	if (!temp) {
+		mutex_unlock(&xattr_list_mutex);
+		return -ENOMEM;
+	}
+
+	temp[size] = '\0';
+
+	/*
+	 * No truncation possible: size is computed over the same enabled
+	 * xattrs under xattr_list_mutex, so offset never exceeds size.
+	 */
+	list_for_each_entry(xattr, &evm_config_xattrnames, list) {
+		if (!xattr->enabled)
+			continue;
+
+		offset += snprintf(temp + offset, size + 1 - offset, "%s\n",
+				   xattr->name);
+	}
+
+	mutex_unlock(&xattr_list_mutex);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, offset);
+
+	kfree(temp);
+
+	return rc;
+}
+
+/**
+ * evm_write_xattrs - write() for <securityfs>/evm_xattrs
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t evm_write_xattrs(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	int len, err;
+	struct xattr_list *xattr, *tmp;
+	struct audit_buffer *ab;
+	struct iattr newattrs;
+	struct inode *inode;
+
+	if (!capable(CAP_SYS_ADMIN) || evm_xattrs_locked)
+		return -EPERM;
+
+	if (*ppos != 0)
+		return -EINVAL;
+
+	if (count > XATTR_NAME_MAX)
+		return -E2BIG;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL,
+			     AUDIT_INTEGRITY_EVM_XATTR);
+	if (!ab && IS_ENABLED(CONFIG_AUDIT))
+		return -ENOMEM;
+
+	xattr = kmalloc_obj(struct xattr_list);
+	if (!xattr) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	xattr->enabled = true;
+	xattr->name = memdup_user_nul(buf, count);
+	if (IS_ERR(xattr->name)) {
+		err = PTR_ERR(xattr->name);
+		xattr->name = NULL;
+		goto out;
+	}
+
+	/* Remove any trailing newline */
+	len = strlen(xattr->name);
+	if (len && xattr->name[len-1] == '\n')
+		xattr->name[len-1] = '\0';
+
+	audit_log_format(ab, "xattr=");
+	audit_log_untrustedstring(ab, xattr->name);
+
+	if (strcmp(xattr->name, ".") == 0) {
+		evm_xattrs_locked = 1;
+		newattrs.ia_mode = S_IFREG | 0440;
+		newattrs.ia_valid = ATTR_MODE;
+		inode = evm_xattrs->d_inode;
+		inode_lock(inode);
+		err = simple_setattr(&nop_mnt_idmap, evm_xattrs, &newattrs);
+		inode_unlock(inode);
+		if (!err)
+			err = count;
+		goto out;
+	}
+
+	if (strncmp(xattr->name, XATTR_SECURITY_PREFIX,
+		    XATTR_SECURITY_PREFIX_LEN) != 0) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * xattr_list_mutex guards against races in evm_read_xattrs().
+	 * Entries are only added to the evm_config_xattrnames list
+	 * and never deleted. Therefore, the list is traversed
+	 * using list_for_each_entry_lockless() without holding
+	 * the mutex in evm_calc_hmac_or_hash(), evm_find_protected_xattrs()
+	 * and evm_protected_xattr().
+	 */
+	mutex_lock(&xattr_list_mutex);
+	list_for_each_entry(tmp, &evm_config_xattrnames, list) {
+		if (strcmp(xattr->name, tmp->name) == 0) {
+			err = -EEXIST;
+			if (!tmp->enabled) {
+				tmp->enabled = true;
+				err = count;
+			}
+			mutex_unlock(&xattr_list_mutex);
+			goto out;
+		}
+	}
+	list_add_tail_rcu(&xattr->list, &evm_config_xattrnames);
+	mutex_unlock(&xattr_list_mutex);
+
+	audit_log_format(ab, " res=0");
+	audit_log_end(ab);
+	return count;
+out:
+	audit_log_format(ab, " res=%d", (err < 0) ? err : 0);
+	audit_log_end(ab);
+	if (xattr) {
+		kfree(xattr->name);
+		kfree(xattr);
+	}
+	return err;
+}
+
+static const struct file_operations evm_xattr_ops = {
+	.read		= evm_read_xattrs,
+	.write		= evm_write_xattrs,
+};
+
+static int evm_init_xattrs(void)
+{
+	evm_xattrs = securityfs_create_file("evm_xattrs", 0660, evm_dir, NULL,
+					    &evm_xattr_ops);
+	if (IS_ERR(evm_xattrs))
+		return -EFAULT;
+
+	return 0;
+}
+#else
+static int evm_init_xattrs(void)
+{
+	return 0;
+}
+#endif
+
+int __init evm_init_secfs(void)
+{
+	int error = 0;
+	struct dentry *dentry;
+
+	error = integrity_fs_init();
+	if (error < 0)
+		return -EFAULT;
+
+	evm_dir = securityfs_create_dir("evm", integrity_dir);
+	if (IS_ERR(evm_dir)) {
+		error = -EFAULT;
+		goto out;
+	}
+
+	dentry = securityfs_create_file("evm", 0660,
+				      evm_dir, NULL, &evm_key_ops);
+	if (IS_ERR(dentry)) {
+		error = -EFAULT;
+		goto out;
+	}
+
+	evm_symlink = securityfs_create_symlink("evm", NULL,
+						"integrity/evm/evm", NULL);
+	if (IS_ERR(evm_symlink)) {
+		error = -EFAULT;
+		goto out;
+	}
+
+	if (evm_init_xattrs() != 0) {
+		error = -EFAULT;
+		goto out;
+	}
+
+	return 0;
+out:
+	securityfs_remove(evm_symlink);
+	securityfs_remove(evm_dir);
+	integrity_fs_fini();
+	return error;
+}
diff --git a/security/integrity/iint.c b/security/integrity/iint.c
new file mode 100644
index 000000000..8ec1a3436
--- /dev/null
+++ b/security/integrity/iint.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: integrity_iint.c
+ *	- initialize the integrity directory in securityfs
+ *	- load IMA and EVM keys
+ */
+#include <linux/security.h>
+#include "integrity.h"
+
+struct dentry *integrity_dir;
+
+/*
+ * integrity_kernel_read - read data from the file
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+int integrity_kernel_read(struct file *file, loff_t offset,
+			  void *addr, unsigned long count)
+{
+	return __kernel_read(file, addr, count, &offset);
+}
+
+/*
+ * integrity_load_keys - load integrity keys hook
+ *
+ * Hooks is called from init/main.c:kernel_init_freeable()
+ * when rootfs is ready
+ */
+void __init integrity_load_keys(void)
+{
+	ima_load_x509();
+
+	if (!IS_ENABLED(CONFIG_IMA_LOAD_X509))
+		evm_load_x509();
+}
+
+int __init integrity_fs_init(void)
+{
+	if (integrity_dir)
+		return 0;
+
+	integrity_dir = securityfs_create_dir("integrity", NULL);
+	if (IS_ERR(integrity_dir)) {
+		int ret = PTR_ERR(integrity_dir);
+
+		if (ret != -ENODEV)
+			pr_err("Unable to create integrity sysfs dir: %d\n",
+			       ret);
+		integrity_dir = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+void __init integrity_fs_fini(void)
+{
+	if (!integrity_dir || !simple_empty(integrity_dir))
+		return;
+
+	securityfs_remove(integrity_dir);
+	integrity_dir = NULL;
+}
diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
new file mode 100644
index 000000000..b3a9f8680
--- /dev/null
+++ b/security/integrity/ima/Kconfig
@@ -0,0 +1,360 @@
+# SPDX-License-Identifier: GPL-2.0-only
+# IBM Integrity Measurement Architecture
+#
+config IMA
+	bool "Integrity Measurement Architecture(IMA)"
+	select SECURITYFS
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	select CRYPTO_HASH_INFO
+	select SECURITY_PATH
+	select TCG_TPM if HAS_IOMEM
+	select TCG_TIS if TCG_TPM && X86
+	select TCG_CRB if TCG_TPM && ACPI
+	select TCG_IBMVTPM if TCG_TPM && PPC_PSERIES
+	select INTEGRITY_AUDIT if AUDIT
+	help
+	  The Trusted Computing Group(TCG) runtime Integrity
+	  Measurement Architecture(IMA) maintains a list of hash
+	  values of executables and other sensitive system files,
+	  as they are read or executed. If an attacker manages
+	  to change the contents of an important system file
+	  being measured, we can tell.
+
+	  If your system has a TPM chip, then IMA also maintains
+	  an aggregate integrity value over this list inside the
+	  TPM hardware, so that the TPM can prove to a third party
+	  whether or not critical system files have been modified.
+	  Read <https://www.usenix.org/events/sec04/tech/sailer.html>
+	  to learn more about IMA.
+	  If unsure, say N.
+
+if IMA
+
+config IMA_KEXEC
+	bool "Enable carrying the IMA measurement list across a soft boot"
+	depends on TCG_TPM && HAVE_IMA_KEXEC
+	default n
+	help
+	   TPM PCRs are only reset on a hard reboot.  In order to validate
+	   a TPM's quote after a soft boot, the IMA measurement list of the
+	   running kernel must be saved and restored on boot.
+
+	   Depending on the IMA policy, the measurement list can grow to
+	   be very large.
+
+config IMA_MEASURE_PCR_IDX
+	int
+	range 8 14
+	default 10
+	help
+	  IMA_MEASURE_PCR_IDX determines the TPM PCR register index
+	  that IMA uses to maintain the integrity aggregate of the
+	  measurement list.  If unsure, use the default 10.
+
+config IMA_LSM_RULES
+	bool
+	depends on AUDIT && (SECURITY_SELINUX || SECURITY_SMACK || SECURITY_APPARMOR)
+	default y
+	help
+	  Disabling this option will disregard LSM based policy rules.
+
+choice
+	prompt "Default template"
+	default IMA_NG_TEMPLATE
+	help
+	  Select the default IMA measurement template.
+
+	  The original 'ima' measurement list template contains a
+	  hash, defined as 20 bytes, and a null terminated pathname,
+	  limited to 255 characters.  The 'ima-ng' measurement list
+	  template permits both larger hash digests and longer
+	  pathnames. The configured default template can be replaced
+	  by specifying "ima_template=" on the boot command line.
+
+	config IMA_NG_TEMPLATE
+		bool "ima-ng (default)"
+	config IMA_SIG_TEMPLATE
+		bool "ima-sig"
+endchoice
+
+config IMA_DEFAULT_TEMPLATE
+	string
+	default "ima-ng" if IMA_NG_TEMPLATE
+	default "ima-sig" if IMA_SIG_TEMPLATE
+
+choice
+	prompt "Default integrity hash algorithm"
+	default IMA_DEFAULT_HASH_SHA1
+	help
+	   Select the default hash algorithm used for the measurement
+	   list, integrity appraisal and audit log.  The compiled default
+	   hash algorithm can be overwritten using the kernel command
+	   line 'ima_hash=' option.
+
+	config IMA_DEFAULT_HASH_SHA1
+		bool "SHA1 (default)"
+		depends on CRYPTO_SHA1=y
+
+	config IMA_DEFAULT_HASH_SHA256
+		bool "SHA256"
+		depends on CRYPTO_SHA256=y
+
+	config IMA_DEFAULT_HASH_SHA512
+		bool "SHA512"
+		depends on CRYPTO_SHA512=y
+
+	config IMA_DEFAULT_HASH_WP512
+		bool "WP512"
+		depends on CRYPTO_WP512=y
+
+	config IMA_DEFAULT_HASH_SM3
+		bool "SM3"
+		depends on CRYPTO_SM3=y
+endchoice
+
+config IMA_DEFAULT_HASH
+	string
+	default "sha1" if IMA_DEFAULT_HASH_SHA1
+	default "sha256" if IMA_DEFAULT_HASH_SHA256
+	default "sha512" if IMA_DEFAULT_HASH_SHA512
+	default "wp512" if IMA_DEFAULT_HASH_WP512
+	default "sm3" if IMA_DEFAULT_HASH_SM3
+
+config IMA_WRITE_POLICY
+	bool "Enable multiple writes to the IMA policy"
+	default n
+	help
+	  IMA policy can now be updated multiple times.  The new rules get
+	  appended to the original policy.  Have in mind that the rules are
+	  scanned in FIFO order so be careful when you design and add new ones.
+
+	  If unsure, say N.
+
+config IMA_READ_POLICY
+	bool "Enable reading back the current IMA policy"
+	default y if IMA_WRITE_POLICY
+	default n if !IMA_WRITE_POLICY
+	help
+	   It is often useful to be able to read back the IMA policy.  It is
+	   even more important after introducing CONFIG_IMA_WRITE_POLICY.
+	   This option allows the root user to see the current policy rules.
+
+config IMA_APPRAISE
+	bool "Appraise integrity measurements"
+	default n
+	help
+	  This option enables local measurement integrity appraisal.
+	  It requires the system to be labeled with a security extended
+	  attribute containing the file hash measurement.  To protect
+	  the security extended attributes from offline attack, enable
+	  and configure EVM.
+
+	  For more information on integrity appraisal refer to:
+	  <http://linux-ima.sourceforge.net>
+	  If unsure, say N.
+
+config IMA_ARCH_POLICY
+        bool "Enable loading an IMA architecture specific policy"
+        depends on (KEXEC_SIG && IMA) || IMA_APPRAISE \
+		   && INTEGRITY_ASYMMETRIC_KEYS
+        default n
+        help
+          This option enables loading an IMA architecture specific policy
+          based on run time secure boot flags.
+
+config IMA_APPRAISE_BUILD_POLICY
+	bool "IMA build time configured policy rules"
+	depends on IMA_APPRAISE && INTEGRITY_ASYMMETRIC_KEYS
+	default n
+	help
+	  This option defines an IMA appraisal policy at build time, which
+	  is enforced at run time without having to specify a builtin
+	  policy name on the boot command line.  The build time appraisal
+	  policy rules persist after loading a custom policy.
+
+	  Depending on the rules configured, this policy may require kernel
+	  modules, firmware, the kexec kernel image, and/or the IMA policy
+	  to be signed.  Unsigned files might prevent the system from
+	  booting or applications from working properly.
+
+config IMA_APPRAISE_REQUIRE_FIRMWARE_SIGS
+	bool "Appraise firmware signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  This option defines a policy requiring all firmware to be signed,
+	  including the regulatory.db.  If both this option and
+	  CFG80211_REQUIRE_SIGNED_REGDB are enabled, then both signature
+	  verification methods are necessary.
+
+config IMA_APPRAISE_REQUIRE_KEXEC_SIGS
+	bool "Appraise kexec kernel image signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require all kexec'ed kernel images to
+	  be signed and verified by a public key on the trusted IMA
+	  keyring.
+
+	  Kernel image signatures can not be verified by the original
+	  kexec_load syscall.  Enabling this rule will prevent its
+	  usage.
+
+config IMA_APPRAISE_REQUIRE_MODULE_SIGS
+	bool "Appraise kernel modules signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require all kernel modules to be signed
+	  and verified by a public key on the trusted IMA keyring.
+
+	  Kernel module signatures can only be verified by IMA-appraisal,
+	  via the finit_module syscall. Enabling this rule will prevent
+	  the usage of the init_module syscall.
+
+config IMA_APPRAISE_REQUIRE_POLICY_SIGS
+	bool "Appraise IMA policy signature"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require the IMA policy to be signed and
+	  and verified by a key on the trusted IMA keyring.
+
+config IMA_APPRAISE_BOOTPARAM
+	bool "ima_appraise boot parameter"
+	depends on IMA_APPRAISE
+	default y
+	help
+	  This option enables the different "ima_appraise=" modes
+	  (eg. fix, log) from the boot command line.
+
+config IMA_APPRAISE_MODSIG
+	bool "Support module-style signatures for appraisal"
+	depends on IMA_APPRAISE
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	select PKCS7_MESSAGE_PARSER
+	select MODULE_SIG_FORMAT
+	default n
+	help
+	   Adds support for signatures appended to files. The format of the
+	   appended signature is the same used for signed kernel modules.
+	   The modsig keyword can be used in the IMA policy to allow a hook
+	   to accept such signatures.
+
+config IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY
+	bool "Permit keys validly signed by a built-in, machine (if configured) or secondary"
+	depends on SYSTEM_TRUSTED_KEYRING
+	depends on SECONDARY_TRUSTED_KEYRING
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	select INTEGRITY_TRUSTED_KEYRING
+	default n
+	help
+	  Keys may be added to the IMA or IMA blacklist keyrings, if the
+	  key is validly signed by a CA cert in the system built-in,
+	  machine (if configured), or secondary trusted keyrings. The
+	  key must also have the digitalSignature usage set.
+
+	  Intermediate keys between those the kernel has compiled in and the
+	  IMA keys to be added may be added to the system secondary keyring,
+	  provided they are validly signed by a key already resident in the
+	  built-in, machine (if configured) or secondary trusted keyrings.
+
+config IMA_BLACKLIST_KEYRING
+	bool "Create IMA machine owner blacklist keyrings (EXPERIMENTAL)"
+	depends on SYSTEM_TRUSTED_KEYRING
+	depends on INTEGRITY_TRUSTED_KEYRING
+	default n
+	help
+	   This option creates an IMA blacklist keyring, which contains all
+	   revoked IMA keys.  It is consulted before any other keyring.  If
+	   the search is successful the requested operation is rejected and
+	   an error is returned to the caller.
+
+config IMA_LOAD_X509
+	bool "Load X509 certificate onto the '.ima' trusted keyring"
+	depends on INTEGRITY_TRUSTED_KEYRING
+	default n
+	help
+	   File signature verification is based on the public keys
+	   loaded on the .ima trusted keyring. These public keys are
+	   X509 certificates signed by a trusted key on the
+	   .system keyring.  This option enables X509 certificate
+	   loading from the kernel onto the '.ima' trusted keyring.
+
+config IMA_X509_PATH
+	string "IMA X509 certificate path"
+	depends on IMA_LOAD_X509
+	default "/etc/keys/x509_ima.der"
+	help
+	   This option defines IMA X509 certificate path.
+
+config IMA_APPRAISE_SIGNED_INIT
+	bool "Require signed user-space initialization"
+	depends on IMA_LOAD_X509
+	default n
+	help
+	   This option requires user-space init to be signed.
+
+config IMA_MEASURE_ASYMMETRIC_KEYS
+	bool
+	depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE=y
+	default y
+
+config IMA_QUEUE_EARLY_BOOT_KEYS
+	bool
+	depends on IMA_MEASURE_ASYMMETRIC_KEYS
+	depends on SYSTEM_TRUSTED_KEYRING
+	default y
+
+config IMA_SECURE_AND_OR_TRUSTED_BOOT
+       bool
+       depends on IMA_ARCH_POLICY
+       help
+          This option is selected by architectures to enable secure and/or
+          trusted boot based on IMA runtime policies.
+
+config IMA_DISABLE_HTABLE
+	bool "Disable htable to allow measurement of duplicate records"
+	default n
+	help
+	   This option disables htable to allow measurement of duplicate records.
+
+config IMA_KEXEC_EXTRA_MEMORY_KB
+	int "Extra memory for IMA measurements added during kexec soft reboot"
+	range 0 40
+	depends on IMA_KEXEC
+	default 0
+	help
+	  IMA_KEXEC_EXTRA_MEMORY_KB determines the extra memory to be
+	  allocated (in kb) for IMA measurements added during kexec soft reboot.
+	  If set to the default value of 0, an extra half page of memory for those
+	  additional measurements will be allocated.
+
+config IMA_STAGING
+	bool "Support for staging the measurements list"
+	default n
+	help
+	  Add support for staging the measurements list.
+
+	  It allows user space to stage the measurements list for deletion and
+	  to delete the staged measurements after confirmation.
+
+	  Or, alternatively, it allows user space to specify N measurements
+	  records to stage internally, so that they can be immediately deleted.
+
+	  On kexec, staging is aborted and any staged measurement records are
+	  copied to the secondary kernel.
+
+config IMA_INIT_LATE_SYNC
+	bool "Initialise IMA at late_initcall_sync"
+	default n
+	help
+	  This option initialises IMA at late_initcall_sync for platforms
+	  where TPM device probing is deferred.
+	  When this option is enabled, modules that access files in the
+	  initramfs through usermode helper calls such as request_module()
+	  during initcall must not be built-in. Otherwise, IMA may miss
+	  file measurements for them.
+endif
diff --git a/security/integrity/ima/Makefile b/security/integrity/ima/Makefile
new file mode 100644
index 000000000..b376d38b4
--- /dev/null
+++ b/security/integrity/ima/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for building Trusted Computing Group's(TCG) runtime Integrity
+# Measurement Architecture(IMA).
+#
+
+obj-$(CONFIG_IMA) += ima.o ima_iint.o
+
+ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
+	 ima_policy.o ima_template.o ima_template_lib.o
+ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
+ima-$(CONFIG_IMA_APPRAISE_MODSIG) += ima_modsig.o
+ima-$(CONFIG_HAVE_IMA_KEXEC) += ima_kexec.o
+ima-$(CONFIG_IMA_BLACKLIST_KEYRING) += ima_mok.o
+ima-$(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) += ima_asymmetric_keys.o
+ima-$(CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS) += ima_queue_keys.o
+
+ifeq ($(CONFIG_EFI),y)
+ima-$(CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT) += ima_efi.o
+endif
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
new file mode 100644
index 000000000..10214f73c
--- /dev/null
+++ b/security/integrity/ima/ima.h
@@ -0,0 +1,630 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima.h
+ *	internal Integrity Measurement Architecture (IMA) definitions
+ */
+
+#ifndef __LINUX_IMA_H
+#define __LINUX_IMA_H
+
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/hash.h>
+#include <linux/tpm.h>
+#include <linux/audit.h>
+#include <crypto/hash_info.h>
+
+#include "../integrity.h"
+
+enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
+		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
+enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8, TPM_PCR10 = 10 };
+
+/*
+ * BINARY: current binary measurements list
+ * BINARY_STAGED: staged binary measurements list
+ * BINARY_FULL: binary measurements list since IMA init (lost after kexec)
+ */
+enum binary_lists {
+	BINARY, BINARY_STAGED, BINARY_FULL, BINARY__LAST
+};
+
+/* digest size for IMA, fits SHA1 or MD5 */
+#define IMA_DIGEST_SIZE		SHA1_DIGEST_SIZE
+#define IMA_EVENT_NAME_LEN_MAX	255
+
+#define IMA_HASH_BITS 10
+#define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
+
+#define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
+#define IMA_TEMPLATE_NUM_FIELDS_MAX	15
+
+#define IMA_TEMPLATE_IMA_NAME "ima"
+#define IMA_TEMPLATE_IMA_FMT "d|n"
+
+#define NR_BANKS(chip) ((chip != NULL) ? chip->nr_allocated_banks : 0)
+
+/* current content of the policy */
+extern int ima_policy_flag;
+
+extern struct mutex ima_write_mutex;
+
+/* bitset of digests algorithms allowed in the setxattr hook */
+extern atomic_t ima_setxattr_allowed_hash_algorithms;
+
+/* IMA hash algorithm description */
+struct ima_algo_desc {
+	struct crypto_shash *tfm;
+	enum hash_algo algo;
+	unsigned int digest_size;
+};
+
+/* set during initialization */
+extern int ima_hash_algo __ro_after_init;
+extern int ima_sha1_idx __ro_after_init;
+extern int ima_hash_algo_idx __ro_after_init;
+extern int ima_extra_slots __ro_after_init;
+extern struct ima_algo_desc *ima_algo_array __ro_after_init;
+
+extern int ima_appraise;
+extern struct tpm_chip *ima_tpm_chip;
+extern const char boot_aggregate_name[];
+extern const char boot_aggregate_late_name[];
+
+/* IMA event related data */
+struct ima_event_data {
+	struct ima_iint_cache *iint;
+	struct file *file;
+	const unsigned char *filename;
+	struct evm_ima_xattr_data *xattr_value;
+	int xattr_len;
+	const struct modsig *modsig;
+	const char *violation;
+	const void *buf;
+	int buf_len;
+};
+
+/* IMA template field data definition */
+struct ima_field_data {
+	u8 *data;
+	u32 len;
+};
+
+/* IMA template field definition */
+struct ima_template_field {
+	const char field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN];
+	int (*field_init)(struct ima_event_data *event_data,
+			  struct ima_field_data *field_data);
+	void (*field_show)(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data);
+};
+
+/* IMA template descriptor definition */
+struct ima_template_desc {
+	struct list_head list;
+	char *name;
+	char *fmt;
+	int num_fields;
+	const struct ima_template_field **fields;
+};
+
+struct ima_template_entry {
+	int pcr;
+	struct tpm_digest *digests;
+	struct ima_template_desc *template_desc; /* template descriptor */
+	u32 template_data_len;
+	struct ima_field_data template_data[];	/* template related data */
+};
+
+struct ima_queue_entry {
+	struct hlist_node hnext;	/* place in hash collision list */
+	struct list_head later;		/* place in ima_measurements list */
+	struct ima_template_entry *entry;
+};
+extern struct list_head ima_measurements;	/* list of all measurements */
+extern struct list_head ima_measurements_staged; /* list of staged meas. */
+
+/* Some details preceding the binary serialized measurement list */
+struct ima_kexec_hdr {
+	u16 version;
+	u16 _reserved0;
+	u32 _reserved1;
+	u64 buffer_size;
+	u64 count;
+};
+
+/* IMA iint action cache flags */
+#define IMA_MEASURE		0x00000001
+#define IMA_MEASURED		0x00000002
+#define IMA_APPRAISE		0x00000004
+#define IMA_APPRAISED		0x00000008
+/*#define IMA_COLLECT		0x00000010  do not use this flag */
+#define IMA_COLLECTED		0x00000020
+#define IMA_AUDIT		0x00000040
+#define IMA_AUDITED		0x00000080
+#define IMA_HASH		0x00000100
+#define IMA_HASHED		0x00000200
+
+/* IMA iint policy rule cache flags */
+#define IMA_NONACTION_FLAGS	0xff000000
+#define IMA_DIGSIG_REQUIRED	0x01000000
+#define IMA_PERMIT_DIRECTIO	0x02000000
+#define IMA_NEW_FILE		0x04000000
+#define IMA_SIGV3_REQUIRED	0x08000000
+#define IMA_FAIL_UNVERIFIABLE_SIGS	0x10000000
+#define IMA_MODSIG_ALLOWED	0x20000000
+#define IMA_CHECK_BLACKLIST	0x40000000
+#define IMA_VERITY_REQUIRED	0x80000000
+
+/* Exclude non-action flags which are not rule-specific. */
+#define IMA_NONACTION_RULE_FLAGS	(IMA_NONACTION_FLAGS & ~IMA_NEW_FILE)
+
+#define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
+				 IMA_HASH | IMA_APPRAISE_SUBMASK)
+#define IMA_DONE_MASK		(IMA_MEASURED | IMA_APPRAISED | IMA_AUDITED | \
+				 IMA_HASHED | IMA_COLLECTED | \
+				 IMA_APPRAISED_SUBMASK)
+
+/* IMA iint subaction appraise cache flags */
+#define IMA_FILE_APPRAISE	0x00001000
+#define IMA_FILE_APPRAISED	0x00002000
+#define IMA_MMAP_APPRAISE	0x00004000
+#define IMA_MMAP_APPRAISED	0x00008000
+#define IMA_BPRM_APPRAISE	0x00010000
+#define IMA_BPRM_APPRAISED	0x00020000
+#define IMA_READ_APPRAISE	0x00040000
+#define IMA_READ_APPRAISED	0x00080000
+#define IMA_CREDS_APPRAISE	0x00100000
+#define IMA_CREDS_APPRAISED	0x00200000
+#define IMA_APPRAISE_SUBMASK	(IMA_FILE_APPRAISE | IMA_MMAP_APPRAISE | \
+				 IMA_BPRM_APPRAISE | IMA_READ_APPRAISE | \
+				 IMA_CREDS_APPRAISE)
+#define IMA_APPRAISED_SUBMASK	(IMA_FILE_APPRAISED | IMA_MMAP_APPRAISED | \
+				 IMA_BPRM_APPRAISED | IMA_READ_APPRAISED | \
+				 IMA_CREDS_APPRAISED)
+
+/*
+ * IMA iint cache atomic_flags
+ *
+ * IMA_CHANGE_ATTR - indicates that chATTR() was called (chmod, chown, chgrp)
+ * and file attributes have changed. On file open, it causes IMA to clear
+ * iint->flags to re-evaluate policy and perform IMA functions again.
+ *
+ * IMA_CHANGE_XATTR - indicates that setxattr or removexattr was called and
+ * extended attributes have changed. On file open, it causes IMA to clear
+ * iint->flags IMA_DONE_MASK to re-appraise.
+ *
+ * IMA_UPDATE_XATTR - indicates that security.ima needs to be updated. It is
+ * cleared if file policy changes and no update is needed.
+ *
+ * IMA_DIGSIG - indicates that file security.ima has signature and file
+ * security.ima must not update on file close.
+ *
+ * IMA_MAY_EMIT_TOMTOU - indicates to add Time-of-Measure-Time-of-Use (ToMToU)
+ * integrity violation (a file that is already opened for read is opened for
+ * write) to the measurement list and to also emit an audit message.
+ *
+ * IMA_EMITTED_OPENWRITERS - indicates to add open-writers integrity violation
+ * (a file that is already opened for write is opened for read) to the
+ * measurement list and to also emit an audit message.
+ *
+ */
+#define IMA_CHANGE_XATTR	0
+#define IMA_UPDATE_XATTR	1
+#define IMA_CHANGE_ATTR		2
+#define IMA_DIGSIG		3
+#define IMA_MAY_EMIT_TOMTOU	4
+#define IMA_EMITTED_OPENWRITERS	5
+
+/* IMA integrity metadata associated with an inode */
+struct ima_iint_cache {
+	struct mutex mutex;	/* protects: version, flags, digest */
+	struct integrity_inode_attributes real_inode;
+	unsigned long flags;
+	unsigned long measured_pcrs;
+	unsigned long atomic_flags;
+	enum integrity_status ima_file_status:4;
+	enum integrity_status ima_mmap_status:4;
+	enum integrity_status ima_bprm_status:4;
+	enum integrity_status ima_read_status:4;
+	enum integrity_status ima_creds_status:4;
+	struct ima_digest_data *ima_hash;
+};
+
+extern struct lsm_blob_sizes ima_blob_sizes;
+
+static inline struct ima_iint_cache *
+ima_inode_get_iint(const struct inode *inode)
+{
+	struct ima_iint_cache **iint_sec;
+
+	if (unlikely(!inode->i_security))
+		return NULL;
+
+	iint_sec = inode->i_security + ima_blob_sizes.lbs_inode;
+	return *iint_sec;
+}
+
+static inline void ima_inode_set_iint(const struct inode *inode,
+				      struct ima_iint_cache *iint)
+{
+	struct ima_iint_cache **iint_sec;
+
+	if (unlikely(!inode->i_security))
+		return;
+
+	iint_sec = inode->i_security + ima_blob_sizes.lbs_inode;
+	*iint_sec = iint;
+}
+
+struct ima_iint_cache *ima_iint_find(struct inode *inode);
+struct ima_iint_cache *ima_inode_get(struct inode *inode);
+void ima_inode_free_rcu(void *inode_security);
+void __init ima_iintcache_init(void);
+
+extern const int read_idmap[];
+
+#ifdef CONFIG_HAVE_IMA_KEXEC
+void ima_load_kexec_buffer(void);
+#else
+static inline void ima_load_kexec_buffer(void) {}
+#endif /* CONFIG_HAVE_IMA_KEXEC */
+
+#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
+void ima_post_key_create_or_update(struct key *keyring, struct key *key,
+				   const void *payload, size_t plen,
+				   unsigned long flags, bool create);
+#endif
+
+#ifdef CONFIG_IMA_KEXEC
+void ima_measure_kexec_event(const char *event_name);
+#else
+static inline void ima_measure_kexec_event(const char *event_name) {}
+#endif
+
+/*
+ * The default binary_runtime_measurements list format is defined as the
+ * platform native format.  The canonical format is defined as little-endian.
+ */
+extern bool ima_canonical_fmt;
+
+/* Internal IMA function definitions */
+int ima_init(void);
+int ima_fs_init(void);
+int ima_add_template_entry(struct ima_template_entry *entry, int violation,
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename);
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
+int ima_calc_buffer_hash(const void *buf, loff_t len,
+			 struct ima_digest_data *hash);
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_entry *entry);
+int ima_calc_boot_aggregate(struct ima_digest_data *hash);
+void ima_add_violation(struct file *file, const unsigned char *filename,
+		       struct ima_iint_cache *iint, const char *op,
+		       const char *cause);
+int ima_init_crypto(void);
+void ima_putc(struct seq_file *m, void *data, int datalen);
+void ima_print_digest(struct seq_file *m, u8 *digest, u32 size);
+int template_desc_init_fields(const char *template_fmt,
+			      const struct ima_template_field ***fields,
+			      int *num_fields);
+struct ima_template_desc *ima_template_desc_current(void);
+struct ima_template_desc *ima_template_desc_buf(void);
+struct ima_template_desc *lookup_template_desc(const char *name);
+bool ima_template_has_modsig(const struct ima_template_desc *ima_template);
+int ima_queue_stage(void);
+int ima_queue_staged_delete_all(void);
+int ima_queue_delete_partial(unsigned long req_value);
+int ima_restore_measurement_entry(struct ima_template_entry *entry);
+int ima_restore_measurement_list(loff_t bufsize, void *buf);
+int ima_measurements_show(struct seq_file *m, void *v);
+int __init ima_init_htable(void);
+unsigned long ima_get_binary_runtime_size(enum binary_lists binary_list);
+int ima_init_template(void);
+void ima_init_template_list(void);
+int __init ima_init_digests(void);
+void __init ima_init_reboot_notifier(void);
+int ima_lsm_policy_change(struct notifier_block *nb, unsigned long event,
+			  void *lsm_data);
+
+/*
+ * used to protect h_table and sha_table
+ */
+extern spinlock_t ima_queue_lock;
+
+/* Total number of measurement list records since hard boot. */
+extern atomic_long_t ima_num_records[BINARY__LAST];
+/* Total number of violations since hard boot. */
+extern atomic_long_t ima_num_violations;
+extern struct hlist_head __rcu *ima_htable;
+extern bool ima_flush_htable;
+
+static inline unsigned int ima_hash_key(u8 *digest)
+{
+	/* there is no point in taking a hash of part of a digest */
+	return (digest[0] | digest[1] << 8) % IMA_MEASURE_HTABLE_SIZE;
+}
+
+#define __ima_hooks(hook)				\
+	hook(NONE, none)				\
+	hook(FILE_CHECK, file)				\
+	hook(MMAP_CHECK, mmap)				\
+	hook(MMAP_CHECK_REQPROT, mmap_reqprot)		\
+	hook(BPRM_CHECK, bprm)				\
+	hook(CREDS_CHECK, creds)			\
+	hook(POST_SETATTR, post_setattr)		\
+	hook(MODULE_CHECK, module)			\
+	hook(FIRMWARE_CHECK, firmware)			\
+	hook(KEXEC_KERNEL_CHECK, kexec_kernel)		\
+	hook(KEXEC_INITRAMFS_CHECK, kexec_initramfs)	\
+	hook(POLICY_CHECK, policy)			\
+	hook(KEXEC_CMDLINE, kexec_cmdline)		\
+	hook(KEY_CHECK, key)				\
+	hook(CRITICAL_DATA, critical_data)		\
+	hook(SETXATTR_CHECK, setxattr_check)		\
+	hook(MAX_CHECK, none)
+
+#define __ima_hook_enumify(ENUM, str)	ENUM,
+#define __ima_stringify(arg) (#arg)
+#define __ima_hook_measuring_stringify(ENUM, str) \
+		(__ima_stringify(measuring_ ##str)),
+
+enum ima_hooks {
+	__ima_hooks(__ima_hook_enumify)
+};
+
+static const char * const ima_hooks_measure_str[] = {
+	__ima_hooks(__ima_hook_measuring_stringify)
+};
+
+static inline const char *func_measure_str(enum ima_hooks func)
+{
+	if (func >= MAX_CHECK)
+		return ima_hooks_measure_str[NONE];
+
+	return ima_hooks_measure_str[func];
+}
+
+extern const char *const func_tokens[];
+
+struct modsig;
+
+#ifdef CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS
+/*
+ * To track keys that need to be measured.
+ */
+struct ima_key_entry {
+	struct list_head list;
+	void *payload;
+	size_t payload_len;
+	char *keyring_name;
+};
+void ima_init_key_queue(void);
+bool ima_should_queue_key(void);
+bool ima_queue_key(struct key *keyring, const void *payload,
+		   size_t payload_len);
+void ima_process_queued_keys(void);
+#else
+static inline void ima_init_key_queue(void) {}
+static inline bool ima_should_queue_key(void) { return false; }
+static inline bool ima_queue_key(struct key *keyring,
+				 const void *payload,
+				 size_t payload_len) { return false; }
+static inline void ima_process_queued_keys(void) {}
+#endif /* CONFIG_IMA_QUEUE_EARLY_BOOT_KEYS */
+
+/* LIM API function definitions */
+int ima_get_action(struct mnt_idmap *idmap, struct inode *inode,
+		   const struct cred *cred, struct lsm_prop *prop, int mask,
+		   enum ima_hooks func, int *pcr,
+		   struct ima_template_desc **template_desc,
+		   const char *func_data, unsigned int *allowed_algos);
+int ima_must_measure(struct inode *inode, int mask, enum ima_hooks func);
+int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file,
+			    void *buf, loff_t size, enum hash_algo algo,
+			    struct modsig *modsig);
+void ima_store_measurement(struct ima_iint_cache *iint, struct file *file,
+			   const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len, const struct modsig *modsig, int pcr,
+			   struct ima_template_desc *template_desc);
+int process_buffer_measurement(struct mnt_idmap *idmap,
+			       struct inode *inode, const void *buf, int size,
+			       const char *eventname, enum ima_hooks func,
+			       int pcr, const char *func_data,
+			       bool buf_hash, u8 *digest, size_t digest_len);
+void ima_audit_measurement(struct ima_iint_cache *iint,
+			   const unsigned char *filename);
+int ima_alloc_init_template(struct ima_event_data *event_data,
+			    struct ima_template_entry **entry,
+			    struct ima_template_desc *template_desc);
+int ima_store_template(struct ima_template_entry *entry, int violation,
+		       struct inode *inode,
+		       const unsigned char *filename, int pcr);
+void ima_free_template_entry(struct ima_template_entry *entry);
+const char *ima_d_path(const struct path *path, char **pathbuf, char *filename);
+
+/* IMA policy related functions */
+int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode,
+		     const struct cred *cred, struct lsm_prop *prop,
+		     enum ima_hooks func, int mask, int flags, int *pcr,
+		     struct ima_template_desc **template_desc,
+		     const char *func_data, unsigned int *allowed_algos);
+void ima_init_policy(void);
+void ima_update_policy(void);
+void ima_update_policy_flags(void);
+ssize_t ima_parse_add_rule(char *);
+void ima_delete_rules(void);
+int ima_check_policy(void);
+void *ima_policy_start(struct seq_file *m, loff_t *pos);
+void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos);
+void ima_policy_stop(struct seq_file *m, void *v);
+int ima_policy_show(struct seq_file *m, void *v);
+void ima_measure_loaded_policy(void);
+int ima_measure_raw_policy(const char *buf, size_t buf_len);
+
+/* Appraise integrity measurements */
+#define IMA_APPRAISE_ENFORCE	0x01
+#define IMA_APPRAISE_FIX	0x02
+#define IMA_APPRAISE_LOG	0x04
+#define IMA_APPRAISE_MODULES	0x08
+#define IMA_APPRAISE_FIRMWARE	0x10
+#define IMA_APPRAISE_POLICY	0x20
+#define IMA_APPRAISE_KEXEC	0x40
+
+#ifdef CONFIG_IMA_APPRAISE
+int ima_check_blacklist(struct ima_iint_cache *iint,
+			const struct modsig *modsig, int pcr);
+int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint,
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len, const struct modsig *modsig,
+			     bool bprm_is_check);
+int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode,
+		      int mask, enum ima_hooks func);
+void ima_update_xattr(struct ima_iint_cache *iint, struct file *file);
+enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint,
+					   enum ima_hooks func);
+enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value,
+				 int xattr_len);
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value, int xattr_len);
+void __init init_ima_appraise_lsm(const struct lsm_id *lsmid);
+
+#else
+static inline int ima_check_blacklist(struct ima_iint_cache *iint,
+				      const struct modsig *modsig, int pcr)
+{
+	return 0;
+}
+
+static inline int ima_appraise_measurement(enum ima_hooks func,
+					   struct ima_iint_cache *iint,
+					   struct file *file,
+					   const unsigned char *filename,
+					   struct evm_ima_xattr_data *xattr_value,
+					   int xattr_len,
+					   const struct modsig *modsig,
+					   bool bprm_is_check)
+{
+	return INTEGRITY_UNKNOWN;
+}
+
+static inline int ima_must_appraise(struct mnt_idmap *idmap,
+				    struct inode *inode, int mask,
+				    enum ima_hooks func)
+{
+	return 0;
+}
+
+static inline void ima_update_xattr(struct ima_iint_cache *iint,
+				    struct file *file)
+{
+}
+
+static inline enum integrity_status
+ima_get_cache_status(struct ima_iint_cache *iint, enum ima_hooks func)
+{
+	return INTEGRITY_UNKNOWN;
+}
+
+static inline enum hash_algo
+ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len)
+{
+	return ima_hash_algo;
+}
+
+static inline int ima_read_xattr(struct dentry *dentry,
+				 struct evm_ima_xattr_data **xattr_value,
+				 int xattr_len)
+{
+	return 0;
+}
+
+static inline void __init init_ima_appraise_lsm(const struct lsm_id *lsmid)
+{
+}
+
+#endif /* CONFIG_IMA_APPRAISE */
+
+#ifdef CONFIG_IMA_APPRAISE_MODSIG
+int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len,
+		    struct modsig **modsig);
+void ima_collect_modsig(struct modsig *modsig, const void *buf, loff_t size);
+int ima_get_modsig_digest(const struct modsig *modsig, enum hash_algo *algo,
+			  const u8 **digest, u32 *digest_size);
+int ima_get_raw_modsig(const struct modsig *modsig, const void **data,
+		       u32 *data_len);
+void ima_free_modsig(struct modsig *modsig);
+#else
+static inline int ima_read_modsig(enum ima_hooks func, const void *buf,
+				  loff_t buf_len, struct modsig **modsig)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void ima_collect_modsig(struct modsig *modsig, const void *buf,
+				      loff_t size)
+{
+}
+
+static inline int ima_get_modsig_digest(const struct modsig *modsig,
+					enum hash_algo *algo, const u8 **digest,
+					u32 *digest_size)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int ima_get_raw_modsig(const struct modsig *modsig,
+				     const void **data, u32 *data_len)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void ima_free_modsig(struct modsig *modsig)
+{
+}
+#endif /* CONFIG_IMA_APPRAISE_MODSIG */
+
+/* LSM based policy rules require audit */
+#ifdef CONFIG_IMA_LSM_RULES
+
+#define ima_filter_rule_init security_audit_rule_init
+#define ima_filter_rule_free security_audit_rule_free
+#define ima_filter_rule_match security_audit_rule_match
+
+#else
+
+static inline int ima_filter_rule_init(u32 field, u32 op, char *rulestr,
+				       void **lsmrule, gfp_t gfp)
+{
+	return -EINVAL;
+}
+
+static inline void ima_filter_rule_free(void *lsmrule)
+{
+}
+
+static inline int ima_filter_rule_match(struct lsm_prop *prop, u32 field, u32 op,
+					void *lsmrule)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IMA_LSM_RULES */
+
+#ifdef	CONFIG_IMA_READ_POLICY
+#define	POLICY_FILE_FLAGS	(S_IWUSR | S_IRUSR)
+#else
+#define	POLICY_FILE_FLAGS	S_IWUSR
+#endif /* CONFIG_IMA_READ_POLICY */
+
+#endif /* __LINUX_IMA_H */
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
new file mode 100644
index 000000000..122d127e1
--- /dev/null
+++ b/security/integrity/ima/ima_api.c
@@ -0,0 +1,470 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 IBM Corporation
+ *
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima_api.c
+ *	Implements must_appraise_or_measure, collect_measurement,
+ *	appraise_measurement, store_measurement and store_template.
+ */
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/hex.h>
+#include <linux/xattr.h>
+#include <linux/evm.h>
+#include <linux/fsverity.h>
+
+#include "ima.h"
+
+/*
+ * ima_free_template_entry - free an existing template entry
+ */
+void ima_free_template_entry(struct ima_template_entry *entry)
+{
+	int i;
+
+	for (i = 0; i < entry->template_desc->num_fields; i++)
+		kfree(entry->template_data[i].data);
+
+	kfree(entry->digests);
+	kfree(entry);
+}
+
+/*
+ * ima_alloc_init_template - create and initialize a new template entry
+ */
+int ima_alloc_init_template(struct ima_event_data *event_data,
+			    struct ima_template_entry **entry,
+			    struct ima_template_desc *desc)
+{
+	struct ima_template_desc *template_desc;
+	struct tpm_digest *digests;
+	int i, result = 0;
+
+	if (desc)
+		template_desc = desc;
+	else
+		template_desc = ima_template_desc_current();
+
+	*entry = kzalloc_flex(**entry, template_data, template_desc->num_fields,
+			      GFP_NOFS);
+	if (!*entry)
+		return -ENOMEM;
+
+	digests = kzalloc_objs(*digests,
+			       NR_BANKS(ima_tpm_chip) + ima_extra_slots,
+			       GFP_NOFS);
+	if (!digests) {
+		kfree(*entry);
+		*entry = NULL;
+		return -ENOMEM;
+	}
+
+	(*entry)->digests = digests;
+	(*entry)->template_desc = template_desc;
+	for (i = 0; i < template_desc->num_fields; i++) {
+		const struct ima_template_field *field =
+			template_desc->fields[i];
+		u32 len;
+
+		result = field->field_init(event_data,
+					   &((*entry)->template_data[i]));
+		if (result != 0)
+			goto out;
+
+		len = (*entry)->template_data[i].len;
+		(*entry)->template_data_len += sizeof(len);
+		(*entry)->template_data_len += len;
+	}
+	return 0;
+out:
+	ima_free_template_entry(*entry);
+	*entry = NULL;
+	return result;
+}
+
+/*
+ * ima_store_template - store ima template measurements
+ *
+ * Calculate the hash of a template entry, add the template entry
+ * to an ordered list of measurement entries maintained inside the kernel,
+ * and also update the aggregate integrity value (maintained inside the
+ * configured TPM PCR) over the hashes of the current list of measurement
+ * entries.
+ *
+ * Applications retrieve the current kernel-held measurement list through
+ * the securityfs entries in /sys/kernel/security/ima. The signed aggregate
+ * TPM PCR (called quote) can be retrieved using a TPM user space library
+ * and is used to validate the measurement list.
+ *
+ * Returns 0 on success, error code otherwise
+ */
+int ima_store_template(struct ima_template_entry *entry,
+		       int violation, struct inode *inode,
+		       const unsigned char *filename, int pcr)
+{
+	static const char op[] = "add_template_measure";
+	static const char audit_cause[] = "hashing_error";
+	char *template_name = entry->template_desc->name;
+	int result;
+
+	if (!violation) {
+		result = ima_calc_field_array_hash(&entry->template_data[0],
+						   entry);
+		if (result < 0) {
+			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
+					    template_name, op,
+					    audit_cause, result, 0);
+			return result;
+		}
+	}
+	entry->pcr = pcr;
+	result = ima_add_template_entry(entry, violation, op, inode, filename);
+	return result;
+}
+
+/*
+ * ima_add_violation - add violation to measurement list.
+ *
+ * Violations are flagged in the measurement list with zero hash values.
+ * By extending the PCR with 0xFF's instead of with zeroes, the PCR
+ * value is invalidated.
+ */
+void ima_add_violation(struct file *file, const unsigned char *filename,
+		       struct ima_iint_cache *iint, const char *op,
+		       const char *cause)
+{
+	struct ima_template_entry *entry;
+	struct inode *inode = file_inode(file);
+	struct ima_event_data event_data = { .iint = iint,
+					     .file = file,
+					     .filename = filename,
+					     .violation = cause };
+	int violation = 1;
+	int result;
+
+	/* can overflow, only indicator */
+	atomic_long_inc(&ima_num_violations);
+
+	result = ima_alloc_init_template(&event_data, &entry, NULL);
+	if (result < 0) {
+		result = -ENOMEM;
+		goto err_out;
+	}
+	result = ima_store_template(entry, violation, inode,
+				    filename, CONFIG_IMA_MEASURE_PCR_IDX);
+	if (result < 0)
+		ima_free_template_entry(entry);
+err_out:
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+			    op, cause, result, 0);
+}
+
+/**
+ * ima_get_action - appraise & measure decision based on policy.
+ * @idmap: idmap of the mount the inode was found from
+ * @inode: pointer to the inode associated with the object being validated
+ * @cred: pointer to credentials structure to validate
+ * @prop: properties of the task being validated
+ * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXEC,
+ *        MAY_APPEND)
+ * @func: caller identifier
+ * @pcr: pointer filled in if matched measure policy sets pcr=
+ * @template_desc: pointer filled in if matched measure policy sets template=
+ * @func_data: func specific data, may be NULL
+ * @allowed_algos: allowlist of hash algorithms for the IMA xattr
+ *
+ * The policy is defined in terms of keypairs:
+ *		subj=, obj=, type=, func=, mask=, fsmagic=
+ *	subj,obj, and type: are LSM specific.
+ *	func: FILE_CHECK | BPRM_CHECK | CREDS_CHECK | MMAP_CHECK | MODULE_CHECK
+ *	| KEXEC_CMDLINE | KEY_CHECK | CRITICAL_DATA | SETXATTR_CHECK
+ *	| MMAP_CHECK_REQPROT
+ *	mask: contains the permission mask
+ *	fsmagic: hex value
+ *
+ * Returns IMA_MEASURE, IMA_APPRAISE mask.
+ *
+ */
+int ima_get_action(struct mnt_idmap *idmap, struct inode *inode,
+		   const struct cred *cred, struct lsm_prop *prop, int mask,
+		   enum ima_hooks func, int *pcr,
+		   struct ima_template_desc **template_desc,
+		   const char *func_data, unsigned int *allowed_algos)
+{
+	int flags = IMA_MEASURE | IMA_AUDIT | IMA_APPRAISE | IMA_HASH;
+
+	flags &= ima_policy_flag;
+
+	return ima_match_policy(idmap, inode, cred, prop, func, mask,
+				flags, pcr, template_desc, func_data,
+				allowed_algos);
+}
+
+static bool ima_get_verity_digest(struct ima_iint_cache *iint,
+				  struct inode *inode,
+				  struct ima_max_digest_data *hash)
+{
+	enum hash_algo alg;
+	int digest_len;
+
+	/*
+	 * On failure, 'measure' policy rules will result in a file data
+	 * hash containing 0's.
+	 */
+	digest_len = fsverity_get_digest(inode, hash->digest, NULL, &alg);
+	if (digest_len == 0)
+		return false;
+
+	/*
+	 * Unlike in the case of actually calculating the file hash, in
+	 * the fsverity case regardless of the hash algorithm, return
+	 * the verity digest to be included in the measurement list. A
+	 * mismatch between the verity algorithm and the xattr signature
+	 * algorithm, if one exists, will be detected later.
+	 */
+	hash->hdr.algo = alg;
+	hash->hdr.length = digest_len;
+	return true;
+}
+
+/*
+ * ima_collect_measurement - collect file measurement
+ *
+ * Calculate the file hash, if it doesn't already exist,
+ * storing the measurement and i_version in the iint.
+ *
+ * Must be called with iint->mutex held.
+ *
+ * Return 0 on success, error code otherwise
+ */
+int ima_collect_measurement(struct ima_iint_cache *iint, struct file *file,
+			    void *buf, loff_t size, enum hash_algo algo,
+			    struct modsig *modsig)
+{
+	const char *audit_cause = "failed";
+	struct inode *inode = file_inode(file);
+	struct inode *real_inode = d_real_inode(file_dentry(file));
+	struct ima_max_digest_data hash;
+	struct ima_digest_data *hash_hdr = container_of(&hash.hdr,
+						struct ima_digest_data, hdr);
+	struct name_snapshot filename;
+	struct kstat stat;
+	int result = 0;
+	int length;
+	void *tmpbuf;
+	u64 i_version = 0;
+
+	/*
+	 * Always collect the modsig, because IMA might have already collected
+	 * the file digest without collecting the modsig in a previous
+	 * measurement rule.
+	 */
+	if (modsig)
+		ima_collect_modsig(modsig, buf, size);
+
+	if (iint->flags & IMA_COLLECTED)
+		goto out;
+
+	/*
+	 * Detect file change based on STATX_CHANGE_COOKIE, when supported,
+	 * and fallback to detecting file change based on i_version.
+	 *
+	 * On filesystems which did not support i_version, support was
+	 * originally limited to an initial measurement/appraisal/audit,
+	 * but was later modified to assume the file changed.
+	 */
+	result = vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE,
+				   AT_STATX_SYNC_AS_STAT);
+	if (!result && (stat.result_mask & STATX_CHANGE_COOKIE))
+		i_version = stat.change_cookie;
+	else if (IS_I_VERSION(real_inode))
+		i_version = inode_peek_iversion(real_inode);
+
+	hash.hdr.algo = algo;
+	hash.hdr.length = hash_digest_size[algo];
+
+	/* Initialize hash digest to 0's in case of failure */
+	memset(&hash.digest, 0, sizeof(hash.digest));
+
+	if (iint->flags & IMA_VERITY_REQUIRED) {
+		if (!ima_get_verity_digest(iint, inode, &hash)) {
+			audit_cause = "no-verity-digest";
+			result = -ENODATA;
+		}
+	} else if (buf) {
+		result = ima_calc_buffer_hash(buf, size, hash_hdr);
+	} else {
+		result = ima_calc_file_hash(file, hash_hdr);
+	}
+
+	if (result && result != -EBADF && result != -EINVAL)
+		goto out;
+
+	length = sizeof(hash.hdr) + hash.hdr.length;
+	tmpbuf = krealloc(iint->ima_hash, length, GFP_NOFS);
+	if (!tmpbuf) {
+		result = -ENOMEM;
+		goto out;
+	}
+
+	iint->ima_hash = tmpbuf;
+	memcpy(iint->ima_hash, &hash, length);
+	if (real_inode == inode)
+		iint->real_inode.version = i_version;
+	else
+		integrity_inode_attrs_store(&iint->real_inode, i_version,
+					    real_inode);
+
+	/* Possibly temporary failure due to type of read (eg. O_DIRECT) */
+	if (!result)
+		iint->flags |= IMA_COLLECTED;
+out:
+	if (result) {
+		if (file->f_flags & O_DIRECT)
+			audit_cause = "failed(directio)";
+
+		take_dentry_name_snapshot(&filename, file->f_path.dentry);
+
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+				    filename.name.name, "collect_data",
+				    audit_cause, result, 0);
+
+		release_dentry_name_snapshot(&filename);
+	}
+	return result;
+}
+
+/*
+ * ima_store_measurement - store file measurement
+ *
+ * Create an "ima" template and then store the template by calling
+ * ima_store_template.
+ *
+ * We only get here if the inode has not already been measured,
+ * but the measurement could already exist:
+ *	- multiple copies of the same file on either the same or
+ *	  different filesystems.
+ *	- the inode was previously flushed as well as the iint info,
+ *	  containing the hashing info.
+ *
+ * Must be called with iint->mutex held.
+ */
+void ima_store_measurement(struct ima_iint_cache *iint, struct file *file,
+			   const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len, const struct modsig *modsig, int pcr,
+			   struct ima_template_desc *template_desc)
+{
+	static const char op[] = "add_template_measure";
+	static const char audit_cause[] = "ENOMEM";
+	int result = -ENOMEM;
+	struct inode *inode = file_inode(file);
+	struct ima_template_entry *entry;
+	struct ima_event_data event_data = { .iint = iint,
+					     .file = file,
+					     .filename = filename,
+					     .xattr_value = xattr_value,
+					     .xattr_len = xattr_len,
+					     .modsig = modsig };
+	int violation = 0;
+
+	/*
+	 * We still need to store the measurement in the case of MODSIG because
+	 * we only have its contents to put in the list at the time of
+	 * appraisal, but a file measurement from earlier might already exist in
+	 * the measurement list.
+	 */
+	if (iint->measured_pcrs & (0x1 << pcr) && !modsig)
+		return;
+
+	result = ima_alloc_init_template(&event_data, &entry, template_desc);
+	if (result < 0) {
+		integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+				    op, audit_cause, result, 0);
+		return;
+	}
+
+	result = ima_store_template(entry, violation, inode, filename, pcr);
+	if ((!result || result == -EEXIST) && !(file->f_flags & O_DIRECT)) {
+		iint->flags |= IMA_MEASURED;
+		iint->measured_pcrs |= (0x1 << pcr);
+	}
+	if (result < 0)
+		ima_free_template_entry(entry);
+}
+
+void ima_audit_measurement(struct ima_iint_cache *iint,
+			   const unsigned char *filename)
+{
+	struct audit_buffer *ab;
+	char *hash;
+	const char *algo_name = hash_algo_name[iint->ima_hash->algo];
+	int i;
+
+	if (iint->flags & IMA_AUDITED)
+		return;
+
+	hash = kzalloc((iint->ima_hash->length * 2) + 1, GFP_KERNEL);
+	if (!hash)
+		return;
+
+	for (i = 0; i < iint->ima_hash->length; i++)
+		hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]);
+	hash[i * 2] = '\0';
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL,
+			     AUDIT_INTEGRITY_RULE);
+	if (!ab)
+		goto out;
+
+	audit_log_format(ab, "file=");
+	audit_log_untrustedstring(ab, filename);
+	audit_log_format(ab, " hash=\"%s:%s\"", algo_name, hash);
+
+	audit_log_task_info(ab);
+	audit_log_end(ab);
+
+	iint->flags |= IMA_AUDITED;
+out:
+	kfree(hash);
+	return;
+}
+
+/*
+ * ima_d_path - return a pointer to the full pathname
+ *
+ * Attempt to return a pointer to the full pathname for use in the
+ * IMA measurement list, IMA audit records, and auditing logs.
+ *
+ * On failure, return a pointer to a copy of the filename, not dname.
+ * Returning a pointer to dname, could result in using the pointer
+ * after the memory has been freed.
+ */
+const char *ima_d_path(const struct path *path, char **pathbuf, char *namebuf)
+{
+	struct name_snapshot filename;
+	char *pathname = NULL;
+
+	*pathbuf = __getname();
+	if (*pathbuf) {
+		pathname = d_absolute_path(path, *pathbuf, PATH_MAX);
+		if (IS_ERR(pathname)) {
+			__putname(*pathbuf);
+			*pathbuf = NULL;
+			pathname = NULL;
+		}
+	}
+
+	if (!pathname) {
+		take_dentry_name_snapshot(&filename, path->dentry);
+		strscpy(namebuf, filename.name.name, NAME_MAX);
+		release_dentry_name_snapshot(&filename);
+
+		pathname = namebuf;
+	}
+
+	return pathname;
+}
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
new file mode 100644
index 000000000..ced2e131b
--- /dev/null
+++ b/security/integrity/ima/ima_appraise.c
@@ -0,0 +1,836 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2011 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/binfmts.h>
+#include <linux/fs.h>
+#include <linux/xattr.h>
+#include <linux/magic.h>
+#include <linux/ima.h>
+#include <linux/evm.h>
+#include <linux/fsverity.h>
+#include <keys/system_keyring.h>
+#include <uapi/linux/fsverity.h>
+
+#include "ima.h"
+
+#ifdef CONFIG_IMA_APPRAISE_BOOTPARAM
+static char *ima_appraise_cmdline_default __initdata;
+core_param(ima_appraise, ima_appraise_cmdline_default, charp, 0);
+
+void __init ima_appraise_parse_cmdline(void)
+{
+	const char *str = ima_appraise_cmdline_default;
+	bool sb_state = arch_get_secureboot();
+	int appraisal_state = ima_appraise;
+
+	if (!str)
+		return;
+
+	if (strncmp(str, "off", 3) == 0)
+		appraisal_state = 0;
+	else if (strncmp(str, "log", 3) == 0)
+		appraisal_state = IMA_APPRAISE_LOG;
+	else if (strncmp(str, "fix", 3) == 0)
+		appraisal_state = IMA_APPRAISE_FIX;
+	else if (strncmp(str, "enforce", 7) == 0)
+		appraisal_state = IMA_APPRAISE_ENFORCE;
+	else
+		pr_err("invalid \"%s\" appraise option", str);
+
+	/* If appraisal state was changed, but secure boot is enabled,
+	 * keep its default */
+	if (sb_state) {
+		if (!(appraisal_state & IMA_APPRAISE_ENFORCE))
+			pr_info("Secure boot enabled: ignoring ima_appraise=%s option",
+				str);
+	} else {
+		ima_appraise = appraisal_state;
+	}
+}
+#endif
+
+/*
+ * is_ima_appraise_enabled - return appraise status
+ *
+ * Only return enabled, if not in ima_appraise="fix" or "log" modes.
+ */
+bool is_ima_appraise_enabled(void)
+{
+	return ima_appraise & IMA_APPRAISE_ENFORCE;
+}
+
+/*
+ * ima_must_appraise - set appraise flag
+ *
+ * Return 1 to appraise or hash
+ */
+int ima_must_appraise(struct mnt_idmap *idmap, struct inode *inode,
+		      int mask, enum ima_hooks func)
+{
+	struct lsm_prop prop;
+
+	if (!ima_appraise)
+		return 0;
+
+	security_current_getlsmprop_subj(&prop);
+	return ima_match_policy(idmap, inode, current_cred(), &prop,
+				func, mask, IMA_APPRAISE | IMA_HASH, NULL,
+				NULL, NULL, NULL);
+}
+
+static int ima_fix_xattr(struct dentry *dentry, struct ima_iint_cache *iint)
+{
+	int rc, offset;
+	u8 algo = iint->ima_hash->algo;
+
+	if (IS_RDONLY(d_inode(dentry)))
+		return -EROFS;
+	if (IS_IMMUTABLE(d_inode(dentry)))
+		return -EPERM;
+
+	if (algo <= HASH_ALGO_SHA1) {
+		offset = 1;
+		iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST;
+	} else {
+		offset = 0;
+		iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG;
+		iint->ima_hash->xattr.ng.algo = algo;
+	}
+	rc = __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_IMA,
+				   &iint->ima_hash->xattr.data[offset],
+				   (sizeof(iint->ima_hash->xattr) - offset) +
+				   iint->ima_hash->length, 0);
+	return rc;
+}
+
+/* Return specific func appraised cached result */
+enum integrity_status ima_get_cache_status(struct ima_iint_cache *iint,
+					   enum ima_hooks func)
+{
+	switch (func) {
+	case MMAP_CHECK:
+	case MMAP_CHECK_REQPROT:
+		return iint->ima_mmap_status;
+	case BPRM_CHECK:
+		return iint->ima_bprm_status;
+	case CREDS_CHECK:
+		return iint->ima_creds_status;
+	case FILE_CHECK:
+	case POST_SETATTR:
+		return iint->ima_file_status;
+	case MODULE_CHECK ... MAX_CHECK - 1:
+	default:
+		return iint->ima_read_status;
+	}
+}
+
+static void ima_set_cache_status(struct ima_iint_cache *iint,
+				 enum ima_hooks func,
+				 enum integrity_status status)
+{
+	switch (func) {
+	case MMAP_CHECK:
+	case MMAP_CHECK_REQPROT:
+		iint->ima_mmap_status = status;
+		break;
+	case BPRM_CHECK:
+		iint->ima_bprm_status = status;
+		break;
+	case CREDS_CHECK:
+		iint->ima_creds_status = status;
+		break;
+	case FILE_CHECK:
+	case POST_SETATTR:
+		iint->ima_file_status = status;
+		break;
+	case MODULE_CHECK ... MAX_CHECK - 1:
+	default:
+		iint->ima_read_status = status;
+		break;
+	}
+}
+
+static void ima_cache_flags(struct ima_iint_cache *iint, enum ima_hooks func)
+{
+	switch (func) {
+	case MMAP_CHECK:
+	case MMAP_CHECK_REQPROT:
+		iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED);
+		break;
+	case BPRM_CHECK:
+		iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED);
+		break;
+	case CREDS_CHECK:
+		iint->flags |= (IMA_CREDS_APPRAISED | IMA_APPRAISED);
+		break;
+	case FILE_CHECK:
+	case POST_SETATTR:
+		iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED);
+		break;
+	case MODULE_CHECK ... MAX_CHECK - 1:
+	default:
+		iint->flags |= (IMA_READ_APPRAISED | IMA_APPRAISED);
+		break;
+	}
+}
+
+enum hash_algo ima_get_hash_algo(const struct evm_ima_xattr_data *xattr_value,
+				 int xattr_len)
+{
+	struct signature_v2_hdr *sig;
+	enum hash_algo ret;
+
+	if (!xattr_value || xattr_len < 2)
+		/* return default hash algo */
+		return ima_hash_algo;
+
+	switch (xattr_value->type) {
+	case IMA_VERITY_DIGSIG:
+		sig = (typeof(sig))xattr_value;
+		if (sig->version != 3 || xattr_len <= sizeof(*sig) ||
+		    sig->hash_algo >= HASH_ALGO__LAST)
+			return ima_hash_algo;
+		return sig->hash_algo;
+	case EVM_IMA_XATTR_DIGSIG:
+		sig = (typeof(sig))xattr_value;
+		if ((sig->version != 2 && sig->version != 3) ||
+		    xattr_len <= sizeof(*sig) ||
+		    sig->hash_algo >= HASH_ALGO__LAST)
+			return ima_hash_algo;
+		return sig->hash_algo;
+	case IMA_XATTR_DIGEST_NG:
+		/* first byte contains algorithm id */
+		ret = xattr_value->data[0];
+		if (ret < HASH_ALGO__LAST)
+			return ret;
+		break;
+	case IMA_XATTR_DIGEST:
+		/* this is for backward compatibility */
+		if (xattr_len == 21) {
+			unsigned int zero = 0;
+			if (!memcmp(&xattr_value->data[16], &zero, 4))
+				return HASH_ALGO_MD5;
+			else
+				return HASH_ALGO_SHA1;
+		} else if (xattr_len == 17)
+			return HASH_ALGO_MD5;
+		break;
+	}
+
+	/* return default hash algo */
+	return ima_hash_algo;
+}
+
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value, int xattr_len)
+{
+	int ret;
+
+	ret = vfs_getxattr_alloc(&nop_mnt_idmap, dentry, XATTR_NAME_IMA,
+				 (char **)xattr_value, xattr_len, GFP_NOFS);
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
+	return ret;
+}
+
+/*
+ * xattr_verify - verify xattr digest or signature
+ *
+ * Verify whether the hash or signature matches the file contents.
+ *
+ * Return 0 on success, error code otherwise.
+ */
+static int xattr_verify(enum ima_hooks func, struct ima_iint_cache *iint,
+			struct evm_ima_xattr_data *xattr_value, int xattr_len,
+			enum integrity_status *status, const char **cause)
+{
+	struct signature_v2_hdr *sig;
+	int rc = -EINVAL, hash_start = 0;
+	int mask;
+
+	switch (xattr_value->type) {
+	case IMA_XATTR_DIGEST_NG:
+		/* first byte contains algorithm id */
+		hash_start = 1;
+		fallthrough;
+	case IMA_XATTR_DIGEST:
+		if (*status != INTEGRITY_PASS_IMMUTABLE) {
+			if (iint->flags & IMA_DIGSIG_REQUIRED) {
+				if (iint->flags & IMA_VERITY_REQUIRED)
+					*cause = "verity-signature-required";
+				else
+					*cause = "IMA-signature-required";
+				*status = INTEGRITY_FAIL;
+				break;
+			}
+			clear_bit(IMA_DIGSIG, &iint->atomic_flags);
+		} else {
+			set_bit(IMA_DIGSIG, &iint->atomic_flags);
+		}
+		/*
+		 * Use addition, not subtraction: sizeof() forces unsigned
+		 * math and a short xattr_len would wrap around, bypassing
+		 * this bounds check.
+		 */
+		if (xattr_len >= (int)sizeof(xattr_value->type) + hash_start +
+				(int)iint->ima_hash->length)
+			/*
+			 * xattr length may be longer. md5 hash in previous
+			 * version occupied 20 bytes in xattr, instead of 16
+			 */
+			rc = memcmp(&xattr_value->data[hash_start],
+				    iint->ima_hash->digest,
+				    iint->ima_hash->length);
+		else
+			rc = -EINVAL;
+		if (rc) {
+			*cause = "invalid-hash";
+			*status = INTEGRITY_FAIL;
+			break;
+		}
+		*status = INTEGRITY_PASS;
+		break;
+	case EVM_IMA_XATTR_DIGSIG:
+		set_bit(IMA_DIGSIG, &iint->atomic_flags);
+
+		mask = IMA_DIGSIG_REQUIRED | IMA_VERITY_REQUIRED;
+		if ((iint->flags & mask) == mask) {
+			*cause = "verity-signature-required";
+			*status = INTEGRITY_FAIL;
+			break;
+		}
+
+		sig = (typeof(sig))xattr_value;
+		if (sig->version > 3) {
+			*cause = "invalid-signature-version";
+			*status = INTEGRITY_FAIL;
+			break;
+		}
+
+		if ((iint->flags & IMA_SIGV3_REQUIRED) && sig->version != 3) {
+			*cause = "IMA-sigv3-required";
+			*status = INTEGRITY_FAIL;
+			break;
+		}
+
+		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
+					     (const char *)xattr_value,
+					     xattr_len,
+					     iint->ima_hash->digest,
+					     iint->ima_hash->length,
+					     iint->ima_hash->algo);
+		if (rc == -EOPNOTSUPP) {
+			*status = INTEGRITY_UNKNOWN;
+			break;
+		}
+		if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc &&
+		    func == KEXEC_KERNEL_CHECK)
+			rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM,
+						     (const char *)xattr_value,
+						     xattr_len,
+						     iint->ima_hash->digest,
+						     iint->ima_hash->length,
+						     iint->ima_hash->algo);
+
+		if (rc) {
+			*cause = "invalid-signature";
+			*status = INTEGRITY_FAIL;
+		} else {
+			*status = INTEGRITY_PASS;
+		}
+		break;
+	case IMA_VERITY_DIGSIG:
+		set_bit(IMA_DIGSIG, &iint->atomic_flags);
+
+		if (iint->flags & IMA_DIGSIG_REQUIRED) {
+			if (!(iint->flags & IMA_VERITY_REQUIRED)) {
+				*cause = "IMA-signature-required";
+				*status = INTEGRITY_FAIL;
+				break;
+			}
+		}
+
+		sig = (typeof(sig))xattr_value;
+		if (sig->version != 3) {
+			*cause = "invalid-signature-version";
+			*status = INTEGRITY_FAIL;
+			break;
+		}
+
+		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
+					     (const char *)xattr_value,
+					     xattr_len,
+					     iint->ima_hash->digest,
+					     iint->ima_hash->length,
+					     iint->ima_hash->algo);
+		if (rc == -EOPNOTSUPP) {
+			*status = INTEGRITY_UNKNOWN;
+			break;
+		} else if (rc) {
+			*cause = "invalid-verity-signature";
+			*status = INTEGRITY_FAIL;
+		} else {
+			*status = INTEGRITY_PASS;
+		}
+
+		break;
+	default:
+		*status = INTEGRITY_UNKNOWN;
+		*cause = "unknown-ima-data";
+		break;
+	}
+
+	return rc;
+}
+
+/*
+ * modsig_verify - verify modsig signature
+ *
+ * Verify whether the signature matches the file contents.
+ *
+ * Return 0 on success, error code otherwise.
+ */
+static int modsig_verify(enum ima_hooks func, const struct modsig *modsig,
+			 enum integrity_status *status, const char **cause)
+{
+	int rc;
+
+	rc = integrity_modsig_verify(INTEGRITY_KEYRING_IMA, modsig);
+	if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc &&
+	    func == KEXEC_KERNEL_CHECK)
+		rc = integrity_modsig_verify(INTEGRITY_KEYRING_PLATFORM,
+					     modsig);
+	if (rc) {
+		*cause = "invalid-signature";
+		*status = INTEGRITY_FAIL;
+	} else {
+		*status = INTEGRITY_PASS;
+	}
+
+	return rc;
+}
+
+/*
+ * ima_check_blacklist - determine if the binary is blacklisted.
+ *
+ * Add the hash of the blacklisted binary to the measurement list, based
+ * on policy.
+ *
+ * Returns -EPERM if the hash is blacklisted.
+ */
+int ima_check_blacklist(struct ima_iint_cache *iint,
+			const struct modsig *modsig, int pcr)
+{
+	enum hash_algo hash_algo;
+	const u8 *digest = NULL;
+	u32 digestsize = 0;
+	int rc = 0;
+
+	if (!(iint->flags & IMA_CHECK_BLACKLIST))
+		return 0;
+
+	if (iint->flags & IMA_MODSIG_ALLOWED && modsig) {
+		ima_get_modsig_digest(modsig, &hash_algo, &digest, &digestsize);
+
+		rc = is_binary_blacklisted(digest, digestsize);
+	} else if (iint->flags & IMA_DIGSIG_REQUIRED && iint->ima_hash)
+		rc = is_binary_blacklisted(iint->ima_hash->digest, iint->ima_hash->length);
+
+	if ((rc == -EPERM) && (iint->flags & IMA_MEASURE))
+		process_buffer_measurement(&nop_mnt_idmap, NULL, digest, digestsize,
+					   "blacklisted-hash", NONE,
+					   pcr, NULL, false, NULL, 0);
+
+	return rc;
+}
+
+/*
+ * ima_appraise_measurement - appraise file measurement
+ *
+ * Call evm_verifyxattr() to verify the integrity of 'security.ima'.
+ * Assuming success, compare the xattr hash with the collected measurement.
+ *
+ * Return 0 on success, error code otherwise
+ */
+int ima_appraise_measurement(enum ima_hooks func, struct ima_iint_cache *iint,
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len, const struct modsig *modsig,
+			     bool bprm_is_check)
+{
+	static const char op[] = "appraise_data";
+	int audit_msgno = AUDIT_INTEGRITY_DATA;
+	const char *cause = "unknown";
+	struct dentry *dentry = file_dentry(file);
+	struct inode *inode = d_backing_inode(dentry);
+	enum integrity_status status = INTEGRITY_UNKNOWN;
+	int rc = xattr_len;
+	bool try_modsig = iint->flags & IMA_MODSIG_ALLOWED && modsig;
+
+	/* If not appraising a modsig, we need an xattr. */
+	if (!(inode->i_opflags & IOP_XATTR) && !try_modsig)
+		return INTEGRITY_UNKNOWN;
+
+	/*
+	 * Unlike any of the other LSM hooks where the kernel enforces file
+	 * integrity, enforcing file integrity for the bprm_creds_for_exec()
+	 * LSM hook with the AT_EXECVE_CHECK flag is left up to the discretion
+	 * of the script interpreter(userspace). Differentiate kernel and
+	 * userspace enforced integrity audit messages.
+	 */
+	if (bprm_is_check)
+		audit_msgno = AUDIT_INTEGRITY_USERSPACE;
+
+	/* If reading the xattr failed and there's no modsig, error out. */
+	if (rc <= 0 && !try_modsig) {
+		if (rc && rc != -ENODATA)
+			goto out;
+
+		if (iint->flags & IMA_DIGSIG_REQUIRED) {
+			if (iint->flags & IMA_VERITY_REQUIRED)
+				cause = "verity-signature-required";
+			else
+				cause = "IMA-signature-required";
+		} else {
+			cause = "missing-hash";
+		}
+
+		status = INTEGRITY_NOLABEL;
+		if (file->f_mode & FMODE_CREATED)
+			iint->flags |= IMA_NEW_FILE;
+		if ((iint->flags & IMA_NEW_FILE) &&
+		    (!(iint->flags & IMA_DIGSIG_REQUIRED) ||
+		     (inode->i_size == 0)))
+			status = INTEGRITY_PASS;
+		goto out;
+	}
+
+	status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value,
+				 rc < 0 ? 0 : rc);
+	switch (status) {
+	case INTEGRITY_PASS:
+	case INTEGRITY_PASS_IMMUTABLE:
+	case INTEGRITY_UNKNOWN:
+		break;
+	case INTEGRITY_NOXATTRS:	/* No EVM protected xattrs. */
+		/* It's fine not to have xattrs when using a modsig. */
+		if (try_modsig)
+			break;
+		fallthrough;
+	case INTEGRITY_NOLABEL:		/* No security.evm xattr. */
+		cause = "missing-HMAC";
+		goto out;
+	case INTEGRITY_FAIL_IMMUTABLE:
+		set_bit(IMA_DIGSIG, &iint->atomic_flags);
+		cause = "invalid-fail-immutable";
+		goto out;
+	case INTEGRITY_FAIL:		/* Invalid HMAC/signature. */
+		cause = "invalid-HMAC";
+		goto out;
+	default:
+		WARN_ONCE(true, "Unexpected integrity status %d\n", status);
+	}
+
+	if (xattr_value)
+		rc = xattr_verify(func, iint, xattr_value, xattr_len, &status,
+				  &cause);
+
+	/*
+	 * If we have a modsig and either no imasig or the imasig's key isn't
+	 * known, then try verifying the modsig.
+	 */
+	if (try_modsig &&
+	    (!xattr_value || xattr_value->type == IMA_XATTR_DIGEST_NG ||
+	     rc == -ENOKEY))
+		rc = modsig_verify(func, modsig, &status, &cause);
+
+out:
+	/*
+	 * File signatures on some filesystems can not be properly verified.
+	 * When such filesystems are mounted by an untrusted mounter or on a
+	 * system not willing to accept such a risk, fail the file signature
+	 * verification.
+	 */
+	if ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) &&
+	    ((inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) ||
+	     (iint->flags & IMA_FAIL_UNVERIFIABLE_SIGS))) {
+		status = INTEGRITY_FAIL;
+		cause = "unverifiable-signature";
+		integrity_audit_msg(audit_msgno, inode, filename,
+				    op, cause, rc, 0);
+	} else if (status != INTEGRITY_PASS) {
+		/* Fix mode, but don't replace file signatures. */
+		if ((ima_appraise & IMA_APPRAISE_FIX) && !try_modsig &&
+		    (!xattr_value ||
+		     xattr_value->type != EVM_IMA_XATTR_DIGSIG)) {
+			if (!ima_fix_xattr(dentry, iint))
+				status = INTEGRITY_PASS;
+		} else if (status == INTEGRITY_NOLABEL) {
+			if (!evm_fix_hmac(dentry, XATTR_NAME_IMA,
+					  (const char *)xattr_value,
+					  xattr_len))
+				status = INTEGRITY_PASS;
+		}
+
+		/*
+		 * Permit new files with file/EVM portable signatures, but
+		 * without data.
+		 */
+		if (inode->i_size == 0 && iint->flags & IMA_NEW_FILE &&
+		    test_bit(IMA_DIGSIG, &iint->atomic_flags)) {
+			status = INTEGRITY_PASS;
+		}
+
+		integrity_audit_msg(audit_msgno, inode, filename,
+				    op, cause, rc, 0);
+	} else {
+		ima_cache_flags(iint, func);
+	}
+
+	ima_set_cache_status(iint, func, status);
+	return status;
+}
+
+/*
+ * ima_update_xattr - update 'security.ima' hash value
+ */
+void ima_update_xattr(struct ima_iint_cache *iint, struct file *file)
+{
+	struct dentry *dentry = file_dentry(file);
+	int rc = 0;
+
+	/* do not collect and update hash for digital signatures */
+	if (test_bit(IMA_DIGSIG, &iint->atomic_flags))
+		return;
+
+	if ((iint->ima_file_status != INTEGRITY_PASS) &&
+	    !(iint->flags & IMA_HASH))
+		return;
+
+	rc = ima_collect_measurement(iint, file, NULL, 0, ima_hash_algo, NULL);
+	if (rc < 0)
+		return;
+
+	inode_lock(file_inode(file));
+	ima_fix_xattr(dentry, iint);
+	inode_unlock(file_inode(file));
+}
+
+/**
+ * ima_inode_post_setattr - reflect file metadata changes
+ * @idmap:  idmap of the mount the inode was found from
+ * @dentry: pointer to the affected dentry
+ * @ia_valid: for the UID and GID status
+ *
+ * Changes to a dentry's metadata might result in needing to appraise.
+ *
+ * This function is called from notify_change(), which expects the caller
+ * to lock the inode's i_mutex.
+ */
+static void ima_inode_post_setattr(struct mnt_idmap *idmap,
+				   struct dentry *dentry, int ia_valid)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct ima_iint_cache *iint;
+	int action;
+
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)
+	    || !(inode->i_opflags & IOP_XATTR))
+		return;
+
+	action = ima_must_appraise(idmap, inode, MAY_ACCESS, POST_SETATTR);
+	iint = ima_iint_find(inode);
+	if (iint) {
+		set_bit(IMA_CHANGE_ATTR, &iint->atomic_flags);
+		if (!action)
+			clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
+	}
+}
+
+/*
+ * ima_protect_xattr - protect 'security.ima'
+ *
+ * Ensure that not just anyone can modify or remove 'security.ima'.
+ */
+static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name,
+			     const void *xattr_value, size_t xattr_value_len)
+{
+	if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * ima_reset_appraise_flags - reset ima_iint_cache flags
+ *
+ * @digsig: whether to clear/set IMA_DIGSIG flag, tristate values
+ *          0: clear IMA_DIGSIG
+ *          1: set IMA_DIGSIG
+ *         -1: don't change IMA_DIGSIG
+ *
+ */
+static void ima_reset_appraise_flags(struct inode *inode, int digsig)
+{
+	struct ima_iint_cache *iint;
+
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = ima_iint_find(inode);
+	if (!iint)
+		return;
+	iint->measured_pcrs = 0;
+	set_bit(IMA_CHANGE_XATTR, &iint->atomic_flags);
+	if (digsig == 1)
+		set_bit(IMA_DIGSIG, &iint->atomic_flags);
+	else if (digsig == 0)
+		clear_bit(IMA_DIGSIG, &iint->atomic_flags);
+}
+
+/**
+ * validate_hash_algo() - Block setxattr with unsupported hash algorithms
+ * @dentry: object of the setxattr()
+ * @xattr_value: userland supplied xattr value
+ * @xattr_value_len: length of xattr_value
+ *
+ * The xattr value is mapped to its hash algorithm, and this algorithm
+ * must be built in the kernel for the setxattr to be allowed.
+ *
+ * Emit an audit message when the algorithm is invalid.
+ *
+ * Return: 0 on success, else an error.
+ */
+static int validate_hash_algo(struct dentry *dentry,
+			      const struct evm_ima_xattr_data *xattr_value,
+			      size_t xattr_value_len)
+{
+	char *path = NULL, *pathbuf = NULL;
+	enum hash_algo xattr_hash_algo;
+	const char *errmsg = "unavailable-hash-algorithm";
+	unsigned int allowed_hashes;
+
+	xattr_hash_algo = ima_get_hash_algo(xattr_value, xattr_value_len);
+
+	allowed_hashes = atomic_read(&ima_setxattr_allowed_hash_algorithms);
+
+	if (allowed_hashes) {
+		/* success if the algorithm is allowed in the ima policy */
+		if (allowed_hashes & (1U << xattr_hash_algo))
+			return 0;
+
+		/*
+		 * We use a different audit message when the hash algorithm
+		 * is denied by a policy rule, instead of not being built
+		 * in the kernel image
+		 */
+		errmsg = "denied-hash-algorithm";
+	} else {
+		if (likely(xattr_hash_algo == ima_hash_algo))
+			return 0;
+
+		/* allow any xattr using an algorithm built in the kernel */
+		if (crypto_has_alg(hash_algo_name[xattr_hash_algo], 0, 0))
+			return 0;
+	}
+
+	pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!pathbuf)
+		return -EACCES;
+
+	path = dentry_path(dentry, pathbuf, PATH_MAX);
+
+	integrity_audit_msg(AUDIT_INTEGRITY_DATA, d_inode(dentry), path,
+			    "set_data", errmsg, -EACCES, 0);
+
+	kfree(pathbuf);
+
+	return -EACCES;
+}
+
+static int ima_inode_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			      const char *xattr_name, const void *xattr_value,
+			      size_t xattr_value_len, int flags)
+{
+	const struct evm_ima_xattr_data *xvalue = xattr_value;
+	int digsig = 0;
+	int result;
+	int err;
+
+	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
+				   xattr_value_len);
+	if (result == 1) {
+		if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST))
+			return -EINVAL;
+
+		err = validate_hash_algo(dentry, xvalue, xattr_value_len);
+		if (err)
+			return err;
+
+		digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG);
+	} else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) {
+		digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG);
+	} else {
+		digsig = -1;
+	}
+	if (result == 1 || evm_revalidate_status(xattr_name)) {
+		ima_reset_appraise_flags(d_backing_inode(dentry), digsig);
+		if (result == 1)
+			result = 0;
+	}
+	return result;
+}
+
+static int ima_inode_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+			     const char *acl_name, struct posix_acl *kacl)
+{
+	if (evm_revalidate_status(acl_name))
+		ima_reset_appraise_flags(d_backing_inode(dentry), -1);
+
+	return 0;
+}
+
+static int ima_inode_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
+				 const char *xattr_name)
+{
+	int result, digsig = -1;
+
+	result = ima_protect_xattr(dentry, xattr_name, NULL, 0);
+	if (result == 1 || evm_revalidate_status(xattr_name)) {
+		if (!strcmp(xattr_name, XATTR_NAME_IMA))
+			digsig = 0;
+		ima_reset_appraise_flags(d_backing_inode(dentry), digsig);
+		if (result == 1)
+			result = 0;
+	}
+	return result;
+}
+
+static int ima_inode_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+				const char *acl_name)
+{
+	return ima_inode_set_acl(idmap, dentry, acl_name, NULL);
+}
+
+static struct security_hook_list ima_appraise_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(inode_post_setattr, ima_inode_post_setattr),
+	LSM_HOOK_INIT(inode_setxattr, ima_inode_setxattr),
+	LSM_HOOK_INIT(inode_set_acl, ima_inode_set_acl),
+	LSM_HOOK_INIT(inode_removexattr, ima_inode_removexattr),
+	LSM_HOOK_INIT(inode_remove_acl, ima_inode_remove_acl),
+};
+
+void __init init_ima_appraise_lsm(const struct lsm_id *lsmid)
+{
+	security_add_hooks(ima_appraise_hooks, ARRAY_SIZE(ima_appraise_hooks),
+			   lsmid);
+}
diff --git a/security/integrity/ima/ima_asymmetric_keys.c b/security/integrity/ima/ima_asymmetric_keys.c
new file mode 100644
index 000000000..caacfe686
--- /dev/null
+++ b/security/integrity/ima/ima_asymmetric_keys.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Microsoft Corporation
+ *
+ * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
+ *
+ * File: ima_asymmetric_keys.c
+ *       Defines an IMA hook to measure asymmetric keys on key
+ *       create or update.
+ */
+
+#include <keys/asymmetric-type.h>
+#include <linux/user_namespace.h>
+#include <linux/ima.h>
+#include "ima.h"
+
+/**
+ * ima_post_key_create_or_update - measure asymmetric keys
+ * @keyring: keyring to which the key is linked to
+ * @key: created or updated key
+ * @payload: The data used to instantiate or update the key.
+ * @payload_len: The length of @payload.
+ * @flags: key flags
+ * @create: flag indicating whether the key was created or updated
+ *
+ * Keys can only be measured, not appraised.
+ * The payload data used to instantiate or update the key is measured.
+ */
+void ima_post_key_create_or_update(struct key *keyring, struct key *key,
+				   const void *payload, size_t payload_len,
+				   unsigned long flags, bool create)
+{
+	bool queued = false;
+
+	/* Only asymmetric keys are handled by this hook. */
+	if (key->type != &key_type_asymmetric)
+		return;
+
+	if (!payload || (payload_len == 0))
+		return;
+
+	if (ima_should_queue_key())
+		queued = ima_queue_key(keyring, payload, payload_len);
+
+	if (queued)
+		return;
+
+	/*
+	 * keyring->description points to the name of the keyring
+	 * (such as ".builtin_trusted_keys", ".ima", etc.) to
+	 * which the given key is linked to.
+	 *
+	 * The name of the keyring is passed in the "eventname"
+	 * parameter to process_buffer_measurement() and is set
+	 * in the "eventname" field in ima_event_data for
+	 * the key measurement IMA event.
+	 *
+	 * The name of the keyring is also passed in the "keyring"
+	 * parameter to process_buffer_measurement() to check
+	 * if the IMA policy is configured to measure a key linked
+	 * to the given keyring.
+	 */
+	process_buffer_measurement(&nop_mnt_idmap, NULL, payload, payload_len,
+				   keyring->description, KEY_CHECK, 0,
+				   keyring->description, false, NULL, 0);
+}
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
new file mode 100644
index 000000000..0d72b4824
--- /dev/null
+++ b/security/integrity/ima/ima_crypto.c
@@ -0,0 +1,519 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * File: ima_crypto.c
+ *	Calculates md5/sha1 file hash, template hash, boot-aggreate hash
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <crypto/hash.h>
+
+#include "ima.h"
+
+static struct crypto_shash *ima_shash_tfm;
+
+int ima_sha1_idx __ro_after_init;
+int ima_hash_algo_idx __ro_after_init;
+/*
+ * Additional number of slots reserved, as needed, for SHA1
+ * and IMA default algo.
+ */
+int ima_extra_slots __ro_after_init;
+
+struct ima_algo_desc *ima_algo_array __ro_after_init;
+
+static int __init ima_init_ima_crypto(void)
+{
+	long rc;
+
+	ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0);
+	if (IS_ERR(ima_shash_tfm)) {
+		rc = PTR_ERR(ima_shash_tfm);
+		pr_err("Can not allocate %s (reason: %ld)\n",
+		       hash_algo_name[ima_hash_algo], rc);
+		return rc;
+	}
+	pr_info("Allocated hash algorithm: %s\n",
+		hash_algo_name[ima_hash_algo]);
+	return 0;
+}
+
+static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo)
+{
+	struct crypto_shash *tfm = ima_shash_tfm;
+	int rc, i;
+
+	if (algo < 0 || algo >= HASH_ALGO__LAST)
+		algo = ima_hash_algo;
+
+	if (algo == ima_hash_algo)
+		return tfm;
+
+	for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++)
+		if (ima_algo_array[i].tfm && ima_algo_array[i].algo == algo)
+			return ima_algo_array[i].tfm;
+
+	tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
+	if (IS_ERR(tfm)) {
+		rc = PTR_ERR(tfm);
+		pr_err("Can not allocate %s (reason: %d)\n",
+		       hash_algo_name[algo], rc);
+	}
+	return tfm;
+}
+
+int __init ima_init_crypto(void)
+{
+	unsigned int digest_size;
+	enum hash_algo algo;
+	long rc;
+	int i;
+
+	rc = ima_init_ima_crypto();
+	if (rc)
+		return rc;
+
+	ima_sha1_idx = -1;
+	ima_hash_algo_idx = -1;
+
+	for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) {
+		algo = ima_tpm_chip->allocated_banks[i].crypto_id;
+		if (algo == HASH_ALGO_SHA1)
+			ima_sha1_idx = i;
+
+		if (algo == ima_hash_algo)
+			ima_hash_algo_idx = i;
+	}
+
+	if (ima_sha1_idx < 0) {
+		ima_sha1_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++;
+		if (ima_hash_algo == HASH_ALGO_SHA1)
+			ima_hash_algo_idx = ima_sha1_idx;
+	}
+
+	if (ima_hash_algo_idx < 0)
+		ima_hash_algo_idx = NR_BANKS(ima_tpm_chip) + ima_extra_slots++;
+
+	ima_algo_array = kzalloc_objs(*ima_algo_array,
+				      NR_BANKS(ima_tpm_chip) + ima_extra_slots);
+	if (!ima_algo_array) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < NR_BANKS(ima_tpm_chip); i++) {
+		algo = ima_tpm_chip->allocated_banks[i].crypto_id;
+		digest_size = ima_tpm_chip->allocated_banks[i].digest_size;
+		ima_algo_array[i].algo = algo;
+		ima_algo_array[i].digest_size = digest_size;
+
+		/* unknown TPM algorithm */
+		if (algo == HASH_ALGO__LAST)
+			continue;
+
+		if (algo == ima_hash_algo) {
+			ima_algo_array[i].tfm = ima_shash_tfm;
+			continue;
+		}
+
+		ima_algo_array[i].tfm = ima_alloc_tfm(algo);
+		if (IS_ERR(ima_algo_array[i].tfm)) {
+			if (algo == HASH_ALGO_SHA1) {
+				rc = PTR_ERR(ima_algo_array[i].tfm);
+				ima_algo_array[i].tfm = NULL;
+				goto out_array;
+			}
+
+			ima_algo_array[i].tfm = NULL;
+		}
+	}
+
+	if (ima_sha1_idx >= NR_BANKS(ima_tpm_chip)) {
+		if (ima_hash_algo == HASH_ALGO_SHA1) {
+			ima_algo_array[ima_sha1_idx].tfm = ima_shash_tfm;
+		} else {
+			ima_algo_array[ima_sha1_idx].tfm =
+						ima_alloc_tfm(HASH_ALGO_SHA1);
+			if (IS_ERR(ima_algo_array[ima_sha1_idx].tfm)) {
+				rc = PTR_ERR(ima_algo_array[ima_sha1_idx].tfm);
+				goto out_array;
+			}
+		}
+
+		ima_algo_array[ima_sha1_idx].algo = HASH_ALGO_SHA1;
+		ima_algo_array[ima_sha1_idx].digest_size = SHA1_DIGEST_SIZE;
+	}
+
+	if (ima_hash_algo_idx >= NR_BANKS(ima_tpm_chip) &&
+	    ima_hash_algo_idx != ima_sha1_idx) {
+		digest_size = hash_digest_size[ima_hash_algo];
+		ima_algo_array[ima_hash_algo_idx].tfm = ima_shash_tfm;
+		ima_algo_array[ima_hash_algo_idx].algo = ima_hash_algo;
+		ima_algo_array[ima_hash_algo_idx].digest_size = digest_size;
+	}
+
+	return 0;
+out_array:
+	for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) {
+		if (!ima_algo_array[i].tfm ||
+		    ima_algo_array[i].tfm == ima_shash_tfm)
+			continue;
+
+		crypto_free_shash(ima_algo_array[i].tfm);
+	}
+	kfree(ima_algo_array);
+out:
+	crypto_free_shash(ima_shash_tfm);
+	return rc;
+}
+
+static void ima_free_tfm(struct crypto_shash *tfm)
+{
+	int i;
+
+	if (tfm == ima_shash_tfm)
+		return;
+
+	for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++)
+		if (ima_algo_array[i].tfm == tfm)
+			return;
+
+	crypto_free_shash(tfm);
+}
+
+static int ima_calc_file_hash_tfm(struct file *file,
+				  struct ima_digest_data *hash,
+				  struct crypto_shash *tfm)
+{
+	loff_t i_size, offset = 0;
+	char *rbuf;
+	int rc;
+	SHASH_DESC_ON_STACK(shash, tfm);
+
+	shash->tfm = tfm;
+
+	hash->length = crypto_shash_digestsize(tfm);
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	i_size = i_size_read(file_inode(file));
+
+	if (i_size == 0)
+		goto out;
+
+	rbuf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!rbuf)
+		return -ENOMEM;
+
+	while (offset < i_size) {
+		int rbuf_len;
+
+		rbuf_len = integrity_kernel_read(file, offset, rbuf, PAGE_SIZE);
+		if (rbuf_len < 0) {
+			rc = rbuf_len;
+			break;
+		}
+		if (rbuf_len == 0) {	/* unexpected EOF */
+			rc = -EINVAL;
+			break;
+		}
+		offset += rbuf_len;
+
+		rc = crypto_shash_update(shash, rbuf, rbuf_len);
+		if (rc)
+			break;
+	}
+	kfree(rbuf);
+out:
+	if (!rc)
+		rc = crypto_shash_final(shash, hash->digest);
+	return rc;
+}
+
+/*
+ * ima_calc_file_hash - calculate file hash
+ */
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
+{
+	int rc;
+	struct file *f = file;
+	bool new_file_instance = false;
+	struct crypto_shash *tfm;
+
+	/*
+	 * For consistency, fail file's opened with the O_DIRECT flag on
+	 * filesystems mounted with/without DAX option.
+	 */
+	if (file->f_flags & O_DIRECT) {
+		hash->length = hash_digest_size[ima_hash_algo];
+		hash->algo = ima_hash_algo;
+		return -EINVAL;
+	}
+
+	/* Open a new file instance in O_RDONLY if we cannot read */
+	if (!(file->f_mode & FMODE_READ)) {
+		int flags = file->f_flags & ~(O_WRONLY | O_APPEND |
+				O_TRUNC | O_CREAT | O_NOCTTY | O_EXCL);
+		flags |= O_RDONLY;
+		f = dentry_open(&file->f_path, flags, file->f_cred);
+		if (IS_ERR(f))
+			return PTR_ERR(f);
+
+		new_file_instance = true;
+	}
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm)) {
+		rc = PTR_ERR(tfm);
+	} else {
+		rc = ima_calc_file_hash_tfm(f, hash, tfm);
+		ima_free_tfm(tfm);
+	}
+	if (new_file_instance)
+		fput(f);
+	return rc;
+}
+
+/*
+ * Calculate the hash of template data
+ */
+static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
+					 struct ima_template_entry *entry,
+					 int tfm_idx)
+{
+	SHASH_DESC_ON_STACK(shash, ima_algo_array[tfm_idx].tfm);
+	struct ima_template_desc *td = entry->template_desc;
+	int num_fields = entry->template_desc->num_fields;
+	int rc, i;
+
+	shash->tfm = ima_algo_array[tfm_idx].tfm;
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	for (i = 0; i < num_fields; i++) {
+		u8 buffer[IMA_EVENT_NAME_LEN_MAX + 1] = { 0 };
+		u8 *data_to_hash = field_data[i].data;
+		u32 datalen = field_data[i].len;
+		u32 datalen_to_hash = !ima_canonical_fmt ?
+				datalen : (__force u32)cpu_to_le32(datalen);
+
+		if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) {
+			rc = crypto_shash_update(shash,
+						(const u8 *) &datalen_to_hash,
+						sizeof(datalen_to_hash));
+			if (rc)
+				break;
+		} else if (strcmp(td->fields[i]->field_id, "n") == 0) {
+			memcpy(buffer, data_to_hash, datalen);
+			data_to_hash = buffer;
+			datalen = IMA_EVENT_NAME_LEN_MAX + 1;
+		}
+		rc = crypto_shash_update(shash, data_to_hash, datalen);
+		if (rc)
+			break;
+	}
+
+	if (!rc)
+		rc = crypto_shash_final(shash, entry->digests[tfm_idx].digest);
+
+	return rc;
+}
+
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_entry *entry)
+{
+	u16 alg_id;
+	int rc, i;
+
+	rc = ima_calc_field_array_hash_tfm(field_data, entry, ima_sha1_idx);
+	if (rc)
+		return rc;
+
+	entry->digests[ima_sha1_idx].alg_id = TPM_ALG_SHA1;
+
+	for (i = 0; i < NR_BANKS(ima_tpm_chip) + ima_extra_slots; i++) {
+		if (i == ima_sha1_idx)
+			continue;
+
+		if (i < NR_BANKS(ima_tpm_chip)) {
+			alg_id = ima_tpm_chip->allocated_banks[i].alg_id;
+			entry->digests[i].alg_id = alg_id;
+		}
+
+		/* for unmapped TPM algorithms digest is still a padded SHA1 */
+		if (!ima_algo_array[i].tfm) {
+			memcpy(entry->digests[i].digest,
+			       entry->digests[ima_sha1_idx].digest,
+			       TPM_DIGEST_SIZE);
+			continue;
+		}
+
+		rc = ima_calc_field_array_hash_tfm(field_data, entry, i);
+		if (rc)
+			return rc;
+	}
+	return rc;
+}
+
+static int calc_buffer_shash_tfm(const void *buf, loff_t size,
+				struct ima_digest_data *hash,
+				struct crypto_shash *tfm)
+{
+	SHASH_DESC_ON_STACK(shash, tfm);
+	unsigned int len;
+	int rc;
+
+	shash->tfm = tfm;
+
+	hash->length = crypto_shash_digestsize(tfm);
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	while (size) {
+		len = size < PAGE_SIZE ? size : PAGE_SIZE;
+		rc = crypto_shash_update(shash, buf, len);
+		if (rc)
+			break;
+		buf += len;
+		size -= len;
+	}
+
+	if (!rc)
+		rc = crypto_shash_final(shash, hash->digest);
+	return rc;
+}
+
+int ima_calc_buffer_hash(const void *buf, loff_t len,
+			 struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	rc = calc_buffer_shash_tfm(buf, len, hash, tfm);
+
+	ima_free_tfm(tfm);
+	return rc;
+}
+
+static void ima_pcrread(u32 idx, struct tpm_digest *d)
+{
+	if (!ima_tpm_chip)
+		return;
+
+	if (tpm_pcr_read(ima_tpm_chip, idx, d) != 0)
+		pr_err("Error Communicating to TPM chip\n");
+}
+
+/*
+ * The boot_aggregate is a cumulative hash over TPM registers 0 - 7.  With
+ * TPM 1.2 the boot_aggregate was based on reading the SHA1 PCRs, but with
+ * TPM 2.0 hash agility, TPM chips could support multiple TPM PCR banks,
+ * allowing firmware to configure and enable different banks.
+ *
+ * Knowing which TPM bank is read to calculate the boot_aggregate digest
+ * needs to be conveyed to a verifier.  For this reason, use the same
+ * hash algorithm for reading the TPM PCRs as for calculating the boot
+ * aggregate digest as stored in the measurement list.
+ */
+static int ima_calc_boot_aggregate_tfm(char *digest, u16 alg_id,
+				       struct crypto_shash *tfm)
+{
+	struct tpm_digest d = { .alg_id = alg_id, .digest = {0} };
+	int rc;
+	u32 i;
+	SHASH_DESC_ON_STACK(shash, tfm);
+
+	shash->tfm = tfm;
+
+	pr_devel("calculating the boot-aggregate based on TPM bank: %04x\n",
+		 d.alg_id);
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	/* cumulative digest over TPM registers 0-7 */
+	for (i = TPM_PCR0; i < TPM_PCR8; i++) {
+		ima_pcrread(i, &d);
+		/* now accumulate with current aggregate */
+		rc = crypto_shash_update(shash, d.digest,
+					 crypto_shash_digestsize(tfm));
+		if (rc != 0)
+			return rc;
+	}
+	/*
+	 * Extend cumulative digest over TPM registers 8-9, which contain
+	 * measurement for the kernel command line (reg. 8) and image (reg. 9)
+	 * in a typical PCR allocation. Registers 8-9 are only included in
+	 * non-SHA1 boot_aggregate digests to avoid ambiguity.
+	 */
+	if (alg_id != TPM_ALG_SHA1) {
+		for (i = TPM_PCR8; i < TPM_PCR10; i++) {
+			ima_pcrread(i, &d);
+			rc = crypto_shash_update(shash, d.digest,
+						crypto_shash_digestsize(tfm));
+		}
+	}
+	if (!rc)
+		rc = crypto_shash_final(shash, digest);
+	return rc;
+}
+
+int ima_calc_boot_aggregate(struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	u16 crypto_id, alg_id;
+	int rc, i, bank_idx = -1;
+
+	for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) {
+		crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id;
+		if (crypto_id == hash->algo) {
+			bank_idx = i;
+			break;
+		}
+
+		if (crypto_id == HASH_ALGO_SHA256)
+			bank_idx = i;
+
+		if (bank_idx == -1 && crypto_id == HASH_ALGO_SHA1)
+			bank_idx = i;
+	}
+
+	if (bank_idx == -1) {
+		pr_err("No suitable TPM algorithm for boot aggregate\n");
+		return 0;
+	}
+
+	hash->algo = ima_tpm_chip->allocated_banks[bank_idx].crypto_id;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	hash->length = crypto_shash_digestsize(tfm);
+	alg_id = ima_tpm_chip->allocated_banks[bank_idx].alg_id;
+	rc = ima_calc_boot_aggregate_tfm(hash->digest, alg_id, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}
diff --git a/security/integrity/ima/ima_efi.c b/security/integrity/ima/ima_efi.c
new file mode 100644
index 000000000..be7911009
--- /dev/null
+++ b/security/integrity/ima/ima_efi.c
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2018 IBM Corporation
+ */
+#include <linux/module.h>
+#include <linux/ima.h>
+#include <linux/secure_boot.h>
+
+/* secureboot arch rules */
+static const char * const sb_arch_rules[] = {
+#if !IS_ENABLED(CONFIG_KEXEC_SIG)
+	"appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig",
+#endif /* CONFIG_KEXEC_SIG */
+	"measure func=KEXEC_KERNEL_CHECK",
+#if !IS_ENABLED(CONFIG_MODULE_SIG)
+	"appraise func=MODULE_CHECK appraise_type=imasig",
+#endif
+#if IS_ENABLED(CONFIG_INTEGRITY_MACHINE_KEYRING) && IS_ENABLED(CONFIG_IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY)
+	"appraise func=POLICY_CHECK appraise_type=imasig",
+#else
+	"measure func=CRITICAL_DATA label=ima_policy",
+#endif
+	"measure func=MODULE_CHECK",
+	NULL
+};
+
+const char * const *arch_get_ima_policy(void)
+{
+	if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_get_secureboot()) {
+		set_module_sig_enforced();
+		set_kexec_sig_enforced();
+		return sb_arch_rules;
+	}
+	return NULL;
+}
diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
new file mode 100644
index 000000000..2a0bca554
--- /dev/null
+++ b/security/integrity/ima/ima_fs.c
@@ -0,0 +1,856 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Kylene Hall <kjhall@us.ibm.com>
+ * Reiner Sailer <sailer@us.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima_fs.c
+ *	implemenents security file system for reporting
+ *	current measurement list and IMA statistics
+ */
+
+#include <linux/fcntl.h>
+#include <linux/kernel_read_file.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/parser.h>
+#include <linux/vmalloc.h>
+
+#include "ima.h"
+
+/*
+ * Requests:
+ * 'A\n': stage the entire measurements list
+ * 'D\n': delete all staged measurements
+ * '[1, ULONG_MAX]\n' delete N measurements records
+ */
+#define STAGED_REQ_LENGTH 21
+
+/* lock for protecting concurrent IMA policy updates */
+DEFINE_MUTEX(ima_write_mutex);
+
+static DEFINE_MUTEX(ima_measure_mutex);
+static long ima_measure_users;
+static struct task_struct *measure_writer;
+static long measure_writer_extra_writes;
+
+bool ima_canonical_fmt;
+static int __init default_canonical_fmt_setup(char *str)
+{
+#ifdef __BIG_ENDIAN
+	ima_canonical_fmt = true;
+#endif
+	return 1;
+}
+__setup("ima_canonical_fmt", default_canonical_fmt_setup);
+
+static int valid_policy = 1;
+
+static ssize_t ima_show_counter(char __user *buf, size_t count, loff_t *ppos,
+				atomic_long_t *val)
+{
+	char tmpbuf[32];	/* greater than largest 'long' string value */
+	ssize_t len;
+
+	len = scnprintf(tmpbuf, sizeof(tmpbuf), "%li\n", atomic_long_read(val));
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, len);
+}
+
+static ssize_t ima_show_num_violations(struct file *filp, char __user *buf,
+				       size_t count, loff_t *ppos)
+{
+	return ima_show_counter(buf, count, ppos, &ima_num_violations);
+}
+
+static const struct file_operations ima_num_violations_ops = {
+	.read = ima_show_num_violations,
+	.llseek = generic_file_llseek,
+};
+
+static ssize_t ima_show_measurements_count(struct file *filp,
+					   char __user *buf,
+					   size_t count, loff_t *ppos)
+{
+	return ima_show_counter(buf, count, ppos, &ima_num_records[BINARY]);
+}
+
+static const struct file_operations ima_measurements_count_ops = {
+	.read = ima_show_measurements_count,
+	.llseek = generic_file_llseek,
+};
+
+/* returns pointer to hlist_node */
+static void *_ima_measurements_start(struct seq_file *m, loff_t *pos,
+				     struct list_head *head)
+{
+	loff_t l = *pos;
+	struct ima_queue_entry *qe;
+
+	/* we need a lock since pos could point beyond last element */
+	rcu_read_lock();
+	list_for_each_entry_rcu(qe, head, later) {
+		if (!l--) {
+			rcu_read_unlock();
+			return qe;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+static void *ima_measurements_start(struct seq_file *m, loff_t *pos)
+{
+	return _ima_measurements_start(m, pos, &ima_measurements);
+}
+
+static void *ima_measurements_staged_start(struct seq_file *m, loff_t *pos)
+{
+	return _ima_measurements_start(m, pos, &ima_measurements_staged);
+}
+
+static void *_ima_measurements_next(struct seq_file *m, void *v, loff_t *pos,
+				    struct list_head *head)
+{
+	struct ima_queue_entry *qe = v;
+
+	/* lock protects when reading beyond last element
+	 * against concurrent list-extension
+	 */
+	rcu_read_lock();
+	qe = list_entry_rcu(qe->later.next, struct ima_queue_entry, later);
+	rcu_read_unlock();
+	(*pos)++;
+
+	return (&qe->later == head) ? NULL : qe;
+}
+
+static void *ima_measurements_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	return _ima_measurements_next(m, v, pos, &ima_measurements);
+}
+
+static void *ima_measurements_staged_next(struct seq_file *m, void *v,
+					  loff_t *pos)
+{
+	return _ima_measurements_next(m, v, pos, &ima_measurements_staged);
+}
+
+static void ima_measurements_stop(struct seq_file *m, void *v)
+{
+}
+
+void ima_putc(struct seq_file *m, void *data, int datalen)
+{
+	while (datalen--)
+		seq_putc(m, *(char *)data++);
+}
+
+/* print format:
+ *       32bit-le=pcr#
+ *       char[n]=template digest
+ *       32bit-le=template name size
+ *       char[n]=template name
+ *       [eventdata length]
+ *       eventdata[n]=template specific data
+ */
+int ima_measurements_show(struct seq_file *m, void *v)
+{
+	/* the list never shrinks, so we don't need a lock here */
+	struct ima_queue_entry *qe = v;
+	struct ima_template_entry *e;
+	char *template_name;
+	u32 pcr, namelen, template_data_len; /* temporary fields */
+	bool is_ima_template = false;
+	int i, algo_idx;
+
+	algo_idx = ima_sha1_idx;
+
+	if (m->file != NULL)
+		algo_idx = (unsigned long)file_inode(m->file)->i_private;
+
+	/* get entry */
+	e = qe->entry;
+	if (e == NULL)
+		return -1;
+
+	template_name = (e->template_desc->name[0] != '\0') ?
+	    e->template_desc->name : e->template_desc->fmt;
+
+	/*
+	 * 1st: PCRIndex
+	 * PCR used defaults to the same (config option) in
+	 * little-endian format, unless set in policy
+	 */
+	pcr = !ima_canonical_fmt ? e->pcr : (__force u32)cpu_to_le32(e->pcr);
+	ima_putc(m, &pcr, sizeof(e->pcr));
+
+	/* 2nd: template digest */
+	ima_putc(m, e->digests[algo_idx].digest,
+		 ima_algo_array[algo_idx].digest_size);
+
+	/* 3rd: template name size */
+	namelen = !ima_canonical_fmt ? strlen(template_name) :
+		(__force u32)cpu_to_le32(strlen(template_name));
+	ima_putc(m, &namelen, sizeof(namelen));
+
+	/* 4th:  template name */
+	ima_putc(m, template_name, strlen(template_name));
+
+	/* 5th:  template length (except for 'ima' template) */
+	if (strcmp(template_name, IMA_TEMPLATE_IMA_NAME) == 0)
+		is_ima_template = true;
+
+	if (!is_ima_template) {
+		template_data_len = !ima_canonical_fmt ? e->template_data_len :
+			(__force u32)cpu_to_le32(e->template_data_len);
+		ima_putc(m, &template_data_len, sizeof(e->template_data_len));
+	}
+
+	/* 6th:  template specific data */
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		enum ima_show_type show = IMA_SHOW_BINARY;
+		const struct ima_template_field *field =
+			e->template_desc->fields[i];
+
+		if (is_ima_template && strcmp(field->field_id, "d") == 0)
+			show = IMA_SHOW_BINARY_NO_FIELD_LEN;
+		if (is_ima_template && strcmp(field->field_id, "n") == 0)
+			show = IMA_SHOW_BINARY_OLD_STRING_FMT;
+		field->field_show(m, show, &e->template_data[i]);
+	}
+	return 0;
+}
+
+static const struct seq_operations ima_measurments_seqops = {
+	.start = ima_measurements_start,
+	.next = ima_measurements_next,
+	.stop = ima_measurements_stop,
+	.show = ima_measurements_show
+};
+
+static const struct seq_operations ima_measurments_staged_seqops = {
+	.start = ima_measurements_staged_start,
+	.next = ima_measurements_staged_next,
+	.stop = ima_measurements_stop,
+	.show = ima_measurements_show
+};
+
+static int ima_measure_lock(bool write)
+{
+	mutex_lock(&ima_measure_mutex);
+	/* Overflow check. */
+	if (!write && ima_measure_users == LONG_MAX) {
+		mutex_unlock(&ima_measure_mutex);
+		return -ENFILE;
+	}
+
+	/* Same writer can do additional writes or read/writes. */
+	if (write && current == measure_writer) {
+		measure_writer_extra_writes++;
+		mutex_unlock(&ima_measure_mutex);
+		return 0;
+	}
+
+	/*
+	 * ima_measure_users: > 0 open readers
+	 * ima_measure_users: == -1 open writer
+	 */
+	if ((write && ima_measure_users != 0) ||
+	    (!write && ima_measure_users < 0)) {
+		mutex_unlock(&ima_measure_mutex);
+		return -EBUSY;
+	}
+
+	if (write) {
+		ima_measure_users--;
+		/* Pointer valid, no reuse while the file descriptor is open. */
+		measure_writer = current;
+	} else {
+		ima_measure_users++;
+	}
+	mutex_unlock(&ima_measure_mutex);
+	return 0;
+}
+
+static void ima_measure_unlock(bool write)
+{
+	mutex_lock(&ima_measure_mutex);
+	/* Decrement additional writes or read/writes. */
+	if (write && current == measure_writer &&
+	    measure_writer_extra_writes != 0) {
+		measure_writer_extra_writes--;
+		mutex_unlock(&ima_measure_mutex);
+		return;
+	}
+	if (write) {
+		ima_measure_users++;
+		measure_writer = NULL;
+	} else {
+		ima_measure_users--;
+	}
+	mutex_unlock(&ima_measure_mutex);
+}
+
+static int _ima_measurements_open(struct inode *inode, struct file *file,
+				  const struct seq_operations *seq_ops)
+{
+	bool write = (file->f_mode & FMODE_WRITE);
+	int ret;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = ima_measure_lock(write);
+	if (ret < 0)
+		return ret;
+
+	ret = seq_open(file, seq_ops);
+	if (ret < 0)
+		ima_measure_unlock(write);
+
+	return ret;
+}
+
+static int ima_measurements_open(struct inode *inode, struct file *file)
+{
+	return _ima_measurements_open(inode, file, &ima_measurments_seqops);
+}
+
+static int ima_measurements_release(struct inode *inode, struct file *file)
+{
+	bool write = (file->f_mode & FMODE_WRITE);
+	int ret;
+
+	/* seq_release() always returns zero. */
+	ret = seq_release(inode, file);
+
+	ima_measure_unlock(write);
+
+	return ret;
+}
+
+static int ima_measurements_staged_open(struct inode *inode, struct file *file)
+{
+	return _ima_measurements_open(inode, file,
+				      &ima_measurments_staged_seqops);
+}
+
+static ssize_t _ima_measurements_write(struct file *file,
+				       const char __user *buf, size_t datalen,
+				       loff_t *ppos, bool staged_interface)
+{
+	char req[STAGED_REQ_LENGTH];
+	unsigned long req_value;
+	int ret;
+
+	if (datalen < 2 || datalen > STAGED_REQ_LENGTH)
+		return -EINVAL;
+
+	if (copy_from_user(req, buf, datalen) != 0)
+		return -EFAULT;
+
+	if (req[datalen - 1] != '\n')
+		return -EINVAL;
+
+	req[datalen - 1] = '\0';
+
+	switch (req[0]) {
+	case 'A':
+		if (datalen != 2 || !staged_interface)
+			return -EINVAL;
+
+		ret = ima_queue_stage();
+		break;
+	case 'D':
+		if (datalen != 2 || !staged_interface)
+			return -EINVAL;
+
+		ret = ima_queue_staged_delete_all();
+		break;
+	default:
+		if (staged_interface)
+			return -EINVAL;
+
+		if (ima_flush_htable) {
+			pr_debug("Deleting staged N measurements not supported when flushing the hash table is requested\n");
+			return -EINVAL;
+		}
+
+		ret = kstrtoul(req, 10, &req_value);
+		if (ret < 0)
+			return ret;
+
+		if (req_value == 0) {
+			pr_debug("Must delete at least one entry\n");
+			return -EINVAL;
+		}
+
+		ret = ima_queue_delete_partial(req_value);
+	}
+
+	if (ret < 0)
+		return ret;
+
+	return datalen;
+}
+
+static ssize_t ima_measurements_write(struct file *file, const char __user *buf,
+				      size_t datalen, loff_t *ppos)
+{
+	return _ima_measurements_write(file, buf, datalen, ppos, false);
+}
+
+static ssize_t ima_measurements_staged_write(struct file *file,
+					     const char __user *buf,
+					     size_t datalen, loff_t *ppos)
+{
+	return _ima_measurements_write(file, buf, datalen, ppos, true);
+}
+
+static const struct file_operations ima_measurements_ops = {
+	.open = ima_measurements_open,
+	.read = seq_read,
+	.write = ima_measurements_write,
+	.llseek = seq_lseek,
+	.release = ima_measurements_release,
+};
+
+static const struct file_operations ima_measurements_staged_ops = {
+	.open = ima_measurements_staged_open,
+	.read = seq_read,
+	.write = ima_measurements_staged_write,
+	.llseek = seq_lseek,
+	.release = ima_measurements_release,
+};
+
+void ima_print_digest(struct seq_file *m, u8 *digest, u32 size)
+{
+	u32 i;
+
+	for (i = 0; i < size; i++)
+		seq_printf(m, "%02x", *(digest + i));
+}
+
+/* print in ascii */
+static int ima_ascii_measurements_show(struct seq_file *m, void *v)
+{
+	/* the list never shrinks, so we don't need a lock here */
+	struct ima_queue_entry *qe = v;
+	struct ima_template_entry *e;
+	char *template_name;
+	int i, algo_idx;
+
+	algo_idx = ima_sha1_idx;
+
+	if (m->file != NULL)
+		algo_idx = (unsigned long)file_inode(m->file)->i_private;
+
+	/* get entry */
+	e = qe->entry;
+	if (e == NULL)
+		return -1;
+
+	template_name = (e->template_desc->name[0] != '\0') ?
+	    e->template_desc->name : e->template_desc->fmt;
+
+	/* 1st: PCR used (config option) */
+	seq_printf(m, "%2d ", e->pcr);
+
+	/* 2nd: template hash */
+	ima_print_digest(m, e->digests[algo_idx].digest,
+			 ima_algo_array[algo_idx].digest_size);
+
+	/* 3th:  template name */
+	seq_printf(m, " %s", template_name);
+
+	/* 4th:  template specific data */
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		seq_puts(m, " ");
+		if (e->template_data[i].len == 0)
+			continue;
+
+		e->template_desc->fields[i]->field_show(m, IMA_SHOW_ASCII,
+							&e->template_data[i]);
+	}
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static const struct seq_operations ima_ascii_measurements_seqops = {
+	.start = ima_measurements_start,
+	.next = ima_measurements_next,
+	.stop = ima_measurements_stop,
+	.show = ima_ascii_measurements_show
+};
+
+static int ima_ascii_measurements_open(struct inode *inode, struct file *file)
+{
+	return _ima_measurements_open(inode, file,
+				      &ima_ascii_measurements_seqops);
+}
+
+static const struct file_operations ima_ascii_measurements_ops = {
+	.open = ima_ascii_measurements_open,
+	.read = seq_read,
+	.write = ima_measurements_write,
+	.llseek = seq_lseek,
+	.release = ima_measurements_release,
+};
+
+static const struct seq_operations ima_ascii_measurements_staged_seqops = {
+	.start = ima_measurements_staged_start,
+	.next = ima_measurements_staged_next,
+	.stop = ima_measurements_stop,
+	.show = ima_ascii_measurements_show
+};
+
+static int ima_ascii_measurements_staged_open(struct inode *inode,
+					      struct file *file)
+{
+	return _ima_measurements_open(inode, file,
+				      &ima_ascii_measurements_staged_seqops);
+}
+
+static const struct file_operations ima_ascii_measurements_staged_ops = {
+	.open = ima_ascii_measurements_staged_open,
+	.read = seq_read,
+	.write = ima_measurements_staged_write,
+	.llseek = seq_lseek,
+	.release = ima_measurements_release,
+};
+
+static ssize_t ima_read_policy(char *path)
+{
+	void *data = NULL;
+	char *datap;
+	size_t size;
+	int rc, pathlen = strlen(path);
+
+	char *p;
+
+	/* remove \n */
+	datap = path;
+	strsep(&datap, "\n");
+
+	rc = kernel_read_file_from_path(path, 0, &data, INT_MAX, NULL,
+					READING_POLICY);
+	if (rc < 0) {
+		pr_err("Unable to open file: %s (%d)", path, rc);
+		return rc;
+	}
+	size = rc;
+	rc = 0;
+
+	datap = data;
+	while (size > 0 && (p = strsep(&datap, "\n"))) {
+		pr_debug("rule: %s\n", p);
+		rc = ima_parse_add_rule(p);
+		if (rc < 0)
+			break;
+		size -= rc;
+	}
+
+	vfree(data);
+	if (rc < 0)
+		return rc;
+	else if (size)
+		return -EINVAL;
+	else
+		return pathlen;
+}
+
+static ssize_t ima_write_policy(struct file *file, const char __user *buf,
+				size_t datalen, loff_t *ppos)
+{
+	char *data;
+	ssize_t result;
+
+	if (datalen >= PAGE_SIZE)
+		datalen = PAGE_SIZE - 1;
+
+	/* No partial writes. */
+	result = -EINVAL;
+	if (*ppos != 0)
+		goto out;
+
+	data = memdup_user_nul(buf, datalen);
+	if (IS_ERR(data)) {
+		result = PTR_ERR(data);
+		goto out;
+	}
+
+	result = mutex_lock_interruptible(&ima_write_mutex);
+	if (result < 0)
+		goto out_free;
+
+	if (data[0] == '/') {
+		result = ima_read_policy(data);
+	} else if (ima_appraise & IMA_APPRAISE_POLICY) {
+		pr_err("signed policy file (specified as an absolute pathname) required\n");
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
+				    "policy_update", "signed policy required",
+				    1, 0);
+		result = -EACCES;
+	} else {
+		ima_measure_raw_policy(data, datalen);
+		result = ima_parse_add_rule(data);
+	}
+	mutex_unlock(&ima_write_mutex);
+out_free:
+	kfree(data);
+out:
+	if (result < 0)
+		valid_policy = 0;
+
+	return result;
+}
+
+static struct dentry *ima_dir;
+static struct dentry *ima_symlink;
+
+enum ima_fs_flags {
+	IMA_FS_BUSY,
+};
+
+static unsigned long ima_fs_flags;
+
+#ifdef	CONFIG_IMA_READ_POLICY
+static const struct seq_operations ima_policy_seqops = {
+		.start = ima_policy_start,
+		.next = ima_policy_next,
+		.stop = ima_policy_stop,
+		.show = ima_policy_show,
+};
+#endif
+
+static int __init create_securityfs_measurement_lists(bool staging)
+{
+	const struct file_operations *ascii_ops = &ima_ascii_measurements_ops;
+	const struct file_operations *binary_ops = &ima_measurements_ops;
+	umode_t permissions = (S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP);
+	const char *file_suffix = "";
+	int count = NR_BANKS(ima_tpm_chip);
+
+	if (staging) {
+		ascii_ops = &ima_ascii_measurements_staged_ops;
+		binary_ops = &ima_measurements_staged_ops;
+		file_suffix = "_staged";
+	}
+
+	if (ima_sha1_idx >= NR_BANKS(ima_tpm_chip))
+		count++;
+
+	for (int i = 0; i < count; i++) {
+		u16 algo = ima_algo_array[i].algo;
+		char file_name[NAME_MAX + 1];
+		struct dentry *dentry;
+
+		if (algo == HASH_ALGO__LAST)
+			snprintf(file_name, sizeof(file_name),
+				 "ascii_runtime_measurements_tpm_alg_%x%s",
+				 ima_tpm_chip->allocated_banks[i].alg_id,
+				 file_suffix);
+		else
+			snprintf(file_name, sizeof(file_name),
+				 "ascii_runtime_measurements_%s%s",
+				 hash_algo_name[algo], file_suffix);
+		dentry = securityfs_create_file(file_name, permissions,
+						ima_dir, (void *)(uintptr_t)i,
+						ascii_ops);
+		if (IS_ERR(dentry))
+			return PTR_ERR(dentry);
+
+		if (algo == HASH_ALGO__LAST)
+			snprintf(file_name, sizeof(file_name),
+				 "binary_runtime_measurements_tpm_alg_%x%s",
+				 ima_tpm_chip->allocated_banks[i].alg_id,
+				 file_suffix);
+		else
+			snprintf(file_name, sizeof(file_name),
+				 "binary_runtime_measurements_%s%s",
+				 hash_algo_name[algo], file_suffix);
+
+		dentry = securityfs_create_file(file_name, permissions,
+						ima_dir, (void *)(uintptr_t)i,
+						binary_ops);
+		if (IS_ERR(dentry))
+			return PTR_ERR(dentry);
+	}
+
+	return 0;
+}
+
+static int __init create_securityfs_staging_links(void)
+{
+	struct dentry *dentry;
+
+	dentry = securityfs_create_symlink("binary_runtime_measurements_staged",
+		ima_dir, "binary_runtime_measurements_sha1_staged", NULL);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	dentry = securityfs_create_symlink("ascii_runtime_measurements_staged",
+		ima_dir, "ascii_runtime_measurements_sha1_staged", NULL);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return 0;
+}
+
+/*
+ * ima_open_policy: sequentialize access to the policy file
+ */
+static int ima_open_policy(struct inode *inode, struct file *filp)
+{
+	if (!(filp->f_flags & O_WRONLY)) {
+#ifndef	CONFIG_IMA_READ_POLICY
+		return -EACCES;
+#else
+		if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+			return -EACCES;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		return seq_open(filp, &ima_policy_seqops);
+#endif
+	}
+	if (test_and_set_bit(IMA_FS_BUSY, &ima_fs_flags))
+		return -EBUSY;
+	return 0;
+}
+
+/*
+ * ima_release_policy - start using the new measure policy rules.
+ *
+ * Initially, ima_measure points to the default policy rules, now
+ * point to the new policy rules, and remove the securityfs policy file,
+ * assuming a valid policy.
+ */
+static int ima_release_policy(struct inode *inode, struct file *file)
+{
+	const char *cause = valid_policy ? "completed" : "failed";
+
+	if ((file->f_flags & O_ACCMODE) == O_RDONLY)
+		return seq_release(inode, file);
+
+	if (valid_policy && ima_check_policy() < 0) {
+		cause = "failed";
+		valid_policy = 0;
+	}
+
+	pr_info("policy update %s\n", cause);
+	integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL, NULL,
+			    "policy_update", cause, !valid_policy, 0);
+
+	if (!valid_policy) {
+		ima_delete_rules();
+		valid_policy = 1;
+		clear_bit(IMA_FS_BUSY, &ima_fs_flags);
+		return 0;
+	}
+
+	ima_update_policy();
+
+	mutex_lock(&ima_write_mutex);
+	ima_measure_loaded_policy();
+	mutex_unlock(&ima_write_mutex);
+#if !defined(CONFIG_IMA_WRITE_POLICY) && !defined(CONFIG_IMA_READ_POLICY)
+	securityfs_remove(file->f_path.dentry);
+#elif defined(CONFIG_IMA_WRITE_POLICY)
+	clear_bit(IMA_FS_BUSY, &ima_fs_flags);
+#elif defined(CONFIG_IMA_READ_POLICY)
+	inode->i_mode &= ~S_IWUSR;
+#endif
+	return 0;
+}
+
+static const struct file_operations ima_measure_policy_ops = {
+	.open = ima_open_policy,
+	.write = ima_write_policy,
+	.read = seq_read,
+	.release = ima_release_policy,
+	.llseek = generic_file_llseek,
+};
+
+int __init ima_fs_init(void)
+{
+	struct dentry *dentry;
+	int ret;
+
+	ret = integrity_fs_init();
+	if (ret < 0)
+		return ret;
+
+	ima_dir = securityfs_create_dir("ima", integrity_dir);
+	if (IS_ERR(ima_dir)) {
+		ret = PTR_ERR(ima_dir);
+		goto out;
+	}
+
+	ima_symlink = securityfs_create_symlink("ima", NULL, "integrity/ima",
+						NULL);
+	if (IS_ERR(ima_symlink)) {
+		ret = PTR_ERR(ima_symlink);
+		goto out;
+	}
+
+	ret = create_securityfs_measurement_lists(false);
+	if (ret == 0 && IS_ENABLED(CONFIG_IMA_STAGING)) {
+		ret = create_securityfs_measurement_lists(true);
+		if (ret == 0)
+			ret = create_securityfs_staging_links();
+	}
+
+	if (ret != 0)
+		goto out;
+
+	dentry = securityfs_create_symlink("binary_runtime_measurements", ima_dir,
+				      "binary_runtime_measurements_sha1", NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = securityfs_create_symlink("ascii_runtime_measurements", ima_dir,
+				      "ascii_runtime_measurements_sha1", NULL);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = securityfs_create_file("runtime_measurements_count",
+				   S_IRUSR | S_IRGRP, ima_dir, NULL,
+				   &ima_measurements_count_ops);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = securityfs_create_file("violations", S_IRUSR | S_IRGRP,
+				   ima_dir, NULL, &ima_num_violations_ops);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	dentry = securityfs_create_file("policy", POLICY_FILE_FLAGS,
+					    ima_dir, NULL,
+					    &ima_measure_policy_ops);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto out;
+	}
+
+	return 0;
+out:
+	securityfs_remove(ima_symlink);
+	securityfs_remove(ima_dir);
+	integrity_fs_fini();
+
+	return ret;
+}
diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c
new file mode 100644
index 000000000..00b249101
--- /dev/null
+++ b/security/integrity/ima/ima_iint.c
@@ -0,0 +1,138 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima_iint.c
+ *	- implements the IMA hook: ima_inode_free
+ *	- cache integrity information in the inode security blob
+ */
+#include <linux/slab.h>
+
+#include "ima.h"
+
+static struct kmem_cache *ima_iint_cache __ro_after_init;
+
+/**
+ * ima_iint_find - Return the iint associated with an inode
+ * @inode: Pointer to the inode
+ *
+ * Return the IMA integrity information (iint) associated with an inode, if the
+ * inode was processed by IMA.
+ *
+ * Return: Found iint or NULL.
+ */
+struct ima_iint_cache *ima_iint_find(struct inode *inode)
+{
+	if (!IS_IMA(inode))
+		return NULL;
+
+	return ima_inode_get_iint(inode);
+}
+
+#define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH + 1)
+
+/*
+ * It is not clear that IMA should be nested at all, but as long is it measures
+ * files both on overlayfs and on underlying fs, we need to annotate the iint
+ * mutex to avoid lockdep false positives related to IMA + overlayfs.
+ * See ovl_lockdep_annotate_inode_mutex_key() for more details.
+ */
+static inline void ima_iint_lockdep_annotate(struct ima_iint_cache *iint,
+					     struct inode *inode)
+{
+#ifdef CONFIG_LOCKDEP
+	static struct lock_class_key ima_iint_mutex_key[IMA_MAX_NESTING];
+
+	int depth = inode->i_sb->s_stack_depth;
+
+	if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING))
+		depth = 0;
+
+	lockdep_set_class(&iint->mutex, &ima_iint_mutex_key[depth]);
+#endif
+}
+
+static void ima_iint_init_always(struct ima_iint_cache *iint,
+				 struct inode *inode)
+{
+	iint->ima_hash = NULL;
+	iint->real_inode.version = 0;
+	iint->flags = 0UL;
+	iint->atomic_flags = 0UL;
+	iint->ima_file_status = INTEGRITY_UNKNOWN;
+	iint->ima_mmap_status = INTEGRITY_UNKNOWN;
+	iint->ima_bprm_status = INTEGRITY_UNKNOWN;
+	iint->ima_read_status = INTEGRITY_UNKNOWN;
+	iint->ima_creds_status = INTEGRITY_UNKNOWN;
+	iint->measured_pcrs = 0;
+	mutex_init(&iint->mutex);
+	ima_iint_lockdep_annotate(iint, inode);
+}
+
+static void ima_iint_free(struct ima_iint_cache *iint)
+{
+	kfree(iint->ima_hash);
+	mutex_destroy(&iint->mutex);
+	kmem_cache_free(ima_iint_cache, iint);
+}
+
+/**
+ * ima_inode_get - Find or allocate an iint associated with an inode
+ * @inode: Pointer to the inode
+ *
+ * Find an iint associated with an inode, and allocate a new one if not found.
+ * Caller must lock i_mutex.
+ *
+ * Return: An iint on success, NULL on error.
+ */
+struct ima_iint_cache *ima_inode_get(struct inode *inode)
+{
+	struct ima_iint_cache *iint;
+
+	iint = ima_iint_find(inode);
+	if (iint)
+		return iint;
+
+	iint = kmem_cache_alloc(ima_iint_cache, GFP_NOFS);
+	if (!iint)
+		return NULL;
+
+	ima_iint_init_always(iint, inode);
+
+	inode->i_flags |= S_IMA;
+	ima_inode_set_iint(inode, iint);
+
+	return iint;
+}
+
+/**
+ * ima_inode_free_rcu - Called to free an inode via a RCU callback
+ * @inode_security: The inode->i_security pointer
+ *
+ * Free the IMA data associated with an inode.
+ */
+void ima_inode_free_rcu(void *inode_security)
+{
+	struct ima_iint_cache **iint_p = inode_security + ima_blob_sizes.lbs_inode;
+
+	/* *iint_p should be NULL if !IS_IMA(inode) */
+	if (*iint_p)
+		ima_iint_free(*iint_p);
+}
+
+static void ima_iint_init_once(void *foo)
+{
+	struct ima_iint_cache *iint = (struct ima_iint_cache *)foo;
+
+	memset(iint, 0, sizeof(*iint));
+}
+
+void __init ima_iintcache_init(void)
+{
+	ima_iint_cache =
+	    kmem_cache_create("ima_iint_cache", sizeof(struct ima_iint_cache),
+			      0, SLAB_PANIC, ima_iint_init_once);
+}
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
new file mode 100644
index 000000000..d53f4d89a
--- /dev/null
+++ b/security/integrity/ima/ima_init.c
@@ -0,0 +1,174 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer      <sailer@watson.ibm.com>
+ * Leendert van Doorn <leendert@watson.ibm.com>
+ * Mimi Zohar         <zohar@us.ibm.com>
+ *
+ * File: ima_init.c
+ *             initialization and cleanup functions
+ */
+
+#include <linux/init.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/ima.h>
+#include <generated/utsrelease.h>
+
+#include "ima.h"
+
+/* name for boot aggregate entry */
+const char boot_aggregate_name[] = "boot_aggregate";
+const char boot_aggregate_late_name[] = "boot_aggregate_late";
+struct tpm_chip *ima_tpm_chip;
+
+/* Add the boot aggregate to the IMA measurement list and extend
+ * the PCR register.
+ *
+ * Calculate the boot aggregate, a hash over tpm registers 0-7,
+ * assuming a TPM chip exists, and zeroes if the TPM chip does not
+ * exist.  Add the boot aggregate measurement to the measurement
+ * list and extend the PCR register.
+ *
+ * If a tpm chip does not exist, indicate the core root of trust is
+ * not hardware based by invalidating the aggregate PCR value.
+ * (The aggregate PCR value is invalidated by adding one value to
+ * the measurement list and extending the aggregate PCR value with
+ * a different value.) Violations add a zero entry to the measurement
+ * list and extend the aggregate PCR value with ff...ff's.
+ */
+static int __init ima_add_boot_aggregate(void)
+{
+	static const char op[] = "add_boot_aggregate";
+	const char *audit_cause = "ENOMEM";
+	struct ima_template_entry *entry;
+	struct ima_iint_cache tmp_iint, *iint = &tmp_iint;
+	struct ima_event_data event_data = { .iint = iint };
+	struct ima_max_digest_data hash;
+	struct ima_digest_data *hash_hdr = container_of(&hash.hdr,
+						struct ima_digest_data, hdr);
+	const char *filename;
+	int result = -ENOMEM;
+	int violation = 0;
+
+	memset(iint, 0, sizeof(*iint));
+	memset(&hash, 0, sizeof(hash));
+	iint->ima_hash = hash_hdr;
+	iint->ima_hash->algo = ima_hash_algo;
+	iint->ima_hash->length = hash_digest_size[ima_hash_algo];
+
+	if (IS_ENABLED(CONFIG_IMA_INIT_LATE_SYNC))
+		filename = boot_aggregate_late_name;
+	else
+		filename = boot_aggregate_name;
+	event_data.filename = filename;
+
+	/*
+	 * With TPM 2.0 hash agility, TPM chips could support multiple TPM
+	 * PCR banks, allowing firmware to configure and enable different
+	 * banks.  The SHA1 bank is not necessarily enabled.
+	 *
+	 * Use the same hash algorithm for reading the TPM PCRs as for
+	 * calculating the boot aggregate digest.  Preference is given to
+	 * the configured IMA default hash algorithm.  Otherwise, use the
+	 * TCG required banks - SHA256 for TPM 2.0, SHA1 for TPM 1.2.
+	 * Ultimately select SHA1 also for TPM 2.0 if the SHA256 PCR bank
+	 * is not found.
+	 */
+	if (ima_tpm_chip) {
+		result = ima_calc_boot_aggregate(hash_hdr);
+		if (result < 0) {
+			audit_cause = "hashing_error";
+			goto err_out;
+		}
+	}
+
+	result = ima_alloc_init_template(&event_data, &entry, NULL);
+	if (result < 0) {
+		audit_cause = "alloc_entry";
+		goto err_out;
+	}
+
+	result = ima_store_template(entry, violation, NULL,
+				    filename,
+				    CONFIG_IMA_MEASURE_PCR_IDX);
+	if (result < 0) {
+		ima_free_template_entry(entry);
+		audit_cause = "store_entry";
+		goto err_out;
+	}
+	return 0;
+err_out:
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, filename, op,
+			    audit_cause, result, 0);
+	return result;
+}
+
+#ifdef CONFIG_IMA_LOAD_X509
+void __init ima_load_x509(void)
+{
+	int unset_flags = ima_policy_flag & IMA_APPRAISE;
+
+	ima_policy_flag &= ~unset_flags;
+	integrity_load_x509(INTEGRITY_KEYRING_IMA, CONFIG_IMA_X509_PATH);
+
+	/* load also EVM key to avoid appraisal */
+	evm_load_x509();
+
+	ima_policy_flag |= unset_flags;
+}
+#endif
+
+int __init ima_init(void)
+{
+	int rc;
+
+	ima_tpm_chip = tpm_default_chip();
+	if (!ima_tpm_chip)
+		pr_info("No TPM chip found, activating TPM-bypass!\n");
+
+	rc = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
+	if (rc)
+		return rc;
+
+	rc = ima_init_crypto();
+	if (rc)
+		return rc;
+	rc = ima_init_template();
+	if (rc != 0)
+		return rc;
+
+	/* It can be called before ima_init_digests(), it does not use TPM. */
+	ima_load_kexec_buffer();
+
+	rc = ima_init_digests();
+	if (rc != 0)
+		return rc;
+
+	rc = ima_init_htable();
+	if (rc != 0)
+		return rc;
+
+	rc = ima_add_boot_aggregate();	/* boot aggregate must be first entry */
+	if (rc != 0)
+		return rc;
+
+	ima_init_policy();
+
+	rc = ima_fs_init();
+	if (rc != 0)
+		return rc;
+
+	ima_init_key_queue();
+
+	ima_init_reboot_notifier();
+
+	ima_measure_critical_data("kernel_info", "kernel_version",
+				  UTS_RELEASE, strlen(UTS_RELEASE), false,
+				  NULL, 0);
+
+	return rc;
+}
diff --git a/security/integrity/ima/ima_kexec.c b/security/integrity/ima/ima_kexec.c
new file mode 100644
index 000000000..0d845693a
--- /dev/null
+++ b/security/integrity/ima/ima_kexec.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2016 IBM Corporation
+ *
+ * Authors:
+ * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
+ * Mimi Zohar <zohar@linux.vnet.ibm.com>
+ */
+
+#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
+#include <linux/kexec.h>
+#include <linux/of.h>
+#include <linux/ima.h>
+#include <linux/mm.h>
+#include <linux/overflow.h>
+#include <linux/reboot.h>
+#include <asm/page.h>
+#include "ima.h"
+
+#ifdef CONFIG_IMA_KEXEC
+#define IMA_KEXEC_EVENT_LEN 256
+
+static bool ima_kexec_update_registered;
+static struct seq_file ima_kexec_file;
+static size_t kexec_segment_size;
+static void *ima_kexec_buffer;
+
+static void ima_free_kexec_file_buf(struct seq_file *sf)
+{
+	vfree(sf->buf);
+	sf->buf = NULL;
+	sf->size = 0;
+	sf->read_pos = 0;
+	sf->count = 0;
+}
+
+void ima_measure_kexec_event(const char *event_name)
+{
+	char ima_kexec_event[IMA_KEXEC_EVENT_LEN];
+	size_t buf_size = 0;
+	long len;
+	int n;
+
+	buf_size = ima_get_binary_runtime_size(BINARY_FULL);
+	len = atomic_long_read(&ima_num_records[BINARY_FULL]);
+
+	n = scnprintf(ima_kexec_event, IMA_KEXEC_EVENT_LEN,
+		      "kexec_segment_size=%lu;ima_binary_runtime_size=%lu;"
+		      "ima_runtime_measurements_count=%ld;",
+		      kexec_segment_size, buf_size, len);
+
+	ima_measure_critical_data("ima_kexec", event_name, ima_kexec_event, n, false, NULL, 0);
+}
+
+static int ima_alloc_kexec_file_buf(size_t segment_size)
+{
+	/*
+	 * kexec 'load' may be called multiple times.
+	 * Free and realloc the buffer only if the segment_size is
+	 * changed from the previous kexec 'load' call.
+	 */
+	if (ima_kexec_file.buf && ima_kexec_file.size == segment_size)
+		goto out;
+
+	ima_free_kexec_file_buf(&ima_kexec_file);
+
+	/* segment size can't change between kexec load and execute */
+	ima_kexec_file.buf = vmalloc(segment_size);
+	if (!ima_kexec_file.buf)
+		return -ENOMEM;
+
+	ima_kexec_file.size = segment_size;
+
+out:
+	ima_kexec_file.read_pos = 0;
+	ima_kexec_file.count = sizeof(struct ima_kexec_hdr);	/* reserved space */
+	ima_measure_kexec_event("kexec_load");
+
+	return 0;
+}
+
+static int ima_dump_measurement(struct ima_kexec_hdr *khdr,
+				struct ima_queue_entry *qe)
+{
+	if (ima_kexec_file.count >= ima_kexec_file.size)
+		return -EINVAL;
+
+	khdr->count++;
+	ima_measurements_show(&ima_kexec_file, qe);
+	return 0;
+}
+
+static int ima_dump_measurement_list(unsigned long *buffer_size, void **buffer,
+				     unsigned long segment_size)
+{
+	struct ima_queue_entry *qe;
+	struct ima_kexec_hdr khdr;
+	int ret = 0;
+
+	/* segment size can't change between kexec load and execute */
+	if (!ima_kexec_file.buf) {
+		pr_err("Kexec file buf not allocated\n");
+		return -EINVAL;
+	}
+
+	memset(&khdr, 0, sizeof(khdr));
+	khdr.version = 1;
+	/*
+	 * Lockless walks possible due to strict ordering of the reboot
+	 * notifiers, suspending measurement before dump, and forbidding
+	 * staging/deleting (list mutations) after suspend.
+	 */
+	list_for_each_entry(qe, &ima_measurements_staged, later) {
+		ret = ima_dump_measurement(&khdr, qe);
+		if (ret < 0)
+			break;
+	}
+
+	list_for_each_entry(qe, &ima_measurements, later) {
+		if (!ret)
+			ret = ima_dump_measurement(&khdr, qe);
+		if (ret < 0)
+			break;
+	}
+
+	/*
+	 * fill in reserved space with some buffer details
+	 * (eg. version, buffer size, number of measurements)
+	 */
+	khdr.buffer_size = ima_kexec_file.count;
+	if (ima_canonical_fmt) {
+		khdr.version = cpu_to_le16(khdr.version);
+		khdr.count = cpu_to_le64(khdr.count);
+		khdr.buffer_size = cpu_to_le64(khdr.buffer_size);
+	}
+	memcpy(ima_kexec_file.buf, &khdr, sizeof(khdr));
+
+	print_hex_dump_debug("ima dump: ", DUMP_PREFIX_NONE, 16, 1,
+			     ima_kexec_file.buf, ima_kexec_file.count < 100 ?
+			     ima_kexec_file.count : 100,
+			     true);
+
+	*buffer_size = ima_kexec_file.count;
+	*buffer = ima_kexec_file.buf;
+
+	return ret;
+}
+
+/*
+ * Called during kexec_file_load so that IMA can add a segment to the kexec
+ * image for the measurement list for the next kernel.
+ *
+ * This function assumes that kexec_lock is held.
+ */
+void ima_add_kexec_buffer(struct kimage *image)
+{
+	struct kexec_buf kbuf = { .image = image, .buf_align = PAGE_SIZE,
+				  .buf_min = 0, .buf_max = ULONG_MAX,
+				  .top_down = true };
+	unsigned long binary_runtime_size;
+	unsigned long extra_memory;
+
+	/* use more understandable variable names than defined in kbuf */
+	size_t kexec_buffer_size = 0;
+	void *kexec_buffer = NULL;
+	int ret;
+
+	if (image->type == KEXEC_TYPE_CRASH)
+		return;
+
+	/*
+	 * Reserve extra memory for measurements added during kexec.
+	 */
+	if (CONFIG_IMA_KEXEC_EXTRA_MEMORY_KB <= 0)
+		extra_memory = PAGE_SIZE / 2;
+	else
+		extra_memory = CONFIG_IMA_KEXEC_EXTRA_MEMORY_KB * 1024;
+
+	binary_runtime_size = ima_get_binary_runtime_size(BINARY) +
+			      ima_get_binary_runtime_size(BINARY_STAGED) +
+			      extra_memory;
+
+	if (binary_runtime_size >= ULONG_MAX - PAGE_SIZE)
+		kexec_segment_size = ULONG_MAX;
+	else
+		kexec_segment_size = ALIGN(binary_runtime_size, PAGE_SIZE);
+
+	if ((kexec_segment_size == ULONG_MAX) ||
+	    ((kexec_segment_size >> PAGE_SHIFT) > totalram_pages() / 2)) {
+		pr_err("Binary measurement list too large.\n");
+		return;
+	}
+
+	ret = ima_alloc_kexec_file_buf(kexec_segment_size);
+	if (ret < 0) {
+		pr_err("Not enough memory for the kexec measurement buffer.\n");
+		return;
+	}
+
+	kbuf.buffer = kexec_buffer;
+	kbuf.bufsz = kexec_buffer_size;
+	kbuf.memsz = kexec_segment_size;
+	image->is_ima_segment_index_set = false;
+	ret = kexec_add_buffer(&kbuf);
+	if (ret) {
+		pr_err("Error passing over kexec measurement buffer.\n");
+		vfree(kexec_buffer);
+		return;
+	}
+
+	image->ima_buffer_addr = kbuf.mem;
+	image->ima_buffer_size = kexec_segment_size;
+	image->ima_buffer = kexec_buffer;
+	image->ima_segment_index = image->nr_segments - 1;
+	image->is_ima_segment_index_set = true;
+
+	kexec_dprintk("kexec measurement buffer for the loaded kernel at 0x%lx.\n",
+		      kbuf.mem);
+}
+
+/*
+ * Called during kexec execute so that IMA can update the measurement list.
+ */
+static int ima_update_kexec_buffer(struct notifier_block *self,
+				   unsigned long action, void *data)
+{
+	size_t buf_size = 0;
+	int ret = NOTIFY_OK;
+	void *buf = NULL;
+
+	if (!kexec_in_progress) {
+		pr_info("No kexec in progress.\n");
+		return ret;
+	}
+
+	if (!ima_kexec_buffer) {
+		pr_err("Kexec buffer not set.\n");
+		return ret;
+	}
+
+	ret = ima_dump_measurement_list(&buf_size, &buf, kexec_segment_size);
+
+	if (ret)
+		pr_err("Dump measurements failed. Error:%d\n", ret);
+
+	if (buf_size != 0)
+		memcpy(ima_kexec_buffer, buf, buf_size);
+
+	kimage_unmap_segment(ima_kexec_buffer);
+	ima_kexec_buffer = NULL;
+
+	return ret;
+}
+
+static struct notifier_block update_buffer_nb = {
+	.notifier_call = ima_update_kexec_buffer,
+	.priority = INT_MIN
+};
+
+/*
+ * Create a mapping for the source pages that contain the IMA buffer
+ * so we can update it later.
+ */
+void ima_kexec_post_load(struct kimage *image)
+{
+	if (ima_kexec_buffer) {
+		kimage_unmap_segment(ima_kexec_buffer);
+		ima_kexec_buffer = NULL;
+	}
+
+	if (!image->ima_buffer_addr)
+		return;
+
+	ima_kexec_buffer = kimage_map_segment(image, image->ima_segment_index);
+	if (!ima_kexec_buffer) {
+		pr_err("Could not map measurements buffer.\n");
+		return;
+	}
+
+	if (!ima_kexec_update_registered) {
+		register_reboot_notifier(&update_buffer_nb);
+		ima_kexec_update_registered = true;
+	}
+}
+
+#endif /* IMA_KEXEC */
+
+/*
+ * Restore the measurement list from the previous kernel.
+ */
+void __init ima_load_kexec_buffer(void)
+{
+	void *kexec_buffer = NULL;
+	size_t kexec_buffer_size = 0;
+	int rc;
+
+	rc = ima_get_kexec_buffer(&kexec_buffer, &kexec_buffer_size);
+	switch (rc) {
+	case 0:
+		rc = ima_restore_measurement_list(kexec_buffer_size,
+						  kexec_buffer);
+		if (rc != 0)
+			pr_err("Failed to restore the measurement list: %d\n",
+				rc);
+
+		ima_free_kexec_buffer();
+		break;
+	case -ENOTSUPP:
+		pr_debug("Restoring the measurement list not supported\n");
+		break;
+	case -ENOENT:
+		pr_debug("No measurement list to restore\n");
+		break;
+	default:
+		pr_debug("Error restoring the measurement list: %d\n", rc);
+	}
+}
+
+/*
+ * ima_validate_range - verify a physical buffer lies in addressable RAM
+ * @phys: physical start address of the buffer from previous kernel
+ * @size: size of the buffer
+ *
+ * On success return 0. On failure returns -EINVAL so callers can skip
+ * restoring.
+ */
+int ima_validate_range(phys_addr_t phys, size_t size)
+{
+	unsigned long start_pfn, end_pfn;
+	phys_addr_t end_phys;
+
+	if (check_add_overflow(phys, (phys_addr_t)size - 1, &end_phys))
+		return -EINVAL;
+
+	start_pfn = PHYS_PFN(phys);
+	end_pfn = PHYS_PFN(end_phys);
+
+#ifdef CONFIG_X86
+	if (!pfn_range_is_mapped(start_pfn, end_pfn))
+#else
+	if (!page_is_ram(start_pfn) || !page_is_ram(end_pfn))
+#endif
+	{
+		pr_warn("IMA: previous kernel measurement buffer %pa (size 0x%zx) lies outside available memory\n",
+			&phys, size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
new file mode 100644
index 000000000..ab1e53b32
--- /dev/null
+++ b/security/integrity/ima/ima_main.c
@@ -0,0 +1,1406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Integrity Measurement Architecture
+ *
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Serge Hallyn <serue@us.ibm.com>
+ * Kylene Hall <kylene@us.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima_main.c
+ *	implements the IMA hooks: ima_bprm_check, ima_file_mmap,
+ *	and ima_file_check.
+ */
+
+#include <linux/module.h>
+#include <linux/file.h>
+#include <linux/binfmts.h>
+#include <linux/kernel_read_file.h>
+#include <linux/mount.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/ima.h>
+#include <linux/fs.h>
+#include <linux/iversion.h>
+#include <linux/evm.h>
+#include <linux/crash_dump.h>
+
+#include "ima.h"
+
+#ifdef CONFIG_IMA_APPRAISE
+int ima_appraise = IMA_APPRAISE_ENFORCE;
+#else
+int ima_appraise;
+#endif
+
+int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1;
+static int hash_setup_done;
+static int ima_disabled __ro_after_init;
+
+static struct notifier_block ima_lsm_policy_notifier = {
+	.notifier_call = ima_lsm_policy_change,
+};
+
+static int __init ima_setup(char *str)
+{
+	if (!is_kdump_kernel()) {
+		pr_info("Warning: ima setup option only permitted in kdump");
+		return 1;
+	}
+
+	if (strncmp(str, "off", 3) == 0)
+		ima_disabled = 1;
+	else if (strncmp(str, "on", 2) == 0)
+		ima_disabled = 0;
+	else
+		pr_err("Invalid ima setup option: \"%s\" , please specify ima=on|off.", str);
+
+	return 1;
+}
+__setup("ima=", ima_setup);
+
+static int __init hash_setup(char *str)
+{
+	struct ima_template_desc *template_desc = ima_template_desc_current();
+	int i;
+
+	if (hash_setup_done)
+		return 1;
+
+	if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+		if (strncmp(str, "sha1", 4) == 0) {
+			ima_hash_algo = HASH_ALGO_SHA1;
+		} else if (strncmp(str, "md5", 3) == 0) {
+			ima_hash_algo = HASH_ALGO_MD5;
+		} else {
+			pr_err("invalid hash algorithm \"%s\" for template \"%s\"",
+				str, IMA_TEMPLATE_IMA_NAME);
+			return 1;
+		}
+		goto out;
+	}
+
+	i = match_string(hash_algo_name, HASH_ALGO__LAST, str);
+	if (i < 0) {
+		pr_err("invalid hash algorithm \"%s\"", str);
+		return 1;
+	}
+
+	ima_hash_algo = i;
+out:
+	hash_setup_done = 1;
+	return 1;
+}
+__setup("ima_hash=", hash_setup);
+
+enum hash_algo ima_get_current_hash_algo(void)
+{
+	return ima_hash_algo;
+}
+
+/* Prevent mmap'ing a file execute that is already mmap'ed write */
+static int mmap_violation_check(enum ima_hooks func, struct file *file,
+				char **pathbuf, const char **pathname,
+				char *filename)
+{
+	struct inode *inode;
+	int rc = 0;
+
+	if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) &&
+	    mapping_writably_mapped(file->f_mapping)) {
+		rc = -ETXTBSY;
+		inode = file_inode(file);
+
+		if (!*pathbuf)	/* ima_rdwr_violation possibly pre-fetched */
+			*pathname = ima_d_path(&file->f_path, pathbuf,
+					       filename);
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname,
+				    "mmap_file", "mmapped_writers", rc, 0);
+	}
+	return rc;
+}
+
+/*
+ * ima_rdwr_violation_check
+ *
+ * Only invalidate the PCR for measured files:
+ *	- Opening a file for write when already open for read,
+ *	  results in a time of measure, time of use (ToMToU) error.
+ *	- Opening a file for read when already open for write,
+ *	  could result in a file measurement error.
+ *
+ */
+static void ima_rdwr_violation_check(struct file *file,
+				     struct ima_iint_cache *iint,
+				     int must_measure,
+				     char **pathbuf,
+				     const char **pathname,
+				     char *filename)
+{
+	struct inode *inode = file_inode(file);
+	fmode_t mode = file->f_mode;
+	bool send_tomtou = false, send_writers = false;
+
+	if (mode & FMODE_WRITE) {
+		if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) {
+			if (!iint)
+				iint = ima_iint_find(inode);
+
+			/* IMA_MEASURE is set from reader side */
+			if (iint && test_and_clear_bit(IMA_MAY_EMIT_TOMTOU,
+						       &iint->atomic_flags))
+				send_tomtou = true;
+		}
+	} else {
+		if (must_measure)
+			set_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags);
+
+		/* Limit number of open_writers violations */
+		if (inode_is_open_for_write(inode) && must_measure) {
+			if (!test_and_set_bit(IMA_EMITTED_OPENWRITERS,
+					      &iint->atomic_flags))
+				send_writers = true;
+		}
+	}
+
+	if (!send_tomtou && !send_writers)
+		return;
+
+	*pathname = ima_d_path(&file->f_path, pathbuf, filename);
+
+	if (send_tomtou)
+		ima_add_violation(file, *pathname, iint,
+				  "invalid_pcr", "ToMToU");
+	if (send_writers)
+		ima_add_violation(file, *pathname, iint,
+				  "invalid_pcr", "open_writers");
+}
+
+/*
+ * Detect file change based on STATX_CHANGE_COOKIE, when supported, and
+ * fallback to detecting file change based on i_version. On filesystems
+ * which do not support either, assume the file changed.
+ */
+static bool ima_detect_file_change(struct ima_iint_cache *iint,
+				   struct inode *inode, struct file *file)
+{
+	struct kstat stat;
+	int result;
+
+	result = vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE,
+				   AT_STATX_SYNC_AS_STAT);
+
+	if (!result && stat.result_mask & STATX_CHANGE_COOKIE)
+		return stat.change_cookie != iint->real_inode.version;
+
+	if (IS_I_VERSION(inode))
+		return !inode_eq_iversion(inode, iint->real_inode.version);
+
+	return true;
+}
+
+static void ima_check_last_writer(struct ima_iint_cache *iint,
+				  struct inode *inode, struct file *file)
+{
+	fmode_t mode = file->f_mode;
+	bool update;
+
+	if (!(mode & FMODE_WRITE))
+		return;
+
+	mutex_lock(&iint->mutex);
+	if (atomic_read(&inode->i_writecount) == 1) {
+		clear_bit(IMA_EMITTED_OPENWRITERS, &iint->atomic_flags);
+
+		update = test_and_clear_bit(IMA_UPDATE_XATTR,
+					    &iint->atomic_flags);
+
+		if (iint->flags & IMA_NEW_FILE ||
+		    ima_detect_file_change(iint, inode, file)) {
+			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
+			iint->measured_pcrs = 0;
+			if (update)
+				ima_update_xattr(iint, file);
+		}
+	}
+	mutex_unlock(&iint->mutex);
+}
+
+/**
+ * ima_file_free - called on __fput()
+ * @file: pointer to file structure being freed
+ *
+ * Flag files that changed, based on i_version
+ */
+static void ima_file_free(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+	struct ima_iint_cache *iint;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = ima_iint_find(inode);
+	if (!iint)
+		return;
+
+	ima_check_last_writer(iint, inode, file);
+}
+
+static int process_measurement(struct file *file, const struct cred *cred,
+			       struct lsm_prop *prop, char *buf, loff_t size,
+			       int mask, enum ima_hooks func,
+			       enum kernel_read_file_id read_id,
+			       bool bprm_is_check)
+{
+	struct inode *real_inode, *inode = file_inode(file);
+	struct ima_iint_cache *iint = NULL;
+	struct ima_template_desc *template_desc = NULL;
+	struct inode *metadata_inode;
+	char *pathbuf = NULL;
+	char filename[NAME_MAX];
+	const char *pathname = NULL;
+	int rc = 0, action, must_appraise = 0;
+	int pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+	struct evm_ima_xattr_data *xattr_value = NULL;
+	struct modsig *modsig = NULL;
+	int xattr_len = 0;
+	bool violation_check;
+	enum hash_algo hash_algo;
+	unsigned int allowed_algos = 0;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return 0;
+
+	/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
+	 * bitmask based on the appraise/audit/measurement policy.
+	 * Included is the appraise submask.
+	 */
+	action = ima_get_action(file_mnt_idmap(file), inode, cred, prop,
+				mask, func, &pcr, &template_desc, NULL,
+				&allowed_algos);
+	violation_check = ((func == FILE_CHECK || func == MMAP_CHECK ||
+			    func == MMAP_CHECK_REQPROT) &&
+			   (ima_policy_flag & IMA_MEASURE) &&
+			   ((action & IMA_MEASURE) ||
+			    (file->f_mode & FMODE_WRITE)));
+	if (!action && !violation_check)
+		return 0;
+
+	must_appraise = action & IMA_APPRAISE;
+
+	/*  Is the appraise rule hook specific?  */
+	if (action & IMA_FILE_APPRAISE)
+		func = FILE_CHECK;
+
+	inode_lock(inode);
+
+	if (action) {
+		iint = ima_inode_get(inode);
+		if (!iint)
+			rc = -ENOMEM;
+	}
+
+	if (!rc && violation_check)
+		ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
+					 &pathbuf, &pathname, filename);
+
+	inode_unlock(inode);
+
+	if (rc)
+		goto out;
+	if (!action)
+		goto out;
+
+	mutex_lock(&iint->mutex);
+
+	if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags))
+		/*
+		 * Reset appraisal flags (action and non-action rule-specific)
+		 * if ima_inode_post_setattr was called.
+		 */
+		iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED |
+				 IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK |
+				 IMA_NONACTION_RULE_FLAGS);
+
+	/*
+	 * Re-evaulate the file if either the xattr has changed or the
+	 * kernel has no way of detecting file change on the filesystem.
+	 * (Limited to privileged mounted filesystems.)
+	 */
+	if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) ||
+	    ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) &&
+	     !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) &&
+	     !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) {
+		iint->flags &= ~IMA_DONE_MASK;
+		iint->measured_pcrs = 0;
+	}
+
+	/*
+	 * On stacked filesystems, detect and re-evaluate file data and
+	 * metadata changes.
+	 */
+	real_inode = d_real_inode(file_dentry(file));
+	if (real_inode != inode &&
+	    (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) {
+		if (!IS_I_VERSION(real_inode) ||
+		    integrity_inode_attrs_changed(&iint->real_inode,
+						  real_inode)) {
+			iint->flags &= ~IMA_DONE_MASK;
+			iint->measured_pcrs = 0;
+		}
+
+		/*
+		 * Reset the EVM status when metadata changed.
+		 */
+		metadata_inode = d_inode(d_real(file_dentry(file),
+					 D_REAL_METADATA));
+		if (evm_metadata_changed(inode, metadata_inode))
+			iint->flags &= ~(IMA_APPRAISED |
+					 IMA_APPRAISED_SUBMASK);
+	}
+
+	/* Determine if already appraised/measured based on bitmask
+	 * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
+	 *  IMA_AUDIT, IMA_AUDITED)
+	 */
+	iint->flags |= action;
+	action &= IMA_DO_MASK;
+	action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1);
+
+	/* If target pcr is already measured, unset IMA_MEASURE action */
+	if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr)))
+		action ^= IMA_MEASURE;
+
+	/* HASH sets the digital signature and update flags, nothing else */
+	if ((action & IMA_HASH) &&
+	    !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) {
+		xattr_len = ima_read_xattr(file_dentry(file),
+					   &xattr_value, xattr_len);
+		if ((xattr_value && xattr_len > 2) &&
+		    (xattr_value->type == EVM_IMA_XATTR_DIGSIG))
+			set_bit(IMA_DIGSIG, &iint->atomic_flags);
+		iint->flags |= IMA_HASHED;
+		action ^= IMA_HASH;
+		set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
+	}
+
+	/* Nothing to do, just return existing appraised status */
+	if (!action) {
+		if (must_appraise) {
+			rc = mmap_violation_check(func, file, &pathbuf,
+						  &pathname, filename);
+			if (!rc)
+				rc = ima_get_cache_status(iint, func);
+		}
+		goto out_locked;
+	}
+
+	if ((action & IMA_APPRAISE_SUBMASK) ||
+	    strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) {
+		/* read 'security.ima' */
+		xattr_len = ima_read_xattr(file_dentry(file),
+					   &xattr_value, xattr_len);
+
+		/*
+		 * Read the appended modsig if allowed by the policy, and allow
+		 * an additional measurement list entry, if needed, based on the
+		 * template format and whether the file was already measured.
+		 */
+		if (iint->flags & IMA_MODSIG_ALLOWED) {
+			rc = ima_read_modsig(func, buf, size, &modsig);
+
+			if (!rc && ima_template_has_modsig(template_desc) &&
+			    iint->flags & IMA_MEASURED)
+				action |= IMA_MEASURE;
+		}
+	}
+
+	hash_algo = ima_get_hash_algo(xattr_value, xattr_len);
+
+	rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig);
+	if (rc != 0 && rc != -EBADF && rc != -EINVAL)
+		goto out_locked;
+
+	/* Defer measuring/appraising kernel modules to READING_MODULE */
+	if (read_id == READING_MODULE_COMPRESSED) {
+		must_appraise = 0;
+		goto out_locked;
+	}
+
+	if (!pathbuf)	/* ima_rdwr_violation possibly pre-fetched */
+		pathname = ima_d_path(&file->f_path, &pathbuf, filename);
+
+	if (action & IMA_MEASURE)
+		ima_store_measurement(iint, file, pathname,
+				      xattr_value, xattr_len, modsig, pcr,
+				      template_desc);
+	if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
+		rc = ima_check_blacklist(iint, modsig, pcr);
+		if (rc != -EPERM) {
+			inode_lock(inode);
+			rc = ima_appraise_measurement(func, iint, file,
+						      pathname, xattr_value,
+						      xattr_len, modsig,
+						      bprm_is_check);
+			inode_unlock(inode);
+		}
+		if (!rc)
+			rc = mmap_violation_check(func, file, &pathbuf,
+						  &pathname, filename);
+	}
+	if (action & IMA_AUDIT)
+		ima_audit_measurement(iint, pathname);
+
+	if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO))
+		rc = 0;
+
+	/* Ensure the digest was generated using an allowed algorithm */
+	if (rc == 0 && must_appraise && allowed_algos != 0 &&
+	    (allowed_algos & (1U << hash_algo)) == 0) {
+		rc = -EACCES;
+
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file),
+				    pathname, "collect_data",
+				    "denied-hash-algorithm", rc, 0);
+	}
+out_locked:
+	if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) &&
+	     !(iint->flags & IMA_NEW_FILE))
+		rc = -EACCES;
+	mutex_unlock(&iint->mutex);
+	kfree(xattr_value);
+	ima_free_modsig(modsig);
+out:
+	if (pathbuf)
+		__putname(pathbuf);
+	if (must_appraise) {
+		if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE))
+			return -EACCES;
+		if (file->f_mode & FMODE_WRITE)
+			set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
+	}
+	return 0;
+}
+
+/**
+ * ima_file_mmap - based on policy, collect/store measurement.
+ * @file: pointer to the file to be measured (May be NULL)
+ * @reqprot: protection requested by the application
+ * @prot: protection that will be applied by the kernel
+ * @flags: operational flags
+ *
+ * Measure files being mmapped executable based on the ima_must_measure()
+ * policy decision.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_file_mmap(struct file *file, unsigned long reqprot,
+			 unsigned long prot, unsigned long flags)
+{
+	struct lsm_prop prop;
+	int ret;
+
+	if (!file)
+		return 0;
+
+	security_current_getlsmprop_subj(&prop);
+
+	if (reqprot & PROT_EXEC) {
+		ret = process_measurement(file, current_cred(), &prop, NULL,
+					  0, MAY_EXEC, MMAP_CHECK_REQPROT, 0,
+					  false);
+		if (ret)
+			return ret;
+	}
+
+	if (prot & PROT_EXEC)
+		return process_measurement(file, current_cred(), &prop, NULL,
+					   0, MAY_EXEC, MMAP_CHECK, 0, false);
+
+	return 0;
+}
+
+/**
+ * ima_file_mprotect - based on policy, limit mprotect change
+ * @vma: vm_area_struct protection is set to
+ * @reqprot: protection requested by the application
+ * @prot: protection that will be applied by the kernel
+ *
+ * Files can be mmap'ed read/write and later changed to execute to circumvent
+ * IMA's mmap appraisal policy rules.  Due to locking issues (mmap semaphore
+ * would be taken before i_mutex), files can not be measured or appraised at
+ * this point.  Eliminate this integrity gap by denying the mprotect
+ * PROT_EXECUTE change, if an mmap appraise policy rule exists.
+ *
+ * On mprotect change success, return 0.  On failure, return -EACESS.
+ */
+static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
+			     unsigned long prot)
+{
+	struct ima_template_desc *template = NULL;
+	struct file *file;
+	char filename[NAME_MAX];
+	char *pathbuf = NULL;
+	const char *pathname = NULL;
+	struct inode *inode;
+	struct lsm_prop prop;
+	int result = 0;
+	int action;
+	int pcr;
+
+	/* Is mprotect making an mmap'ed file executable? */
+	if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file ||
+	    !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC))
+		return 0;
+
+	security_current_getlsmprop_subj(&prop);
+	inode = file_inode(vma->vm_file);
+	action = ima_get_action(file_mnt_idmap(vma->vm_file), inode,
+				current_cred(), &prop, MAY_EXEC, MMAP_CHECK,
+				&pcr, &template, NULL, NULL);
+	action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode,
+				 current_cred(), &prop, MAY_EXEC,
+				 MMAP_CHECK_REQPROT, &pcr, &template, NULL,
+				 NULL);
+
+	/* Is the mmap'ed file in policy? */
+	if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK)))
+		return 0;
+
+	if (action & IMA_APPRAISE_SUBMASK)
+		result = -EPERM;
+
+	file = vma->vm_file;
+	pathname = ima_d_path(&file->f_path, &pathbuf, filename);
+	integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname,
+			    "collect_data", "failed-mprotect", result, 0);
+	if (pathbuf)
+		__putname(pathbuf);
+
+	return result;
+}
+
+/**
+ * ima_bprm_check - based on policy, collect/store measurement.
+ * @bprm: contains the linux_binprm structure
+ *
+ * The OS protects against an executable file, already open for write,
+ * from being executed in deny_write_access() and an executable file,
+ * already open for execute, from being modified in get_write_access().
+ * So we can be certain that what we verify and measure here is actually
+ * what is being executed.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_bprm_check(struct linux_binprm *bprm)
+{
+	struct lsm_prop prop;
+
+	security_current_getlsmprop_subj(&prop);
+	return process_measurement(bprm->file, current_cred(),
+				   &prop, NULL, 0, MAY_EXEC, BPRM_CHECK, 0,
+				   bprm->is_check);
+}
+
+/**
+ * ima_creds_check - based on policy, collect/store measurement.
+ * @bprm: contains the linux_binprm structure
+ * @file: contains the file descriptor of the binary being executed
+ *
+ * The OS protects against an executable file, already open for write,
+ * from being executed in deny_write_access() and an executable file,
+ * already open for execute, from being modified in get_write_access().
+ * So we can be certain that what we verify and measure here is actually
+ * what is being executed.
+ *
+ * The difference from ima_bprm_check() is that ima_creds_check() is invoked
+ * only after determining the final binary to be executed without interpreter,
+ * and not when searching for intermediate binaries. The reason is that since
+ * commit 56305aa9b6fab ("exec: Compute file based creds only once"), the
+ * credentials to be applied to the process are calculated only at that stage
+ * (bprm_creds_from_file security hook instead of bprm_check_security).
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_creds_check(struct linux_binprm *bprm, const struct file *file)
+{
+	struct lsm_prop prop;
+
+	security_current_getlsmprop_subj(&prop);
+	return process_measurement((struct file *)file, bprm->cred, &prop, NULL,
+				   0, MAY_EXEC, CREDS_CHECK, 0, false);
+}
+
+/**
+ * ima_bprm_creds_for_exec - collect/store/appraise measurement.
+ * @bprm: contains the linux_binprm structure
+ *
+ * Based on the IMA policy and the execveat(2) AT_EXECVE_CHECK flag, measure
+ * and appraise the integrity of a file to be executed by script interpreters.
+ * Unlike any of the other LSM hooks where the kernel enforces file integrity,
+ * enforcing file integrity is left up to the discretion of the script
+ * interpreter (userspace).
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	/*
+	 * As security_bprm_check() is called multiple times, both
+	 * the script and the shebang interpreter are measured, appraised,
+	 * and audited. Limit usage of this LSM hook to just measuring,
+	 * appraising, and auditing the indirect script execution
+	 * (e.g. ./sh example.sh).
+	 */
+	if (!bprm->is_check)
+		return 0;
+
+	return ima_bprm_check(bprm);
+}
+
+/**
+ * ima_file_check - based on policy, collect/store measurement.
+ * @file: pointer to the file to be measured
+ * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND
+ *
+ * Measure files based on the ima_must_measure() policy decision.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_file_check(struct file *file, int mask)
+{
+	struct lsm_prop prop;
+
+	security_current_getlsmprop_subj(&prop);
+	return process_measurement(file, current_cred(), &prop, NULL, 0,
+				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
+					   MAY_APPEND), FILE_CHECK, 0, false);
+}
+
+/*
+ * ima_reset_action_flags - invalidate action flags after a content change
+ * @inode: inode of the file whose content is about to be truncated
+ *
+ * Clear IMA_DONE_MASK so the file is re-collected, re-measured,
+ * re-audited, and re-appraised on next access.
+ */
+static void ima_reset_action_flags(struct inode *inode)
+{
+	struct ima_iint_cache *iint;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = ima_iint_find(inode);
+	if (!iint)
+		return;
+
+	mutex_lock(&iint->mutex);
+	iint->flags &= ~IMA_DONE_MASK;
+	iint->measured_pcrs = 0;
+	mutex_unlock(&iint->mutex);
+	return;
+}
+
+static int ima_path_truncate(const struct path *path)
+{
+	ima_reset_action_flags(path->dentry->d_inode);
+	return 0;
+}
+
+static int ima_file_truncate(struct file *file)
+{
+	ima_reset_action_flags(file_inode(file));
+	return 0;
+}
+
+static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf,
+			    size_t buf_size)
+{
+	struct ima_iint_cache *iint = NULL, tmp_iint;
+	int rc, hash_algo;
+
+	if (ima_policy_flag) {
+		iint = ima_iint_find(inode);
+		if (iint)
+			mutex_lock(&iint->mutex);
+	}
+
+	if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) {
+		if (iint)
+			mutex_unlock(&iint->mutex);
+
+		memset(&tmp_iint, 0, sizeof(tmp_iint));
+		mutex_init(&tmp_iint.mutex);
+
+		rc = ima_collect_measurement(&tmp_iint, file, NULL, 0,
+					     ima_hash_algo, NULL);
+		if (rc < 0) {
+			/* ima_hash could be allocated in case of failure. */
+			if (rc != -ENOMEM)
+				kfree(tmp_iint.ima_hash);
+
+			return -EOPNOTSUPP;
+		}
+
+		iint = &tmp_iint;
+		mutex_lock(&iint->mutex);
+	}
+
+	if (!iint)
+		return -EOPNOTSUPP;
+
+	/*
+	 * ima_file_hash can be called when ima_collect_measurement has still
+	 * not been called, we might not always have a hash.
+	 */
+	if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) {
+		mutex_unlock(&iint->mutex);
+		return -EOPNOTSUPP;
+	}
+
+	if (buf) {
+		size_t copied_size;
+
+		copied_size = min_t(size_t, iint->ima_hash->length, buf_size);
+		memcpy(buf, iint->ima_hash->digest, copied_size);
+	}
+	hash_algo = iint->ima_hash->algo;
+	mutex_unlock(&iint->mutex);
+
+	if (iint == &tmp_iint)
+		kfree(iint->ima_hash);
+
+	return hash_algo;
+}
+
+/**
+ * ima_file_hash - return a measurement of the file
+ * @file: pointer to the file
+ * @buf: buffer in which to store the hash
+ * @buf_size: length of the buffer
+ *
+ * On success, return the hash algorithm (as defined in the enum hash_algo).
+ * If buf is not NULL, this function also outputs the hash into buf.
+ * If the hash is larger than buf_size, then only buf_size bytes will be copied.
+ * It generally just makes sense to pass a buffer capable of holding the largest
+ * possible hash: IMA_MAX_DIGEST_SIZE.
+ * The file hash returned is based on the entire file, including the appended
+ * signature.
+ *
+ * If the measurement cannot be performed, return -EOPNOTSUPP.
+ * If the parameters are incorrect, return -EINVAL.
+ */
+int ima_file_hash(struct file *file, char *buf, size_t buf_size)
+{
+	if (!file)
+		return -EINVAL;
+
+	return __ima_inode_hash(file_inode(file), file, buf, buf_size);
+}
+EXPORT_SYMBOL_GPL(ima_file_hash);
+
+/**
+ * ima_inode_hash - return the stored measurement if the inode has been hashed
+ * and is in the iint cache.
+ * @inode: pointer to the inode
+ * @buf: buffer in which to store the hash
+ * @buf_size: length of the buffer
+ *
+ * On success, return the hash algorithm (as defined in the enum hash_algo).
+ * If buf is not NULL, this function also outputs the hash into buf.
+ * If the hash is larger than buf_size, then only buf_size bytes will be copied.
+ * It generally just makes sense to pass a buffer capable of holding the largest
+ * possible hash: IMA_MAX_DIGEST_SIZE.
+ * The hash returned is based on the entire contents, including the appended
+ * signature.
+ *
+ * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP.
+ * If the parameters are incorrect, return -EINVAL.
+ */
+int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size)
+{
+	if (!inode)
+		return -EINVAL;
+
+	return __ima_inode_hash(inode, NULL, buf, buf_size);
+}
+EXPORT_SYMBOL_GPL(ima_inode_hash);
+
+/**
+ * ima_post_create_tmpfile - mark newly created tmpfile as new
+ * @idmap: idmap of the mount the inode was found from
+ * @inode: inode of the newly created tmpfile
+ *
+ * No measuring, appraising or auditing of newly created tmpfiles is needed.
+ * Skip calling process_measurement(), but indicate which newly, created
+ * tmpfiles are in policy.
+ */
+static void ima_post_create_tmpfile(struct mnt_idmap *idmap,
+				    struct inode *inode)
+
+{
+	struct ima_iint_cache *iint;
+	int must_appraise;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return;
+
+	must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS,
+					  FILE_CHECK);
+	if (!must_appraise)
+		return;
+
+	/* Nothing to do if we can't allocate memory */
+	iint = ima_inode_get(inode);
+	if (!iint)
+		return;
+
+	/* needed for writing the security xattrs */
+	set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags);
+	iint->ima_file_status = INTEGRITY_PASS;
+}
+
+/**
+ * ima_post_path_mknod - mark as a new inode
+ * @idmap: idmap of the mount the inode was found from
+ * @dentry: newly created dentry
+ *
+ * Mark files created via the mknodat syscall as new, so that the
+ * file data can be written later.
+ */
+static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry)
+{
+	struct ima_iint_cache *iint;
+	struct inode *inode = dentry->d_inode;
+	int must_appraise;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return;
+
+	must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS,
+					  FILE_CHECK);
+	if (!must_appraise)
+		return;
+
+	/* Nothing to do if we can't allocate memory */
+	iint = ima_inode_get(inode);
+	if (!iint)
+		return;
+
+	/* needed for re-opening empty files */
+	iint->flags |= IMA_NEW_FILE;
+}
+
+/**
+ * ima_read_file - pre-measure/appraise hook decision based on policy
+ * @file: pointer to the file to be measured/appraised/audit
+ * @read_id: caller identifier
+ * @contents: whether a subsequent call will be made to ima_post_read_file()
+ *
+ * Permit reading a file based on policy. The policy rules are written
+ * in terms of the policy identifier.  Appraising the integrity of
+ * a file requires a file descriptor.
+ *
+ * For permission return 0, otherwise return -EACCES.
+ */
+static int ima_read_file(struct file *file, enum kernel_read_file_id read_id,
+			 bool contents)
+{
+	enum ima_hooks func;
+	struct lsm_prop prop;
+
+	/*
+	 * Do devices using pre-allocated memory run the risk of the
+	 * firmware being accessible to the device prior to the completion
+	 * of IMA's signature verification any more than when using two
+	 * buffers? It may be desirable to include the buffer address
+	 * in this API and walk all the dma_map_single() mappings to check.
+	 */
+
+	/*
+	 * There will be a call made to ima_post_read_file() with
+	 * a filled buffer, so we don't need to perform an extra
+	 * read early here.
+	 */
+	if (contents)
+		return 0;
+
+	/* Read entire file for all partial reads. */
+	func = read_idmap[read_id] ?: FILE_CHECK;
+	security_current_getlsmprop_subj(&prop);
+	return process_measurement(file, current_cred(), &prop, NULL, 0,
+				   MAY_READ, func, 0, false);
+}
+
+const int read_idmap[READING_MAX_ID] = {
+	[READING_FIRMWARE] = FIRMWARE_CHECK,
+	[READING_MODULE] = MODULE_CHECK,
+	[READING_MODULE_COMPRESSED] = MODULE_CHECK,
+	[READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK,
+	[READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK,
+	[READING_POLICY] = POLICY_CHECK
+};
+
+/**
+ * ima_post_read_file - in memory collect/appraise/audit measurement
+ * @file: pointer to the file to be measured/appraised/audit
+ * @buf: pointer to in memory file contents
+ * @size: size of in memory file contents
+ * @read_id: caller identifier
+ *
+ * Measure/appraise/audit in memory file based on policy.  Policy rules
+ * are written in terms of a policy identifier.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_post_read_file(struct file *file, char *buf, loff_t size,
+			      enum kernel_read_file_id read_id)
+{
+	enum ima_hooks func;
+	struct lsm_prop prop;
+
+	/* permit signed certs */
+	if (!file && read_id == READING_X509_CERTIFICATE)
+		return 0;
+
+	if (!file || !buf || size == 0) { /* should never happen */
+		if (ima_appraise & IMA_APPRAISE_ENFORCE)
+			return -EACCES;
+		return 0;
+	}
+
+	func = read_idmap[read_id] ?: FILE_CHECK;
+	security_current_getlsmprop_subj(&prop);
+	return process_measurement(file, current_cred(), &prop, buf, size,
+				   MAY_READ, func, read_id, false);
+}
+
+/**
+ * ima_load_data - appraise decision based on policy
+ * @id: kernel load data caller identifier
+ * @contents: whether the full contents will be available in a later
+ *	      call to ima_post_load_data().
+ *
+ * Callers of this LSM hook can not measure, appraise, or audit the
+ * data provided by userspace.  Enforce policy rules requiring a file
+ * signature (eg. kexec'ed kernel image).
+ *
+ * For permission return 0, otherwise return -EACCES.
+ */
+static int ima_load_data(enum kernel_load_data_id id, bool contents)
+{
+	bool ima_enforce, sig_enforce;
+
+	ima_enforce =
+		(ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE;
+
+	switch (id) {
+	case LOADING_KEXEC_IMAGE:
+		if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_get_secureboot()) {
+			pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
+			return -EACCES;
+		}
+
+		if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) {
+			pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
+		break;
+	case LOADING_FIRMWARE:
+		if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) {
+			pr_err("Prevent firmware sysfs fallback loading.\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
+		break;
+	case LOADING_MODULE:
+		sig_enforce = is_module_sig_enforced();
+
+		if (ima_enforce && (!sig_enforce
+				    && (ima_appraise & IMA_APPRAISE_MODULES))) {
+			pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+/**
+ * ima_post_load_data - appraise decision based on policy
+ * @buf: pointer to in memory file contents
+ * @size: size of in memory file contents
+ * @load_id: kernel load data caller identifier
+ * @description: @load_id-specific description of contents
+ *
+ * Measure/appraise/audit in memory buffer based on policy.  Policy rules
+ * are written in terms of a policy identifier.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+static int ima_post_load_data(char *buf, loff_t size,
+			      enum kernel_load_data_id load_id,
+			      char *description)
+{
+	if (load_id == LOADING_FIRMWARE) {
+		if ((ima_appraise & IMA_APPRAISE_FIRMWARE) &&
+		    (ima_appraise & IMA_APPRAISE_ENFORCE)) {
+			pr_err("Prevent firmware loading_store.\n");
+			return -EACCES; /* INTEGRITY_UNKNOWN */
+		}
+		return 0;
+	}
+
+	/*
+	 * Measure the init_module syscall buffer containing the ELF image.
+	 */
+	if (load_id == LOADING_MODULE)
+		ima_measure_critical_data("modules", "init_module",
+					  buf, size, true, NULL, 0);
+
+	return 0;
+}
+
+/**
+ * process_buffer_measurement - Measure the buffer or the buffer data hash
+ * @idmap: idmap of the mount the inode was found from
+ * @inode: inode associated with the object being measured (NULL for KEY_CHECK)
+ * @buf: pointer to the buffer that needs to be added to the log.
+ * @size: size of buffer(in bytes).
+ * @eventname: event name to be used for the buffer entry.
+ * @func: IMA hook
+ * @pcr: pcr to extend the measurement
+ * @func_data: func specific data, may be NULL
+ * @buf_hash: measure buffer data hash
+ * @digest: buffer digest will be written to
+ * @digest_len: buffer length
+ *
+ * Based on policy, either the buffer data or buffer data hash is measured
+ *
+ * Return: 0 if the buffer has been successfully measured, 1 if the digest
+ * has been written to the passed location but not added to a measurement entry,
+ * a negative value otherwise.
+ */
+int process_buffer_measurement(struct mnt_idmap *idmap,
+			       struct inode *inode, const void *buf, int size,
+			       const char *eventname, enum ima_hooks func,
+			       int pcr, const char *func_data,
+			       bool buf_hash, u8 *digest, size_t digest_len)
+{
+	int ret = 0;
+	const char *audit_cause = "ENOMEM";
+	struct ima_template_entry *entry = NULL;
+	struct ima_iint_cache iint = {};
+	struct ima_event_data event_data = {.iint = &iint,
+					    .filename = eventname,
+					    .buf = buf,
+					    .buf_len = size};
+	struct ima_template_desc *template;
+	struct ima_max_digest_data hash;
+	struct ima_digest_data *hash_hdr = container_of(&hash.hdr,
+						struct ima_digest_data, hdr);
+	char digest_hash[IMA_MAX_DIGEST_SIZE];
+	int digest_hash_len = hash_digest_size[ima_hash_algo];
+	int violation = 0;
+	int action = 0;
+	struct lsm_prop prop;
+
+	if (digest && digest_len < digest_hash_len)
+		return -EINVAL;
+
+	if (!ima_policy_flag && !digest)
+		return -ENOENT;
+
+	template = ima_template_desc_buf();
+	if (!template) {
+		ret = -EINVAL;
+		audit_cause = "ima_template_desc_buf";
+		goto out;
+	}
+
+	/*
+	 * Both LSM hooks and auxiliary based buffer measurements are
+	 * based on policy. To avoid code duplication, differentiate
+	 * between the LSM hooks and auxiliary buffer measurements,
+	 * retrieving the policy rule information only for the LSM hook
+	 * buffer measurements.
+	 */
+	if (func) {
+		security_current_getlsmprop_subj(&prop);
+		action = ima_get_action(idmap, inode, current_cred(),
+					&prop, 0, func, &pcr, &template,
+					func_data, NULL);
+		if (!(action & IMA_MEASURE) && !digest)
+			return -ENOENT;
+	}
+
+	if (!pcr)
+		pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+
+	iint.ima_hash = hash_hdr;
+	iint.ima_hash->algo = ima_hash_algo;
+	iint.ima_hash->length = hash_digest_size[ima_hash_algo];
+
+	ret = ima_calc_buffer_hash(buf, size, iint.ima_hash);
+	if (ret < 0) {
+		audit_cause = "hashing_error";
+		goto out;
+	}
+
+	if (buf_hash) {
+		memcpy(digest_hash, hash_hdr->digest, digest_hash_len);
+
+		ret = ima_calc_buffer_hash(digest_hash, digest_hash_len,
+					   iint.ima_hash);
+		if (ret < 0) {
+			audit_cause = "hashing_error";
+			goto out;
+		}
+
+		event_data.buf = digest_hash;
+		event_data.buf_len = digest_hash_len;
+	}
+
+	if (digest)
+		memcpy(digest, iint.ima_hash->digest, digest_hash_len);
+
+	if (!ima_policy_flag || (func && !(action & IMA_MEASURE)))
+		return 1;
+
+	ret = ima_alloc_init_template(&event_data, &entry, template);
+	if (ret < 0) {
+		audit_cause = "alloc_entry";
+		goto out;
+	}
+
+	ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr);
+	if (ret < 0) {
+		audit_cause = "store_entry";
+		ima_free_template_entry(entry);
+	}
+
+out:
+	if (ret < 0)
+		integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname,
+					func_measure_str(func),
+					audit_cause, ret, 0, ret);
+
+	return ret;
+}
+
+/**
+ * ima_kexec_cmdline - measure kexec cmdline boot args
+ * @kernel_fd: file descriptor of the kexec kernel being loaded
+ * @buf: pointer to buffer
+ * @size: size of buffer
+ *
+ * Buffers can only be measured, not appraised.
+ */
+void ima_kexec_cmdline(int kernel_fd, const void *buf, int size)
+{
+	if (!buf || !size)
+		return;
+
+	CLASS(fd, f)(kernel_fd);
+	if (fd_empty(f))
+		return;
+
+	process_buffer_measurement(file_mnt_idmap(fd_file(f)), file_inode(fd_file(f)),
+				   buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0,
+				   NULL, false, NULL, 0);
+}
+
+/**
+ * ima_measure_critical_data - measure kernel integrity critical data
+ * @event_label: unique event label for grouping and limiting critical data
+ * @event_name: event name for the record in the IMA measurement list
+ * @buf: pointer to buffer data
+ * @buf_len: length of buffer data (in bytes)
+ * @hash: measure buffer data hash
+ * @digest: buffer digest will be written to
+ * @digest_len: buffer length
+ *
+ * Measure data critical to the integrity of the kernel into the IMA log
+ * and extend the pcr.  Examples of critical data could be various data
+ * structures, policies, and states stored in kernel memory that can
+ * impact the integrity of the system.
+ *
+ * Return: 0 if the buffer has been successfully measured, 1 if the digest
+ * has been written to the passed location but not added to a measurement entry,
+ * a negative value otherwise.
+ */
+int ima_measure_critical_data(const char *event_label,
+			      const char *event_name,
+			      const void *buf, size_t buf_len,
+			      bool hash, u8 *digest, size_t digest_len)
+{
+	if (!event_name || !event_label || !buf || !buf_len)
+		return -ENOPARAM;
+
+	return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len,
+					  event_name, CRITICAL_DATA, 0,
+					  event_label, hash, digest,
+					  digest_len);
+}
+EXPORT_SYMBOL_GPL(ima_measure_critical_data);
+
+/**
+ * ima_measure_raw_policy - Measure the raw policy write buffer
+ * @buf: pointer to the buffer containing the raw policy data
+ * @buf_len: size of the buffer
+ *
+ * Measure the raw policy buffer sent to the IMA policy securityfs file. The
+ * buffer is written from userspace, and the measurement is performed before
+ * parsing it. This measurement includes any data written on the policy file
+ * such as malformed policy rules and comments.
+ *
+ * Return 0 on success, a negative value otherwise.
+ */
+int ima_measure_raw_policy(const char *buf, size_t buf_len)
+{
+	if (!buf || !buf_len)
+		return -EINVAL;
+
+	return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len,
+					  "ima_policy_written", POLICY_CHECK,
+					  0, NULL, false, NULL, 0);
+}
+
+#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+
+/**
+ * ima_kernel_module_request - Prevent crypto-pkcs1(rsa,*) requests
+ * @kmod_name: kernel module name
+ *
+ * Avoid a verification loop where verifying the signature of the modprobe
+ * binary requires executing modprobe itself. Since the modprobe iint->mutex
+ * is already held when the signature verification is performed, a deadlock
+ * occurs as soon as modprobe is executed within the critical region, since
+ * the same lock cannot be taken again.
+ *
+ * This happens when public_key_verify_signature(), in case of RSA algorithm,
+ * use alg_name to store internal information in order to construct an
+ * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name
+ * in order to load a kernel module with same name.
+ *
+ * Since we don't have any real "crypto-pkcs1(rsa,*)" kernel modules,
+ * we are safe to fail such module request from crypto_larval_lookup(), and
+ * avoid the verification loop.
+ *
+ * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise.
+ */
+static int ima_kernel_module_request(char *kmod_name)
+{
+	if (strncmp(kmod_name, "crypto-pkcs1(rsa,", 17) == 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */
+
+static int __init init_ima(void)
+{
+	int error;
+
+	/*Note that turning IMA off is intentionally limited to kdump kernel.*/
+	if (ima_disabled && is_kdump_kernel()) {
+		pr_info("IMA functionality is disabled");
+		return 0;
+	}
+
+	ima_appraise_parse_cmdline();
+	ima_init_template_list();
+	hash_setup(CONFIG_IMA_DEFAULT_HASH);
+	error = ima_init();
+
+	if (error && strcmp(hash_algo_name[ima_hash_algo],
+			    CONFIG_IMA_DEFAULT_HASH) != 0) {
+		pr_info("Allocating %s failed, going to use default hash algorithm %s\n",
+			hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH);
+		hash_setup_done = 0;
+		hash_setup(CONFIG_IMA_DEFAULT_HASH);
+		error = ima_init();
+	}
+
+	if (error)
+		return error;
+
+	error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier);
+	if (error)
+		pr_warn("Couldn't register LSM notifier, error %d\n", error);
+
+	if (!error)
+		ima_update_policy_flags();
+
+	return error;
+}
+
+static struct security_hook_list ima_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(bprm_check_security, ima_bprm_check),
+	LSM_HOOK_INIT(bprm_creds_for_exec, ima_bprm_creds_for_exec),
+	LSM_HOOK_INIT(bprm_creds_from_file, ima_creds_check),
+	LSM_HOOK_INIT(file_post_open, ima_file_check),
+	LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile),
+	LSM_HOOK_INIT(file_release, ima_file_free),
+	LSM_HOOK_INIT(mmap_file, ima_file_mmap),
+	LSM_HOOK_INIT(file_mprotect, ima_file_mprotect),
+	LSM_HOOK_INIT(file_truncate, ima_file_truncate),
+	LSM_HOOK_INIT(kernel_load_data, ima_load_data),
+	LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data),
+	LSM_HOOK_INIT(kernel_read_file, ima_read_file),
+	LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file),
+	LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod),
+	LSM_HOOK_INIT(path_truncate, ima_path_truncate),
+#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
+	LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update),
+#endif
+#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+	LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request),
+#endif
+	LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu),
+};
+
+static const struct lsm_id ima_lsmid = {
+	.name = "ima",
+	.id = LSM_ID_IMA,
+};
+
+static int __init init_ima_lsm(void)
+{
+	ima_iintcache_init();
+	security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid);
+	init_ima_appraise_lsm(&ima_lsmid);
+	return 0;
+}
+
+struct lsm_blob_sizes ima_blob_sizes __ro_after_init = {
+	.lbs_inode = sizeof(struct ima_iint_cache *),
+};
+
+DEFINE_LSM(ima) = {
+	.id = &ima_lsmid,
+	.init = init_ima_lsm,
+	.order = LSM_ORDER_LAST,
+	.blobs = &ima_blob_sizes,
+	/* Start IMA after the TPM is available */
+#ifndef CONFIG_IMA_INIT_LATE_SYNC
+	.initcall_late = init_ima,
+#else
+	.initcall_late_sync = init_ima,
+#endif
+};
diff --git a/security/integrity/ima/ima_modsig.c b/security/integrity/ima/ima_modsig.c
new file mode 100644
index 000000000..632c746fd
--- /dev/null
+++ b/security/integrity/ima/ima_modsig.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * IMA support for appraising module-style appended signatures.
+ *
+ * Copyright (C) 2019  IBM Corporation
+ *
+ * Author:
+ * Thiago Jung Bauermann <bauerman@linux.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/module_signature.h>
+#include <keys/asymmetric-type.h>
+#include <crypto/pkcs7.h>
+
+#include "ima.h"
+
+struct modsig {
+	struct pkcs7_message *pkcs7_msg;
+
+	enum hash_algo hash_algo;
+
+	/* This digest will go in the 'd-modsig' field of the IMA template. */
+	const u8 *digest;
+	u32 digest_size;
+
+	/*
+	 * This is what will go to the measurement list if the template requires
+	 * storing the signature.
+	 */
+	int raw_pkcs7_len;
+	u8 raw_pkcs7[] __counted_by(raw_pkcs7_len);
+};
+
+/*
+ * ima_read_modsig - Read modsig from buf.
+ *
+ * Return: 0 on success, error code otherwise.
+ */
+int ima_read_modsig(enum ima_hooks func, const void *buf, loff_t buf_len,
+		    struct modsig **modsig)
+{
+	const size_t marker_len = strlen(MODULE_SIGNATURE_MARKER);
+	const struct module_signature *sig;
+	struct modsig *hdr;
+	size_t sig_len;
+	const void *p;
+	int rc;
+
+	if (buf_len <= marker_len + sizeof(*sig))
+		return -ENOENT;
+
+	p = buf + buf_len - marker_len;
+	if (memcmp(p, MODULE_SIGNATURE_MARKER, marker_len))
+		return -ENOENT;
+
+	buf_len -= marker_len;
+	sig = (const struct module_signature *)(p - sizeof(*sig));
+
+	rc = mod_check_sig(sig, buf_len, func_tokens[func]);
+	if (rc)
+		return rc;
+
+	sig_len = be32_to_cpu(sig->sig_len);
+	buf_len -= sig_len + sizeof(*sig);
+
+	/* Allocate sig_len additional bytes to hold the raw PKCS#7 data. */
+	hdr = kzalloc_flex(*hdr, raw_pkcs7, sig_len);
+	if (!hdr)
+		return -ENOMEM;
+
+	hdr->raw_pkcs7_len = sig_len;
+	hdr->pkcs7_msg = pkcs7_parse_message(buf + buf_len, sig_len);
+	if (IS_ERR(hdr->pkcs7_msg)) {
+		rc = PTR_ERR(hdr->pkcs7_msg);
+		kfree(hdr);
+		return rc;
+	}
+
+	memcpy(hdr->raw_pkcs7, buf + buf_len, sig_len);
+
+	/* We don't know the hash algorithm yet. */
+	hdr->hash_algo = HASH_ALGO__LAST;
+
+	*modsig = hdr;
+
+	return 0;
+}
+
+/**
+ * ima_collect_modsig - Calculate the file hash without the appended signature.
+ * @modsig: parsed module signature
+ * @buf: data to verify the signature on
+ * @size: data size
+ *
+ * Since the modsig is part of the file contents, the hash used in its signature
+ * isn't the same one ordinarily calculated by IMA. Therefore PKCS7 code
+ * calculates a separate one for signature verification.
+ */
+void ima_collect_modsig(struct modsig *modsig, const void *buf, loff_t size)
+{
+	int rc;
+
+	/*
+	 * Provide the file contents (minus the appended sig) so that the PKCS7
+	 * code can calculate the file hash.
+	 */
+	size -= modsig->raw_pkcs7_len + strlen(MODULE_SIGNATURE_MARKER) +
+		sizeof(struct module_signature);
+	rc = pkcs7_supply_detached_data(modsig->pkcs7_msg, buf, size);
+	if (rc)
+		return;
+
+	/* Ask the PKCS7 code to calculate the file hash. */
+	rc = pkcs7_get_digest(modsig->pkcs7_msg, &modsig->digest,
+			      &modsig->digest_size, &modsig->hash_algo);
+}
+
+int ima_modsig_verify(struct key *keyring, const struct modsig *modsig)
+{
+	return verify_pkcs7_message_sig(NULL, 0, modsig->pkcs7_msg, keyring,
+					VERIFYING_MODULE_SIGNATURE, NULL, NULL);
+}
+
+int ima_get_modsig_digest(const struct modsig *modsig, enum hash_algo *algo,
+			  const u8 **digest, u32 *digest_size)
+{
+	*algo = modsig->hash_algo;
+	*digest = modsig->digest;
+	*digest_size = modsig->digest_size;
+
+	return 0;
+}
+
+int ima_get_raw_modsig(const struct modsig *modsig, const void **data,
+		       u32 *data_len)
+{
+	*data = &modsig->raw_pkcs7;
+	*data_len = modsig->raw_pkcs7_len;
+
+	return 0;
+}
+
+void ima_free_modsig(struct modsig *modsig)
+{
+	if (!modsig)
+		return;
+
+	pkcs7_free_message(modsig->pkcs7_msg);
+	kfree(modsig);
+}
diff --git a/security/integrity/ima/ima_mok.c b/security/integrity/ima/ima_mok.c
new file mode 100644
index 000000000..14d93d573
--- /dev/null
+++ b/security/integrity/ima/ima_mok.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 Juniper Networks, Inc.
+ *
+ * Author:
+ * Petko Manolov <petko.manolov@konsulko.com>
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <keys/system_keyring.h>
+
+
+struct key *ima_blacklist_keyring;
+
+/*
+ * Allocate the IMA blacklist keyring
+ */
+static __init int ima_mok_init(void)
+{
+	struct key_restriction *restriction;
+
+	pr_notice("Allocating IMA blacklist keyring.\n");
+
+	restriction = kzalloc_obj(struct key_restriction);
+	if (!restriction)
+		panic("Can't allocate IMA blacklist restriction.");
+
+	restriction->check = restrict_link_by_builtin_trusted;
+
+	ima_blacklist_keyring = keyring_alloc(".ima_blacklist",
+				KUIDT_INIT(0), KGIDT_INIT(0), current_cred(),
+				(KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				KEY_USR_VIEW | KEY_USR_READ |
+				KEY_USR_WRITE | KEY_USR_SEARCH,
+				KEY_ALLOC_NOT_IN_QUOTA |
+				KEY_ALLOC_SET_KEEP,
+				restriction, NULL);
+
+	if (IS_ERR(ima_blacklist_keyring))
+		panic("Can't allocate IMA blacklist keyring.");
+	return 0;
+}
+device_initcall(ima_mok_init);
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
new file mode 100644
index 000000000..f79d07bb6
--- /dev/null
+++ b/security/integrity/ima/ima_policy.c
@@ -0,0 +1,2473 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 IBM Corporation
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * ima_policy.c
+ *	- initialize default measure policy rules
+ */
+
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/kernel_read_file.h>
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/magic.h>
+#include <linux/parser.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+#include <linux/seq_file.h>
+#include <linux/ima.h>
+
+#include "ima.h"
+
+/* flags definitions */
+#define IMA_FUNC	0x0001
+#define IMA_MASK	0x0002
+#define IMA_FSMAGIC	0x0004
+#define IMA_UID		0x0008
+#define IMA_FOWNER	0x0010
+#define IMA_FSUUID	0x0020
+#define IMA_INMASK	0x0040
+#define IMA_EUID	0x0080
+#define IMA_PCR		0x0100
+#define IMA_FSNAME	0x0200
+#define IMA_KEYRINGS	0x0400
+#define IMA_LABEL	0x0800
+#define IMA_VALIDATE_ALGOS	0x1000
+#define IMA_GID		0x2000
+#define IMA_EGID	0x4000
+#define IMA_FGROUP	0x8000
+#define IMA_FS_SUBTYPE	0x10000
+
+#define UNKNOWN		0
+#define MEASURE		0x0001	/* same as IMA_MEASURE */
+#define DONT_MEASURE	0x0002
+#define APPRAISE	0x0004	/* same as IMA_APPRAISE */
+#define DONT_APPRAISE	0x0008
+#define AUDIT		0x0040
+#define DONT_AUDIT	0x0080
+#define HASH		0x0100
+#define DONT_HASH	0x0200
+
+#define INVALID_PCR(a) (((a) < 0) || \
+	(a) >= (sizeof_field(struct ima_iint_cache, measured_pcrs) * 8))
+
+static size_t max_rule_len;
+
+int ima_policy_flag;
+static int temp_ima_appraise;
+static int build_ima_appraise __ro_after_init;
+
+atomic_t ima_setxattr_allowed_hash_algorithms;
+
+#define MAX_LSM_RULES 6
+enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE,
+	LSM_SUBJ_USER, LSM_SUBJ_ROLE, LSM_SUBJ_TYPE
+};
+
+enum policy_types { ORIGINAL_TCB = 1, DEFAULT_TCB };
+
+enum policy_rule_list { IMA_DEFAULT_POLICY = 1, IMA_CUSTOM_POLICY };
+
+struct ima_rule_opt_list {
+	size_t count;
+	char *items[] __counted_by(count);
+};
+
+/*
+ * These comparators are needed nowhere outside of ima so just define them here.
+ * This pattern should hopefully never be needed outside of ima.
+ */
+static inline bool vfsuid_gt_kuid(vfsuid_t vfsuid, kuid_t kuid)
+{
+	return __vfsuid_val(vfsuid) > __kuid_val(kuid);
+}
+
+static inline bool vfsgid_gt_kgid(vfsgid_t vfsgid, kgid_t kgid)
+{
+	return __vfsgid_val(vfsgid) > __kgid_val(kgid);
+}
+
+static inline bool vfsuid_lt_kuid(vfsuid_t vfsuid, kuid_t kuid)
+{
+	return __vfsuid_val(vfsuid) < __kuid_val(kuid);
+}
+
+static inline bool vfsgid_lt_kgid(vfsgid_t vfsgid, kgid_t kgid)
+{
+	return __vfsgid_val(vfsgid) < __kgid_val(kgid);
+}
+
+struct ima_rule_entry {
+	struct list_head list;
+	int action;
+	unsigned int flags;
+	enum ima_hooks func;
+	int mask;
+	unsigned long fsmagic;
+	uuid_t fsuuid;
+	kuid_t uid;
+	kgid_t gid;
+	kuid_t fowner;
+	kgid_t fgroup;
+	bool (*uid_op)(kuid_t cred_uid, kuid_t rule_uid);    /* Handlers for operators       */
+	bool (*gid_op)(kgid_t cred_gid, kgid_t rule_gid);
+	bool (*fowner_op)(vfsuid_t vfsuid, kuid_t rule_uid); /* vfsuid_eq_kuid(), vfsuid_gt_kuid(), vfsuid_lt_kuid() */
+	bool (*fgroup_op)(vfsgid_t vfsgid, kgid_t rule_gid); /* vfsgid_eq_kgid(), vfsgid_gt_kgid(), vfsgid_lt_kgid() */
+	int pcr;
+	unsigned int allowed_algos; /* bitfield of allowed hash algorithms */
+	struct {
+		void *rule;	/* LSM file metadata specific */
+		char *args_p;	/* audit value */
+		int type;	/* audit type */
+	} lsm[MAX_LSM_RULES];
+	char *fsname;
+	char *fs_subtype;
+	struct ima_rule_opt_list *keyrings; /* Measure keys added to these keyrings */
+	struct ima_rule_opt_list *label; /* Measure data grouped under this label */
+	struct ima_template_desc *template;
+};
+
+/*
+ * sanity check in case the kernels gains more hash algorithms that can
+ * fit in an unsigned int
+ */
+static_assert(
+	8 * sizeof(unsigned int) >= HASH_ALGO__LAST,
+	"The bitfield allowed_algos in ima_rule_entry is too small to contain all the supported hash algorithms, consider using a bigger type");
+
+/*
+ * Without LSM specific knowledge, the default policy can only be
+ * written in terms of .action, .func, .mask, .fsmagic, .uid, .gid,
+ * .fowner, and .fgroup
+ */
+
+/*
+ * The minimum rule set to allow for full TCB coverage.  Measures all files
+ * opened or mmap for exec and everything read by root.  Dangerous because
+ * normal users can easily run the machine out of memory simply building
+ * and running executables.
+ */
+static struct ima_rule_entry dont_measure_rules[] __ro_after_init = {
+	{.action = DONT_MEASURE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = TMPFS_MAGIC, .func = FILE_CHECK,
+	 .flags = IMA_FSMAGIC | IMA_FUNC},
+	{.action = DONT_MEASURE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SMACK_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = CGROUP_SUPER_MAGIC,
+	 .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = CGROUP2_SUPER_MAGIC,
+	 .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC}
+};
+
+static struct ima_rule_entry original_measurement_rules[] __ro_after_init = {
+	{.action = MEASURE, .func = MMAP_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = BPRM_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ,
+	 .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq,
+	 .flags = IMA_FUNC | IMA_MASK | IMA_UID},
+	{.action = MEASURE, .func = MODULE_CHECK, .flags = IMA_FUNC},
+	{.action = MEASURE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC},
+};
+
+static struct ima_rule_entry default_measurement_rules[] __ro_after_init = {
+	{.action = MEASURE, .func = MMAP_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = BPRM_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ,
+	 .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq,
+	 .flags = IMA_FUNC | IMA_INMASK | IMA_EUID},
+	{.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ,
+	 .uid = GLOBAL_ROOT_UID, .uid_op = &uid_eq,
+	 .flags = IMA_FUNC | IMA_INMASK | IMA_UID},
+	{.action = MEASURE, .func = MODULE_CHECK, .flags = IMA_FUNC},
+	{.action = MEASURE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC},
+	{.action = MEASURE, .func = POLICY_CHECK, .flags = IMA_FUNC},
+};
+
+static struct ima_rule_entry default_appraise_rules[] __ro_after_init = {
+	{.action = DONT_APPRAISE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = TMPFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = RAMFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SMACK_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+#ifdef CONFIG_IMA_WRITE_POLICY
+	{.action = APPRAISE, .func = POLICY_CHECK,
+	.flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifndef CONFIG_IMA_APPRAISE_SIGNED_INIT
+	{.action = APPRAISE, .fowner = GLOBAL_ROOT_UID, .fowner_op = &vfsuid_eq_kuid,
+	 .flags = IMA_FOWNER},
+#else
+	/* force signature */
+	{.action = APPRAISE, .fowner = GLOBAL_ROOT_UID, .fowner_op = &vfsuid_eq_kuid,
+	 .flags = IMA_FOWNER | IMA_DIGSIG_REQUIRED},
+#endif
+};
+
+static struct ima_rule_entry build_appraise_rules[] __ro_after_init = {
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_MODULE_SIGS
+	{.action = APPRAISE, .func = MODULE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_FIRMWARE_SIGS
+	{.action = APPRAISE, .func = FIRMWARE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_KEXEC_SIGS
+	{.action = APPRAISE, .func = KEXEC_KERNEL_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_POLICY_SIGS
+	{.action = APPRAISE, .func = POLICY_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+};
+
+static struct ima_rule_entry secure_boot_rules[] __ro_after_init = {
+	{.action = APPRAISE, .func = MODULE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED |
+		  IMA_CHECK_BLACKLIST},
+	{.action = APPRAISE, .func = FIRMWARE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+	{.action = APPRAISE, .func = KEXEC_KERNEL_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+	{.action = APPRAISE, .func = POLICY_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+};
+
+static struct ima_rule_entry critical_data_rules[] __ro_after_init = {
+	{.action = MEASURE, .func = CRITICAL_DATA, .flags = IMA_FUNC},
+};
+
+/* An array of architecture specific rules */
+static struct ima_rule_entry *arch_policy_entry __ro_after_init;
+
+static LIST_HEAD(ima_default_rules);
+static LIST_HEAD(ima_policy_rules);
+static LIST_HEAD(ima_temp_rules);
+static struct list_head __rcu *ima_rules = (struct list_head __rcu *)(&ima_default_rules);
+
+static int ima_policy __initdata;
+
+static int __init default_measure_policy_setup(char *str)
+{
+	if (ima_policy)
+		return 1;
+
+	ima_policy = ORIGINAL_TCB;
+	return 1;
+}
+__setup("ima_tcb", default_measure_policy_setup);
+
+static bool ima_use_appraise_tcb __initdata;
+static bool ima_use_secure_boot __initdata;
+static bool ima_use_critical_data __initdata;
+static bool ima_fail_unverifiable_sigs __ro_after_init;
+static int __init policy_setup(char *str)
+{
+	char *p;
+
+	while ((p = strsep(&str, " |\n")) != NULL) {
+		if (*p == ' ')
+			continue;
+		if ((strcmp(p, "tcb") == 0) && !ima_policy)
+			ima_policy = DEFAULT_TCB;
+		else if (strcmp(p, "appraise_tcb") == 0)
+			ima_use_appraise_tcb = true;
+		else if (strcmp(p, "secure_boot") == 0)
+			ima_use_secure_boot = true;
+		else if (strcmp(p, "critical_data") == 0)
+			ima_use_critical_data = true;
+		else if (strcmp(p, "fail_securely") == 0)
+			ima_fail_unverifiable_sigs = true;
+		else
+			pr_err("policy \"%s\" not found", p);
+	}
+
+	return 1;
+}
+__setup("ima_policy=", policy_setup);
+
+static int __init default_appraise_policy_setup(char *str)
+{
+	ima_use_appraise_tcb = true;
+	return 1;
+}
+__setup("ima_appraise_tcb", default_appraise_policy_setup);
+
+static struct ima_rule_opt_list *ima_alloc_rule_opt_list(const substring_t *src)
+{
+	struct ima_rule_opt_list *opt_list;
+	size_t count = 0;
+	char *src_copy;
+	char *cur, *next;
+	size_t i;
+
+	src_copy = match_strdup(src);
+	if (!src_copy)
+		return ERR_PTR(-ENOMEM);
+
+	next = src_copy;
+	while ((cur = strsep(&next, "|"))) {
+		/* Don't accept an empty list item */
+		if (!(*cur)) {
+			kfree(src_copy);
+			return ERR_PTR(-EINVAL);
+		}
+		count++;
+	}
+
+	/* Don't accept an empty list */
+	if (!count) {
+		kfree(src_copy);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opt_list = kzalloc_flex(*opt_list, items, count);
+	if (!opt_list) {
+		kfree(src_copy);
+		return ERR_PTR(-ENOMEM);
+	}
+	opt_list->count = count;
+
+	/*
+	 * strsep() has already replaced all instances of '|' with '\0',
+	 * leaving a byte sequence of NUL-terminated strings. Reference each
+	 * string with the array of items.
+	 *
+	 * IMPORTANT: Ownership of the allocated buffer is transferred from
+	 * src_copy to the first element in the items array. To free the
+	 * buffer, kfree() must only be called on the first element of the
+	 * array.
+	 */
+	for (i = 0, cur = src_copy; i < count; i++) {
+		opt_list->items[i] = cur;
+		cur = strchr(cur, '\0') + 1;
+	}
+
+	return opt_list;
+}
+
+static void ima_free_rule_opt_list(struct ima_rule_opt_list *opt_list)
+{
+	if (!opt_list)
+		return;
+
+	if (opt_list->count) {
+		kfree(opt_list->items[0]);
+		opt_list->count = 0;
+	}
+
+	kfree(opt_list);
+}
+
+static void ima_lsm_free_rule(struct ima_rule_entry *entry)
+{
+	int i;
+
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		ima_filter_rule_free(entry->lsm[i].rule);
+		kfree(entry->lsm[i].args_p);
+	}
+}
+
+static void ima_free_rule(struct ima_rule_entry *entry)
+{
+	if (!entry)
+		return;
+
+	/*
+	 * entry->template->fields may be allocated in ima_parse_rule() but that
+	 * reference is owned by the corresponding ima_template_desc element in
+	 * the defined_templates list and cannot be freed here
+	 */
+	kfree(entry->fsname);
+	kfree(entry->fs_subtype);
+	ima_free_rule_opt_list(entry->keyrings);
+	ima_lsm_free_rule(entry);
+	kfree(entry);
+}
+
+static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry,
+						gfp_t gfp)
+{
+	struct ima_rule_entry *nentry;
+	int i;
+
+	/*
+	 * Immutable elements are copied over as pointers and data; only
+	 * lsm rules can change
+	 */
+	nentry = kmemdup(entry, sizeof(*nentry), gfp);
+	if (!nentry)
+		return NULL;
+
+	memset(nentry->lsm, 0, sizeof_field(struct ima_rule_entry, lsm));
+
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		if (!entry->lsm[i].args_p)
+			continue;
+
+		nentry->lsm[i].type = entry->lsm[i].type;
+		nentry->lsm[i].args_p = entry->lsm[i].args_p;
+
+		ima_filter_rule_init(nentry->lsm[i].type, Audit_equal,
+				     nentry->lsm[i].args_p,
+				     &nentry->lsm[i].rule,
+				     gfp);
+		if (!nentry->lsm[i].rule)
+			pr_warn("rule for LSM \'%s\' is undefined\n",
+				nentry->lsm[i].args_p);
+	}
+	return nentry;
+}
+
+static int ima_lsm_update_rule(struct ima_rule_entry *entry)
+{
+	int i;
+	struct ima_rule_entry *nentry;
+
+	nentry = ima_lsm_copy_rule(entry, GFP_KERNEL);
+	if (!nentry)
+		return -ENOMEM;
+
+	list_replace_rcu(&entry->list, &nentry->list);
+	synchronize_rcu();
+	/*
+	 * ima_lsm_copy_rule() shallow copied all references, except for the
+	 * LSM references, from entry to nentry so we only want to free the LSM
+	 * references and the entry itself. All other memory references will now
+	 * be owned by nentry.
+	 */
+	for (i = 0; i < MAX_LSM_RULES; i++)
+		ima_filter_rule_free(entry->lsm[i].rule);
+	kfree(entry);
+
+	return 0;
+}
+
+static bool ima_rule_contains_lsm_cond(struct ima_rule_entry *entry)
+{
+	int i;
+
+	for (i = 0; i < MAX_LSM_RULES; i++)
+		if (entry->lsm[i].args_p)
+			return true;
+
+	return false;
+}
+
+/*
+ * The LSM policy can be reloaded, leaving the IMA LSM based rules referring
+ * to the old, stale LSM policy.  Update the IMA LSM based rules to reflect
+ * the reloaded LSM policy.
+ */
+static void ima_lsm_update_rules(void)
+{
+	struct ima_rule_entry *entry, *e;
+	int result;
+
+	list_for_each_entry_safe(entry, e, &ima_policy_rules, list) {
+		if (!ima_rule_contains_lsm_cond(entry))
+			continue;
+
+		result = ima_lsm_update_rule(entry);
+		if (result) {
+			pr_err("lsm rule update error %d\n", result);
+			return;
+		}
+	}
+}
+
+int ima_lsm_policy_change(struct notifier_block *nb, unsigned long event,
+			  void *lsm_data)
+{
+	if (event != LSM_POLICY_CHANGE)
+		return NOTIFY_DONE;
+
+	ima_lsm_update_rules();
+	return NOTIFY_OK;
+}
+
+/**
+ * ima_match_rule_data - determine whether func_data matches the policy rule
+ * @rule: a pointer to a rule
+ * @func_data: data to match against the measure rule data
+ * @cred: a pointer to a credentials structure for user validation
+ *
+ * Returns true if func_data matches one in the rule, false otherwise.
+ */
+static bool ima_match_rule_data(struct ima_rule_entry *rule,
+				const char *func_data,
+				const struct cred *cred)
+{
+	const struct ima_rule_opt_list *opt_list = NULL;
+	bool matched = false;
+	size_t i;
+
+	if ((rule->flags & IMA_UID) && !rule->uid_op(cred->uid, rule->uid))
+		return false;
+
+	switch (rule->func) {
+	case KEY_CHECK:
+		if (!rule->keyrings)
+			return true;
+
+		opt_list = rule->keyrings;
+		break;
+	case CRITICAL_DATA:
+		if (!rule->label)
+			return true;
+
+		opt_list = rule->label;
+		break;
+	case POLICY_CHECK:
+		return true;
+	default:
+		return false;
+	}
+
+	if (!func_data)
+		return false;
+
+	for (i = 0; i < opt_list->count; i++) {
+		if (!strcmp(opt_list->items[i], func_data)) {
+			matched = true;
+			break;
+		}
+	}
+
+	return matched;
+}
+
+/**
+ * ima_match_rules - determine whether an inode matches the policy rule.
+ * @rule: a pointer to a rule
+ * @idmap: idmap of the mount the inode was found from
+ * @inode: a pointer to an inode
+ * @cred: a pointer to a credentials structure for user validation
+ * @prop: LSM properties of the task to be validated
+ * @func: LIM hook identifier
+ * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC)
+ * @func_data: func specific data, may be NULL
+ *
+ * Returns true on rule match, false on failure.
+ */
+static bool ima_match_rules(struct ima_rule_entry *rule,
+			    struct mnt_idmap *idmap,
+			    struct inode *inode, const struct cred *cred,
+			    struct lsm_prop *prop, enum ima_hooks func, int mask,
+			    const char *func_data)
+{
+	int i;
+	bool result = false;
+	struct ima_rule_entry *lsm_rule = rule;
+	bool rule_reinitialized = false;
+
+	if ((rule->flags & IMA_FUNC) &&
+	    (rule->func != func && func != POST_SETATTR))
+		return false;
+
+	switch (func) {
+	case POLICY_CHECK:
+		if (inode)
+			break;
+		fallthrough;
+	case KEY_CHECK:
+	case CRITICAL_DATA:
+		return ((rule->func == func) &&
+			ima_match_rule_data(rule, func_data, cred));
+	default:
+		break;
+	}
+
+	if ((rule->flags & IMA_MASK) &&
+	    (rule->mask != mask && func != POST_SETATTR))
+		return false;
+	if ((rule->flags & IMA_INMASK) &&
+	    (!(rule->mask & mask) && func != POST_SETATTR))
+		return false;
+	if ((rule->flags & IMA_FSMAGIC)
+	    && rule->fsmagic != inode->i_sb->s_magic)
+		return false;
+	if ((rule->flags & IMA_FSNAME)
+	    && strcmp(rule->fsname, inode->i_sb->s_type->name))
+		return false;
+	if (rule->flags & IMA_FS_SUBTYPE) {
+		if (!inode->i_sb->s_subtype)
+			return false;
+		if (strcmp(rule->fs_subtype, inode->i_sb->s_subtype))
+			return false;
+	}
+	if ((rule->flags & IMA_FSUUID) &&
+	    !uuid_equal(&rule->fsuuid, &inode->i_sb->s_uuid))
+		return false;
+	if ((rule->flags & IMA_UID) && !rule->uid_op(cred->uid, rule->uid))
+		return false;
+	if (rule->flags & IMA_EUID) {
+		if (has_capability_noaudit(current, CAP_SETUID)) {
+			if (!rule->uid_op(cred->euid, rule->uid)
+			    && !rule->uid_op(cred->suid, rule->uid)
+			    && !rule->uid_op(cred->uid, rule->uid))
+				return false;
+		} else if (!rule->uid_op(cred->euid, rule->uid))
+			return false;
+	}
+	if ((rule->flags & IMA_GID) && !rule->gid_op(cred->gid, rule->gid))
+		return false;
+	if (rule->flags & IMA_EGID) {
+		if (has_capability_noaudit(current, CAP_SETGID)) {
+			if (!rule->gid_op(cred->egid, rule->gid)
+			    && !rule->gid_op(cred->sgid, rule->gid)
+			    && !rule->gid_op(cred->gid, rule->gid))
+				return false;
+		} else if (!rule->gid_op(cred->egid, rule->gid))
+			return false;
+	}
+	if ((rule->flags & IMA_FOWNER) &&
+	    !rule->fowner_op(i_uid_into_vfsuid(idmap, inode),
+			     rule->fowner))
+		return false;
+	if ((rule->flags & IMA_FGROUP) &&
+	    !rule->fgroup_op(i_gid_into_vfsgid(idmap, inode),
+			     rule->fgroup))
+		return false;
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		int rc = 0;
+		struct lsm_prop inode_prop = { };
+
+		if (!lsm_rule->lsm[i].rule) {
+			if (!lsm_rule->lsm[i].args_p)
+				continue;
+			else
+				return false;
+		}
+
+retry:
+		switch (i) {
+		case LSM_OBJ_USER:
+		case LSM_OBJ_ROLE:
+		case LSM_OBJ_TYPE:
+			security_inode_getlsmprop(inode, &inode_prop);
+			rc = ima_filter_rule_match(&inode_prop,
+						   lsm_rule->lsm[i].type,
+						   Audit_equal,
+						   lsm_rule->lsm[i].rule);
+			break;
+		case LSM_SUBJ_USER:
+		case LSM_SUBJ_ROLE:
+		case LSM_SUBJ_TYPE:
+			rc = ima_filter_rule_match(prop, lsm_rule->lsm[i].type,
+						   Audit_equal,
+						   lsm_rule->lsm[i].rule);
+			break;
+		default:
+			break;
+		}
+
+		if (rc == -ESTALE && !rule_reinitialized) {
+			lsm_rule = ima_lsm_copy_rule(rule, GFP_ATOMIC);
+			if (lsm_rule) {
+				rule_reinitialized = true;
+				goto retry;
+			}
+		}
+		if (rc <= 0) {
+			result = false;
+			goto out;
+		}
+	}
+	result = true;
+
+out:
+	if (rule_reinitialized) {
+		for (i = 0; i < MAX_LSM_RULES; i++)
+			ima_filter_rule_free(lsm_rule->lsm[i].rule);
+		kfree(lsm_rule);
+	}
+	return result;
+}
+
+/*
+ * In addition to knowing that we need to appraise the file in general,
+ * we need to differentiate between calling hooks, for hook specific rules.
+ */
+static int get_subaction(struct ima_rule_entry *rule, enum ima_hooks func)
+{
+	if (!(rule->flags & IMA_FUNC))
+		return IMA_FILE_APPRAISE;
+
+	switch (func) {
+	case MMAP_CHECK:
+	case MMAP_CHECK_REQPROT:
+		return IMA_MMAP_APPRAISE;
+	case BPRM_CHECK:
+		return IMA_BPRM_APPRAISE;
+	case CREDS_CHECK:
+		return IMA_CREDS_APPRAISE;
+	case FILE_CHECK:
+	case POST_SETATTR:
+		return IMA_FILE_APPRAISE;
+	case MODULE_CHECK ... MAX_CHECK - 1:
+	default:
+		return IMA_READ_APPRAISE;
+	}
+}
+
+/**
+ * ima_match_policy - decision based on LSM and other conditions
+ * @idmap: idmap of the mount the inode was found from
+ * @inode: pointer to an inode for which the policy decision is being made
+ * @cred: pointer to a credentials structure for which the policy decision is
+ *        being made
+ * @prop: LSM properties of the task to be validated
+ * @func: IMA hook identifier
+ * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC)
+ * @flags: IMA actions to consider (e.g. IMA_MEASURE | IMA_APPRAISE)
+ * @pcr: set the pcr to extend
+ * @template_desc: the template that should be used for this rule
+ * @func_data: func specific data, may be NULL
+ * @allowed_algos: allowlist of hash algorithms for the IMA xattr
+ *
+ * Measure decision based on func/mask/fsmagic and LSM(subj/obj/type)
+ * conditions.
+ *
+ * Since the IMA policy may be updated multiple times we need to lock the
+ * list when walking it.  Reads are many orders of magnitude more numerous
+ * than writes so ima_match_policy() is classical RCU candidate.
+ */
+int ima_match_policy(struct mnt_idmap *idmap, struct inode *inode,
+		     const struct cred *cred, struct lsm_prop *prop,
+		     enum ima_hooks func, int mask, int flags, int *pcr,
+		     struct ima_template_desc **template_desc,
+		     const char *func_data, unsigned int *allowed_algos)
+{
+	struct ima_rule_entry *entry;
+	int action = 0, actmask = flags | (flags << 1);
+	struct list_head *ima_rules_tmp;
+
+	if (template_desc && !*template_desc)
+		*template_desc = ima_template_desc_current();
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(entry, ima_rules_tmp, list) {
+
+		if (!(entry->action & actmask))
+			continue;
+
+		if (!ima_match_rules(entry, idmap, inode, cred, prop,
+				     func, mask, func_data))
+			continue;
+
+		action |= entry->flags & IMA_NONACTION_FLAGS;
+
+		action |= entry->action & IMA_DO_MASK;
+		if (entry->action & IMA_APPRAISE) {
+			action |= get_subaction(entry, func);
+			action &= ~IMA_HASH;
+			if (ima_fail_unverifiable_sigs)
+				action |= IMA_FAIL_UNVERIFIABLE_SIGS;
+
+			if (allowed_algos &&
+			    entry->flags & IMA_VALIDATE_ALGOS)
+				*allowed_algos = entry->allowed_algos;
+		}
+
+		if (entry->action & IMA_DO_MASK)
+			actmask &= ~(entry->action | entry->action << 1);
+		else
+			actmask &= ~(entry->action | entry->action >> 1);
+
+		if ((pcr) && (entry->flags & IMA_PCR))
+			*pcr = entry->pcr;
+
+		if (template_desc && entry->template)
+			*template_desc = entry->template;
+
+		if (!actmask)
+			break;
+	}
+	rcu_read_unlock();
+
+	return action;
+}
+
+/**
+ * ima_update_policy_flags() - Update global IMA variables
+ *
+ * Update ima_policy_flag and ima_setxattr_allowed_hash_algorithms
+ * based on the currently loaded policy.
+ *
+ * With ima_policy_flag, the decision to short circuit out of a function
+ * or not call the function in the first place can be made earlier.
+ *
+ * With ima_setxattr_allowed_hash_algorithms, the policy can restrict the
+ * set of hash algorithms accepted when updating the security.ima xattr of
+ * a file.
+ *
+ * Context: called after a policy update and at system initialization.
+ */
+void ima_update_policy_flags(void)
+{
+	struct ima_rule_entry *entry;
+	int new_policy_flag = 0;
+	struct list_head *ima_rules_tmp;
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(entry, ima_rules_tmp, list) {
+		/*
+		 * SETXATTR_CHECK rules do not implement a full policy check
+		 * because rule checking would probably have an important
+		 * performance impact on setxattr(). As a consequence, only one
+		 * SETXATTR_CHECK can be active at a given time.
+		 * Because we want to preserve that property, we set out to use
+		 * atomic_cmpxchg. Either:
+		 * - the atomic was non-zero: a setxattr hash policy is
+		 *   already enforced, we do nothing
+		 * - the atomic was zero: no setxattr policy was set, enable
+		 *   the setxattr hash policy
+		 */
+		if (entry->func == SETXATTR_CHECK) {
+			atomic_cmpxchg(&ima_setxattr_allowed_hash_algorithms,
+				       0, entry->allowed_algos);
+			/* SETXATTR_CHECK doesn't impact ima_policy_flag */
+			continue;
+		}
+
+		if (entry->action & IMA_DO_MASK)
+			new_policy_flag |= entry->action;
+	}
+	rcu_read_unlock();
+
+	ima_appraise |= (build_ima_appraise | temp_ima_appraise);
+	if (!ima_appraise)
+		new_policy_flag &= ~IMA_APPRAISE;
+
+	ima_policy_flag = new_policy_flag;
+}
+
+static int ima_appraise_flag(enum ima_hooks func)
+{
+	if (func == MODULE_CHECK)
+		return IMA_APPRAISE_MODULES;
+	else if (func == FIRMWARE_CHECK)
+		return IMA_APPRAISE_FIRMWARE;
+	else if (func == POLICY_CHECK)
+		return IMA_APPRAISE_POLICY;
+	else if (func == KEXEC_KERNEL_CHECK)
+		return IMA_APPRAISE_KEXEC;
+	return 0;
+}
+
+static void add_rules(struct ima_rule_entry *entries, int count,
+		      enum policy_rule_list policy_rule)
+{
+	int i = 0;
+
+	for (i = 0; i < count; i++) {
+		struct ima_rule_entry *entry;
+
+		if (policy_rule & IMA_DEFAULT_POLICY)
+			list_add_tail(&entries[i].list, &ima_default_rules);
+
+		if (policy_rule & IMA_CUSTOM_POLICY) {
+			entry = kmemdup(&entries[i], sizeof(*entry),
+					GFP_KERNEL);
+			if (!entry)
+				continue;
+
+			list_add_tail(&entry->list, &ima_policy_rules);
+		}
+		if (entries[i].action == APPRAISE) {
+			if (entries != build_appraise_rules)
+				temp_ima_appraise |=
+					ima_appraise_flag(entries[i].func);
+			else
+				build_ima_appraise |=
+					ima_appraise_flag(entries[i].func);
+		}
+	}
+}
+
+static int ima_parse_rule(char *rule, struct ima_rule_entry *entry);
+
+static int __init ima_init_arch_policy(void)
+{
+	const char * const *arch_rules;
+	const char * const *rules;
+	int arch_entries = 0;
+	int i = 0;
+
+	arch_rules = arch_get_ima_policy();
+	if (!arch_rules)
+		return arch_entries;
+
+	/* Get number of rules */
+	for (rules = arch_rules; *rules != NULL; rules++)
+		arch_entries++;
+
+	arch_policy_entry = kzalloc_objs(*arch_policy_entry, arch_entries + 1);
+	if (!arch_policy_entry)
+		return 0;
+
+	/* Convert each policy string rules to struct ima_rule_entry format */
+	for (rules = arch_rules, i = 0; *rules != NULL; rules++) {
+		char rule[255];
+		int result;
+
+		result = strscpy(rule, *rules, sizeof(rule));
+
+		INIT_LIST_HEAD(&arch_policy_entry[i].list);
+		result = ima_parse_rule(rule, &arch_policy_entry[i]);
+		if (result) {
+			pr_warn("Skipping unknown architecture policy rule: %s\n",
+				rule);
+			memset(&arch_policy_entry[i], 0,
+			       sizeof(*arch_policy_entry));
+			continue;
+		}
+		i++;
+	}
+	return i;
+}
+
+/**
+ * ima_init_policy - initialize the default measure rules.
+ *
+ * ima_rules points to either the ima_default_rules or the new ima_policy_rules.
+ */
+void __init ima_init_policy(void)
+{
+	int build_appraise_entries, arch_entries;
+
+	max_rule_len = 255;
+
+	/* if !ima_policy, we load NO default rules */
+	if (ima_policy)
+		add_rules(dont_measure_rules, ARRAY_SIZE(dont_measure_rules),
+			  IMA_DEFAULT_POLICY);
+
+	switch (ima_policy) {
+	case ORIGINAL_TCB:
+		add_rules(original_measurement_rules,
+			  ARRAY_SIZE(original_measurement_rules),
+			  IMA_DEFAULT_POLICY);
+		break;
+	case DEFAULT_TCB:
+		add_rules(default_measurement_rules,
+			  ARRAY_SIZE(default_measurement_rules),
+			  IMA_DEFAULT_POLICY);
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * Based on runtime secure boot flags, insert arch specific measurement
+	 * and appraise rules requiring file signatures for both the initial
+	 * and custom policies, prior to other appraise rules.
+	 * (Highest priority)
+	 */
+	arch_entries = ima_init_arch_policy();
+	if (!arch_entries)
+		pr_info("No architecture policies found\n");
+	else
+		add_rules(arch_policy_entry, arch_entries,
+			  IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY);
+
+	/*
+	 * Insert the builtin "secure_boot" policy rules requiring file
+	 * signatures, prior to other appraise rules.
+	 */
+	if (ima_use_secure_boot)
+		add_rules(secure_boot_rules, ARRAY_SIZE(secure_boot_rules),
+			  IMA_DEFAULT_POLICY);
+
+	/*
+	 * Insert the build time appraise rules requiring file signatures
+	 * for both the initial and custom policies, prior to other appraise
+	 * rules. As the secure boot rules includes all of the build time
+	 * rules, include either one or the other set of rules, but not both.
+	 */
+	build_appraise_entries = ARRAY_SIZE(build_appraise_rules);
+	if (build_appraise_entries) {
+		if (ima_use_secure_boot)
+			add_rules(build_appraise_rules, build_appraise_entries,
+				  IMA_CUSTOM_POLICY);
+		else
+			add_rules(build_appraise_rules, build_appraise_entries,
+				  IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY);
+	}
+
+	if (ima_use_appraise_tcb)
+		add_rules(default_appraise_rules,
+			  ARRAY_SIZE(default_appraise_rules),
+			  IMA_DEFAULT_POLICY);
+
+	if (ima_use_critical_data)
+		add_rules(critical_data_rules,
+			  ARRAY_SIZE(critical_data_rules),
+			  IMA_DEFAULT_POLICY);
+
+	atomic_set(&ima_setxattr_allowed_hash_algorithms, 0);
+
+	ima_update_policy_flags();
+}
+
+/* Make sure we have a valid policy, at least containing some rules. */
+int ima_check_policy(void)
+{
+	if (list_empty(&ima_temp_rules))
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * ima_update_policy - update default_rules with new measure rules
+ *
+ * Called on file .release to update the default rules with a complete new
+ * policy.  What we do here is to splice ima_policy_rules and ima_temp_rules so
+ * they make a queue.  The policy may be updated multiple times and this is the
+ * RCU updater.
+ *
+ * Policy rules are never deleted so ima_policy_flag gets zeroed only once when
+ * we switch from the default policy to user defined.
+ */
+void ima_update_policy(void)
+{
+	struct list_head *policy = &ima_policy_rules;
+
+	list_splice_tail_init_rcu(&ima_temp_rules, policy, synchronize_rcu);
+
+	if (ima_rules != (struct list_head __rcu *)policy) {
+		ima_policy_flag = 0;
+
+		rcu_assign_pointer(ima_rules, policy);
+		/*
+		 * IMA architecture specific policy rules are specified
+		 * as strings and converted to an array of ima_entry_rules
+		 * on boot.  After loading a custom policy, free the
+		 * architecture specific rules stored as an array.
+		 */
+		kfree(arch_policy_entry);
+	}
+	ima_update_policy_flags();
+
+	/* Custom IMA policy has been loaded */
+	ima_process_queued_keys();
+}
+
+/* Keep the enumeration in sync with the policy_tokens! */
+enum policy_opt {
+	Opt_measure, Opt_dont_measure,
+	Opt_appraise, Opt_dont_appraise,
+	Opt_audit, Opt_dont_audit, Opt_hash, Opt_dont_hash,
+	Opt_obj_user, Opt_obj_role, Opt_obj_type,
+	Opt_subj_user, Opt_subj_role, Opt_subj_type,
+	Opt_func, Opt_mask, Opt_fsmagic, Opt_fsname, Opt_fs_subtype, Opt_fsuuid,
+	Opt_uid_eq, Opt_euid_eq, Opt_gid_eq, Opt_egid_eq,
+	Opt_fowner_eq, Opt_fgroup_eq,
+	Opt_uid_gt, Opt_euid_gt, Opt_gid_gt, Opt_egid_gt,
+	Opt_fowner_gt, Opt_fgroup_gt,
+	Opt_uid_lt, Opt_euid_lt, Opt_gid_lt, Opt_egid_lt,
+	Opt_fowner_lt, Opt_fgroup_lt,
+	Opt_digest_type,
+	Opt_appraise_type, Opt_appraise_flag, Opt_appraise_algos,
+	Opt_permit_directio, Opt_pcr, Opt_template, Opt_keyrings,
+	Opt_label, Opt_err
+};
+
+static const match_table_t policy_tokens = {
+	{Opt_measure, "measure"},
+	{Opt_dont_measure, "dont_measure"},
+	{Opt_appraise, "appraise"},
+	{Opt_dont_appraise, "dont_appraise"},
+	{Opt_audit, "audit"},
+	{Opt_dont_audit, "dont_audit"},
+	{Opt_hash, "hash"},
+	{Opt_dont_hash, "dont_hash"},
+	{Opt_obj_user, "obj_user=%s"},
+	{Opt_obj_role, "obj_role=%s"},
+	{Opt_obj_type, "obj_type=%s"},
+	{Opt_subj_user, "subj_user=%s"},
+	{Opt_subj_role, "subj_role=%s"},
+	{Opt_subj_type, "subj_type=%s"},
+	{Opt_func, "func=%s"},
+	{Opt_mask, "mask=%s"},
+	{Opt_fsmagic, "fsmagic=%s"},
+	{Opt_fsname, "fsname=%s"},
+	{Opt_fs_subtype, "fs_subtype=%s"},
+	{Opt_fsuuid, "fsuuid=%s"},
+	{Opt_uid_eq, "uid=%s"},
+	{Opt_euid_eq, "euid=%s"},
+	{Opt_gid_eq, "gid=%s"},
+	{Opt_egid_eq, "egid=%s"},
+	{Opt_fowner_eq, "fowner=%s"},
+	{Opt_fgroup_eq, "fgroup=%s"},
+	{Opt_uid_gt, "uid>%s"},
+	{Opt_euid_gt, "euid>%s"},
+	{Opt_gid_gt, "gid>%s"},
+	{Opt_egid_gt, "egid>%s"},
+	{Opt_fowner_gt, "fowner>%s"},
+	{Opt_fgroup_gt, "fgroup>%s"},
+	{Opt_uid_lt, "uid<%s"},
+	{Opt_euid_lt, "euid<%s"},
+	{Opt_gid_lt, "gid<%s"},
+	{Opt_egid_lt, "egid<%s"},
+	{Opt_fowner_lt, "fowner<%s"},
+	{Opt_fgroup_lt, "fgroup<%s"},
+	{Opt_digest_type, "digest_type=%s"},
+	{Opt_appraise_type, "appraise_type=%s"},
+	{Opt_appraise_flag, "appraise_flag=%s"},
+	{Opt_appraise_algos, "appraise_algos=%s"},
+	{Opt_permit_directio, "permit_directio"},
+	{Opt_pcr, "pcr=%s"},
+	{Opt_template, "template=%s"},
+	{Opt_keyrings, "keyrings=%s"},
+	{Opt_label, "label=%s"},
+	{Opt_err, NULL}
+};
+
+static int ima_lsm_rule_init(struct ima_rule_entry *entry,
+			     substring_t *args, int lsm_rule, int audit_type)
+{
+	int result;
+
+	if (entry->lsm[lsm_rule].rule)
+		return -EINVAL;
+
+	entry->lsm[lsm_rule].args_p = match_strdup(args);
+	if (!entry->lsm[lsm_rule].args_p)
+		return -ENOMEM;
+
+	entry->lsm[lsm_rule].type = audit_type;
+	result = ima_filter_rule_init(entry->lsm[lsm_rule].type, Audit_equal,
+				      entry->lsm[lsm_rule].args_p,
+				      &entry->lsm[lsm_rule].rule,
+				      GFP_KERNEL);
+	if (!entry->lsm[lsm_rule].rule) {
+		pr_warn("rule for LSM \'%s\' is undefined\n",
+			entry->lsm[lsm_rule].args_p);
+
+		if (ima_rules == (struct list_head __rcu *)(&ima_default_rules)) {
+			kfree(entry->lsm[lsm_rule].args_p);
+			entry->lsm[lsm_rule].args_p = NULL;
+			result = -EINVAL;
+		} else
+			result = 0;
+	}
+
+	return result;
+}
+
+static void ima_log_string_op(struct audit_buffer *ab, char *key, char *value,
+			      enum policy_opt rule_operator)
+{
+	if (!ab)
+		return;
+
+	switch (rule_operator) {
+	case Opt_uid_gt:
+	case Opt_euid_gt:
+	case Opt_gid_gt:
+	case Opt_egid_gt:
+	case Opt_fowner_gt:
+	case Opt_fgroup_gt:
+		audit_log_format(ab, "%s>", key);
+		break;
+	case Opt_uid_lt:
+	case Opt_euid_lt:
+	case Opt_gid_lt:
+	case Opt_egid_lt:
+	case Opt_fowner_lt:
+	case Opt_fgroup_lt:
+		audit_log_format(ab, "%s<", key);
+		break;
+	default:
+		audit_log_format(ab, "%s=", key);
+	}
+	audit_log_format(ab, "%s ", value);
+}
+static void ima_log_string(struct audit_buffer *ab, char *key, char *value)
+{
+	ima_log_string_op(ab, key, value, Opt_err);
+}
+
+/*
+ * Validating the appended signature included in the measurement list requires
+ * the file hash calculated without the appended signature (i.e., the 'd-modsig'
+ * field). Therefore, notify the user if they have the 'modsig' field but not
+ * the 'd-modsig' field in the template.
+ */
+static void check_template_modsig(const struct ima_template_desc *template)
+{
+#define MSG "template with 'modsig' field also needs 'd-modsig' field\n"
+	bool has_modsig, has_dmodsig;
+	static bool checked;
+	int i;
+
+	/* We only need to notify the user once. */
+	if (checked)
+		return;
+
+	has_modsig = has_dmodsig = false;
+	for (i = 0; i < template->num_fields; i++) {
+		if (!strcmp(template->fields[i]->field_id, "modsig"))
+			has_modsig = true;
+		else if (!strcmp(template->fields[i]->field_id, "d-modsig"))
+			has_dmodsig = true;
+	}
+
+	if (has_modsig && !has_dmodsig)
+		pr_notice(MSG);
+
+	checked = true;
+#undef MSG
+}
+
+/*
+ * Warn if the template does not contain the given field.
+ */
+static void check_template_field(const struct ima_template_desc *template,
+				 const char *field, const char *msg)
+{
+	int i;
+
+	for (i = 0; i < template->num_fields; i++)
+		if (!strcmp(template->fields[i]->field_id, field))
+			return;
+
+	pr_notice_once("%s", msg);
+}
+
+static bool ima_validate_rule(struct ima_rule_entry *entry)
+{
+	/* Ensure that the action is set and is compatible with the flags */
+	if (entry->action == UNKNOWN)
+		return false;
+
+	if (entry->action != MEASURE && entry->flags & IMA_PCR)
+		return false;
+
+	if (entry->action != APPRAISE &&
+	    entry->flags & (IMA_DIGSIG_REQUIRED | IMA_MODSIG_ALLOWED |
+			    IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS))
+		return false;
+
+	/*
+	 * The IMA_FUNC bit must be set if and only if there's a valid hook
+	 * function specified, and vice versa. Enforcing this property allows
+	 * for the NONE case below to validate a rule without an explicit hook
+	 * function.
+	 */
+	if (((entry->flags & IMA_FUNC) && entry->func == NONE) ||
+	    (!(entry->flags & IMA_FUNC) && entry->func != NONE))
+		return false;
+
+	/*
+	 * Ensure that the hook function is compatible with the other
+	 * components of the rule
+	 */
+	switch (entry->func) {
+	case NONE:
+	case FILE_CHECK:
+	case MMAP_CHECK:
+	case MMAP_CHECK_REQPROT:
+	case BPRM_CHECK:
+	case CREDS_CHECK:
+	case POST_SETATTR:
+	case FIRMWARE_CHECK:
+	case POLICY_CHECK:
+		if (entry->flags & ~(IMA_FUNC | IMA_MASK | IMA_FSMAGIC |
+				     IMA_UID | IMA_FOWNER | IMA_FSUUID |
+				     IMA_INMASK | IMA_EUID | IMA_PCR |
+				     IMA_FSNAME | IMA_FS_SUBTYPE |
+				     IMA_GID | IMA_EGID |
+				     IMA_FGROUP | IMA_DIGSIG_REQUIRED |
+				     IMA_PERMIT_DIRECTIO | IMA_VALIDATE_ALGOS |
+				     IMA_CHECK_BLACKLIST | IMA_VERITY_REQUIRED |
+				     IMA_SIGV3_REQUIRED))
+			return false;
+
+		break;
+	case MODULE_CHECK:
+	case KEXEC_KERNEL_CHECK:
+	case KEXEC_INITRAMFS_CHECK:
+		if (entry->flags & ~(IMA_FUNC | IMA_MASK | IMA_FSMAGIC |
+				     IMA_UID | IMA_FOWNER | IMA_FSUUID |
+				     IMA_INMASK | IMA_EUID | IMA_PCR |
+				     IMA_FSNAME | IMA_FS_SUBTYPE |
+				     IMA_GID | IMA_EGID |
+				     IMA_FGROUP | IMA_DIGSIG_REQUIRED |
+				     IMA_PERMIT_DIRECTIO | IMA_MODSIG_ALLOWED |
+				     IMA_CHECK_BLACKLIST | IMA_VALIDATE_ALGOS |
+				     IMA_SIGV3_REQUIRED))
+			return false;
+
+		break;
+	case KEXEC_CMDLINE:
+		if (entry->action & ~(MEASURE | DONT_MEASURE))
+			return false;
+
+		if (entry->flags & ~(IMA_FUNC | IMA_FSMAGIC | IMA_UID |
+				     IMA_FOWNER | IMA_FSUUID | IMA_EUID |
+				     IMA_PCR | IMA_FSNAME | IMA_FS_SUBTYPE |
+				     IMA_GID | IMA_EGID |
+				     IMA_FGROUP))
+			return false;
+
+		break;
+	case KEY_CHECK:
+		if (entry->action & ~(MEASURE | DONT_MEASURE))
+			return false;
+
+		if (entry->flags & ~(IMA_FUNC | IMA_UID | IMA_GID | IMA_PCR |
+				     IMA_KEYRINGS))
+			return false;
+
+		if (ima_rule_contains_lsm_cond(entry))
+			return false;
+
+		break;
+	case CRITICAL_DATA:
+		if (entry->action & ~(MEASURE | DONT_MEASURE))
+			return false;
+
+		if (entry->flags & ~(IMA_FUNC | IMA_UID | IMA_GID | IMA_PCR |
+				     IMA_LABEL))
+			return false;
+
+		if (ima_rule_contains_lsm_cond(entry))
+			return false;
+
+		break;
+	case SETXATTR_CHECK:
+		/* any action other than APPRAISE is unsupported */
+		if (entry->action != APPRAISE)
+			return false;
+
+		/* SETXATTR_CHECK requires an appraise_algos parameter */
+		if (!(entry->flags & IMA_VALIDATE_ALGOS))
+			return false;
+
+		/*
+		 * full policies are not supported, they would have too
+		 * much of a performance impact
+		 */
+		if (entry->flags & ~(IMA_FUNC | IMA_VALIDATE_ALGOS))
+			return false;
+
+		break;
+	default:
+		return false;
+	}
+
+	/* Ensure that combinations of flags are compatible with each other */
+	if (entry->flags & IMA_CHECK_BLACKLIST &&
+	    !(entry->flags & IMA_DIGSIG_REQUIRED))
+		return false;
+
+	/*
+	 * Unlike for regular IMA 'appraise' policy rules where security.ima
+	 * xattr may contain either a file hash or signature, the security.ima
+	 * xattr for fsverity must contain a file signature (sigv3).  Ensure
+	 * that 'appraise' rules for fsverity require file signatures by
+	 * checking the IMA_DIGSIG_REQUIRED flag is set.
+	 */
+	if (entry->action == APPRAISE &&
+	    (entry->flags & IMA_VERITY_REQUIRED) &&
+	    !(entry->flags & IMA_DIGSIG_REQUIRED))
+		return false;
+
+	return true;
+}
+
+static unsigned int ima_parse_appraise_algos(char *arg)
+{
+	unsigned int res = 0;
+	int idx;
+	char *token;
+
+	while ((token = strsep(&arg, ",")) != NULL) {
+		idx = match_string(hash_algo_name, HASH_ALGO__LAST, token);
+
+		if (idx < 0) {
+			pr_err("unknown hash algorithm \"%s\"",
+			       token);
+			return 0;
+		}
+
+		if (!crypto_has_alg(hash_algo_name[idx], 0, 0)) {
+			pr_err("unavailable hash algorithm \"%s\", check your kernel configuration",
+			       token);
+			return 0;
+		}
+
+		/* Add the hash algorithm to the 'allowed' bitfield */
+		res |= (1U << idx);
+	}
+
+	return res;
+}
+
+static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
+{
+	struct audit_buffer *ab;
+	char *from;
+	char *p;
+	bool eid_token; /* either euid or egid */
+	struct ima_template_desc *template_desc;
+	int result = 0;
+
+	ab = integrity_audit_log_start(audit_context(), GFP_KERNEL,
+				       AUDIT_INTEGRITY_POLICY_RULE);
+
+	entry->uid = INVALID_UID;
+	entry->gid = INVALID_GID;
+	entry->fowner = INVALID_UID;
+	entry->fgroup = INVALID_GID;
+	entry->uid_op = &uid_eq;
+	entry->gid_op = &gid_eq;
+	entry->fowner_op = &vfsuid_eq_kuid;
+	entry->fgroup_op = &vfsgid_eq_kgid;
+	entry->action = UNKNOWN;
+	while ((p = strsep(&rule, " \t")) != NULL) {
+		substring_t args[MAX_OPT_ARGS];
+		int token;
+		unsigned long lnum;
+
+		if (result < 0 || *p == '#')  /* ignore suffixed comment */
+			break;
+		if ((*p == '\0') || (*p == ' ') || (*p == '\t'))
+			continue;
+		token = match_token(p, policy_tokens, args);
+		switch (token) {
+		case Opt_measure:
+			ima_log_string(ab, "action", "measure");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = MEASURE;
+			break;
+		case Opt_dont_measure:
+			ima_log_string(ab, "action", "dont_measure");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_MEASURE;
+			break;
+		case Opt_appraise:
+			ima_log_string(ab, "action", "appraise");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = APPRAISE;
+			break;
+		case Opt_dont_appraise:
+			ima_log_string(ab, "action", "dont_appraise");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_APPRAISE;
+			break;
+		case Opt_audit:
+			ima_log_string(ab, "action", "audit");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = AUDIT;
+			break;
+		case Opt_dont_audit:
+			ima_log_string(ab, "action", "dont_audit");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_AUDIT;
+			break;
+		case Opt_hash:
+			ima_log_string(ab, "action", "hash");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = HASH;
+			break;
+		case Opt_dont_hash:
+			ima_log_string(ab, "action", "dont_hash");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_HASH;
+			break;
+		case Opt_func:
+			ima_log_string(ab, "func", args[0].from);
+
+			if (entry->func)
+				result = -EINVAL;
+
+			if (strcmp(args[0].from, "FILE_CHECK") == 0)
+				entry->func = FILE_CHECK;
+			/* PATH_CHECK is for backwards compat */
+			else if (strcmp(args[0].from, "PATH_CHECK") == 0)
+				entry->func = FILE_CHECK;
+			else if (strcmp(args[0].from, "MODULE_CHECK") == 0)
+				entry->func = MODULE_CHECK;
+			else if (strcmp(args[0].from, "FIRMWARE_CHECK") == 0)
+				entry->func = FIRMWARE_CHECK;
+			else if ((strcmp(args[0].from, "FILE_MMAP") == 0)
+				|| (strcmp(args[0].from, "MMAP_CHECK") == 0))
+				entry->func = MMAP_CHECK;
+			else if ((strcmp(args[0].from, "MMAP_CHECK_REQPROT") == 0))
+				entry->func = MMAP_CHECK_REQPROT;
+			else if (strcmp(args[0].from, "BPRM_CHECK") == 0)
+				entry->func = BPRM_CHECK;
+			else if (strcmp(args[0].from, "CREDS_CHECK") == 0)
+				entry->func = CREDS_CHECK;
+			else if (strcmp(args[0].from, "KEXEC_KERNEL_CHECK") ==
+				 0)
+				entry->func = KEXEC_KERNEL_CHECK;
+			else if (strcmp(args[0].from, "KEXEC_INITRAMFS_CHECK")
+				 == 0)
+				entry->func = KEXEC_INITRAMFS_CHECK;
+			else if (strcmp(args[0].from, "POLICY_CHECK") == 0)
+				entry->func = POLICY_CHECK;
+			else if (strcmp(args[0].from, "KEXEC_CMDLINE") == 0)
+				entry->func = KEXEC_CMDLINE;
+			else if (IS_ENABLED(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) &&
+				 strcmp(args[0].from, "KEY_CHECK") == 0)
+				entry->func = KEY_CHECK;
+			else if (strcmp(args[0].from, "CRITICAL_DATA") == 0)
+				entry->func = CRITICAL_DATA;
+			else if (strcmp(args[0].from, "SETXATTR_CHECK") == 0)
+				entry->func = SETXATTR_CHECK;
+			else
+				result = -EINVAL;
+			if (!result)
+				entry->flags |= IMA_FUNC;
+			break;
+		case Opt_mask:
+			ima_log_string(ab, "mask", args[0].from);
+
+			if (entry->mask)
+				result = -EINVAL;
+
+			from = args[0].from;
+			if (*from == '^')
+				from++;
+
+			if ((strcmp(from, "MAY_EXEC")) == 0)
+				entry->mask = MAY_EXEC;
+			else if (strcmp(from, "MAY_WRITE") == 0)
+				entry->mask = MAY_WRITE;
+			else if (strcmp(from, "MAY_READ") == 0)
+				entry->mask = MAY_READ;
+			else if (strcmp(from, "MAY_APPEND") == 0)
+				entry->mask = MAY_APPEND;
+			else
+				result = -EINVAL;
+			if (!result)
+				entry->flags |= (*args[0].from == '^')
+				     ? IMA_INMASK : IMA_MASK;
+			break;
+		case Opt_fsmagic:
+			ima_log_string(ab, "fsmagic", args[0].from);
+
+			if (entry->fsmagic) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 16, &entry->fsmagic);
+			if (!result)
+				entry->flags |= IMA_FSMAGIC;
+			break;
+		case Opt_fsname:
+			ima_log_string(ab, "fsname", args[0].from);
+
+			entry->fsname = kstrdup(args[0].from, GFP_KERNEL);
+			if (!entry->fsname) {
+				result = -ENOMEM;
+				break;
+			}
+			result = 0;
+			entry->flags |= IMA_FSNAME;
+			break;
+		case Opt_fs_subtype:
+			ima_log_string(ab, "fs_subtype", args[0].from);
+
+			if (entry->fs_subtype) {
+				result = -EINVAL;
+				break;
+			}
+
+			entry->fs_subtype = kstrdup(args[0].from, GFP_KERNEL);
+			if (!entry->fs_subtype) {
+				result = -ENOMEM;
+				break;
+			}
+			result = 0;
+			entry->flags |= IMA_FS_SUBTYPE;
+			break;
+		case Opt_keyrings:
+			ima_log_string(ab, "keyrings", args[0].from);
+
+			if (!IS_ENABLED(CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS) ||
+			    entry->keyrings) {
+				result = -EINVAL;
+				break;
+			}
+
+			entry->keyrings = ima_alloc_rule_opt_list(args);
+			if (IS_ERR(entry->keyrings)) {
+				result = PTR_ERR(entry->keyrings);
+				entry->keyrings = NULL;
+				break;
+			}
+
+			entry->flags |= IMA_KEYRINGS;
+			break;
+		case Opt_label:
+			ima_log_string(ab, "label", args[0].from);
+
+			if (entry->label) {
+				result = -EINVAL;
+				break;
+			}
+
+			entry->label = ima_alloc_rule_opt_list(args);
+			if (IS_ERR(entry->label)) {
+				result = PTR_ERR(entry->label);
+				entry->label = NULL;
+				break;
+			}
+
+			entry->flags |= IMA_LABEL;
+			break;
+		case Opt_fsuuid:
+			ima_log_string(ab, "fsuuid", args[0].from);
+
+			if (!uuid_is_null(&entry->fsuuid)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = uuid_parse(args[0].from, &entry->fsuuid);
+			if (!result)
+				entry->flags |= IMA_FSUUID;
+			break;
+		case Opt_uid_gt:
+		case Opt_euid_gt:
+			entry->uid_op = &uid_gt;
+			fallthrough;
+		case Opt_uid_lt:
+		case Opt_euid_lt:
+			if ((token == Opt_uid_lt) || (token == Opt_euid_lt))
+				entry->uid_op = &uid_lt;
+			fallthrough;
+		case Opt_uid_eq:
+		case Opt_euid_eq:
+			eid_token = (token == Opt_euid_eq) ||
+				    (token == Opt_euid_gt) ||
+				    (token == Opt_euid_lt);
+
+			ima_log_string_op(ab, eid_token ? "euid" : "uid",
+					  args[0].from, token);
+
+			if (uid_valid(entry->uid)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->uid = make_kuid(current_user_ns(),
+						       (uid_t) lnum);
+				if (!uid_valid(entry->uid) ||
+				    (uid_t)lnum != lnum)
+					result = -EINVAL;
+				else
+					entry->flags |= eid_token
+					    ? IMA_EUID : IMA_UID;
+			}
+			break;
+		case Opt_gid_gt:
+		case Opt_egid_gt:
+			entry->gid_op = &gid_gt;
+			fallthrough;
+		case Opt_gid_lt:
+		case Opt_egid_lt:
+			if ((token == Opt_gid_lt) || (token == Opt_egid_lt))
+				entry->gid_op = &gid_lt;
+			fallthrough;
+		case Opt_gid_eq:
+		case Opt_egid_eq:
+			eid_token = (token == Opt_egid_eq) ||
+				    (token == Opt_egid_gt) ||
+				    (token == Opt_egid_lt);
+
+			ima_log_string_op(ab, eid_token ? "egid" : "gid",
+					  args[0].from, token);
+
+			if (gid_valid(entry->gid)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->gid = make_kgid(current_user_ns(),
+						       (gid_t)lnum);
+				if (!gid_valid(entry->gid) ||
+				    (((gid_t)lnum) != lnum))
+					result = -EINVAL;
+				else
+					entry->flags |= eid_token
+					    ? IMA_EGID : IMA_GID;
+			}
+			break;
+		case Opt_fowner_gt:
+			entry->fowner_op = &vfsuid_gt_kuid;
+			fallthrough;
+		case Opt_fowner_lt:
+			if (token == Opt_fowner_lt)
+				entry->fowner_op = &vfsuid_lt_kuid;
+			fallthrough;
+		case Opt_fowner_eq:
+			ima_log_string_op(ab, "fowner", args[0].from, token);
+
+			if (uid_valid(entry->fowner)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->fowner = make_kuid(current_user_ns(),
+							  (uid_t)lnum);
+				if (!uid_valid(entry->fowner) ||
+				    (((uid_t)lnum) != lnum))
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_FOWNER;
+			}
+			break;
+		case Opt_fgroup_gt:
+			entry->fgroup_op = &vfsgid_gt_kgid;
+			fallthrough;
+		case Opt_fgroup_lt:
+			if (token == Opt_fgroup_lt)
+				entry->fgroup_op = &vfsgid_lt_kgid;
+			fallthrough;
+		case Opt_fgroup_eq:
+			ima_log_string_op(ab, "fgroup", args[0].from, token);
+
+			if (gid_valid(entry->fgroup)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->fgroup = make_kgid(current_user_ns(),
+							  (gid_t)lnum);
+				if (!gid_valid(entry->fgroup) ||
+				    (((gid_t)lnum) != lnum))
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_FGROUP;
+			}
+			break;
+		case Opt_obj_user:
+			ima_log_string(ab, "obj_user", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_USER,
+						   AUDIT_OBJ_USER);
+			break;
+		case Opt_obj_role:
+			ima_log_string(ab, "obj_role", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_ROLE,
+						   AUDIT_OBJ_ROLE);
+			break;
+		case Opt_obj_type:
+			ima_log_string(ab, "obj_type", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_TYPE,
+						   AUDIT_OBJ_TYPE);
+			break;
+		case Opt_subj_user:
+			ima_log_string(ab, "subj_user", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_USER,
+						   AUDIT_SUBJ_USER);
+			break;
+		case Opt_subj_role:
+			ima_log_string(ab, "subj_role", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_ROLE,
+						   AUDIT_SUBJ_ROLE);
+			break;
+		case Opt_subj_type:
+			ima_log_string(ab, "subj_type", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_TYPE,
+						   AUDIT_SUBJ_TYPE);
+			break;
+		case Opt_digest_type:
+			ima_log_string(ab, "digest_type", args[0].from);
+			if ((strcmp(args[0].from, "verity")) == 0)
+				entry->flags |= IMA_VERITY_REQUIRED;
+			else
+				result = -EINVAL;
+			break;
+		case Opt_appraise_type:
+			ima_log_string(ab, "appraise_type", args[0].from);
+
+			if ((strcmp(args[0].from, "imasig")) == 0) {
+				if (entry->flags & IMA_VERITY_REQUIRED)
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_DIGSIG_REQUIRED | IMA_CHECK_BLACKLIST;
+			} else if (strcmp(args[0].from, "sigv3") == 0) {
+				entry->flags |= IMA_SIGV3_REQUIRED |
+					IMA_DIGSIG_REQUIRED |
+					IMA_CHECK_BLACKLIST;
+			} else if (IS_ENABLED(CONFIG_IMA_APPRAISE_MODSIG) &&
+				 strcmp(args[0].from, "imasig|modsig") == 0) {
+				if ((entry->flags & IMA_VERITY_REQUIRED) ||
+				    (entry->flags & IMA_SIGV3_REQUIRED))
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_DIGSIG_REQUIRED |
+						IMA_MODSIG_ALLOWED | IMA_CHECK_BLACKLIST;
+			} else {
+				result = -EINVAL;
+			}
+			break;
+		case Opt_appraise_flag:
+			ima_log_string(ab, "appraise_flag", args[0].from);
+			break;
+		case Opt_appraise_algos:
+			ima_log_string(ab, "appraise_algos", args[0].from);
+
+			if (entry->allowed_algos) {
+				result = -EINVAL;
+				break;
+			}
+
+			entry->allowed_algos =
+				ima_parse_appraise_algos(args[0].from);
+			/* invalid or empty list of algorithms */
+			if (!entry->allowed_algos) {
+				result = -EINVAL;
+				break;
+			}
+
+			entry->flags |= IMA_VALIDATE_ALGOS;
+
+			break;
+		case Opt_permit_directio:
+			entry->flags |= IMA_PERMIT_DIRECTIO;
+			break;
+		case Opt_pcr:
+			ima_log_string(ab, "pcr", args[0].from);
+
+			result = kstrtoint(args[0].from, 10, &entry->pcr);
+			if (result || INVALID_PCR(entry->pcr))
+				result = -EINVAL;
+			else
+				entry->flags |= IMA_PCR;
+
+			break;
+		case Opt_template:
+			ima_log_string(ab, "template", args[0].from);
+			if (entry->action != MEASURE) {
+				result = -EINVAL;
+				break;
+			}
+			template_desc = lookup_template_desc(args[0].from);
+			if (!template_desc || entry->template) {
+				result = -EINVAL;
+				break;
+			}
+
+			/*
+			 * template_desc_init_fields() does nothing if
+			 * the template is already initialised, so
+			 * it's safe to do this unconditionally
+			 */
+			template_desc_init_fields(template_desc->fmt,
+						 &(template_desc->fields),
+						 &(template_desc->num_fields));
+			entry->template = template_desc;
+			break;
+		case Opt_err:
+			ima_log_string(ab, "UNKNOWN", p);
+			result = -EINVAL;
+			break;
+		}
+	}
+	if (!result && !ima_validate_rule(entry))
+		result = -EINVAL;
+	else if (entry->action == APPRAISE)
+		temp_ima_appraise |= ima_appraise_flag(entry->func);
+
+	if (!result && entry->flags & IMA_MODSIG_ALLOWED) {
+		template_desc = entry->template ? entry->template :
+						  ima_template_desc_current();
+		check_template_modsig(template_desc);
+	}
+
+	/* d-ngv2 template field recommended for unsigned fs-verity digests */
+	if (!result && entry->action == MEASURE &&
+	    (entry->flags & IMA_VERITY_REQUIRED)) {
+		template_desc = entry->template ? entry->template :
+						  ima_template_desc_current();
+		check_template_field(template_desc, "d-ngv2",
+				     "verity rules should include d-ngv2");
+	}
+
+	audit_log_format(ab, "res=%d", !result);
+	audit_log_end(ab);
+	return result;
+}
+
+/**
+ * ima_parse_add_rule - add a rule to ima_policy_rules
+ * @rule: ima measurement policy rule
+ *
+ * Avoid locking by allowing just one writer at a time in ima_write_policy()
+ * Returns the length of the rule parsed, an error code on failure
+ */
+ssize_t ima_parse_add_rule(char *rule)
+{
+	static const char op[] = "update_policy";
+	char *p;
+	struct ima_rule_entry *entry;
+	ssize_t result, len;
+	int audit_info = 0;
+
+	p = strsep(&rule, "\n");
+	len = strlen(p) + 1;
+	p += strspn(p, " \t");
+
+	if (*p == '#' || *p == '\0')
+		return len;
+
+	entry = kzalloc_obj(*entry);
+	if (!entry) {
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+				    NULL, op, "-ENOMEM", -ENOMEM, audit_info);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&entry->list);
+
+	result = ima_parse_rule(p, entry);
+	if (result) {
+		ima_free_rule(entry);
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+				    NULL, op, "invalid-policy", result,
+				    audit_info);
+		return result;
+	}
+
+	list_add_tail(&entry->list, &ima_temp_rules);
+
+	if (len > max_rule_len)
+		max_rule_len = len;
+
+	return len;
+}
+
+/**
+ * ima_delete_rules() - called to cleanup invalid in-flight policy.
+ *
+ * We don't need locking as we operate on the temp list, which is
+ * different from the active one.  There is also only one user of
+ * ima_delete_rules() at a time.
+ */
+void ima_delete_rules(void)
+{
+	struct ima_rule_entry *entry, *tmp;
+
+	temp_ima_appraise = 0;
+	list_for_each_entry_safe(entry, tmp, &ima_temp_rules, list) {
+		list_del(&entry->list);
+		ima_free_rule(entry);
+	}
+}
+
+#define __ima_hook_stringify(func, str)	(#func),
+
+const char *const func_tokens[] = {
+	__ima_hooks(__ima_hook_stringify)
+};
+
+enum {
+	mask_exec = 0, mask_write, mask_read, mask_append
+};
+
+static const char *const mask_tokens[] = {
+	"^MAY_EXEC",
+	"^MAY_WRITE",
+	"^MAY_READ",
+	"^MAY_APPEND"
+};
+
+void *ima_policy_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t l = *pos;
+	struct ima_rule_entry *entry;
+	struct list_head *ima_rules_tmp;
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(entry, ima_rules_tmp, list) {
+		if (!l--) {
+			rcu_read_unlock();
+			return entry;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+void *ima_policy_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct ima_rule_entry *entry = v;
+
+	rcu_read_lock();
+	entry = list_entry_rcu(entry->list.next, struct ima_rule_entry, list);
+	rcu_read_unlock();
+	(*pos)++;
+
+	return (&entry->list == &ima_default_rules ||
+		&entry->list == &ima_policy_rules) ? NULL : entry;
+}
+
+void ima_policy_stop(struct seq_file *m, void *v)
+{
+}
+
+#define pt(token)	policy_tokens[token].pattern
+#define mt(token)	mask_tokens[token]
+
+/*
+ * policy_func_show - display the ima_hooks policy rule
+ */
+static void policy_func_show(struct seq_file *m, enum ima_hooks func)
+{
+	if (func > 0 && func < MAX_CHECK)
+		seq_printf(m, "func=%s ", func_tokens[func]);
+	else
+		seq_printf(m, "func=%d ", func);
+}
+
+static void ima_show_rule_opt_list(struct seq_file *m,
+				   const struct ima_rule_opt_list *opt_list)
+{
+	size_t i;
+
+	for (i = 0; i < opt_list->count; i++)
+		seq_printf(m, "%s%s", i ? "|" : "", opt_list->items[i]);
+}
+
+static void ima_policy_show_appraise_algos(struct seq_file *m,
+					   unsigned int allowed_hashes)
+{
+	int idx, list_size = 0;
+
+	for (idx = 0; idx < HASH_ALGO__LAST; idx++) {
+		if (!(allowed_hashes & (1U << idx)))
+			continue;
+
+		/* only add commas if the list contains multiple entries */
+		if (list_size++)
+			seq_puts(m, ",");
+
+		seq_puts(m, hash_algo_name[idx]);
+	}
+}
+
+int ima_policy_show(struct seq_file *m, void *v)
+{
+	struct ima_rule_entry *entry = v;
+	int i;
+	char tbuf[64] = {0,};
+	int offset = 0;
+
+	rcu_read_lock();
+
+	/* Do not print rules with inactive LSM labels */
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		if (entry->lsm[i].args_p && !entry->lsm[i].rule) {
+			rcu_read_unlock();
+			return 0;
+		}
+	}
+
+	if (entry->action & MEASURE)
+		seq_puts(m, pt(Opt_measure));
+	if (entry->action & DONT_MEASURE)
+		seq_puts(m, pt(Opt_dont_measure));
+	if (entry->action & APPRAISE)
+		seq_puts(m, pt(Opt_appraise));
+	if (entry->action & DONT_APPRAISE)
+		seq_puts(m, pt(Opt_dont_appraise));
+	if (entry->action & AUDIT)
+		seq_puts(m, pt(Opt_audit));
+	if (entry->action & DONT_AUDIT)
+		seq_puts(m, pt(Opt_dont_audit));
+	if (entry->action & HASH)
+		seq_puts(m, pt(Opt_hash));
+	if (entry->action & DONT_HASH)
+		seq_puts(m, pt(Opt_dont_hash));
+
+	seq_puts(m, " ");
+
+	if (entry->flags & IMA_FUNC)
+		policy_func_show(m, entry->func);
+
+	if ((entry->flags & IMA_MASK) || (entry->flags & IMA_INMASK)) {
+		if (entry->flags & IMA_MASK)
+			offset = 1;
+		if (entry->mask & MAY_EXEC)
+			seq_printf(m, pt(Opt_mask), mt(mask_exec) + offset);
+		if (entry->mask & MAY_WRITE)
+			seq_printf(m, pt(Opt_mask), mt(mask_write) + offset);
+		if (entry->mask & MAY_READ)
+			seq_printf(m, pt(Opt_mask), mt(mask_read) + offset);
+		if (entry->mask & MAY_APPEND)
+			seq_printf(m, pt(Opt_mask), mt(mask_append) + offset);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FSMAGIC) {
+		snprintf(tbuf, sizeof(tbuf), "0x%lx", entry->fsmagic);
+		seq_printf(m, pt(Opt_fsmagic), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FSNAME) {
+		snprintf(tbuf, sizeof(tbuf), "%s", entry->fsname);
+		seq_printf(m, pt(Opt_fsname), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FS_SUBTYPE) {
+		snprintf(tbuf, sizeof(tbuf), "%s", entry->fs_subtype);
+		seq_printf(m, pt(Opt_fs_subtype), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_KEYRINGS) {
+		seq_puts(m, "keyrings=");
+		ima_show_rule_opt_list(m, entry->keyrings);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_LABEL) {
+		seq_puts(m, "label=");
+		ima_show_rule_opt_list(m, entry->label);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_PCR) {
+		snprintf(tbuf, sizeof(tbuf), "%d", entry->pcr);
+		seq_printf(m, pt(Opt_pcr), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FSUUID) {
+		seq_printf(m, "fsuuid=%pU", &entry->fsuuid);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_UID) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->uid));
+		if (entry->uid_op == &uid_gt)
+			seq_printf(m, pt(Opt_uid_gt), tbuf);
+		else if (entry->uid_op == &uid_lt)
+			seq_printf(m, pt(Opt_uid_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_uid_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_EUID) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->uid));
+		if (entry->uid_op == &uid_gt)
+			seq_printf(m, pt(Opt_euid_gt), tbuf);
+		else if (entry->uid_op == &uid_lt)
+			seq_printf(m, pt(Opt_euid_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_euid_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_GID) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->gid));
+		if (entry->gid_op == &gid_gt)
+			seq_printf(m, pt(Opt_gid_gt), tbuf);
+		else if (entry->gid_op == &gid_lt)
+			seq_printf(m, pt(Opt_gid_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_gid_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_EGID) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->gid));
+		if (entry->gid_op == &gid_gt)
+			seq_printf(m, pt(Opt_egid_gt), tbuf);
+		else if (entry->gid_op == &gid_lt)
+			seq_printf(m, pt(Opt_egid_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_egid_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FOWNER) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kuid_val(entry->fowner));
+		if (entry->fowner_op == &vfsuid_gt_kuid)
+			seq_printf(m, pt(Opt_fowner_gt), tbuf);
+		else if (entry->fowner_op == &vfsuid_lt_kuid)
+			seq_printf(m, pt(Opt_fowner_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_fowner_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_FGROUP) {
+		snprintf(tbuf, sizeof(tbuf), "%d", __kgid_val(entry->fgroup));
+		if (entry->fgroup_op == &vfsgid_gt_kgid)
+			seq_printf(m, pt(Opt_fgroup_gt), tbuf);
+		else if (entry->fgroup_op == &vfsgid_lt_kgid)
+			seq_printf(m, pt(Opt_fgroup_lt), tbuf);
+		else
+			seq_printf(m, pt(Opt_fgroup_eq), tbuf);
+		seq_puts(m, " ");
+	}
+
+	if (entry->flags & IMA_VALIDATE_ALGOS) {
+		seq_puts(m, "appraise_algos=");
+		ima_policy_show_appraise_algos(m, entry->allowed_algos);
+		seq_puts(m, " ");
+	}
+
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		if (entry->lsm[i].rule) {
+			switch (i) {
+			case LSM_OBJ_USER:
+				seq_printf(m, pt(Opt_obj_user),
+					   entry->lsm[i].args_p);
+				break;
+			case LSM_OBJ_ROLE:
+				seq_printf(m, pt(Opt_obj_role),
+					   entry->lsm[i].args_p);
+				break;
+			case LSM_OBJ_TYPE:
+				seq_printf(m, pt(Opt_obj_type),
+					   entry->lsm[i].args_p);
+				break;
+			case LSM_SUBJ_USER:
+				seq_printf(m, pt(Opt_subj_user),
+					   entry->lsm[i].args_p);
+				break;
+			case LSM_SUBJ_ROLE:
+				seq_printf(m, pt(Opt_subj_role),
+					   entry->lsm[i].args_p);
+				break;
+			case LSM_SUBJ_TYPE:
+				seq_printf(m, pt(Opt_subj_type),
+					   entry->lsm[i].args_p);
+				break;
+			}
+			seq_puts(m, " ");
+		}
+	}
+	if (entry->template)
+		seq_printf(m, "template=%s ", entry->template->name);
+	if (entry->flags & IMA_DIGSIG_REQUIRED) {
+		if (entry->flags & IMA_SIGV3_REQUIRED)
+			seq_puts(m, "appraise_type=sigv3 ");
+		else if (entry->flags & IMA_MODSIG_ALLOWED)
+			seq_puts(m, "appraise_type=imasig|modsig ");
+		else
+			seq_puts(m, "appraise_type=imasig ");
+	}
+	if (entry->flags & IMA_VERITY_REQUIRED)
+		seq_puts(m, "digest_type=verity ");
+	if (entry->flags & IMA_PERMIT_DIRECTIO)
+		seq_puts(m, "permit_directio ");
+	rcu_read_unlock();
+	seq_puts(m, "\n");
+	return 0;
+}
+
+#if defined(CONFIG_IMA_APPRAISE) && defined(CONFIG_INTEGRITY_TRUSTED_KEYRING)
+/*
+ * ima_appraise_signature: whether IMA will appraise a given function using
+ * an IMA digital signature. This is restricted to cases where the kernel
+ * has a set of built-in trusted keys in order to avoid an attacker simply
+ * loading additional keys.
+ */
+bool ima_appraise_signature(enum kernel_read_file_id id)
+{
+	struct ima_rule_entry *entry;
+	bool found = false;
+	enum ima_hooks func;
+	struct list_head *ima_rules_tmp;
+
+	if (id >= READING_MAX_ID)
+		return false;
+
+	if (id == READING_KEXEC_IMAGE && !(ima_appraise & IMA_APPRAISE_ENFORCE)
+	    && security_locked_down(LOCKDOWN_KEXEC))
+		return false;
+
+	func = read_idmap[id] ?: FILE_CHECK;
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(entry, ima_rules_tmp, list) {
+		if (entry->action != APPRAISE)
+			continue;
+
+		/*
+		 * A generic entry will match, but otherwise require that it
+		 * match the func we're looking for
+		 */
+		if (entry->func && entry->func != func)
+			continue;
+
+		/*
+		 * We require this to be a digital signature, not a raw IMA
+		 * hash.
+		 */
+		if (entry->flags & IMA_DIGSIG_REQUIRED)
+			found = true;
+
+		/*
+		 * We've found a rule that matches, so break now even if it
+		 * didn't require a digital signature - a later rule that does
+		 * won't override it, so would be a false positive.
+		 */
+		break;
+	}
+
+	rcu_read_unlock();
+	return found;
+}
+#endif /* CONFIG_IMA_APPRAISE && CONFIG_INTEGRITY_TRUSTED_KEYRING */
+
+/**
+ * ima_measure_loaded_policy - measure the active IMA policy ruleset
+ *
+ * Must be called with ima_write_mutex held, as it performs two
+ * separate RCU read passes over ima_rules and relies on the mutex
+ * to prevent concurrent policy updates between them.
+ */
+void ima_measure_loaded_policy(void)
+{
+	const char *event_name = "ima_policy_loaded";
+	const char *op = "measure_loaded_ima_policy";
+	size_t rule_len = max_rule_len + 2;
+	struct ima_rule_entry *rule_entry;
+	struct list_head *ima_rules_tmp;
+	struct seq_file file = { 0 };
+	int result = -ENOMEM;
+	size_t file_len = 0;
+	char *rule;
+
+	lockdep_assert_held(&ima_write_mutex);
+
+	rule = kmalloc(rule_len, GFP_KERNEL);
+	if (!rule) {
+		integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, event_name,
+				    op, "ENOMEM", result, 0);
+		return;
+	}
+
+	/* calculate IMA policy rules memory size */
+	file.buf = rule;
+	file.read_pos = 0;
+	file.size = rule_len;
+	file.count = 0;
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(rule_entry, ima_rules_tmp, list) {
+		ima_policy_show(&file, rule_entry);
+
+		if (seq_has_overflowed(&file)) {
+			result = -E2BIG;
+			integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL,
+					    event_name, op, "rule_length",
+					    result, 0);
+			rcu_read_unlock();
+			goto free_rule;
+		}
+
+		file_len += file.count;
+		file.count = 0;
+	}
+	rcu_read_unlock();
+
+	/* copy IMA policy rules to a buffer for measuring */
+	file.buf = kmalloc(file_len, GFP_KERNEL);
+	if (!file.buf) {
+		integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, event_name,
+				    op, "ENOMEM", result, 0);
+		goto free_rule;
+	}
+
+	file.read_pos = 0;
+	file.size = file_len;
+	file.count = 0;
+
+	rcu_read_lock();
+	ima_rules_tmp = rcu_dereference(ima_rules);
+	list_for_each_entry_rcu(rule_entry, ima_rules_tmp, list) {
+		ima_policy_show(&file, rule_entry);
+	}
+	rcu_read_unlock();
+
+	ima_measure_critical_data("ima_policy", event_name, file.buf,
+				  file.count, false, NULL, 0);
+
+	kfree(file.buf);
+free_rule:
+	kfree(rule);
+}
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
new file mode 100644
index 000000000..f89f0ca3d
--- /dev/null
+++ b/security/integrity/ima/ima_queue.c
@@ -0,0 +1,577 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Serge Hallyn <serue@us.ibm.com>
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: ima_queue.c
+ *       Implements queues that store template measurements and
+ *       maintains aggregate over the stored measurements
+ *       in the pre-configured TPM PCR (if available).
+ *       The measurement list is append-only. No entry is
+ *       ever removed or changed during the boot-cycle.
+ */
+
+#include <linux/rculist.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include "ima.h"
+
+#define AUDIT_CAUSE_LEN_MAX 32
+
+bool ima_flush_htable;
+
+static int __init ima_flush_htable_setup(char *str)
+{
+	if (IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) {
+		pr_warn("Hash table not enabled, ignoring request to flush\n");
+		return 1;
+	}
+
+	ima_flush_htable = true;
+	return 1;
+}
+__setup("ima_flush_htable", ima_flush_htable_setup);
+
+/* pre-allocated array of tpm_digest structures to extend a PCR */
+static struct tpm_digest *digests;
+
+LIST_HEAD(ima_measurements);	/* list of all measurements */
+LIST_HEAD(ima_measurements_staged); /* list of staged measurements */
+#ifdef CONFIG_IMA_KEXEC
+static unsigned long binary_runtime_size[BINARY__LAST];
+#else
+static unsigned long binary_runtime_size[BINARY__LAST] = {
+	[0 ... BINARY__LAST - 1] = ULONG_MAX
+};
+#endif
+
+atomic_long_t ima_num_records[BINARY__LAST] = {
+	[0 ... BINARY__LAST - 1] = ATOMIC_LONG_INIT(0)
+};
+atomic_long_t ima_num_violations = ATOMIC_LONG_INIT(0);
+
+/* key: inode (before secure-hashing a file) */
+struct hlist_head __rcu *ima_htable;
+
+/* mutex protects atomicity of extending and staging measurement list
+ * and extending the TPM PCR aggregate. Since tpm_extend can take
+ * long (and the tpm driver uses a mutex), we can't use the spinlock.
+ */
+static DEFINE_MUTEX(ima_extend_list_mutex);
+
+/*
+ * Used internally by the kernel to suspend measurements.
+ * Protected by ima_extend_list_mutex.
+ */
+static bool ima_measurements_suspended;
+
+/* Callers must call synchronize_rcu() and free the hash table. */
+static struct hlist_head *ima_alloc_replace_htable(void)
+{
+	struct hlist_head *old_htable, *new_htable;
+
+	/* Initializing to zeros is equivalent to call HLIST_HEAD_INIT. */
+	new_htable = kcalloc(IMA_MEASURE_HTABLE_SIZE, sizeof(struct hlist_head),
+			     GFP_KERNEL);
+	if (!new_htable)
+		return ERR_PTR(-ENOMEM);
+
+	old_htable = rcu_replace_pointer(ima_htable, new_htable,
+				lockdep_is_held(&ima_extend_list_mutex));
+
+	return old_htable;
+}
+
+int __init ima_init_htable(void)
+{
+	struct hlist_head *old_htable;
+
+	mutex_lock(&ima_extend_list_mutex);
+	old_htable = ima_alloc_replace_htable();
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (IS_ERR(old_htable))
+		return PTR_ERR(old_htable);
+
+	/* Synchronize_rcu() and kfree() not necessary, only for robustness. */
+	synchronize_rcu();
+	kfree(old_htable);
+	return 0;
+}
+
+/* lookup up the digest value in the hash table, and return the entry */
+static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value,
+						       int pcr)
+{
+	struct ima_queue_entry *qe, *ret = NULL;
+	struct hlist_head *htable;
+	unsigned int key;
+	int rc;
+
+	key = ima_hash_key(digest_value);
+	rcu_read_lock();
+	htable = rcu_dereference(ima_htable);
+	hlist_for_each_entry_rcu(qe, &htable[key], hnext) {
+		rc = memcmp(qe->entry->digests[ima_hash_algo_idx].digest,
+			    digest_value, hash_digest_size[ima_hash_algo]);
+		if ((rc == 0) && (qe->entry->pcr == pcr)) {
+			ret = qe;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/*
+ * Calculate the memory required for serializing a single
+ * binary_runtime_measurement list entry, which contains a
+ * couple of variable length fields (e.g template name and data).
+ */
+static int get_binary_runtime_size(struct ima_template_entry *entry)
+{
+	int size = 0;
+
+	size += sizeof(u32);	/* pcr */
+	size += TPM_DIGEST_SIZE;
+	size += sizeof(int);	/* template name size field */
+	size += strlen(entry->template_desc->name);
+	size += sizeof(entry->template_data_len);
+	size += entry->template_data_len;
+	return size;
+}
+
+static void ima_update_binary_runtime_size(struct ima_template_entry *entry,
+					   enum binary_lists binary_list)
+{
+	int size;
+
+	if (binary_runtime_size[binary_list] == ULONG_MAX)
+		return;
+
+	size = get_binary_runtime_size(entry);
+	binary_runtime_size[binary_list] =
+		(binary_runtime_size[binary_list] < ULONG_MAX - size) ?
+		binary_runtime_size[binary_list] + size : ULONG_MAX;
+}
+
+/* ima_add_template_entry helper function:
+ * - Add template entry to the measurement list and hash table, for
+ *   all entries except those carried across kexec.
+ *
+ * (Called with ima_extend_list_mutex held.)
+ */
+static int ima_add_digest_entry(struct ima_template_entry *entry,
+				bool update_htable)
+{
+	struct ima_queue_entry *qe;
+	struct hlist_head *htable;
+	unsigned int key;
+
+	qe = kmalloc_obj(*qe);
+	if (qe == NULL) {
+		pr_err("OUT OF MEMORY ERROR creating queue entry\n");
+		return -ENOMEM;
+	}
+	qe->entry = entry;
+
+	INIT_LIST_HEAD(&qe->later);
+	list_add_tail_rcu(&qe->later, &ima_measurements);
+
+	htable = rcu_dereference_protected(ima_htable,
+				lockdep_is_held(&ima_extend_list_mutex));
+
+	atomic_long_inc(&ima_num_records[BINARY]);
+	atomic_long_inc(&ima_num_records[BINARY_FULL]);
+
+	if (update_htable) {
+		key = ima_hash_key(entry->digests[ima_hash_algo_idx].digest);
+		hlist_add_head_rcu(&qe->hnext, &htable[key]);
+	}
+
+	ima_update_binary_runtime_size(entry, BINARY);
+	ima_update_binary_runtime_size(entry, BINARY_FULL);
+
+	return 0;
+}
+
+/*
+ * Return the amount of memory required for serializing the
+ * entire binary_runtime_measurement list, including the ima_kexec_hdr
+ * structure.
+ */
+unsigned long ima_get_binary_runtime_size(enum binary_lists binary_list)
+{
+	unsigned long val;
+
+	mutex_lock(&ima_extend_list_mutex);
+	val = binary_runtime_size[binary_list];
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (val >= (ULONG_MAX - sizeof(struct ima_kexec_hdr)))
+		return ULONG_MAX;
+	else
+		return val + sizeof(struct ima_kexec_hdr);
+}
+
+static int ima_pcr_extend(struct tpm_digest *digests_arg, int pcr)
+{
+	int result = 0;
+
+	if (!ima_tpm_chip)
+		return result;
+
+	result = tpm_pcr_extend(ima_tpm_chip, pcr, digests_arg);
+	if (result != 0)
+		pr_err("Error Communicating to TPM chip, result: %d\n", result);
+	return result;
+}
+
+/*
+ * Add template entry to the measurement list and hash table, and
+ * extend the pcr.
+ *
+ * On systems which support carrying the IMA measurement list across
+ * kexec, maintain the total memory size required for serializing the
+ * binary_runtime_measurements.
+ */
+int ima_add_template_entry(struct ima_template_entry *entry, int violation,
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename)
+{
+	u8 *digest = entry->digests[ima_hash_algo_idx].digest;
+	struct tpm_digest *digests_arg = entry->digests;
+	const char *audit_cause = "hash_added";
+	char tpm_audit_cause[AUDIT_CAUSE_LEN_MAX];
+	int audit_info = 1;
+	int result = 0, tpmresult = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+
+	/*
+	 * Avoid appending to the measurement log when the TPM subsystem has
+	 * been shut down while preparing for system reboot.
+	 */
+	if (ima_measurements_suspended) {
+		audit_cause = "measurements_suspended";
+		audit_info = 0;
+		result = -ENODEV;
+		goto out;
+	}
+
+	if (!violation && !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE)) {
+		if (ima_lookup_digest_entry(digest, entry->pcr)) {
+			audit_cause = "hash_exists";
+			result = -EEXIST;
+			goto out;
+		}
+	}
+
+	result = ima_add_digest_entry(entry,
+				      !IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE));
+	if (result < 0) {
+		audit_cause = "ENOMEM";
+		audit_info = 0;
+		goto out;
+	}
+
+	if (violation)		/* invalidate pcr */
+		digests_arg = digests;
+
+	tpmresult = ima_pcr_extend(digests_arg, entry->pcr);
+	if (tpmresult != 0) {
+		snprintf(tpm_audit_cause, AUDIT_CAUSE_LEN_MAX, "TPM_error(%d)",
+			 tpmresult);
+		audit_cause = tpm_audit_cause;
+		audit_info = 0;
+	}
+out:
+	mutex_unlock(&ima_extend_list_mutex);
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+			    op, audit_cause, result, audit_info);
+	return result;
+}
+
+/**
+ * ima_queue_stage - Stage all measurements
+ *
+ * If the staged measurements list is empty, the current measurements list is
+ * not empty, and measurement is not suspended, move the measurements from the
+ * current list to the staged one, and update the number of records and binary
+ * run-time size accordingly.
+ *
+ * Do not allow staging after measurement is suspended, so that dumping
+ * measurements can be done in a lockless way.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_stage(void)
+{
+	int ret = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (!list_empty(&ima_measurements_staged)) {
+		ret = -EEXIST;
+		goto out_unlock;
+	}
+
+	if (list_empty(&ima_measurements)) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (ima_measurements_suspended) {
+		ret = -EACCES;
+		goto out_unlock;
+	}
+
+	list_replace(&ima_measurements, &ima_measurements_staged);
+	INIT_LIST_HEAD(&ima_measurements);
+
+	atomic_long_set(&ima_num_records[BINARY_STAGED],
+			atomic_long_read(&ima_num_records[BINARY]));
+	atomic_long_set(&ima_num_records[BINARY], 0);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC)) {
+		binary_runtime_size[BINARY_STAGED] =
+					binary_runtime_size[BINARY];
+		binary_runtime_size[BINARY] = 0;
+	}
+out_unlock:
+	mutex_unlock(&ima_extend_list_mutex);
+	return ret;
+}
+
+static void ima_queue_delete(struct list_head *head, bool flush_htable);
+
+/**
+ * ima_queue_staged_delete_all - Delete staged measurements
+ *
+ * Move staged measurements to a temporary list, ima_measurements_trim, update
+ * the number of records and the binary run-time size accordingly. Finally,
+ * delete measurements in the temporary list.
+ *
+ * Refuse to delete staged measurements if measurement is suspended, so that
+ * dump can be done in a lockless way and user space is notified about staged
+ * measurements being carried over to the secondary kernel, so that it does not
+ * save them twice.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_staged_delete_all(void)
+{
+	struct hlist_head *old_queue = NULL;
+	LIST_HEAD(ima_measurements_trim);
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (list_empty(&ima_measurements_staged)) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ENOENT;
+	}
+
+	if (ima_measurements_suspended) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ESTALE;
+	}
+
+	list_replace(&ima_measurements_staged, &ima_measurements_trim);
+	INIT_LIST_HEAD(&ima_measurements_staged);
+
+	atomic_long_set(&ima_num_records[BINARY_STAGED], 0);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC))
+		binary_runtime_size[BINARY_STAGED] = 0;
+
+	if (ima_flush_htable) {
+		old_queue = ima_alloc_replace_htable();
+		if (IS_ERR(old_queue)) {
+			mutex_unlock(&ima_extend_list_mutex);
+			return PTR_ERR(old_queue);
+		}
+	}
+
+	mutex_unlock(&ima_extend_list_mutex);
+
+	if (ima_flush_htable) {
+		synchronize_rcu();
+		kfree(old_queue);
+	}
+
+	ima_queue_delete(&ima_measurements_trim, ima_flush_htable);
+	return 0;
+}
+
+/**
+ * ima_queue_delete_partial - Delete current measurements
+ * @req_value: Number of measurements to delete
+ *
+ * Delete the requested number of measurements from the current measurements
+ * list, and update the number of records and the binary run-time size
+ * accordingly.
+ *
+ * Refuse to delete current measurements if measurement is suspended, so that
+ * dump can be done in a lockless way and user space is notified about current
+ * measurements being carried over to the secondary kernel, so that it does not
+ * save them twice.
+ *
+ * Return: Zero on success, a negative value otherwise.
+ */
+int ima_queue_delete_partial(unsigned long req_value)
+{
+	unsigned long req_value_copy = req_value;
+	unsigned long size_to_remove = 0, num_to_remove = 0;
+	LIST_HEAD(ima_measurements_trim);
+	struct ima_queue_entry *qe;
+	int ret = 0;
+
+	/*
+	 * list_for_each_entry_rcu() without rcu_read_lock() is fine because
+	 * only list append can happen concurrently. No list replace due to the
+	 * staging/delete writers mutual exclusion.
+	 */
+	list_for_each_entry_rcu(qe, &ima_measurements, later, true) {
+		size_to_remove += get_binary_runtime_size(qe->entry);
+		num_to_remove++;
+
+		if (--req_value_copy == 0)
+			break;
+	}
+
+	/* Not enough records to delete. */
+	if (req_value_copy > 0)
+		return -ENOENT;
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (ima_measurements_suspended) {
+		mutex_unlock(&ima_extend_list_mutex);
+		return -ESTALE;
+	}
+
+	/*
+	 * qe remains valid because ima_fs.c enforces single-writer exclusion.
+	 */
+	__list_cut_position(&ima_measurements_trim, &ima_measurements,
+			    &qe->later);
+
+	atomic_long_sub(num_to_remove, &ima_num_records[BINARY]);
+
+	if (IS_ENABLED(CONFIG_IMA_KEXEC))
+		binary_runtime_size[BINARY] -= size_to_remove;
+
+	mutex_unlock(&ima_extend_list_mutex);
+
+	ima_queue_delete(&ima_measurements_trim, false);
+	return ret;
+}
+
+/**
+ * ima_queue_delete - Delete measurements
+ * @head: List head measurements are deleted from
+ * @flush_htable: Whether or not the hash table is being flushed
+ *
+ * Delete the measurements from the passed list head completely if the
+ * hash table is not enabled or is being flushed, or partially (only the
+ * template data), if the hash table is used.
+ */
+static void ima_queue_delete(struct list_head *head, bool flush_htable)
+{
+	struct ima_queue_entry *qe, *qe_tmp;
+	unsigned int i;
+
+	list_for_each_entry_safe(qe, qe_tmp, head, later) {
+		/*
+		 * Safe to free template_data here without synchronize_rcu()
+		 * because the only htable reader, ima_lookup_digest_entry(),
+		 * accesses only entry->digests, not template_data. If new
+		 * htable readers are added that access template_data, a
+		 * synchronize_rcu() is required here.
+		 */
+		for (i = 0; i < qe->entry->template_desc->num_fields; i++) {
+			kfree(qe->entry->template_data[i].data);
+			qe->entry->template_data[i].data = NULL;
+			qe->entry->template_data[i].len = 0;
+		}
+
+		list_del(&qe->later);
+
+		/* No leak if condition is false, referenced by ima_htable. */
+		if (IS_ENABLED(CONFIG_IMA_DISABLE_HTABLE) || flush_htable) {
+			kfree(qe->entry->digests);
+			kfree(qe->entry);
+			kfree(qe);
+		}
+	}
+}
+
+int ima_restore_measurement_entry(struct ima_template_entry *entry)
+{
+	int result = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+	result = ima_add_digest_entry(entry, 0);
+	mutex_unlock(&ima_extend_list_mutex);
+	return result;
+}
+
+static void ima_measurements_suspend(void)
+{
+	mutex_lock(&ima_extend_list_mutex);
+	ima_measurements_suspended = true;
+	mutex_unlock(&ima_extend_list_mutex);
+}
+
+static int ima_reboot_notifier(struct notifier_block *nb,
+			       unsigned long action,
+			       void *data)
+{
+#ifdef CONFIG_IMA_KEXEC
+	if (action == SYS_RESTART && data && !strcmp(data, "kexec reboot"))
+		ima_measure_kexec_event("kexec_execute");
+#endif
+
+	ima_measurements_suspend();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block ima_reboot_nb = {
+	.notifier_call = ima_reboot_notifier,
+};
+
+void __init ima_init_reboot_notifier(void)
+{
+	register_reboot_notifier(&ima_reboot_nb);
+}
+
+int __init ima_init_digests(void)
+{
+	u16 digest_size;
+	u16 crypto_id;
+	int i;
+
+	if (!ima_tpm_chip)
+		return 0;
+
+	digests = kzalloc_objs(*digests, ima_tpm_chip->nr_allocated_banks,
+			       GFP_NOFS);
+	if (!digests)
+		return -ENOMEM;
+
+	for (i = 0; i < ima_tpm_chip->nr_allocated_banks; i++) {
+		digests[i].alg_id = ima_tpm_chip->allocated_banks[i].alg_id;
+		digest_size = ima_tpm_chip->allocated_banks[i].digest_size;
+		crypto_id = ima_tpm_chip->allocated_banks[i].crypto_id;
+
+		/* for unmapped TPM algorithms digest is still a padded SHA1 */
+		if (crypto_id == HASH_ALGO__LAST)
+			digest_size = SHA1_DIGEST_SIZE;
+
+		memset(digests[i].digest, 0xff, digest_size);
+	}
+
+	return 0;
+}
diff --git a/security/integrity/ima/ima_queue_keys.c b/security/integrity/ima/ima_queue_keys.c
new file mode 100644
index 000000000..b5ed33cbb
--- /dev/null
+++ b/security/integrity/ima/ima_queue_keys.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Microsoft Corporation
+ *
+ * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
+ *
+ * File: ima_queue_keys.c
+ *       Enables deferred processing of keys
+ */
+
+#include <linux/user_namespace.h>
+#include <linux/workqueue.h>
+#include <keys/asymmetric-type.h>
+#include "ima.h"
+
+/*
+ * Flag to indicate whether a key can be processed
+ * right away or should be queued for processing later.
+ */
+static bool ima_process_keys;
+
+/*
+ * To synchronize access to the list of keys that need to be measured
+ */
+static DEFINE_MUTEX(ima_keys_lock);
+static LIST_HEAD(ima_keys);
+
+/*
+ * If custom IMA policy is not loaded then keys queued up
+ * for measurement should be freed. This worker is used
+ * for handling this scenario.
+ */
+static long ima_key_queue_timeout = 300000; /* 5 Minutes */
+static void ima_keys_handler(struct work_struct *work);
+static DECLARE_DELAYED_WORK(ima_keys_delayed_work, ima_keys_handler);
+static bool timer_expired;
+
+/*
+ * This worker function frees keys that may still be
+ * queued up in case custom IMA policy was not loaded.
+ */
+static void ima_keys_handler(struct work_struct *work)
+{
+	timer_expired = true;
+	ima_process_queued_keys();
+}
+
+/*
+ * This function sets up a worker to free queued keys in case
+ * custom IMA policy was never loaded.
+ */
+void ima_init_key_queue(void)
+{
+	schedule_delayed_work(&ima_keys_delayed_work,
+			      msecs_to_jiffies(ima_key_queue_timeout));
+}
+
+static void ima_free_key_entry(struct ima_key_entry *entry)
+{
+	if (entry) {
+		kfree(entry->payload);
+		kfree(entry->keyring_name);
+		kfree(entry);
+	}
+}
+
+static struct ima_key_entry *ima_alloc_key_entry(struct key *keyring,
+						 const void *payload,
+						 size_t payload_len)
+{
+	int rc = 0;
+	const char *audit_cause = "ENOMEM";
+	struct ima_key_entry *entry;
+
+	entry = kzalloc_obj(*entry);
+	if (entry) {
+		entry->payload = kmemdup(payload, payload_len, GFP_KERNEL);
+		entry->keyring_name = kstrdup(keyring->description,
+					      GFP_KERNEL);
+		entry->payload_len = payload_len;
+	}
+
+	if ((entry == NULL) || (entry->payload == NULL) ||
+	    (entry->keyring_name == NULL)) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	INIT_LIST_HEAD(&entry->list);
+
+out:
+	if (rc) {
+		integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL,
+					keyring->description,
+					func_measure_str(KEY_CHECK),
+					audit_cause, rc, 0, rc);
+		ima_free_key_entry(entry);
+		entry = NULL;
+	}
+
+	return entry;
+}
+
+bool ima_queue_key(struct key *keyring, const void *payload,
+		   size_t payload_len)
+{
+	bool queued = false;
+	struct ima_key_entry *entry;
+
+	entry = ima_alloc_key_entry(keyring, payload, payload_len);
+	if (!entry)
+		return false;
+
+	mutex_lock(&ima_keys_lock);
+	if (!ima_process_keys) {
+		list_add_tail(&entry->list, &ima_keys);
+		queued = true;
+	}
+	mutex_unlock(&ima_keys_lock);
+
+	if (!queued)
+		ima_free_key_entry(entry);
+
+	return queued;
+}
+
+/*
+ * ima_process_queued_keys() - process keys queued for measurement
+ *
+ * This function sets ima_process_keys to true and processes queued keys.
+ * From here on keys will be processed right away (not queued).
+ */
+void ima_process_queued_keys(void)
+{
+	struct ima_key_entry *entry, *tmp;
+	bool process = false;
+
+	if (ima_process_keys)
+		return;
+
+	/*
+	 * Since ima_process_keys is set to true, any new key will be
+	 * processed immediately and not be queued to ima_keys list.
+	 * First one setting the ima_process_keys flag to true will
+	 * process the queued keys.
+	 */
+	mutex_lock(&ima_keys_lock);
+	if (!ima_process_keys) {
+		ima_process_keys = true;
+		process = true;
+	}
+	mutex_unlock(&ima_keys_lock);
+
+	if (!process)
+		return;
+
+	if (!timer_expired)
+		cancel_delayed_work_sync(&ima_keys_delayed_work);
+
+	list_for_each_entry_safe(entry, tmp, &ima_keys, list) {
+		if (!timer_expired)
+			process_buffer_measurement(&nop_mnt_idmap, NULL,
+						   entry->payload,
+						   entry->payload_len,
+						   entry->keyring_name,
+						   KEY_CHECK, 0,
+						   entry->keyring_name,
+						   false, NULL, 0);
+		list_del(&entry->list);
+		ima_free_key_entry(entry);
+	}
+}
+
+inline bool ima_should_queue_key(void)
+{
+	return !ima_process_keys;
+}
diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c
new file mode 100644
index 000000000..7034573fb
--- /dev/null
+++ b/security/integrity/ima/ima_template.c
@@ -0,0 +1,537 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * File: ima_template.c
+ *      Helpers to manage template descriptors.
+ */
+
+#include <linux/rculist.h>
+#include "ima.h"
+#include "ima_template_lib.h"
+
+enum header_fields { HDR_PCR, HDR_DIGEST, HDR_TEMPLATE_NAME,
+		     HDR_TEMPLATE_DATA, HDR__LAST };
+
+static struct ima_template_desc builtin_templates[] = {
+	{.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
+	{.name = "ima-ng", .fmt = "d-ng|n-ng"},
+	{.name = "ima-sig", .fmt = "d-ng|n-ng|sig"},
+	{.name = "ima-ngv2", .fmt = "d-ngv2|n-ng"},
+	{.name = "ima-sigv2", .fmt = "d-ngv2|n-ng|sig"},
+	{.name = "ima-buf", .fmt = "d-ng|n-ng|buf"},
+	{.name = "ima-modsig", .fmt = "d-ng|n-ng|sig|d-modsig|modsig"},
+	{.name = "evm-sig",
+	 .fmt = "d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode"},
+	{.name = "", .fmt = ""},	/* placeholder for a custom format */
+};
+
+static LIST_HEAD(defined_templates);
+static DEFINE_SPINLOCK(template_list);
+static int template_setup_done;
+
+static const struct ima_template_field supported_fields[] = {
+	{.field_id = "d", .field_init = ima_eventdigest_init,
+	 .field_show = ima_show_template_digest},
+	{.field_id = "n", .field_init = ima_eventname_init,
+	 .field_show = ima_show_template_string},
+	{.field_id = "d-ng", .field_init = ima_eventdigest_ng_init,
+	 .field_show = ima_show_template_digest_ng},
+	{.field_id = "d-ngv2", .field_init = ima_eventdigest_ngv2_init,
+	 .field_show = ima_show_template_digest_ngv2},
+	{.field_id = "n-ng", .field_init = ima_eventname_ng_init,
+	 .field_show = ima_show_template_string},
+	{.field_id = "sig", .field_init = ima_eventsig_init,
+	 .field_show = ima_show_template_sig},
+	{.field_id = "buf", .field_init = ima_eventbuf_init,
+	 .field_show = ima_show_template_buf},
+	{.field_id = "d-modsig", .field_init = ima_eventdigest_modsig_init,
+	 .field_show = ima_show_template_digest_ng},
+	{.field_id = "modsig", .field_init = ima_eventmodsig_init,
+	 .field_show = ima_show_template_sig},
+	{.field_id = "evmsig", .field_init = ima_eventevmsig_init,
+	 .field_show = ima_show_template_sig},
+	{.field_id = "iuid", .field_init = ima_eventinodeuid_init,
+	 .field_show = ima_show_template_uint},
+	{.field_id = "igid", .field_init = ima_eventinodegid_init,
+	 .field_show = ima_show_template_uint},
+	{.field_id = "imode", .field_init = ima_eventinodemode_init,
+	 .field_show = ima_show_template_uint},
+	{.field_id = "xattrnames",
+	 .field_init = ima_eventinodexattrnames_init,
+	 .field_show = ima_show_template_string},
+	{.field_id = "xattrlengths",
+	 .field_init = ima_eventinodexattrlengths_init,
+	 .field_show = ima_show_template_sig},
+	{.field_id = "xattrvalues",
+	 .field_init = ima_eventinodexattrvalues_init,
+	 .field_show = ima_show_template_sig},
+};
+
+/*
+ * Used when restoring measurements carried over from a kexec. 'd' and 'n' don't
+ * need to be accounted for since they shouldn't be defined in the same template
+ * description as 'd-ng' and 'n-ng' respectively.
+ */
+#define MAX_TEMPLATE_NAME_LEN \
+	sizeof("d-ng|n-ng|evmsig|xattrnames|xattrlengths|xattrvalues|iuid|igid|imode")
+
+static struct ima_template_desc *ima_template;
+static struct ima_template_desc *ima_buf_template;
+
+/**
+ * ima_template_has_modsig - Check whether template has modsig-related fields.
+ * @ima_template: IMA template to check.
+ *
+ * Tells whether the given template has fields referencing a file's appended
+ * signature.
+ */
+bool ima_template_has_modsig(const struct ima_template_desc *ima_template)
+{
+	int i;
+
+	for (i = 0; i < ima_template->num_fields; i++)
+		if (!strcmp(ima_template->fields[i]->field_id, "modsig") ||
+		    !strcmp(ima_template->fields[i]->field_id, "d-modsig"))
+			return true;
+
+	return false;
+}
+
+static int __init ima_template_setup(char *str)
+{
+	struct ima_template_desc *template_desc;
+	int template_len = strlen(str);
+
+	if (template_setup_done)
+		return 1;
+
+	if (!ima_template)
+		ima_init_template_list();
+
+	/*
+	 * Verify that a template with the supplied name exists.
+	 * If not, use CONFIG_IMA_DEFAULT_TEMPLATE.
+	 */
+	template_desc = lookup_template_desc(str);
+	if (!template_desc) {
+		pr_err("template %s not found, using %s\n",
+		       str, CONFIG_IMA_DEFAULT_TEMPLATE);
+		return 1;
+	}
+
+	/*
+	 * Verify whether the current hash algorithm is supported
+	 * by the 'ima' template.
+	 */
+	if (template_len == 3 && strcmp(str, IMA_TEMPLATE_IMA_NAME) == 0 &&
+	    ima_hash_algo != HASH_ALGO_SHA1 && ima_hash_algo != HASH_ALGO_MD5) {
+		pr_err("template does not support hash alg\n");
+		return 1;
+	}
+
+	ima_template = template_desc;
+	template_setup_done = 1;
+	return 1;
+}
+__setup("ima_template=", ima_template_setup);
+
+static int __init ima_template_fmt_setup(char *str)
+{
+	int num_templates = ARRAY_SIZE(builtin_templates);
+
+	if (template_setup_done)
+		return 1;
+
+	if (template_desc_init_fields(str, NULL, NULL) < 0) {
+		pr_err("format string '%s' not valid, using template %s\n",
+		       str, CONFIG_IMA_DEFAULT_TEMPLATE);
+		return 1;
+	}
+
+	builtin_templates[num_templates - 1].fmt = str;
+	ima_template = builtin_templates + num_templates - 1;
+	template_setup_done = 1;
+
+	return 1;
+}
+__setup("ima_template_fmt=", ima_template_fmt_setup);
+
+struct ima_template_desc *lookup_template_desc(const char *name)
+{
+	struct ima_template_desc *template_desc;
+	int found = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(template_desc, &defined_templates, list) {
+		if ((strcmp(template_desc->name, name) == 0) ||
+		    (strcmp(template_desc->fmt, name) == 0)) {
+			found = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return found ? template_desc : NULL;
+}
+
+static const struct ima_template_field *
+lookup_template_field(const char *field_id)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(supported_fields); i++)
+		if (strncmp(supported_fields[i].field_id, field_id,
+			    IMA_TEMPLATE_FIELD_ID_MAX_LEN) == 0)
+			return &supported_fields[i];
+	return NULL;
+}
+
+static int template_fmt_size(const char *template_fmt)
+{
+	char c;
+	int template_fmt_len = strlen(template_fmt);
+	int i = 0, j = 0;
+
+	while (i < template_fmt_len) {
+		c = template_fmt[i];
+		if (c == '|')
+			j++;
+		i++;
+	}
+
+	return j + 1;
+}
+
+int template_desc_init_fields(const char *template_fmt,
+			      const struct ima_template_field ***fields,
+			      int *num_fields)
+{
+	const char *template_fmt_ptr;
+	const struct ima_template_field *found_fields[IMA_TEMPLATE_NUM_FIELDS_MAX];
+	int template_num_fields;
+	int i, len;
+
+	if (num_fields && *num_fields > 0) /* already initialized? */
+		return 0;
+
+	template_num_fields = template_fmt_size(template_fmt);
+
+	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX) {
+		pr_err("format string '%s' contains too many fields\n",
+		       template_fmt);
+		return -EINVAL;
+	}
+
+	for (i = 0, template_fmt_ptr = template_fmt; i < template_num_fields;
+	     i++, template_fmt_ptr += len + 1) {
+		char tmp_field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN + 1];
+
+		len = strchrnul(template_fmt_ptr, '|') - template_fmt_ptr;
+		if (len == 0 || len > IMA_TEMPLATE_FIELD_ID_MAX_LEN) {
+			pr_err("Invalid field with length %d\n", len);
+			return -EINVAL;
+		}
+
+		memcpy(tmp_field_id, template_fmt_ptr, len);
+		tmp_field_id[len] = '\0';
+		found_fields[i] = lookup_template_field(tmp_field_id);
+		if (!found_fields[i]) {
+			pr_err("field '%s' not found\n", tmp_field_id);
+			return -ENOENT;
+		}
+	}
+
+	if (fields && num_fields) {
+		*fields = kmalloc_objs(**fields, i);
+		if (*fields == NULL)
+			return -ENOMEM;
+
+		memcpy(*fields, found_fields, i * sizeof(**fields));
+		*num_fields = i;
+	}
+
+	return 0;
+}
+
+void ima_init_template_list(void)
+{
+	int i;
+
+	if (!list_empty(&defined_templates))
+		return;
+
+	spin_lock(&template_list);
+	for (i = 0; i < ARRAY_SIZE(builtin_templates); i++) {
+		list_add_tail_rcu(&builtin_templates[i].list,
+				  &defined_templates);
+	}
+	spin_unlock(&template_list);
+}
+
+struct ima_template_desc *ima_template_desc_current(void)
+{
+	if (!ima_template) {
+		ima_init_template_list();
+		ima_template =
+		    lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE);
+	}
+	return ima_template;
+}
+
+struct ima_template_desc *ima_template_desc_buf(void)
+{
+	if (!ima_buf_template) {
+		ima_init_template_list();
+		ima_buf_template = lookup_template_desc("ima-buf");
+	}
+	return ima_buf_template;
+}
+
+int __init ima_init_template(void)
+{
+	struct ima_template_desc *template = ima_template_desc_current();
+	int result;
+
+	result = template_desc_init_fields(template->fmt,
+					   &(template->fields),
+					   &(template->num_fields));
+	if (result < 0) {
+		pr_err("template %s init failed, result: %d\n",
+		       (strlen(template->name) ?
+		       template->name : template->fmt), result);
+		return result;
+	}
+
+	template = ima_template_desc_buf();
+	if (!template) {
+		pr_err("Failed to get ima-buf template\n");
+		return -EINVAL;
+	}
+
+	result = template_desc_init_fields(template->fmt,
+					   &(template->fields),
+					   &(template->num_fields));
+	if (result < 0)
+		pr_err("template %s init failed, result: %d\n",
+		       (strlen(template->name) ?
+		       template->name : template->fmt), result);
+
+	return result;
+}
+
+static struct ima_template_desc *restore_template_fmt(char *template_name)
+{
+	struct ima_template_desc *template_desc = NULL;
+	int ret;
+
+	ret = template_desc_init_fields(template_name, NULL, NULL);
+	if (ret < 0) {
+		pr_err("attempting to initialize the template \"%s\" failed\n",
+			template_name);
+		goto out;
+	}
+
+	template_desc = kzalloc_obj(*template_desc);
+	if (!template_desc)
+		goto out;
+
+	template_desc->name = "";
+	template_desc->fmt = kstrdup(template_name, GFP_KERNEL);
+	if (!template_desc->fmt) {
+		kfree(template_desc);
+		template_desc = NULL;
+		goto out;
+	}
+
+	spin_lock(&template_list);
+	list_add_tail_rcu(&template_desc->list, &defined_templates);
+	spin_unlock(&template_list);
+out:
+	return template_desc;
+}
+
+static int ima_restore_template_data(struct ima_template_desc *template_desc,
+				     void *template_data,
+				     int template_data_size,
+				     struct ima_template_entry **entry)
+{
+	struct tpm_digest *digests;
+	int ret = 0;
+	int i;
+
+	*entry = kzalloc_flex(**entry, template_data, template_desc->num_fields,
+			      GFP_NOFS);
+	if (!*entry)
+		return -ENOMEM;
+
+	digests = kzalloc_objs(*digests,
+			       NR_BANKS(ima_tpm_chip) + ima_extra_slots,
+			       GFP_NOFS);
+	if (!digests) {
+		kfree(*entry);
+		return -ENOMEM;
+	}
+
+	(*entry)->digests = digests;
+
+	ret = ima_parse_buf(template_data, template_data + template_data_size,
+			    NULL, template_desc->num_fields,
+			    (*entry)->template_data, NULL, NULL,
+			    ENFORCE_FIELDS | ENFORCE_BUFEND, "template data");
+	if (ret < 0) {
+		kfree((*entry)->digests);
+		kfree(*entry);
+		return ret;
+	}
+
+	(*entry)->template_desc = template_desc;
+	for (i = 0; i < template_desc->num_fields; i++) {
+		struct ima_field_data *field_data = &(*entry)->template_data[i];
+		u8 *data = field_data->data;
+
+		(*entry)->template_data[i].data =
+			kzalloc(field_data->len + 1, GFP_KERNEL);
+		if (!(*entry)->template_data[i].data) {
+			ret = -ENOMEM;
+			break;
+		}
+		memcpy((*entry)->template_data[i].data, data, field_data->len);
+		(*entry)->template_data_len += sizeof(field_data->len);
+		(*entry)->template_data_len += field_data->len;
+	}
+
+	if (ret < 0) {
+		ima_free_template_entry(*entry);
+		*entry = NULL;
+	}
+
+	return ret;
+}
+
+/* Restore the serialized binary measurement list without extending PCRs. */
+int ima_restore_measurement_list(loff_t size, void *buf)
+{
+	char template_name[MAX_TEMPLATE_NAME_LEN];
+	unsigned char zero[TPM_DIGEST_SIZE] = { 0 };
+
+	struct ima_kexec_hdr *khdr = buf;
+	struct ima_field_data hdr[HDR__LAST] = {
+		[HDR_PCR] = {.len = sizeof(u32)},
+		[HDR_DIGEST] = {.len = TPM_DIGEST_SIZE},
+	};
+
+	void *bufp = buf + sizeof(*khdr);
+	void *bufendp;
+	struct ima_template_entry *entry;
+	struct ima_template_desc *template_desc;
+	DECLARE_BITMAP(hdr_mask, HDR__LAST);
+	unsigned long count = 0;
+	int ret = 0;
+
+	if (!buf || size < sizeof(*khdr))
+		return 0;
+
+	if (ima_canonical_fmt) {
+		khdr->version = le16_to_cpu((__force __le16)khdr->version);
+		khdr->count = le64_to_cpu((__force __le64)khdr->count);
+		khdr->buffer_size = le64_to_cpu((__force __le64)khdr->buffer_size);
+	}
+
+	if (khdr->version != 1) {
+		pr_err("attempting to restore a incompatible measurement list");
+		return -EINVAL;
+	}
+
+	if (khdr->count > ULONG_MAX - 1) {
+		pr_err("attempting to restore too many measurements");
+		return -EINVAL;
+	}
+
+	bitmap_zero(hdr_mask, HDR__LAST);
+	bitmap_set(hdr_mask, HDR_PCR, 1);
+	bitmap_set(hdr_mask, HDR_DIGEST, 1);
+
+	/*
+	 * ima kexec buffer prefix: version, buffer size, count
+	 * v1 format: pcr, digest, template-name-len, template-name,
+	 *	      template-data-size, template-data
+	 */
+	bufendp = buf + khdr->buffer_size;
+	while ((bufp < bufendp) && (count++ < khdr->count)) {
+		int enforce_mask = ENFORCE_FIELDS;
+
+		enforce_mask |= (count == khdr->count) ? ENFORCE_BUFEND : 0;
+		ret = ima_parse_buf(bufp, bufendp, &bufp, HDR__LAST, hdr, NULL,
+				    hdr_mask, enforce_mask, "entry header");
+		if (ret < 0)
+			break;
+
+		if (hdr[HDR_TEMPLATE_NAME].len >= MAX_TEMPLATE_NAME_LEN) {
+			pr_err("attempting to restore a template name that is too long\n");
+			ret = -EINVAL;
+			break;
+		}
+
+		/* template name is not null terminated */
+		memcpy(template_name, hdr[HDR_TEMPLATE_NAME].data,
+		       hdr[HDR_TEMPLATE_NAME].len);
+		template_name[hdr[HDR_TEMPLATE_NAME].len] = 0;
+
+		if (strcmp(template_name, "ima") == 0) {
+			pr_err("attempting to restore an unsupported template \"%s\" failed\n",
+			       template_name);
+			ret = -EINVAL;
+			break;
+		}
+
+		template_desc = lookup_template_desc(template_name);
+		if (!template_desc) {
+			template_desc = restore_template_fmt(template_name);
+			if (!template_desc)
+				break;
+		}
+
+		/*
+		 * Only the running system's template format is initialized
+		 * on boot.  As needed, initialize the other template formats.
+		 */
+		ret = template_desc_init_fields(template_desc->fmt,
+						&(template_desc->fields),
+						&(template_desc->num_fields));
+		if (ret < 0) {
+			pr_err("attempting to restore the template fmt \"%s\" failed\n",
+			       template_desc->fmt);
+			ret = -EINVAL;
+			break;
+		}
+
+		ret = ima_restore_template_data(template_desc,
+						hdr[HDR_TEMPLATE_DATA].data,
+						hdr[HDR_TEMPLATE_DATA].len,
+						&entry);
+		if (ret < 0)
+			break;
+
+		if (memcmp(hdr[HDR_DIGEST].data, zero, sizeof(zero))) {
+			ret = ima_calc_field_array_hash(
+						&entry->template_data[0],
+						entry);
+			if (ret < 0) {
+				pr_err("cannot calculate template digest\n");
+				ret = -EINVAL;
+				break;
+			}
+		}
+
+		entry->pcr = !ima_canonical_fmt ? *(u32 *)(hdr[HDR_PCR].data) :
+			     le32_to_cpu(*(__le32 *)(hdr[HDR_PCR].data));
+		ret = ima_restore_measurement_entry(entry);
+		if (ret < 0)
+			break;
+
+	}
+	return ret;
+}
diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
new file mode 100644
index 000000000..8a89236f9
--- /dev/null
+++ b/security/integrity/ima/ima_template_lib.c
@@ -0,0 +1,765 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * File: ima_template_lib.c
+ *      Library of supported template fields.
+ */
+
+#include "ima_template_lib.h"
+#include <linux/xattr.h>
+#include <linux/evm.h>
+
+static bool ima_template_hash_algo_allowed(u8 algo)
+{
+	if (algo == HASH_ALGO_SHA1 || algo == HASH_ALGO_MD5)
+		return true;
+
+	return false;
+}
+
+enum data_formats {
+	DATA_FMT_DIGEST = 0,
+	DATA_FMT_DIGEST_WITH_ALGO,
+	DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO,
+	DATA_FMT_STRING,
+	DATA_FMT_HEX,
+	DATA_FMT_UINT
+};
+
+enum digest_type {
+	DIGEST_TYPE_IMA,
+	DIGEST_TYPE_VERITY,
+	DIGEST_TYPE__LAST
+};
+
+#define DIGEST_TYPE_NAME_LEN_MAX 7	/* including NUL */
+static const char * const digest_type_name[DIGEST_TYPE__LAST] = {
+	[DIGEST_TYPE_IMA] = "ima",
+	[DIGEST_TYPE_VERITY] = "verity"
+};
+
+static int ima_write_template_field_data(const void *data, const u32 datalen,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	u8 *buf, *buf_ptr;
+	u32 buflen = datalen;
+
+	if (datafmt == DATA_FMT_STRING)
+		buflen = datalen + 1;
+
+	buf = kzalloc(buflen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, data, datalen);
+
+	/*
+	 * Replace all space characters with underscore for event names and
+	 * strings. This avoid that, during the parsing of a measurements list,
+	 * filenames with spaces or that end with the suffix ' (deleted)' are
+	 * split into multiple template fields (the space is the delimitator
+	 * character for measurements lists in ASCII format).
+	 */
+	if (datafmt == DATA_FMT_STRING) {
+		for (buf_ptr = buf; buf_ptr - buf < datalen; buf_ptr++)
+			if (*buf_ptr == ' ')
+				*buf_ptr = '_';
+	}
+
+	field_data->data = buf;
+	field_data->len = buflen;
+	return 0;
+}
+
+static void ima_show_template_data_ascii(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	u8 *buf_ptr = field_data->data;
+	u32 buflen = field_data->len;
+
+	switch (datafmt) {
+	case DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO:
+	case DATA_FMT_DIGEST_WITH_ALGO:
+		buf_ptr = strrchr(field_data->data, ':');
+		if (buf_ptr != field_data->data)
+			seq_printf(m, "%s", field_data->data);
+
+		/* skip ':' and '\0' */
+		buf_ptr += 2;
+		buflen -= buf_ptr - field_data->data;
+		fallthrough;
+	case DATA_FMT_DIGEST:
+	case DATA_FMT_HEX:
+		if (!buflen)
+			break;
+		ima_print_digest(m, buf_ptr, buflen);
+		break;
+	case DATA_FMT_STRING:
+		seq_printf(m, "%s", buf_ptr);
+		break;
+	case DATA_FMT_UINT:
+		switch (field_data->len) {
+		case sizeof(u8):
+			seq_printf(m, "%u", *(u8 *)buf_ptr);
+			break;
+		case sizeof(u16):
+			if (ima_canonical_fmt)
+				seq_printf(m, "%u",
+					   le16_to_cpu(*(__le16 *)buf_ptr));
+			else
+				seq_printf(m, "%u", *(u16 *)buf_ptr);
+			break;
+		case sizeof(u32):
+			if (ima_canonical_fmt)
+				seq_printf(m, "%u",
+					   le32_to_cpu(*(__le32 *)buf_ptr));
+			else
+				seq_printf(m, "%u", *(u32 *)buf_ptr);
+			break;
+		case sizeof(u64):
+			if (ima_canonical_fmt)
+				seq_printf(m, "%llu",
+					   le64_to_cpu(*(__le64 *)buf_ptr));
+			else
+				seq_printf(m, "%llu", *(u64 *)buf_ptr);
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+static void ima_show_template_data_binary(struct seq_file *m,
+					  enum ima_show_type show,
+					  enum data_formats datafmt,
+					  struct ima_field_data *field_data)
+{
+	u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ?
+	    strlen(field_data->data) : field_data->len;
+
+	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN) {
+		u32 field_len = !ima_canonical_fmt ?
+				len : (__force u32)cpu_to_le32(len);
+
+		ima_putc(m, &field_len, sizeof(field_len));
+	}
+
+	if (!len)
+		return;
+
+	ima_putc(m, field_data->data, len);
+}
+
+static void ima_show_template_field_data(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	switch (show) {
+	case IMA_SHOW_ASCII:
+		ima_show_template_data_ascii(m, show, datafmt, field_data);
+		break;
+	case IMA_SHOW_BINARY:
+	case IMA_SHOW_BINARY_NO_FIELD_LEN:
+	case IMA_SHOW_BINARY_OLD_STRING_FMT:
+		ima_show_template_data_binary(m, show, datafmt, field_data);
+		break;
+	default:
+		break;
+	}
+}
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data);
+}
+
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_ALGO,
+				     field_data);
+}
+
+void ima_show_template_digest_ngv2(struct seq_file *m, enum ima_show_type show,
+				   struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show,
+				     DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO,
+				     field_data);
+}
+
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
+}
+
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data);
+}
+
+void ima_show_template_buf(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data);
+}
+
+void ima_show_template_uint(struct seq_file *m, enum ima_show_type show,
+			    struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_UINT, field_data);
+}
+
+/**
+ * ima_parse_buf() - Parses lengths and data from an input buffer
+ * @bufstartp:       Buffer start address.
+ * @bufendp:         Buffer end address.
+ * @bufcurp:         Pointer to remaining (non-parsed) data.
+ * @maxfields:       Length of fields array.
+ * @fields:          Array containing lengths and pointers of parsed data.
+ * @curfields:       Number of array items containing parsed data.
+ * @len_mask:        Bitmap (if bit is set, data length should not be parsed).
+ * @enforce_mask:    Check if curfields == maxfields and/or bufcurp == bufendp.
+ * @bufname:         String identifier of the input buffer.
+ *
+ * Return: 0 on success, -EINVAL on error.
+ */
+int ima_parse_buf(void *bufstartp, void *bufendp, void **bufcurp,
+		  int maxfields, struct ima_field_data *fields, int *curfields,
+		  unsigned long *len_mask, int enforce_mask, char *bufname)
+{
+	void *bufp = bufstartp;
+	int i;
+
+	for (i = 0; i < maxfields; i++) {
+		if (len_mask == NULL || !test_bit(i, len_mask)) {
+			if (bufp > (bufendp - sizeof(u32)))
+				break;
+
+			if (ima_canonical_fmt)
+				fields[i].len = le32_to_cpu(*(__le32 *)bufp);
+			else
+				fields[i].len = *(u32 *)bufp;
+
+			bufp += sizeof(u32);
+		}
+
+		if (bufp > (bufendp - fields[i].len))
+			break;
+
+		fields[i].data = bufp;
+		bufp += fields[i].len;
+	}
+
+	if ((enforce_mask & ENFORCE_FIELDS) && i != maxfields) {
+		pr_err("%s: nr of fields mismatch: expected: %d, current: %d\n",
+		       bufname, maxfields, i);
+		return -EINVAL;
+	}
+
+	if ((enforce_mask & ENFORCE_BUFEND) && bufp != bufendp) {
+		pr_err("%s: buf end mismatch: expected: %p, current: %p\n",
+		       bufname, bufendp, bufp);
+		return -EINVAL;
+	}
+
+	if (curfields)
+		*curfields = i;
+
+	if (bufcurp)
+		*bufcurp = bufp;
+
+	return 0;
+}
+
+static int ima_eventdigest_init_common(const u8 *digest, u32 digestsize,
+				       u8 digest_type, u8 hash_algo,
+				       struct ima_field_data *field_data)
+{
+	/*
+	 * digest formats:
+	 *  - DATA_FMT_DIGEST: digest
+	 *  - DATA_FMT_DIGEST_WITH_ALGO: <hash algo> + ':' + '\0' + digest,
+	 *  - DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO:
+	 *	<digest type> + ':' + <hash algo> + ':' + '\0' + digest,
+	 *
+	 *    where 'DATA_FMT_DIGEST' is the original digest format ('d')
+	 *      with a hash size limitation of 20 bytes,
+	 *    where <digest type> is either "ima" or "verity",
+	 *    where <hash algo> is the hash_algo_name[] string.
+	 */
+	u8 buffer[DIGEST_TYPE_NAME_LEN_MAX + CRYPTO_MAX_ALG_NAME + 2 +
+		IMA_MAX_DIGEST_SIZE] = { 0 };
+	enum data_formats fmt = DATA_FMT_DIGEST;
+	u32 offset = 0;
+
+	if (digest_type < DIGEST_TYPE__LAST && hash_algo < HASH_ALGO__LAST) {
+		fmt = DATA_FMT_DIGEST_WITH_TYPE_AND_ALGO;
+		offset += 1 + sprintf(buffer, "%s:%s:",
+				      digest_type_name[digest_type],
+				      hash_algo_name[hash_algo]);
+	} else if (hash_algo < HASH_ALGO__LAST) {
+		fmt = DATA_FMT_DIGEST_WITH_ALGO;
+		offset += 1 + sprintf(buffer, "%s:",
+				      hash_algo_name[hash_algo]);
+	}
+
+	if (digest) {
+		memcpy(buffer + offset, digest, digestsize);
+	} else {
+		/*
+		 * If digest is NULL, the event being recorded is a violation.
+		 * Make room for the digest by increasing the offset by the
+		 * hash algorithm digest size. If the hash algorithm is not
+		 * specified increase the offset by IMA_DIGEST_SIZE which
+		 * fits SHA1 or MD5
+		 */
+		if (hash_algo < HASH_ALGO__LAST)
+			offset += hash_digest_size[hash_algo];
+		else
+			offset += IMA_DIGEST_SIZE;
+	}
+
+	return ima_write_template_field_data(buffer, offset + digestsize,
+					     fmt, field_data);
+}
+
+/*
+ * This function writes the digest of an event (with size limit).
+ */
+int ima_eventdigest_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data)
+{
+	struct ima_max_digest_data hash;
+	struct ima_digest_data *hash_hdr = container_of(&hash.hdr,
+						struct ima_digest_data, hdr);
+	u8 *cur_digest = NULL;
+	u32 cur_digestsize = 0;
+	struct inode *inode;
+	int result;
+
+	memset(&hash, 0, sizeof(hash));
+
+	if (event_data->violation)	/* recording a violation. */
+		goto out;
+
+	if (ima_template_hash_algo_allowed(event_data->iint->ima_hash->algo)) {
+		cur_digest = event_data->iint->ima_hash->digest;
+		cur_digestsize = event_data->iint->ima_hash->length;
+		goto out;
+	}
+
+	if ((const char *)event_data->filename == boot_aggregate_name ||
+	    (const char *)event_data->filename == boot_aggregate_late_name) {
+		if (ima_tpm_chip) {
+			hash.hdr.algo = HASH_ALGO_SHA1;
+			result = ima_calc_boot_aggregate(hash_hdr);
+
+			/* algo can change depending on available PCR banks */
+			if (!result && hash.hdr.algo != HASH_ALGO_SHA1)
+				result = -EINVAL;
+
+			if (result < 0)
+				memset(&hash, 0, sizeof(hash));
+		}
+
+		cur_digest = hash_hdr->digest;
+		cur_digestsize = hash_digest_size[HASH_ALGO_SHA1];
+		goto out;
+	}
+
+	if (!event_data->file)	/* missing info to re-calculate the digest */
+		return -EINVAL;
+
+	inode = file_inode(event_data->file);
+	hash.hdr.algo = ima_template_hash_algo_allowed(ima_hash_algo) ?
+	    ima_hash_algo : HASH_ALGO_SHA1;
+	result = ima_calc_file_hash(event_data->file, hash_hdr);
+	if (result) {
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+				    event_data->filename, "collect_data",
+				    "failed", result, 0);
+		return result;
+	}
+	cur_digest = hash_hdr->digest;
+	cur_digestsize = hash.hdr.length;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   DIGEST_TYPE__LAST, HASH_ALGO__LAST,
+					   field_data);
+}
+
+/*
+ * This function writes the digest of an event (without size limit).
+ */
+int ima_eventdigest_ng_init(struct ima_event_data *event_data,
+			    struct ima_field_data *field_data)
+{
+	u8 *cur_digest = NULL, hash_algo = ima_hash_algo;
+	u32 cur_digestsize = 0;
+
+	if (event_data->violation)	/* recording a violation. */
+		goto out;
+
+	cur_digest = event_data->iint->ima_hash->digest;
+	cur_digestsize = event_data->iint->ima_hash->length;
+
+	hash_algo = event_data->iint->ima_hash->algo;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   DIGEST_TYPE__LAST, hash_algo,
+					   field_data);
+}
+
+/*
+ * This function writes the digest of an event (without size limit),
+ * prefixed with both the digest type and hash algorithm.
+ */
+int ima_eventdigest_ngv2_init(struct ima_event_data *event_data,
+			      struct ima_field_data *field_data)
+{
+	u8 *cur_digest = NULL, hash_algo = ima_hash_algo;
+	u32 cur_digestsize = 0;
+	u8 digest_type = DIGEST_TYPE_IMA;
+
+	if (event_data->violation)	/* recording a violation. */
+		goto out;
+
+	cur_digest = event_data->iint->ima_hash->digest;
+	cur_digestsize = event_data->iint->ima_hash->length;
+
+	hash_algo = event_data->iint->ima_hash->algo;
+	if (event_data->iint->flags & IMA_VERITY_REQUIRED)
+		digest_type = DIGEST_TYPE_VERITY;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   digest_type, hash_algo,
+					   field_data);
+}
+
+/*
+ * This function writes the digest of the file which is expected to match the
+ * digest contained in the file's appended signature.
+ */
+int ima_eventdigest_modsig_init(struct ima_event_data *event_data,
+				struct ima_field_data *field_data)
+{
+	enum hash_algo hash_algo;
+	const u8 *cur_digest;
+	u32 cur_digestsize;
+
+	if (!event_data->modsig)
+		return 0;
+
+	if (event_data->violation) {
+		/* Recording a violation. */
+		hash_algo = HASH_ALGO_SHA1;
+		cur_digest = NULL;
+		cur_digestsize = 0;
+	} else {
+		int rc;
+
+		rc = ima_get_modsig_digest(event_data->modsig, &hash_algo,
+					   &cur_digest, &cur_digestsize);
+		if (rc)
+			return rc;
+		else if (hash_algo == HASH_ALGO__LAST || cur_digestsize == 0)
+			/* There was some error collecting the digest. */
+			return -EINVAL;
+	}
+
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   DIGEST_TYPE__LAST, hash_algo,
+					   field_data);
+}
+
+static int ima_eventname_init_common(struct ima_event_data *event_data,
+				     struct ima_field_data *field_data,
+				     bool size_limit)
+{
+	const char *cur_filename = NULL;
+	struct name_snapshot filename;
+	u32 cur_filename_len = 0;
+	bool snapshot = false;
+	int ret;
+
+	BUG_ON(event_data->filename == NULL && event_data->file == NULL);
+
+	if (event_data->filename) {
+		cur_filename = event_data->filename;
+		cur_filename_len = strlen(event_data->filename);
+
+		if (!size_limit || cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
+			goto out;
+	}
+
+	if (event_data->file) {
+		take_dentry_name_snapshot(&filename,
+					  event_data->file->f_path.dentry);
+		snapshot = true;
+		cur_filename = filename.name.name;
+		cur_filename_len = strlen(cur_filename);
+	} else
+		/*
+		 * Truncate filename if the latter is too long and
+		 * the file descriptor is not available.
+		 */
+		cur_filename_len = IMA_EVENT_NAME_LEN_MAX;
+out:
+	ret = ima_write_template_field_data(cur_filename, cur_filename_len,
+					    DATA_FMT_STRING, field_data);
+
+	if (snapshot)
+		release_dentry_name_snapshot(&filename);
+
+	return ret;
+}
+
+/*
+ * This function writes the name of an event (with size limit).
+ */
+int ima_eventname_init(struct ima_event_data *event_data,
+		       struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(event_data, field_data, true);
+}
+
+/*
+ * This function writes the name of an event (without size limit).
+ */
+int ima_eventname_ng_init(struct ima_event_data *event_data,
+			  struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(event_data, field_data, false);
+}
+
+/*
+ *  ima_eventsig_init - include the file signature as part of the template data
+ */
+int ima_eventsig_init(struct ima_event_data *event_data,
+		      struct ima_field_data *field_data)
+{
+	struct evm_ima_xattr_data *xattr_value = event_data->xattr_value;
+
+	if (!xattr_value ||
+	    (xattr_value->type != EVM_IMA_XATTR_DIGSIG &&
+	     xattr_value->type != IMA_VERITY_DIGSIG))
+		return ima_eventevmsig_init(event_data, field_data);
+
+	return ima_write_template_field_data(xattr_value, event_data->xattr_len,
+					     DATA_FMT_HEX, field_data);
+}
+
+/*
+ *  ima_eventbuf_init - include the buffer(kexec-cmldine) as part of the
+ *  template data.
+ */
+int ima_eventbuf_init(struct ima_event_data *event_data,
+		      struct ima_field_data *field_data)
+{
+	if ((!event_data->buf) || (event_data->buf_len == 0))
+		return 0;
+
+	return ima_write_template_field_data(event_data->buf,
+					     event_data->buf_len, DATA_FMT_HEX,
+					     field_data);
+}
+
+/*
+ *  ima_eventmodsig_init - include the appended file signature as part of the
+ *  template data
+ */
+int ima_eventmodsig_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data)
+{
+	const void *data;
+	u32 data_len;
+	int rc;
+
+	if (!event_data->modsig)
+		return 0;
+
+	/*
+	 * modsig is a runtime structure containing pointers. Get its raw data
+	 * instead.
+	 */
+	rc = ima_get_raw_modsig(event_data->modsig, &data, &data_len);
+	if (rc)
+		return rc;
+
+	return ima_write_template_field_data(data, data_len, DATA_FMT_HEX,
+					     field_data);
+}
+
+/*
+ *  ima_eventevmsig_init - include the EVM portable signature as part of the
+ *  template data
+ */
+int ima_eventevmsig_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data)
+{
+	struct evm_ima_xattr_data *xattr_data = NULL;
+	int rc = 0;
+
+	if (!event_data->file)
+		return 0;
+
+	rc = vfs_getxattr_alloc(&nop_mnt_idmap, file_dentry(event_data->file),
+				XATTR_NAME_EVM, (char **)&xattr_data, 0,
+				GFP_NOFS);
+	if (rc <= 0 || xattr_data->type != EVM_XATTR_PORTABLE_DIGSIG) {
+		rc = 0;
+		goto out;
+	}
+
+	rc = ima_write_template_field_data((char *)xattr_data, rc, DATA_FMT_HEX,
+					   field_data);
+
+out:
+	kfree(xattr_data);
+	return rc;
+}
+
+static int ima_eventinodedac_init_common(struct ima_event_data *event_data,
+					 struct ima_field_data *field_data,
+					 bool get_uid)
+{
+	unsigned int id;
+
+	if (!event_data->file)
+		return 0;
+
+	if (get_uid)
+		id = i_uid_read(file_inode(event_data->file));
+	else
+		id = i_gid_read(file_inode(event_data->file));
+
+	if (ima_canonical_fmt) {
+		if (sizeof(id) == sizeof(u16))
+			id = (__force u16)cpu_to_le16(id);
+		else
+			id = (__force u32)cpu_to_le32(id);
+	}
+
+	return ima_write_template_field_data((void *)&id, sizeof(id),
+					     DATA_FMT_UINT, field_data);
+}
+
+/*
+ *  ima_eventinodeuid_init - include the inode UID as part of the template
+ *  data
+ */
+int ima_eventinodeuid_init(struct ima_event_data *event_data,
+			   struct ima_field_data *field_data)
+{
+	return ima_eventinodedac_init_common(event_data, field_data, true);
+}
+
+/*
+ *  ima_eventinodegid_init - include the inode GID as part of the template
+ *  data
+ */
+int ima_eventinodegid_init(struct ima_event_data *event_data,
+			   struct ima_field_data *field_data)
+{
+	return ima_eventinodedac_init_common(event_data, field_data, false);
+}
+
+/*
+ *  ima_eventinodemode_init - include the inode mode as part of the template
+ *  data
+ */
+int ima_eventinodemode_init(struct ima_event_data *event_data,
+			    struct ima_field_data *field_data)
+{
+	struct inode *inode;
+	u16 mode;
+
+	if (!event_data->file)
+		return 0;
+
+	inode = file_inode(event_data->file);
+	mode = inode->i_mode;
+	if (ima_canonical_fmt)
+		mode = (__force u16)cpu_to_le16(mode);
+
+	return ima_write_template_field_data((char *)&mode, sizeof(mode),
+					     DATA_FMT_UINT, field_data);
+}
+
+static int ima_eventinodexattrs_init_common(struct ima_event_data *event_data,
+					    struct ima_field_data *field_data,
+					    char type)
+{
+	u8 *buffer = NULL;
+	int rc;
+
+	if (!event_data->file)
+		return 0;
+
+	rc = evm_read_protected_xattrs(file_dentry(event_data->file), NULL, 0,
+				       type, ima_canonical_fmt);
+	if (rc < 0)
+		return 0;
+
+	buffer = kmalloc(rc, GFP_KERNEL);
+	if (!buffer)
+		return 0;
+
+	rc = evm_read_protected_xattrs(file_dentry(event_data->file), buffer,
+				       rc, type, ima_canonical_fmt);
+	if (rc < 0) {
+		rc = 0;
+		goto out;
+	}
+
+	rc = ima_write_template_field_data((char *)buffer, rc, DATA_FMT_HEX,
+					   field_data);
+out:
+	kfree(buffer);
+	return rc;
+}
+
+/*
+ *  ima_eventinodexattrnames_init - include a list of xattr names as part of the
+ *  template data
+ */
+int ima_eventinodexattrnames_init(struct ima_event_data *event_data,
+				  struct ima_field_data *field_data)
+{
+	return ima_eventinodexattrs_init_common(event_data, field_data, 'n');
+}
+
+/*
+ *  ima_eventinodexattrlengths_init - include a list of xattr lengths as part of
+ *  the template data
+ */
+int ima_eventinodexattrlengths_init(struct ima_event_data *event_data,
+				    struct ima_field_data *field_data)
+{
+	return ima_eventinodexattrs_init_common(event_data, field_data, 'l');
+}
+
+/*
+ *  ima_eventinodexattrvalues_init - include a list of xattr values as part of
+ *  the template data
+ */
+int ima_eventinodexattrvalues_init(struct ima_event_data *event_data,
+				   struct ima_field_data *field_data)
+{
+	return ima_eventinodexattrs_init_common(event_data, field_data, 'v');
+}
diff --git a/security/integrity/ima/ima_template_lib.h b/security/integrity/ima/ima_template_lib.h
new file mode 100644
index 000000000..9f7c335f3
--- /dev/null
+++ b/security/integrity/ima/ima_template_lib.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * File: ima_template_lib.h
+ *      Header for the library of supported template fields.
+ */
+#ifndef __LINUX_IMA_TEMPLATE_LIB_H
+#define __LINUX_IMA_TEMPLATE_LIB_H
+
+#include <linux/seq_file.h>
+#include "ima.h"
+
+#define ENFORCE_FIELDS 0x00000001
+#define ENFORCE_BUFEND 0x00000002
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data);
+void ima_show_template_digest_ngv2(struct seq_file *m, enum ima_show_type show,
+				   struct ima_field_data *field_data);
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data);
+void ima_show_template_buf(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data);
+void ima_show_template_uint(struct seq_file *m, enum ima_show_type show,
+			    struct ima_field_data *field_data);
+int ima_parse_buf(void *bufstartp, void *bufendp, void **bufcurp,
+		  int maxfields, struct ima_field_data *fields, int *curfields,
+		  unsigned long *len_mask, int enforce_mask, char *bufname);
+int ima_eventdigest_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data);
+int ima_eventname_init(struct ima_event_data *event_data,
+		       struct ima_field_data *field_data);
+int ima_eventdigest_ng_init(struct ima_event_data *event_data,
+			    struct ima_field_data *field_data);
+int ima_eventdigest_ngv2_init(struct ima_event_data *event_data,
+			      struct ima_field_data *field_data);
+int ima_eventdigest_modsig_init(struct ima_event_data *event_data,
+				struct ima_field_data *field_data);
+int ima_eventname_ng_init(struct ima_event_data *event_data,
+			  struct ima_field_data *field_data);
+int ima_eventsig_init(struct ima_event_data *event_data,
+		      struct ima_field_data *field_data);
+int ima_eventbuf_init(struct ima_event_data *event_data,
+		      struct ima_field_data *field_data);
+int ima_eventmodsig_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data);
+int ima_eventevmsig_init(struct ima_event_data *event_data,
+			 struct ima_field_data *field_data);
+int ima_eventinodeuid_init(struct ima_event_data *event_data,
+			   struct ima_field_data *field_data);
+int ima_eventinodegid_init(struct ima_event_data *event_data,
+			   struct ima_field_data *field_data);
+int ima_eventinodemode_init(struct ima_event_data *event_data,
+			    struct ima_field_data *field_data);
+int ima_eventinodexattrnames_init(struct ima_event_data *event_data,
+				  struct ima_field_data *field_data);
+int ima_eventinodexattrlengths_init(struct ima_event_data *event_data,
+				    struct ima_field_data *field_data);
+int ima_eventinodexattrvalues_init(struct ima_event_data *event_data,
+				   struct ima_field_data *field_data);
+#endif /* __LINUX_IMA_TEMPLATE_LIB_H */
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
new file mode 100644
index 000000000..0c581c03c
--- /dev/null
+++ b/security/integrity/integrity.h
@@ -0,0 +1,281 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ */
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/integrity.h>
+#include <linux/secure_boot.h>
+#include <crypto/sha1.h>
+#include <crypto/hash.h>
+#include <linux/key.h>
+#include <linux/audit.h>
+#include <linux/lsm_hooks.h>
+
+enum evm_ima_xattr_type {
+	IMA_XATTR_DIGEST = 0x01,
+	EVM_XATTR_HMAC,
+	EVM_IMA_XATTR_DIGSIG,
+	IMA_XATTR_DIGEST_NG,
+	EVM_XATTR_PORTABLE_DIGSIG,
+	IMA_VERITY_DIGSIG,
+	IMA_XATTR_LAST
+};
+
+struct evm_ima_xattr_data {
+	/* New members must be added within the __struct_group() macro below. */
+	__struct_group(evm_ima_xattr_data_hdr, hdr, __packed,
+		u8 type;
+	);
+	u8 data[];
+} __packed;
+static_assert(offsetof(struct evm_ima_xattr_data, data) == sizeof(struct evm_ima_xattr_data_hdr),
+	      "struct member likely outside of __struct_group()");
+
+/* Only used in the EVM HMAC code. */
+struct evm_xattr {
+	struct evm_ima_xattr_data_hdr data;
+	u8 digest[SHA1_DIGEST_SIZE];
+} __packed;
+
+#define IMA_MAX_DIGEST_SIZE	HASH_MAX_DIGESTSIZE
+
+struct ima_digest_data {
+	/* New members must be added within the __struct_group() macro below. */
+	__struct_group(ima_digest_data_hdr, hdr, __packed,
+	u8 algo;
+	u8 length;
+	union {
+		struct {
+			u8 unused;
+			u8 type;
+		} sha1;
+		struct {
+			u8 type;
+			u8 algo;
+		} ng;
+		u8 data[2];
+	} xattr;
+	);
+	u8 digest[];
+} __packed;
+static_assert(offsetof(struct ima_digest_data, digest) == sizeof(struct ima_digest_data_hdr),
+	      "struct member likely outside of __struct_group()");
+
+/*
+ * Instead of wrapping the ima_digest_data struct inside a local structure
+ * with the maximum hash size, define ima_max_digest_data struct.
+ */
+struct ima_max_digest_data {
+	struct ima_digest_data_hdr hdr;
+	u8 digest[HASH_MAX_DIGESTSIZE];
+} __packed;
+
+/*
+ * signature header format v2 - for using with asymmetric keys
+ *
+ * The signature_v2_hdr struct includes a signature format version
+ * to simplify defining new signature formats.
+ *
+ * signature format:
+ * version 2: regular file data hash based signature
+ * version 3: struct ima_file_id data based signature
+ */
+struct signature_v2_hdr {
+	uint8_t type;		/* xattr type */
+	uint8_t version;	/* signature format version */
+	uint8_t	hash_algo;	/* Digest algorithm [enum hash_algo] */
+	__be32 keyid;		/* IMA key identifier - not X509/PGP specific */
+	__be16 sig_size;	/* signature size */
+	uint8_t sig[];		/* signature payload */
+} __packed;
+
+/*
+ * IMA signature version 3 disambiguates the data that is signed, by
+ * indirectly signing the hash of the ima_file_id structure data,
+ * containing either the fsverity_descriptor struct digest or, in the
+ * future, the regular IMA file hash.
+ *
+ * (The hash of the ima_file_id structure is only of the portion used.)
+ */
+struct ima_file_id {
+	__u8 hash_type;		/* xattr type [enum evm_ima_xattr_type] */
+	__u8 hash_algorithm;	/* Digest algorithm [enum hash_algo] */
+	__u8 hash[HASH_MAX_DIGESTSIZE];
+} __packed;
+
+int integrity_kernel_read(struct file *file, loff_t offset,
+			  void *addr, unsigned long count);
+int __init integrity_fs_init(void);
+void __init integrity_fs_fini(void);
+
+#define INTEGRITY_KEYRING_EVM		0
+#define INTEGRITY_KEYRING_IMA		1
+#define INTEGRITY_KEYRING_PLATFORM	2
+#define INTEGRITY_KEYRING_MACHINE	3
+#define INTEGRITY_KEYRING_MAX		4
+
+extern struct dentry *integrity_dir;
+
+struct modsig;
+
+#ifdef CONFIG_INTEGRITY_SIGNATURE
+
+int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
+			    const char *digest, int digestlen, u8 algo);
+int integrity_modsig_verify(unsigned int id, const struct modsig *modsig);
+
+int __init integrity_init_keyring(const unsigned int id);
+int __init integrity_load_x509(const unsigned int id, const char *path);
+int __init integrity_load_cert(const unsigned int id, const char *source,
+			       const void *data, size_t len, key_perm_t perm);
+#else
+
+static inline int integrity_digsig_verify(const unsigned int id,
+					  const char *sig, int siglen,
+					  const char *digest, int digestlen,
+					  u8 algo)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int integrity_modsig_verify(unsigned int id,
+					  const struct modsig *modsig)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int integrity_init_keyring(const unsigned int id)
+{
+	return 0;
+}
+
+static inline int __init integrity_load_cert(const unsigned int id,
+					     const char *source,
+					     const void *data, size_t len,
+					     key_perm_t perm)
+{
+	return 0;
+}
+#endif /* CONFIG_INTEGRITY_SIGNATURE */
+
+#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+int asymmetric_verify(struct key *keyring, const char *sig,
+		      int siglen, const char *data, int datalen);
+int asymmetric_verify_v3(struct key *keyring, const char *sig,
+			 int siglen, const char *data, int datalen, u8 algo);
+#else
+static inline int asymmetric_verify(struct key *keyring, const char *sig,
+				    int siglen, const char *data, int datalen)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int asymmetric_verify_v3(struct key *keyring,
+				       const char *sig, int siglen,
+				       const char *data, int datalen, u8 algo)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#ifdef CONFIG_IMA_APPRAISE_MODSIG
+int ima_modsig_verify(struct key *keyring, const struct modsig *modsig);
+#else
+static inline int ima_modsig_verify(struct key *keyring,
+				    const struct modsig *modsig)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#ifdef CONFIG_IMA_LOAD_X509
+void __init ima_load_x509(void);
+#else
+static inline void ima_load_x509(void)
+{
+}
+#endif
+
+#ifdef CONFIG_EVM_LOAD_X509
+void __init evm_load_x509(void);
+#else
+static inline void evm_load_x509(void)
+{
+}
+#endif
+
+#ifdef CONFIG_INTEGRITY_AUDIT
+/* declarations */
+void integrity_audit_msg(int audit_msgno, struct inode *inode,
+			 const unsigned char *fname, const char *op,
+			 const char *cause, int result, int info);
+
+void integrity_audit_message(int audit_msgno, struct inode *inode,
+			     const unsigned char *fname, const char *op,
+			     const char *cause, int result, int info,
+			     int errno);
+
+static inline struct audit_buffer *
+integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type)
+{
+	return audit_log_start(ctx, gfp_mask, type);
+}
+
+#else
+static inline void integrity_audit_msg(int audit_msgno, struct inode *inode,
+				       const unsigned char *fname,
+				       const char *op, const char *cause,
+				       int result, int info)
+{
+}
+
+static inline void integrity_audit_message(int audit_msgno,
+					   struct inode *inode,
+					   const unsigned char *fname,
+					   const char *op, const char *cause,
+					   int result, int info, int errno)
+{
+}
+
+static inline struct audit_buffer *
+integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type)
+{
+	return NULL;
+}
+
+#endif
+
+#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING
+void __init add_to_platform_keyring(const char *source, const void *data,
+				    size_t len);
+#else
+static inline void __init add_to_platform_keyring(const char *source,
+						  const void *data, size_t len)
+{
+}
+#endif
+
+#ifdef CONFIG_INTEGRITY_MACHINE_KEYRING
+void __init add_to_machine_keyring(const char *source, const void *data, size_t len);
+bool __init imputed_trust_enabled(void);
+#else
+static inline void __init add_to_machine_keyring(const char *source,
+						  const void *data, size_t len)
+{
+}
+
+static inline bool __init imputed_trust_enabled(void)
+{
+	return false;
+}
+#endif
diff --git a/security/integrity/integrity_audit.c b/security/integrity/integrity_audit.c
new file mode 100644
index 000000000..d8d9e5ff1
--- /dev/null
+++ b/security/integrity/integrity_audit.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2008 IBM Corporation
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * File: integrity_audit.c
+ *	Audit calls for the integrity subsystem
+ */
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/audit.h>
+#include "integrity.h"
+
+static int integrity_audit_info;
+
+/* ima_audit_setup - enable informational auditing messages */
+static int __init integrity_audit_setup(char *str)
+{
+	unsigned long audit;
+
+	if (!kstrtoul(str, 0, &audit))
+		integrity_audit_info = audit ? 1 : 0;
+	return 1;
+}
+__setup("integrity_audit=", integrity_audit_setup);
+
+void integrity_audit_msg(int audit_msgno, struct inode *inode,
+			 const unsigned char *fname, const char *op,
+			 const char *cause, int result, int audit_info)
+{
+	integrity_audit_message(audit_msgno, inode, fname, op, cause,
+				result, audit_info, 0);
+}
+
+void integrity_audit_message(int audit_msgno, struct inode *inode,
+			     const unsigned char *fname, const char *op,
+			     const char *cause, int result, int audit_info,
+			     int errno)
+{
+	struct audit_buffer *ab;
+	char name[TASK_COMM_LEN];
+
+	if (!integrity_audit_info && audit_info == 1)	/* Skip info messages */
+		return;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL, audit_msgno);
+	if (!ab)
+		return;
+	audit_log_format(ab, "pid=%d uid=%u auid=%u ses=%u",
+			 task_pid_nr(current),
+			 from_kuid(&init_user_ns, current_uid()),
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current));
+	audit_log_task_context(ab);
+	audit_log_format(ab, " op=%s cause=%s comm=", op, cause);
+	audit_log_untrustedstring(ab, get_task_comm(name, current));
+	if (fname) {
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, fname);
+	}
+	if (inode) {
+		audit_log_format(ab, " dev=");
+		audit_log_untrustedstring(ab, inode->i_sb->s_id);
+		audit_log_format(ab, " ino=%llu", inode->i_ino);
+	}
+	audit_log_format(ab, " res=%d errno=%d", !result, errno);
+	audit_log_end(ab);
+}
diff --git a/security/integrity/platform_certs/efi_parser.c b/security/integrity/platform_certs/efi_parser.c
new file mode 100644
index 000000000..d98260f84
--- /dev/null
+++ b/security/integrity/platform_certs/efi_parser.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* EFI signature/key/certificate list parser
+ *
+ * Copyright (C) 2012, 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) "EFI: "fmt
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+
+/**
+ * parse_efi_signature_list - Parse an EFI signature list for certificates
+ * @source: The source of the key
+ * @data: The data blob to parse
+ * @size: The size of the data blob
+ * @get_handler_for_guid: Get the handler func for the sig type (or NULL)
+ *
+ * Parse an EFI signature list looking for elements of interest.  A list is
+ * made up of a series of sublists, where all the elements in a sublist are of
+ * the same type, but sublists can be of different types.
+ *
+ * For each sublist encountered, the @get_handler_for_guid function is called
+ * with the type specifier GUID and returns either a pointer to a function to
+ * handle elements of that type or NULL if the type is not of interest.
+ *
+ * If the sublist is of interest, each element is passed to the handler
+ * function in turn.
+ *
+ * Error EBADMSG is returned if the list doesn't parse correctly and 0 is
+ * returned if the list was parsed correctly.  No error can be returned from
+ * the @get_handler_for_guid function or the element handler function it
+ * returns.
+ */
+int __init parse_efi_signature_list(
+	const char *source,
+	const void *data, size_t size,
+	efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *))
+{
+	efi_element_handler_t handler;
+	unsigned int offs = 0;
+
+	pr_devel("-->%s(,%zu)\n", __func__, size);
+
+	while (size > 0) {
+		const efi_signature_data_t *elem;
+		efi_signature_list_t list;
+		size_t lsize, esize, hsize, elsize;
+
+		if (size < sizeof(list))
+			return -EBADMSG;
+
+		memcpy(&list, data, sizeof(list));
+		pr_devel("LIST[%04x] guid=%pUl ls=%x hs=%x ss=%x\n",
+			 offs,
+			 &list.signature_type, list.signature_list_size,
+			 list.signature_header_size, list.signature_size);
+
+		lsize = list.signature_list_size;
+		hsize = list.signature_header_size;
+		esize = list.signature_size;
+		elsize = lsize - sizeof(list) - hsize;
+
+		if (lsize > size) {
+			pr_devel("<--%s() = -EBADMSG [overrun @%x]\n",
+				 __func__, offs);
+			return -EBADMSG;
+		}
+
+		if (lsize < sizeof(list) ||
+		    lsize - sizeof(list) < hsize ||
+		    esize < sizeof(*elem) ||
+		    elsize < esize ||
+		    elsize % esize != 0) {
+			pr_devel("- bad size combo @%x\n", offs);
+			return -EBADMSG;
+		}
+
+		handler = get_handler_for_guid(&list.signature_type);
+		if (!handler) {
+			data += lsize;
+			size -= lsize;
+			offs += lsize;
+			continue;
+		}
+
+		data += sizeof(list) + hsize;
+		size -= sizeof(list) + hsize;
+		offs += sizeof(list) + hsize;
+
+		for (; elsize > 0; elsize -= esize) {
+			elem = data;
+
+			pr_devel("ELEM[%04x]\n", offs);
+			handler(source,
+				&elem->signature_data,
+				esize - sizeof(*elem));
+
+			data += esize;
+			size -= esize;
+			offs += esize;
+		}
+	}
+
+	return 0;
+}
diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c
new file mode 100644
index 000000000..13ea17207
--- /dev/null
+++ b/security/integrity/platform_certs/keyring_handler.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "../integrity.h"
+#include "keyring_handler.h"
+
+static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID;
+static efi_guid_t efi_cert_x509_sha256_guid __initdata =
+	EFI_CERT_X509_SHA256_GUID;
+static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID;
+
+/*
+ * Blacklist an X509 TBS hash.
+ */
+static __init void uefi_blacklist_x509_tbs(const char *source,
+					   const void *data, size_t len)
+{
+	mark_hash_blacklisted(data, len, BLACKLIST_HASH_X509_TBS);
+}
+
+/*
+ * Blacklist the hash of an executable.
+ */
+static __init void uefi_blacklist_binary(const char *source,
+					 const void *data, size_t len)
+{
+	mark_hash_blacklisted(data, len, BLACKLIST_HASH_BINARY);
+}
+
+/*
+ * Add an X509 cert to the revocation list.
+ */
+static __init void uefi_revocation_list_x509(const char *source,
+					     const void *data, size_t len)
+{
+	add_key_to_revocation_list(data, len);
+}
+
+/*
+ * Return the appropriate handler for particular signature list types found in
+ * the UEFI db tables.
+ */
+__init efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type)
+{
+	if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0)
+		return add_to_platform_keyring;
+	return NULL;
+}
+
+/*
+ * Return the appropriate handler for particular signature list types found in
+ * the MokListRT tables.
+ */
+__init efi_element_handler_t get_handler_for_mok(const efi_guid_t *sig_type)
+{
+	if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) {
+		if (IS_ENABLED(CONFIG_INTEGRITY_MACHINE_KEYRING) &&
+		    imputed_trust_enabled())
+			return add_to_machine_keyring;
+		else
+			return add_to_platform_keyring;
+	}
+	return NULL;
+}
+
+__init efi_element_handler_t get_handler_for_ca_keys(const efi_guid_t *sig_type)
+{
+	if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0)
+		return add_to_machine_keyring;
+
+	return NULL;
+}
+
+__init efi_element_handler_t get_handler_for_code_signing_keys(const efi_guid_t *sig_type)
+{
+	if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0)
+		return add_to_secondary_keyring;
+
+	return NULL;
+}
+
+/*
+ * Return the appropriate handler for particular signature list types found in
+ * the UEFI dbx and MokListXRT tables.
+ */
+__init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type)
+{
+	if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0)
+		return uefi_blacklist_x509_tbs;
+	if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0)
+		return uefi_blacklist_binary;
+	if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0)
+		return uefi_revocation_list_x509;
+	return NULL;
+}
diff --git a/security/integrity/platform_certs/keyring_handler.h b/security/integrity/platform_certs/keyring_handler.h
new file mode 100644
index 000000000..f92895cc5
--- /dev/null
+++ b/security/integrity/platform_certs/keyring_handler.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef PLATFORM_CERTS_INTERNAL_H
+#define PLATFORM_CERTS_INTERNAL_H
+
+#include <linux/efi.h>
+
+void blacklist_hash(const char *source, const void *data,
+		    size_t len, const char *type,
+		    size_t type_len);
+
+/*
+ * Blacklist an X509 TBS hash.
+ */
+void blacklist_x509_tbs(const char *source, const void *data, size_t len);
+
+/*
+ * Blacklist the hash of an executable.
+ */
+void blacklist_binary(const char *source, const void *data, size_t len);
+
+/*
+ * Return the handler for particular signature list types found in the db.
+ */
+efi_element_handler_t get_handler_for_db(const efi_guid_t *sig_type);
+
+/*
+ * Return the handler for particular signature list types found in the mok.
+ */
+efi_element_handler_t get_handler_for_mok(const efi_guid_t *sig_type);
+
+/*
+ * Return the handler for particular signature list types for CA keys.
+ */
+efi_element_handler_t get_handler_for_ca_keys(const efi_guid_t *sig_type);
+
+/*
+ * Return the handler for particular signature list types for code signing keys.
+ */
+efi_element_handler_t get_handler_for_code_signing_keys(const efi_guid_t *sig_type);
+
+/*
+ * Return the handler for particular signature list types found in the dbx.
+ */
+efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type);
+
+#endif
+
+#ifndef UEFI_QUIRK_SKIP_CERT
+#define UEFI_QUIRK_SKIP_CERT(vendor, product) \
+		 .matches = { \
+			DMI_MATCH(DMI_BOARD_VENDOR, vendor), \
+			DMI_MATCH(DMI_PRODUCT_NAME, product), \
+		},
+#endif
diff --git a/security/integrity/platform_certs/load_ipl_s390.c b/security/integrity/platform_certs/load_ipl_s390.c
new file mode 100644
index 000000000..c7c381a9d
--- /dev/null
+++ b/security/integrity/platform_certs/load_ipl_s390.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include <asm/boot_data.h>
+#include "../integrity.h"
+
+/*
+ * Load the certs contained in the IPL report created by the machine loader
+ * into the platform trusted keyring.
+ */
+static int __init load_ipl_certs(void)
+{
+	void *ptr, *end;
+	unsigned int len;
+
+	if (!ipl_cert_list_addr)
+		return 0;
+	/* Copy the certificates to the platform keyring */
+	ptr = __va(ipl_cert_list_addr);
+	end = ptr + ipl_cert_list_size;
+	while ((void *) ptr < end) {
+		len = *(unsigned int *) ptr;
+		ptr += sizeof(unsigned int);
+		add_to_platform_keyring("IPL:db", ptr, len);
+		ptr += len;
+	}
+	return 0;
+}
+late_initcall(load_ipl_certs);
diff --git a/security/integrity/platform_certs/load_powerpc.c b/security/integrity/platform_certs/load_powerpc.c
new file mode 100644
index 000000000..714c961a0
--- /dev/null
+++ b/security/integrity/platform_certs/load_powerpc.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 IBM Corporation
+ * Author: Nayna Jain
+ *
+ *      - loads keys and hashes stored and controlled by the firmware.
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <asm/secure_boot.h>
+#include <asm/secvar.h>
+#include "keyring_handler.h"
+#include "../integrity.h"
+
+#define extract_esl(db, data, size, offset)	\
+	do { db = data + offset; size = size - offset; } while (0)
+
+/*
+ * Get a certificate list blob from the named secure variable.
+ *
+ * Returns:
+ *  - a pointer to a kmalloc'd buffer containing the cert list on success
+ *  - NULL if the key does not exist
+ *  - an ERR_PTR on error
+ */
+static __init void *get_cert_list(u8 *key, unsigned long keylen, u64 *size)
+{
+	int rc;
+	void *db;
+
+	rc = secvar_ops->get(key, keylen, NULL, size);
+	if (rc) {
+		if (rc == -ENOENT)
+			return NULL;
+		return ERR_PTR(rc);
+	}
+
+	db = kmalloc(*size, GFP_KERNEL);
+	if (!db)
+		return ERR_PTR(-ENOMEM);
+
+	rc = secvar_ops->get(key, keylen, db, size);
+	if (rc) {
+		kfree(db);
+		return ERR_PTR(rc);
+	}
+
+	return db;
+}
+
+/*
+ * Load the certs contained in the keys databases into the platform trusted
+ * keyring and the blacklisted X.509 cert SHA256 hashes into the blacklist
+ * keyring.
+ */
+static int __init load_powerpc_certs(void)
+{
+	void *db = NULL, *dbx = NULL, *data = NULL;
+	void *trustedca;
+	void *moduledb;
+	u64 dsize = 0;
+	u64 offset = 0;
+	int rc = 0;
+	ssize_t len;
+	char buf[32];
+
+	if (!secvar_ops)
+		return -ENODEV;
+
+	len = secvar_ops->format(buf, sizeof(buf));
+	if (len <= 0)
+		return -ENODEV;
+
+	// Check for known secure boot implementations from OPAL or PLPKS
+	if (strcmp("ibm,edk2-compat-v1", buf) && strcmp("ibm,plpks-sb-v1", buf) &&
+	    strcmp("ibm,plpks-sb-v0", buf)) {
+		pr_err("Unsupported secvar implementation \"%s\", not loading certs\n", buf);
+		return -ENODEV;
+	}
+
+	if (strcmp("ibm,plpks-sb-v1", buf) == 0 || strcmp("ibm,plpks-sb-v0", buf) == 0)
+		/* PLPKS authenticated variables ESL data is prefixed with 8 bytes of timestamp */
+		offset = 8;
+
+	/*
+	 * Get db, and dbx. They might not exist, so it isn't an error if we
+	 * can't get them.
+	 */
+	data = get_cert_list("db", 3, &dsize);
+	if (!data) {
+		pr_info("Couldn't get db list from firmware\n");
+	} else if (IS_ERR(data)) {
+		rc = PTR_ERR(data);
+		pr_err("Error reading db from firmware: %d\n", rc);
+		return rc;
+	} else {
+		extract_esl(db, data, dsize, offset);
+
+		rc = parse_efi_signature_list("powerpc:db", db, dsize,
+					      get_handler_for_db);
+		if (rc)
+			pr_err("Couldn't parse db signatures: %d\n", rc);
+		kfree(data);
+	}
+
+	data = get_cert_list("dbx", 4,  &dsize);
+	if (!data) {
+		pr_info("Couldn't get dbx list from firmware\n");
+	} else if (IS_ERR(data)) {
+		rc = PTR_ERR(data);
+		pr_err("Error reading dbx from firmware: %d\n", rc);
+		return rc;
+	} else {
+		extract_esl(dbx, data, dsize, offset);
+
+		rc = parse_efi_signature_list("powerpc:dbx", dbx, dsize,
+					      get_handler_for_dbx);
+		if (rc)
+			pr_err("Couldn't parse dbx signatures: %d\n", rc);
+		kfree(data);
+	}
+
+	data = get_cert_list("trustedcadb", 12,  &dsize);
+	if (!data) {
+		pr_info("Couldn't get trustedcadb list from firmware\n");
+	} else if (IS_ERR(data)) {
+		rc = PTR_ERR(data);
+		pr_err("Error reading trustedcadb from firmware: %d\n", rc);
+	} else {
+		extract_esl(trustedca, data, dsize, offset);
+
+		rc = parse_efi_signature_list("powerpc:trustedca", trustedca, dsize,
+					      get_handler_for_ca_keys);
+		if (rc)
+			pr_err("Couldn't parse trustedcadb signatures: %d\n", rc);
+		kfree(data);
+	}
+
+	data = get_cert_list("moduledb", 9,  &dsize);
+	if (!data) {
+		pr_info("Couldn't get moduledb list from firmware\n");
+	} else if (IS_ERR(data)) {
+		rc = PTR_ERR(data);
+		pr_err("Error reading moduledb from firmware: %d\n", rc);
+	} else {
+		extract_esl(moduledb, data, dsize, offset);
+
+		rc = parse_efi_signature_list("powerpc:moduledb", moduledb, dsize,
+					      get_handler_for_code_signing_keys);
+		if (rc)
+			pr_err("Couldn't parse moduledb signatures: %d\n", rc);
+		kfree(data);
+	}
+
+	return rc;
+}
+late_initcall(load_powerpc_certs);
diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c
new file mode 100644
index 000000000..c0d694844
--- /dev/null
+++ b/security/integrity/platform_certs/load_uefi.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/dmi.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <linux/ima.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include "../integrity.h"
+#include "keyring_handler.h"
+
+/*
+ * On T2 Macs reading the db and dbx efi variables to load UEFI Secure Boot
+ * certificates causes occurrence of a page fault in Apple's firmware and
+ * a crash disabling EFI runtime services. The following quirk skips reading
+ * these variables.
+ */
+static const struct dmi_system_id uefi_skip_cert[] = {
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,2") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,3") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro15,4") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,2") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,3") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookPro16,4") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir8,2") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacBookAir9,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "Macmini8,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "MacPro7,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,1") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMac20,2") },
+	{ UEFI_QUIRK_SKIP_CERT("Apple Inc.", "iMacPro1,1") },
+	{ }
+};
+
+/*
+ * Look to see if a UEFI variable called MokIgnoreDB exists and return true if
+ * it does.
+ *
+ * This UEFI variable is set by the shim if a user tells the shim to not use
+ * the certs/hashes in the UEFI db variable for verification purposes.  If it
+ * is set, we should ignore the db variable also and the true return indicates
+ * this.
+ */
+static __init bool uefi_check_ignore_db(void)
+{
+	efi_status_t status;
+	unsigned int db = 0;
+	unsigned long size = sizeof(db);
+	efi_guid_t guid = EFI_SHIM_LOCK_GUID;
+
+	status = efi.get_variable(L"MokIgnoreDB", &guid, NULL, &size, &db);
+	return status == EFI_SUCCESS;
+}
+
+/*
+ * Get a certificate list blob from the named EFI variable.
+ */
+static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid,
+				  unsigned long *size, efi_status_t *status)
+{
+	unsigned long lsize = 4;
+	unsigned long tmpdb[4];
+	void *db;
+
+	*status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb);
+	if (*status == EFI_NOT_FOUND)
+		return NULL;
+
+	if (*status != EFI_BUFFER_TOO_SMALL) {
+		pr_err("Couldn't get size: 0x%lx\n", *status);
+		return NULL;
+	}
+
+	db = kmalloc(lsize, GFP_KERNEL);
+	if (!db)
+		return NULL;
+
+	*status = efi.get_variable(name, guid, NULL, &lsize, db);
+	if (*status != EFI_SUCCESS) {
+		kfree(db);
+		pr_err("Error reading db var: 0x%lx\n", *status);
+		return NULL;
+	}
+
+	*size = lsize;
+	return db;
+}
+
+/*
+ * load_moklist_certs() - Load MokList certs
+ *
+ * Load the certs contained in the UEFI MokListRT database into the
+ * platform trusted keyring.
+ *
+ * This routine checks the EFI MOK config table first. If and only if
+ * that fails, this routine uses the MokListRT ordinary UEFI variable.
+ *
+ * Return:	Status
+ */
+static int __init load_moklist_certs(void)
+{
+	struct efi_mokvar_table_entry *mokvar_entry;
+	efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
+	void *mok;
+	unsigned long moksize;
+	efi_status_t status;
+	int rc;
+
+	/* First try to load certs from the EFI MOKvar config table.
+	 * It's not an error if the MOKvar config table doesn't exist
+	 * or the MokListRT entry is not found in it.
+	 */
+	mokvar_entry = efi_mokvar_entry_find("MokListRT");
+	if (mokvar_entry) {
+		rc = parse_efi_signature_list("UEFI:MokListRT (MOKvar table)",
+					      mokvar_entry->data,
+					      mokvar_entry->data_size,
+					      get_handler_for_mok);
+		/* All done if that worked. */
+		if (!rc)
+			return rc;
+
+		pr_err("Couldn't parse MokListRT signatures from EFI MOKvar config table: %d\n",
+		       rc);
+	}
+
+	/* Get MokListRT. It might not exist, so it isn't an error
+	 * if we can't get it.
+	 */
+	mok = get_cert_list(L"MokListRT", &mok_var, &moksize, &status);
+	if (mok) {
+		rc = parse_efi_signature_list("UEFI:MokListRT",
+					      mok, moksize, get_handler_for_mok);
+		kfree(mok);
+		if (rc)
+			pr_err("Couldn't parse MokListRT signatures: %d\n", rc);
+		return rc;
+	}
+	if (status == EFI_NOT_FOUND)
+		pr_debug("MokListRT variable wasn't found\n");
+	else
+		pr_info("Couldn't get UEFI MokListRT\n");
+	return 0;
+}
+
+/*
+ * load_uefi_certs() - Load certs from UEFI sources
+ *
+ * Load the certs contained in the UEFI databases into the platform trusted
+ * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist
+ * keyring.
+ */
+static int __init load_uefi_certs(void)
+{
+	efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID;
+	efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
+	void *db = NULL, *dbx = NULL, *mokx = NULL;
+	unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0;
+	efi_status_t status;
+	int rc = 0;
+	const struct dmi_system_id *dmi_id;
+
+	dmi_id = dmi_first_match(uefi_skip_cert);
+	if (dmi_id) {
+		pr_err("Reading UEFI Secure Boot Certs is not supported on T2 Macs.\n");
+		return false;
+	}
+
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
+		return false;
+
+	/* Get db and dbx.  They might not exist, so it isn't an error
+	 * if we can't get them.
+	 */
+	if (!uefi_check_ignore_db()) {
+		db = get_cert_list(L"db", &secure_var, &dbsize, &status);
+		if (!db) {
+			if (status == EFI_NOT_FOUND)
+				pr_debug("MODSIGN: db variable wasn't found\n");
+			else
+				pr_err("MODSIGN: Couldn't get UEFI db list\n");
+		} else {
+			rc = parse_efi_signature_list("UEFI:db",
+					db, dbsize, get_handler_for_db);
+			if (rc)
+				pr_err("Couldn't parse db signatures: %d\n",
+				       rc);
+			kfree(db);
+		}
+	}
+
+	dbx = get_cert_list(L"dbx", &secure_var, &dbxsize, &status);
+	if (!dbx) {
+		if (status == EFI_NOT_FOUND)
+			pr_debug("dbx variable wasn't found\n");
+		else
+			pr_info("Couldn't get UEFI dbx list\n");
+	} else {
+		rc = parse_efi_signature_list("UEFI:dbx",
+					      dbx, dbxsize,
+					      get_handler_for_dbx);
+		if (rc)
+			pr_err("Couldn't parse dbx signatures: %d\n", rc);
+		kfree(dbx);
+	}
+
+	/* the MOK/MOKx can not be trusted when secure boot is disabled */
+	if (!arch_get_secureboot())
+		return 0;
+
+	mokx = get_cert_list(L"MokListXRT", &mok_var, &mokxsize, &status);
+	if (!mokx) {
+		if (status == EFI_NOT_FOUND)
+			pr_debug("mokx variable wasn't found\n");
+		else
+			pr_info("Couldn't get mokx list\n");
+	} else {
+		rc = parse_efi_signature_list("UEFI:MokListXRT",
+					      mokx, mokxsize,
+					      get_handler_for_dbx);
+		if (rc)
+			pr_err("Couldn't parse mokx signatures %d\n", rc);
+		kfree(mokx);
+	}
+
+	/* Load the MokListRT certs */
+	rc = load_moklist_certs();
+
+	return rc;
+}
+late_initcall(load_uefi_certs);
diff --git a/security/integrity/platform_certs/machine_keyring.c b/security/integrity/platform_certs/machine_keyring.c
new file mode 100644
index 000000000..a401640a6
--- /dev/null
+++ b/security/integrity/platform_certs/machine_keyring.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Machine keyring routines.
+ *
+ * Copyright (c) 2021, Oracle and/or its affiliates.
+ */
+
+#include <linux/efi.h>
+#include "../integrity.h"
+
+static __init int machine_keyring_init(void)
+{
+	int rc;
+
+	rc = integrity_init_keyring(INTEGRITY_KEYRING_MACHINE);
+	if (rc)
+		return rc;
+
+	pr_notice("Machine keyring initialized\n");
+	return 0;
+}
+device_initcall(machine_keyring_init);
+
+void __init add_to_machine_keyring(const char *source, const void *data, size_t len)
+{
+	key_perm_t perm;
+	int rc;
+
+	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW;
+	rc = integrity_load_cert(INTEGRITY_KEYRING_MACHINE, source, data, len, perm);
+
+	/*
+	 * Some MOKList keys may not pass the machine keyring restrictions.
+	 * If the restriction check does not pass and the platform keyring
+	 * is configured, try to add it into that keyring instead.
+	 */
+	if (rc && efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING))
+		rc = integrity_load_cert(INTEGRITY_KEYRING_PLATFORM, source,
+					 data, len, perm);
+
+	if (rc)
+		pr_info("Error adding keys to machine keyring %s\n", source);
+}
+
+/*
+ * Try to load the MokListTrustedRT MOK variable to see if we should trust
+ * the MOK keys within the kernel. It is not an error if this variable
+ * does not exist.  If it does not exist, MOK keys should not be trusted
+ * within the machine keyring.
+ */
+static __init bool uefi_check_trust_mok_keys(void)
+{
+	struct efi_mokvar_table_entry *mokvar_entry;
+
+	mokvar_entry = efi_mokvar_entry_find("MokListTrustedRT");
+
+	if (mokvar_entry)
+		return true;
+
+	return false;
+}
+
+static bool __init trust_moklist(void)
+{
+	static bool initialized;
+	static bool trust_mok;
+
+	if (!initialized) {
+		initialized = true;
+		trust_mok = false;
+
+		if (uefi_check_trust_mok_keys())
+			trust_mok = true;
+	}
+
+	return trust_mok;
+}
+
+/*
+ * Provides platform specific check for trusting imputed keys before loading
+ * on .machine keyring. UEFI systems enable this trust based on a variable,
+ * and for other platforms, it is always enabled.
+ */
+bool __init imputed_trust_enabled(void)
+{
+	if (efi_enabled(EFI_BOOT))
+		return trust_moklist();
+
+	return true;
+}
diff --git a/security/integrity/platform_certs/platform_keyring.c b/security/integrity/platform_certs/platform_keyring.c
new file mode 100644
index 000000000..bcafd7387
--- /dev/null
+++ b/security/integrity/platform_certs/platform_keyring.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Platform keyring for firmware/platform keys
+ *
+ * Copyright IBM Corporation, 2018
+ * Author(s): Nayna Jain <nayna@linux.ibm.com>
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include "../integrity.h"
+
+/**
+ * add_to_platform_keyring - Add to platform keyring without validation.
+ * @source: Source of key
+ * @data: The blob holding the key
+ * @len: The length of the data blob
+ *
+ * Add a key to the platform keyring without checking its trust chain.  This
+ * is available only during kernel initialisation.
+ */
+void __init add_to_platform_keyring(const char *source, const void *data,
+				    size_t len)
+{
+	key_perm_t perm;
+	int rc;
+
+	perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW;
+
+	rc = integrity_load_cert(INTEGRITY_KEYRING_PLATFORM, source, data, len,
+				 perm);
+	if (rc)
+		pr_info("Error adding keys to platform keyring %s\n", source);
+}
+
+/*
+ * Create the trusted keyrings.
+ */
+static __init int platform_keyring_init(void)
+{
+	int rc;
+
+	rc = integrity_init_keyring(INTEGRITY_KEYRING_PLATFORM);
+	if (rc)
+		return rc;
+
+	pr_notice("Platform Keyring initialized\n");
+	return 0;
+}
+
+/*
+ * Must be initialised before we try and load the keys into the keyring.
+ */
+device_initcall(platform_keyring_init);
diff --git a/security/ipe/.gitignore b/security/ipe/.gitignore
new file mode 100644
index 000000000..6e9939be1
--- /dev/null
+++ b/security/ipe/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+boot_policy.c
diff --git a/security/ipe/Kconfig b/security/ipe/Kconfig
new file mode 100644
index 000000000..a110a6cd8
--- /dev/null
+++ b/security/ipe/Kconfig
@@ -0,0 +1,117 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Integrity Policy Enforcement (IPE) configuration
+#
+
+menuconfig SECURITY_IPE
+	bool "Integrity Policy Enforcement (IPE)"
+	depends on SECURITY && SECURITYFS && AUDIT && AUDITSYSCALL
+	select CRYPTO_LIB_SHA256
+	select PKCS7_MESSAGE_PARSER
+	select SYSTEM_DATA_VERIFICATION
+	select IPE_PROP_DM_VERITY if DM_VERITY
+	select IPE_PROP_DM_VERITY_SIGNATURE if DM_VERITY && DM_VERITY_VERIFY_ROOTHASH_SIG
+	select IPE_PROP_FS_VERITY if FS_VERITY
+	select IPE_PROP_FS_VERITY_BUILTIN_SIG if FS_VERITY && FS_VERITY_BUILTIN_SIGNATURES
+	help
+	  This option enables the Integrity Policy Enforcement LSM
+	  allowing users to define a policy to enforce a trust-based access
+	  control. A key feature of IPE is a customizable policy to allow
+	  admins to reconfigure trust requirements on the fly.
+
+	  If unsure, answer N.
+
+if SECURITY_IPE
+config IPE_BOOT_POLICY
+	string "Integrity policy to apply on system startup"
+	help
+	  This option specifies a filepath to an IPE policy that is compiled
+	  into the kernel. This policy will be enforced until a policy update
+	  is deployed via the $securityfs/ipe/policies/$policy_name/active
+	  interface.
+
+	  If unsure, leave blank.
+
+config IPE_POLICY_SIG_SECONDARY_KEYRING
+	bool "IPE policy update verification with secondary keyring"
+	default y
+	depends on SECONDARY_TRUSTED_KEYRING
+	help
+	  Also allow the secondary trusted keyring to verify IPE policy
+	  updates.
+
+	  If unsure, answer Y.
+
+config IPE_POLICY_SIG_PLATFORM_KEYRING
+	bool "IPE policy update verification with platform keyring"
+	default y
+	depends on INTEGRITY_PLATFORM_KEYRING
+	help
+	  Also allow the platform keyring to verify IPE policy updates.
+
+	  If unsure, answer Y.
+
+menu "IPE Trust Providers"
+
+config IPE_PROP_DM_VERITY
+	bool "Enable support for dm-verity based on root hash"
+	depends on DM_VERITY
+	help
+	  This option enables the 'dmverity_roothash' property within IPE
+	  policies. The property evaluates to TRUE when a file from a dm-verity
+	  volume is evaluated, and the volume's root hash matches the value
+	  supplied in the policy.
+
+config IPE_PROP_DM_VERITY_SIGNATURE
+	bool "Enable support for dm-verity based on root hash signature"
+	depends on DM_VERITY && DM_VERITY_VERIFY_ROOTHASH_SIG
+	help
+	  This option enables the 'dmverity_signature' property within IPE
+	  policies. The property evaluates to TRUE when a file from a dm-verity
+	  volume, which has been mounted with a valid signed root hash,
+	  is evaluated.
+
+	  If unsure, answer Y.
+
+config IPE_PROP_FS_VERITY
+	bool "Enable support for fs-verity based on file digest"
+	depends on FS_VERITY
+	help
+	  This option enables the 'fsverity_digest' property within IPE
+	  policies. The property evaluates to TRUE when a file is fsverity
+	  enabled and its digest matches the supplied digest value in the
+	  policy.
+
+	  if unsure, answer Y.
+
+config IPE_PROP_FS_VERITY_BUILTIN_SIG
+	bool "Enable support for fs-verity based on builtin signature"
+	depends on FS_VERITY && FS_VERITY_BUILTIN_SIGNATURES
+	help
+	  This option enables the 'fsverity_signature' property within IPE
+	  policies. The property evaluates to TRUE when a file is fsverity
+	  enabled and it has a valid builtin signature whose signing cert
+	  is in the .fs-verity keyring.
+
+	  if unsure, answer Y.
+
+endmenu
+
+config SECURITY_IPE_KUNIT_TEST
+	bool "Build KUnit tests for IPE" if !KUNIT_ALL_TESTS
+	depends on KUNIT=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the IPE KUnit tests.
+
+	  KUnit tests run during boot and output the results to the debug log
+	  in TAP format (https://testanything.org/). Only useful for kernel devs
+	  running KUnit test harness and are not for inclusion into a
+	  production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
+endif
diff --git a/security/ipe/Makefile b/security/ipe/Makefile
new file mode 100644
index 000000000..2ffabfa63
--- /dev/null
+++ b/security/ipe/Makefile
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+#
+# Makefile for building the IPE module as part of the kernel tree.
+#
+
+quiet_cmd_polgen = IPE_POL $(2)
+      cmd_polgen = scripts/ipe/polgen/polgen security/ipe/boot_policy.c $(2)
+
+targets += boot_policy.c
+
+$(obj)/boot_policy.c: scripts/ipe/polgen/polgen $(CONFIG_IPE_BOOT_POLICY) FORCE
+	$(call if_changed,polgen,$(CONFIG_IPE_BOOT_POLICY))
+
+obj-$(CONFIG_SECURITY_IPE) += \
+	boot_policy.o \
+	digest.o \
+	eval.o \
+	hooks.o \
+	fs.o \
+	ipe.o \
+	policy.o \
+	policy_fs.o \
+	policy_parser.o \
+	audit.o \
+
+clean-files := boot_policy.c \
+
+obj-$(CONFIG_SECURITY_IPE_KUNIT_TEST) += \
+	policy_tests.o \
diff --git a/security/ipe/audit.c b/security/ipe/audit.c
new file mode 100644
index 000000000..93fb59fbd
--- /dev/null
+++ b/security/ipe/audit.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/slab.h>
+#include <linux/audit.h>
+#include <linux/types.h>
+#include <crypto/sha2.h>
+
+#include "ipe.h"
+#include "eval.h"
+#include "hooks.h"
+#include "policy.h"
+#include "audit.h"
+#include "digest.h"
+
+#define ACTSTR(x) ((x) == IPE_ACTION_ALLOW ? "ALLOW" : "DENY")
+
+#define IPE_AUDIT_HASH_ALG "sha256" /* keep in sync with audit_policy() */
+
+#define AUDIT_POLICY_LOAD_FMT "policy_name=\"%s\" policy_version=%hu.%hu.%hu "\
+			      "policy_digest=" IPE_AUDIT_HASH_ALG ":"
+#define AUDIT_POLICY_LOAD_NULL_FMT "policy_name=? policy_version=? "\
+				   "policy_digest=?"
+#define AUDIT_OLD_ACTIVE_POLICY_FMT "old_active_pol_name=\"%s\" "\
+				    "old_active_pol_version=%hu.%hu.%hu "\
+				    "old_policy_digest=" IPE_AUDIT_HASH_ALG ":"
+#define AUDIT_OLD_ACTIVE_POLICY_NULL_FMT "old_active_pol_name=? "\
+					 "old_active_pol_version=? "\
+					 "old_policy_digest=?"
+#define AUDIT_NEW_ACTIVE_POLICY_FMT "new_active_pol_name=\"%s\" "\
+				    "new_active_pol_version=%hu.%hu.%hu "\
+				    "new_policy_digest=" IPE_AUDIT_HASH_ALG ":"
+
+static const char *const audit_op_names[__IPE_OP_MAX + 1] = {
+	"EXECUTE",
+	"FIRMWARE",
+	"KMODULE",
+	"KEXEC_IMAGE",
+	"KEXEC_INITRAMFS",
+	"POLICY",
+	"X509_CERT",
+	"UNKNOWN",
+};
+
+static const char *const audit_hook_names[__IPE_HOOK_MAX] = {
+	"BPRM_CHECK",
+	"BPRM_CREDS_FOR_EXEC",
+	"MMAP",
+	"MPROTECT",
+	"KERNEL_READ",
+	"KERNEL_LOAD",
+};
+
+static const char *const audit_prop_names[__IPE_PROP_MAX] = {
+	"boot_verified=FALSE",
+	"boot_verified=TRUE",
+	"dmverity_roothash=",
+	"dmverity_signature=FALSE",
+	"dmverity_signature=TRUE",
+	"fsverity_digest=",
+	"fsverity_signature=FALSE",
+	"fsverity_signature=TRUE",
+};
+
+/**
+ * audit_dmv_roothash() - audit the roothash of a dmverity_roothash property.
+ * @ab: Supplies a pointer to the audit_buffer to append to.
+ * @rh: Supplies a pointer to the digest structure.
+ */
+static void audit_dmv_roothash(struct audit_buffer *ab, const void *rh)
+{
+	audit_log_format(ab, "%s", audit_prop_names[IPE_PROP_DMV_ROOTHASH]);
+	ipe_digest_audit(ab, rh);
+}
+
+/**
+ * audit_fsv_digest() - audit the digest of a fsverity_digest property.
+ * @ab: Supplies a pointer to the audit_buffer to append to.
+ * @d: Supplies a pointer to the digest structure.
+ */
+static void audit_fsv_digest(struct audit_buffer *ab, const void *d)
+{
+	audit_log_format(ab, "%s", audit_prop_names[IPE_PROP_FSV_DIGEST]);
+	ipe_digest_audit(ab, d);
+}
+
+/**
+ * audit_rule() - audit an IPE policy rule.
+ * @ab: Supplies a pointer to the audit_buffer to append to.
+ * @r: Supplies a pointer to the ipe_rule to approximate a string form for.
+ */
+static void audit_rule(struct audit_buffer *ab, const struct ipe_rule *r)
+{
+	const struct ipe_prop *ptr;
+
+	audit_log_format(ab, " rule=\"op=%s ", audit_op_names[r->op]);
+
+	list_for_each_entry(ptr, &r->props, next) {
+		switch (ptr->type) {
+		case IPE_PROP_DMV_ROOTHASH:
+			audit_dmv_roothash(ab, ptr->value);
+			break;
+		case IPE_PROP_FSV_DIGEST:
+			audit_fsv_digest(ab, ptr->value);
+			break;
+		default:
+			audit_log_format(ab, "%s", audit_prop_names[ptr->type]);
+			break;
+		}
+
+		audit_log_format(ab, " ");
+	}
+
+	audit_log_format(ab, "action=%s\"", ACTSTR(r->action));
+}
+
+/**
+ * ipe_audit_match() - Audit a rule match in a policy evaluation.
+ * @ctx: Supplies a pointer to the evaluation context that was used in the
+ *	 evaluation.
+ * @match_type: Supplies the scope of the match: rule, operation default,
+ *		global default.
+ * @act: Supplies the IPE's evaluation decision, deny or allow.
+ * @r: Supplies a pointer to the rule that was matched, if possible.
+ */
+void ipe_audit_match(const struct ipe_eval_ctx *const ctx,
+		     enum ipe_match match_type,
+		     enum ipe_action_type act, const struct ipe_rule *const r)
+{
+	const char *op = audit_op_names[ctx->op];
+	char comm[sizeof(current->comm)];
+	struct audit_buffer *ab;
+	struct inode *inode;
+
+	if (act != IPE_ACTION_DENY && !READ_ONCE(success_audit))
+		return;
+
+	ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN,
+			     AUDIT_IPE_ACCESS);
+	if (!ab)
+		return;
+
+	audit_log_format(ab, "ipe_op=%s ipe_hook=%s enforcing=%d pid=%d comm=",
+			 op, audit_hook_names[ctx->hook], READ_ONCE(enforce),
+			 task_tgid_nr(current));
+	audit_log_untrustedstring(ab, get_task_comm(comm, current));
+
+	if (ctx->file) {
+		audit_log_d_path(ab, " path=", &ctx->file->f_path);
+		inode = file_inode(ctx->file);
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%llu", inode->i_ino);
+		} else {
+			audit_log_format(ab, " dev=? ino=?");
+		}
+	} else {
+		audit_log_format(ab, " path=? dev=? ino=?");
+	}
+
+	if (match_type == IPE_MATCH_RULE)
+		audit_rule(ab, r);
+	else if (match_type == IPE_MATCH_TABLE)
+		audit_log_format(ab, " rule=\"DEFAULT op=%s action=%s\"", op,
+				 ACTSTR(act));
+	else
+		audit_log_format(ab, " rule=\"DEFAULT action=%s\"",
+				 ACTSTR(act));
+
+	audit_log_end(ab);
+}
+
+/**
+ * audit_policy() - Audit a policy's name, version and thumbprint to @ab.
+ * @ab: Supplies a pointer to the audit buffer to append to.
+ * @audit_format: Supplies a pointer to the audit format string
+ * @p: Supplies a pointer to the policy to audit.
+ */
+static void audit_policy(struct audit_buffer *ab,
+			 const char *audit_format,
+			 const struct ipe_policy *const p)
+{
+	u8 digest[SHA256_DIGEST_SIZE];
+
+	sha256(p->pkcs7, p->pkcs7len, digest);
+
+	audit_log_format(ab, audit_format, p->parsed->name,
+			 p->parsed->version.major, p->parsed->version.minor,
+			 p->parsed->version.rev);
+	audit_log_n_hex(ab, digest, sizeof(digest));
+}
+
+/**
+ * ipe_audit_policy_activation() - Audit a policy being activated.
+ * @op: Supplies a pointer to the previously activated policy to audit.
+ * @np: Supplies a pointer to the newly activated policy to audit.
+ */
+void ipe_audit_policy_activation(const struct ipe_policy *const op,
+				 const struct ipe_policy *const np)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL,
+			     AUDIT_IPE_CONFIG_CHANGE);
+	if (!ab)
+		return;
+
+	if (op) {
+		audit_policy(ab, AUDIT_OLD_ACTIVE_POLICY_FMT, op);
+		audit_log_format(ab, " ");
+	} else {
+		/*
+		 * old active policy can be NULL if there is no kernel
+		 * built-in policy
+		 */
+		audit_log_format(ab, AUDIT_OLD_ACTIVE_POLICY_NULL_FMT);
+		audit_log_format(ab, " ");
+	}
+	audit_policy(ab, AUDIT_NEW_ACTIVE_POLICY_FMT, np);
+	audit_log_format(ab, " auid=%u ses=%u lsm=ipe res=1",
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current));
+
+	audit_log_end(ab);
+}
+
+/**
+ * ipe_audit_policy_load() - Audit a policy loading event.
+ * @p: Supplies a pointer to the policy to audit or an error pointer.
+ */
+void ipe_audit_policy_load(const struct ipe_policy *const p)
+{
+	struct audit_buffer *ab;
+	int err = 0;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL,
+			     AUDIT_IPE_POLICY_LOAD);
+	if (!ab)
+		return;
+
+	if (!IS_ERR(p)) {
+		audit_policy(ab, AUDIT_POLICY_LOAD_FMT, p);
+	} else {
+		audit_log_format(ab, AUDIT_POLICY_LOAD_NULL_FMT);
+		err = PTR_ERR(p);
+	}
+
+	audit_log_format(ab, " auid=%u ses=%u lsm=ipe res=%d errno=%d",
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current), !err, err);
+
+	audit_log_end(ab);
+}
+
+/**
+ * ipe_audit_enforce() - Audit a change in IPE's enforcement state.
+ * @new_enforce: The new value enforce to be set.
+ * @old_enforce: The old value currently in enforce.
+ */
+void ipe_audit_enforce(bool new_enforce, bool old_enforce)
+{
+	struct audit_buffer *ab;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS);
+	if (!ab)
+		return;
+
+	audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS,
+		  "enforcing=%d old_enforcing=%d auid=%u ses=%u"
+		  " enabled=1 old-enabled=1 lsm=ipe res=1",
+		  new_enforce, old_enforce,
+		  from_kuid(&init_user_ns, audit_get_loginuid(current)),
+		  audit_get_sessionid(current));
+
+	audit_log_end(ab);
+}
diff --git a/security/ipe/audit.h b/security/ipe/audit.h
new file mode 100644
index 000000000..ed2620846
--- /dev/null
+++ b/security/ipe/audit.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _IPE_AUDIT_H
+#define _IPE_AUDIT_H
+
+#include "policy.h"
+
+void ipe_audit_match(const struct ipe_eval_ctx *const ctx,
+		     enum ipe_match match_type,
+		     enum ipe_action_type act, const struct ipe_rule *const r);
+void ipe_audit_policy_load(const struct ipe_policy *const p);
+void ipe_audit_policy_activation(const struct ipe_policy *const op,
+				 const struct ipe_policy *const np);
+void ipe_audit_enforce(bool new_enforce, bool old_enforce);
+
+#endif /* _IPE_AUDIT_H */
diff --git a/security/ipe/digest.c b/security/ipe/digest.c
new file mode 100644
index 000000000..6e597a6b7
--- /dev/null
+++ b/security/ipe/digest.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/hex.h>
+#include "digest.h"
+
+/**
+ * ipe_digest_parse() - parse a digest in IPE's policy.
+ * @valstr: Supplies the string parsed from the policy.
+ *
+ * Digests in IPE are defined in a standard way:
+ *	<alg_name>:<hex>
+ *
+ * Use this function to create a property to parse the digest
+ * consistently. The parsed digest will be saved in @value in IPE's
+ * policy.
+ *
+ * Return: The parsed digest_info structure on success. If an error occurs,
+ * the function will return the error value (via ERR_PTR).
+ */
+struct digest_info *ipe_digest_parse(const char *valstr)
+{
+	struct digest_info *info = NULL;
+	char *sep, *raw_digest;
+	size_t raw_digest_len;
+	u8 *digest = NULL;
+	char *alg = NULL;
+	int rc = 0;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	sep = strchr(valstr, ':');
+	if (!sep) {
+		rc = -EBADMSG;
+		goto err;
+	}
+
+	alg = kstrndup(valstr, sep - valstr, GFP_KERNEL);
+	if (!alg) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	raw_digest = sep + 1;
+	raw_digest_len = strlen(raw_digest);
+
+	info->digest_len = (raw_digest_len + 1) / 2;
+	digest = kzalloc(info->digest_len, GFP_KERNEL);
+	if (!digest) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	rc = hex2bin(digest, raw_digest, info->digest_len);
+	if (rc < 0) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	info->alg = alg;
+	info->digest = digest;
+	return info;
+
+err:
+	kfree(alg);
+	kfree(digest);
+	kfree(info);
+	return ERR_PTR(rc);
+}
+
+/**
+ * ipe_digest_eval() - evaluate an IPE digest against another digest.
+ * @expected: Supplies the policy-provided digest value.
+ * @digest: Supplies the digest to compare against the policy digest value.
+ *
+ * Return:
+ * * %true	- digests match
+ * * %false	- digests do not match
+ */
+bool ipe_digest_eval(const struct digest_info *expected,
+		     const struct digest_info *digest)
+{
+	return (expected->digest_len == digest->digest_len) &&
+	       (!strcmp(expected->alg, digest->alg)) &&
+	       (!memcmp(expected->digest, digest->digest, expected->digest_len));
+}
+
+/**
+ * ipe_digest_free() - free an IPE digest.
+ * @info: Supplies a pointer the policy-provided digest to free.
+ */
+void ipe_digest_free(struct digest_info *info)
+{
+	if (IS_ERR_OR_NULL(info))
+		return;
+
+	kfree(info->alg);
+	kfree(info->digest);
+	kfree(info);
+}
+
+/**
+ * ipe_digest_audit() - audit a digest that was sourced from IPE's policy.
+ * @ab: Supplies the audit_buffer to append the formatted result.
+ * @info: Supplies a pointer to source the audit record from.
+ *
+ * Digests in IPE are audited in this format:
+ *	<alg_name>:<hex>
+ */
+void ipe_digest_audit(struct audit_buffer *ab, const struct digest_info *info)
+{
+	audit_log_untrustedstring(ab, info->alg);
+	audit_log_format(ab, ":");
+	audit_log_n_hex(ab, info->digest, info->digest_len);
+}
diff --git a/security/ipe/digest.h b/security/ipe/digest.h
new file mode 100644
index 000000000..52c9b3844
--- /dev/null
+++ b/security/ipe/digest.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _IPE_DIGEST_H
+#define _IPE_DIGEST_H
+
+#include <linux/types.h>
+#include <linux/audit.h>
+
+#include "policy.h"
+
+struct digest_info {
+	const char *alg;
+	const u8 *digest;
+	size_t digest_len;
+};
+
+struct digest_info *ipe_digest_parse(const char *valstr);
+void ipe_digest_free(struct digest_info *digest_info);
+void ipe_digest_audit(struct audit_buffer *ab, const struct digest_info *val);
+bool ipe_digest_eval(const struct digest_info *expected,
+		     const struct digest_info *digest);
+
+#endif /* _IPE_DIGEST_H */
diff --git a/security/ipe/eval.c b/security/ipe/eval.c
new file mode 100644
index 000000000..21439c5be
--- /dev/null
+++ b/security/ipe/eval.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/sched.h>
+#include <linux/rcupdate.h>
+#include <linux/moduleparam.h>
+#include <linux/fsverity.h>
+
+#include "ipe.h"
+#include "eval.h"
+#include "policy.h"
+#include "audit.h"
+#include "digest.h"
+
+struct ipe_policy __rcu *ipe_active_policy;
+bool success_audit;
+bool enforce = true;
+#define INO_BLOCK_DEV(ino) ((ino)->i_sb->s_bdev)
+
+#define FILE_SUPERBLOCK(f) ((f)->f_path.mnt->mnt_sb)
+
+/**
+ * build_ipe_sb_ctx() - Build initramfs field of an ipe evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @file: Supplies the file struct of the file triggered IPE event.
+ */
+static void build_ipe_sb_ctx(struct ipe_eval_ctx *ctx, const struct file *const file)
+{
+	ctx->initramfs = ipe_sb(FILE_SUPERBLOCK(file))->initramfs;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * build_ipe_bdev_ctx() - Build ipe_bdev field of an evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @ino: Supplies the inode struct of the file triggered IPE event.
+ */
+static void build_ipe_bdev_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+	if (INO_BLOCK_DEV(ino))
+		ctx->ipe_bdev = ipe_bdev(INO_BLOCK_DEV(ino));
+}
+#else
+static void build_ipe_bdev_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+static void build_ipe_inode_blob_ctx(struct ipe_eval_ctx *ctx,
+				     const struct inode *const ino)
+{
+	ctx->ipe_inode = ipe_inode(ctx->ino);
+}
+#else
+static inline void build_ipe_inode_blob_ctx(struct ipe_eval_ctx *ctx,
+					    const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+/**
+ * build_ipe_inode_ctx() - Build inode fields of an evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @ino: Supplies the inode struct of the file triggered IPE event.
+ */
+static void build_ipe_inode_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+	ctx->ino = ino;
+	build_ipe_inode_blob_ctx(ctx, ino);
+}
+#else
+static void build_ipe_inode_ctx(struct ipe_eval_ctx *ctx, const struct inode *const ino)
+{
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY */
+
+/**
+ * ipe_build_eval_ctx() - Build an ipe evaluation context.
+ * @ctx: Supplies a pointer to the context to be populated.
+ * @file: Supplies a pointer to the file to associated with the evaluation.
+ * @op: Supplies the IPE policy operation associated with the evaluation.
+ * @hook: Supplies the LSM hook associated with the evaluation.
+ */
+void ipe_build_eval_ctx(struct ipe_eval_ctx *ctx,
+			const struct file *file,
+			enum ipe_op_type op,
+			enum ipe_hook_type hook)
+{
+	struct inode *ino;
+
+	ctx->file = file;
+	ctx->op = op;
+	ctx->hook = hook;
+
+	if (file) {
+		build_ipe_sb_ctx(ctx, file);
+		ino = d_real_inode(file->f_path.dentry);
+		build_ipe_bdev_ctx(ctx, ino);
+		build_ipe_inode_ctx(ctx, ino);
+	}
+}
+
+/**
+ * evaluate_boot_verified() - Evaluate @ctx for the boot verified property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_boot_verified(const struct ipe_eval_ctx *const ctx)
+{
+	return ctx->initramfs;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * evaluate_dmv_roothash() - Evaluate @ctx against a dmv roothash property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @p: Supplies a pointer to the property being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_dmv_roothash(const struct ipe_eval_ctx *const ctx,
+				  struct ipe_prop *p)
+{
+	return !!ctx->ipe_bdev &&
+	       !!ctx->ipe_bdev->root_hash &&
+	       ipe_digest_eval(p->value,
+			       ctx->ipe_bdev->root_hash);
+}
+#else
+static bool evaluate_dmv_roothash(const struct ipe_eval_ctx *const ctx,
+				  struct ipe_prop *p)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY_SIGNATURE
+/**
+ * evaluate_dmv_sig_false() - Evaluate @ctx against a dmv sig false property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_dmv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return !ctx->ipe_bdev || (!ctx->ipe_bdev->dm_verity_signed);
+}
+
+/**
+ * evaluate_dmv_sig_true() - Evaluate @ctx against a dmv sig true property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_dmv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return !evaluate_dmv_sig_false(ctx);
+}
+#else
+static bool evaluate_dmv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+
+static bool evaluate_dmv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY_SIGNATURE */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY
+/**
+ * evaluate_fsv_digest() - Evaluate @ctx against a fsv digest property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ * @p: Supplies a pointer to the property being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_fsv_digest(const struct ipe_eval_ctx *const ctx,
+				struct ipe_prop *p)
+{
+	enum hash_algo alg;
+	u8 digest[FS_VERITY_MAX_DIGEST_SIZE];
+	struct digest_info info;
+
+	if (!ctx->ino)
+		return false;
+	if (!fsverity_get_digest((struct inode *)ctx->ino,
+				 digest,
+				 NULL,
+				 &alg))
+		return false;
+
+	info.alg = hash_algo_name[alg];
+	info.digest = digest;
+	info.digest_len = hash_digest_size[alg];
+
+	return ipe_digest_eval(p->value, &info);
+}
+#else
+static bool evaluate_fsv_digest(const struct ipe_eval_ctx *const ctx,
+				struct ipe_prop *p)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+/**
+ * evaluate_fsv_sig_false() - Evaluate @ctx against a fsv sig false property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true	- The current @ctx match the property
+ * * %false	- The current @ctx doesn't match the property
+ */
+static bool evaluate_fsv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return !ctx->ino ||
+	       !IS_VERITY(ctx->ino) ||
+	       !ctx->ipe_inode ||
+	       !ctx->ipe_inode->fs_verity_signed;
+}
+
+/**
+ * evaluate_fsv_sig_true() - Evaluate @ctx against a fsv sig true property.
+ * @ctx: Supplies a pointer to the context being evaluated.
+ *
+ * Return:
+ * * %true - The current @ctx match the property
+ * * %false - The current @ctx doesn't match the property
+ */
+static bool evaluate_fsv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return !evaluate_fsv_sig_false(ctx);
+}
+#else
+static bool evaluate_fsv_sig_false(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+
+static bool evaluate_fsv_sig_true(const struct ipe_eval_ctx *const ctx)
+{
+	return false;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+/**
+ * evaluate_property() - Analyze @ctx against a rule property.
+ * @ctx: Supplies a pointer to the context to be evaluated.
+ * @p: Supplies a pointer to the property to be evaluated.
+ *
+ * This function Determines whether the specified @ctx
+ * matches the conditions defined by a rule property @p.
+ *
+ * Return:
+ * * %true	- The current @ctx match the @p
+ * * %false	- The current @ctx doesn't match the @p
+ */
+static bool evaluate_property(const struct ipe_eval_ctx *const ctx,
+			      struct ipe_prop *p)
+{
+	switch (p->type) {
+	case IPE_PROP_BOOT_VERIFIED_FALSE:
+		return !evaluate_boot_verified(ctx);
+	case IPE_PROP_BOOT_VERIFIED_TRUE:
+		return evaluate_boot_verified(ctx);
+	case IPE_PROP_DMV_ROOTHASH:
+		return evaluate_dmv_roothash(ctx, p);
+	case IPE_PROP_DMV_SIG_FALSE:
+		return evaluate_dmv_sig_false(ctx);
+	case IPE_PROP_DMV_SIG_TRUE:
+		return evaluate_dmv_sig_true(ctx);
+	case IPE_PROP_FSV_DIGEST:
+		return evaluate_fsv_digest(ctx, p);
+	case IPE_PROP_FSV_SIG_FALSE:
+		return evaluate_fsv_sig_false(ctx);
+	case IPE_PROP_FSV_SIG_TRUE:
+		return evaluate_fsv_sig_true(ctx);
+	default:
+		return false;
+	}
+}
+
+/**
+ * ipe_evaluate_event() - Analyze @ctx against the current active policy.
+ * @ctx: Supplies a pointer to the context to be evaluated.
+ *
+ * This is the loop where all policy evaluations happen against the IPE policy.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- @ctx did not pass evaluation
+ */
+int ipe_evaluate_event(const struct ipe_eval_ctx *const ctx)
+{
+	const struct ipe_op_table *rules = NULL;
+	const struct ipe_rule *rule = NULL;
+	struct ipe_policy *pol = NULL;
+	struct ipe_prop *prop = NULL;
+	enum ipe_action_type action;
+	enum ipe_match match_type;
+	bool match = false;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	pol = rcu_dereference(ipe_active_policy);
+	if (!pol) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	if (ctx->op == IPE_OP_INVALID) {
+		if (pol->parsed->global_default_action == IPE_ACTION_INVALID) {
+			WARN(1, "no default rule set for unknown op, ALLOW it");
+			action = IPE_ACTION_ALLOW;
+		} else {
+			action = pol->parsed->global_default_action;
+		}
+		match_type = IPE_MATCH_GLOBAL;
+		goto eval;
+	}
+
+	rules = &pol->parsed->rules[ctx->op];
+
+	list_for_each_entry(rule, &rules->rules, next) {
+		match = true;
+
+		list_for_each_entry(prop, &rule->props, next) {
+			match = evaluate_property(ctx, prop);
+			if (!match)
+				break;
+		}
+
+		if (match)
+			break;
+	}
+
+	if (match) {
+		action = rule->action;
+		match_type = IPE_MATCH_RULE;
+	} else if (rules->default_action != IPE_ACTION_INVALID) {
+		action = rules->default_action;
+		match_type = IPE_MATCH_TABLE;
+	} else {
+		action = pol->parsed->global_default_action;
+		match_type = IPE_MATCH_GLOBAL;
+	}
+
+eval:
+	ipe_audit_match(ctx, match_type, action, rule);
+	rcu_read_unlock();
+
+	if (action == IPE_ACTION_DENY)
+		rc = -EACCES;
+
+	if (!READ_ONCE(enforce))
+		rc = 0;
+
+	return rc;
+}
+
+/* Set the right module name */
+#ifdef KBUILD_MODNAME
+#undef KBUILD_MODNAME
+#define KBUILD_MODNAME "ipe"
+#endif
+
+module_param(success_audit, bool, 0400);
+MODULE_PARM_DESC(success_audit, "Start IPE with success auditing enabled");
+module_param(enforce, bool, 0400);
+MODULE_PARM_DESC(enforce, "Start IPE in enforce or permissive mode");
diff --git a/security/ipe/eval.h b/security/ipe/eval.h
new file mode 100644
index 000000000..fef65a364
--- /dev/null
+++ b/security/ipe/eval.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _IPE_EVAL_H
+#define _IPE_EVAL_H
+
+#include <linux/file.h>
+#include <linux/types.h>
+
+#include "policy.h"
+#include "hooks.h"
+
+#define IPE_EVAL_CTX_INIT ((struct ipe_eval_ctx){ 0 })
+
+extern struct ipe_policy __rcu *ipe_active_policy;
+extern bool success_audit;
+extern bool enforce;
+
+struct ipe_superblock {
+	bool initramfs;
+};
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+struct ipe_bdev {
+#ifdef CONFIG_IPE_PROP_DM_VERITY_SIGNATURE
+	bool dm_verity_signed;
+#endif /* CONFIG_IPE_PROP_DM_VERITY_SIGNATURE */
+	struct digest_info *root_hash;
+};
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+struct ipe_inode {
+	bool fs_verity_signed;
+};
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+struct ipe_eval_ctx {
+	enum ipe_op_type op;
+	enum ipe_hook_type hook;
+
+	const struct file *file;
+	bool initramfs;
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+	const struct ipe_bdev *ipe_bdev;
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+#ifdef CONFIG_IPE_PROP_FS_VERITY
+	const struct inode *ino;
+#endif /* CONFIG_IPE_PROP_FS_VERITY */
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+	const struct ipe_inode *ipe_inode;
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+};
+
+enum ipe_match {
+	IPE_MATCH_RULE = 0,
+	IPE_MATCH_TABLE,
+	IPE_MATCH_GLOBAL,
+	__IPE_MATCH_MAX
+};
+
+void ipe_build_eval_ctx(struct ipe_eval_ctx *ctx,
+			const struct file *file,
+			enum ipe_op_type op,
+			enum ipe_hook_type hook);
+int ipe_evaluate_event(const struct ipe_eval_ctx *const ctx);
+
+#endif /* _IPE_EVAL_H */
diff --git a/security/ipe/fs.c b/security/ipe/fs.c
new file mode 100644
index 000000000..076c111c8
--- /dev/null
+++ b/security/ipe/fs.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/dcache.h>
+#include <linux/security.h>
+
+#include "ipe.h"
+#include "fs.h"
+#include "eval.h"
+#include "policy.h"
+#include "audit.h"
+
+static struct dentry *root __ro_after_init;
+struct dentry *policy_root __ro_after_init;
+
+/**
+ * setaudit() - Write handler for the securityfs node, "ipe/success_audit"
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-EPERM			- Insufficient permission
+ */
+static ssize_t setaudit(struct file *f, const char __user *data,
+			size_t len, loff_t *offset)
+{
+	int rc = 0;
+	bool value;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	rc = kstrtobool_from_user(data, len, &value);
+	if (rc)
+		return rc;
+
+	WRITE_ONCE(success_audit, value);
+
+	return len;
+}
+
+/**
+ * getaudit() - Read handler for the securityfs node, "ipe/success_audit"
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the read syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return: Length of buffer written
+ */
+static ssize_t getaudit(struct file *f, char __user *data,
+			size_t len, loff_t *offset)
+{
+	const char *result;
+
+	result = ((READ_ONCE(success_audit)) ? "1" : "0");
+
+	return simple_read_from_buffer(data, len, offset, result, 1);
+}
+
+/**
+ * setenforce() - Write handler for the securityfs node, "ipe/enforce"
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-EPERM			- Insufficient permission
+ */
+static ssize_t setenforce(struct file *f, const char __user *data,
+			  size_t len, loff_t *offset)
+{
+	int rc = 0;
+	bool new_value, old_value;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	old_value = READ_ONCE(enforce);
+	rc = kstrtobool_from_user(data, len, &new_value);
+	if (rc)
+		return rc;
+
+	if (new_value != old_value) {
+		ipe_audit_enforce(new_value, old_value);
+		WRITE_ONCE(enforce, new_value);
+	}
+
+	return len;
+}
+
+/**
+ * getenforce() - Read handler for the securityfs node, "ipe/enforce"
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the read syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return: Length of buffer written
+ */
+static ssize_t getenforce(struct file *f, char __user *data,
+			  size_t len, loff_t *offset)
+{
+	const char *result;
+
+	result = ((READ_ONCE(enforce)) ? "1" : "0");
+
+	return simple_read_from_buffer(data, len, offset, result, 1);
+}
+
+/**
+ * new_policy() - Write handler for the securityfs node, "ipe/new_policy".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-EPERM			- Insufficient permission
+ * * %-ENOMEM			- Out of memory (OOM)
+ * * %-EBADMSG			- Policy is invalid
+ * * %-ERANGE			- Policy version number overflow
+ * * %-EINVAL			- Policy version parsing error
+ * * %-EEXIST			- Same name policy already deployed
+ * * %-ENOKEY			- Policy signing key not found
+ * * %-EKEYREJECTED		- Policy signature verification failed
+ */
+static ssize_t new_policy(struct file *f, const char __user *data,
+			  size_t len, loff_t *offset)
+{
+	struct ipe_policy *p = NULL;
+	char *copy = NULL;
+	int rc = 0;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN)) {
+		rc = -EPERM;
+		goto out;
+	}
+
+	copy = memdup_user_nul(data, len);
+	if (IS_ERR(copy)) {
+		rc = PTR_ERR(copy);
+		copy = NULL;
+		goto out;
+	}
+
+	p = ipe_new_policy(NULL, 0, copy, len);
+	if (IS_ERR(p)) {
+		rc = PTR_ERR(p);
+		goto out;
+	}
+
+	rc = ipe_new_policyfs_node(p);
+	if (rc)
+		goto out;
+
+out:
+	kfree(copy);
+	if (rc < 0) {
+		ipe_free_policy(p);
+		ipe_audit_policy_load(ERR_PTR(rc));
+	} else {
+		ipe_audit_policy_load(p);
+	}
+	return (rc < 0) ? rc : len;
+}
+
+static const struct file_operations np_fops = {
+	.write = new_policy,
+};
+
+static const struct file_operations audit_fops = {
+	.write = setaudit,
+	.read = getaudit,
+};
+
+static const struct file_operations enforce_fops = {
+	.write = setenforce,
+	.read = getenforce,
+};
+
+/**
+ * ipe_init_securityfs() - Initialize IPE's securityfs tree at fsinit.
+ *
+ * Return: %0 on success. If an error occurs, the function will return
+ * the -errno.
+ */
+int __init ipe_init_securityfs(void)
+{
+	int rc = 0;
+	struct ipe_policy *ap;
+	struct dentry *dentry;
+
+	if (!ipe_enabled)
+		return -EOPNOTSUPP;
+
+	root = securityfs_create_dir("ipe", NULL);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	dentry = securityfs_create_file("success_audit", 0600, root,
+					    NULL, &audit_fops);
+	if (IS_ERR(dentry)) {
+		rc = PTR_ERR(dentry);
+		goto err;
+	}
+
+	dentry = securityfs_create_file("enforce", 0600, root, NULL,
+					      &enforce_fops);
+	if (IS_ERR(dentry)) {
+		rc = PTR_ERR(dentry);
+		goto err;
+	}
+
+	policy_root = securityfs_create_dir("policies", root);
+	if (IS_ERR(policy_root)) {
+		rc = PTR_ERR(policy_root);
+		goto err;
+	}
+
+	ap = rcu_access_pointer(ipe_active_policy);
+	if (ap) {
+		rc = ipe_new_policyfs_node(ap);
+		if (rc)
+			goto err;
+	}
+
+	dentry = securityfs_create_file("new_policy", 0200, root, NULL, &np_fops);
+	if (IS_ERR(dentry)) {
+		rc = PTR_ERR(dentry);
+		goto err;
+	}
+
+	return 0;
+err:
+	securityfs_remove(root);
+	return rc;
+}
diff --git a/security/ipe/fs.h b/security/ipe/fs.h
new file mode 100644
index 000000000..0141ae8e8
--- /dev/null
+++ b/security/ipe/fs.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _IPE_FS_H
+#define _IPE_FS_H
+
+#include "policy.h"
+
+extern struct dentry *policy_root __ro_after_init;
+
+int ipe_new_policyfs_node(struct ipe_policy *p);
+void ipe_del_policyfs_node(struct ipe_policy *p);
+
+#endif /* _IPE_FS_H */
diff --git a/security/ipe/hooks.c b/security/ipe/hooks.c
new file mode 100644
index 000000000..0ae54a880
--- /dev/null
+++ b/security/ipe/hooks.c
@@ -0,0 +1,342 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/fs_struct.h>
+#include <linux/types.h>
+#include <linux/binfmts.h>
+#include <linux/mman.h>
+#include <linux/blk_types.h>
+
+#include "ipe.h"
+#include "hooks.h"
+#include "eval.h"
+#include "digest.h"
+
+/**
+ * ipe_bprm_check_security() - ipe security hook function for bprm check.
+ * @bprm: Supplies a pointer to a linux_binprm structure to source the file
+ *	  being evaluated.
+ *
+ * This LSM hook is called when a binary is loaded through the exec
+ * family of system calls.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_bprm_check_security(struct linux_binprm *bprm)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	ipe_build_eval_ctx(&ctx, bprm->file, IPE_OP_EXEC, IPE_HOOK_BPRM_CHECK);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_bprm_creds_for_exec() - ipe security hook function for bprm creds check.
+ * @bprm: Supplies a pointer to a linux_binprm structure to source the file
+ *	  being evaluated.
+ *
+ * This LSM hook is called when userspace signals the kernel to check a file
+ * for execution through the execveat syscall with the AT_EXECVE_CHECK flag.
+ * The hook triggers IPE policy evaluation on the script file and returns
+ * the policy decision to userspace. The userspace program receives the
+ * return code and can decide whether to proceed with script execution.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	if (!bprm->is_check)
+		return 0;
+
+	ipe_build_eval_ctx(&ctx, bprm->file, IPE_OP_EXEC,
+			   IPE_HOOK_BPRM_CREDS_FOR_EXEC);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_mmap_file() - ipe security hook function for mmap check.
+ * @f: File being mmap'd. Can be NULL in the case of anonymous memory.
+ * @reqprot: The requested protection on the mmap, passed from usermode.
+ * @prot: The effective protection on the mmap, resolved from reqprot and
+ *	  system configuration.
+ * @flags: Unused.
+ *
+ * This hook is called when a file is loaded through the mmap
+ * family of system calls.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_mmap_file(struct file *f, unsigned long reqprot __always_unused,
+		  unsigned long prot, unsigned long flags)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	if (prot & PROT_EXEC) {
+		ipe_build_eval_ctx(&ctx, f, IPE_OP_EXEC, IPE_HOOK_MMAP);
+		return ipe_evaluate_event(&ctx);
+	}
+
+	return 0;
+}
+
+/**
+ * ipe_file_mprotect() - ipe security hook function for mprotect check.
+ * @vma: Existing virtual memory area created by mmap or similar.
+ * @reqprot: The requested protection on the mmap, passed from usermode.
+ * @prot: The effective protection on the mmap, resolved from reqprot and
+ *	  system configuration.
+ *
+ * This LSM hook is called when a mmap'd region of memory is changing
+ * its protections via mprotect.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_file_mprotect(struct vm_area_struct *vma,
+		      unsigned long reqprot __always_unused,
+		      unsigned long prot)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+
+	/* Already Executable */
+	if (vma->vm_flags & VM_EXEC)
+		return 0;
+
+	if (prot & PROT_EXEC) {
+		ipe_build_eval_ctx(&ctx, vma->vm_file, IPE_OP_EXEC, IPE_HOOK_MPROTECT);
+		return ipe_evaluate_event(&ctx);
+	}
+
+	return 0;
+}
+
+/**
+ * ipe_kernel_read_file() - ipe security hook function for kernel read.
+ * @file: Supplies a pointer to the file structure being read in from disk.
+ * @id: Supplies the enumeration identifying the purpose of the read.
+ * @contents: Unused.
+ *
+ * This LSM hook is called when a file is read from disk in the kernel.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			 bool contents)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+	enum ipe_op_type op;
+
+	switch (id) {
+	case READING_FIRMWARE:
+		op = IPE_OP_FIRMWARE;
+		break;
+	case READING_MODULE:
+	case READING_MODULE_COMPRESSED:
+		op = IPE_OP_KERNEL_MODULE;
+		break;
+	case READING_KEXEC_INITRAMFS:
+		op = IPE_OP_KEXEC_INITRAMFS;
+		break;
+	case READING_KEXEC_IMAGE:
+		op = IPE_OP_KEXEC_IMAGE;
+		break;
+	case READING_POLICY:
+		op = IPE_OP_POLICY;
+		break;
+	case READING_X509_CERTIFICATE:
+		op = IPE_OP_X509;
+		break;
+	default:
+		op = IPE_OP_INVALID;
+		WARN(1, "no rule setup for kernel_read_file enum %d", id);
+	}
+
+	ipe_build_eval_ctx(&ctx, file, op, IPE_HOOK_KERNEL_READ);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_kernel_load_data() - ipe security hook function for kernel load data.
+ * @id: Supplies the enumeration identifying the purpose of the load.
+ * @contents: Unused.
+ *
+ * This LSM hook is called when a data buffer provided by userspace is loading
+ * into the kernel.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EACCES	- Did not pass IPE policy
+ */
+int ipe_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	struct ipe_eval_ctx ctx = IPE_EVAL_CTX_INIT;
+	enum ipe_op_type op;
+
+	switch (id) {
+	case LOADING_FIRMWARE:
+		op = IPE_OP_FIRMWARE;
+		break;
+	case LOADING_MODULE:
+		op = IPE_OP_KERNEL_MODULE;
+		break;
+	case LOADING_KEXEC_INITRAMFS:
+		op = IPE_OP_KEXEC_INITRAMFS;
+		break;
+	case LOADING_KEXEC_IMAGE:
+		op = IPE_OP_KEXEC_IMAGE;
+		break;
+	case LOADING_POLICY:
+		op = IPE_OP_POLICY;
+		break;
+	case LOADING_X509_CERTIFICATE:
+		op = IPE_OP_X509;
+		break;
+	default:
+		op = IPE_OP_INVALID;
+		WARN(1, "no rule setup for kernel_load_data enum %d", id);
+	}
+
+	ipe_build_eval_ctx(&ctx, NULL, op, IPE_HOOK_KERNEL_LOAD);
+	return ipe_evaluate_event(&ctx);
+}
+
+/**
+ * ipe_unpack_initramfs() - Mark the current rootfs as initramfs.
+ */
+void ipe_unpack_initramfs(void)
+{
+	ipe_sb(current->fs->root.mnt->mnt_sb)->initramfs = true;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+/**
+ * ipe_bdev_free_security() - Free IPE's LSM blob of block_devices.
+ * @bdev: Supplies a pointer to a block_device that contains the structure
+ *	  to free.
+ */
+void ipe_bdev_free_security(struct block_device *bdev)
+{
+	struct ipe_bdev *blob = ipe_bdev(bdev);
+
+	ipe_digest_free(blob->root_hash);
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY_SIGNATURE
+static void ipe_set_dmverity_signature(struct ipe_bdev *blob,
+				       const void *value,
+				       size_t size)
+{
+	blob->dm_verity_signed = size > 0 && value;
+}
+#else
+static inline void ipe_set_dmverity_signature(struct ipe_bdev *blob,
+					      const void *value,
+					      size_t size)
+{
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY_SIGNATURE */
+
+/**
+ * ipe_bdev_setintegrity() - Save integrity data from a bdev to IPE's LSM blob.
+ * @bdev: Supplies a pointer to a block_device that contains the LSM blob.
+ * @type: Supplies the integrity type.
+ * @value: Supplies the value to store.
+ * @size: The size of @value.
+ *
+ * This hook is currently used to save dm-verity's root hash or the existence
+ * of a validated signed dm-verity root hash into LSM blob.
+ *
+ * Return: %0 on success. If an error occurs, the function will return the
+ * -errno.
+ */
+int ipe_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type,
+			  const void *value, size_t size)
+{
+	const struct dm_verity_digest *digest = NULL;
+	struct ipe_bdev *blob = ipe_bdev(bdev);
+	struct digest_info *info = NULL;
+
+	if (type == LSM_INT_DMVERITY_SIG_VALID) {
+		ipe_set_dmverity_signature(blob, value, size);
+
+		return 0;
+	}
+
+	if (type != LSM_INT_DMVERITY_ROOTHASH)
+		return -EINVAL;
+
+	if (!value) {
+		ipe_digest_free(blob->root_hash);
+		blob->root_hash = NULL;
+
+		return 0;
+	}
+	digest = value;
+
+	info = kzalloc_obj(*info);
+	if (!info)
+		return -ENOMEM;
+
+	info->digest = kmemdup(digest->digest, digest->digest_len, GFP_KERNEL);
+	if (!info->digest)
+		goto err;
+
+	info->alg = kstrdup(digest->alg, GFP_KERNEL);
+	if (!info->alg)
+		goto err;
+
+	info->digest_len = digest->digest_len;
+
+	ipe_digest_free(blob->root_hash);
+	blob->root_hash = info;
+
+	return 0;
+err:
+	ipe_digest_free(info);
+
+	return -ENOMEM;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+/**
+ * ipe_inode_setintegrity() - save integrity data from a inode to IPE's LSM blob.
+ * @inode: The inode to source the security blob from.
+ * @type: Supplies the integrity type.
+ * @value: The value to be stored.
+ * @size: The size of @value.
+ *
+ * This hook is currently used to save the existence of a validated fs-verity
+ * builtin signature into LSM blob.
+ *
+ * Return: %0 on success. If an error occurs, the function will return the
+ * -errno.
+ */
+int ipe_inode_setintegrity(const struct inode *inode,
+			   enum lsm_integrity_type type,
+			   const void *value, size_t size)
+{
+	struct ipe_inode *inode_sec = ipe_inode(inode);
+
+	if (type == LSM_INT_FSVERITY_BUILTINSIG_VALID) {
+		inode_sec->fs_verity_signed = size > 0 && value;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
diff --git a/security/ipe/hooks.h b/security/ipe/hooks.h
new file mode 100644
index 000000000..07db37332
--- /dev/null
+++ b/security/ipe/hooks.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+#ifndef _IPE_HOOKS_H
+#define _IPE_HOOKS_H
+
+#include <linux/fs.h>
+#include <linux/binfmts.h>
+#include <linux/security.h>
+#include <linux/blk_types.h>
+#include <linux/fsverity.h>
+
+enum ipe_hook_type {
+	IPE_HOOK_BPRM_CHECK = 0,
+	IPE_HOOK_BPRM_CREDS_FOR_EXEC,
+	IPE_HOOK_MMAP,
+	IPE_HOOK_MPROTECT,
+	IPE_HOOK_KERNEL_READ,
+	IPE_HOOK_KERNEL_LOAD,
+	__IPE_HOOK_MAX
+};
+
+#define IPE_HOOK_INVALID __IPE_HOOK_MAX
+
+int ipe_bprm_check_security(struct linux_binprm *bprm);
+
+int ipe_bprm_creds_for_exec(struct linux_binprm *bprm);
+
+int ipe_mmap_file(struct file *f, unsigned long reqprot, unsigned long prot,
+		  unsigned long flags);
+
+int ipe_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
+		      unsigned long prot);
+
+int ipe_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			 bool contents);
+
+int ipe_kernel_load_data(enum kernel_load_data_id id, bool contents);
+
+void ipe_unpack_initramfs(void);
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+void ipe_bdev_free_security(struct block_device *bdev);
+
+int ipe_bdev_setintegrity(struct block_device *bdev, enum lsm_integrity_type type,
+			  const void *value, size_t len);
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+int ipe_inode_setintegrity(const struct inode *inode, enum lsm_integrity_type type,
+			   const void *value, size_t size);
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+#endif /* _IPE_HOOKS_H */
diff --git a/security/ipe/ipe.c b/security/ipe/ipe.c
new file mode 100644
index 000000000..495bb765d
--- /dev/null
+++ b/security/ipe/ipe.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+#include <uapi/linux/lsm.h>
+
+#include "ipe.h"
+#include "eval.h"
+#include "hooks.h"
+
+extern const char *const ipe_boot_policy;
+bool ipe_enabled;
+
+static struct lsm_blob_sizes ipe_blobs __ro_after_init = {
+	.lbs_superblock = sizeof(struct ipe_superblock),
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+	.lbs_bdev = sizeof(struct ipe_bdev),
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+	.lbs_inode = sizeof(struct ipe_inode),
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+};
+
+static const struct lsm_id ipe_lsmid = {
+	.name = "ipe",
+	.id = LSM_ID_IPE,
+};
+
+struct ipe_superblock *ipe_sb(const struct super_block *sb)
+{
+	return sb->s_security + ipe_blobs.lbs_superblock;
+}
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+struct ipe_bdev *ipe_bdev(struct block_device *b)
+{
+	return b->bd_security + ipe_blobs.lbs_bdev;
+}
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+struct ipe_inode *ipe_inode(const struct inode *inode)
+{
+	return inode->i_security + ipe_blobs.lbs_inode;
+}
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+static struct security_hook_list ipe_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(bprm_check_security, ipe_bprm_check_security),
+	LSM_HOOK_INIT(bprm_creds_for_exec, ipe_bprm_creds_for_exec),
+	LSM_HOOK_INIT(mmap_file, ipe_mmap_file),
+	LSM_HOOK_INIT(file_mprotect, ipe_file_mprotect),
+	LSM_HOOK_INIT(kernel_read_file, ipe_kernel_read_file),
+	LSM_HOOK_INIT(kernel_load_data, ipe_kernel_load_data),
+	LSM_HOOK_INIT(initramfs_populated, ipe_unpack_initramfs),
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+	LSM_HOOK_INIT(bdev_free_security, ipe_bdev_free_security),
+	LSM_HOOK_INIT(bdev_setintegrity, ipe_bdev_setintegrity),
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+	LSM_HOOK_INIT(inode_setintegrity, ipe_inode_setintegrity),
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+};
+
+/**
+ * ipe_init() - Entry point of IPE.
+ *
+ * This is called at LSM init, which happens occurs early during kernel
+ * start up. During this phase, IPE registers its hooks and loads the
+ * builtin boot policy.
+ *
+ * Return:
+ * * %0		- OK
+ * * %-ENOMEM	- Out of memory (OOM)
+ */
+static int __init ipe_init(void)
+{
+	struct ipe_policy *p = NULL;
+
+	security_add_hooks(ipe_hooks, ARRAY_SIZE(ipe_hooks), &ipe_lsmid);
+	ipe_enabled = true;
+
+	if (ipe_boot_policy) {
+		p = ipe_new_policy(ipe_boot_policy, strlen(ipe_boot_policy),
+				   NULL, 0);
+		if (IS_ERR(p))
+			return PTR_ERR(p);
+
+		rcu_assign_pointer(ipe_active_policy, p);
+	}
+
+	return 0;
+}
+
+DEFINE_LSM(ipe) = {
+	.id = &ipe_lsmid,
+	.init = ipe_init,
+	.blobs = &ipe_blobs,
+	.initcall_fs = ipe_init_securityfs,
+};
diff --git a/security/ipe/ipe.h b/security/ipe/ipe.h
new file mode 100644
index 000000000..25cfdb8f0
--- /dev/null
+++ b/security/ipe/ipe.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#ifndef _IPE_H
+#define _IPE_H
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt) "ipe: " fmt
+
+#include <linux/lsm_hooks.h>
+struct ipe_superblock *ipe_sb(const struct super_block *sb);
+
+extern bool ipe_enabled;
+
+#ifdef CONFIG_IPE_PROP_DM_VERITY
+struct ipe_bdev *ipe_bdev(struct block_device *b);
+#endif /* CONFIG_IPE_PROP_DM_VERITY */
+#ifdef CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG
+struct ipe_inode *ipe_inode(const struct inode *inode);
+#endif /* CONFIG_IPE_PROP_FS_VERITY_BUILTIN_SIG */
+
+int ipe_init_securityfs(void);
+
+#endif /* _IPE_H */
diff --git a/security/ipe/policy.c b/security/ipe/policy.c
new file mode 100644
index 000000000..827867be4
--- /dev/null
+++ b/security/ipe/policy.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/errno.h>
+#include <linux/verification.h>
+
+#include "ipe.h"
+#include "eval.h"
+#include "fs.h"
+#include "policy.h"
+#include "policy_parser.h"
+#include "audit.h"
+
+/* lock for synchronizing writers across ipe policy */
+DEFINE_MUTEX(ipe_policy_lock);
+
+/**
+ * ver_to_u64() - Convert an internal ipe_policy_version to a u64.
+ * @p: Policy to extract the version from.
+ *
+ * Bits (LSB is index 0):
+ *	[48,32] -> Major
+ *	[32,16] -> Minor
+ *	[16, 0] -> Revision
+ *
+ * Return: u64 version of the embedded version structure.
+ */
+static inline u64 ver_to_u64(const struct ipe_policy *const p)
+{
+	u64 r;
+
+	r = (((u64)p->parsed->version.major) << 32)
+	  | (((u64)p->parsed->version.minor) << 16)
+	  | ((u64)(p->parsed->version.rev));
+
+	return r;
+}
+
+/**
+ * ipe_free_policy() - Deallocate a given IPE policy.
+ * @p: Supplies the policy to free.
+ *
+ * Safe to call on IS_ERR/NULL.
+ */
+void ipe_free_policy(struct ipe_policy *p)
+{
+	if (IS_ERR_OR_NULL(p))
+		return;
+
+	ipe_del_policyfs_node(p);
+	ipe_free_parsed_policy(p->parsed);
+	/*
+	 * p->text is allocated only when p->pkcs7 is not NULL
+	 * otherwise it points to the plaintext data inside the pkcs7
+	 */
+	if (!p->pkcs7)
+		kfree(p->text);
+	kfree(p->pkcs7);
+	kfree(p);
+}
+
+static int set_pkcs7_data(void *ctx, const void *data, size_t len,
+			  size_t asn1hdrlen __always_unused)
+{
+	struct ipe_policy *p = ctx;
+
+	p->text = (const char *)data;
+	p->textlen = len;
+
+	return 0;
+}
+
+/**
+ * ipe_update_policy() - parse a new policy and replace old with it.
+ * @root: Supplies a pointer to the securityfs inode saved the policy.
+ * @text: Supplies a pointer to the plain text policy.
+ * @textlen: Supplies the length of @text.
+ * @pkcs7: Supplies a pointer to a buffer containing a pkcs7 message.
+ * @pkcs7len: Supplies the length of @pkcs7len.
+ *
+ * @text/@textlen is mutually exclusive with @pkcs7/@pkcs7len - see
+ * ipe_new_policy.
+ *
+ * Context: Requires root->i_rwsem to be held.
+ * Return:
+ * * %0	- Success
+ * * %-ENOENT	- Policy was deleted while updating
+ * * %-EINVAL	- Policy name mismatch
+ * * %-ESTALE	- Policy version too old
+ */
+int ipe_update_policy(struct inode *root, const char *text, size_t textlen,
+		      const char *pkcs7, size_t pkcs7len)
+{
+	struct ipe_policy *old, *ap, *new = NULL;
+	int rc = 0;
+
+	old = (struct ipe_policy *)root->i_private;
+	if (!old)
+		return -ENOENT;
+
+	new = ipe_new_policy(text, textlen, pkcs7, pkcs7len);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+
+	if (strcmp(new->parsed->name, old->parsed->name)) {
+		rc = -EINVAL;
+		goto err;
+	}
+
+	if (ver_to_u64(old) >= ver_to_u64(new)) {
+		rc = -ESTALE;
+		goto err;
+	}
+
+	root->i_private = new;
+	swap(new->policyfs, old->policyfs);
+	ipe_audit_policy_load(new);
+
+	mutex_lock(&ipe_policy_lock);
+	ap = rcu_dereference_protected(ipe_active_policy,
+				       lockdep_is_held(&ipe_policy_lock));
+	if (old == ap) {
+		rcu_assign_pointer(ipe_active_policy, new);
+		mutex_unlock(&ipe_policy_lock);
+		ipe_audit_policy_activation(old, new);
+	} else {
+		mutex_unlock(&ipe_policy_lock);
+	}
+	synchronize_rcu();
+	ipe_free_policy(old);
+
+	return 0;
+err:
+	ipe_free_policy(new);
+	return rc;
+}
+
+/**
+ * ipe_new_policy() - Allocate and parse an ipe_policy structure.
+ *
+ * @text: Supplies a pointer to the plain-text policy to parse.
+ * @textlen: Supplies the length of @text.
+ * @pkcs7: Supplies a pointer to a pkcs7-signed IPE policy.
+ * @pkcs7len: Supplies the length of @pkcs7.
+ *
+ * @text/@textlen Should be NULL/0 if @pkcs7/@pkcs7len is set.
+ *
+ * Return:
+ * * a pointer to the ipe_policy structure	- Success
+ * * %-EBADMSG				- Policy is invalid
+ * * %-ENOMEM				- Out of memory (OOM)
+ * * %-ERANGE				- Policy version number overflow
+ * * %-EINVAL				- Policy version parsing error
+ * * %-ENOKEY				- Policy signing key not found
+ * * %-EKEYREJECTED			- Policy signature verification failed
+ */
+struct ipe_policy *ipe_new_policy(const char *text, size_t textlen,
+				  const char *pkcs7, size_t pkcs7len)
+{
+	struct ipe_policy *new = NULL;
+	int rc = 0;
+
+	new = kzalloc_obj(*new);
+	if (!new)
+		return ERR_PTR(-ENOMEM);
+
+	if (!text) {
+		new->pkcs7len = pkcs7len;
+		new->pkcs7 = kmemdup(pkcs7, pkcs7len, GFP_KERNEL);
+		if (!new->pkcs7) {
+			rc = -ENOMEM;
+			goto err;
+		}
+
+		rc = verify_pkcs7_signature(NULL, 0, new->pkcs7, pkcs7len,
+#ifdef CONFIG_IPE_POLICY_SIG_SECONDARY_KEYRING
+					    VERIFY_USE_SECONDARY_KEYRING,
+#else
+					    NULL,
+#endif
+					    VERIFYING_UNSPECIFIED_SIGNATURE,
+					    set_pkcs7_data, new);
+#ifdef CONFIG_IPE_POLICY_SIG_PLATFORM_KEYRING
+		if (rc == -ENOKEY || rc == -EKEYREJECTED)
+			rc = verify_pkcs7_signature(NULL, 0, new->pkcs7, pkcs7len,
+						    VERIFY_USE_PLATFORM_KEYRING,
+						    VERIFYING_UNSPECIFIED_SIGNATURE,
+						    set_pkcs7_data, new);
+#endif
+		if (rc)
+			goto err;
+	} else {
+		new->textlen = textlen;
+		new->text = kstrdup(text, GFP_KERNEL);
+		if (!new->text) {
+			rc = -ENOMEM;
+			goto err;
+		}
+	}
+
+	rc = ipe_parse_policy(new);
+	if (rc)
+		goto err;
+
+	return new;
+err:
+	ipe_free_policy(new);
+	return ERR_PTR(rc);
+}
+
+/**
+ * ipe_set_active_pol() - Make @p the active policy.
+ * @p: Supplies a pointer to the policy to make active.
+ *
+ * Context: Requires root->i_rwsem, which i_private has the policy, to be held.
+ * Return:
+ * * %0	- Success
+ * * %-EINVAL	- New active policy version is invalid
+ */
+int ipe_set_active_pol(const struct ipe_policy *p)
+{
+	struct ipe_policy *ap = NULL;
+
+	mutex_lock(&ipe_policy_lock);
+
+	ap = rcu_dereference_protected(ipe_active_policy,
+				       lockdep_is_held(&ipe_policy_lock));
+	if (ap == p) {
+		mutex_unlock(&ipe_policy_lock);
+		return 0;
+	}
+	if (ap && ver_to_u64(ap) > ver_to_u64(p)) {
+		mutex_unlock(&ipe_policy_lock);
+		return -EINVAL;
+	}
+
+	rcu_assign_pointer(ipe_active_policy, p);
+	ipe_audit_policy_activation(ap, p);
+	mutex_unlock(&ipe_policy_lock);
+
+	return 0;
+}
diff --git a/security/ipe/policy.h b/security/ipe/policy.h
new file mode 100644
index 000000000..5bfbdbdde
--- /dev/null
+++ b/security/ipe/policy.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+#ifndef _IPE_POLICY_H
+#define _IPE_POLICY_H
+
+#include <linux/list.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+
+enum ipe_op_type {
+	IPE_OP_EXEC = 0,
+	IPE_OP_FIRMWARE,
+	IPE_OP_KERNEL_MODULE,
+	IPE_OP_KEXEC_IMAGE,
+	IPE_OP_KEXEC_INITRAMFS,
+	IPE_OP_POLICY,
+	IPE_OP_X509,
+	__IPE_OP_MAX,
+};
+
+#define IPE_OP_INVALID __IPE_OP_MAX
+
+enum ipe_action_type {
+	IPE_ACTION_ALLOW = 0,
+	IPE_ACTION_DENY,
+	__IPE_ACTION_MAX
+};
+
+#define IPE_ACTION_INVALID __IPE_ACTION_MAX
+
+enum ipe_prop_type {
+	IPE_PROP_BOOT_VERIFIED_FALSE,
+	IPE_PROP_BOOT_VERIFIED_TRUE,
+	IPE_PROP_DMV_ROOTHASH,
+	IPE_PROP_DMV_SIG_FALSE,
+	IPE_PROP_DMV_SIG_TRUE,
+	IPE_PROP_FSV_DIGEST,
+	IPE_PROP_FSV_SIG_FALSE,
+	IPE_PROP_FSV_SIG_TRUE,
+	__IPE_PROP_MAX
+};
+
+#define IPE_PROP_INVALID __IPE_PROP_MAX
+
+struct ipe_prop {
+	struct list_head next;
+	enum ipe_prop_type type;
+	void *value;
+};
+
+struct ipe_rule {
+	enum ipe_op_type op;
+	enum ipe_action_type action;
+	struct list_head props;
+	struct list_head next;
+};
+
+struct ipe_op_table {
+	struct list_head rules;
+	enum ipe_action_type default_action;
+};
+
+struct ipe_parsed_policy {
+	const char *name;
+	struct {
+		u16 major;
+		u16 minor;
+		u16 rev;
+	} version;
+
+	enum ipe_action_type global_default_action;
+
+	struct ipe_op_table rules[__IPE_OP_MAX];
+};
+
+struct ipe_policy {
+	const char *pkcs7;
+	size_t pkcs7len;
+
+	const char *text;
+	size_t textlen;
+
+	struct ipe_parsed_policy *parsed;
+
+	struct dentry *policyfs;
+};
+
+struct ipe_policy *ipe_new_policy(const char *text, size_t textlen,
+				  const char *pkcs7, size_t pkcs7len);
+void ipe_free_policy(struct ipe_policy *pol);
+int ipe_update_policy(struct inode *root, const char *text, size_t textlen,
+		      const char *pkcs7, size_t pkcs7len);
+int ipe_set_active_pol(const struct ipe_policy *p);
+extern struct mutex ipe_policy_lock;
+
+#endif /* _IPE_POLICY_H */
diff --git a/security/ipe/policy_fs.c b/security/ipe/policy_fs.c
new file mode 100644
index 000000000..9d92d8a14
--- /dev/null
+++ b/security/ipe/policy_fs.c
@@ -0,0 +1,490 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/types.h>
+#include <linux/dcache.h>
+#include <linux/security.h>
+
+#include "ipe.h"
+#include "policy.h"
+#include "eval.h"
+#include "fs.h"
+#include "audit.h"
+
+#define MAX_VERSION_SIZE ARRAY_SIZE("65535.65535.65535")
+
+/**
+ * struct ipefs_file - defines a file in securityfs.
+ *
+ * @name: file name inside the policy subdirectory
+ * @access: file permissions
+ * @fops: &file_operations specific to this file
+ */
+struct ipefs_file {
+	const char *name;
+	umode_t access;
+	const struct file_operations *fops;
+};
+
+/**
+ * read_pkcs7() - Read handler for "ipe/policies/$name/pkcs7".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * @data will be populated with the pkcs7 blob representing the policy
+ * on success. If the policy is unsigned (like the boot policy), this
+ * will return -ENOENT.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-ENOENT			- Policy initializing/deleted or is unsigned
+ */
+static ssize_t read_pkcs7(struct file *f, char __user *data,
+			  size_t len, loff_t *offset)
+{
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	int rc = 0;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+
+	inode_lock_shared(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	if (!p->pkcs7) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	rc = simple_read_from_buffer(data, len, offset, p->pkcs7, p->pkcs7len);
+
+out:
+	inode_unlock_shared(root);
+
+	return rc;
+}
+
+/**
+ * read_policy() - Read handler for "ipe/policies/$name/policy".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * @data will be populated with the plain-text version of the policy
+ * on success.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t read_policy(struct file *f, char __user *data,
+			   size_t len, loff_t *offset)
+{
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	int rc = 0;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+
+	inode_lock_shared(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	rc = simple_read_from_buffer(data, len, offset, p->text, p->textlen);
+
+out:
+	inode_unlock_shared(root);
+
+	return rc;
+}
+
+/**
+ * read_name() - Read handler for "ipe/policies/$name/name".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * @data will be populated with the policy_name attribute on success.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t read_name(struct file *f, char __user *data,
+			 size_t len, loff_t *offset)
+{
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	int rc = 0;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+
+	inode_lock_shared(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	rc = simple_read_from_buffer(data, len, offset, p->parsed->name,
+				     strlen(p->parsed->name));
+
+out:
+	inode_unlock_shared(root);
+
+	return rc;
+}
+
+/**
+ * read_version() - Read handler for "ipe/policies/$name/version".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * @data will be populated with the version string on success.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t read_version(struct file *f, char __user *data,
+			    size_t len, loff_t *offset)
+{
+	char buffer[MAX_VERSION_SIZE] = { 0 };
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	size_t strsize = 0;
+	ssize_t rc = 0;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+
+	inode_lock_shared(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	strsize = scnprintf(buffer, ARRAY_SIZE(buffer), "%hu.%hu.%hu",
+			    p->parsed->version.major, p->parsed->version.minor,
+			    p->parsed->version.rev);
+
+	rc = simple_read_from_buffer(data, len, offset, buffer, strsize);
+
+out:
+	inode_unlock_shared(root);
+
+	return rc;
+}
+
+/**
+ * setactive() - Write handler for "ipe/policies/$name/active".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-EPERM			- Insufficient permission
+ * * %-EINVAL			- Invalid input
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t setactive(struct file *f, const char __user *data,
+			 size_t len, loff_t *offset)
+{
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	bool value = false;
+	int rc = 0;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	rc = kstrtobool_from_user(data, len, &value);
+	if (rc)
+		return rc;
+
+	if (!value)
+		return -EINVAL;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+	inode_lock(root);
+
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		rc = -ENOENT;
+		goto out;
+	}
+
+	rc = ipe_set_active_pol(p);
+
+out:
+	inode_unlock(root);
+	return (rc < 0) ? rc : len;
+}
+
+/**
+ * getactive() - Read handler for "ipe/policies/$name/active".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * @data will be populated with the 1 or 0 depending on if the
+ * corresponding policy is active.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t getactive(struct file *f, char __user *data,
+			 size_t len, loff_t *offset)
+{
+	const struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	const char *str;
+	int rc = 0;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+
+	inode_lock_shared(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		inode_unlock_shared(root);
+		return -ENOENT;
+	}
+	inode_unlock_shared(root);
+
+	str = (p == rcu_access_pointer(ipe_active_policy)) ? "1" : "0";
+	rc = simple_read_from_buffer(data, len, offset, str, 1);
+
+	return rc;
+}
+
+/**
+ * update_policy() - Write handler for "ipe/policies/$name/update".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * On success this updates the policy represented by $name,
+ * in-place.
+ *
+ * Return:
+ * * Length of buffer written		- Success
+ * * %-EPERM				- Insufficient permission
+ * * %-ENOMEM				- Out of memory (OOM)
+ * * %-ENOENT				- Policy was deleted while updating
+ * * %-EINVAL				- Policy name mismatch
+ * * %-ESTALE				- Policy version too old
+ */
+static ssize_t update_policy(struct file *f, const char __user *data,
+			     size_t len, loff_t *offset)
+{
+	struct inode *root = NULL;
+	char *copy = NULL;
+	int rc = 0;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN)) {
+		rc = -EPERM;
+		goto out;
+	}
+
+	copy = memdup_user(data, len);
+	if (IS_ERR(copy)) {
+		rc = PTR_ERR(copy);
+		copy = NULL;
+		goto out;
+	}
+
+	root = d_inode(f->f_path.dentry->d_parent);
+	inode_lock(root);
+	rc = ipe_update_policy(root, NULL, 0, copy, len);
+	inode_unlock(root);
+
+out:
+	kfree(copy);
+	if (rc) {
+		ipe_audit_policy_load(ERR_PTR(rc));
+		return rc;
+	}
+
+	return len;
+}
+
+/**
+ * delete_policy() - write handler for  "ipe/policies/$name/delete".
+ * @f: Supplies a file structure representing the securityfs node.
+ * @data: Supplies a buffer passed to the write syscall.
+ * @len: Supplies the length of @data.
+ * @offset: unused.
+ *
+ * On success this deletes the policy represented by $name.
+ *
+ * Return:
+ * * Length of buffer written	- Success
+ * * %-EPERM			- Insufficient permission/deleting active policy
+ * * %-EINVAL			- Invalid input
+ * * %-ENOENT			- Policy initializing/deleted
+ */
+static ssize_t delete_policy(struct file *f, const char __user *data,
+			     size_t len, loff_t *offset)
+{
+	struct ipe_policy *ap = NULL;
+	struct ipe_policy *p = NULL;
+	struct inode *root = NULL;
+	bool value = false;
+	int rc = 0;
+
+	if (!file_ns_capable(f, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	rc = kstrtobool_from_user(data, len, &value);
+	if (rc)
+		return rc;
+
+	if (!value)
+		return -EINVAL;
+
+	root = d_inode(f->f_path.dentry->d_parent);
+	inode_lock(root);
+	p = (struct ipe_policy *)root->i_private;
+	if (!p) {
+		inode_unlock(root);
+		return -ENOENT;
+	}
+
+	mutex_lock(&ipe_policy_lock);
+	ap = rcu_dereference_protected(ipe_active_policy,
+				       lockdep_is_held(&ipe_policy_lock));
+	if (p == ap) {
+		mutex_unlock(&ipe_policy_lock);
+		inode_unlock(root);
+		return -EPERM;
+	}
+	mutex_unlock(&ipe_policy_lock);
+
+	root->i_private = NULL;
+	inode_unlock(root);
+
+	synchronize_rcu();
+	ipe_free_policy(p);
+
+	return len;
+}
+
+static const struct file_operations content_fops = {
+	.read = read_policy,
+};
+
+static const struct file_operations pkcs7_fops = {
+	.read = read_pkcs7,
+};
+
+static const struct file_operations name_fops = {
+	.read = read_name,
+};
+
+static const struct file_operations ver_fops = {
+	.read = read_version,
+};
+
+static const struct file_operations active_fops = {
+	.write = setactive,
+	.read = getactive,
+};
+
+static const struct file_operations update_fops = {
+	.write = update_policy,
+};
+
+static const struct file_operations delete_fops = {
+	.write = delete_policy,
+};
+
+/*
+ * policy_subdir - files under a policy subdirectory
+ */
+static const struct ipefs_file policy_subdir[] = {
+	{ "pkcs7", 0444, &pkcs7_fops },
+	{ "policy", 0444, &content_fops },
+	{ "name", 0444, &name_fops },
+	{ "version", 0444, &ver_fops },
+	{ "active", 0600, &active_fops },
+	{ "update", 0200, &update_fops },
+	{ "delete", 0200, &delete_fops },
+};
+
+/**
+ * ipe_del_policyfs_node() - Delete a securityfs entry for @p.
+ * @p: Supplies a pointer to the policy to delete a securityfs entry for.
+ */
+void ipe_del_policyfs_node(struct ipe_policy *p)
+{
+	securityfs_remove(p->policyfs);
+	p->policyfs = NULL;
+}
+
+/**
+ * ipe_new_policyfs_node() - Create a securityfs entry for @p.
+ * @p: Supplies a pointer to the policy to create a securityfs entry for.
+ *
+ * Return: %0 on success. If an error occurs, the function will return
+ * the -errno.
+ */
+int ipe_new_policyfs_node(struct ipe_policy *p)
+{
+	const struct ipefs_file *f = NULL;
+	struct dentry *policyfs = NULL;
+	struct inode *root = NULL;
+	struct dentry *d = NULL;
+	size_t i = 0;
+	int rc = 0;
+
+	if (p->policyfs)
+		return 0;
+
+	policyfs = securityfs_create_dir(p->parsed->name, policy_root);
+	if (IS_ERR(policyfs))
+		return PTR_ERR(policyfs);
+
+	root = d_inode(policyfs);
+
+	for (i = 0; i < ARRAY_SIZE(policy_subdir); ++i) {
+		f = &policy_subdir[i];
+
+		d = securityfs_create_file(f->name, f->access, policyfs,
+					   NULL, f->fops);
+		if (IS_ERR(d)) {
+			rc = PTR_ERR(d);
+			goto err;
+		}
+	}
+
+	inode_lock(root);
+	p->policyfs = policyfs;
+	root->i_private = p;
+	inode_unlock(root);
+
+	return 0;
+err:
+	securityfs_remove(policyfs);
+	return rc;
+}
diff --git a/security/ipe/policy_parser.c b/security/ipe/policy_parser.c
new file mode 100644
index 000000000..6fa5bebf8
--- /dev/null
+++ b/security/ipe/policy_parser.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+
+#include "policy.h"
+#include "policy_parser.h"
+#include "digest.h"
+
+#define START_COMMENT	'#'
+#define IPE_POLICY_DELIM " \t"
+#define IPE_LINE_DELIM "\n\r"
+
+/**
+ * new_parsed_policy() - Allocate and initialize a parsed policy.
+ *
+ * Return:
+ * * a pointer to the ipe_parsed_policy structure	- Success
+ * * %-ENOMEM						- Out of memory (OOM)
+ */
+static struct ipe_parsed_policy *new_parsed_policy(void)
+{
+	struct ipe_parsed_policy *p = NULL;
+	struct ipe_op_table *t = NULL;
+	size_t i = 0;
+
+	p = kzalloc_obj(*p);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	p->global_default_action = IPE_ACTION_INVALID;
+
+	for (i = 0; i < ARRAY_SIZE(p->rules); ++i) {
+		t = &p->rules[i];
+
+		t->default_action = IPE_ACTION_INVALID;
+		INIT_LIST_HEAD(&t->rules);
+	}
+
+	return p;
+}
+
+/**
+ * remove_comment() - Truncate all chars following START_COMMENT in a string.
+ *
+ * @line: Supplies a policy line string for preprocessing.
+ */
+static void remove_comment(char *line)
+{
+	line = strchr(line, START_COMMENT);
+
+	if (line)
+		*line = '\0';
+}
+
+/**
+ * remove_trailing_spaces() - Truncate all trailing spaces in a string.
+ *
+ * @line: Supplies a policy line string for preprocessing.
+ *
+ * Return: The length of truncated string.
+ */
+static size_t remove_trailing_spaces(char *line)
+{
+	size_t i = 0;
+
+	i = strlen(line);
+	while (i > 0 && isspace(line[i - 1]))
+		i--;
+
+	line[i] = '\0';
+
+	return i;
+}
+
+/**
+ * parse_version() - Parse policy version.
+ * @ver: Supplies a version string to be parsed.
+ * @p: Supplies the partial parsed policy.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EBADMSG	- Version string is invalid
+ * * %-ERANGE	- Version number overflow
+ * * %-EINVAL	- Parsing error
+ */
+static int parse_version(char *ver, struct ipe_parsed_policy *p)
+{
+	u16 *const cv[] = { &p->version.major, &p->version.minor, &p->version.rev };
+	size_t sep_count = 0;
+	char *token;
+	int rc = 0;
+
+	while ((token = strsep(&ver, ".")) != NULL) {
+		/* prevent overflow */
+		if (sep_count >= ARRAY_SIZE(cv))
+			return -EBADMSG;
+
+		rc = kstrtou16(token, 10, cv[sep_count]);
+		if (rc)
+			return rc;
+
+		++sep_count;
+	}
+
+	/* prevent underflow */
+	if (sep_count != ARRAY_SIZE(cv))
+		return -EBADMSG;
+
+	return 0;
+}
+
+enum header_opt {
+	IPE_HEADER_POLICY_NAME = 0,
+	IPE_HEADER_POLICY_VERSION,
+	__IPE_HEADER_MAX
+};
+
+static const match_table_t header_tokens = {
+	{IPE_HEADER_POLICY_NAME,	"policy_name=%s"},
+	{IPE_HEADER_POLICY_VERSION,	"policy_version=%s"},
+	{__IPE_HEADER_MAX,		NULL}
+};
+
+/**
+ * parse_header() - Parse policy header information.
+ * @line: Supplies header line to be parsed.
+ * @p: Supplies the partial parsed policy.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EBADMSG	- Header string is invalid
+ * * %-ENOMEM	- Out of memory (OOM)
+ * * %-ERANGE	- Version number overflow
+ * * %-EINVAL	- Version parsing error
+ */
+static int parse_header(char *line, struct ipe_parsed_policy *p)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *t, *ver = NULL;
+	size_t idx = 0;
+	int rc = 0;
+
+	while ((t = strsep(&line, IPE_POLICY_DELIM)) != NULL) {
+		int token;
+
+		if (*t == '\0')
+			continue;
+		if (idx >= __IPE_HEADER_MAX) {
+			rc = -EBADMSG;
+			goto out;
+		}
+
+		token = match_token(t, header_tokens, args);
+		if (token != idx) {
+			rc = -EBADMSG;
+			goto out;
+		}
+
+		switch (token) {
+		case IPE_HEADER_POLICY_NAME:
+			p->name = match_strdup(&args[0]);
+			if (!p->name)
+				rc = -ENOMEM;
+			break;
+		case IPE_HEADER_POLICY_VERSION:
+			ver = match_strdup(&args[0]);
+			if (!ver) {
+				rc = -ENOMEM;
+				break;
+			}
+			rc = parse_version(ver, p);
+			break;
+		default:
+			rc = -EBADMSG;
+		}
+		if (rc)
+			goto out;
+		++idx;
+	}
+
+	if (idx != __IPE_HEADER_MAX)
+		rc = -EBADMSG;
+
+out:
+	kfree(ver);
+	return rc;
+}
+
+/**
+ * token_default() - Determine if the given token is "DEFAULT".
+ * @token: Supplies the token string to be compared.
+ *
+ * Return:
+ * * %false	- The token is not "DEFAULT"
+ * * %true	- The token is "DEFAULT"
+ */
+static bool token_default(char *token)
+{
+	return !strcmp(token, "DEFAULT");
+}
+
+/**
+ * free_rule() - Free the supplied ipe_rule struct.
+ * @r: Supplies the ipe_rule struct to be freed.
+ *
+ * Free a ipe_rule struct @r. Note @r must be removed from any lists before
+ * calling this function.
+ */
+static void free_rule(struct ipe_rule *r)
+{
+	struct ipe_prop *p, *t;
+
+	if (IS_ERR_OR_NULL(r))
+		return;
+
+	list_for_each_entry_safe(p, t, &r->props, next) {
+		list_del(&p->next);
+		ipe_digest_free(p->value);
+		kfree(p);
+	}
+
+	kfree(r);
+}
+
+static const match_table_t operation_tokens = {
+	{IPE_OP_EXEC,			"op=EXECUTE"},
+	{IPE_OP_FIRMWARE,		"op=FIRMWARE"},
+	{IPE_OP_KERNEL_MODULE,		"op=KMODULE"},
+	{IPE_OP_KEXEC_IMAGE,		"op=KEXEC_IMAGE"},
+	{IPE_OP_KEXEC_INITRAMFS,	"op=KEXEC_INITRAMFS"},
+	{IPE_OP_POLICY,			"op=POLICY"},
+	{IPE_OP_X509,			"op=X509_CERT"},
+	{IPE_OP_INVALID,		NULL}
+};
+
+/**
+ * parse_operation() - Parse the operation type given a token string.
+ * @t: Supplies the token string to be parsed.
+ *
+ * Return: The parsed operation type.
+ */
+static enum ipe_op_type parse_operation(char *t)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	return match_token(t, operation_tokens, args);
+}
+
+static const match_table_t action_tokens = {
+	{IPE_ACTION_ALLOW,	"action=ALLOW"},
+	{IPE_ACTION_DENY,	"action=DENY"},
+	{IPE_ACTION_INVALID,	NULL}
+};
+
+/**
+ * parse_action() - Parse the action type given a token string.
+ * @t: Supplies the token string to be parsed.
+ *
+ * Return: The parsed action type.
+ */
+static enum ipe_action_type parse_action(char *t)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	return match_token(t, action_tokens, args);
+}
+
+static const match_table_t property_tokens = {
+	{IPE_PROP_BOOT_VERIFIED_FALSE,	"boot_verified=FALSE"},
+	{IPE_PROP_BOOT_VERIFIED_TRUE,	"boot_verified=TRUE"},
+	{IPE_PROP_DMV_ROOTHASH,		"dmverity_roothash=%s"},
+	{IPE_PROP_DMV_SIG_FALSE,	"dmverity_signature=FALSE"},
+	{IPE_PROP_DMV_SIG_TRUE,		"dmverity_signature=TRUE"},
+	{IPE_PROP_FSV_DIGEST,		"fsverity_digest=%s"},
+	{IPE_PROP_FSV_SIG_FALSE,	"fsverity_signature=FALSE"},
+	{IPE_PROP_FSV_SIG_TRUE,		"fsverity_signature=TRUE"},
+	{IPE_PROP_INVALID,		NULL}
+};
+
+/**
+ * parse_property() - Parse a rule property given a token string.
+ * @t: Supplies the token string to be parsed.
+ * @r: Supplies the ipe_rule the parsed property will be associated with.
+ *
+ * This function parses and associates a property with an IPE rule based
+ * on a token string.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-ENOMEM	- Out of memory (OOM)
+ * * %-EBADMSG	- The supplied token cannot be parsed
+ */
+static int parse_property(char *t, struct ipe_rule *r)
+{
+	substring_t args[MAX_OPT_ARGS];
+	struct ipe_prop *p = NULL;
+	int rc = 0;
+	int token;
+	char *dup = NULL;
+
+	p = kzalloc_obj(*p);
+	if (!p)
+		return -ENOMEM;
+
+	token = match_token(t, property_tokens, args);
+
+	switch (token) {
+	case IPE_PROP_DMV_ROOTHASH:
+	case IPE_PROP_FSV_DIGEST:
+		dup = match_strdup(&args[0]);
+		if (!dup) {
+			rc = -ENOMEM;
+			goto err;
+		}
+		p->value = ipe_digest_parse(dup);
+		if (IS_ERR(p->value)) {
+			rc = PTR_ERR(p->value);
+			goto err;
+		}
+		fallthrough;
+	case IPE_PROP_BOOT_VERIFIED_FALSE:
+	case IPE_PROP_BOOT_VERIFIED_TRUE:
+	case IPE_PROP_DMV_SIG_FALSE:
+	case IPE_PROP_DMV_SIG_TRUE:
+	case IPE_PROP_FSV_SIG_FALSE:
+	case IPE_PROP_FSV_SIG_TRUE:
+		p->type = token;
+		break;
+	default:
+		rc = -EBADMSG;
+		break;
+	}
+	if (rc)
+		goto err;
+	list_add_tail(&p->next, &r->props);
+
+out:
+	kfree(dup);
+	return rc;
+err:
+	kfree(p);
+	goto out;
+}
+
+/**
+ * parse_rule() - parse a policy rule line.
+ * @line: Supplies rule line to be parsed.
+ * @p: Supplies the partial parsed policy.
+ *
+ * Return:
+ * * 0		- Success
+ * * %-ENOMEM	- Out of memory (OOM)
+ * * %-EBADMSG	- Policy syntax error
+ */
+static int parse_rule(char *line, struct ipe_parsed_policy *p)
+{
+	enum ipe_action_type action = IPE_ACTION_INVALID;
+	enum ipe_op_type op = IPE_OP_INVALID;
+	bool is_default_rule = false;
+	struct ipe_rule *r = NULL;
+	bool first_token = true;
+	bool op_parsed = false;
+	int rc = 0;
+	char *t;
+
+	if (IS_ERR_OR_NULL(line))
+		return -EBADMSG;
+
+	r = kzalloc_obj(*r);
+	if (!r)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&r->next);
+	INIT_LIST_HEAD(&r->props);
+
+	while (t = strsep(&line, IPE_POLICY_DELIM), line) {
+		if (*t == '\0')
+			continue;
+		if (first_token && token_default(t)) {
+			is_default_rule = true;
+		} else {
+			if (!op_parsed) {
+				op = parse_operation(t);
+				if (op == IPE_OP_INVALID)
+					rc = -EBADMSG;
+				else
+					op_parsed = true;
+			} else {
+				rc = parse_property(t, r);
+			}
+		}
+
+		if (rc)
+			goto err;
+		first_token = false;
+	}
+
+	action = parse_action(t);
+	if (action == IPE_ACTION_INVALID) {
+		rc = -EBADMSG;
+		goto err;
+	}
+
+	if (is_default_rule) {
+		if (!list_empty(&r->props)) {
+			rc = -EBADMSG;
+		} else if (op == IPE_OP_INVALID) {
+			if (p->global_default_action != IPE_ACTION_INVALID)
+				rc = -EBADMSG;
+			else
+				p->global_default_action = action;
+		} else {
+			if (p->rules[op].default_action != IPE_ACTION_INVALID)
+				rc = -EBADMSG;
+			else
+				p->rules[op].default_action = action;
+		}
+	} else if (op != IPE_OP_INVALID && action != IPE_ACTION_INVALID) {
+		r->op = op;
+		r->action = action;
+	} else {
+		rc = -EBADMSG;
+	}
+
+	if (rc)
+		goto err;
+	if (!is_default_rule)
+		list_add_tail(&r->next, &p->rules[op].rules);
+	else
+		free_rule(r);
+
+	return rc;
+err:
+	free_rule(r);
+	return rc;
+}
+
+/**
+ * ipe_free_parsed_policy() - free a parsed policy structure.
+ * @p: Supplies the parsed policy.
+ */
+void ipe_free_parsed_policy(struct ipe_parsed_policy *p)
+{
+	struct ipe_rule *pp, *t;
+	size_t i = 0;
+
+	if (IS_ERR_OR_NULL(p))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(p->rules); ++i)
+		list_for_each_entry_safe(pp, t, &p->rules[i].rules, next) {
+			list_del(&pp->next);
+			free_rule(pp);
+		}
+
+	kfree(p->name);
+	kfree(p);
+}
+
+/**
+ * validate_policy() - validate a parsed policy.
+ * @p: Supplies the fully parsed policy.
+ *
+ * Given a policy structure that was just parsed, validate that all
+ * operations have their default rules or a global default rule is set.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EBADMSG	- Policy is invalid
+ */
+static int validate_policy(const struct ipe_parsed_policy *p)
+{
+	size_t i = 0;
+
+	if (p->global_default_action != IPE_ACTION_INVALID)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(p->rules); ++i) {
+		if (p->rules[i].default_action == IPE_ACTION_INVALID)
+			return -EBADMSG;
+	}
+
+	return 0;
+}
+
+/**
+ * ipe_parse_policy() - Given a string, parse the string into an IPE policy.
+ * @p: partially filled ipe_policy structure to populate with the result.
+ *     it must have text and textlen set.
+ *
+ * Return:
+ * * %0		- Success
+ * * %-EBADMSG	- Policy is invalid
+ * * %-ENOMEM	- Out of Memory
+ * * %-ERANGE	- Policy version number overflow
+ * * %-EINVAL	- Policy version parsing error
+ */
+int ipe_parse_policy(struct ipe_policy *p)
+{
+	struct ipe_parsed_policy *pp = NULL;
+	char *policy = NULL, *dup = NULL;
+	bool header_parsed = false;
+	char *line = NULL;
+	size_t len;
+	int rc = 0;
+
+	if (!p->textlen)
+		return -EBADMSG;
+
+	policy = kmemdup_nul(p->text, p->textlen, GFP_KERNEL);
+	if (!policy)
+		return -ENOMEM;
+	dup = policy;
+
+	pp = new_parsed_policy();
+	if (IS_ERR(pp)) {
+		rc = PTR_ERR(pp);
+		goto out;
+	}
+
+	while ((line = strsep(&policy, IPE_LINE_DELIM)) != NULL) {
+		remove_comment(line);
+		len = remove_trailing_spaces(line);
+		if (!len)
+			continue;
+
+		if (!header_parsed) {
+			rc = parse_header(line, pp);
+			if (rc)
+				goto err;
+			header_parsed = true;
+		} else {
+			rc = parse_rule(line, pp);
+			if (rc)
+				goto err;
+		}
+	}
+
+	if (!header_parsed || validate_policy(pp)) {
+		rc = -EBADMSG;
+		goto err;
+	}
+
+	p->parsed = pp;
+
+out:
+	kfree(dup);
+	return rc;
+err:
+	ipe_free_parsed_policy(pp);
+	goto out;
+}
diff --git a/security/ipe/policy_parser.h b/security/ipe/policy_parser.h
new file mode 100644
index 000000000..62b620901
--- /dev/null
+++ b/security/ipe/policy_parser.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+#ifndef _IPE_POLICY_PARSER_H
+#define _IPE_POLICY_PARSER_H
+
+int ipe_parse_policy(struct ipe_policy *p);
+void ipe_free_parsed_policy(struct ipe_parsed_policy *p);
+
+#endif /* _IPE_POLICY_PARSER_H */
diff --git a/security/ipe/policy_tests.c b/security/ipe/policy_tests.c
new file mode 100644
index 000000000..5f1654dee
--- /dev/null
+++ b/security/ipe/policy_tests.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020-2024 Microsoft Corporation. All rights reserved.
+ */
+
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <kunit/test.h>
+#include "policy.h"
+struct policy_case {
+	const char *const policy;
+	int errno;
+	const char *const desc;
+};
+
+static const struct policy_case policy_cases[] = {
+	{
+		"policy_name=allowall policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW",
+		0,
+		"basic",
+	},
+	{
+		"policy_name=trailing_comment policy_version=152.0.0 #This is comment\n"
+		"DEFAULT action=ALLOW",
+		0,
+		"trailing comment",
+	},
+	{
+		"policy_name=allowallnewline policy_version=0.2.0\n"
+		"DEFAULT action=ALLOW\n"
+		"\n",
+		0,
+		"trailing newline",
+	},
+	{
+		"policy_name=carriagereturnlinefeed policy_version=0.0.1\n"
+		"DEFAULT action=ALLOW\n"
+		"\r\n",
+		0,
+		"clrf newline",
+	},
+	{
+		"policy_name=whitespace policy_version=0.0.0\n"
+		"DEFAULT\taction=ALLOW\n"
+		"     \t     DEFAULT \t    op=EXECUTE      action=DENY\n"
+		"op=EXECUTE boot_verified=TRUE action=ALLOW\n"
+		"# this is a\tcomment\t\t\t\t\n"
+		"DEFAULT \t op=KMODULE\t\t\t  action=DENY\r\n"
+		"op=KMODULE boot_verified=TRUE action=ALLOW\n",
+		0,
+		"various whitespaces and nested default",
+	},
+	{
+		"policy_name=boot_verified policy_version=-1236.0.0\n"
+		"DEFAULT\taction=ALLOW\n",
+		-EINVAL,
+		"negative version",
+	},
+	{
+		"policy_name=$@!*&^%%\\:;{}() policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW",
+		0,
+		"special characters",
+	},
+	{
+		"policy_name=test policy_version=999999.0.0\n"
+		"DEFAULT action=ALLOW",
+		-ERANGE,
+		"overflow version",
+	},
+	{
+		"policy_name=test policy_version=255.0\n"
+		"DEFAULT action=ALLOW",
+		-EBADMSG,
+		"incomplete version",
+	},
+	{
+		"policy_name=test policy_version=111.0.0.0\n"
+		"DEFAULT action=ALLOW",
+		-EBADMSG,
+		"extra version",
+	},
+	{
+		"",
+		-EBADMSG,
+		"0-length policy",
+	},
+	{
+		"policy_name=test\0policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW",
+		-EBADMSG,
+		"random null in header",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"\0DEFAULT action=ALLOW",
+		-EBADMSG,
+		"incomplete policy from NULL",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=DENY\n\0"
+		"op=EXECUTE dmverity_signature=TRUE action=ALLOW\n",
+		0,
+		"NULL truncates policy",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE dmverity_signature=abc action=ALLOW",
+		-EBADMSG,
+		"invalid property type",
+	},
+	{
+		"DEFAULT action=ALLOW",
+		-EBADMSG,
+		"missing policy header",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n",
+		-EBADMSG,
+		"missing default definition",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"dmverity_signature=TRUE op=EXECUTE action=ALLOW",
+		-EBADMSG,
+		"invalid rule ordering"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"action=ALLOW op=EXECUTE dmverity_signature=TRUE",
+		-EBADMSG,
+		"invalid rule ordering (2)",
+	},
+	{
+		"policy_name=test policy_version=0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE dmverity_signature=TRUE action=ALLOW",
+		-EBADMSG,
+		"invalid version",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=UNKNOWN dmverity_signature=TRUE action=ALLOW",
+		-EBADMSG,
+		"unknown operation",
+	},
+	{
+		"policy_name=asdvpolicy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n",
+		-EBADMSG,
+		"missing space after policy name",
+	},
+	{
+		"policy_name=test\xFF\xEF policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE dmverity_signature=TRUE action=ALLOW",
+		0,
+		"expanded ascii",
+	},
+	{
+		"policy_name=test\xFF\xEF policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE dmverity_roothash=GOOD_DOG action=ALLOW",
+		-EBADMSG,
+		"invalid property value (2)",
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"policy_name=test policy_version=0.1.0\n"
+		"DEFAULT action=ALLOW",
+		-EBADMSG,
+		"double header"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"DEFAULT action=ALLOW\n",
+		-EBADMSG,
+		"double default"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"DEFAULT op=EXECUTE action=DENY\n"
+		"DEFAULT op=EXECUTE action=ALLOW\n",
+		-EBADMSG,
+		"double operation default"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"DEFAULT op=EXECUTE action=DEN\n",
+		-EBADMSG,
+		"invalid action value"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"DEFAULT op=EXECUTE action\n",
+		-EBADMSG,
+		"invalid action value (2)"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"UNKNOWN value=true\n",
+		-EBADMSG,
+		"unrecognized statement"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE dmverity_roothash=1c0d7ee1f8343b7fbe418378e8eb22c061d7dec7 action=DENY\n",
+		-EBADMSG,
+		"old-style digest"
+	},
+	{
+		"policy_name=test policy_version=0.0.0\n"
+		"DEFAULT action=ALLOW\n"
+		"op=EXECUTE fsverity_digest=1c0d7ee1f8343b7fbe418378e8eb22c061d7dec7 action=DENY\n",
+		-EBADMSG,
+		"old-style digest"
+	}
+};
+
+static void pol_to_desc(const struct policy_case *c, char *desc)
+{
+	strscpy(desc, c->desc, KUNIT_PARAM_DESC_SIZE);
+}
+
+KUNIT_ARRAY_PARAM(ipe_policies, policy_cases, pol_to_desc);
+
+/**
+ * ipe_parser_unsigned_test - Test the parser by passing unsigned policies.
+ * @test: Supplies a pointer to a kunit structure.
+ *
+ * This is called by the kunit harness. This test does not check the correctness
+ * of the policy, but ensures that errors are handled correctly.
+ */
+static void ipe_parser_unsigned_test(struct kunit *test)
+{
+	const struct policy_case *p = test->param_value;
+	struct ipe_policy *pol;
+
+	pol = ipe_new_policy(p->policy, strlen(p->policy), NULL, 0);
+
+	if (p->errno) {
+		KUNIT_EXPECT_EQ(test, PTR_ERR(pol), p->errno);
+		return;
+	}
+
+	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, pol);
+	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, pol->parsed);
+	KUNIT_EXPECT_STREQ(test, pol->text, p->policy);
+	KUNIT_EXPECT_PTR_EQ(test, NULL, pol->pkcs7);
+	KUNIT_EXPECT_EQ(test, 0, pol->pkcs7len);
+
+	ipe_free_policy(pol);
+}
+
+/**
+ * ipe_parser_widestring_test - Ensure parser fail on a wide string policy.
+ * @test: Supplies a pointer to a kunit structure.
+ *
+ * This is called by the kunit harness.
+ */
+static void ipe_parser_widestring_test(struct kunit *test)
+{
+	const unsigned short policy[] = L"policy_name=Test policy_version=0.0.0\n"
+					L"DEFAULT action=ALLOW";
+	struct ipe_policy *pol = NULL;
+
+	pol = ipe_new_policy((const char *)policy, (ARRAY_SIZE(policy) - 1) * 2, NULL, 0);
+	KUNIT_EXPECT_TRUE(test, IS_ERR_OR_NULL(pol));
+
+	ipe_free_policy(pol);
+}
+
+static struct kunit_case ipe_parser_test_cases[] = {
+	KUNIT_CASE_PARAM(ipe_parser_unsigned_test, ipe_policies_gen_params),
+	KUNIT_CASE(ipe_parser_widestring_test),
+	{ }
+};
+
+static struct kunit_suite ipe_parser_test_suite = {
+	.name = "ipe-parser",
+	.test_cases = ipe_parser_test_cases,
+};
+
+kunit_test_suite(ipe_parser_test_suite);
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
new file mode 100644
index 000000000..f4510d8cb
--- /dev/null
+++ b/security/keys/Kconfig
@@ -0,0 +1,131 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Key management configuration
+#
+
+menuconfig KEYS
+	bool "Enable access key retention support"
+	select ASSOCIATIVE_ARRAY
+	help
+	  This option provides support for retaining authentication tokens and
+	  access keys in the kernel.
+
+	  It also includes provision of methods by which such keys might be
+	  associated with a process so that network filesystems, encryption
+	  support and the like can find them.
+
+	  Furthermore, a special type of key is available that acts as keyring:
+	  a searchable sequence of keys. Each process is equipped with access
+	  to five standard keyrings: UID-specific, GID-specific, session,
+	  process and thread.
+
+	  If you are unsure as to whether this is required, answer N.
+
+if KEYS
+
+config KEYS_REQUEST_CACHE
+	bool "Enable temporary caching of the last request_key() result"
+	help
+	  This option causes the result of the last successful request_key()
+	  call that didn't upcall to the kernel to be cached temporarily in the
+	  task_struct.  The cache is cleared by exit and just prior to the
+	  resumption of userspace.
+
+	  This allows the key used for multiple step processes where each step
+	  wants to request a key that is likely the same as the one requested
+	  by the last step to save on the searching.
+
+	  An example of such a process is a pathwalk through a network
+	  filesystem in which each method needs to request an authentication
+	  key.  Pathwalk will call multiple methods for each dentry traversed
+	  (permission, d_revalidate, lookup, getxattr, getacl, ...).
+
+config PERSISTENT_KEYRINGS
+	bool "Enable register of persistent per-UID keyrings"
+	help
+	  This option provides a register of persistent per-UID keyrings,
+	  primarily aimed at Kerberos key storage.  The keyrings are persistent
+	  in the sense that they stay around after all processes of that UID
+	  have exited, not that they survive the machine being rebooted.
+
+	  A particular keyring may be accessed by either the user whose keyring
+	  it is or by a process with administrative privileges.  The active
+	  LSMs gets to rule on which admin-level processes get to access the
+	  cache.
+
+	  Keyrings are created and added into the register upon demand and get
+	  removed if they expire (a default timeout is set upon creation).
+
+config BIG_KEYS
+	bool "Large payload keys"
+	depends on TMPFS
+	select CRYPTO_LIB_CHACHA20POLY1305
+	help
+	  This option provides support for holding large keys within the kernel
+	  (for example Kerberos ticket caches).  The data may be stored out to
+	  swapspace by tmpfs.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config TRUSTED_KEYS
+	tristate "TRUSTED KEYS"
+	help
+	  This option provides support for creating, sealing, and unsealing
+	  keys in the kernel. Trusted keys are random number symmetric keys,
+	  generated and sealed by a trust source selected at kernel boot-time.
+	  Userspace will only ever see encrypted blobs.
+
+	  If you are unsure as to whether this is required, answer N.
+
+if TRUSTED_KEYS
+source "security/keys/trusted-keys/Kconfig"
+endif
+
+config ENCRYPTED_KEYS
+	tristate "ENCRYPTED KEYS"
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_LIB_SHA256
+	help
+	  This option provides support for create/encrypting/decrypting keys
+	  in the kernel.  Encrypted keys are instantiated using kernel
+	  generated random numbers or provided decrypted data, and are
+	  encrypted/decrypted with a 'master' symmetric key. The 'master'
+	  key can be either a trusted-key or user-key type. Only encrypted
+	  blobs are ever output to Userspace.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config USER_DECRYPTED_DATA
+	bool "Allow encrypted keys with user decrypted data"
+	depends on ENCRYPTED_KEYS
+	help
+	  This option provides support for instantiating encrypted keys using
+	  user-provided decrypted data.  The decrypted data must be hex-ascii
+	  encoded.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config KEY_DH_OPERATIONS
+       bool "Diffie-Hellman operations on retained keys"
+       select CRYPTO
+       select CRYPTO_KDF800108_CTR
+       select CRYPTO_DH
+       help
+	 This option provides support for calculating Diffie-Hellman
+	 public keys and shared secrets using values stored as keys
+	 in the kernel.
+
+	 If you are unsure as to whether this is required, answer N.
+
+config KEY_NOTIFICATIONS
+	bool "Provide key/keyring change notifications"
+	depends on WATCH_QUEUE
+	help
+	  This option provides support for getting change notifications
+	  on keys and keyrings on which the caller has View permission.
+	  This makes use of pipes to handle the notification buffer and
+	  provides KEYCTL_WATCH_KEY to enable/disable watches.
+
+endif # KEYS
diff --git a/security/keys/Makefile b/security/keys/Makefile
new file mode 100644
index 000000000..5f40807f0
--- /dev/null
+++ b/security/keys/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for key management
+#
+
+#
+# Core
+#
+obj-y := \
+	gc.o \
+	key.o \
+	keyring.o \
+	keyctl.o \
+	permission.o \
+	process_keys.o \
+	request_key.o \
+	request_key_auth.o \
+	user_defined.o
+compat-obj-$(CONFIG_KEY_DH_OPERATIONS) += compat_dh.o
+obj-$(CONFIG_COMPAT) += compat.o $(compat-obj-y)
+obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_SYSCTL) += sysctl.o
+obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o
+obj-$(CONFIG_KEY_DH_OPERATIONS) += dh.o
+obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += keyctl_pkey.o
+
+#
+# Key types
+#
+obj-$(CONFIG_BIG_KEYS) += big_key.o
+obj-$(CONFIG_TRUSTED_KEYS) += trusted-keys/
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
new file mode 100644
index 000000000..268f702df
--- /dev/null
+++ b/security/keys/big_key.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Large capacity key type
+ *
+ * Copyright (C) 2017-2020 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define pr_fmt(fmt) "big_key: "fmt
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <linux/random.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+#include <crypto/chacha20poly1305.h>
+
+/*
+ * Layout of key payload words.
+ */
+struct big_key_payload {
+	u8 *data;
+	struct path path;
+	size_t length;
+};
+#define to_big_key_payload(payload)			\
+	(struct big_key_payload *)((payload).data)
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+	.name			= "big_key",
+	.preparse		= big_key_preparse,
+	.free_preparse		= big_key_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.revoke			= big_key_revoke,
+	.destroy		= big_key_destroy,
+	.describe		= big_key_describe,
+	.read			= big_key_read,
+	.update			= big_key_update,
+};
+
+/*
+ * Preparse a big key
+ */
+int big_key_preparse(struct key_preparsed_payload *prep)
+{
+	struct big_key_payload *payload = to_big_key_payload(prep->payload);
+	struct file *file;
+	u8 *buf, *enckey;
+	ssize_t written;
+	size_t datalen = prep->datalen;
+	size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*payload) != sizeof(prep->payload.data));
+
+	if (datalen == 0 || datalen > 1024 * 1024 || !prep->data)
+		return -EINVAL;
+
+	/* Set an arbitrary quota */
+	prep->quotalen = 16;
+
+	payload->length = datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		/* Create a shmem file to store the data in.  This will permit the data
+		 * to be swapped out if needed.
+		 *
+		 * File content is stored encrypted with randomly generated key.
+		 * Since the key is random for each file, we can set the nonce
+		 * to zero, provided we never define a ->update() call.
+		 */
+		loff_t pos = 0;
+
+		buf = kvmalloc(enclen, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		/* generate random key */
+		enckey = kmalloc(CHACHA20POLY1305_KEY_SIZE, GFP_KERNEL);
+		if (!enckey) {
+			ret = -ENOMEM;
+			goto error;
+		}
+		ret = get_random_bytes_wait(enckey, CHACHA20POLY1305_KEY_SIZE);
+		if (unlikely(ret))
+			goto err_enckey;
+
+		/* encrypt data */
+		chacha20poly1305_encrypt(buf, prep->data, datalen, NULL, 0,
+					 0, enckey);
+
+		/* save aligned data to file */
+		file = shmem_kernel_file_setup("", enclen, EMPTY_VMA_FLAGS);
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
+			goto err_enckey;
+		}
+
+		written = kernel_write(file, buf, enclen, &pos);
+		if (written != enclen) {
+			ret = written;
+			if (written >= 0)
+				ret = -EIO;
+			goto err_fput;
+		}
+
+		/* Pin the mount and dentry to the key so that we can open it again
+		 * later
+		 */
+		payload->data = enckey;
+		payload->path = file->f_path;
+		path_get(&payload->path);
+		fput(file);
+		kvfree_sensitive(buf, enclen);
+	} else {
+		/* Just store the data in a buffer */
+		void *data = kmalloc(datalen, GFP_KERNEL);
+
+		if (!data)
+			return -ENOMEM;
+
+		payload->data = data;
+		memcpy(data, prep->data, prep->datalen);
+	}
+	return 0;
+
+err_fput:
+	fput(file);
+err_enckey:
+	kfree_sensitive(enckey);
+error:
+	kvfree_sensitive(buf, enclen);
+	return ret;
+}
+
+/*
+ * Clear preparsement.
+ */
+void big_key_free_preparse(struct key_preparsed_payload *prep)
+{
+	struct big_key_payload *payload = to_big_key_payload(prep->payload);
+
+	if (prep->datalen > BIG_KEY_FILE_THRESHOLD)
+		path_put(&payload->path);
+	kfree_sensitive(payload->data);
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+	if (key_is_positive(key) && payload->length > BIG_KEY_FILE_THRESHOLD)
+		vfs_truncate(&payload->path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	if (payload->length > BIG_KEY_FILE_THRESHOLD) {
+		path_put(&payload->path);
+		payload->path.mnt = NULL;
+		payload->path.dentry = NULL;
+	}
+	kfree_sensitive(payload->data);
+	payload->data = NULL;
+}
+
+/*
+ * Update a big key
+ */
+int big_key_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	int ret;
+
+	ret = key_payload_reserve(key, prep->datalen);
+	if (ret < 0)
+		return ret;
+
+	if (key_is_positive(key))
+		big_key_destroy(key);
+
+	return generic_key_instantiate(key, prep);
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+
+	seq_puts(m, key->description);
+
+	if (key_is_positive(key))
+		seq_printf(m, ": %zu [%s]",
+			   payload->length,
+			   payload->length > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char *buffer, size_t buflen)
+{
+	struct big_key_payload *payload = to_big_key_payload(key->payload);
+	size_t datalen = payload->length;
+	long ret;
+
+	if (!buffer || buflen < datalen)
+		return datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct file *file;
+		u8 *buf, *enckey = payload->data;
+		size_t enclen = datalen + CHACHA20POLY1305_AUTHTAG_SIZE;
+		loff_t pos = 0;
+
+		buf = kvmalloc(enclen, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		file = dentry_open(&payload->path, O_RDONLY, current_cred());
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
+			goto error;
+		}
+
+		/* read file to kernel and decrypt */
+		ret = kernel_read(file, buf, enclen, &pos);
+		if (ret != enclen) {
+			if (ret >= 0)
+				ret = -EIO;
+			goto err_fput;
+		}
+
+		ret = chacha20poly1305_decrypt(buf, buf, enclen, NULL, 0, 0,
+					       enckey) ? 0 : -EBADMSG;
+		if (unlikely(ret))
+			goto err_fput;
+
+		ret = datalen;
+
+		/* copy out decrypted data */
+		memcpy(buffer, buf, datalen);
+
+err_fput:
+		fput(file);
+error:
+		kvfree_sensitive(buf, enclen);
+	} else {
+		ret = datalen;
+		memcpy(buffer, payload->data, datalen);
+	}
+
+	return ret;
+}
+
+/*
+ * Register key type
+ */
+static int __init big_key_init(void)
+{
+	return register_key_type(&key_type_big_key);
+}
+
+late_initcall(big_key_init);
diff --git a/security/keys/compat.c b/security/keys/compat.c
new file mode 100644
index 000000000..1545efdca
--- /dev/null
+++ b/security/keys/compat.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 32-bit compatibility syscall for 64-bit systems
+ *
+ * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/syscalls.h>
+#include <linux/keyctl.h>
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * The key control system call, 32-bit compatibility version for 64-bit archs
+ */
+COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
+		       u32, arg2, u32, arg3, u32, arg4, u32, arg5)
+{
+	switch (option) {
+	case KEYCTL_GET_KEYRING_ID:
+		return keyctl_get_keyring_ID(arg2, arg3);
+
+	case KEYCTL_JOIN_SESSION_KEYRING:
+		return keyctl_join_session_keyring(compat_ptr(arg2));
+
+	case KEYCTL_UPDATE:
+		return keyctl_update_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_REVOKE:
+		return keyctl_revoke_key(arg2);
+
+	case KEYCTL_DESCRIBE:
+		return keyctl_describe_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_CLEAR:
+		return keyctl_keyring_clear(arg2);
+
+	case KEYCTL_LINK:
+		return keyctl_keyring_link(arg2, arg3);
+
+	case KEYCTL_UNLINK:
+		return keyctl_keyring_unlink(arg2, arg3);
+
+	case KEYCTL_SEARCH:
+		return keyctl_keyring_search(arg2, compat_ptr(arg3),
+					     compat_ptr(arg4), arg5);
+
+	case KEYCTL_READ:
+		return keyctl_read_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_CHOWN:
+		return keyctl_chown_key(arg2, arg3, arg4);
+
+	case KEYCTL_SETPERM:
+		return keyctl_setperm_key(arg2, arg3);
+
+	case KEYCTL_INSTANTIATE:
+		return keyctl_instantiate_key(arg2, compat_ptr(arg3), arg4,
+					      arg5);
+
+	case KEYCTL_NEGATE:
+		return keyctl_negate_key(arg2, arg3, arg4);
+
+	case KEYCTL_SET_REQKEY_KEYRING:
+		return keyctl_set_reqkey_keyring(arg2);
+
+	case KEYCTL_SET_TIMEOUT:
+		return keyctl_set_timeout(arg2, arg3);
+
+	case KEYCTL_ASSUME_AUTHORITY:
+		return keyctl_assume_authority(arg2);
+
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_SESSION_TO_PARENT:
+		return keyctl_session_to_parent();
+
+	case KEYCTL_REJECT:
+		return keyctl_reject_key(arg2, arg3, arg4, arg5);
+
+	case KEYCTL_INSTANTIATE_IOV:
+		return keyctl_instantiate_key_iov(arg2, compat_ptr(arg3), arg4,
+						  arg5);
+
+	case KEYCTL_INVALIDATE:
+		return keyctl_invalidate_key(arg2);
+
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent(arg2, arg3);
+
+	case KEYCTL_DH_COMPUTE:
+		return compat_keyctl_dh_compute(compat_ptr(arg2),
+						compat_ptr(arg3),
+						arg4, compat_ptr(arg5));
+
+	case KEYCTL_RESTRICT_KEYRING:
+		return keyctl_restrict_keyring(arg2, compat_ptr(arg3),
+					       compat_ptr(arg4));
+
+	case KEYCTL_PKEY_QUERY:
+		if (arg3 != 0)
+			return -EINVAL;
+		return keyctl_pkey_query(arg2,
+					 compat_ptr(arg4),
+					 compat_ptr(arg5));
+
+	case KEYCTL_PKEY_ENCRYPT:
+	case KEYCTL_PKEY_DECRYPT:
+	case KEYCTL_PKEY_SIGN:
+		return keyctl_pkey_e_d_s(option,
+					 compat_ptr(arg2), compat_ptr(arg3),
+					 compat_ptr(arg4), compat_ptr(arg5));
+
+	case KEYCTL_PKEY_VERIFY:
+		return keyctl_pkey_verify(compat_ptr(arg2), compat_ptr(arg3),
+					  compat_ptr(arg4), compat_ptr(arg5));
+
+	case KEYCTL_MOVE:
+		return keyctl_keyring_move(arg2, arg3, arg4, arg5);
+
+	case KEYCTL_CAPABILITIES:
+		return keyctl_capabilities(compat_ptr(arg2), arg3);
+
+	case KEYCTL_WATCH_KEY:
+		return keyctl_watch_key(arg2, arg3, arg4);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/security/keys/compat_dh.c b/security/keys/compat_dh.c
new file mode 100644
index 000000000..19384e7e9
--- /dev/null
+++ b/security/keys/compat_dh.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* 32-bit compatibility syscall for 64-bit systems for DH operations
+ *
+ * Copyright (C) 2016 Stephan Mueller <smueller@chronox.de>
+ */
+
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+/*
+ * Perform the DH computation or DH based key derivation.
+ *
+ * If successful, 0 will be returned.
+ */
+long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params,
+			      char __user *buffer, size_t buflen,
+			      struct compat_keyctl_kdf_params __user *kdf)
+{
+	struct keyctl_kdf_params kdfcopy;
+	struct compat_keyctl_kdf_params compat_kdfcopy;
+
+	if (!kdf)
+		return __keyctl_dh_compute(params, buffer, buflen, NULL);
+
+	if (copy_from_user(&compat_kdfcopy, kdf, sizeof(compat_kdfcopy)) != 0)
+		return -EFAULT;
+
+	kdfcopy.hashname = compat_ptr(compat_kdfcopy.hashname);
+	kdfcopy.otherinfo = compat_ptr(compat_kdfcopy.otherinfo);
+	kdfcopy.otherinfolen = compat_kdfcopy.otherinfolen;
+	memcpy(kdfcopy.__spare, compat_kdfcopy.__spare,
+	       sizeof(kdfcopy.__spare));
+
+	return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy);
+}
diff --git a/security/keys/dh.c b/security/keys/dh.c
new file mode 100644
index 000000000..da64c3584
--- /dev/null
+++ b/security/keys/dh.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Crypto operations using stored keys
+ *
+ * Copyright (c) 2016, Intel Corporation
+ */
+
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/scatterlist.h>
+#include <linux/crypto.h>
+#include <crypto/hash.h>
+#include <crypto/kpp.h>
+#include <crypto/dh.h>
+#include <crypto/kdf_sp800108.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+static ssize_t dh_data_from_key(key_serial_t keyid, const void **data)
+{
+	struct key *key;
+	key_ref_t key_ref;
+	long status;
+	ssize_t ret;
+
+	key_ref = lookup_user_key(keyid, 0, KEY_NEED_READ);
+	if (IS_ERR(key_ref)) {
+		ret = -ENOKEY;
+		goto error;
+	}
+
+	key = key_ref_to_ptr(key_ref);
+
+	ret = -EOPNOTSUPP;
+	if (key->type == &key_type_user) {
+		down_read(&key->sem);
+		status = key_validate(key);
+		if (status == 0) {
+			const struct user_key_payload *payload;
+			uint8_t *duplicate;
+
+			payload = user_key_payload_locked(key);
+
+			duplicate = kmemdup(payload->data, payload->datalen,
+					    GFP_KERNEL);
+			if (duplicate) {
+				*data = duplicate;
+				ret = payload->datalen;
+			} else {
+				ret = -ENOMEM;
+			}
+		}
+		up_read(&key->sem);
+	}
+
+	key_put(key);
+error:
+	return ret;
+}
+
+static void dh_free_data(struct dh *dh)
+{
+	kfree_sensitive(dh->key);
+	kfree_sensitive(dh->p);
+	kfree_sensitive(dh->g);
+}
+
+static int kdf_alloc(struct crypto_shash **hash, char *hashname)
+{
+	struct crypto_shash *tfm;
+
+	/* allocate synchronous hash */
+	tfm = crypto_alloc_shash(hashname, 0, 0);
+	if (IS_ERR(tfm)) {
+		pr_info("could not allocate digest TFM handle %s\n", hashname);
+		return PTR_ERR(tfm);
+	}
+
+	if (crypto_shash_digestsize(tfm) == 0) {
+		crypto_free_shash(tfm);
+		return -EINVAL;
+	}
+
+	*hash = tfm;
+
+	return 0;
+}
+
+static void kdf_dealloc(struct crypto_shash *hash)
+{
+	if (hash)
+		crypto_free_shash(hash);
+}
+
+static int keyctl_dh_compute_kdf(struct crypto_shash *hash,
+				 char __user *buffer, size_t buflen,
+				 uint8_t *kbuf, size_t kbuflen)
+{
+	struct kvec kbuf_iov = { .iov_base = kbuf, .iov_len = kbuflen };
+	uint8_t *outbuf = NULL;
+	int ret;
+	size_t outbuf_len = roundup(buflen, crypto_shash_digestsize(hash));
+
+	outbuf = kmalloc(outbuf_len, GFP_KERNEL);
+	if (!outbuf) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = crypto_kdf108_ctr_generate(hash, &kbuf_iov, 1, outbuf, outbuf_len);
+	if (ret)
+		goto err;
+
+	ret = buflen;
+	if (copy_to_user(buffer, outbuf, buflen) != 0)
+		ret = -EFAULT;
+
+err:
+	kfree_sensitive(outbuf);
+	return ret;
+}
+
+long __keyctl_dh_compute(struct keyctl_dh_params __user *params,
+			 char __user *buffer, size_t buflen,
+			 struct keyctl_kdf_params *kdfcopy)
+{
+	long ret;
+	ssize_t dlen;
+	int secretlen;
+	int outlen;
+	struct keyctl_dh_params pcopy;
+	struct dh dh_inputs;
+	struct scatterlist outsg;
+	DECLARE_CRYPTO_WAIT(compl);
+	struct crypto_kpp *tfm;
+	struct kpp_request *req;
+	uint8_t *secret;
+	uint8_t *outbuf;
+	struct crypto_shash *hash = NULL;
+
+	if (!params || (!buffer && buflen)) {
+		ret = -EINVAL;
+		goto out1;
+	}
+	if (copy_from_user(&pcopy, params, sizeof(pcopy)) != 0) {
+		ret = -EFAULT;
+		goto out1;
+	}
+
+	if (kdfcopy) {
+		char *hashname;
+
+		if (memchr_inv(kdfcopy->__spare, 0, sizeof(kdfcopy->__spare))) {
+			ret = -EINVAL;
+			goto out1;
+		}
+
+		if (buflen > KEYCTL_KDF_MAX_OUTPUT_LEN ||
+		    kdfcopy->otherinfolen > KEYCTL_KDF_MAX_OI_LEN) {
+			ret = -EMSGSIZE;
+			goto out1;
+		}
+
+		/* get KDF name string */
+		hashname = strndup_user(kdfcopy->hashname, CRYPTO_MAX_ALG_NAME);
+		if (IS_ERR(hashname)) {
+			ret = PTR_ERR(hashname);
+			goto out1;
+		}
+
+		/* allocate KDF from the kernel crypto API */
+		ret = kdf_alloc(&hash, hashname);
+		kfree(hashname);
+		if (ret)
+			goto out1;
+	}
+
+	memset(&dh_inputs, 0, sizeof(dh_inputs));
+
+	dlen = dh_data_from_key(pcopy.prime, &dh_inputs.p);
+	if (dlen < 0) {
+		ret = dlen;
+		goto out1;
+	}
+	dh_inputs.p_size = dlen;
+
+	dlen = dh_data_from_key(pcopy.base, &dh_inputs.g);
+	if (dlen < 0) {
+		ret = dlen;
+		goto out2;
+	}
+	dh_inputs.g_size = dlen;
+
+	dlen = dh_data_from_key(pcopy.private, &dh_inputs.key);
+	if (dlen < 0) {
+		ret = dlen;
+		goto out2;
+	}
+	dh_inputs.key_size = dlen;
+
+	secretlen = crypto_dh_key_len(&dh_inputs);
+	secret = kmalloc(secretlen, GFP_KERNEL);
+	if (!secret) {
+		ret = -ENOMEM;
+		goto out2;
+	}
+	ret = crypto_dh_encode_key(secret, secretlen, &dh_inputs);
+	if (ret)
+		goto out3;
+
+	tfm = crypto_alloc_kpp("dh", 0, 0);
+	if (IS_ERR(tfm)) {
+		ret = PTR_ERR(tfm);
+		goto out3;
+	}
+
+	ret = crypto_kpp_set_secret(tfm, secret, secretlen);
+	if (ret)
+		goto out4;
+
+	outlen = crypto_kpp_maxsize(tfm);
+
+	if (!kdfcopy) {
+		/*
+		 * When not using a KDF, buflen 0 is used to read the
+		 * required buffer length
+		 */
+		if (buflen == 0) {
+			ret = outlen;
+			goto out4;
+		} else if (outlen > buflen) {
+			ret = -EOVERFLOW;
+			goto out4;
+		}
+	}
+
+	outbuf = kzalloc(kdfcopy ? (outlen + kdfcopy->otherinfolen) : outlen,
+			 GFP_KERNEL);
+	if (!outbuf) {
+		ret = -ENOMEM;
+		goto out4;
+	}
+
+	sg_init_one(&outsg, outbuf, outlen);
+
+	req = kpp_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		ret = -ENOMEM;
+		goto out5;
+	}
+
+	kpp_request_set_input(req, NULL, 0);
+	kpp_request_set_output(req, &outsg, outlen);
+	kpp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+				 CRYPTO_TFM_REQ_MAY_SLEEP,
+				 crypto_req_done, &compl);
+
+	/*
+	 * For DH, generate_public_key and generate_shared_secret are
+	 * the same calculation
+	 */
+	ret = crypto_kpp_generate_public_key(req);
+	ret = crypto_wait_req(ret, &compl);
+	if (ret)
+		goto out6;
+
+	if (kdfcopy) {
+		/*
+		 * Concatenate SP800-56A otherinfo past DH shared secret -- the
+		 * input to the KDF is (DH shared secret || otherinfo)
+		 */
+		if (copy_from_user(outbuf + req->dst_len, kdfcopy->otherinfo,
+				   kdfcopy->otherinfolen) != 0) {
+			ret = -EFAULT;
+			goto out6;
+		}
+
+		ret = keyctl_dh_compute_kdf(hash, buffer, buflen, outbuf,
+					    req->dst_len + kdfcopy->otherinfolen);
+	} else if (copy_to_user(buffer, outbuf, req->dst_len) == 0) {
+		ret = req->dst_len;
+	} else {
+		ret = -EFAULT;
+	}
+
+out6:
+	kpp_request_free(req);
+out5:
+	kfree_sensitive(outbuf);
+out4:
+	crypto_free_kpp(tfm);
+out3:
+	kfree_sensitive(secret);
+out2:
+	dh_free_data(&dh_inputs);
+out1:
+	kdf_dealloc(hash);
+	return ret;
+}
+
+long keyctl_dh_compute(struct keyctl_dh_params __user *params,
+		       char __user *buffer, size_t buflen,
+		       struct keyctl_kdf_params __user *kdf)
+{
+	struct keyctl_kdf_params kdfcopy;
+
+	if (!kdf)
+		return __keyctl_dh_compute(params, buffer, buflen, NULL);
+
+	if (copy_from_user(&kdfcopy, kdf, sizeof(kdfcopy)) != 0)
+		return -EFAULT;
+
+	return __keyctl_dh_compute(params, buffer, buflen, &kdfcopy);
+}
diff --git a/security/keys/encrypted-keys/Makefile b/security/keys/encrypted-keys/Makefile
new file mode 100644
index 000000000..7a44dce6f
--- /dev/null
+++ b/security/keys/encrypted-keys/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for encrypted keys
+#
+
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys.o
+
+encrypted-keys-y := encrypted.o ecryptfs_format.o
+masterkey-$(CONFIG_TRUSTED_KEYS) := masterkey_trusted.o
+masterkey-$(CONFIG_TRUSTED_KEYS)-$(CONFIG_ENCRYPTED_KEYS) := masterkey_trusted.o
+encrypted-keys-y += $(masterkey-y) $(masterkey-m-m)
diff --git a/security/keys/encrypted-keys/ecryptfs_format.c b/security/keys/encrypted-keys/ecryptfs_format.c
new file mode 100644
index 000000000..2fc6f3a66
--- /dev/null
+++ b/security/keys/encrypted-keys/ecryptfs_format.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * ecryptfs_format.c: helper functions for the encrypted key type
+ *
+ * Copyright (C) 2006 International Business Machines Corp.
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Authors:
+ * Michael A. Halcrow <mahalcro@us.ibm.com>
+ * Tyler Hicks <tyhicks@ou.edu>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ */
+
+#include <linux/export.h>
+#include <linux/string.h>
+#include "ecryptfs_format.h"
+
+u8 *ecryptfs_get_auth_tok_key(struct ecryptfs_auth_tok *auth_tok)
+{
+	return auth_tok->token.password.session_key_encryption_key;
+}
+EXPORT_SYMBOL(ecryptfs_get_auth_tok_key);
+
+/*
+ * ecryptfs_get_versions()
+ *
+ * Source code taken from the software 'ecryptfs-utils' version 83.
+ *
+ */
+void ecryptfs_get_versions(int *major, int *minor, int *file_version)
+{
+	*major = ECRYPTFS_VERSION_MAJOR;
+	*minor = ECRYPTFS_VERSION_MINOR;
+	if (file_version)
+		*file_version = ECRYPTFS_SUPPORTED_FILE_VERSION;
+}
+EXPORT_SYMBOL(ecryptfs_get_versions);
+
+/*
+ * ecryptfs_fill_auth_tok - fill the ecryptfs_auth_tok structure
+ *
+ * Fill the ecryptfs_auth_tok structure with required ecryptfs data.
+ * The source code is inspired to the original function generate_payload()
+ * shipped with the software 'ecryptfs-utils' version 83.
+ *
+ */
+int ecryptfs_fill_auth_tok(struct ecryptfs_auth_tok *auth_tok,
+			   const char *key_desc)
+{
+	int major, minor;
+
+	ecryptfs_get_versions(&major, &minor, NULL);
+	auth_tok->version = (((uint16_t)(major << 8) & 0xFF00)
+			     | ((uint16_t)minor & 0x00FF));
+	auth_tok->token_type = ECRYPTFS_PASSWORD;
+	strscpy_pad(auth_tok->token.password.signature, key_desc);
+	auth_tok->token.password.session_key_encryption_key_bytes =
+		ECRYPTFS_MAX_KEY_BYTES;
+	/*
+	 * Removed auth_tok->token.password.salt and
+	 * auth_tok->token.password.session_key_encryption_key
+	 * initialization from the original code
+	 */
+	/* TODO: Make the hash parameterizable via policy */
+	auth_tok->token.password.flags |=
+		ECRYPTFS_SESSION_KEY_ENCRYPTION_KEY_SET;
+	/* The kernel code will encrypt the session key. */
+	auth_tok->session_key.encrypted_key[0] = 0;
+	auth_tok->session_key.encrypted_key_size = 0;
+	/* Default; subject to change by kernel eCryptfs */
+	auth_tok->token.password.hash_algo = PGP_DIGEST_ALGO_SHA512;
+	auth_tok->token.password.flags &= ~(ECRYPTFS_PERSISTENT_PASSWORD);
+	return 0;
+}
+EXPORT_SYMBOL(ecryptfs_fill_auth_tok);
diff --git a/security/keys/encrypted-keys/ecryptfs_format.h b/security/keys/encrypted-keys/ecryptfs_format.h
new file mode 100644
index 000000000..ed8466578
--- /dev/null
+++ b/security/keys/encrypted-keys/ecryptfs_format.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * ecryptfs_format.h: helper functions for the encrypted key type
+ *
+ * Copyright (C) 2006 International Business Machines Corp.
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Authors:
+ * Michael A. Halcrow <mahalcro@us.ibm.com>
+ * Tyler Hicks <tyhicks@ou.edu>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ */
+
+#ifndef __KEYS_ECRYPTFS_H
+#define __KEYS_ECRYPTFS_H
+
+#include <linux/ecryptfs.h>
+
+#define PGP_DIGEST_ALGO_SHA512   10
+
+u8 *ecryptfs_get_auth_tok_key(struct ecryptfs_auth_tok *auth_tok);
+void ecryptfs_get_versions(int *major, int *minor, int *file_version);
+int ecryptfs_fill_auth_tok(struct ecryptfs_auth_tok *auth_tok,
+			   const char *key_desc);
+
+#endif /* __KEYS_ECRYPTFS_H */
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
new file mode 100644
index 000000000..59cb77b23
--- /dev/null
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -0,0 +1,1002 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * See Documentation/security/keys/trusted-encrypted.rst
+ */
+
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/hex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <keys/trusted-type.h>
+#include <keys/encrypted-type.h>
+#include <linux/key-type.h>
+#include <linux/random.h>
+#include <linux/rcupdate.h>
+#include <linux/scatterlist.h>
+#include <linux/ctype.h>
+#include <crypto/aes.h>
+#include <crypto/sha2.h>
+#include <crypto/skcipher.h>
+#include <crypto/utils.h>
+
+#include "encrypted.h"
+#include "ecryptfs_format.h"
+
+static const char KEY_TRUSTED_PREFIX[] = "trusted:";
+static const char KEY_USER_PREFIX[] = "user:";
+static const char blkcipher_alg[] = "cbc(aes)";
+static const char key_format_default[] = "default";
+static const char key_format_ecryptfs[] = "ecryptfs";
+static const char key_format_enc32[] = "enc32";
+static unsigned int ivsize;
+static int blksize;
+
+#define KEY_TRUSTED_PREFIX_LEN (sizeof (KEY_TRUSTED_PREFIX) - 1)
+#define KEY_USER_PREFIX_LEN (sizeof (KEY_USER_PREFIX) - 1)
+#define KEY_ECRYPTFS_DESC_LEN 16
+#define HASH_SIZE SHA256_DIGEST_SIZE
+#define MAX_DATA_SIZE 4096
+#define MIN_DATA_SIZE  20
+#define KEY_ENC32_PAYLOAD_LEN 32
+
+enum {
+	Opt_new, Opt_load, Opt_update, Opt_err
+};
+
+enum {
+	Opt_default, Opt_ecryptfs, Opt_enc32, Opt_error
+};
+
+static const match_table_t key_format_tokens = {
+	{Opt_default, "default"},
+	{Opt_ecryptfs, "ecryptfs"},
+	{Opt_enc32, "enc32"},
+	{Opt_error, NULL}
+};
+
+static const match_table_t key_tokens = {
+	{Opt_new, "new"},
+	{Opt_load, "load"},
+	{Opt_update, "update"},
+	{Opt_err, NULL}
+};
+
+static bool user_decrypted_data = IS_ENABLED(CONFIG_USER_DECRYPTED_DATA);
+module_param(user_decrypted_data, bool, 0);
+MODULE_PARM_DESC(user_decrypted_data,
+	"Allow instantiation of encrypted keys using provided decrypted data");
+
+static int aes_get_sizes(void)
+{
+	struct crypto_skcipher *tfm;
+
+	tfm = crypto_alloc_skcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm)) {
+		pr_err("encrypted_key: failed to alloc_cipher (%ld)\n",
+		       PTR_ERR(tfm));
+		return PTR_ERR(tfm);
+	}
+	ivsize = crypto_skcipher_ivsize(tfm);
+	blksize = crypto_skcipher_blocksize(tfm);
+	crypto_free_skcipher(tfm);
+	return 0;
+}
+
+/*
+ * valid_ecryptfs_desc - verify the description of a new/loaded encrypted key
+ *
+ * The description of a encrypted key with format 'ecryptfs' must contain
+ * exactly 16 hexadecimal characters.
+ *
+ */
+static int valid_ecryptfs_desc(const char *ecryptfs_desc)
+{
+	int i;
+
+	if (strlen(ecryptfs_desc) != KEY_ECRYPTFS_DESC_LEN) {
+		pr_err("encrypted_key: key description must be %d hexadecimal "
+		       "characters long\n", KEY_ECRYPTFS_DESC_LEN);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < KEY_ECRYPTFS_DESC_LEN; i++) {
+		if (!isxdigit(ecryptfs_desc[i])) {
+			pr_err("encrypted_key: key description must contain "
+			       "only hexadecimal characters\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * valid_master_desc - verify the 'key-type:desc' of a new/updated master-key
+ *
+ * key-type:= "trusted:" | "user:"
+ * desc:= master-key description
+ *
+ * Verify that 'key-type' is valid and that 'desc' exists. On key update,
+ * only the master key description is permitted to change, not the key-type.
+ * The key-type remains constant.
+ *
+ * On success returns 0, otherwise -EINVAL.
+ */
+static int valid_master_desc(const char *new_desc, const char *orig_desc)
+{
+	int prefix_len;
+
+	if (!strncmp(new_desc, KEY_TRUSTED_PREFIX, KEY_TRUSTED_PREFIX_LEN))
+		prefix_len = KEY_TRUSTED_PREFIX_LEN;
+	else if (!strncmp(new_desc, KEY_USER_PREFIX, KEY_USER_PREFIX_LEN))
+		prefix_len = KEY_USER_PREFIX_LEN;
+	else
+		return -EINVAL;
+
+	if (!new_desc[prefix_len])
+		return -EINVAL;
+
+	if (orig_desc && strncmp(new_desc, orig_desc, prefix_len))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * datablob_parse - parse the keyctl data
+ *
+ * datablob format:
+ * new [<format>] <master-key name> <decrypted data length> [<decrypted data>]
+ * load [<format>] <master-key name> <decrypted data length>
+ *     <encrypted iv + data>
+ * update <new-master-key name>
+ *
+ * Tokenizes a copy of the keyctl data, returning a pointer to each token,
+ * which is null terminated.
+ *
+ * On success returns 0, otherwise -EINVAL.
+ */
+static int datablob_parse(char *datablob, const char **format,
+			  char **master_desc, char **decrypted_datalen,
+			  char **hex_encoded_iv, char **decrypted_data)
+{
+	substring_t args[MAX_OPT_ARGS];
+	int ret = -EINVAL;
+	int key_cmd;
+	int key_format;
+	char *p, *keyword;
+
+	keyword = strsep(&datablob, " \t");
+	if (!keyword) {
+		pr_info("encrypted_key: insufficient parameters specified\n");
+		return ret;
+	}
+	key_cmd = match_token(keyword, key_tokens, args);
+
+	/* Get optional format: default | ecryptfs */
+	p = strsep(&datablob, " \t");
+	if (!p) {
+		pr_err("encrypted_key: insufficient parameters specified\n");
+		return ret;
+	}
+
+	key_format = match_token(p, key_format_tokens, args);
+	switch (key_format) {
+	case Opt_ecryptfs:
+	case Opt_enc32:
+	case Opt_default:
+		*format = p;
+		*master_desc = strsep(&datablob, " \t");
+		break;
+	case Opt_error:
+		*master_desc = p;
+		break;
+	}
+
+	if (!*master_desc) {
+		pr_info("encrypted_key: master key parameter is missing\n");
+		goto out;
+	}
+
+	if (valid_master_desc(*master_desc, NULL) < 0) {
+		pr_info("encrypted_key: master key parameter \'%s\' "
+			"is invalid\n", *master_desc);
+		goto out;
+	}
+
+	if (decrypted_datalen) {
+		*decrypted_datalen = strsep(&datablob, " \t");
+		if (!*decrypted_datalen) {
+			pr_info("encrypted_key: keylen parameter is missing\n");
+			goto out;
+		}
+	}
+
+	switch (key_cmd) {
+	case Opt_new:
+		if (!decrypted_datalen) {
+			pr_info("encrypted_key: keyword \'%s\' not allowed "
+				"when called from .update method\n", keyword);
+			break;
+		}
+		*decrypted_data = strsep(&datablob, " \t");
+		ret = 0;
+		break;
+	case Opt_load:
+		if (!decrypted_datalen) {
+			pr_info("encrypted_key: keyword \'%s\' not allowed "
+				"when called from .update method\n", keyword);
+			break;
+		}
+		*hex_encoded_iv = strsep(&datablob, " \t");
+		if (!*hex_encoded_iv) {
+			pr_info("encrypted_key: hex blob is missing\n");
+			break;
+		}
+		ret = 0;
+		break;
+	case Opt_update:
+		if (decrypted_datalen) {
+			pr_info("encrypted_key: keyword \'%s\' not allowed "
+				"when called from .instantiate method\n",
+				keyword);
+			break;
+		}
+		ret = 0;
+		break;
+	case Opt_err:
+		pr_info("encrypted_key: keyword \'%s\' not recognized\n",
+			keyword);
+		break;
+	}
+out:
+	return ret;
+}
+
+/*
+ * datablob_format - format as an ascii string, before copying to userspace
+ */
+static char *datablob_format(struct encrypted_key_payload *epayload,
+			     size_t asciiblob_len)
+{
+	char *ascii_buf, *bufp;
+	u8 *iv = epayload->iv;
+	int len;
+	int i;
+
+	ascii_buf = kmalloc(asciiblob_len + 1, GFP_KERNEL);
+	if (!ascii_buf)
+		goto out;
+
+	ascii_buf[asciiblob_len] = '\0';
+
+	/* copy datablob master_desc and datalen strings */
+	len = sprintf(ascii_buf, "%s %s %s ", epayload->format,
+		      epayload->master_desc, epayload->datalen);
+
+	/* convert the hex encoded iv, encrypted-data and HMAC to ascii */
+	bufp = &ascii_buf[len];
+	for (i = 0; i < (asciiblob_len - len) / 2; i++)
+		bufp = hex_byte_pack(bufp, iv[i]);
+out:
+	return ascii_buf;
+}
+
+/*
+ * request_user_key - request the user key
+ *
+ * Use a user provided key to encrypt/decrypt an encrypted-key.
+ */
+static struct key *request_user_key(const char *master_desc, const u8 **master_key,
+				    size_t *master_keylen)
+{
+	const struct user_key_payload *upayload;
+	struct key *ukey;
+
+	ukey = request_key(&key_type_user, master_desc, NULL);
+	if (IS_ERR(ukey))
+		goto error;
+
+	down_read(&ukey->sem);
+	upayload = user_key_payload_locked(ukey);
+	if (!upayload) {
+		/* key was revoked before we acquired its semaphore */
+		up_read(&ukey->sem);
+		key_put(ukey);
+		ukey = ERR_PTR(-EKEYREVOKED);
+		goto error;
+	}
+	*master_key = upayload->data;
+	*master_keylen = upayload->datalen;
+error:
+	return ukey;
+}
+
+enum derived_key_type { ENC_KEY, AUTH_KEY };
+
+/* Derive authentication/encryption key from trusted key */
+static int get_derived_key(u8 *derived_key, enum derived_key_type key_type,
+			   const u8 *master_key, size_t master_keylen)
+{
+	u8 *derived_buf;
+	unsigned int derived_buf_len;
+
+	derived_buf_len = strlen("AUTH_KEY") + 1 + master_keylen;
+	if (derived_buf_len < HASH_SIZE)
+		derived_buf_len = HASH_SIZE;
+
+	derived_buf = kzalloc(derived_buf_len, GFP_KERNEL);
+	if (!derived_buf)
+		return -ENOMEM;
+
+	if (key_type)
+		strscpy(derived_buf, "AUTH_KEY", HASH_SIZE);
+	else
+		strscpy(derived_buf, "ENC_KEY", HASH_SIZE);
+
+	memcpy(derived_buf + strlen(derived_buf) + 1, master_key,
+	       master_keylen);
+	sha256(derived_buf, derived_buf_len, derived_key);
+	kfree_sensitive(derived_buf);
+	return 0;
+}
+
+static struct skcipher_request *init_skcipher_req(const u8 *key,
+						  unsigned int key_len)
+{
+	struct skcipher_request *req;
+	struct crypto_skcipher *tfm;
+	int ret;
+
+	tfm = crypto_alloc_skcipher(blkcipher_alg, 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm)) {
+		pr_err("encrypted_key: failed to load %s transform (%ld)\n",
+		       blkcipher_alg, PTR_ERR(tfm));
+		return ERR_CAST(tfm);
+	}
+
+	ret = crypto_skcipher_setkey(tfm, key, key_len);
+	if (ret < 0) {
+		pr_err("encrypted_key: failed to setkey (%d)\n", ret);
+		crypto_free_skcipher(tfm);
+		return ERR_PTR(ret);
+	}
+
+	req = skcipher_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		pr_err("encrypted_key: failed to allocate request for %s\n",
+		       blkcipher_alg);
+		crypto_free_skcipher(tfm);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	skcipher_request_set_callback(req, 0, NULL, NULL);
+	return req;
+}
+
+static struct key *request_master_key(struct encrypted_key_payload *epayload,
+				      const u8 **master_key, size_t *master_keylen)
+{
+	struct key *mkey = ERR_PTR(-EINVAL);
+
+	if (!strncmp(epayload->master_desc, KEY_TRUSTED_PREFIX,
+		     KEY_TRUSTED_PREFIX_LEN)) {
+		mkey = request_trusted_key(epayload->master_desc +
+					   KEY_TRUSTED_PREFIX_LEN,
+					   master_key, master_keylen);
+	} else if (!strncmp(epayload->master_desc, KEY_USER_PREFIX,
+			    KEY_USER_PREFIX_LEN)) {
+		mkey = request_user_key(epayload->master_desc +
+					KEY_USER_PREFIX_LEN,
+					master_key, master_keylen);
+	} else
+		goto out;
+
+	if (IS_ERR(mkey)) {
+		int ret = PTR_ERR(mkey);
+
+		if (ret == -ENOTSUPP)
+			pr_info("encrypted_key: key %s not supported",
+				epayload->master_desc);
+		else
+			pr_info("encrypted_key: key %s not found",
+				epayload->master_desc);
+		goto out;
+	}
+
+	dump_master_key(*master_key, *master_keylen);
+out:
+	return mkey;
+}
+
+/* Before returning data to userspace, encrypt decrypted data. */
+static int derived_key_encrypt(struct encrypted_key_payload *epayload,
+			       const u8 *derived_key,
+			       unsigned int derived_keylen)
+{
+	struct scatterlist sg_in[2];
+	struct scatterlist sg_out[1];
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
+	unsigned int encrypted_datalen;
+	u8 iv[AES_BLOCK_SIZE];
+	int ret;
+
+	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
+
+	req = init_skcipher_req(derived_key, derived_keylen);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+	dump_decrypted_data(epayload);
+
+	sg_init_table(sg_in, 2);
+	sg_set_buf(&sg_in[0], epayload->decrypted_data,
+		   epayload->decrypted_datalen);
+	sg_set_page(&sg_in[1], ZERO_PAGE(0), AES_BLOCK_SIZE, 0);
+
+	sg_init_table(sg_out, 1);
+	sg_set_buf(sg_out, epayload->encrypted_data, encrypted_datalen);
+
+	memcpy(iv, epayload->iv, sizeof(iv));
+	skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
+	ret = crypto_skcipher_encrypt(req);
+	tfm = crypto_skcipher_reqtfm(req);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	if (ret < 0)
+		pr_err("encrypted_key: failed to encrypt (%d)\n", ret);
+	else
+		dump_encrypted_data(epayload, encrypted_datalen);
+out:
+	return ret;
+}
+
+static int datablob_hmac_append(struct encrypted_key_payload *epayload,
+				const u8 *master_key, size_t master_keylen)
+{
+	u8 derived_key[HASH_SIZE];
+	u8 *digest;
+	int ret;
+
+	ret = get_derived_key(derived_key, AUTH_KEY, master_key, master_keylen);
+	if (ret < 0)
+		goto out;
+
+	digest = epayload->format + epayload->datablob_len;
+	hmac_sha256_usingrawkey(derived_key, sizeof(derived_key),
+				epayload->format, epayload->datablob_len,
+				digest);
+	dump_hmac(NULL, digest, HASH_SIZE);
+out:
+	memzero_explicit(derived_key, sizeof(derived_key));
+	return ret;
+}
+
+/* verify HMAC before decrypting encrypted key */
+static int datablob_hmac_verify(struct encrypted_key_payload *epayload,
+				const u8 *format, const u8 *master_key,
+				size_t master_keylen)
+{
+	u8 derived_key[HASH_SIZE];
+	u8 digest[HASH_SIZE];
+	int ret;
+	char *p;
+	unsigned short len;
+
+	ret = get_derived_key(derived_key, AUTH_KEY, master_key, master_keylen);
+	if (ret < 0)
+		goto out;
+
+	len = epayload->datablob_len;
+	if (!format) {
+		p = epayload->master_desc;
+		len -= strlen(epayload->format) + 1;
+	} else
+		p = epayload->format;
+
+	hmac_sha256_usingrawkey(derived_key, sizeof(derived_key), p, len,
+				digest);
+	ret = crypto_memneq(digest, epayload->format + epayload->datablob_len,
+			    sizeof(digest));
+	if (ret) {
+		ret = -EINVAL;
+		dump_hmac("datablob",
+			  epayload->format + epayload->datablob_len,
+			  HASH_SIZE);
+		dump_hmac("calc", digest, HASH_SIZE);
+	}
+out:
+	memzero_explicit(derived_key, sizeof(derived_key));
+	return ret;
+}
+
+static int derived_key_decrypt(struct encrypted_key_payload *epayload,
+			       const u8 *derived_key,
+			       unsigned int derived_keylen)
+{
+	struct scatterlist sg_in[1];
+	struct scatterlist sg_out[2];
+	struct crypto_skcipher *tfm;
+	struct skcipher_request *req;
+	unsigned int encrypted_datalen;
+	u8 iv[AES_BLOCK_SIZE];
+	u8 *pad;
+	int ret;
+
+	/* Throwaway buffer to hold the unused zero padding at the end */
+	pad = kmalloc(AES_BLOCK_SIZE, GFP_KERNEL);
+	if (!pad)
+		return -ENOMEM;
+
+	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
+	req = init_skcipher_req(derived_key, derived_keylen);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+	dump_encrypted_data(epayload, encrypted_datalen);
+
+	sg_init_table(sg_in, 1);
+	sg_init_table(sg_out, 2);
+	sg_set_buf(sg_in, epayload->encrypted_data, encrypted_datalen);
+	sg_set_buf(&sg_out[0], epayload->decrypted_data,
+		   epayload->decrypted_datalen);
+	sg_set_buf(&sg_out[1], pad, AES_BLOCK_SIZE);
+
+	memcpy(iv, epayload->iv, sizeof(iv));
+	skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
+	ret = crypto_skcipher_decrypt(req);
+	tfm = crypto_skcipher_reqtfm(req);
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+	if (ret < 0)
+		goto out;
+	dump_decrypted_data(epayload);
+out:
+	kfree(pad);
+	return ret;
+}
+
+/* Allocate memory for decrypted key and datablob. */
+static struct encrypted_key_payload *encrypted_key_alloc(struct key *key,
+							 const char *format,
+							 const char *master_desc,
+							 const char *datalen,
+							 const char *decrypted_data)
+{
+	struct encrypted_key_payload *epayload = NULL;
+	unsigned short datablob_len;
+	unsigned short decrypted_datalen;
+	unsigned short payload_datalen;
+	unsigned int encrypted_datalen;
+	unsigned int format_len;
+	long dlen;
+	int i;
+	int ret;
+
+	ret = kstrtol(datalen, 10, &dlen);
+	if (ret < 0 || dlen < MIN_DATA_SIZE || dlen > MAX_DATA_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	format_len = (!format) ? strlen(key_format_default) : strlen(format);
+	decrypted_datalen = dlen;
+	payload_datalen = decrypted_datalen;
+
+	if (decrypted_data) {
+		if (!user_decrypted_data) {
+			pr_err("encrypted key: instantiation of keys using provided decrypted data is disabled since CONFIG_USER_DECRYPTED_DATA is set to false\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (strlen(decrypted_data) != decrypted_datalen * 2) {
+			pr_err("encrypted key: decrypted data provided does not match decrypted data length provided\n");
+			return ERR_PTR(-EINVAL);
+		}
+		for (i = 0; i < strlen(decrypted_data); i++) {
+			if (!isxdigit(decrypted_data[i])) {
+				pr_err("encrypted key: decrypted data provided must contain only hexadecimal characters\n");
+				return ERR_PTR(-EINVAL);
+			}
+		}
+	}
+
+	if (format) {
+		if (!strcmp(format, key_format_ecryptfs)) {
+			if (dlen != ECRYPTFS_MAX_KEY_BYTES) {
+				pr_err("encrypted_key: keylen for the ecryptfs format must be equal to %d bytes\n",
+					ECRYPTFS_MAX_KEY_BYTES);
+				return ERR_PTR(-EINVAL);
+			}
+			decrypted_datalen = ECRYPTFS_MAX_KEY_BYTES;
+			payload_datalen = sizeof(struct ecryptfs_auth_tok);
+		} else if (!strcmp(format, key_format_enc32)) {
+			if (decrypted_datalen != KEY_ENC32_PAYLOAD_LEN) {
+				pr_err("encrypted_key: enc32 key payload incorrect length: %d\n",
+						decrypted_datalen);
+				return ERR_PTR(-EINVAL);
+			}
+		}
+	}
+
+	encrypted_datalen = roundup(decrypted_datalen, blksize);
+
+	datablob_len = format_len + 1 + strlen(master_desc) + 1
+	    + strlen(datalen) + 1 + ivsize + 1 + encrypted_datalen;
+
+	ret = key_payload_reserve(key, payload_datalen + datablob_len
+				  + HASH_SIZE + 1);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	epayload = kzalloc(sizeof(*epayload) + payload_datalen +
+			   datablob_len + HASH_SIZE + 1, GFP_KERNEL);
+	if (!epayload)
+		return ERR_PTR(-ENOMEM);
+
+	epayload->payload_datalen = payload_datalen;
+	epayload->decrypted_datalen = decrypted_datalen;
+	epayload->datablob_len = datablob_len;
+	return epayload;
+}
+
+static int encrypted_key_decrypt(struct encrypted_key_payload *epayload,
+				 const char *format, const char *hex_encoded_iv)
+{
+	struct key *mkey;
+	u8 derived_key[HASH_SIZE];
+	const u8 *master_key;
+	u8 *hmac;
+	const char *hex_encoded_data;
+	unsigned int encrypted_datalen;
+	size_t master_keylen;
+	size_t asciilen;
+	int ret;
+
+	encrypted_datalen = roundup(epayload->decrypted_datalen, blksize);
+	asciilen = (ivsize + 1 + encrypted_datalen + HASH_SIZE) * 2;
+	if (strlen(hex_encoded_iv) != asciilen)
+		return -EINVAL;
+
+	hex_encoded_data = hex_encoded_iv + (2 * ivsize) + 2;
+	ret = hex2bin(epayload->iv, hex_encoded_iv, ivsize);
+	if (ret < 0)
+		return -EINVAL;
+	ret = hex2bin(epayload->encrypted_data, hex_encoded_data,
+		      encrypted_datalen);
+	if (ret < 0)
+		return -EINVAL;
+
+	hmac = epayload->format + epayload->datablob_len;
+	ret = hex2bin(hmac, hex_encoded_data + (encrypted_datalen * 2),
+		      HASH_SIZE);
+	if (ret < 0)
+		return -EINVAL;
+
+	mkey = request_master_key(epayload, &master_key, &master_keylen);
+	if (IS_ERR(mkey))
+		return PTR_ERR(mkey);
+
+	ret = datablob_hmac_verify(epayload, format, master_key, master_keylen);
+	if (ret < 0) {
+		pr_err("encrypted_key: bad hmac (%d)\n", ret);
+		goto out;
+	}
+
+	ret = get_derived_key(derived_key, ENC_KEY, master_key, master_keylen);
+	if (ret < 0)
+		goto out;
+
+	ret = derived_key_decrypt(epayload, derived_key, sizeof derived_key);
+	if (ret < 0)
+		pr_err("encrypted_key: failed to decrypt key (%d)\n", ret);
+out:
+	up_read(&mkey->sem);
+	key_put(mkey);
+	memzero_explicit(derived_key, sizeof(derived_key));
+	return ret;
+}
+
+static void __ekey_init(struct encrypted_key_payload *epayload,
+			const char *format, const char *master_desc,
+			const char *datalen)
+{
+	unsigned int format_len;
+
+	format_len = (!format) ? strlen(key_format_default) : strlen(format);
+	epayload->format = epayload->payload_data + epayload->payload_datalen;
+	epayload->master_desc = epayload->format + format_len + 1;
+	epayload->datalen = epayload->master_desc + strlen(master_desc) + 1;
+	epayload->iv = epayload->datalen + strlen(datalen) + 1;
+	epayload->encrypted_data = epayload->iv + ivsize + 1;
+	epayload->decrypted_data = epayload->payload_data;
+
+	if (!format)
+		memcpy(epayload->format, key_format_default, format_len);
+	else {
+		if (!strcmp(format, key_format_ecryptfs))
+			epayload->decrypted_data =
+				ecryptfs_get_auth_tok_key((struct ecryptfs_auth_tok *)epayload->payload_data);
+
+		memcpy(epayload->format, format, format_len);
+	}
+
+	memcpy(epayload->master_desc, master_desc, strlen(master_desc));
+	memcpy(epayload->datalen, datalen, strlen(datalen));
+}
+
+/*
+ * encrypted_init - initialize an encrypted key
+ *
+ * For a new key, use either a random number or user-provided decrypted data in
+ * case it is provided. A random number is used for the iv in both cases. For
+ * an old key, decrypt the hex encoded data.
+ */
+static int encrypted_init(struct encrypted_key_payload *epayload,
+			  const char *key_desc, const char *format,
+			  const char *master_desc, const char *datalen,
+			  const char *hex_encoded_iv, const char *decrypted_data)
+{
+	int ret = 0;
+
+	if (format && !strcmp(format, key_format_ecryptfs)) {
+		ret = valid_ecryptfs_desc(key_desc);
+		if (ret < 0)
+			return ret;
+
+		ecryptfs_fill_auth_tok((struct ecryptfs_auth_tok *)epayload->payload_data,
+				       key_desc);
+	}
+
+	__ekey_init(epayload, format, master_desc, datalen);
+	if (hex_encoded_iv) {
+		ret = encrypted_key_decrypt(epayload, format, hex_encoded_iv);
+	} else if (decrypted_data) {
+		get_random_bytes(epayload->iv, ivsize);
+		ret = hex2bin(epayload->decrypted_data, decrypted_data,
+			      epayload->decrypted_datalen);
+	} else {
+		get_random_bytes(epayload->iv, ivsize);
+		get_random_bytes(epayload->decrypted_data, epayload->decrypted_datalen);
+	}
+	return ret;
+}
+
+/*
+ * encrypted_instantiate - instantiate an encrypted key
+ *
+ * Instantiates the key:
+ * - by decrypting an existing encrypted datablob, or
+ * - by creating a new encrypted key based on a kernel random number, or
+ * - using provided decrypted data.
+ *
+ * On success, return 0. Otherwise return errno.
+ */
+static int encrypted_instantiate(struct key *key,
+				 struct key_preparsed_payload *prep)
+{
+	struct encrypted_key_payload *epayload = NULL;
+	char *datablob = NULL;
+	const char *format = NULL;
+	char *master_desc = NULL;
+	char *decrypted_datalen = NULL;
+	char *hex_encoded_iv = NULL;
+	char *decrypted_data = NULL;
+	size_t datalen = prep->datalen;
+	int ret;
+
+	if (datalen == 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	datablob = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!datablob)
+		return -ENOMEM;
+	datablob[datalen] = 0;
+	memcpy(datablob, prep->data, datalen);
+	ret = datablob_parse(datablob, &format, &master_desc,
+			     &decrypted_datalen, &hex_encoded_iv, &decrypted_data);
+	if (ret < 0)
+		goto out;
+
+	epayload = encrypted_key_alloc(key, format, master_desc,
+				       decrypted_datalen, decrypted_data);
+	if (IS_ERR(epayload)) {
+		ret = PTR_ERR(epayload);
+		goto out;
+	}
+	ret = encrypted_init(epayload, key->description, format, master_desc,
+			     decrypted_datalen, hex_encoded_iv, decrypted_data);
+	if (ret < 0) {
+		kfree_sensitive(epayload);
+		goto out;
+	}
+
+	rcu_assign_keypointer(key, epayload);
+out:
+	kfree_sensitive(datablob);
+	return ret;
+}
+
+static void encrypted_rcu_free(struct rcu_head *rcu)
+{
+	struct encrypted_key_payload *epayload;
+
+	epayload = container_of(rcu, struct encrypted_key_payload, rcu);
+	kfree_sensitive(epayload);
+}
+
+/*
+ * encrypted_update - update the master key description
+ *
+ * Change the master key description for an existing encrypted key.
+ * The next read will return an encrypted datablob using the new
+ * master key description.
+ *
+ * On success, return 0. Otherwise return errno.
+ */
+static int encrypted_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct encrypted_key_payload *epayload = key->payload.data[0];
+	struct encrypted_key_payload *new_epayload;
+	char *buf;
+	char *new_master_desc = NULL;
+	const char *format = NULL;
+	size_t datalen = prep->datalen;
+	int ret = 0;
+
+	if (key_is_negative(key))
+		return -ENOKEY;
+	if (datalen == 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	buf = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	buf[datalen] = 0;
+	memcpy(buf, prep->data, datalen);
+	ret = datablob_parse(buf, &format, &new_master_desc, NULL, NULL, NULL);
+	if (ret < 0)
+		goto out;
+
+	ret = valid_master_desc(new_master_desc, epayload->master_desc);
+	if (ret < 0)
+		goto out;
+
+	new_epayload = encrypted_key_alloc(key, epayload->format,
+					   new_master_desc, epayload->datalen, NULL);
+	if (IS_ERR(new_epayload)) {
+		ret = PTR_ERR(new_epayload);
+		goto out;
+	}
+
+	__ekey_init(new_epayload, epayload->format, new_master_desc,
+		    epayload->datalen);
+
+	memcpy(new_epayload->iv, epayload->iv, ivsize);
+	memcpy(new_epayload->payload_data, epayload->payload_data,
+	       epayload->payload_datalen);
+
+	rcu_assign_keypointer(key, new_epayload);
+	call_rcu(&epayload->rcu, encrypted_rcu_free);
+out:
+	kfree_sensitive(buf);
+	return ret;
+}
+
+/*
+ * encrypted_read - format and copy out the encrypted data
+ *
+ * The resulting datablob format is:
+ * <master-key name> <decrypted data length> <encrypted iv> <encrypted data>
+ *
+ * On success, return to userspace the encrypted key datablob size.
+ */
+static long encrypted_read(const struct key *key, char *buffer,
+			   size_t buflen)
+{
+	struct encrypted_key_payload *epayload;
+	struct key *mkey;
+	const u8 *master_key;
+	size_t master_keylen;
+	char derived_key[HASH_SIZE];
+	char *ascii_buf;
+	size_t asciiblob_len;
+	int ret;
+
+	epayload = dereference_key_locked(key);
+
+	/* returns the hex encoded iv, encrypted-data, and hmac as ascii */
+	asciiblob_len = epayload->datablob_len + ivsize + 1
+	    + roundup(epayload->decrypted_datalen, blksize)
+	    + (HASH_SIZE * 2);
+
+	if (!buffer || buflen < asciiblob_len)
+		return asciiblob_len;
+
+	mkey = request_master_key(epayload, &master_key, &master_keylen);
+	if (IS_ERR(mkey))
+		return PTR_ERR(mkey);
+
+	ret = get_derived_key(derived_key, ENC_KEY, master_key, master_keylen);
+	if (ret < 0)
+		goto out;
+
+	ret = derived_key_encrypt(epayload, derived_key, sizeof derived_key);
+	if (ret < 0)
+		goto out;
+
+	ret = datablob_hmac_append(epayload, master_key, master_keylen);
+	if (ret < 0)
+		goto out;
+
+	ascii_buf = datablob_format(epayload, asciiblob_len);
+	if (!ascii_buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	up_read(&mkey->sem);
+	key_put(mkey);
+	memzero_explicit(derived_key, sizeof(derived_key));
+
+	memcpy(buffer, ascii_buf, asciiblob_len);
+	kfree_sensitive(ascii_buf);
+
+	return asciiblob_len;
+out:
+	up_read(&mkey->sem);
+	key_put(mkey);
+	memzero_explicit(derived_key, sizeof(derived_key));
+	return ret;
+}
+
+/*
+ * encrypted_destroy - clear and free the key's payload
+ */
+static void encrypted_destroy(struct key *key)
+{
+	kfree_sensitive(key->payload.data[0]);
+}
+
+struct key_type key_type_encrypted = {
+	.name = "encrypted",
+	.instantiate = encrypted_instantiate,
+	.update = encrypted_update,
+	.destroy = encrypted_destroy,
+	.describe = user_describe,
+	.read = encrypted_read,
+};
+EXPORT_SYMBOL_GPL(key_type_encrypted);
+
+static int __init init_encrypted(void)
+{
+	int ret;
+
+	ret = aes_get_sizes();
+	if (ret < 0)
+		return ret;
+	return register_key_type(&key_type_encrypted);
+}
+
+static void __exit cleanup_encrypted(void)
+{
+	unregister_key_type(&key_type_encrypted);
+}
+
+late_initcall(init_encrypted);
+module_exit(cleanup_encrypted);
+
+MODULE_DESCRIPTION("Encrypted key type");
+MODULE_LICENSE("GPL");
diff --git a/security/keys/encrypted-keys/encrypted.h b/security/keys/encrypted-keys/encrypted.h
new file mode 100644
index 000000000..1809995db
--- /dev/null
+++ b/security/keys/encrypted-keys/encrypted.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ENCRYPTED_KEY_H
+#define __ENCRYPTED_KEY_H
+
+#define ENCRYPTED_DEBUG 0
+#if defined(CONFIG_TRUSTED_KEYS) || \
+  (defined(CONFIG_TRUSTED_KEYS_MODULE) && defined(CONFIG_ENCRYPTED_KEYS_MODULE))
+extern struct key *request_trusted_key(const char *trusted_desc,
+				       const u8 **master_key, size_t *master_keylen);
+#else
+static inline struct key *request_trusted_key(const char *trusted_desc,
+					      const u8 **master_key,
+					      size_t *master_keylen)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+#if ENCRYPTED_DEBUG
+static inline void dump_master_key(const u8 *master_key, size_t master_keylen)
+{
+	print_hex_dump(KERN_ERR, "master key: ", DUMP_PREFIX_NONE, 32, 1,
+		       master_key, master_keylen, 0);
+}
+
+static inline void dump_decrypted_data(struct encrypted_key_payload *epayload)
+{
+	print_hex_dump(KERN_ERR, "decrypted data: ", DUMP_PREFIX_NONE, 32, 1,
+		       epayload->decrypted_data,
+		       epayload->decrypted_datalen, 0);
+}
+
+static inline void dump_encrypted_data(struct encrypted_key_payload *epayload,
+				       unsigned int encrypted_datalen)
+{
+	print_hex_dump(KERN_ERR, "encrypted data: ", DUMP_PREFIX_NONE, 32, 1,
+		       epayload->encrypted_data, encrypted_datalen, 0);
+}
+
+static inline void dump_hmac(const char *str, const u8 *digest,
+			     unsigned int hmac_size)
+{
+	if (str)
+		pr_info("encrypted_key: %s", str);
+	print_hex_dump(KERN_ERR, "hmac: ", DUMP_PREFIX_NONE, 32, 1, digest,
+		       hmac_size, 0);
+}
+#else
+static inline void dump_master_key(const u8 *master_key, size_t master_keylen)
+{
+}
+
+static inline void dump_decrypted_data(struct encrypted_key_payload *epayload)
+{
+}
+
+static inline void dump_encrypted_data(struct encrypted_key_payload *epayload,
+				       unsigned int encrypted_datalen)
+{
+}
+
+static inline void dump_hmac(const char *str, const u8 *digest,
+			     unsigned int hmac_size)
+{
+}
+#endif
+#endif
diff --git a/security/keys/encrypted-keys/masterkey_trusted.c b/security/keys/encrypted-keys/masterkey_trusted.c
new file mode 100644
index 000000000..e6d22ce77
--- /dev/null
+++ b/security/keys/encrypted-keys/masterkey_trusted.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- https://security.polito.it
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * See Documentation/security/keys/trusted-encrypted.rst
+ */
+
+#include <linux/uaccess.h>
+#include <linux/err.h>
+#include <keys/trusted-type.h>
+#include <keys/encrypted-type.h>
+#include "encrypted.h"
+
+/*
+ * request_trusted_key - request the trusted key
+ *
+ * Trusted keys are sealed to PCRs and other metadata. Although userspace
+ * manages both trusted/encrypted key-types, like the encrypted key type
+ * data, trusted key type data is not visible decrypted from userspace.
+ */
+struct key *request_trusted_key(const char *trusted_desc,
+				const u8 **master_key, size_t *master_keylen)
+{
+	struct trusted_key_payload *tpayload;
+	struct key *tkey;
+
+	tkey = request_key(&key_type_trusted, trusted_desc, NULL);
+	if (IS_ERR(tkey))
+		goto error;
+
+	down_read(&tkey->sem);
+	tpayload = tkey->payload.data[0];
+	*master_key = tpayload->key;
+	*master_keylen = tpayload->key_len;
+error:
+	return tkey;
+}
diff --git a/security/keys/gc.c b/security/keys/gc.c
new file mode 100644
index 000000000..748e83818
--- /dev/null
+++ b/security/keys/gc.c
@@ -0,0 +1,374 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key garbage collector
+ *
+ * Copyright (C) 2009-2011 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <keys/keyring-type.h>
+#include "internal.h"
+
+/*
+ * Delay between key revocation/expiry in seconds
+ */
+unsigned key_gc_delay = 5 * 60;
+
+/*
+ * Reaper for unused keys.
+ */
+static void key_garbage_collector(struct work_struct *work);
+DECLARE_WORK(key_gc_work, key_garbage_collector);
+
+/*
+ * Reaper for links from keyrings to dead keys.
+ */
+static void key_gc_timer_func(struct timer_list *);
+static DEFINE_TIMER(key_gc_timer, key_gc_timer_func);
+
+static time64_t key_gc_next_run = TIME64_MAX;
+static struct key_type *key_gc_dead_keytype;
+
+static unsigned long key_gc_flags;
+#define KEY_GC_KEY_EXPIRED	0	/* A key expired and needs unlinking */
+#define KEY_GC_REAP_KEYTYPE	1	/* A keytype is being unregistered */
+#define KEY_GC_REAPING_KEYTYPE	2	/* Cleared when keytype reaped */
+
+
+/*
+ * Any key whose type gets unregistered will be re-typed to this if it can't be
+ * immediately unlinked.
+ */
+struct key_type key_type_dead = {
+	.name = ".dead",
+};
+
+/*
+ * Schedule a garbage collection run.
+ * - time precision isn't particularly important
+ */
+void key_schedule_gc(time64_t gc_at)
+{
+	unsigned long expires;
+	time64_t now = ktime_get_real_seconds();
+
+	kenter("%lld", gc_at - now);
+
+	if (gc_at <= now || test_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) {
+		kdebug("IMMEDIATE");
+		schedule_work(&key_gc_work);
+	} else if (gc_at < key_gc_next_run) {
+		kdebug("DEFERRED");
+		key_gc_next_run = gc_at;
+		expires = jiffies + (gc_at - now) * HZ;
+		mod_timer(&key_gc_timer, expires);
+	}
+}
+
+/*
+ * Set the expiration time on a key.
+ */
+void key_set_expiry(struct key *key, time64_t expiry)
+{
+	key->expiry = expiry;
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		key_schedule_gc(expiry);
+	}
+}
+
+/*
+ * Schedule a dead links collection run.
+ */
+void key_schedule_gc_links(void)
+{
+	set_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags);
+	schedule_work(&key_gc_work);
+}
+
+/*
+ * Some key's cleanup time was met after it expired, so we need to get the
+ * reaper to go through a cycle finding expired keys.
+ */
+static void key_gc_timer_func(struct timer_list *unused)
+{
+	kenter("");
+	key_gc_next_run = TIME64_MAX;
+	key_schedule_gc_links();
+}
+
+/*
+ * Reap keys of dead type.
+ *
+ * We use three flags to make sure we see three complete cycles of the garbage
+ * collector: the first to mark keys of that type as being dead, the second to
+ * collect dead links and the third to clean up the dead keys.  We have to be
+ * careful as there may already be a cycle in progress.
+ *
+ * The caller must be holding key_types_sem.
+ */
+void key_gc_keytype(struct key_type *ktype)
+{
+	kenter("%s", ktype->name);
+
+	key_gc_dead_keytype = ktype;
+	set_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+	smp_mb();
+	set_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags);
+
+	kdebug("schedule");
+	schedule_work(&key_gc_work);
+
+	kdebug("sleep");
+	wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE,
+		    TASK_UNINTERRUPTIBLE);
+
+	key_gc_dead_keytype = NULL;
+	kleave("");
+}
+
+/*
+ * Garbage collect a list of unreferenced, detached keys
+ */
+static noinline void key_gc_unused_keys(struct list_head *keys)
+{
+	while (!list_empty(keys)) {
+		struct key *key =
+			list_entry(keys->next, struct key, graveyard_link);
+		short state = key->state;
+
+		list_del(&key->graveyard_link);
+
+		kdebug("- %u", key->serial);
+		key_check(key);
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+		remove_watch_list(key->watchers, key->serial);
+		key->watchers = NULL;
+#endif
+
+		/* Throw away the key data if the key is instantiated */
+		if (state == KEY_IS_POSITIVE && key->type->destroy)
+			key->type->destroy(key);
+
+		security_key_free(key);
+
+		atomic_dec(&key->user->nkeys);
+		if (state != KEY_IS_UNINSTANTIATED)
+			atomic_dec(&key->user->nikeys);
+
+		key_user_put(key->user);
+		key_put_tag(key->domain_tag);
+		kfree(key->description);
+
+		memzero_explicit(key, sizeof(*key));
+		kmem_cache_free(key_jar, key);
+	}
+}
+
+/*
+ * Garbage collector for unused keys.
+ *
+ * This is done in process context so that we don't have to disable interrupts
+ * all over the place.  key_put() schedules this rather than trying to do the
+ * cleanup itself, which means key_put() doesn't have to sleep.
+ */
+static void key_garbage_collector(struct work_struct *work)
+{
+	static LIST_HEAD(graveyard);
+	static u8 gc_state;		/* Internal persistent state */
+#define KEY_GC_REAP_AGAIN	0x01	/* - Need another cycle */
+#define KEY_GC_REAPING_LINKS	0x02	/* - We need to reap links */
+#define KEY_GC_REAPING_DEAD_1	0x10	/* - We need to mark dead keys */
+#define KEY_GC_REAPING_DEAD_2	0x20	/* - We need to reap dead key links */
+#define KEY_GC_REAPING_DEAD_3	0x40	/* - We need to reap dead keys */
+#define KEY_GC_FOUND_DEAD_KEY	0x80	/* - We found at least one dead key */
+
+	struct rb_node *cursor;
+	struct key *key;
+	time64_t new_timer, limit, expiry;
+
+	kenter("[%lx,%x]", key_gc_flags, gc_state);
+
+	limit = ktime_get_real_seconds();
+
+	/* Work out what we're going to be doing in this pass */
+	gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
+	gc_state <<= 1;
+	if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
+		gc_state |= KEY_GC_REAPING_LINKS;
+
+	if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
+		gc_state |= KEY_GC_REAPING_DEAD_1;
+	kdebug("new pass %x", gc_state);
+
+	new_timer = TIME64_MAX;
+
+	/* As only this function is permitted to remove things from the key
+	 * serial tree, if cursor is non-NULL then it will always point to a
+	 * valid node in the tree - even if lock got dropped.
+	 */
+	spin_lock(&key_serial_lock);
+	cursor = rb_first(&key_serial_tree);
+
+continue_scanning:
+	while (cursor) {
+		key = rb_entry(cursor, struct key, serial_node);
+		cursor = rb_next(cursor);
+
+		if (!test_bit_acquire(KEY_FLAG_USER_ALIVE, &key->flags)) {
+			/* Clobber key->user after final put seen. */
+			goto found_unreferenced_key;
+		}
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) {
+			if (key->type == key_gc_dead_keytype) {
+				gc_state |= KEY_GC_FOUND_DEAD_KEY;
+				set_bit(KEY_FLAG_DEAD, &key->flags);
+				key->perm = 0;
+				goto skip_dead_key;
+			} else if (key->type == &key_type_keyring &&
+				   key->restrict_link) {
+				goto found_restricted_keyring;
+			}
+		}
+
+		expiry = key->expiry;
+		if (expiry != TIME64_MAX) {
+			if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+				expiry += key_gc_delay;
+			if (expiry > limit && expiry < new_timer) {
+				kdebug("will expire %x in %lld",
+				       key_serial(key), key->expiry - limit);
+				new_timer = key->expiry;
+			}
+		}
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2))
+			if (key->type == key_gc_dead_keytype)
+				gc_state |= KEY_GC_FOUND_DEAD_KEY;
+
+		if ((gc_state & KEY_GC_REAPING_LINKS) ||
+		    unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) {
+			if (key->type == &key_type_keyring)
+				goto found_keyring;
+		}
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3))
+			if (key->type == key_gc_dead_keytype)
+				goto destroy_dead_key;
+
+	skip_dead_key:
+		if (spin_is_contended(&key_serial_lock) || need_resched())
+			goto contended;
+	}
+
+contended:
+	spin_unlock(&key_serial_lock);
+
+maybe_resched:
+	if (cursor) {
+		cond_resched();
+		spin_lock(&key_serial_lock);
+		goto continue_scanning;
+	}
+
+	/* We've completed the pass.  Set the timer if we need to and queue a
+	 * new cycle if necessary.  We keep executing cycles until we find one
+	 * where we didn't reap any keys.
+	 */
+	kdebug("pass complete");
+
+	if (new_timer != TIME64_MAX) {
+		new_timer += key_gc_delay;
+		key_schedule_gc(new_timer);
+	}
+
+	if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2) ||
+	    !list_empty(&graveyard)) {
+		/* Make sure that all pending keyring payload destructions are
+		 * fulfilled and that people aren't now looking at dead or
+		 * dying keys that they don't have a reference upon or a link
+		 * to.
+		 */
+		kdebug("gc sync");
+		synchronize_rcu();
+	}
+
+	if (!list_empty(&graveyard)) {
+		kdebug("gc keys");
+		key_gc_unused_keys(&graveyard);
+	}
+
+	if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 |
+				 KEY_GC_REAPING_DEAD_2))) {
+		if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) {
+			/* No remaining dead keys: short circuit the remaining
+			 * keytype reap cycles.
+			 */
+			kdebug("dead short");
+			gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2);
+			gc_state |= KEY_GC_REAPING_DEAD_3;
+		} else {
+			gc_state |= KEY_GC_REAP_AGAIN;
+		}
+	}
+
+	if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) {
+		kdebug("dead wake");
+		smp_mb();
+		clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+		wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE);
+	}
+
+	if (gc_state & KEY_GC_REAP_AGAIN)
+		schedule_work(&key_gc_work);
+	kleave(" [end %x]", gc_state);
+	return;
+
+	/* We found an unreferenced key - once we've removed it from the tree,
+	 * we can safely drop the lock.
+	 */
+found_unreferenced_key:
+	kdebug("unrefd key %d", key->serial);
+	rb_erase(&key->serial_node, &key_serial_tree);
+	spin_unlock(&key_serial_lock);
+
+	list_add_tail(&key->graveyard_link, &graveyard);
+	gc_state |= KEY_GC_REAP_AGAIN;
+	goto maybe_resched;
+
+	/* We found a restricted keyring and need to update the restriction if
+	 * it is associated with the dead key type.
+	 */
+found_restricted_keyring:
+	spin_unlock(&key_serial_lock);
+	keyring_restriction_gc(key, key_gc_dead_keytype);
+	goto maybe_resched;
+
+	/* We found a keyring and we need to check the payload for links to
+	 * dead or expired keys.  We don't flag another reap immediately as we
+	 * have to wait for the old payload to be destroyed by RCU before we
+	 * can reap the keys to which it refers.
+	 */
+found_keyring:
+	spin_unlock(&key_serial_lock);
+	keyring_gc(key, limit);
+	goto maybe_resched;
+
+	/* We found a dead key that is still referenced.  Reset its type and
+	 * destroy its payload with its semaphore held.
+	 */
+destroy_dead_key:
+	spin_unlock(&key_serial_lock);
+	kdebug("destroy key %d", key->serial);
+	down_write(&key->sem);
+	key->type = &key_type_dead;
+	if (key_gc_dead_keytype->destroy)
+		key_gc_dead_keytype->destroy(key);
+	memset(&key->payload, KEY_DESTROY, sizeof(key->payload));
+	up_write(&key->sem);
+	goto maybe_resched;
+}
diff --git a/security/keys/internal.h b/security/keys/internal.h
new file mode 100644
index 000000000..b7b622bc3
--- /dev/null
+++ b/security/keys/internal.h
@@ -0,0 +1,378 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Authentication token and access key management internal defs
+ *
+ * Copyright (C) 2003-5, 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _INTERNAL_H
+#define _INTERNAL_H
+
+#include <linux/sched.h>
+#include <linux/wait_bit.h>
+#include <linux/cred.h>
+#include <linux/key-type.h>
+#include <linux/task_work.h>
+#include <linux/keyctl.h>
+#include <linux/refcount.h>
+#include <linux/watch_queue.h>
+#include <linux/compat.h>
+#include <linux/mm.h>
+#include <linux/vmalloc.h>
+
+struct iovec;
+
+#ifdef __KDEBUG
+#define kenter(FMT, ...) \
+	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	printk(KERN_DEBUG "   "FMT"\n", ##__VA_ARGS__)
+#else
+#define kenter(FMT, ...) \
+	no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
+#endif
+
+extern struct key_type key_type_dead;
+extern struct key_type key_type_user;
+extern struct key_type key_type_logon;
+
+/*****************************************************************************/
+/*
+ * Keep track of keys for a user.
+ *
+ * This needs to be separate to user_struct to avoid a refcount-loop
+ * (user_struct pins some keyrings which pin this struct).
+ *
+ * We also keep track of keys under request from userspace for this UID here.
+ */
+struct key_user {
+	struct rb_node		node;
+	struct mutex		cons_lock;	/* construction initiation lock */
+	spinlock_t		lock;
+	refcount_t		usage;		/* for accessing qnkeys & qnbytes */
+	atomic_t		nkeys;		/* number of keys */
+	atomic_t		nikeys;		/* number of instantiated keys */
+	kuid_t			uid;
+	int			qnkeys;		/* number of keys allocated to this user */
+	int			qnbytes;	/* number of bytes allocated to this user */
+};
+
+extern struct rb_root	key_user_tree;
+extern spinlock_t	key_user_lock;
+extern struct key_user	root_key_user;
+
+extern struct key_user *key_user_lookup(kuid_t uid);
+extern void key_user_put(struct key_user *user);
+
+/*
+ * Key quota limits.
+ * - root has its own separate limits to everyone else
+ */
+extern unsigned key_quota_root_maxkeys;
+extern unsigned key_quota_root_maxbytes;
+extern unsigned key_quota_maxkeys;
+extern unsigned key_quota_maxbytes;
+
+#define KEYQUOTA_LINK_BYTES	4		/* a link in a keyring is worth 4 bytes */
+
+
+extern struct kmem_cache *key_jar;
+extern struct rb_root key_serial_tree;
+extern spinlock_t key_serial_lock;
+extern struct mutex key_construction_mutex;
+extern wait_queue_head_t request_key_conswq;
+
+extern void key_set_index_key(struct keyring_index_key *index_key);
+extern struct key_type *key_type_lookup(const char *type);
+extern void key_type_put(struct key_type *ktype);
+
+extern int __key_link_lock(struct key *keyring,
+			   const struct keyring_index_key *index_key);
+extern int __key_move_lock(struct key *l_keyring, struct key *u_keyring,
+			   const struct keyring_index_key *index_key);
+extern int __key_link_begin(struct key *keyring,
+			    const struct keyring_index_key *index_key,
+			    struct assoc_array_edit **_edit);
+extern int __key_link_check_live_key(struct key *keyring, struct key *key);
+extern void __key_link(struct key *keyring, struct key *key,
+		       struct assoc_array_edit **_edit);
+extern void __key_link_end(struct key *keyring,
+			   const struct keyring_index_key *index_key,
+			   struct assoc_array_edit *edit);
+
+extern key_ref_t find_key_to_update(key_ref_t keyring_ref,
+				    const struct keyring_index_key *index_key);
+
+struct keyring_search_context {
+	struct keyring_index_key index_key;
+	const struct cred	*cred;
+	struct key_match_data	match_data;
+	unsigned		flags;
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0001	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0002	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0004	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0008	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0010	/* Give an error on excessive depth */
+#define KEYRING_SEARCH_SKIP_EXPIRED	0x0020	/* Ignore expired keys (intention to replace) */
+#define KEYRING_SEARCH_RECURSE		0x0040	/* Search child keyrings also */
+
+	int (*iterator)(const void *object, void *iterator_data);
+
+	/* Internal stuff */
+	int			skipped_ret;
+	bool			possessed;
+	key_ref_t		result;
+	time64_t		now;
+};
+
+extern bool key_default_cmp(const struct key *key,
+			    const struct key_match_data *match_data);
+extern key_ref_t keyring_search_rcu(key_ref_t keyring_ref,
+				    struct keyring_search_context *ctx);
+
+extern key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx);
+extern key_ref_t search_process_keyrings_rcu(struct keyring_search_context *ctx);
+
+extern struct key *find_keyring_by_name(const char *name, bool uid_keyring);
+
+extern int look_up_user_keyrings(struct key **, struct key **);
+extern struct key *get_user_session_keyring_rcu(const struct cred *);
+extern int install_thread_keyring_to_cred(struct cred *);
+extern int install_process_keyring_to_cred(struct cred *);
+extern int install_session_keyring_to_cred(struct cred *, struct key *);
+
+extern struct key *request_key_and_link(struct key_type *type,
+					const char *description,
+					struct key_tag *domain_tag,
+					const void *callout_info,
+					size_t callout_len,
+					void *aux,
+					struct key *dest_keyring,
+					unsigned long flags);
+
+extern bool lookup_user_key_possessed(const struct key *key,
+				      const struct key_match_data *match_data);
+
+extern long join_session_keyring(const char *name);
+extern void key_change_session_keyring(struct callback_head *twork);
+
+extern struct work_struct key_gc_work;
+extern unsigned key_gc_delay;
+extern void keyring_gc(struct key *keyring, time64_t limit);
+extern void keyring_restriction_gc(struct key *keyring,
+				   struct key_type *dead_type);
+void key_set_expiry(struct key *key, time64_t expiry);
+extern void key_schedule_gc(time64_t gc_at);
+extern void key_schedule_gc_links(void);
+extern void key_gc_keytype(struct key_type *ktype);
+
+extern int key_task_permission(const key_ref_t key_ref,
+			       const struct cred *cred,
+			       enum key_need_perm need_perm);
+
+static inline void notify_key(struct key *key,
+			      enum key_notification_subtype subtype, u32 aux)
+{
+#ifdef CONFIG_KEY_NOTIFICATIONS
+	struct key_notification n = {
+		.watch.type	= WATCH_TYPE_KEY_NOTIFY,
+		.watch.subtype	= subtype,
+		.watch.info	= watch_sizeof(n),
+		.key_id		= key_serial(key),
+		.aux		= aux,
+	};
+
+	post_watch_notification(key->watchers, &n.watch, current_cred(),
+				n.key_id);
+#endif
+}
+
+/*
+ * Check to see whether permission is granted to use a key in the desired way.
+ */
+static inline int key_permission(const key_ref_t key_ref,
+				 enum key_need_perm need_perm)
+{
+	return key_task_permission(key_ref, current_cred(), need_perm);
+}
+
+extern struct key_type key_type_request_key_auth;
+extern struct key *request_key_auth_new(struct key *target,
+					const char *op,
+					const void *callout_info,
+					size_t callout_len,
+					struct key *dest_keyring);
+struct request_key_auth *request_key_auth_get(struct key *authkey);
+void request_key_auth_put(struct request_key_auth *rka);
+
+extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
+
+/*
+ * Determine whether a key is dead.
+ */
+static inline bool key_is_dead(const struct key *key, time64_t limit)
+{
+	time64_t expiry = key->expiry;
+
+	if (expiry != TIME64_MAX) {
+		if (!(key->type->flags & KEY_TYPE_INSTANT_REAP))
+			expiry += key_gc_delay;
+		if (expiry <= limit)
+			return true;
+	}
+
+	return
+		key->flags & ((1 << KEY_FLAG_DEAD) |
+			      (1 << KEY_FLAG_INVALIDATED)) ||
+		key->domain_tag->removed;
+}
+
+/*
+ * keyctl() functions
+ */
+extern long keyctl_get_keyring_ID(key_serial_t, int);
+extern long keyctl_join_session_keyring(const char __user *);
+extern long keyctl_update_key(key_serial_t, const void __user *, size_t);
+extern long keyctl_revoke_key(key_serial_t);
+extern long keyctl_keyring_clear(key_serial_t);
+extern long keyctl_keyring_link(key_serial_t, key_serial_t);
+extern long keyctl_keyring_move(key_serial_t, key_serial_t, key_serial_t, unsigned int);
+extern long keyctl_keyring_unlink(key_serial_t, key_serial_t);
+extern long keyctl_describe_key(key_serial_t, char __user *, size_t);
+extern long keyctl_keyring_search(key_serial_t, const char __user *,
+				  const char __user *, key_serial_t);
+extern long keyctl_read_key(key_serial_t, char __user *, size_t);
+extern long keyctl_chown_key(key_serial_t, uid_t, gid_t);
+extern long keyctl_setperm_key(key_serial_t, key_perm_t);
+extern long keyctl_instantiate_key(key_serial_t, const void __user *,
+				   size_t, key_serial_t);
+extern long keyctl_negate_key(key_serial_t, unsigned, key_serial_t);
+extern long keyctl_set_reqkey_keyring(int);
+extern long keyctl_set_timeout(key_serial_t, unsigned);
+extern long keyctl_assume_authority(key_serial_t);
+extern long keyctl_get_security(key_serial_t keyid, char __user *buffer,
+				size_t buflen);
+extern long keyctl_session_to_parent(void);
+extern long keyctl_reject_key(key_serial_t, unsigned, unsigned, key_serial_t);
+extern long keyctl_instantiate_key_iov(key_serial_t,
+				       const struct iovec __user *,
+				       unsigned, key_serial_t);
+extern long keyctl_invalidate_key(key_serial_t);
+extern long keyctl_restrict_keyring(key_serial_t id,
+				    const char __user *_type,
+				    const char __user *_restriction);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+extern long keyctl_get_persistent(uid_t, key_serial_t);
+extern unsigned persistent_keyring_expiry;
+#else
+static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#ifdef CONFIG_KEY_DH_OPERATIONS
+extern long keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *,
+			      size_t, struct keyctl_kdf_params __user *);
+extern long __keyctl_dh_compute(struct keyctl_dh_params __user *, char __user *,
+				size_t, struct keyctl_kdf_params *);
+#ifdef CONFIG_COMPAT
+extern long compat_keyctl_dh_compute(struct keyctl_dh_params __user *params,
+				char __user *buffer, size_t buflen,
+				struct compat_keyctl_kdf_params __user *kdf);
+#endif
+#define KEYCTL_KDF_MAX_OUTPUT_LEN	1024	/* max length of KDF output */
+#define KEYCTL_KDF_MAX_OI_LEN		64	/* max length of otherinfo */
+#else
+static inline long keyctl_dh_compute(struct keyctl_dh_params __user *params,
+				     char __user *buffer, size_t buflen,
+				     struct keyctl_kdf_params __user *kdf)
+{
+	return -EOPNOTSUPP;
+}
+
+#ifdef CONFIG_COMPAT
+static inline long compat_keyctl_dh_compute(
+				struct keyctl_dh_params __user *params,
+				char __user *buffer, size_t buflen,
+				struct keyctl_kdf_params __user *kdf)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+#endif
+
+#ifdef CONFIG_ASYMMETRIC_KEY_TYPE
+extern long keyctl_pkey_query(key_serial_t,
+			      const char __user *,
+			      struct keyctl_pkey_query __user *);
+
+extern long keyctl_pkey_verify(const struct keyctl_pkey_params __user *,
+			       const char __user *,
+			       const void __user *, const void __user *);
+
+extern long keyctl_pkey_e_d_s(int,
+			      const struct keyctl_pkey_params __user *,
+			      const char __user *,
+			      const void __user *, void __user *);
+#else
+static inline long keyctl_pkey_query(key_serial_t id,
+				     const char __user *_info,
+				     struct keyctl_pkey_query __user *_res)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline long keyctl_pkey_verify(const struct keyctl_pkey_params __user *params,
+				      const char __user *_info,
+				      const void __user *_in,
+				      const void __user *_in2)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline long keyctl_pkey_e_d_s(int op,
+				     const struct keyctl_pkey_params __user *params,
+				     const char __user *_info,
+				     const void __user *_in,
+				     void __user *_out)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+extern long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen);
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+extern long keyctl_watch_key(key_serial_t, int, int);
+#else
+static inline long keyctl_watch_key(key_serial_t key_id, int watch_fd, int watch_id)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+/*
+ * Debugging key validation
+ */
+#ifdef KEY_DEBUGGING
+extern void __key_check(const struct key *);
+
+static inline void key_check(const struct key *key)
+{
+	if (key && (IS_ERR(key) || key->magic != KEY_DEBUG_MAGIC))
+		__key_check(key);
+}
+
+#else
+
+#define key_check(key) do {} while(0)
+
+#endif
+#endif /* _INTERNAL_H */
diff --git a/security/keys/key.c b/security/keys/key.c
new file mode 100644
index 000000000..b34a64d81
--- /dev/null
+++ b/security/keys/key.c
@@ -0,0 +1,1293 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Basic authentication token and access key management
+ *
+ * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/poison.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/workqueue.h>
+#include <linux/random.h>
+#include <linux/err.h>
+#include "internal.h"
+
+struct kmem_cache *key_jar;
+struct rb_root		key_serial_tree; /* tree of keys indexed by serial */
+DEFINE_SPINLOCK(key_serial_lock);
+
+struct rb_root	key_user_tree; /* tree of quota records indexed by UID */
+DEFINE_SPINLOCK(key_user_lock);
+
+unsigned int key_quota_root_maxkeys = 1000000;	/* root's key count quota */
+unsigned int key_quota_root_maxbytes = 25000000; /* root's key space quota */
+unsigned int key_quota_maxkeys = 200;		/* general key count quota */
+unsigned int key_quota_maxbytes = 20000;	/* general key space quota */
+
+static LIST_HEAD(key_types_list);
+static DECLARE_RWSEM(key_types_sem);
+
+/* We serialise key instantiation and link */
+DEFINE_MUTEX(key_construction_mutex);
+
+#ifdef KEY_DEBUGGING
+void __key_check(const struct key *key)
+{
+	printk("__key_check: key %p {%08x} should be {%08x}\n",
+	       key, key->magic, KEY_DEBUG_MAGIC);
+	BUG();
+}
+#endif
+
+/*
+ * Get the key quota record for a user, allocating a new record if one doesn't
+ * already exist.
+ */
+struct key_user *key_user_lookup(kuid_t uid)
+{
+	struct key_user *candidate = NULL, *user;
+	struct rb_node *parent, **p;
+
+try_again:
+	parent = NULL;
+	p = &key_user_tree.rb_node;
+	spin_lock(&key_user_lock);
+
+	/* search the tree for a user record with a matching UID */
+	while (*p) {
+		parent = *p;
+		user = rb_entry(parent, struct key_user, node);
+
+		if (uid_lt(uid, user->uid))
+			p = &(*p)->rb_left;
+		else if (uid_gt(uid, user->uid))
+			p = &(*p)->rb_right;
+		else
+			goto found;
+	}
+
+	/* if we get here, we failed to find a match in the tree */
+	if (!candidate) {
+		/* allocate a candidate user record if we don't already have
+		 * one */
+		spin_unlock(&key_user_lock);
+
+		user = NULL;
+		candidate = kmalloc_obj(struct key_user);
+		if (unlikely(!candidate))
+			goto out;
+
+		/* the allocation may have scheduled, so we need to repeat the
+		 * search lest someone else added the record whilst we were
+		 * asleep */
+		goto try_again;
+	}
+
+	/* if we get here, then the user record still hadn't appeared on the
+	 * second pass - so we use the candidate record */
+	refcount_set(&candidate->usage, 1);
+	atomic_set(&candidate->nkeys, 0);
+	atomic_set(&candidate->nikeys, 0);
+	candidate->uid = uid;
+	candidate->qnkeys = 0;
+	candidate->qnbytes = 0;
+	spin_lock_init(&candidate->lock);
+	mutex_init(&candidate->cons_lock);
+
+	rb_link_node(&candidate->node, parent, p);
+	rb_insert_color(&candidate->node, &key_user_tree);
+	spin_unlock(&key_user_lock);
+	user = candidate;
+	goto out;
+
+	/* okay - we found a user record for this UID */
+found:
+	refcount_inc(&user->usage);
+	spin_unlock(&key_user_lock);
+	kfree(candidate);
+out:
+	return user;
+}
+
+/*
+ * Dispose of a user structure
+ */
+void key_user_put(struct key_user *user)
+{
+	if (refcount_dec_and_lock(&user->usage, &key_user_lock)) {
+		rb_erase(&user->node, &key_user_tree);
+		spin_unlock(&key_user_lock);
+
+		kfree(user);
+	}
+}
+
+/*
+ * Allocate a serial number for a key.  These are assigned randomly to avoid
+ * security issues through covert channel problems.
+ */
+static inline void key_alloc_serial(struct key *key)
+{
+	struct rb_node *parent, **p;
+	struct key *xkey;
+
+	/* propose a random serial number and look for a hole for it in the
+	 * serial number tree */
+	do {
+		get_random_bytes(&key->serial, sizeof(key->serial));
+
+		key->serial >>= 1; /* negative numbers are not permitted */
+	} while (key->serial < 3);
+
+	spin_lock(&key_serial_lock);
+
+attempt_insertion:
+	parent = NULL;
+	p = &key_serial_tree.rb_node;
+
+	while (*p) {
+		parent = *p;
+		xkey = rb_entry(parent, struct key, serial_node);
+
+		if (key->serial < xkey->serial)
+			p = &(*p)->rb_left;
+		else if (key->serial > xkey->serial)
+			p = &(*p)->rb_right;
+		else
+			goto serial_exists;
+	}
+
+	/* we've found a suitable hole - arrange for this key to occupy it */
+	rb_link_node(&key->serial_node, parent, p);
+	rb_insert_color(&key->serial_node, &key_serial_tree);
+
+	spin_unlock(&key_serial_lock);
+	return;
+
+	/* we found a key with the proposed serial number - walk the tree from
+	 * that point looking for the next unused serial number */
+serial_exists:
+	for (;;) {
+		key->serial++;
+		if (key->serial < 3) {
+			key->serial = 3;
+			goto attempt_insertion;
+		}
+
+		parent = rb_next(parent);
+		if (!parent)
+			goto attempt_insertion;
+
+		xkey = rb_entry(parent, struct key, serial_node);
+		if (key->serial < xkey->serial)
+			goto attempt_insertion;
+	}
+}
+
+/**
+ * key_alloc - Allocate a key of the specified type.
+ * @type: The type of key to allocate.
+ * @desc: The key description to allow the key to be searched out.
+ * @uid: The owner of the new key.
+ * @gid: The group ID for the new key's group permissions.
+ * @cred: The credentials specifying UID namespace.
+ * @perm: The permissions mask of the new key.
+ * @flags: Flags specifying quota properties.
+ * @restrict_link: Optional link restriction for new keyrings.
+ *
+ * Allocate a key of the specified type with the attributes given.  The key is
+ * returned in an uninstantiated state and the caller needs to instantiate the
+ * key before returning.
+ *
+ * The restrict_link structure (if not NULL) will be freed when the
+ * keyring is destroyed, so it must be dynamically allocated.
+ *
+ * The user's key count quota is updated to reflect the creation of the key and
+ * the user's key data quota has the default for the key type reserved.  The
+ * instantiation function should amend this as necessary.  If insufficient
+ * quota is available, -EDQUOT will be returned.
+ *
+ * The LSM security modules can prevent a key being created, in which case
+ * -EACCES will be returned.
+ *
+ * Returns a pointer to the new key if successful and an error code otherwise.
+ *
+ * Note that the caller needs to ensure the key type isn't uninstantiated.
+ * Internally this can be done by locking key_types_sem.  Externally, this can
+ * be done by either never unregistering the key type, or making sure
+ * key_alloc() calls don't race with module unloading.
+ */
+struct key *key_alloc(struct key_type *type, const char *desc,
+		      kuid_t uid, kgid_t gid, const struct cred *cred,
+		      key_perm_t perm, unsigned long flags,
+		      struct key_restriction *restrict_link)
+{
+	struct key_user *user = NULL;
+	struct key *key;
+	size_t desclen, quotalen;
+	int ret;
+	unsigned long irqflags;
+
+	key = ERR_PTR(-EINVAL);
+	if (!desc || !*desc)
+		goto error;
+
+	if (type->vet_description) {
+		ret = type->vet_description(desc);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
+	desclen = strlen(desc);
+	quotalen = desclen + 1 + type->def_datalen;
+
+	/* get hold of the key tracking for this user */
+	user = key_user_lookup(uid);
+	if (!user)
+		goto no_memory_1;
+
+	/* check that the user's quota permits allocation of another key and
+	 * its description */
+	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) {
+		unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ?
+			key_quota_root_maxkeys : key_quota_maxkeys;
+		unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ?
+			key_quota_root_maxbytes : key_quota_maxbytes;
+
+		spin_lock_irqsave(&user->lock, irqflags);
+		if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) {
+			if (user->qnkeys + 1 > maxkeys ||
+			    user->qnbytes + quotalen > maxbytes ||
+			    user->qnbytes + quotalen < user->qnbytes)
+				goto no_quota;
+		}
+
+		user->qnkeys++;
+		user->qnbytes += quotalen;
+		spin_unlock_irqrestore(&user->lock, irqflags);
+	}
+
+	/* allocate and initialise the key and its description */
+	key = kmem_cache_zalloc(key_jar, GFP_KERNEL);
+	if (!key)
+		goto no_memory_2;
+
+	key->index_key.desc_len = desclen;
+	key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL);
+	if (!key->index_key.description)
+		goto no_memory_3;
+	key->index_key.type = type;
+	key_set_index_key(&key->index_key);
+
+	refcount_set(&key->usage, 1);
+	init_rwsem(&key->sem);
+	lockdep_set_class(&key->sem, &type->lock_class);
+	key->user = user;
+	key->quotalen = quotalen;
+	key->datalen = type->def_datalen;
+	key->uid = uid;
+	key->gid = gid;
+	key->perm = perm;
+	key->expiry = TIME64_MAX;
+	key->restrict_link = restrict_link;
+	key->last_used_at = ktime_get_real_seconds();
+
+	key->flags |= 1 << KEY_FLAG_USER_ALIVE;
+	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
+		key->flags |= 1 << KEY_FLAG_IN_QUOTA;
+	if (flags & KEY_ALLOC_BUILT_IN)
+		key->flags |= 1 << KEY_FLAG_BUILTIN;
+	if (flags & KEY_ALLOC_UID_KEYRING)
+		key->flags |= 1 << KEY_FLAG_UID_KEYRING;
+	if (flags & KEY_ALLOC_SET_KEEP)
+		key->flags |= 1 << KEY_FLAG_KEEP;
+
+#ifdef KEY_DEBUGGING
+	key->magic = KEY_DEBUG_MAGIC;
+#endif
+
+	/* let the security module know about the key */
+	ret = security_key_alloc(key, cred, flags);
+	if (ret < 0)
+		goto security_error;
+
+	/* publish the key by giving it a serial number */
+	refcount_inc(&key->domain_tag->usage);
+	atomic_inc(&user->nkeys);
+	key_alloc_serial(key);
+
+error:
+	return key;
+
+security_error:
+	kfree(key->description);
+	kmem_cache_free(key_jar, key);
+	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) {
+		spin_lock_irqsave(&user->lock, irqflags);
+		user->qnkeys--;
+		user->qnbytes -= quotalen;
+		spin_unlock_irqrestore(&user->lock, irqflags);
+	}
+	key_user_put(user);
+	key = ERR_PTR(ret);
+	goto error;
+
+no_memory_3:
+	kmem_cache_free(key_jar, key);
+no_memory_2:
+	if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) {
+		spin_lock_irqsave(&user->lock, irqflags);
+		user->qnkeys--;
+		user->qnbytes -= quotalen;
+		spin_unlock_irqrestore(&user->lock, irqflags);
+	}
+	key_user_put(user);
+no_memory_1:
+	key = ERR_PTR(-ENOMEM);
+	goto error;
+
+no_quota:
+	spin_unlock_irqrestore(&user->lock, irqflags);
+	key_user_put(user);
+	key = ERR_PTR(-EDQUOT);
+	goto error;
+}
+EXPORT_SYMBOL(key_alloc);
+
+/**
+ * key_payload_reserve - Adjust data quota reservation for the key's payload
+ * @key: The key to make the reservation for.
+ * @datalen: The amount of data payload the caller now wants.
+ *
+ * Adjust the amount of the owning user's key data quota that a key reserves.
+ * If the amount is increased, then -EDQUOT may be returned if there isn't
+ * enough free quota available.
+ *
+ * If successful, 0 is returned.
+ */
+int key_payload_reserve(struct key *key, size_t datalen)
+{
+	int delta = (int)datalen - key->datalen;
+	int ret = 0;
+
+	key_check(key);
+
+	/* contemplate the quota adjustment */
+	if (delta != 0 && test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+		unsigned maxbytes = uid_eq(key->user->uid, GLOBAL_ROOT_UID) ?
+			key_quota_root_maxbytes : key_quota_maxbytes;
+		unsigned long flags;
+
+		spin_lock_irqsave(&key->user->lock, flags);
+
+		if (delta > 0 &&
+		    (key->user->qnbytes + delta > maxbytes ||
+		     key->user->qnbytes + delta < key->user->qnbytes)) {
+			ret = -EDQUOT;
+		}
+		else {
+			key->user->qnbytes += delta;
+			key->quotalen += delta;
+		}
+		spin_unlock_irqrestore(&key->user->lock, flags);
+	}
+
+	/* change the recorded data length if that didn't generate an error */
+	if (ret == 0)
+		key->datalen = datalen;
+
+	return ret;
+}
+EXPORT_SYMBOL(key_payload_reserve);
+
+/*
+ * Change the key state to being instantiated.
+ */
+static void mark_key_instantiated(struct key *key, int reject_error)
+{
+	/* Commit the payload before setting the state; barrier versus
+	 * key_read_state().
+	 */
+	smp_store_release(&key->state,
+			  (reject_error < 0) ? reject_error : KEY_IS_POSITIVE);
+}
+
+/*
+ * Instantiate a key and link it into the target keyring atomically.  Must be
+ * called with the target keyring's semaphore writelocked.  The target key's
+ * semaphore need not be locked as instantiation is serialised by
+ * key_construction_mutex.
+ */
+static int __key_instantiate_and_link(struct key *key,
+				      struct key_preparsed_payload *prep,
+				      struct key *keyring,
+				      struct key *authkey,
+				      struct assoc_array_edit **_edit)
+{
+	int ret, awaken;
+
+	key_check(key);
+	key_check(keyring);
+
+	awaken = 0;
+	ret = -EBUSY;
+
+	mutex_lock(&key_construction_mutex);
+
+	/* can't instantiate twice */
+	if (key->state == KEY_IS_UNINSTANTIATED) {
+		/* instantiate the key */
+		ret = key->type->instantiate(key, prep);
+
+		if (ret == 0) {
+			/* mark the key as being instantiated */
+			atomic_inc(&key->user->nikeys);
+			mark_key_instantiated(key, 0);
+			notify_key(key, NOTIFY_KEY_INSTANTIATED, 0);
+
+			if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
+				awaken = 1;
+
+			/* and link it into the destination keyring */
+			if (keyring) {
+				if (test_bit(KEY_FLAG_KEEP, &keyring->flags))
+					set_bit(KEY_FLAG_KEEP, &key->flags);
+
+				__key_link(keyring, key, _edit);
+			}
+
+			/* disable the authorisation key */
+			if (authkey)
+				key_invalidate(authkey);
+
+			if (prep->expiry != TIME64_MAX)
+				key_set_expiry(key, prep->expiry);
+		}
+	}
+
+	mutex_unlock(&key_construction_mutex);
+
+	/* wake up anyone waiting for a key to be constructed */
+	if (awaken)
+		wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT);
+
+	return ret;
+}
+
+/**
+ * key_instantiate_and_link - Instantiate a key and link it into the keyring.
+ * @key: The key to instantiate.
+ * @data: The data to use to instantiate the keyring.
+ * @datalen: The length of @data.
+ * @keyring: Keyring to create a link in on success (or NULL).
+ * @authkey: The authorisation token permitting instantiation.
+ *
+ * Instantiate a key that's in the uninstantiated state using the provided data
+ * and, if successful, link it in to the destination keyring if one is
+ * supplied.
+ *
+ * If successful, 0 is returned, the authorisation token is revoked and anyone
+ * waiting for the key is woken up.  If the key was already instantiated,
+ * -EBUSY will be returned.
+ */
+int key_instantiate_and_link(struct key *key,
+			     const void *data,
+			     size_t datalen,
+			     struct key *keyring,
+			     struct key *authkey)
+{
+	struct key_preparsed_payload prep;
+	struct assoc_array_edit *edit = NULL;
+	int ret;
+
+	memset(&prep, 0, sizeof(prep));
+	prep.orig_description = key->description;
+	prep.data = data;
+	prep.datalen = datalen;
+	prep.quotalen = key->type->def_datalen;
+	prep.expiry = TIME64_MAX;
+	if (key->type->preparse) {
+		ret = key->type->preparse(&prep);
+		if (ret < 0)
+			goto error;
+	}
+
+	if (keyring) {
+		ret = __key_link_lock(keyring, &key->index_key);
+		if (ret < 0)
+			goto error;
+
+		ret = __key_link_begin(keyring, &key->index_key, &edit);
+		if (ret < 0)
+			goto error_link_end;
+
+		if (keyring->restrict_link && keyring->restrict_link->check) {
+			struct key_restriction *keyres = keyring->restrict_link;
+
+			ret = keyres->check(keyring, key->type, &prep.payload,
+					    keyres->key);
+			if (ret < 0)
+				goto error_link_end;
+		}
+	}
+
+	ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit);
+
+error_link_end:
+	if (keyring)
+		__key_link_end(keyring, &key->index_key, edit);
+
+error:
+	if (key->type->preparse)
+		key->type->free_preparse(&prep);
+	return ret;
+}
+
+EXPORT_SYMBOL(key_instantiate_and_link);
+
+/**
+ * key_reject_and_link - Negatively instantiate a key and link it into the keyring.
+ * @key: The key to instantiate.
+ * @timeout: The timeout on the negative key.
+ * @error: The error to return when the key is hit.
+ * @keyring: Keyring to create a link in on success (or NULL).
+ * @authkey: The authorisation token permitting instantiation.
+ *
+ * Negatively instantiate a key that's in the uninstantiated state and, if
+ * successful, set its timeout and stored error and link it in to the
+ * destination keyring if one is supplied.  The key and any links to the key
+ * will be automatically garbage collected after the timeout expires.
+ *
+ * Negative keys are used to rate limit repeated request_key() calls by causing
+ * them to return the stored error code (typically ENOKEY) until the negative
+ * key expires.
+ *
+ * If successful, 0 is returned, the authorisation token is revoked and anyone
+ * waiting for the key is woken up.  If the key was already instantiated,
+ * -EBUSY will be returned.
+ */
+int key_reject_and_link(struct key *key,
+			unsigned timeout,
+			unsigned error,
+			struct key *keyring,
+			struct key *authkey)
+{
+	struct assoc_array_edit *edit = NULL;
+	int ret, awaken, link_ret = 0;
+
+	key_check(key);
+	key_check(keyring);
+
+	awaken = 0;
+	ret = -EBUSY;
+
+	if (keyring) {
+		if (keyring->restrict_link)
+			return -EPERM;
+
+		link_ret = __key_link_lock(keyring, &key->index_key);
+		if (link_ret == 0) {
+			link_ret = __key_link_begin(keyring, &key->index_key, &edit);
+			if (link_ret < 0)
+				__key_link_end(keyring, &key->index_key, edit);
+		}
+	}
+
+	mutex_lock(&key_construction_mutex);
+
+	/* can't instantiate twice */
+	if (key->state == KEY_IS_UNINSTANTIATED) {
+		/* mark the key as being negatively instantiated */
+		atomic_inc(&key->user->nikeys);
+		mark_key_instantiated(key, -error);
+		notify_key(key, NOTIFY_KEY_INSTANTIATED, -error);
+		key_set_expiry(key, ktime_get_real_seconds() + timeout);
+
+		if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
+			awaken = 1;
+
+		ret = 0;
+
+		/* and link it into the destination keyring */
+		if (keyring && link_ret == 0)
+			__key_link(keyring, key, &edit);
+
+		/* disable the authorisation key */
+		if (authkey)
+			key_invalidate(authkey);
+	}
+
+	mutex_unlock(&key_construction_mutex);
+
+	if (keyring && link_ret == 0)
+		__key_link_end(keyring, &key->index_key, edit);
+
+	/* wake up anyone waiting for a key to be constructed */
+	if (awaken)
+		wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT);
+
+	return ret == 0 ? link_ret : ret;
+}
+EXPORT_SYMBOL(key_reject_and_link);
+
+/**
+ * key_put - Discard a reference to a key.
+ * @key: The key to discard a reference from.
+ *
+ * Discard a reference to a key, and when all the references are gone, we
+ * schedule the cleanup task to come and pull it out of the tree in process
+ * context at some later time.
+ */
+void key_put(struct key *key)
+{
+	if (key) {
+		key_check(key);
+
+		if (refcount_dec_and_test(&key->usage)) {
+			unsigned long flags;
+
+			/* deal with the user's key tracking and quota */
+			if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+				spin_lock_irqsave(&key->user->lock, flags);
+				key->user->qnkeys--;
+				key->user->qnbytes -= key->quotalen;
+				spin_unlock_irqrestore(&key->user->lock, flags);
+			}
+			/* Mark key as safe for GC after key->user done. */
+			clear_bit_unlock(KEY_FLAG_USER_ALIVE, &key->flags);
+			schedule_work(&key_gc_work);
+		}
+	}
+}
+EXPORT_SYMBOL(key_put);
+
+/*
+ * Find a key by its serial number.
+ */
+struct key *key_lookup(key_serial_t id)
+{
+	struct rb_node *n;
+	struct key *key;
+
+	spin_lock(&key_serial_lock);
+
+	/* search the tree for the specified key */
+	n = key_serial_tree.rb_node;
+	while (n) {
+		key = rb_entry(n, struct key, serial_node);
+
+		if (id < key->serial)
+			n = n->rb_left;
+		else if (id > key->serial)
+			n = n->rb_right;
+		else
+			goto found;
+	}
+
+not_found:
+	key = ERR_PTR(-ENOKEY);
+	goto error;
+
+found:
+	/* A key is allowed to be looked up only if someone still owns a
+	 * reference to it - otherwise it's awaiting the gc.
+	 */
+	if (!refcount_inc_not_zero(&key->usage))
+		goto not_found;
+
+error:
+	spin_unlock(&key_serial_lock);
+	return key;
+}
+EXPORT_SYMBOL(key_lookup);
+
+/*
+ * Find and lock the specified key type against removal.
+ *
+ * We return with the sem read-locked if successful.  If the type wasn't
+ * available -ENOKEY is returned instead.
+ */
+struct key_type *key_type_lookup(const char *type)
+{
+	struct key_type *ktype;
+
+	down_read(&key_types_sem);
+
+	/* look up the key type to see if it's one of the registered kernel
+	 * types */
+	list_for_each_entry(ktype, &key_types_list, link) {
+		if (strcmp(ktype->name, type) == 0)
+			goto found_kernel_type;
+	}
+
+	up_read(&key_types_sem);
+	ktype = ERR_PTR(-ENOKEY);
+
+found_kernel_type:
+	return ktype;
+}
+
+void key_set_timeout(struct key *key, unsigned timeout)
+{
+	time64_t expiry = TIME64_MAX;
+
+	/* make the changes with the locks held to prevent races */
+	down_write(&key->sem);
+
+	if (timeout > 0)
+		expiry = ktime_get_real_seconds() + timeout;
+	key_set_expiry(key, expiry);
+
+	up_write(&key->sem);
+}
+EXPORT_SYMBOL_GPL(key_set_timeout);
+
+/*
+ * Unlock a key type locked by key_type_lookup().
+ */
+void key_type_put(struct key_type *ktype)
+{
+	up_read(&key_types_sem);
+}
+
+/*
+ * Attempt to update an existing key.
+ *
+ * The key is given to us with an incremented refcount that we need to discard
+ * if we get an error.
+ */
+static inline key_ref_t __key_update(key_ref_t key_ref,
+				     struct key_preparsed_payload *prep)
+{
+	struct key *key = key_ref_to_ptr(key_ref);
+	int ret;
+
+	/* need write permission on the key to update it */
+	ret = key_permission(key_ref, KEY_NEED_WRITE);
+	if (ret < 0)
+		goto error;
+
+	ret = -EEXIST;
+	if (!key->type->update)
+		goto error;
+
+	down_write(&key->sem);
+
+	ret = key->type->update(key, prep);
+	if (ret == 0) {
+		/* Updating a negative key positively instantiates it */
+		mark_key_instantiated(key, 0);
+		notify_key(key, NOTIFY_KEY_UPDATED, 0);
+	}
+
+	up_write(&key->sem);
+
+	if (ret < 0)
+		goto error;
+out:
+	return key_ref;
+
+error:
+	key_put(key);
+	key_ref = ERR_PTR(ret);
+	goto out;
+}
+
+/*
+ * Create or potentially update a key. The combined logic behind
+ * key_create_or_update() and key_create()
+ */
+static key_ref_t __key_create_or_update(key_ref_t keyring_ref,
+					const char *type,
+					const char *description,
+					const void *payload,
+					size_t plen,
+					key_perm_t perm,
+					unsigned long flags,
+					bool allow_update)
+{
+	struct keyring_index_key index_key = {
+		.description	= description,
+	};
+	struct key_preparsed_payload prep;
+	struct assoc_array_edit *edit = NULL;
+	const struct cred *cred = current_cred();
+	struct key *keyring, *key = NULL;
+	key_ref_t key_ref;
+	int ret;
+	struct key_restriction *restrict_link = NULL;
+
+	/* look up the key type to see if it's one of the registered kernel
+	 * types */
+	index_key.type = key_type_lookup(type);
+	if (IS_ERR(index_key.type)) {
+		key_ref = ERR_PTR(-ENODEV);
+		goto error;
+	}
+
+	key_ref = ERR_PTR(-EINVAL);
+	if (!index_key.type->instantiate ||
+	    (!index_key.description && !index_key.type->preparse))
+		goto error_put_type;
+
+	keyring = key_ref_to_ptr(keyring_ref);
+
+	key_check(keyring);
+
+	if (!(flags & KEY_ALLOC_BYPASS_RESTRICTION))
+		restrict_link = keyring->restrict_link;
+
+	key_ref = ERR_PTR(-ENOTDIR);
+	if (keyring->type != &key_type_keyring)
+		goto error_put_type;
+
+	memset(&prep, 0, sizeof(prep));
+	prep.orig_description = description;
+	prep.data = payload;
+	prep.datalen = plen;
+	prep.quotalen = index_key.type->def_datalen;
+	prep.expiry = TIME64_MAX;
+	if (index_key.type->preparse) {
+		ret = index_key.type->preparse(&prep);
+		if (ret < 0) {
+			key_ref = ERR_PTR(ret);
+			goto error_free_prep;
+		}
+		if (!index_key.description)
+			index_key.description = prep.description;
+		key_ref = ERR_PTR(-EINVAL);
+		if (!index_key.description)
+			goto error_free_prep;
+	}
+	index_key.desc_len = strlen(index_key.description);
+	key_set_index_key(&index_key);
+
+	ret = __key_link_lock(keyring, &index_key);
+	if (ret < 0) {
+		key_ref = ERR_PTR(ret);
+		goto error_free_prep;
+	}
+
+	ret = __key_link_begin(keyring, &index_key, &edit);
+	if (ret < 0) {
+		key_ref = ERR_PTR(ret);
+		goto error_link_end;
+	}
+
+	if (restrict_link && restrict_link->check) {
+		ret = restrict_link->check(keyring, index_key.type,
+					   &prep.payload, restrict_link->key);
+		if (ret < 0) {
+			key_ref = ERR_PTR(ret);
+			goto error_link_end;
+		}
+	}
+
+	/* if we're going to allocate a new key, we're going to have
+	 * to modify the keyring */
+	ret = key_permission(keyring_ref, KEY_NEED_WRITE);
+	if (ret < 0) {
+		key_ref = ERR_PTR(ret);
+		goto error_link_end;
+	}
+
+	/* if it's requested and possible to update this type of key, search
+	 * for an existing key of the same type and description in the
+	 * destination keyring and update that instead if possible
+	 */
+	if (allow_update) {
+		if (index_key.type->update) {
+			key_ref = find_key_to_update(keyring_ref, &index_key);
+			if (key_ref)
+				goto found_matching_key;
+		}
+	} else {
+		key_ref = find_key_to_update(keyring_ref, &index_key);
+		if (key_ref) {
+			key_ref_put(key_ref);
+			key_ref = ERR_PTR(-EEXIST);
+			goto error_link_end;
+		}
+	}
+
+	/* if the client doesn't provide, decide on the permissions we want */
+	if (perm == KEY_PERM_UNDEF) {
+		perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
+		perm |= KEY_USR_VIEW;
+
+		if (index_key.type->read)
+			perm |= KEY_POS_READ;
+
+		if (index_key.type == &key_type_keyring ||
+		    index_key.type->update)
+			perm |= KEY_POS_WRITE;
+	}
+
+	/* allocate a new key */
+	key = key_alloc(index_key.type, index_key.description,
+			cred->fsuid, cred->fsgid, cred, perm, flags, NULL);
+	if (IS_ERR(key)) {
+		key_ref = ERR_CAST(key);
+		goto error_link_end;
+	}
+
+	/* instantiate it and link it into the target keyring */
+	ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit);
+	if (ret < 0) {
+		key_put(key);
+		key_ref = ERR_PTR(ret);
+		goto error_link_end;
+	}
+
+	security_key_post_create_or_update(keyring, key, payload, plen, flags,
+					   true);
+
+	key_ref = make_key_ref(key, is_key_possessed(keyring_ref));
+
+error_link_end:
+	__key_link_end(keyring, &index_key, edit);
+error_free_prep:
+	if (index_key.type->preparse)
+		index_key.type->free_preparse(&prep);
+error_put_type:
+	key_type_put(index_key.type);
+error:
+	return key_ref;
+
+ found_matching_key:
+	/* we found a matching key, so we're going to try to update it
+	 * - we can drop the locks first as we have the key pinned
+	 */
+	__key_link_end(keyring, &index_key, edit);
+
+	key = key_ref_to_ptr(key_ref);
+	if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) {
+		ret = wait_for_key_construction(key, true);
+		if (ret < 0) {
+			key_ref_put(key_ref);
+			key_ref = ERR_PTR(ret);
+			goto error_free_prep;
+		}
+	}
+
+	key_ref = __key_update(key_ref, &prep);
+
+	if (!IS_ERR(key_ref))
+		security_key_post_create_or_update(keyring, key, payload, plen,
+						   flags, false);
+
+	goto error_free_prep;
+}
+
+/**
+ * key_create_or_update - Update or create and instantiate a key.
+ * @keyring_ref: A pointer to the destination keyring with possession flag.
+ * @type: The type of key.
+ * @description: The searchable description for the key.
+ * @payload: The data to use to instantiate or update the key.
+ * @plen: The length of @payload.
+ * @perm: The permissions mask for a new key.
+ * @flags: The quota flags for a new key.
+ *
+ * Search the destination keyring for a key of the same description and if one
+ * is found, update it, otherwise create and instantiate a new one and create a
+ * link to it from that keyring.
+ *
+ * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be
+ * concocted.
+ *
+ * Returns a pointer to the new key if successful, -ENODEV if the key type
+ * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the
+ * caller isn't permitted to modify the keyring or the LSM did not permit
+ * creation of the key.
+ *
+ * On success, the possession flag from the keyring ref will be tacked on to
+ * the key ref before it is returned.
+ */
+key_ref_t key_create_or_update(key_ref_t keyring_ref,
+			       const char *type,
+			       const char *description,
+			       const void *payload,
+			       size_t plen,
+			       key_perm_t perm,
+			       unsigned long flags)
+{
+	return __key_create_or_update(keyring_ref, type, description, payload,
+				      plen, perm, flags, true);
+}
+EXPORT_SYMBOL(key_create_or_update);
+
+/**
+ * key_create - Create and instantiate a key.
+ * @keyring_ref: A pointer to the destination keyring with possession flag.
+ * @type: The type of key.
+ * @description: The searchable description for the key.
+ * @payload: The data to use to instantiate or update the key.
+ * @plen: The length of @payload.
+ * @perm: The permissions mask for a new key.
+ * @flags: The quota flags for a new key.
+ *
+ * Create and instantiate a new key and link to it from the destination keyring.
+ *
+ * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be
+ * concocted.
+ *
+ * Returns a pointer to the new key if successful, -EEXIST if a key with the
+ * same description already exists, -ENODEV if the key type wasn't available,
+ * -ENOTDIR if the keyring wasn't a keyring, -EACCES if the caller isn't
+ * permitted to modify the keyring or the LSM did not permit creation of the
+ * key.
+ *
+ * On success, the possession flag from the keyring ref will be tacked on to
+ * the key ref before it is returned.
+ */
+key_ref_t key_create(key_ref_t keyring_ref,
+		     const char *type,
+		     const char *description,
+		     const void *payload,
+		     size_t plen,
+		     key_perm_t perm,
+		     unsigned long flags)
+{
+	return __key_create_or_update(keyring_ref, type, description, payload,
+				      plen, perm, flags, false);
+}
+EXPORT_SYMBOL(key_create);
+
+/**
+ * key_update - Update a key's contents.
+ * @key_ref: The pointer (plus possession flag) to the key.
+ * @payload: The data to be used to update the key.
+ * @plen: The length of @payload.
+ *
+ * Attempt to update the contents of a key with the given payload data.  The
+ * caller must be granted Write permission on the key.  Negative keys can be
+ * instantiated by this method.
+ *
+ * Returns 0 on success, -EACCES if not permitted and -EOPNOTSUPP if the key
+ * type does not support updating.  The key type may return other errors.
+ */
+int key_update(key_ref_t key_ref, const void *payload, size_t plen)
+{
+	struct key_preparsed_payload prep;
+	struct key *key = key_ref_to_ptr(key_ref);
+	int ret;
+
+	key_check(key);
+
+	/* the key must be writable */
+	ret = key_permission(key_ref, KEY_NEED_WRITE);
+	if (ret < 0)
+		return ret;
+
+	/* attempt to update it if supported */
+	if (!key->type->update)
+		return -EOPNOTSUPP;
+
+	memset(&prep, 0, sizeof(prep));
+	prep.data = payload;
+	prep.datalen = plen;
+	prep.quotalen = key->type->def_datalen;
+	prep.expiry = TIME64_MAX;
+	if (key->type->preparse) {
+		ret = key->type->preparse(&prep);
+		if (ret < 0)
+			goto error;
+	}
+
+	down_write(&key->sem);
+
+	ret = key->type->update(key, &prep);
+	if (ret == 0) {
+		/* Updating a negative key positively instantiates it */
+		mark_key_instantiated(key, 0);
+		notify_key(key, NOTIFY_KEY_UPDATED, 0);
+	}
+
+	up_write(&key->sem);
+
+error:
+	if (key->type->preparse)
+		key->type->free_preparse(&prep);
+	return ret;
+}
+EXPORT_SYMBOL(key_update);
+
+/**
+ * key_revoke - Revoke a key.
+ * @key: The key to be revoked.
+ *
+ * Mark a key as being revoked and ask the type to free up its resources.  The
+ * revocation timeout is set and the key and all its links will be
+ * automatically garbage collected after key_gc_delay amount of time if they
+ * are not manually dealt with first.
+ */
+void key_revoke(struct key *key)
+{
+	time64_t time;
+
+	key_check(key);
+
+	/* make sure no one's trying to change or use the key when we mark it
+	 * - we tell lockdep that we might nest because we might be revoking an
+	 *   authorisation key whilst holding the sem on a key we've just
+	 *   instantiated
+	 */
+	down_write_nested(&key->sem, 1);
+	if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) {
+		notify_key(key, NOTIFY_KEY_REVOKED, 0);
+		if (key->type->revoke)
+			key->type->revoke(key);
+
+		/* set the death time to no more than the expiry time */
+		time = ktime_get_real_seconds();
+		if (key->revoked_at == 0 || key->revoked_at > time) {
+			key->revoked_at = time;
+			key_schedule_gc(key->revoked_at + key_gc_delay);
+		}
+	}
+
+	up_write(&key->sem);
+}
+EXPORT_SYMBOL(key_revoke);
+
+/**
+ * key_invalidate - Invalidate a key.
+ * @key: The key to be invalidated.
+ *
+ * Mark a key as being invalidated and have it cleaned up immediately.  The key
+ * is ignored by all searches and other operations from this point.
+ */
+void key_invalidate(struct key *key)
+{
+	kenter("%d", key_serial(key));
+
+	key_check(key);
+
+	if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) {
+		down_write_nested(&key->sem, 1);
+		if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) {
+			notify_key(key, NOTIFY_KEY_INVALIDATED, 0);
+			key_schedule_gc_links();
+		}
+		up_write(&key->sem);
+	}
+}
+EXPORT_SYMBOL(key_invalidate);
+
+/**
+ * generic_key_instantiate - Simple instantiation of a key from preparsed data
+ * @key: The key to be instantiated
+ * @prep: The preparsed data to load.
+ *
+ * Instantiate a key from preparsed data.  We assume we can just copy the data
+ * in directly and clear the old pointers.
+ *
+ * This can be pointed to directly by the key type instantiate op pointer.
+ */
+int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
+{
+	int ret;
+
+	pr_devel("==>%s()\n", __func__);
+
+	ret = key_payload_reserve(key, prep->quotalen);
+	if (ret == 0) {
+		rcu_assign_keypointer(key, prep->payload.data[0]);
+		key->payload.data[1] = prep->payload.data[1];
+		key->payload.data[2] = prep->payload.data[2];
+		key->payload.data[3] = prep->payload.data[3];
+		prep->payload.data[0] = NULL;
+		prep->payload.data[1] = NULL;
+		prep->payload.data[2] = NULL;
+		prep->payload.data[3] = NULL;
+	}
+	pr_devel("<==%s() = %d\n", __func__, ret);
+	return ret;
+}
+EXPORT_SYMBOL(generic_key_instantiate);
+
+/**
+ * register_key_type - Register a type of key.
+ * @ktype: The new key type.
+ *
+ * Register a new key type.
+ *
+ * Returns 0 on success or -EEXIST if a type of this name already exists.
+ */
+int register_key_type(struct key_type *ktype)
+{
+	struct key_type *p;
+	int ret;
+
+	memset(&ktype->lock_class, 0, sizeof(ktype->lock_class));
+
+	ret = -EEXIST;
+	down_write(&key_types_sem);
+
+	/* disallow key types with the same name */
+	list_for_each_entry(p, &key_types_list, link) {
+		if (strcmp(p->name, ktype->name) == 0)
+			goto out;
+	}
+
+	/* store the type */
+	list_add(&ktype->link, &key_types_list);
+
+	pr_notice("Key type %s registered\n", ktype->name);
+	ret = 0;
+
+out:
+	up_write(&key_types_sem);
+	return ret;
+}
+EXPORT_SYMBOL(register_key_type);
+
+/**
+ * unregister_key_type - Unregister a type of key.
+ * @ktype: The key type.
+ *
+ * Unregister a key type and mark all the extant keys of this type as dead.
+ * Those keys of this type are then destroyed to get rid of their payloads and
+ * they and their links will be garbage collected as soon as possible.
+ */
+void unregister_key_type(struct key_type *ktype)
+{
+	down_write(&key_types_sem);
+	list_del_init(&ktype->link);
+	downgrade_write(&key_types_sem);
+	key_gc_keytype(ktype);
+	pr_notice("Key type %s unregistered\n", ktype->name);
+	up_read(&key_types_sem);
+}
+EXPORT_SYMBOL(unregister_key_type);
+
+/*
+ * Initialise the key management state.
+ */
+void __init key_init(void)
+{
+	/* allocate a slab in which we can store keys */
+	key_jar = kmem_cache_create("key_jar", sizeof(struct key),
+			0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_NO_MERGE, NULL);
+
+	/* add the special key types */
+	list_add_tail(&key_type_keyring.link, &key_types_list);
+	list_add_tail(&key_type_dead.link, &key_types_list);
+	list_add_tail(&key_type_user.link, &key_types_list);
+	list_add_tail(&key_type_logon.link, &key_types_list);
+
+	/* record the root user tracking */
+	rb_link_node(&root_key_user.node,
+		     NULL,
+		     &key_user_tree.rb_node);
+
+	rb_insert_color(&root_key_user.node,
+			&key_user_tree);
+}
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
new file mode 100644
index 000000000..d14ace88e
--- /dev/null
+++ b/security/keys/keyctl.c
@@ -0,0 +1,2038 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Userspace key control operations
+ *
+ * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/fs.h>
+#include <linux/capability.h>
+#include <linux/cred.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/security.h>
+#include <linux/uio.h>
+#include <linux/uaccess.h>
+#include <keys/request_key_auth-type.h>
+#include "internal.h"
+
+#define KEY_MAX_DESC_SIZE 4096
+
+static const unsigned char keyrings_capabilities[2] = {
+	[0] = (KEYCTL_CAPS0_CAPABILITIES |
+	       (IS_ENABLED(CONFIG_PERSISTENT_KEYRINGS)	? KEYCTL_CAPS0_PERSISTENT_KEYRINGS : 0) |
+	       (IS_ENABLED(CONFIG_KEY_DH_OPERATIONS)	? KEYCTL_CAPS0_DIFFIE_HELLMAN : 0) |
+	       (IS_ENABLED(CONFIG_ASYMMETRIC_KEY_TYPE)	? KEYCTL_CAPS0_PUBLIC_KEY : 0) |
+	       (IS_ENABLED(CONFIG_BIG_KEYS)		? KEYCTL_CAPS0_BIG_KEY : 0) |
+	       KEYCTL_CAPS0_INVALIDATE |
+	       KEYCTL_CAPS0_RESTRICT_KEYRING |
+	       KEYCTL_CAPS0_MOVE
+	       ),
+	[1] = (KEYCTL_CAPS1_NS_KEYRING_NAME |
+	       KEYCTL_CAPS1_NS_KEY_TAG |
+	       (IS_ENABLED(CONFIG_KEY_NOTIFICATIONS)	? KEYCTL_CAPS1_NOTIFICATIONS : 0)
+	       ),
+};
+
+static int key_get_type_from_user(char *type,
+				  const char __user *_type,
+				  unsigned len)
+{
+	int ret;
+
+	ret = strncpy_from_user(type, _type, len);
+	if (ret < 0)
+		return ret;
+	if (ret == 0 || ret >= len)
+		return -EINVAL;
+	if (type[0] == '.')
+		return -EPERM;
+	type[len - 1] = '\0';
+	return 0;
+}
+
+/*
+ * Extract the description of a new key from userspace and either add it as a
+ * new key to the specified keyring or update a matching key in that keyring.
+ *
+ * If the description is NULL or an empty string, the key type is asked to
+ * generate one from the payload.
+ *
+ * The keyring must be writable so that we can attach the key to it.
+ *
+ * If successful, the new key's serial number is returned, otherwise an error
+ * code is returned.
+ */
+SYSCALL_DEFINE5(add_key, const char __user *, _type,
+		const char __user *, _description,
+		const void __user *, _payload,
+		size_t, plen,
+		key_serial_t, ringid)
+{
+	key_ref_t keyring_ref, key_ref;
+	char type[32], *description;
+	void *payload;
+	long ret;
+
+	ret = -EINVAL;
+	if (plen > 1024 * 1024 - 1)
+		goto error;
+
+	/* draw all the data into kernel space */
+	ret = key_get_type_from_user(type, _type, sizeof(type));
+	if (ret < 0)
+		goto error;
+
+	description = NULL;
+	if (_description) {
+		description = strndup_user(_description, KEY_MAX_DESC_SIZE);
+		if (IS_ERR(description)) {
+			ret = PTR_ERR(description);
+			goto error;
+		}
+		if (!*description) {
+			kfree(description);
+			description = NULL;
+		} else if ((description[0] == '.') &&
+			   (strncmp(type, "keyring", 7) == 0)) {
+			ret = -EPERM;
+			goto error2;
+		}
+	}
+
+	/* pull the payload in if one was supplied */
+	payload = NULL;
+
+	if (plen) {
+		ret = -ENOMEM;
+		payload = kvmalloc(plen, GFP_KERNEL);
+		if (!payload)
+			goto error2;
+
+		ret = -EFAULT;
+		if (copy_from_user(payload, _payload, plen) != 0)
+			goto error3;
+	}
+
+	/* find the target keyring (which must be writable) */
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(keyring_ref)) {
+		ret = PTR_ERR(keyring_ref);
+		goto error3;
+	}
+
+	/* create or update the requested key and add it to the target
+	 * keyring */
+	key_ref = key_create_or_update(keyring_ref, type, description,
+				       payload, plen, KEY_PERM_UNDEF,
+				       KEY_ALLOC_IN_QUOTA);
+	if (!IS_ERR(key_ref)) {
+		ret = key_ref_to_ptr(key_ref)->serial;
+		key_ref_put(key_ref);
+	}
+	else {
+		ret = PTR_ERR(key_ref);
+	}
+
+	key_ref_put(keyring_ref);
+ error3:
+	kvfree_sensitive(payload, plen);
+ error2:
+	kfree(description);
+ error:
+	return ret;
+}
+
+/*
+ * Search the process keyrings and keyring trees linked from those for a
+ * matching key.  Keyrings must have appropriate Search permission to be
+ * searched.
+ *
+ * If a key is found, it will be attached to the destination keyring if there's
+ * one specified and the serial number of the key will be returned.
+ *
+ * If no key is found, /sbin/request-key will be invoked if _callout_info is
+ * non-NULL in an attempt to create a key.  The _callout_info string will be
+ * passed to /sbin/request-key to aid with completing the request.  If the
+ * _callout_info string is "" then it will be changed to "-".
+ */
+SYSCALL_DEFINE4(request_key, const char __user *, _type,
+		const char __user *, _description,
+		const char __user *, _callout_info,
+		key_serial_t, destringid)
+{
+	struct key_type *ktype;
+	struct key *key;
+	key_ref_t dest_ref;
+	size_t callout_len;
+	char type[32], *description, *callout_info;
+	long ret;
+
+	/* pull the type into kernel space */
+	ret = key_get_type_from_user(type, _type, sizeof(type));
+	if (ret < 0)
+		goto error;
+
+	/* pull the description into kernel space */
+	description = strndup_user(_description, KEY_MAX_DESC_SIZE);
+	if (IS_ERR(description)) {
+		ret = PTR_ERR(description);
+		goto error;
+	}
+
+	/* pull the callout info into kernel space */
+	callout_info = NULL;
+	callout_len = 0;
+	if (_callout_info) {
+		callout_info = strndup_user(_callout_info, PAGE_SIZE);
+		if (IS_ERR(callout_info)) {
+			ret = PTR_ERR(callout_info);
+			goto error2;
+		}
+		callout_len = strlen(callout_info);
+	}
+
+	/* get the destination keyring if specified */
+	dest_ref = NULL;
+	if (destringid) {
+		dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE,
+					   KEY_NEED_WRITE);
+		if (IS_ERR(dest_ref)) {
+			ret = PTR_ERR(dest_ref);
+			goto error3;
+		}
+	}
+
+	/* find the key type */
+	ktype = key_type_lookup(type);
+	if (IS_ERR(ktype)) {
+		ret = PTR_ERR(ktype);
+		goto error4;
+	}
+
+	/* do the search */
+	key = request_key_and_link(ktype, description, NULL, callout_info,
+				   callout_len, NULL, key_ref_to_ptr(dest_ref),
+				   KEY_ALLOC_IN_QUOTA);
+	if (IS_ERR(key)) {
+		ret = PTR_ERR(key);
+		goto error5;
+	}
+
+	/* wait for the key to finish being constructed */
+	ret = wait_for_key_construction(key, 1);
+	if (ret < 0)
+		goto error6;
+
+	ret = key->serial;
+
+error6:
+ 	key_put(key);
+error5:
+	key_type_put(ktype);
+error4:
+	key_ref_put(dest_ref);
+error3:
+	kfree(callout_info);
+error2:
+	kfree(description);
+error:
+	return ret;
+}
+
+/*
+ * Get the ID of the specified process keyring.
+ *
+ * The requested keyring must have search permission to be found.
+ *
+ * If successful, the ID of the requested keyring will be returned.
+ */
+long keyctl_get_keyring_ID(key_serial_t id, int create)
+{
+	key_ref_t key_ref;
+	unsigned long lflags;
+	long ret;
+
+	lflags = create ? KEY_LOOKUP_CREATE : 0;
+	key_ref = lookup_user_key(id, lflags, KEY_NEED_SEARCH);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error;
+	}
+
+	ret = key_ref_to_ptr(key_ref)->serial;
+	key_ref_put(key_ref);
+error:
+	return ret;
+}
+
+/*
+ * Join a (named) session keyring.
+ *
+ * Create and join an anonymous session keyring or join a named session
+ * keyring, creating it if necessary.  A named session keyring must have Search
+ * permission for it to be joined.  Session keyrings without this permit will
+ * be skipped over.  It is not permitted for userspace to create or join
+ * keyrings whose name begin with a dot.
+ *
+ * If successful, the ID of the joined session keyring will be returned.
+ */
+long keyctl_join_session_keyring(const char __user *_name)
+{
+	char *name;
+	long ret;
+
+	/* fetch the name from userspace */
+	name = NULL;
+	if (_name) {
+		name = strndup_user(_name, KEY_MAX_DESC_SIZE);
+		if (IS_ERR(name)) {
+			ret = PTR_ERR(name);
+			goto error;
+		}
+
+		ret = -EPERM;
+		if (name[0] == '.')
+			goto error_name;
+	}
+
+	/* join the session */
+	ret = join_session_keyring(name);
+error_name:
+	kfree(name);
+error:
+	return ret;
+}
+
+/*
+ * Update a key's data payload from the given data.
+ *
+ * The key must grant the caller Write permission and the key type must support
+ * updating for this to work.  A negative key can be positively instantiated
+ * with this call.
+ *
+ * If successful, 0 will be returned.  If the key type does not support
+ * updating, then -EOPNOTSUPP will be returned.
+ */
+long keyctl_update_key(key_serial_t id,
+		       const void __user *_payload,
+		       size_t plen)
+{
+	key_ref_t key_ref;
+	void *payload;
+	long ret;
+
+	ret = -EINVAL;
+	if (plen > PAGE_SIZE)
+		goto error;
+
+	/* pull the payload in if one was supplied */
+	payload = NULL;
+	if (plen) {
+		ret = -ENOMEM;
+		payload = kvmalloc(plen, GFP_KERNEL);
+		if (!payload)
+			goto error;
+
+		ret = -EFAULT;
+		if (copy_from_user(payload, _payload, plen) != 0)
+			goto error2;
+	}
+
+	/* find the target key (which must be writable) */
+	key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error2;
+	}
+
+	/* update the key */
+	ret = key_update(key_ref, payload, plen);
+
+	key_ref_put(key_ref);
+error2:
+	kvfree_sensitive(payload, plen);
+error:
+	return ret;
+}
+
+/*
+ * Revoke a key.
+ *
+ * The key must be grant the caller Write or Setattr permission for this to
+ * work.  The key type should give up its quota claim when revoked.  The key
+ * and any links to the key will be automatically garbage collected after a
+ * certain amount of time (/proc/sys/kernel/keys/gc_delay).
+ *
+ * Keys with KEY_FLAG_KEEP set should not be revoked.
+ *
+ * If successful, 0 is returned.
+ */
+long keyctl_revoke_key(key_serial_t id)
+{
+	key_ref_t key_ref;
+	struct key *key;
+	long ret;
+
+	key_ref = lookup_user_key(id, 0, KEY_NEED_WRITE);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		if (ret != -EACCES)
+			goto error;
+		key_ref = lookup_user_key(id, 0, KEY_NEED_SETATTR);
+		if (IS_ERR(key_ref)) {
+			ret = PTR_ERR(key_ref);
+			goto error;
+		}
+	}
+
+	key = key_ref_to_ptr(key_ref);
+	ret = 0;
+	if (test_bit(KEY_FLAG_KEEP, &key->flags))
+		ret = -EPERM;
+	else
+		key_revoke(key);
+
+	key_ref_put(key_ref);
+error:
+	return ret;
+}
+
+/*
+ * Invalidate a key.
+ *
+ * The key must be grant the caller Invalidate permission for this to work.
+ * The key and any links to the key will be automatically garbage collected
+ * immediately.
+ *
+ * Keys with KEY_FLAG_KEEP set should not be invalidated.
+ *
+ * If successful, 0 is returned.
+ */
+long keyctl_invalidate_key(key_serial_t id)
+{
+	key_ref_t key_ref;
+	struct key *key;
+	long ret;
+
+	kenter("%d", id);
+
+	key_ref = lookup_user_key(id, 0, KEY_NEED_SEARCH);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+
+		/* Root is permitted to invalidate certain special keys */
+		if (capable(CAP_SYS_ADMIN)) {
+			key_ref = lookup_user_key(id, 0, KEY_SYSADMIN_OVERRIDE);
+			if (IS_ERR(key_ref))
+				goto error;
+			if (test_bit(KEY_FLAG_ROOT_CAN_INVAL,
+				     &key_ref_to_ptr(key_ref)->flags))
+				goto invalidate;
+			goto error_put;
+		}
+
+		goto error;
+	}
+
+invalidate:
+	key = key_ref_to_ptr(key_ref);
+	ret = 0;
+	if (test_bit(KEY_FLAG_KEEP, &key->flags))
+		ret = -EPERM;
+	else
+		key_invalidate(key);
+error_put:
+	key_ref_put(key_ref);
+error:
+	kleave(" = %ld", ret);
+	return ret;
+}
+
+/*
+ * Clear the specified keyring, creating an empty process keyring if one of the
+ * special keyring IDs is used.
+ *
+ * The keyring must grant the caller Write permission and not have
+ * KEY_FLAG_KEEP set for this to work.  If successful, 0 will be returned.
+ */
+long keyctl_keyring_clear(key_serial_t ringid)
+{
+	key_ref_t keyring_ref;
+	struct key *keyring;
+	long ret;
+
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(keyring_ref)) {
+		ret = PTR_ERR(keyring_ref);
+
+		/* Root is permitted to invalidate certain special keyrings */
+		if (capable(CAP_SYS_ADMIN)) {
+			keyring_ref = lookup_user_key(ringid, 0,
+						      KEY_SYSADMIN_OVERRIDE);
+			if (IS_ERR(keyring_ref))
+				goto error;
+			if (test_bit(KEY_FLAG_ROOT_CAN_CLEAR,
+				     &key_ref_to_ptr(keyring_ref)->flags))
+				goto clear;
+			goto error_put;
+		}
+
+		goto error;
+	}
+
+clear:
+	keyring = key_ref_to_ptr(keyring_ref);
+	if (test_bit(KEY_FLAG_KEEP, &keyring->flags))
+		ret = -EPERM;
+	else
+		ret = keyring_clear(keyring);
+error_put:
+	key_ref_put(keyring_ref);
+error:
+	return ret;
+}
+
+/*
+ * Create a link from a keyring to a key if there's no matching key in the
+ * keyring, otherwise replace the link to the matching key with a link to the
+ * new key.
+ *
+ * The key must grant the caller Link permission and the keyring must grant
+ * the caller Write permission.  Furthermore, if an additional link is created,
+ * the keyring's quota will be extended.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_keyring_link(key_serial_t id, key_serial_t ringid)
+{
+	key_ref_t keyring_ref, key_ref;
+	long ret;
+
+	keyring_ref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(keyring_ref)) {
+		ret = PTR_ERR(keyring_ref);
+		goto error;
+	}
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_LINK);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error2;
+	}
+
+	ret = key_link(key_ref_to_ptr(keyring_ref), key_ref_to_ptr(key_ref));
+
+	key_ref_put(key_ref);
+error2:
+	key_ref_put(keyring_ref);
+error:
+	return ret;
+}
+
+/*
+ * Unlink a key from a keyring.
+ *
+ * The keyring must grant the caller Write permission for this to work; the key
+ * itself need not grant the caller anything.  If the last link to a key is
+ * removed then that key will be scheduled for destruction.
+ *
+ * Keys or keyrings with KEY_FLAG_KEEP set should not be unlinked.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_keyring_unlink(key_serial_t id, key_serial_t ringid)
+{
+	key_ref_t keyring_ref, key_ref;
+	struct key *keyring, *key;
+	long ret;
+
+	keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_WRITE);
+	if (IS_ERR(keyring_ref)) {
+		ret = PTR_ERR(keyring_ref);
+		goto error;
+	}
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_PARTIAL, KEY_NEED_UNLINK);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error2;
+	}
+
+	keyring = key_ref_to_ptr(keyring_ref);
+	key = key_ref_to_ptr(key_ref);
+	if (test_bit(KEY_FLAG_KEEP, &keyring->flags) &&
+	    test_bit(KEY_FLAG_KEEP, &key->flags))
+		ret = -EPERM;
+	else
+		ret = key_unlink(keyring, key);
+
+	key_ref_put(key_ref);
+error2:
+	key_ref_put(keyring_ref);
+error:
+	return ret;
+}
+
+/*
+ * Move a link to a key from one keyring to another, displacing any matching
+ * key from the destination keyring.
+ *
+ * The key must grant the caller Link permission and both keyrings must grant
+ * the caller Write permission.  There must also be a link in the from keyring
+ * to the key.  If both keyrings are the same, nothing is done.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_keyring_move(key_serial_t id, key_serial_t from_ringid,
+			 key_serial_t to_ringid, unsigned int flags)
+{
+	key_ref_t key_ref, from_ref, to_ref;
+	long ret;
+
+	if (flags & ~KEYCTL_MOVE_EXCL)
+		return -EINVAL;
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_LINK);
+	if (IS_ERR(key_ref))
+		return PTR_ERR(key_ref);
+
+	from_ref = lookup_user_key(from_ringid, 0, KEY_NEED_WRITE);
+	if (IS_ERR(from_ref)) {
+		ret = PTR_ERR(from_ref);
+		goto error2;
+	}
+
+	to_ref = lookup_user_key(to_ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(to_ref)) {
+		ret = PTR_ERR(to_ref);
+		goto error3;
+	}
+
+	ret = key_move(key_ref_to_ptr(key_ref), key_ref_to_ptr(from_ref),
+		       key_ref_to_ptr(to_ref), flags);
+
+	key_ref_put(to_ref);
+error3:
+	key_ref_put(from_ref);
+error2:
+	key_ref_put(key_ref);
+	return ret;
+}
+
+/*
+ * Return a description of a key to userspace.
+ *
+ * The key must grant the caller View permission for this to work.
+ *
+ * If there's a buffer, we place up to buflen bytes of data into it formatted
+ * in the following way:
+ *
+ *	type;uid;gid;perm;description<NUL>
+ *
+ * If successful, we return the amount of description available, irrespective
+ * of how much we may have copied into the buffer.
+ */
+long keyctl_describe_key(key_serial_t keyid,
+			 char __user *buffer,
+			 size_t buflen)
+{
+	struct key *key, *instkey;
+	key_ref_t key_ref;
+	char *infobuf;
+	long ret;
+	int desclen, infolen;
+
+	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW);
+	if (IS_ERR(key_ref)) {
+		/* viewing a key under construction is permitted if we have the
+		 * authorisation token handy */
+		if (PTR_ERR(key_ref) == -EACCES) {
+			instkey = key_get_instantiation_authkey(keyid);
+			if (!IS_ERR(instkey)) {
+				key_put(instkey);
+				key_ref = lookup_user_key(keyid,
+							  KEY_LOOKUP_PARTIAL,
+							  KEY_AUTHTOKEN_OVERRIDE);
+				if (!IS_ERR(key_ref))
+					goto okay;
+			}
+		}
+
+		ret = PTR_ERR(key_ref);
+		goto error;
+	}
+
+okay:
+	key = key_ref_to_ptr(key_ref);
+	desclen = strlen(key->description);
+
+	/* calculate how much information we're going to return */
+	ret = -ENOMEM;
+	infobuf = kasprintf(GFP_KERNEL,
+			    "%s;%d;%d;%08x;",
+			    key->type->name,
+			    from_kuid_munged(current_user_ns(), key->uid),
+			    from_kgid_munged(current_user_ns(), key->gid),
+			    key->perm);
+	if (!infobuf)
+		goto error2;
+	infolen = strlen(infobuf);
+	ret = infolen + desclen + 1;
+
+	/* consider returning the data */
+	if (buffer && buflen >= ret) {
+		if (copy_to_user(buffer, infobuf, infolen) != 0 ||
+		    copy_to_user(buffer + infolen, key->description,
+				 desclen + 1) != 0)
+			ret = -EFAULT;
+	}
+
+	kfree(infobuf);
+error2:
+	key_ref_put(key_ref);
+error:
+	return ret;
+}
+
+/*
+ * Search the specified keyring and any keyrings it links to for a matching
+ * key.  Only keyrings that grant the caller Search permission will be searched
+ * (this includes the starting keyring).  Only keys with Search permission can
+ * be found.
+ *
+ * If successful, the found key will be linked to the destination keyring if
+ * supplied and the key has Link permission, and the found key ID will be
+ * returned.
+ */
+long keyctl_keyring_search(key_serial_t ringid,
+			   const char __user *_type,
+			   const char __user *_description,
+			   key_serial_t destringid)
+{
+	struct key_type *ktype;
+	key_ref_t keyring_ref, key_ref, dest_ref;
+	char type[32], *description;
+	long ret;
+
+	/* pull the type and description into kernel space */
+	ret = key_get_type_from_user(type, _type, sizeof(type));
+	if (ret < 0)
+		goto error;
+
+	description = strndup_user(_description, KEY_MAX_DESC_SIZE);
+	if (IS_ERR(description)) {
+		ret = PTR_ERR(description);
+		goto error;
+	}
+
+	/* get the keyring at which to begin the search */
+	keyring_ref = lookup_user_key(ringid, 0, KEY_NEED_SEARCH);
+	if (IS_ERR(keyring_ref)) {
+		ret = PTR_ERR(keyring_ref);
+		goto error2;
+	}
+
+	/* get the destination keyring if specified */
+	dest_ref = NULL;
+	if (destringid) {
+		dest_ref = lookup_user_key(destringid, KEY_LOOKUP_CREATE,
+					   KEY_NEED_WRITE);
+		if (IS_ERR(dest_ref)) {
+			ret = PTR_ERR(dest_ref);
+			goto error3;
+		}
+	}
+
+	/* find the key type */
+	ktype = key_type_lookup(type);
+	if (IS_ERR(ktype)) {
+		ret = PTR_ERR(ktype);
+		goto error4;
+	}
+
+	/* do the search */
+	key_ref = keyring_search(keyring_ref, ktype, description, true);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+
+		/* treat lack or presence of a negative key the same */
+		if (ret == -EAGAIN)
+			ret = -ENOKEY;
+		goto error5;
+	}
+
+	/* link the resulting key to the destination keyring if we can */
+	if (dest_ref) {
+		ret = key_permission(key_ref, KEY_NEED_LINK);
+		if (ret < 0)
+			goto error6;
+
+		ret = key_link(key_ref_to_ptr(dest_ref), key_ref_to_ptr(key_ref));
+		if (ret < 0)
+			goto error6;
+	}
+
+	ret = key_ref_to_ptr(key_ref)->serial;
+
+error6:
+	key_ref_put(key_ref);
+error5:
+	key_type_put(ktype);
+error4:
+	key_ref_put(dest_ref);
+error3:
+	key_ref_put(keyring_ref);
+error2:
+	kfree(description);
+error:
+	return ret;
+}
+
+/*
+ * Call the read method
+ */
+static long __keyctl_read_key(struct key *key, char *buffer, size_t buflen)
+{
+	long ret;
+
+	down_read(&key->sem);
+	ret = key_validate(key);
+	if (ret == 0)
+		ret = key->type->read(key, buffer, buflen);
+	up_read(&key->sem);
+	return ret;
+}
+
+/*
+ * Read a key's payload.
+ *
+ * The key must either grant the caller Read permission, or it must grant the
+ * caller Search permission when searched for from the process keyrings.
+ *
+ * If successful, we place up to buflen bytes of data into the buffer, if one
+ * is provided, and return the amount of data that is available in the key,
+ * irrespective of how much we copied into the buffer.
+ */
+long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen)
+{
+	struct key *key;
+	key_ref_t key_ref;
+	long ret;
+	char *key_data = NULL;
+	size_t key_data_len;
+
+	/* find the key first */
+	key_ref = lookup_user_key(keyid, 0, KEY_DEFER_PERM_CHECK);
+	if (IS_ERR(key_ref)) {
+		ret = -ENOKEY;
+		goto out;
+	}
+
+	key = key_ref_to_ptr(key_ref);
+
+	ret = key_read_state(key);
+	if (ret < 0)
+		goto key_put_out; /* Negatively instantiated */
+
+	/* see if we can read it directly */
+	ret = key_permission(key_ref, KEY_NEED_READ);
+	if (ret == 0)
+		goto can_read_key;
+	if (ret != -EACCES)
+		goto key_put_out;
+
+	/* we can't; see if it's searchable from this process's keyrings
+	 * - we automatically take account of the fact that it may be
+	 *   dangling off an instantiation key
+	 */
+	if (!is_key_possessed(key_ref)) {
+		ret = -EACCES;
+		goto key_put_out;
+	}
+
+	/* the key is probably readable - now try to read it */
+can_read_key:
+	if (!key->type->read) {
+		ret = -EOPNOTSUPP;
+		goto key_put_out;
+	}
+
+	if (!buffer || !buflen) {
+		/* Get the key length from the read method */
+		ret = __keyctl_read_key(key, NULL, 0);
+		goto key_put_out;
+	}
+
+	/*
+	 * Read the data with the semaphore held (since we might sleep)
+	 * to protect against the key being updated or revoked.
+	 *
+	 * Allocating a temporary buffer to hold the keys before
+	 * transferring them to user buffer to avoid potential
+	 * deadlock involving page fault and mmap_lock.
+	 *
+	 * key_data_len = (buflen <= PAGE_SIZE)
+	 *		? buflen : actual length of key data
+	 *
+	 * This prevents allocating arbitrary large buffer which can
+	 * be much larger than the actual key length. In the latter case,
+	 * at least 2 passes of this loop is required.
+	 */
+	key_data_len = (buflen <= PAGE_SIZE) ? buflen : 0;
+	for (;;) {
+		if (key_data_len) {
+			key_data = kvmalloc(key_data_len, GFP_KERNEL);
+			if (!key_data) {
+				ret = -ENOMEM;
+				goto key_put_out;
+			}
+		}
+
+		ret = __keyctl_read_key(key, key_data, key_data_len);
+
+		/*
+		 * Read methods will just return the required length without
+		 * any copying if the provided length isn't large enough.
+		 */
+		if (ret <= 0 || ret > buflen)
+			break;
+
+		/*
+		 * The key may change (unlikely) in between 2 consecutive
+		 * __keyctl_read_key() calls. In this case, we reallocate
+		 * a larger buffer and redo the key read when
+		 * key_data_len < ret <= buflen.
+		 */
+		if (ret > key_data_len) {
+			if (unlikely(key_data))
+				kvfree_sensitive(key_data, key_data_len);
+			key_data_len = ret;
+			continue;	/* Allocate buffer */
+		}
+
+		if (copy_to_user(buffer, key_data, ret))
+			ret = -EFAULT;
+		break;
+	}
+	kvfree_sensitive(key_data, key_data_len);
+
+key_put_out:
+	key_put(key);
+out:
+	return ret;
+}
+
+/*
+ * Change the ownership of a key
+ *
+ * The key must grant the caller Setattr permission for this to work, though
+ * the key need not be fully instantiated yet.  For the UID to be changed, or
+ * for the GID to be changed to a group the caller is not a member of, the
+ * caller must have sysadmin capability.  If either uid or gid is -1 then that
+ * attribute is not changed.
+ *
+ * If the UID is to be changed, the new user must have sufficient quota to
+ * accept the key.  The quota deduction will be removed from the old user to
+ * the new user should the attribute be changed.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group)
+{
+	struct key_user *newowner, *zapowner = NULL;
+	struct key *key;
+	key_ref_t key_ref;
+	long ret;
+	kuid_t uid;
+	kgid_t gid;
+	unsigned long flags;
+
+	uid = make_kuid(current_user_ns(), user);
+	gid = make_kgid(current_user_ns(), group);
+	ret = -EINVAL;
+	if ((user != (uid_t) -1) && !uid_valid(uid))
+		goto error;
+	if ((group != (gid_t) -1) && !gid_valid(gid))
+		goto error;
+
+	ret = 0;
+	if (user == (uid_t) -1 && group == (gid_t) -1)
+		goto error;
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
+				  KEY_NEED_SETATTR);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error;
+	}
+
+	key = key_ref_to_ptr(key_ref);
+
+	/* make the changes with the locks held to prevent chown/chown races */
+	ret = -EACCES;
+	down_write(&key->sem);
+
+	{
+		bool is_privileged_op = false;
+
+		/* only the sysadmin can chown a key to some other UID */
+		if (user != (uid_t) -1 && !uid_eq(key->uid, uid))
+			is_privileged_op = true;
+
+		/* only the sysadmin can set the key's GID to a group other
+		 * than one of those that the current process subscribes to */
+		if (group != (gid_t) -1 && !gid_eq(gid, key->gid) && !in_group_p(gid))
+			is_privileged_op = true;
+
+		if (is_privileged_op && !capable(CAP_SYS_ADMIN))
+			goto error_put;
+	}
+
+	/* change the UID */
+	if (user != (uid_t) -1 && !uid_eq(uid, key->uid)) {
+		ret = -ENOMEM;
+		newowner = key_user_lookup(uid);
+		if (!newowner)
+			goto error_put;
+
+		/* transfer the quota burden to the new user */
+		if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+			unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ?
+				key_quota_root_maxkeys : key_quota_maxkeys;
+			unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ?
+				key_quota_root_maxbytes : key_quota_maxbytes;
+
+			spin_lock_irqsave(&newowner->lock, flags);
+			if (newowner->qnkeys + 1 > maxkeys ||
+			    newowner->qnbytes + key->quotalen > maxbytes ||
+			    newowner->qnbytes + key->quotalen <
+			    newowner->qnbytes)
+				goto quota_overrun;
+
+			newowner->qnkeys++;
+			newowner->qnbytes += key->quotalen;
+			spin_unlock_irqrestore(&newowner->lock, flags);
+
+			spin_lock_irqsave(&key->user->lock, flags);
+			key->user->qnkeys--;
+			key->user->qnbytes -= key->quotalen;
+			spin_unlock_irqrestore(&key->user->lock, flags);
+		}
+
+		atomic_dec(&key->user->nkeys);
+		atomic_inc(&newowner->nkeys);
+
+		if (key->state != KEY_IS_UNINSTANTIATED) {
+			atomic_dec(&key->user->nikeys);
+			atomic_inc(&newowner->nikeys);
+		}
+
+		zapowner = key->user;
+		key->user = newowner;
+		key->uid = uid;
+	}
+
+	/* change the GID */
+	if (group != (gid_t) -1)
+		key->gid = gid;
+
+	notify_key(key, NOTIFY_KEY_SETATTR, 0);
+	ret = 0;
+
+error_put:
+	up_write(&key->sem);
+	key_put(key);
+	if (zapowner)
+		key_user_put(zapowner);
+error:
+	return ret;
+
+quota_overrun:
+	spin_unlock_irqrestore(&newowner->lock, flags);
+	zapowner = newowner;
+	ret = -EDQUOT;
+	goto error_put;
+}
+
+/*
+ * Change the permission mask on a key.
+ *
+ * The key must grant the caller Setattr permission for this to work, though
+ * the key need not be fully instantiated yet.  If the caller does not have
+ * sysadmin capability, it may only change the permission on keys that it owns.
+ */
+long keyctl_setperm_key(key_serial_t id, key_perm_t perm)
+{
+	struct key *key;
+	key_ref_t key_ref;
+	long ret;
+
+	ret = -EINVAL;
+	if (perm & ~(KEY_POS_ALL | KEY_USR_ALL | KEY_GRP_ALL | KEY_OTH_ALL))
+		goto error;
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
+				  KEY_NEED_SETATTR);
+	if (IS_ERR(key_ref)) {
+		ret = PTR_ERR(key_ref);
+		goto error;
+	}
+
+	key = key_ref_to_ptr(key_ref);
+
+	/* make the changes with the locks held to prevent chown/chmod races */
+	ret = -EACCES;
+	down_write(&key->sem);
+
+	/* if we're not the sysadmin, we can only change a key that we own */
+	if (uid_eq(key->uid, current_fsuid()) || capable(CAP_SYS_ADMIN)) {
+		key->perm = perm;
+		notify_key(key, NOTIFY_KEY_SETATTR, 0);
+		ret = 0;
+	}
+
+	up_write(&key->sem);
+	key_put(key);
+error:
+	return ret;
+}
+
+/*
+ * Get the destination keyring for instantiation and check that the caller has
+ * Write permission on it.
+ */
+static long get_instantiation_keyring(key_serial_t ringid,
+				      struct request_key_auth *rka,
+				      struct key **_dest_keyring)
+{
+	key_ref_t dkref;
+
+	*_dest_keyring = NULL;
+
+	/* just return a NULL pointer if we weren't asked to make a link */
+	if (ringid == 0)
+		return 0;
+
+	/* if a specific keyring is nominated by ID, then use that */
+	if (ringid > 0) {
+		dkref = lookup_user_key(ringid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+		if (IS_ERR(dkref))
+			return PTR_ERR(dkref);
+		*_dest_keyring = key_ref_to_ptr(dkref);
+		return 0;
+	}
+
+	if (ringid == KEY_SPEC_REQKEY_AUTH_KEY)
+		return -EINVAL;
+
+	/* otherwise specify the destination keyring recorded in the
+	 * authorisation key (any KEY_SPEC_*_KEYRING) */
+	if (ringid >= KEY_SPEC_REQUESTOR_KEYRING) {
+		*_dest_keyring = key_get(rka->dest_keyring);
+		return 0;
+	}
+
+	return -ENOKEY;
+}
+
+/*
+ * Change the request_key authorisation key on the current process.
+ */
+static int keyctl_change_reqkey_auth(struct key *key)
+{
+	struct cred *new;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	key_put(new->request_key_auth);
+	new->request_key_auth = key_get(key);
+
+	return commit_creds(new);
+}
+
+/*
+ * Instantiate a key with the specified payload and link the key into the
+ * destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+static long keyctl_instantiate_key_common(key_serial_t id,
+				   struct iov_iter *from,
+				   key_serial_t ringid)
+{
+	const struct cred *cred = current_cred();
+	struct request_key_auth *rka;
+	struct key *instkey, *dest_keyring;
+	size_t plen = from ? iov_iter_count(from) : 0;
+	void *payload;
+	long ret;
+
+	kenter("%d,,%zu,%d", id, plen, ringid);
+
+	if (!plen)
+		from = NULL;
+
+	ret = -EINVAL;
+	if (plen > 1024 * 1024 - 1)
+		goto error;
+
+	/* the appropriate instantiation authorisation key must have been
+	 * assumed before calling this */
+	ret = -EPERM;
+	instkey = cred->request_key_auth;
+	if (!instkey)
+		goto error;
+
+	rka = request_key_auth_get(instkey);
+	if (!rka) {
+		ret = -EKEYREVOKED;
+		goto error;
+	}
+	if (rka->target_key->serial != id)
+		goto error_put_rka;
+
+	/* pull the payload in if one was supplied */
+	payload = NULL;
+
+	if (from) {
+		ret = -ENOMEM;
+		payload = kvmalloc(plen, GFP_KERNEL);
+		if (!payload)
+			goto error_put_rka;
+
+		ret = -EFAULT;
+		if (!copy_from_iter_full(payload, plen, from))
+			goto error2;
+	}
+
+	/* find the destination keyring amongst those belonging to the
+	 * requesting task */
+	ret = get_instantiation_keyring(ringid, rka, &dest_keyring);
+	if (ret < 0)
+		goto error2;
+
+	/* instantiate the key and link it into a keyring */
+	ret = key_instantiate_and_link(rka->target_key, payload, plen,
+				       dest_keyring, instkey);
+
+	key_put(dest_keyring);
+
+	/* discard the assumed authority if it's just been disabled by
+	 * instantiation of the key */
+	if (ret == 0)
+		keyctl_change_reqkey_auth(NULL);
+
+error2:
+	kvfree_sensitive(payload, plen);
+error_put_rka:
+	request_key_auth_put(rka);
+error:
+	return ret;
+}
+
+/*
+ * Instantiate a key with the specified payload and link the key into the
+ * destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_instantiate_key(key_serial_t id,
+			    const void __user *_payload,
+			    size_t plen,
+			    key_serial_t ringid)
+{
+	if (_payload && plen) {
+		struct iov_iter from;
+		int ret;
+
+		ret = import_ubuf(ITER_SOURCE, (void __user *)_payload, plen,
+				  &from);
+		if (unlikely(ret))
+			return ret;
+
+		return keyctl_instantiate_key_common(id, &from, ringid);
+	}
+
+	return keyctl_instantiate_key_common(id, NULL, ringid);
+}
+
+/*
+ * Instantiate a key with the specified multipart payload and link the key into
+ * the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_instantiate_key_iov(key_serial_t id,
+				const struct iovec __user *_payload_iov,
+				unsigned ioc,
+				key_serial_t ringid)
+{
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	struct iov_iter from;
+	long ret;
+
+	if (!_payload_iov)
+		ioc = 0;
+
+	ret = import_iovec(ITER_SOURCE, _payload_iov, ioc,
+				    ARRAY_SIZE(iovstack), &iov, &from);
+	if (ret < 0)
+		return ret;
+	ret = keyctl_instantiate_key_common(id, &from, ringid);
+	kfree(iov);
+	return ret;
+}
+
+/*
+ * Negatively instantiate the key with the given timeout (in seconds) and link
+ * the key into the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * The key and any links to the key will be automatically garbage collected
+ * after the timeout expires.
+ *
+ * Negative keys are used to rate limit repeated request_key() calls by causing
+ * them to return -ENOKEY until the negative key expires.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid)
+{
+	return keyctl_reject_key(id, timeout, ENOKEY, ringid);
+}
+
+/*
+ * Negatively instantiate the key with the given timeout (in seconds) and error
+ * code and link the key into the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * The key and any links to the key will be automatically garbage collected
+ * after the timeout expires.
+ *
+ * Negative keys are used to rate limit repeated request_key() calls by causing
+ * them to return the specified error code until the negative key expires.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_reject_key(key_serial_t id, unsigned timeout, unsigned error,
+		       key_serial_t ringid)
+{
+	const struct cred *cred = current_cred();
+	struct request_key_auth *rka;
+	struct key *instkey, *dest_keyring;
+	long ret;
+
+	kenter("%d,%u,%u,%d", id, timeout, error, ringid);
+
+	/* must be a valid error code and mustn't be a kernel special */
+	if (error <= 0 ||
+	    error >= MAX_ERRNO ||
+	    error == ERESTARTSYS ||
+	    error == ERESTARTNOINTR ||
+	    error == ERESTARTNOHAND ||
+	    error == ERESTART_RESTARTBLOCK)
+		return -EINVAL;
+
+	/* the appropriate instantiation authorisation key must have been
+	 * assumed before calling this */
+	ret = -EPERM;
+	instkey = cred->request_key_auth;
+	if (!instkey)
+		goto error;
+
+	rka = request_key_auth_get(instkey);
+	if (!rka) {
+		ret = -EKEYREVOKED;
+		goto error;
+	}
+	if (rka->target_key->serial != id)
+		goto error_put_rka;
+
+	/* find the destination keyring if present (which must also be
+	 * writable) */
+	ret = get_instantiation_keyring(ringid, rka, &dest_keyring);
+	if (ret < 0)
+		goto error_put_rka;
+
+	/* instantiate the key and link it into a keyring */
+	ret = key_reject_and_link(rka->target_key, timeout, error,
+				  dest_keyring, instkey);
+
+	key_put(dest_keyring);
+
+	/* discard the assumed authority if it's just been disabled by
+	 * instantiation of the key */
+	if (ret == 0)
+		keyctl_change_reqkey_auth(NULL);
+
+error_put_rka:
+	request_key_auth_put(rka);
+error:
+	return ret;
+}
+
+/*
+ * Read or set the default keyring in which request_key() will cache keys and
+ * return the old setting.
+ *
+ * If a thread or process keyring is specified then it will be created if it
+ * doesn't yet exist.  The old setting will be returned if successful.
+ */
+long keyctl_set_reqkey_keyring(int reqkey_defl)
+{
+	struct cred *new;
+	int ret, old_setting;
+
+	old_setting = current_cred_xxx(jit_keyring);
+
+	if (reqkey_defl == KEY_REQKEY_DEFL_NO_CHANGE)
+		return old_setting;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	switch (reqkey_defl) {
+	case KEY_REQKEY_DEFL_THREAD_KEYRING:
+		ret = install_thread_keyring_to_cred(new);
+		if (ret < 0)
+			goto error;
+		goto set;
+
+	case KEY_REQKEY_DEFL_PROCESS_KEYRING:
+		ret = install_process_keyring_to_cred(new);
+		if (ret < 0)
+			goto error;
+		goto set;
+
+	case KEY_REQKEY_DEFL_DEFAULT:
+	case KEY_REQKEY_DEFL_SESSION_KEYRING:
+	case KEY_REQKEY_DEFL_USER_KEYRING:
+	case KEY_REQKEY_DEFL_USER_SESSION_KEYRING:
+	case KEY_REQKEY_DEFL_REQUESTOR_KEYRING:
+		goto set;
+
+	case KEY_REQKEY_DEFL_NO_CHANGE:
+	case KEY_REQKEY_DEFL_GROUP_KEYRING:
+	default:
+		ret = -EINVAL;
+		goto error;
+	}
+
+set:
+	new->jit_keyring = reqkey_defl;
+	commit_creds(new);
+	return old_setting;
+error:
+	abort_creds(new);
+	return ret;
+}
+
+/*
+ * Set or clear the timeout on a key.
+ *
+ * Either the key must grant the caller Setattr permission or else the caller
+ * must hold an instantiation authorisation token for the key.
+ *
+ * The timeout is either 0 to clear the timeout, or a number of seconds from
+ * the current time.  The key and any links to the key will be automatically
+ * garbage collected after the timeout expires.
+ *
+ * Keys with KEY_FLAG_KEEP set should not be timed out.
+ *
+ * If successful, 0 is returned.
+ */
+long keyctl_set_timeout(key_serial_t id, unsigned timeout)
+{
+	struct key *key, *instkey;
+	key_ref_t key_ref;
+	long ret;
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE | KEY_LOOKUP_PARTIAL,
+				  KEY_NEED_SETATTR);
+	if (IS_ERR(key_ref)) {
+		/* setting the timeout on a key under construction is permitted
+		 * if we have the authorisation token handy */
+		if (PTR_ERR(key_ref) == -EACCES) {
+			instkey = key_get_instantiation_authkey(id);
+			if (!IS_ERR(instkey)) {
+				key_put(instkey);
+				key_ref = lookup_user_key(id,
+							  KEY_LOOKUP_PARTIAL,
+							  KEY_AUTHTOKEN_OVERRIDE);
+				if (!IS_ERR(key_ref))
+					goto okay;
+			}
+		}
+
+		ret = PTR_ERR(key_ref);
+		goto error;
+	}
+
+okay:
+	key = key_ref_to_ptr(key_ref);
+	ret = 0;
+	if (test_bit(KEY_FLAG_KEEP, &key->flags)) {
+		ret = -EPERM;
+	} else {
+		key_set_timeout(key, timeout);
+		notify_key(key, NOTIFY_KEY_SETATTR, 0);
+	}
+	key_put(key);
+
+error:
+	return ret;
+}
+
+/*
+ * Assume (or clear) the authority to instantiate the specified key.
+ *
+ * This sets the authoritative token currently in force for key instantiation.
+ * This must be done for a key to be instantiated.  It has the effect of making
+ * available all the keys from the caller of the request_key() that created a
+ * key to request_key() calls made by the caller of this function.
+ *
+ * The caller must have the instantiation key in their process keyrings with a
+ * Search permission grant available to the caller.
+ *
+ * If the ID given is 0, then the setting will be cleared and 0 returned.
+ *
+ * If the ID given has a matching an authorisation key, then that key will be
+ * set and its ID will be returned.  The authorisation key can be read to get
+ * the callout information passed to request_key().
+ */
+long keyctl_assume_authority(key_serial_t id)
+{
+	struct key *authkey;
+	long ret;
+
+	/* special key IDs aren't permitted */
+	ret = -EINVAL;
+	if (id < 0)
+		goto error;
+
+	/* we divest ourselves of authority if given an ID of 0 */
+	if (id == 0) {
+		ret = keyctl_change_reqkey_auth(NULL);
+		goto error;
+	}
+
+	/* attempt to assume the authority temporarily granted to us whilst we
+	 * instantiate the specified key
+	 * - the authorisation key must be in the current task's keyrings
+	 *   somewhere
+	 */
+	authkey = key_get_instantiation_authkey(id);
+	if (IS_ERR(authkey)) {
+		ret = PTR_ERR(authkey);
+		goto error;
+	}
+
+	ret = keyctl_change_reqkey_auth(authkey);
+	if (ret == 0)
+		ret = authkey->serial;
+	key_put(authkey);
+error:
+	return ret;
+}
+
+/*
+ * Get a key's the LSM security label.
+ *
+ * The key must grant the caller View permission for this to work.
+ *
+ * If there's a buffer, then up to buflen bytes of data will be placed into it.
+ *
+ * If successful, the amount of information available will be returned,
+ * irrespective of how much was copied (including the terminal NUL).
+ */
+long keyctl_get_security(key_serial_t keyid,
+			 char __user *buffer,
+			 size_t buflen)
+{
+	struct key *key, *instkey;
+	key_ref_t key_ref;
+	char *context;
+	long ret;
+
+	key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL, KEY_NEED_VIEW);
+	if (IS_ERR(key_ref)) {
+		if (PTR_ERR(key_ref) != -EACCES)
+			return PTR_ERR(key_ref);
+
+		/* viewing a key under construction is also permitted if we
+		 * have the authorisation token handy */
+		instkey = key_get_instantiation_authkey(keyid);
+		if (IS_ERR(instkey))
+			return PTR_ERR(instkey);
+		key_put(instkey);
+
+		key_ref = lookup_user_key(keyid, KEY_LOOKUP_PARTIAL,
+					  KEY_AUTHTOKEN_OVERRIDE);
+		if (IS_ERR(key_ref))
+			return PTR_ERR(key_ref);
+	}
+
+	key = key_ref_to_ptr(key_ref);
+	ret = security_key_getsecurity(key, &context);
+	if (ret == 0) {
+		/* if no information was returned, give userspace an empty
+		 * string */
+		ret = 1;
+		if (buffer && buflen > 0 &&
+		    copy_to_user(buffer, "", 1) != 0)
+			ret = -EFAULT;
+	} else if (ret > 0) {
+		/* return as much data as there's room for */
+		if (buffer && buflen > 0) {
+			if (buflen > ret)
+				buflen = ret;
+
+			if (copy_to_user(buffer, context, buflen) != 0)
+				ret = -EFAULT;
+		}
+
+		kfree(context);
+	}
+
+	key_ref_put(key_ref);
+	return ret;
+}
+
+/*
+ * Attempt to install the calling process's session keyring on the process's
+ * parent process.
+ *
+ * The keyring must exist and must grant the caller LINK permission, and the
+ * parent process must be single-threaded and must have the same effective
+ * ownership as this process and mustn't be SUID/SGID.
+ *
+ * The keyring will be emplaced on the parent when it next resumes userspace.
+ *
+ * If successful, 0 will be returned.
+ */
+long keyctl_session_to_parent(void)
+{
+	struct task_struct *me, *parent;
+	const struct cred *mycred, *pcred;
+	struct callback_head *newwork, *oldwork;
+	key_ref_t keyring_r;
+	struct cred *cred;
+	int ret;
+
+	keyring_r = lookup_user_key(KEY_SPEC_SESSION_KEYRING, 0, KEY_NEED_LINK);
+	if (IS_ERR(keyring_r))
+		return PTR_ERR(keyring_r);
+
+	ret = -ENOMEM;
+
+	/* our parent is going to need a new cred struct, a new tgcred struct
+	 * and new security data, so we allocate them here to prevent ENOMEM in
+	 * our parent */
+	cred = cred_alloc_blank();
+	if (!cred)
+		goto error_keyring;
+	newwork = &cred->rcu;
+
+	cred->session_keyring = key_ref_to_ptr(keyring_r);
+	keyring_r = NULL;
+	init_task_work(newwork, key_change_session_keyring);
+
+	me = current;
+	rcu_read_lock();
+	write_lock_irq(&tasklist_lock);
+
+	ret = -EPERM;
+	oldwork = NULL;
+	parent = rcu_dereference_protected(me->real_parent,
+					   lockdep_is_held(&tasklist_lock));
+
+	/* the parent mustn't be init and mustn't be a kernel thread */
+	if (parent->pid <= 1 || !parent->mm)
+		goto unlock;
+
+	/* the parent must be single threaded */
+	if (!thread_group_empty(parent))
+		goto unlock;
+
+	/* the parent and the child must have different session keyrings or
+	 * there's no point */
+	mycred = current_cred();
+	pcred = __task_cred(parent);
+	if (mycred == pcred ||
+	    mycred->session_keyring == pcred->session_keyring) {
+		ret = 0;
+		goto unlock;
+	}
+
+	/* the parent must have the same effective ownership and mustn't be
+	 * SUID/SGID */
+	if (!uid_eq(pcred->uid,	 mycred->euid) ||
+	    !uid_eq(pcred->euid, mycred->euid) ||
+	    !uid_eq(pcred->suid, mycred->euid) ||
+	    !gid_eq(pcred->gid,	 mycred->egid) ||
+	    !gid_eq(pcred->egid, mycred->egid) ||
+	    !gid_eq(pcred->sgid, mycred->egid))
+		goto unlock;
+
+	/* the keyrings must have the same UID */
+	if ((pcred->session_keyring &&
+	     !uid_eq(pcred->session_keyring->uid, mycred->euid)) ||
+	    !uid_eq(mycred->session_keyring->uid, mycred->euid))
+		goto unlock;
+
+	/* cancel an already pending keyring replacement */
+	oldwork = task_work_cancel_func(parent, key_change_session_keyring);
+
+	/* the replacement session keyring is applied just prior to userspace
+	 * restarting */
+	ret = task_work_add(parent, newwork, TWA_RESUME);
+	if (!ret)
+		newwork = NULL;
+unlock:
+	write_unlock_irq(&tasklist_lock);
+	rcu_read_unlock();
+	if (oldwork)
+		put_cred(container_of(oldwork, struct cred, rcu));
+	if (newwork)
+		put_cred(cred);
+	return ret;
+
+error_keyring:
+	key_ref_put(keyring_r);
+	return ret;
+}
+
+/*
+ * Apply a restriction to a given keyring.
+ *
+ * The caller must have Setattr permission to change keyring restrictions.
+ *
+ * The requested type name may be a NULL pointer to reject all attempts
+ * to link to the keyring.  In this case, _restriction must also be NULL.
+ * Otherwise, both _type and _restriction must be non-NULL.
+ *
+ * Returns 0 if successful.
+ */
+long keyctl_restrict_keyring(key_serial_t id, const char __user *_type,
+			     const char __user *_restriction)
+{
+	key_ref_t key_ref;
+	char type[32];
+	char *restriction = NULL;
+	long ret;
+
+	key_ref = lookup_user_key(id, 0, KEY_NEED_SETATTR);
+	if (IS_ERR(key_ref))
+		return PTR_ERR(key_ref);
+
+	ret = -EINVAL;
+	if (_type) {
+		if (!_restriction)
+			goto error;
+
+		ret = key_get_type_from_user(type, _type, sizeof(type));
+		if (ret < 0)
+			goto error;
+
+		restriction = strndup_user(_restriction, PAGE_SIZE);
+		if (IS_ERR(restriction)) {
+			ret = PTR_ERR(restriction);
+			goto error;
+		}
+	} else {
+		if (_restriction)
+			goto error;
+	}
+
+	ret = keyring_restrict(key_ref, _type ? type : NULL, restriction);
+	kfree(restriction);
+error:
+	key_ref_put(key_ref);
+	return ret;
+}
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+/*
+ * Watch for changes to a key.
+ *
+ * The caller must have View permission to watch a key or keyring.
+ */
+long keyctl_watch_key(key_serial_t id, int watch_queue_fd, int watch_id)
+{
+	struct watch_queue *wqueue;
+	struct watch_list *wlist = NULL;
+	struct watch *watch = NULL;
+	struct key *key;
+	key_ref_t key_ref;
+	long ret;
+
+	if (watch_id < -1 || watch_id > 0xff)
+		return -EINVAL;
+
+	key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_VIEW);
+	if (IS_ERR(key_ref))
+		return PTR_ERR(key_ref);
+	key = key_ref_to_ptr(key_ref);
+
+	wqueue = get_watch_queue(watch_queue_fd);
+	if (IS_ERR(wqueue)) {
+		ret = PTR_ERR(wqueue);
+		goto err_key;
+	}
+
+	if (watch_id >= 0) {
+		ret = -ENOMEM;
+		if (!key->watchers) {
+			wlist = kzalloc_obj(*wlist);
+			if (!wlist)
+				goto err_wqueue;
+			init_watch_list(wlist, NULL);
+		}
+
+		watch = kzalloc_obj(*watch);
+		if (!watch)
+			goto err_wlist;
+
+		init_watch(watch, wqueue);
+		watch->id	= key->serial;
+		watch->info_id	= (u32)watch_id << WATCH_INFO_ID__SHIFT;
+
+		ret = security_watch_key(key);
+		if (ret < 0)
+			goto err_watch;
+
+		down_write(&key->sem);
+		if (!key->watchers) {
+			key->watchers = wlist;
+			wlist = NULL;
+		}
+
+		ret = add_watch_to_object(watch, key->watchers);
+		up_write(&key->sem);
+
+		if (ret == 0)
+			watch = NULL;
+	} else {
+		ret = -EBADSLT;
+		if (key->watchers) {
+			down_write(&key->sem);
+			ret = remove_watch_from_object(key->watchers,
+						       wqueue, key_serial(key),
+						       false);
+			up_write(&key->sem);
+		}
+	}
+
+err_watch:
+	kfree(watch);
+err_wlist:
+	kfree(wlist);
+err_wqueue:
+	put_watch_queue(wqueue);
+err_key:
+	key_put(key);
+	return ret;
+}
+#endif /* CONFIG_KEY_NOTIFICATIONS */
+
+/*
+ * Get keyrings subsystem capabilities.
+ */
+long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen)
+{
+	size_t size = buflen;
+
+	if (size > 0) {
+		if (size > sizeof(keyrings_capabilities))
+			size = sizeof(keyrings_capabilities);
+		if (copy_to_user(_buffer, keyrings_capabilities, size) != 0)
+			return -EFAULT;
+		if (size < buflen &&
+		    clear_user(_buffer + size, buflen - size) != 0)
+			return -EFAULT;
+	}
+
+	return sizeof(keyrings_capabilities);
+}
+
+/*
+ * The key control system call
+ */
+SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
+		unsigned long, arg4, unsigned long, arg5)
+{
+	switch (option) {
+	case KEYCTL_GET_KEYRING_ID:
+		return keyctl_get_keyring_ID((key_serial_t) arg2,
+					     (int) arg3);
+
+	case KEYCTL_JOIN_SESSION_KEYRING:
+		return keyctl_join_session_keyring((const char __user *) arg2);
+
+	case KEYCTL_UPDATE:
+		return keyctl_update_key((key_serial_t) arg2,
+					 (const void __user *) arg3,
+					 (size_t) arg4);
+
+	case KEYCTL_REVOKE:
+		return keyctl_revoke_key((key_serial_t) arg2);
+
+	case KEYCTL_DESCRIBE:
+		return keyctl_describe_key((key_serial_t) arg2,
+					   (char __user *) arg3,
+					   (unsigned) arg4);
+
+	case KEYCTL_CLEAR:
+		return keyctl_keyring_clear((key_serial_t) arg2);
+
+	case KEYCTL_LINK:
+		return keyctl_keyring_link((key_serial_t) arg2,
+					   (key_serial_t) arg3);
+
+	case KEYCTL_UNLINK:
+		return keyctl_keyring_unlink((key_serial_t) arg2,
+					     (key_serial_t) arg3);
+
+	case KEYCTL_SEARCH:
+		return keyctl_keyring_search((key_serial_t) arg2,
+					     (const char __user *) arg3,
+					     (const char __user *) arg4,
+					     (key_serial_t) arg5);
+
+	case KEYCTL_READ:
+		return keyctl_read_key((key_serial_t) arg2,
+				       (char __user *) arg3,
+				       (size_t) arg4);
+
+	case KEYCTL_CHOWN:
+		return keyctl_chown_key((key_serial_t) arg2,
+					(uid_t) arg3,
+					(gid_t) arg4);
+
+	case KEYCTL_SETPERM:
+		return keyctl_setperm_key((key_serial_t) arg2,
+					  (key_perm_t) arg3);
+
+	case KEYCTL_INSTANTIATE:
+		return keyctl_instantiate_key((key_serial_t) arg2,
+					      (const void __user *) arg3,
+					      (size_t) arg4,
+					      (key_serial_t) arg5);
+
+	case KEYCTL_NEGATE:
+		return keyctl_negate_key((key_serial_t) arg2,
+					 (unsigned) arg3,
+					 (key_serial_t) arg4);
+
+	case KEYCTL_SET_REQKEY_KEYRING:
+		return keyctl_set_reqkey_keyring(arg2);
+
+	case KEYCTL_SET_TIMEOUT:
+		return keyctl_set_timeout((key_serial_t) arg2,
+					  (unsigned) arg3);
+
+	case KEYCTL_ASSUME_AUTHORITY:
+		return keyctl_assume_authority((key_serial_t) arg2);
+
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security((key_serial_t) arg2,
+					   (char __user *) arg3,
+					   (size_t) arg4);
+
+	case KEYCTL_SESSION_TO_PARENT:
+		return keyctl_session_to_parent();
+
+	case KEYCTL_REJECT:
+		return keyctl_reject_key((key_serial_t) arg2,
+					 (unsigned) arg3,
+					 (unsigned) arg4,
+					 (key_serial_t) arg5);
+
+	case KEYCTL_INSTANTIATE_IOV:
+		return keyctl_instantiate_key_iov(
+			(key_serial_t) arg2,
+			(const struct iovec __user *) arg3,
+			(unsigned) arg4,
+			(key_serial_t) arg5);
+
+	case KEYCTL_INVALIDATE:
+		return keyctl_invalidate_key((key_serial_t) arg2);
+
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent((uid_t)arg2, (key_serial_t)arg3);
+
+	case KEYCTL_DH_COMPUTE:
+		return keyctl_dh_compute((struct keyctl_dh_params __user *) arg2,
+					 (char __user *) arg3, (size_t) arg4,
+					 (struct keyctl_kdf_params __user *) arg5);
+
+	case KEYCTL_RESTRICT_KEYRING:
+		return keyctl_restrict_keyring((key_serial_t) arg2,
+					       (const char __user *) arg3,
+					       (const char __user *) arg4);
+
+	case KEYCTL_PKEY_QUERY:
+		if (arg3 != 0)
+			return -EINVAL;
+		return keyctl_pkey_query((key_serial_t)arg2,
+					 (const char __user *)arg4,
+					 (struct keyctl_pkey_query __user *)arg5);
+
+	case KEYCTL_PKEY_ENCRYPT:
+	case KEYCTL_PKEY_DECRYPT:
+	case KEYCTL_PKEY_SIGN:
+		return keyctl_pkey_e_d_s(
+			option,
+			(const struct keyctl_pkey_params __user *)arg2,
+			(const char __user *)arg3,
+			(const void __user *)arg4,
+			(void __user *)arg5);
+
+	case KEYCTL_PKEY_VERIFY:
+		return keyctl_pkey_verify(
+			(const struct keyctl_pkey_params __user *)arg2,
+			(const char __user *)arg3,
+			(const void __user *)arg4,
+			(const void __user *)arg5);
+
+	case KEYCTL_MOVE:
+		return keyctl_keyring_move((key_serial_t)arg2,
+					   (key_serial_t)arg3,
+					   (key_serial_t)arg4,
+					   (unsigned int)arg5);
+
+	case KEYCTL_CAPABILITIES:
+		return keyctl_capabilities((unsigned char __user *)arg2, (size_t)arg3);
+
+	case KEYCTL_WATCH_KEY:
+		return keyctl_watch_key((key_serial_t)arg2, (int)arg3, (int)arg4);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c
new file mode 100644
index 000000000..15b6bf639
--- /dev/null
+++ b/security/keys/keyctl_pkey.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Public-key operation keyctls
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/key.h>
+#include <linux/keyctl.h>
+#include <linux/parser.h>
+#include <linux/uaccess.h>
+#include <keys/user-type.h>
+#include "internal.h"
+
+static void keyctl_pkey_params_free(struct kernel_pkey_params *params)
+{
+	kfree(params->info);
+	key_put(params->key);
+}
+
+enum {
+	Opt_err,
+	Opt_enc,		/* "enc=<encoding>" eg. "enc=oaep" */
+	Opt_hash,		/* "hash=<digest-name>" eg. "hash=sha1" */
+};
+
+static const match_table_t param_keys = {
+	{ Opt_enc,	"enc=%s" },
+	{ Opt_hash,	"hash=%s" },
+	{ Opt_err,	NULL }
+};
+
+/*
+ * Parse the information string which consists of key=val pairs.
+ */
+static int keyctl_pkey_params_parse(struct kernel_pkey_params *params)
+{
+	unsigned long token_mask = 0;
+	substring_t args[MAX_OPT_ARGS];
+	char *c = params->info, *p, *q;
+	int token;
+
+	while ((p = strsep(&c, " \t"))) {
+		if (*p == '\0' || *p == ' ' || *p == '\t')
+			continue;
+		token = match_token(p, param_keys, args);
+		if (token == Opt_err)
+			return -EINVAL;
+		if (__test_and_set_bit(token, &token_mask))
+			return -EINVAL;
+		q = args[0].from;
+		if (!q[0])
+			return -EINVAL;
+
+		switch (token) {
+		case Opt_enc:
+			params->encoding = q;
+			break;
+
+		case Opt_hash:
+			params->hash_algo = q;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Interpret parameters.  Callers must always call the free function
+ * on params, even if an error is returned.
+ */
+static int keyctl_pkey_params_get(key_serial_t id,
+				  const char __user *_info,
+				  struct kernel_pkey_params *params)
+{
+	key_ref_t key_ref;
+	void *p;
+	int ret;
+
+	memset(params, 0, sizeof(*params));
+	params->encoding = "raw";
+
+	p = strndup_user(_info, PAGE_SIZE);
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+	params->info = p;
+
+	ret = keyctl_pkey_params_parse(params);
+	if (ret < 0)
+		return ret;
+
+	key_ref = lookup_user_key(id, 0, KEY_NEED_SEARCH);
+	if (IS_ERR(key_ref))
+		return PTR_ERR(key_ref);
+	params->key = key_ref_to_ptr(key_ref);
+
+	if (!params->key->type->asym_query)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+/*
+ * Get parameters from userspace.  Callers must always call the free function
+ * on params, even if an error is returned.
+ */
+static int keyctl_pkey_params_get_2(const struct keyctl_pkey_params __user *_params,
+				    const char __user *_info,
+				    int op,
+				    struct kernel_pkey_params *params)
+{
+	struct keyctl_pkey_params uparams;
+	struct kernel_pkey_query info;
+	int ret;
+
+	memset(params, 0, sizeof(*params));
+	params->encoding = "raw";
+
+	if (copy_from_user(&uparams, _params, sizeof(uparams)) != 0)
+		return -EFAULT;
+
+	ret = keyctl_pkey_params_get(uparams.key_id, _info, params);
+	if (ret < 0)
+		return ret;
+
+	ret = params->key->type->asym_query(params, &info);
+	if (ret < 0)
+		return ret;
+
+	switch (op) {
+	case KEYCTL_PKEY_ENCRYPT:
+		if (uparams.in_len  > info.max_dec_size ||
+		    uparams.out_len > info.max_enc_size)
+			return -EINVAL;
+
+		params->out_len = info.max_enc_size;
+		break;
+	case KEYCTL_PKEY_DECRYPT:
+		if (uparams.in_len  > info.max_enc_size ||
+		    uparams.out_len > info.max_dec_size)
+			return -EINVAL;
+
+		params->out_len = info.max_dec_size;
+		break;
+	case KEYCTL_PKEY_SIGN:
+		if (uparams.in_len  > info.max_data_size ||
+		    uparams.out_len > info.max_sig_size)
+			return -EINVAL;
+
+		params->out_len = info.max_sig_size;
+		break;
+	case KEYCTL_PKEY_VERIFY:
+		if (uparams.in_len  > info.max_data_size ||
+		    uparams.in2_len > info.max_sig_size)
+			return -EINVAL;
+
+		params->out_len = info.max_sig_size;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	params->in_len  = uparams.in_len;
+	return 0;
+}
+
+/*
+ * Query information about an asymmetric key.
+ */
+long keyctl_pkey_query(key_serial_t id,
+		       const char __user *_info,
+		       struct keyctl_pkey_query __user *_res)
+{
+	struct kernel_pkey_params params;
+	struct kernel_pkey_query res;
+	long ret;
+
+	ret = keyctl_pkey_params_get(id, _info, &params);
+	if (ret < 0)
+		goto error;
+
+	ret = params.key->type->asym_query(&params, &res);
+	if (ret < 0)
+		goto error;
+
+	ret = -EFAULT;
+	if (copy_to_user(_res, &res, sizeof(res)) == 0 &&
+	    clear_user(_res->__spare, sizeof(_res->__spare)) == 0)
+		ret = 0;
+
+error:
+	keyctl_pkey_params_free(&params);
+	return ret;
+}
+
+/*
+ * Encrypt/decrypt/sign
+ *
+ * Encrypt data, decrypt data or sign data using a public key.
+ *
+ * _info is a string of supplementary information in key=val format.  For
+ * instance, it might contain:
+ *
+ *	"enc=pkcs1 hash=sha256"
+ *
+ * where enc= specifies the encoding and hash= selects the OID to go in that
+ * particular encoding if required.  If enc= isn't supplied, it's assumed that
+ * the caller is supplying raw values.
+ *
+ * If successful, the amount of data written into the output buffer is
+ * returned.
+ */
+long keyctl_pkey_e_d_s(int op,
+		       const struct keyctl_pkey_params __user *_params,
+		       const char __user *_info,
+		       const void __user *_in,
+		       void __user *_out)
+{
+	struct kernel_pkey_params params;
+	void *in, *out;
+	long ret;
+
+	ret = keyctl_pkey_params_get_2(_params, _info, op, &params);
+	if (ret < 0)
+		goto error_params;
+
+	ret = -EOPNOTSUPP;
+	if (!params.key->type->asym_eds_op)
+		goto error_params;
+
+	switch (op) {
+	case KEYCTL_PKEY_ENCRYPT:
+		params.op = kernel_pkey_encrypt;
+		break;
+	case KEYCTL_PKEY_DECRYPT:
+		params.op = kernel_pkey_decrypt;
+		break;
+	case KEYCTL_PKEY_SIGN:
+		params.op = kernel_pkey_sign;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto error_params;
+	}
+
+	in = memdup_user(_in, params.in_len);
+	if (IS_ERR(in)) {
+		ret = PTR_ERR(in);
+		goto error_params;
+	}
+
+	ret = -ENOMEM;
+	out = kmalloc(params.out_len, GFP_KERNEL);
+	if (!out)
+		goto error_in;
+
+	ret = params.key->type->asym_eds_op(&params, in, out);
+	if (ret < 0)
+		goto error_out;
+
+	if (copy_to_user(_out, out, ret) != 0)
+		ret = -EFAULT;
+
+error_out:
+	kfree(out);
+error_in:
+	kfree(in);
+error_params:
+	keyctl_pkey_params_free(&params);
+	return ret;
+}
+
+/*
+ * Verify a signature.
+ *
+ * Verify a public key signature using the given key, or if not given, search
+ * for a matching key.
+ *
+ * _info is a string of supplementary information in key=val format.  For
+ * instance, it might contain:
+ *
+ *	"enc=pkcs1 hash=sha256"
+ *
+ * where enc= specifies the signature blob encoding and hash= selects the OID
+ * to go in that particular encoding.  If enc= isn't supplied, it's assumed
+ * that the caller is supplying raw values.
+ *
+ * If successful, 0 is returned.
+ */
+long keyctl_pkey_verify(const struct keyctl_pkey_params __user *_params,
+			const char __user *_info,
+			const void __user *_in,
+			const void __user *_in2)
+{
+	struct kernel_pkey_params params;
+	void *in, *in2;
+	long ret;
+
+	ret = keyctl_pkey_params_get_2(_params, _info, KEYCTL_PKEY_VERIFY,
+				       &params);
+	if (ret < 0)
+		goto error_params;
+
+	ret = -EOPNOTSUPP;
+	if (!params.key->type->asym_verify_signature)
+		goto error_params;
+
+	in = memdup_user(_in, params.in_len);
+	if (IS_ERR(in)) {
+		ret = PTR_ERR(in);
+		goto error_params;
+	}
+
+	in2 = memdup_user(_in2, params.in2_len);
+	if (IS_ERR(in2)) {
+		ret = PTR_ERR(in2);
+		goto error_in;
+	}
+
+	params.op = kernel_pkey_verify;
+	ret = params.key->type->asym_verify_signature(&params, in, in2);
+
+	kfree(in2);
+error_in:
+	kfree(in);
+error_params:
+	keyctl_pkey_params_free(&params);
+	return ret;
+}
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
new file mode 100644
index 000000000..15bf4af8f
--- /dev/null
+++ b/security/keys/keyring.c
@@ -0,0 +1,1800 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Keyring handling
+ *
+ * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
+#include <linux/user_namespace.h>
+#include <linux/nsproxy.h>
+#include <keys/keyring-type.h>
+#include <keys/user-type.h>
+#include <linux/assoc_array_priv.h>
+#include <linux/uaccess.h>
+#include <net/net_namespace.h>
+#include "internal.h"
+
+/*
+ * When plumbing the depths of the key tree, this sets a hard limit
+ * set on how deep we're willing to go.
+ */
+#define KEYRING_SEARCH_MAX_DEPTH 6
+
+/*
+ * We mark pointers we pass to the associative array with bit 1 set if
+ * they're keyrings and clear otherwise.
+ */
+#define KEYRING_PTR_SUBTYPE	0x2UL
+
+static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x)
+{
+	return (unsigned long)x & KEYRING_PTR_SUBTYPE;
+}
+static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x)
+{
+	void *object = assoc_array_ptr_to_leaf(x);
+	return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE);
+}
+static inline void *keyring_key_to_ptr(struct key *key)
+{
+	if (key->type == &key_type_keyring)
+		return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE);
+	return key;
+}
+
+static DEFINE_RWLOCK(keyring_name_lock);
+
+/*
+ * Clean up the bits of user_namespace that belong to us.
+ */
+void key_free_user_ns(struct user_namespace *ns)
+{
+	write_lock(&keyring_name_lock);
+	list_del_init(&ns->keyring_name_list);
+	write_unlock(&keyring_name_lock);
+
+	key_put(ns->user_keyring_register);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	key_put(ns->persistent_keyring_register);
+#endif
+}
+
+/*
+ * The keyring key type definition.  Keyrings are simply keys of this type and
+ * can be treated as ordinary keys in addition to having their own special
+ * operations.
+ */
+static int keyring_preparse(struct key_preparsed_payload *prep);
+static void keyring_free_preparse(struct key_preparsed_payload *prep);
+static int keyring_instantiate(struct key *keyring,
+			       struct key_preparsed_payload *prep);
+static void keyring_revoke(struct key *keyring);
+static void keyring_destroy(struct key *keyring);
+static void keyring_describe(const struct key *keyring, struct seq_file *m);
+static long keyring_read(const struct key *keyring,
+			 char *buffer, size_t buflen);
+
+struct key_type key_type_keyring = {
+	.name		= "keyring",
+	.def_datalen	= 0,
+	.preparse	= keyring_preparse,
+	.free_preparse	= keyring_free_preparse,
+	.instantiate	= keyring_instantiate,
+	.revoke		= keyring_revoke,
+	.destroy	= keyring_destroy,
+	.describe	= keyring_describe,
+	.read		= keyring_read,
+};
+EXPORT_SYMBOL(key_type_keyring);
+
+/*
+ * Semaphore to serialise link/link calls to prevent two link calls in parallel
+ * introducing a cycle.
+ */
+static DEFINE_MUTEX(keyring_serialise_link_lock);
+
+/*
+ * Publish the name of a keyring so that it can be found by name (if it has
+ * one and it doesn't begin with a dot).
+ */
+static void keyring_publish_name(struct key *keyring)
+{
+	struct user_namespace *ns = current_user_ns();
+
+	if (keyring->description &&
+	    keyring->description[0] &&
+	    keyring->description[0] != '.') {
+		write_lock(&keyring_name_lock);
+		list_add_tail(&keyring->name_link, &ns->keyring_name_list);
+		write_unlock(&keyring_name_lock);
+	}
+}
+
+/*
+ * Preparse a keyring payload
+ */
+static int keyring_preparse(struct key_preparsed_payload *prep)
+{
+	return prep->datalen != 0 ? -EINVAL : 0;
+}
+
+/*
+ * Free a preparse of a user defined key payload
+ */
+static void keyring_free_preparse(struct key_preparsed_payload *prep)
+{
+}
+
+/*
+ * Initialise a keyring.
+ *
+ * Returns 0 on success, -EINVAL if given any data.
+ */
+static int keyring_instantiate(struct key *keyring,
+			       struct key_preparsed_payload *prep)
+{
+	assoc_array_init(&keyring->keys);
+	/* make the keyring available by name if it has one */
+	keyring_publish_name(keyring);
+	return 0;
+}
+
+/*
+ * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit.  Ideally we'd
+ * fold the carry back too, but that requires inline asm.
+ */
+static u64 mult_64x32_and_fold(u64 x, u32 y)
+{
+	u64 hi = (u64)(u32)(x >> 32) * y;
+	u64 lo = (u64)(u32)(x) * y;
+	return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32);
+}
+
+/*
+ * Hash a key type and description.
+ */
+static void hash_key_type_and_desc(struct keyring_index_key *index_key)
+{
+	const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP;
+	const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK;
+	const char *description = index_key->description;
+	unsigned long hash, type;
+	u32 piece;
+	u64 acc;
+	int n, desc_len = index_key->desc_len;
+
+	type = (unsigned long)index_key->type;
+	acc = mult_64x32_and_fold(type, desc_len + 13);
+	acc = mult_64x32_and_fold(acc, 9207);
+	piece = (unsigned long)index_key->domain_tag;
+	acc = mult_64x32_and_fold(acc, piece);
+	acc = mult_64x32_and_fold(acc, 9207);
+
+	for (;;) {
+		n = desc_len;
+		if (n <= 0)
+			break;
+		if (n > 4)
+			n = 4;
+		piece = 0;
+		memcpy(&piece, description, n);
+		description += n;
+		desc_len -= n;
+		acc = mult_64x32_and_fold(acc, piece);
+		acc = mult_64x32_and_fold(acc, 9207);
+	}
+
+	/* Fold the hash down to 32 bits if need be. */
+	hash = acc;
+	if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32)
+		hash ^= acc >> 32;
+
+	/* Squidge all the keyrings into a separate part of the tree to
+	 * ordinary keys by making sure the lowest level segment in the hash is
+	 * zero for keyrings and non-zero otherwise.
+	 */
+	if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0)
+		hash |= (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1;
+	else if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0)
+		hash = (hash + (hash << level_shift)) & ~fan_mask;
+	index_key->hash = hash;
+}
+
+/*
+ * Finalise an index key to include a part of the description actually in the
+ * index key, to set the domain tag and to calculate the hash.
+ */
+void key_set_index_key(struct keyring_index_key *index_key)
+{
+	static struct key_tag default_domain_tag = { .usage = REFCOUNT_INIT(1), };
+	size_t n = min_t(size_t, index_key->desc_len, sizeof(index_key->desc));
+
+	memcpy(index_key->desc, index_key->description, n);
+
+	if (!index_key->domain_tag) {
+		if (index_key->type->flags & KEY_TYPE_NET_DOMAIN)
+			index_key->domain_tag = current->nsproxy->net_ns->key_domain;
+		else
+			index_key->domain_tag = &default_domain_tag;
+	}
+
+	hash_key_type_and_desc(index_key);
+}
+
+/**
+ * key_put_tag - Release a ref on a tag.
+ * @tag: The tag to release.
+ *
+ * This releases a reference the given tag and returns true if that ref was the
+ * last one.
+ */
+bool key_put_tag(struct key_tag *tag)
+{
+	if (refcount_dec_and_test(&tag->usage)) {
+		kfree_rcu(tag, rcu);
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * key_remove_domain - Kill off a key domain and gc its keys
+ * @domain_tag: The domain tag to release.
+ *
+ * This marks a domain tag as being dead and releases a ref on it.  If that
+ * wasn't the last reference, the garbage collector is poked to try and delete
+ * all keys that were in the domain.
+ */
+void key_remove_domain(struct key_tag *domain_tag)
+{
+	domain_tag->removed = true;
+	if (!key_put_tag(domain_tag))
+		key_schedule_gc_links();
+}
+
+/*
+ * Build the next index key chunk.
+ *
+ * We return it one word-sized chunk at a time.
+ */
+static unsigned long keyring_get_key_chunk(const void *data, int level)
+{
+	const struct keyring_index_key *index_key = data;
+	unsigned long chunk = 0;
+	const u8 *d;
+	int desc_len = index_key->desc_len, n = sizeof(chunk);
+	unsigned int offset;
+
+	level /= ASSOC_ARRAY_KEY_CHUNK_SIZE;
+	switch (level) {
+	case 0:
+		return index_key->hash;
+	case 1:
+		return index_key->x;
+	case 2:
+		return (unsigned long)index_key->type;
+	case 3:
+		return (unsigned long)index_key->domain_tag;
+	default:
+		level -= 4;
+		offset = sizeof(index_key->desc) + level * sizeof(long);
+		if (desc_len <= offset)
+			return 0;
+
+		d = index_key->description + offset;
+		desc_len -= offset;
+		if (desc_len > n)
+			desc_len = n;
+		d += desc_len;
+		do {
+			chunk <<= 8;
+			chunk |= *--d;
+		} while (--desc_len > 0);
+		return chunk;
+	}
+}
+
+static unsigned long keyring_get_object_key_chunk(const void *object, int level)
+{
+	const struct key *key = keyring_ptr_to_key(object);
+	return keyring_get_key_chunk(&key->index_key, level);
+}
+
+static bool keyring_compare_object(const void *object, const void *data)
+{
+	const struct keyring_index_key *index_key = data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	return key->index_key.type == index_key->type &&
+		key->index_key.domain_tag == index_key->domain_tag &&
+		key->index_key.desc_len == index_key->desc_len &&
+		memcmp(key->index_key.description, index_key->description,
+		       index_key->desc_len) == 0;
+}
+
+/*
+ * Compare the index keys of a pair of objects and determine the bit position
+ * at which they differ - if they differ.
+ */
+static int keyring_diff_objects(const void *object, const void *data)
+{
+	const struct key *key_a = keyring_ptr_to_key(object);
+	const struct keyring_index_key *a = &key_a->index_key;
+	const struct keyring_index_key *b = data;
+	unsigned long seg_a, seg_b;
+	int level, i;
+
+	level = 0;
+	seg_a = a->hash;
+	seg_b = b->hash;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+	level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8;
+
+	/* The number of bits contributed by the hash is controlled by a
+	 * constant in the assoc_array headers.  Everything else thereafter we
+	 * can deal with as being machine word-size dependent.
+	 */
+	seg_a = a->x;
+	seg_b = b->x;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+	level += sizeof(unsigned long);
+
+	/* The next bit may not work on big endian */
+	seg_a = (unsigned long)a->type;
+	seg_b = (unsigned long)b->type;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+	level += sizeof(unsigned long);
+
+	seg_a = (unsigned long)a->domain_tag;
+	seg_b = (unsigned long)b->domain_tag;
+	if ((seg_a ^ seg_b) != 0)
+		goto differ;
+	level += sizeof(unsigned long);
+
+	i = sizeof(a->desc);
+	if (a->desc_len <= i)
+		goto same;
+
+	for (; i < a->desc_len; i++) {
+		seg_a = *(unsigned char *)(a->description + i);
+		seg_b = *(unsigned char *)(b->description + i);
+		if ((seg_a ^ seg_b) != 0)
+			goto differ_plus_i;
+	}
+
+same:
+	return -1;
+
+differ_plus_i:
+	level += i - (int)sizeof(a->desc);
+differ:
+	i = level * 8 + __ffs(seg_a ^ seg_b);
+	return i;
+}
+
+/*
+ * Free an object after stripping the keyring flag off of the pointer.
+ */
+static void keyring_free_object(void *object)
+{
+	key_put(keyring_ptr_to_key(object));
+}
+
+/*
+ * Operations for keyring management by the index-tree routines.
+ */
+static const struct assoc_array_ops keyring_assoc_array_ops = {
+	.get_key_chunk		= keyring_get_key_chunk,
+	.get_object_key_chunk	= keyring_get_object_key_chunk,
+	.compare_object		= keyring_compare_object,
+	.diff_objects		= keyring_diff_objects,
+	.free_object		= keyring_free_object,
+};
+
+/*
+ * Clean up a keyring when it is destroyed.  Unpublish its name if it had one
+ * and dispose of its data.
+ *
+ * The garbage collector detects the final key_put(), removes the keyring from
+ * the serial number tree and then does RCU synchronisation before coming here,
+ * so we shouldn't need to worry about code poking around here with the RCU
+ * readlock held by this time.
+ */
+static void keyring_destroy(struct key *keyring)
+{
+	if (keyring->description) {
+		write_lock(&keyring_name_lock);
+
+		if (keyring->name_link.next != NULL &&
+		    !list_empty(&keyring->name_link))
+			list_del(&keyring->name_link);
+
+		write_unlock(&keyring_name_lock);
+	}
+
+	if (keyring->restrict_link) {
+		struct key_restriction *keyres = keyring->restrict_link;
+
+		key_put(keyres->key);
+		kfree(keyres);
+	}
+
+	assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops);
+}
+
+/*
+ * Describe a keyring for /proc.
+ */
+static void keyring_describe(const struct key *keyring, struct seq_file *m)
+{
+	if (keyring->description)
+		seq_puts(m, keyring->description);
+	else
+		seq_puts(m, "[anon]");
+
+	if (key_is_positive(keyring)) {
+		if (keyring->keys.nr_leaves_on_tree != 0)
+			seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree);
+		else
+			seq_puts(m, ": empty");
+	}
+}
+
+struct keyring_read_iterator_context {
+	size_t			buflen;
+	size_t			count;
+	key_serial_t		*buffer;
+};
+
+static int keyring_read_iterator(const void *object, void *data)
+{
+	struct keyring_read_iterator_context *ctx = data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	kenter("{%s,%d},,{%zu/%zu}",
+	       key->type->name, key->serial, ctx->count, ctx->buflen);
+
+	if (ctx->count >= ctx->buflen)
+		return 1;
+
+	*ctx->buffer++ = key->serial;
+	ctx->count += sizeof(key->serial);
+	return 0;
+}
+
+/*
+ * Read a list of key IDs from the keyring's contents in binary form
+ *
+ * The keyring's semaphore is read-locked by the caller.  This prevents someone
+ * from modifying it under us - which could cause us to read key IDs multiple
+ * times.
+ */
+static long keyring_read(const struct key *keyring,
+			 char *buffer, size_t buflen)
+{
+	struct keyring_read_iterator_context ctx;
+	long ret;
+
+	kenter("{%d},,%zu", key_serial(keyring), buflen);
+
+	if (buflen & (sizeof(key_serial_t) - 1))
+		return -EINVAL;
+
+	/* Copy as many key IDs as fit into the buffer */
+	if (buffer && buflen) {
+		ctx.buffer = (key_serial_t *)buffer;
+		ctx.buflen = buflen;
+		ctx.count = 0;
+		ret = assoc_array_iterate(&keyring->keys,
+					  keyring_read_iterator, &ctx);
+		if (ret < 0) {
+			kleave(" = %ld [iterate]", ret);
+			return ret;
+		}
+	}
+
+	/* Return the size of the buffer needed */
+	ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t);
+	if (ret <= buflen)
+		kleave("= %ld [ok]", ret);
+	else
+		kleave("= %ld [buffer too small]", ret);
+	return ret;
+}
+
+/*
+ * Allocate a keyring and link into the destination keyring.
+ */
+struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid,
+			  const struct cred *cred, key_perm_t perm,
+			  unsigned long flags,
+			  struct key_restriction *restrict_link,
+			  struct key *dest)
+{
+	struct key *keyring;
+	int ret;
+
+	keyring = key_alloc(&key_type_keyring, description,
+			    uid, gid, cred, perm, flags, restrict_link);
+	if (!IS_ERR(keyring)) {
+		ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL);
+		if (ret < 0) {
+			key_put(keyring);
+			keyring = ERR_PTR(ret);
+		}
+	}
+
+	return keyring;
+}
+EXPORT_SYMBOL(keyring_alloc);
+
+/**
+ * restrict_link_reject - Give -EPERM to restrict link
+ * @keyring: The keyring being added to.
+ * @type: The type of key being added.
+ * @payload: The payload of the key intended to be added.
+ * @restriction_key: Keys providing additional data for evaluating restriction.
+ *
+ * Reject the addition of any links to a keyring.  It can be overridden by
+ * passing KEY_ALLOC_BYPASS_RESTRICTION to key_instantiate_and_link() when
+ * adding a key to a keyring.
+ *
+ * This is meant to be stored in a key_restriction structure which is passed
+ * in the restrict_link parameter to keyring_alloc().
+ */
+int restrict_link_reject(struct key *keyring,
+			 const struct key_type *type,
+			 const union key_payload *payload,
+			 struct key *restriction_key)
+{
+	return -EPERM;
+}
+
+/*
+ * By default, we keys found by getting an exact match on their descriptions.
+ */
+bool key_default_cmp(const struct key *key,
+		     const struct key_match_data *match_data)
+{
+	return strcmp(key->description, match_data->raw_data) == 0;
+}
+
+/*
+ * Iteration function to consider each key found.
+ */
+static int keyring_search_iterator(const void *object, void *iterator_data)
+{
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+	unsigned long kflags = READ_ONCE(key->flags);
+	short state = key_read_state(key);
+
+	kenter("{%d}", key->serial);
+
+	/* ignore keys not of this type */
+	if (key->type != ctx->index_key.type) {
+		kleave(" = 0 [!type]");
+		return 0;
+	}
+
+	/* skip invalidated, revoked and expired keys */
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		time64_t expiry = READ_ONCE(key->expiry);
+
+		if (kflags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED))) {
+			ctx->result = ERR_PTR(-EKEYREVOKED);
+			kleave(" = %d [invrev]", ctx->skipped_ret);
+			goto skipped;
+		}
+
+		if (expiry && ctx->now >= expiry) {
+			if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED))
+				ctx->result = ERR_PTR(-EKEYEXPIRED);
+			kleave(" = %d [expire]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
+
+	/* keys that don't match */
+	if (!ctx->match_data.cmp(key, &ctx->match_data)) {
+		kleave(" = 0 [!match]");
+		return 0;
+	}
+
+	/* key must have search permissions */
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+	    key_task_permission(make_key_ref(key, ctx->possessed),
+				ctx->cred, KEY_NEED_SEARCH) < 0) {
+		ctx->result = ERR_PTR(-EACCES);
+		kleave(" = %d [!perm]", ctx->skipped_ret);
+		goto skipped;
+	}
+
+	if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) {
+		/* we set a different error code if we pass a negative key */
+		if (state < 0) {
+			ctx->result = ERR_PTR(state);
+			kleave(" = %d [neg]", ctx->skipped_ret);
+			goto skipped;
+		}
+	}
+
+	/* Found */
+	ctx->result = make_key_ref(key, ctx->possessed);
+	kleave(" = 1 [found]");
+	return 1;
+
+skipped:
+	return ctx->skipped_ret;
+}
+
+/*
+ * Search inside a keyring for a key.  We can search by walking to it
+ * directly based on its index-key or we can iterate over the entire
+ * tree looking for it, based on the match function.
+ */
+static int search_keyring(struct key *keyring, struct keyring_search_context *ctx)
+{
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) {
+		const void *object;
+
+		object = assoc_array_find(&keyring->keys,
+					  &keyring_assoc_array_ops,
+					  &ctx->index_key);
+		return object ? ctx->iterator(object, ctx) : 0;
+	}
+	return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx);
+}
+
+/*
+ * Search a tree of keyrings that point to other keyrings up to the maximum
+ * depth.
+ */
+static bool search_nested_keyrings(struct key *keyring,
+				   struct keyring_search_context *ctx)
+{
+	struct {
+		struct key *keyring;
+		struct assoc_array_node *node;
+		int slot;
+	} stack[KEYRING_SEARCH_MAX_DEPTH];
+
+	struct assoc_array_shortcut *shortcut;
+	struct assoc_array_node *node;
+	struct assoc_array_ptr *ptr;
+	struct key *key;
+	int sp = 0, slot;
+
+	kenter("{%d},{%s,%s}",
+	       keyring->serial,
+	       ctx->index_key.type->name,
+	       ctx->index_key.description);
+
+#define STATE_CHECKS (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_DO_STATE_CHECK)
+	BUG_ON((ctx->flags & STATE_CHECKS) == 0 ||
+	       (ctx->flags & STATE_CHECKS) == STATE_CHECKS);
+
+	if (ctx->index_key.description)
+		key_set_index_key(&ctx->index_key);
+
+	/* Check to see if this top-level keyring is what we are looking for
+	 * and whether it is valid or not.
+	 */
+	if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE ||
+	    keyring_compare_object(keyring, &ctx->index_key)) {
+		ctx->skipped_ret = 2;
+		switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) {
+		case 1:
+			goto found;
+		case 2:
+			return false;
+		default:
+			break;
+		}
+	}
+
+	ctx->skipped_ret = 0;
+
+	/* Start processing a new keyring */
+descend_to_keyring:
+	kdebug("descend to %d", keyring->serial);
+	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED)))
+		goto not_this_keyring;
+
+	/* Search through the keys in this keyring before its searching its
+	 * subtrees.
+	 */
+	if (search_keyring(keyring, ctx))
+		goto found;
+
+	/* Then manually iterate through the keyrings nested in this one.
+	 *
+	 * Start from the root node of the index tree.  Because of the way the
+	 * hash function has been set up, keyrings cluster on the leftmost
+	 * branch of the root node (root slot 0) or in the root node itself.
+	 * Non-keyrings avoid the leftmost branch of the root entirely (root
+	 * slots 1-15).
+	 */
+	if (!(ctx->flags & KEYRING_SEARCH_RECURSE))
+		goto not_this_keyring;
+
+	ptr = READ_ONCE(keyring->keys.root);
+	if (!ptr)
+		goto not_this_keyring;
+
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		/* If the root is a shortcut, either the keyring only contains
+		 * keyring pointers (everything clusters behind root slot 0) or
+		 * doesn't contain any keyring pointers.
+		 */
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0)
+			goto not_this_keyring;
+
+		ptr = READ_ONCE(shortcut->next_node);
+		node = assoc_array_ptr_to_node(ptr);
+		goto begin_node;
+	}
+
+	node = assoc_array_ptr_to_node(ptr);
+	ptr = node->slots[0];
+	if (!assoc_array_ptr_is_meta(ptr))
+		goto begin_node;
+
+descend_to_node:
+	/* Descend to a more distal node in this keyring's content tree and go
+	 * through that.
+	 */
+	kdebug("descend");
+	if (assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		ptr = READ_ONCE(shortcut->next_node);
+		BUG_ON(!assoc_array_ptr_is_node(ptr));
+	}
+	node = assoc_array_ptr_to_node(ptr);
+
+begin_node:
+	kdebug("begin_node");
+	slot = 0;
+ascend_to_node:
+	/* Go through the slots in a node */
+	for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) {
+		ptr = READ_ONCE(node->slots[slot]);
+
+		if (assoc_array_ptr_is_meta(ptr)) {
+			if (node->back_pointer ||
+			    assoc_array_ptr_is_shortcut(ptr))
+				goto descend_to_node;
+		}
+
+		if (!keyring_ptr_is_keyring(ptr))
+			continue;
+
+		key = keyring_ptr_to_key(ptr);
+
+		if (sp >= KEYRING_SEARCH_MAX_DEPTH) {
+			if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) {
+				ctx->result = ERR_PTR(-ELOOP);
+				return false;
+			}
+			goto not_this_keyring;
+		}
+
+		/* Search a nested keyring */
+		if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) &&
+		    key_task_permission(make_key_ref(key, ctx->possessed),
+					ctx->cred, KEY_NEED_SEARCH) < 0)
+			continue;
+
+		/* stack the current position */
+		stack[sp].keyring = keyring;
+		stack[sp].node = node;
+		stack[sp].slot = slot;
+		sp++;
+
+		/* begin again with the new keyring */
+		keyring = key;
+		goto descend_to_keyring;
+	}
+
+	/* We've dealt with all the slots in the current node, so now we need
+	 * to ascend to the parent and continue processing there.
+	 */
+	ptr = READ_ONCE(node->back_pointer);
+	slot = node->parent_slot;
+
+	if (ptr && assoc_array_ptr_is_shortcut(ptr)) {
+		shortcut = assoc_array_ptr_to_shortcut(ptr);
+		ptr = READ_ONCE(shortcut->back_pointer);
+		slot = shortcut->parent_slot;
+	}
+	if (!ptr)
+		goto not_this_keyring;
+	node = assoc_array_ptr_to_node(ptr);
+	slot++;
+
+	/* If we've ascended to the root (zero backpointer), we must have just
+	 * finished processing the leftmost branch rather than the root slots -
+	 * so there can't be any more keyrings for us to find.
+	 */
+	if (node->back_pointer) {
+		kdebug("ascend %d", slot);
+		goto ascend_to_node;
+	}
+
+	/* The keyring we're looking at was disqualified or didn't contain a
+	 * matching key.
+	 */
+not_this_keyring:
+	kdebug("not_this_keyring %d", sp);
+	if (sp <= 0) {
+		kleave(" = false");
+		return false;
+	}
+
+	/* Resume the processing of a keyring higher up in the tree */
+	sp--;
+	keyring = stack[sp].keyring;
+	node = stack[sp].node;
+	slot = stack[sp].slot + 1;
+	kdebug("ascend to %d [%d]", keyring->serial, slot);
+	goto ascend_to_node;
+
+	/* We found a viable match */
+found:
+	key = key_ref_to_ptr(ctx->result);
+	key_check(key);
+	if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) {
+		key->last_used_at = ctx->now;
+		keyring->last_used_at = ctx->now;
+		while (sp > 0)
+			stack[--sp].keyring->last_used_at = ctx->now;
+	}
+	kleave(" = true");
+	return true;
+}
+
+/**
+ * keyring_search_rcu - Search a keyring tree for a matching key under RCU
+ * @keyring_ref: A pointer to the keyring with possession indicator.
+ * @ctx: The keyring search context.
+ *
+ * Search the supplied keyring tree for a key that matches the criteria given.
+ * The root keyring and any linked keyrings must grant Search permission to the
+ * caller to be searchable and keys can only be found if they too grant Search
+ * to the caller. The possession flag on the root keyring pointer controls use
+ * of the possessor bits in permissions checking of the entire tree.  In
+ * addition, the LSM gets to forbid keyring searches and key matches.
+ *
+ * The search is performed as a breadth-then-depth search up to the prescribed
+ * limit (KEYRING_SEARCH_MAX_DEPTH).  The caller must hold the RCU read lock to
+ * prevent keyrings from being destroyed or rearranged whilst they are being
+ * searched.
+ *
+ * Keys are matched to the type provided and are then filtered by the match
+ * function, which is given the description to use in any way it sees fit.  The
+ * match function may use any attributes of a key that it wishes to
+ * determine the match.  Normally the match function from the key type would be
+ * used.
+ *
+ * RCU can be used to prevent the keyring key lists from disappearing without
+ * the need to take lots of locks.
+ *
+ * Returns a pointer to the found key and increments the key usage count if
+ * successful; -EAGAIN if no matching keys were found, or if expired or revoked
+ * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the
+ * specified keyring wasn't a keyring.
+ *
+ * In the case of a successful return, the possession attribute from
+ * @keyring_ref is propagated to the returned key reference.
+ */
+key_ref_t keyring_search_rcu(key_ref_t keyring_ref,
+			     struct keyring_search_context *ctx)
+{
+	struct key *keyring;
+	long err;
+
+	ctx->iterator = keyring_search_iterator;
+	ctx->possessed = is_key_possessed(keyring_ref);
+	ctx->result = ERR_PTR(-EAGAIN);
+
+	keyring = key_ref_to_ptr(keyring_ref);
+	key_check(keyring);
+
+	if (keyring->type != &key_type_keyring)
+		return ERR_PTR(-ENOTDIR);
+
+	if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) {
+		err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	ctx->now = ktime_get_real_seconds();
+	if (search_nested_keyrings(keyring, ctx))
+		__key_get(key_ref_to_ptr(ctx->result));
+	return ctx->result;
+}
+
+/**
+ * keyring_search - Search the supplied keyring tree for a matching key
+ * @keyring: The root of the keyring tree to be searched.
+ * @type: The type of keyring we want to find.
+ * @description: The name of the keyring we want to find.
+ * @recurse: True to search the children of @keyring also
+ *
+ * As keyring_search_rcu() above, but using the current task's credentials and
+ * type's default matching function and preferred search method.
+ */
+key_ref_t keyring_search(key_ref_t keyring,
+			 struct key_type *type,
+			 const char *description,
+			 bool recurse)
+{
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.index_key.desc_len	= strlen(description),
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
+	};
+	key_ref_t key;
+	int ret;
+
+	if (recurse)
+		ctx.flags |= KEYRING_SEARCH_RECURSE;
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0)
+			return ERR_PTR(ret);
+	}
+
+	rcu_read_lock();
+	key = keyring_search_rcu(keyring, &ctx);
+	rcu_read_unlock();
+
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
+	return key;
+}
+EXPORT_SYMBOL(keyring_search);
+
+static struct key_restriction *keyring_restriction_alloc(
+	key_restrict_link_func_t check)
+{
+	struct key_restriction *keyres =
+		kzalloc_obj(struct key_restriction);
+
+	if (!keyres)
+		return ERR_PTR(-ENOMEM);
+
+	keyres->check = check;
+
+	return keyres;
+}
+
+/*
+ * Semaphore to serialise restriction setup to prevent reference count
+ * cycles through restriction key pointers.
+ */
+static DECLARE_RWSEM(keyring_serialise_restrict_sem);
+
+/*
+ * Check for restriction cycles that would prevent keyring garbage collection.
+ * keyring_serialise_restrict_sem must be held.
+ */
+static bool keyring_detect_restriction_cycle(const struct key *dest_keyring,
+					     struct key_restriction *keyres)
+{
+	while (keyres && keyres->key &&
+	       keyres->key->type == &key_type_keyring) {
+		if (keyres->key == dest_keyring)
+			return true;
+
+		keyres = keyres->key->restrict_link;
+	}
+
+	return false;
+}
+
+/**
+ * keyring_restrict - Look up and apply a restriction to a keyring
+ * @keyring_ref: The keyring to be restricted
+ * @type: The key type that will provide the restriction checker.
+ * @restriction: The restriction options to apply to the keyring
+ *
+ * Look up a keyring and apply a restriction to it.  The restriction is managed
+ * by the specific key type, but can be configured by the options specified in
+ * the restriction string.
+ */
+int keyring_restrict(key_ref_t keyring_ref, const char *type,
+		     const char *restriction)
+{
+	struct key *keyring;
+	struct key_type *restrict_type = NULL;
+	struct key_restriction *restrict_link;
+	int ret = 0;
+
+	keyring = key_ref_to_ptr(keyring_ref);
+	key_check(keyring);
+
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
+
+	if (!type) {
+		restrict_link = keyring_restriction_alloc(restrict_link_reject);
+	} else {
+		restrict_type = key_type_lookup(type);
+
+		if (IS_ERR(restrict_type))
+			return PTR_ERR(restrict_type);
+
+		if (!restrict_type->lookup_restriction) {
+			ret = -ENOENT;
+			goto error;
+		}
+
+		restrict_link = restrict_type->lookup_restriction(restriction);
+	}
+
+	if (IS_ERR(restrict_link)) {
+		ret = PTR_ERR(restrict_link);
+		goto error;
+	}
+
+	down_write(&keyring->sem);
+	down_write(&keyring_serialise_restrict_sem);
+
+	if (keyring->restrict_link) {
+		ret = -EEXIST;
+	} else if (keyring_detect_restriction_cycle(keyring, restrict_link)) {
+		ret = -EDEADLK;
+	} else {
+		keyring->restrict_link = restrict_link;
+		notify_key(keyring, NOTIFY_KEY_SETATTR, 0);
+	}
+
+	up_write(&keyring_serialise_restrict_sem);
+	up_write(&keyring->sem);
+
+	if (ret < 0) {
+		key_put(restrict_link->key);
+		kfree(restrict_link);
+	}
+
+error:
+	if (restrict_type)
+		key_type_put(restrict_type);
+
+	return ret;
+}
+EXPORT_SYMBOL(keyring_restrict);
+
+/*
+ * Search the given keyring for a key that might be updated.
+ *
+ * The caller must guarantee that the keyring is a keyring and that the
+ * permission is granted to modify the keyring as no check is made here.  The
+ * caller must also hold a lock on the keyring semaphore.
+ *
+ * Returns a pointer to the found key with usage count incremented if
+ * successful and returns NULL if not found.  Revoked and invalidated keys are
+ * skipped over.
+ *
+ * If successful, the possession indicator is propagated from the keyring ref
+ * to the returned key reference.
+ */
+key_ref_t find_key_to_update(key_ref_t keyring_ref,
+			     const struct keyring_index_key *index_key)
+{
+	struct key *keyring, *key;
+	const void *object;
+
+	keyring = key_ref_to_ptr(keyring_ref);
+
+	kenter("{%d},{%s,%s}",
+	       keyring->serial, index_key->type->name, index_key->description);
+
+	guard(rcu)();
+	object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops,
+				  index_key);
+
+	if (object)
+		goto found;
+
+	kleave(" = NULL");
+	return NULL;
+
+found:
+	key = keyring_ptr_to_key(object);
+	if (key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			  (1 << KEY_FLAG_REVOKED))) {
+		kleave(" = NULL [x]");
+		return NULL;
+	}
+	__key_get(key);
+	kleave(" = {%d}", key->serial);
+	return make_key_ref(key, is_key_possessed(keyring_ref));
+}
+
+/*
+ * Find a keyring with the specified name.
+ *
+ * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
+ * user in the current user namespace are considered.  If @uid_keyring is %true,
+ * the keyring additionally must have been allocated as a user or user session
+ * keyring; otherwise, it must grant Search permission directly to the caller.
+ *
+ * Returns a pointer to the keyring with the keyring's refcount having being
+ * incremented on success.  -ENOKEY is returned if a key could not be found.
+ */
+struct key *find_keyring_by_name(const char *name, bool uid_keyring)
+{
+	struct user_namespace *ns = current_user_ns();
+	struct key *keyring;
+
+	if (!name)
+		return ERR_PTR(-EINVAL);
+
+	read_lock(&keyring_name_lock);
+
+	/* Search this hash bucket for a keyring with a matching name that
+	 * grants Search permission and that hasn't been revoked
+	 */
+	list_for_each_entry(keyring, &ns->keyring_name_list, name_link) {
+		if (!kuid_has_mapping(ns, keyring->user->uid))
+			continue;
+
+		if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
+			continue;
+
+		if (strcmp(keyring->description, name) != 0)
+			continue;
+
+		if (uid_keyring) {
+			if (!test_bit(KEY_FLAG_UID_KEYRING,
+				      &keyring->flags))
+				continue;
+		} else {
+			if (key_permission(make_key_ref(keyring, 0),
+					   KEY_NEED_SEARCH) < 0)
+				continue;
+		}
+
+		/* we've got a match but we might end up racing with
+		 * key_cleanup() if the keyring is currently 'dead'
+		 * (ie. it has a zero usage count) */
+		if (!refcount_inc_not_zero(&keyring->usage))
+			continue;
+		keyring->last_used_at = ktime_get_real_seconds();
+		goto out;
+	}
+
+	keyring = ERR_PTR(-ENOKEY);
+out:
+	read_unlock(&keyring_name_lock);
+	return keyring;
+}
+
+static int keyring_detect_cycle_iterator(const void *object,
+					 void *iterator_data)
+{
+	struct keyring_search_context *ctx = iterator_data;
+	const struct key *key = keyring_ptr_to_key(object);
+
+	kenter("{%d}", key->serial);
+
+	/* We might get a keyring with matching index-key that is nonetheless a
+	 * different keyring. */
+	if (key != ctx->match_data.raw_data)
+		return 0;
+
+	ctx->result = ERR_PTR(-EDEADLK);
+	return 1;
+}
+
+/*
+ * See if a cycle will be created by inserting acyclic tree B in acyclic
+ * tree A at the topmost level (ie: as a direct child of A).
+ *
+ * Since we are adding B to A at the top level, checking for cycles should just
+ * be a matter of seeing if node A is somewhere in tree B.
+ */
+static int keyring_detect_cycle(struct key *A, struct key *B)
+{
+	struct keyring_search_context ctx = {
+		.index_key		= A->index_key,
+		.match_data.raw_data	= A,
+		.match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
+		.iterator		= keyring_detect_cycle_iterator,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_NO_UPDATE_TIME |
+					   KEYRING_SEARCH_NO_CHECK_PERM |
+					   KEYRING_SEARCH_DETECT_TOO_DEEP |
+					   KEYRING_SEARCH_RECURSE),
+	};
+
+	rcu_read_lock();
+	search_nested_keyrings(B, &ctx);
+	rcu_read_unlock();
+	return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result);
+}
+
+/*
+ * Lock keyring for link.
+ */
+int __key_link_lock(struct key *keyring,
+		    const struct keyring_index_key *index_key)
+	__acquires(&keyring->sem)
+	__acquires(&keyring_serialise_link_lock)
+{
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
+
+	down_write(&keyring->sem);
+
+	/* Serialise link/link calls to prevent parallel calls causing a cycle
+	 * when linking two keyring in opposite orders.
+	 */
+	if (index_key->type == &key_type_keyring)
+		mutex_lock(&keyring_serialise_link_lock);
+
+	return 0;
+}
+
+/*
+ * Lock keyrings for move (link/unlink combination).
+ */
+int __key_move_lock(struct key *l_keyring, struct key *u_keyring,
+		    const struct keyring_index_key *index_key)
+	__acquires(&l_keyring->sem)
+	__acquires(&u_keyring->sem)
+	__acquires(&keyring_serialise_link_lock)
+{
+	if (l_keyring->type != &key_type_keyring ||
+	    u_keyring->type != &key_type_keyring)
+		return -ENOTDIR;
+
+	/* We have to be very careful here to take the keyring locks in the
+	 * right order, lest we open ourselves to deadlocking against another
+	 * move operation.
+	 */
+	if (l_keyring < u_keyring) {
+		down_write(&l_keyring->sem);
+		down_write_nested(&u_keyring->sem, 1);
+	} else {
+		down_write(&u_keyring->sem);
+		down_write_nested(&l_keyring->sem, 1);
+	}
+
+	/* Serialise link/link calls to prevent parallel calls causing a cycle
+	 * when linking two keyring in opposite orders.
+	 */
+	if (index_key->type == &key_type_keyring)
+		mutex_lock(&keyring_serialise_link_lock);
+
+	return 0;
+}
+
+/*
+ * Preallocate memory so that a key can be linked into to a keyring.
+ */
+int __key_link_begin(struct key *keyring,
+		     const struct keyring_index_key *index_key,
+		     struct assoc_array_edit **_edit)
+{
+	struct assoc_array_edit *edit;
+	int ret;
+
+	kenter("%d,%s,%s,",
+	       keyring->serial, index_key->type->name, index_key->description);
+
+	BUG_ON(index_key->desc_len == 0);
+	BUG_ON(*_edit != NULL);
+
+	*_edit = NULL;
+
+	ret = -EKEYREVOKED;
+	if (test_bit(KEY_FLAG_REVOKED, &keyring->flags))
+		goto error;
+
+	/* Create an edit script that will insert/replace the key in the
+	 * keyring tree.
+	 */
+	edit = assoc_array_insert(&keyring->keys,
+				  &keyring_assoc_array_ops,
+				  index_key,
+				  NULL);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+		goto error;
+	}
+
+	/* If we're not replacing a link in-place then we're going to need some
+	 * extra quota.
+	 */
+	if (!edit->dead_leaf) {
+		ret = key_payload_reserve(keyring,
+					  keyring->datalen + KEYQUOTA_LINK_BYTES);
+		if (ret < 0)
+			goto error_cancel;
+	}
+
+	*_edit = edit;
+	kleave(" = 0");
+	return 0;
+
+error_cancel:
+	assoc_array_cancel_edit(edit);
+error:
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Check already instantiated keys aren't going to be a problem.
+ *
+ * The caller must have called __key_link_begin(). Don't need to call this for
+ * keys that were created since __key_link_begin() was called.
+ */
+int __key_link_check_live_key(struct key *keyring, struct key *key)
+{
+	if (key->type == &key_type_keyring)
+		/* check that we aren't going to create a cycle by linking one
+		 * keyring to another */
+		return keyring_detect_cycle(keyring, key);
+	return 0;
+}
+
+/*
+ * Link a key into to a keyring.
+ *
+ * Must be called with __key_link_begin() having being called.  Discards any
+ * already extant link to matching key if there is one, so that each keyring
+ * holds at most one link to any given key of a particular type+description
+ * combination.
+ */
+void __key_link(struct key *keyring, struct key *key,
+		struct assoc_array_edit **_edit)
+{
+	__key_get(key);
+	assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
+	assoc_array_apply_edit(*_edit);
+	*_edit = NULL;
+	notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key));
+}
+
+/*
+ * Finish linking a key into to a keyring.
+ *
+ * Must be called with __key_link_begin() having being called.
+ */
+void __key_link_end(struct key *keyring,
+		    const struct keyring_index_key *index_key,
+		    struct assoc_array_edit *edit)
+	__releases(&keyring->sem)
+	__releases(&keyring_serialise_link_lock)
+{
+	BUG_ON(index_key->type == NULL);
+	kenter("%d,%s,", keyring->serial, index_key->type->name);
+
+	if (edit) {
+		if (!edit->dead_leaf) {
+			key_payload_reserve(keyring,
+				keyring->datalen - KEYQUOTA_LINK_BYTES);
+		}
+		assoc_array_cancel_edit(edit);
+	}
+	up_write(&keyring->sem);
+
+	if (index_key->type == &key_type_keyring)
+		mutex_unlock(&keyring_serialise_link_lock);
+}
+
+/*
+ * Check addition of keys to restricted keyrings.
+ */
+static int __key_link_check_restriction(struct key *keyring, struct key *key)
+{
+	if (!keyring->restrict_link || !keyring->restrict_link->check)
+		return 0;
+	return keyring->restrict_link->check(keyring, key->type, &key->payload,
+					     keyring->restrict_link->key);
+}
+
+/**
+ * key_link - Link a key to a keyring
+ * @keyring: The keyring to make the link in.
+ * @key: The key to link to.
+ *
+ * Make a link in a keyring to a key, such that the keyring holds a reference
+ * on that key and the key can potentially be found by searching that keyring.
+ *
+ * This function will write-lock the keyring's semaphore and will consume some
+ * of the user's key data quota to hold the link.
+ *
+ * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring,
+ * -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is
+ * full, -EDQUOT if there is insufficient key data quota remaining to add
+ * another link or -ENOMEM if there's insufficient memory.
+ *
+ * It is assumed that the caller has checked that it is permitted for a link to
+ * be made (the keyring should have Write permission and the key Link
+ * permission).
+ */
+int key_link(struct key *keyring, struct key *key)
+{
+	struct assoc_array_edit *edit = NULL;
+	int ret;
+
+	kenter("{%d,%d}", keyring->serial, refcount_read(&keyring->usage));
+
+	key_check(keyring);
+	key_check(key);
+
+	ret = __key_link_lock(keyring, &key->index_key);
+	if (ret < 0)
+		goto error;
+
+	ret = __key_link_begin(keyring, &key->index_key, &edit);
+	if (ret < 0)
+		goto error_end;
+
+	kdebug("begun {%d,%d}", keyring->serial, refcount_read(&keyring->usage));
+	ret = __key_link_check_restriction(keyring, key);
+	if (ret == 0)
+		ret = __key_link_check_live_key(keyring, key);
+	if (ret == 0)
+		__key_link(keyring, key, &edit);
+
+error_end:
+	__key_link_end(keyring, &key->index_key, edit);
+error:
+	kleave(" = %d {%d,%d}", ret, keyring->serial, refcount_read(&keyring->usage));
+	return ret;
+}
+EXPORT_SYMBOL(key_link);
+
+/*
+ * Lock a keyring for unlink.
+ */
+static int __key_unlink_lock(struct key *keyring)
+	__acquires(&keyring->sem)
+{
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
+
+	down_write(&keyring->sem);
+	return 0;
+}
+
+/*
+ * Begin the process of unlinking a key from a keyring.
+ */
+static int __key_unlink_begin(struct key *keyring, struct key *key,
+			      struct assoc_array_edit **_edit)
+{
+	struct assoc_array_edit *edit;
+
+	BUG_ON(*_edit != NULL);
+
+	edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
+				  &key->index_key);
+	if (IS_ERR(edit))
+		return PTR_ERR(edit);
+
+	if (!edit)
+		return -ENOENT;
+
+	*_edit = edit;
+	return 0;
+}
+
+/*
+ * Apply an unlink change.
+ */
+static void __key_unlink(struct key *keyring, struct key *key,
+			 struct assoc_array_edit **_edit)
+{
+	assoc_array_apply_edit(*_edit);
+	notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key));
+	*_edit = NULL;
+	key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
+}
+
+/*
+ * Finish unlinking a key from to a keyring.
+ */
+static void __key_unlink_end(struct key *keyring,
+			     struct key *key,
+			     struct assoc_array_edit *edit)
+	__releases(&keyring->sem)
+{
+	if (edit)
+		assoc_array_cancel_edit(edit);
+	up_write(&keyring->sem);
+}
+
+/**
+ * key_unlink - Unlink the first link to a key from a keyring.
+ * @keyring: The keyring to remove the link from.
+ * @key: The key the link is to.
+ *
+ * Remove a link from a keyring to a key.
+ *
+ * This function will write-lock the keyring's semaphore.
+ *
+ * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if
+ * the key isn't linked to by the keyring or -ENOMEM if there's insufficient
+ * memory.
+ *
+ * It is assumed that the caller has checked that it is permitted for a link to
+ * be removed (the keyring should have Write permission; no permissions are
+ * required on the key).
+ */
+int key_unlink(struct key *keyring, struct key *key)
+{
+	struct assoc_array_edit *edit = NULL;
+	int ret;
+
+	key_check(keyring);
+	key_check(key);
+
+	ret = __key_unlink_lock(keyring);
+	if (ret < 0)
+		return ret;
+
+	ret = __key_unlink_begin(keyring, key, &edit);
+	if (ret == 0)
+		__key_unlink(keyring, key, &edit);
+	__key_unlink_end(keyring, key, edit);
+	return ret;
+}
+EXPORT_SYMBOL(key_unlink);
+
+/**
+ * key_move - Move a key from one keyring to another
+ * @key: The key to move
+ * @from_keyring: The keyring to remove the link from.
+ * @to_keyring: The keyring to make the link in.
+ * @flags: Qualifying flags, such as KEYCTL_MOVE_EXCL.
+ *
+ * Make a link in @to_keyring to a key, such that the keyring holds a reference
+ * on that key and the key can potentially be found by searching that keyring
+ * whilst simultaneously removing a link to the key from @from_keyring.
+ *
+ * This function will write-lock both keyring's semaphores and will consume
+ * some of the user's key data quota to hold the link on @to_keyring.
+ *
+ * Returns 0 if successful, -ENOTDIR if either keyring isn't a keyring,
+ * -EKEYREVOKED if either keyring has been revoked, -ENFILE if the second
+ * keyring is full, -EDQUOT if there is insufficient key data quota remaining
+ * to add another link or -ENOMEM if there's insufficient memory.  If
+ * KEYCTL_MOVE_EXCL is set, then -EEXIST will be returned if there's already a
+ * matching key in @to_keyring.
+ *
+ * It is assumed that the caller has checked that it is permitted for a link to
+ * be made (the keyring should have Write permission and the key Link
+ * permission).
+ */
+int key_move(struct key *key,
+	     struct key *from_keyring,
+	     struct key *to_keyring,
+	     unsigned int flags)
+{
+	struct assoc_array_edit *from_edit = NULL, *to_edit = NULL;
+	int ret;
+
+	kenter("%d,%d,%d", key->serial, from_keyring->serial, to_keyring->serial);
+
+	if (from_keyring == to_keyring)
+		return 0;
+
+	key_check(key);
+	key_check(from_keyring);
+	key_check(to_keyring);
+
+	ret = __key_move_lock(from_keyring, to_keyring, &key->index_key);
+	if (ret < 0)
+		goto out;
+	ret = __key_unlink_begin(from_keyring, key, &from_edit);
+	if (ret < 0)
+		goto error;
+	ret = __key_link_begin(to_keyring, &key->index_key, &to_edit);
+	if (ret < 0)
+		goto error;
+
+	ret = -EEXIST;
+	if (to_edit->dead_leaf && (flags & KEYCTL_MOVE_EXCL))
+		goto error;
+
+	ret = __key_link_check_restriction(to_keyring, key);
+	if (ret < 0)
+		goto error;
+	ret = __key_link_check_live_key(to_keyring, key);
+	if (ret < 0)
+		goto error;
+
+	__key_unlink(from_keyring, key, &from_edit);
+	__key_link(to_keyring, key, &to_edit);
+error:
+	__key_link_end(to_keyring, &key->index_key, to_edit);
+	__key_unlink_end(from_keyring, key, from_edit);
+out:
+	kleave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(key_move);
+
+/**
+ * keyring_clear - Clear a keyring
+ * @keyring: The keyring to clear.
+ *
+ * Clear the contents of the specified keyring.
+ *
+ * Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring.
+ */
+int keyring_clear(struct key *keyring)
+{
+	struct assoc_array_edit *edit;
+	int ret;
+
+	if (keyring->type != &key_type_keyring)
+		return -ENOTDIR;
+
+	down_write(&keyring->sem);
+
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (IS_ERR(edit)) {
+		ret = PTR_ERR(edit);
+	} else {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		notify_key(keyring, NOTIFY_KEY_CLEARED, 0);
+		key_payload_reserve(keyring, 0);
+		ret = 0;
+	}
+
+	up_write(&keyring->sem);
+	return ret;
+}
+EXPORT_SYMBOL(keyring_clear);
+
+/*
+ * Dispose of the links from a revoked keyring.
+ *
+ * This is called with the key sem write-locked.
+ */
+static void keyring_revoke(struct key *keyring)
+{
+	struct assoc_array_edit *edit;
+
+	edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops);
+	if (!IS_ERR(edit)) {
+		if (edit)
+			assoc_array_apply_edit(edit);
+		key_payload_reserve(keyring, 0);
+	}
+}
+
+static bool keyring_gc_select_iterator(void *object, void *iterator_data)
+{
+	struct key *key = keyring_ptr_to_key(object);
+	time64_t *limit = iterator_data;
+
+	if (key_is_dead(key, *limit))
+		return false;
+	key_get(key);
+	return true;
+}
+
+static int keyring_gc_check_iterator(const void *object, void *iterator_data)
+{
+	const struct key *key = keyring_ptr_to_key(object);
+	time64_t *limit = iterator_data;
+
+	key_check(key);
+	return key_is_dead(key, *limit);
+}
+
+/*
+ * Garbage collect pointers from a keyring.
+ *
+ * Not called with any locks held.  The keyring's key struct will not be
+ * deallocated under us as only our caller may deallocate it.
+ */
+void keyring_gc(struct key *keyring, time64_t limit)
+{
+	int result;
+
+	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
+
+	if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			      (1 << KEY_FLAG_REVOKED)))
+		goto dont_gc;
+
+	/* scan the keyring looking for dead keys */
+	rcu_read_lock();
+	result = assoc_array_iterate(&keyring->keys,
+				     keyring_gc_check_iterator, &limit);
+	rcu_read_unlock();
+	if (result == true)
+		goto do_gc;
+
+dont_gc:
+	kleave(" [no gc]");
+	return;
+
+do_gc:
+	down_write(&keyring->sem);
+	assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops,
+		       keyring_gc_select_iterator, &limit);
+	up_write(&keyring->sem);
+	kleave(" [gc]");
+}
+
+/*
+ * Garbage collect restriction pointers from a keyring.
+ *
+ * Keyring restrictions are associated with a key type, and must be cleaned
+ * up if the key type is unregistered. The restriction is altered to always
+ * reject additional keys so a keyring cannot be opened up by unregistering
+ * a key type.
+ *
+ * Not called with any keyring locks held. The keyring's key struct will not
+ * be deallocated under us as only our caller may deallocate it.
+ *
+ * The caller is required to hold key_types_sem and dead_type->sem. This is
+ * fulfilled by key_gc_keytype() holding the locks on behalf of
+ * key_garbage_collector(), which it invokes on a workqueue.
+ */
+void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type)
+{
+	struct key_restriction *keyres;
+
+	kenter("%x{%s}", keyring->serial, keyring->description ?: "");
+
+	/*
+	 * keyring->restrict_link is only assigned at key allocation time
+	 * or with the key type locked, so the only values that could be
+	 * concurrently assigned to keyring->restrict_link are for key
+	 * types other than dead_type. Given this, it's ok to check
+	 * the key type before acquiring keyring->sem.
+	 */
+	if (!dead_type || !keyring->restrict_link ||
+	    keyring->restrict_link->keytype != dead_type) {
+		kleave(" [no restriction gc]");
+		return;
+	}
+
+	/* Lock the keyring to ensure that a link is not in progress */
+	down_write(&keyring->sem);
+
+	keyres = keyring->restrict_link;
+
+	keyres->check = restrict_link_reject;
+
+	key_put(keyres->key);
+	keyres->key = NULL;
+	keyres->keytype = NULL;
+
+	up_write(&keyring->sem);
+
+	kleave(" [restriction gc]");
+}
diff --git a/security/keys/permission.c b/security/keys/permission.c
new file mode 100644
index 000000000..4a61f804e
--- /dev/null
+++ b/security/keys/permission.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key permission checking
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/security.h>
+#include "internal.h"
+
+/**
+ * key_task_permission - Check a key can be used
+ * @key_ref: The key to check.
+ * @cred: The credentials to use.
+ * @need_perm: The permission required.
+ *
+ * Check to see whether permission is granted to use a key in the desired way,
+ * but permit the security modules to override.
+ *
+ * The caller must hold either a ref on cred or must hold the RCU readlock.
+ *
+ * Returns 0 if successful, -EACCES if access is denied based on the
+ * permissions bits or the LSM check.
+ */
+int key_task_permission(const key_ref_t key_ref, const struct cred *cred,
+			enum key_need_perm need_perm)
+{
+	struct key *key;
+	key_perm_t kperm, mask;
+	int ret;
+
+	switch (need_perm) {
+	default:
+		WARN_ON(1);
+		return -EACCES;
+	case KEY_NEED_UNLINK:
+	case KEY_SYSADMIN_OVERRIDE:
+	case KEY_AUTHTOKEN_OVERRIDE:
+	case KEY_DEFER_PERM_CHECK:
+		goto lsm;
+
+	case KEY_NEED_VIEW:	mask = KEY_OTH_VIEW;	break;
+	case KEY_NEED_READ:	mask = KEY_OTH_READ;	break;
+	case KEY_NEED_WRITE:	mask = KEY_OTH_WRITE;	break;
+	case KEY_NEED_SEARCH:	mask = KEY_OTH_SEARCH;	break;
+	case KEY_NEED_LINK:	mask = KEY_OTH_LINK;	break;
+	case KEY_NEED_SETATTR:	mask = KEY_OTH_SETATTR;	break;
+	}
+
+	key = key_ref_to_ptr(key_ref);
+
+	/* use the second 8-bits of permissions for keys the caller owns */
+	if (uid_eq(key->uid, cred->fsuid)) {
+		kperm = key->perm >> 16;
+		goto use_these_perms;
+	}
+
+	/* use the third 8-bits of permissions for keys the caller has a group
+	 * membership in common with */
+	if (gid_valid(key->gid) && key->perm & KEY_GRP_ALL) {
+		if (gid_eq(key->gid, cred->fsgid)) {
+			kperm = key->perm >> 8;
+			goto use_these_perms;
+		}
+
+		ret = groups_search(cred->group_info, key->gid);
+		if (ret) {
+			kperm = key->perm >> 8;
+			goto use_these_perms;
+		}
+	}
+
+	/* otherwise use the least-significant 8-bits */
+	kperm = key->perm;
+
+use_these_perms:
+
+	/* use the top 8-bits of permissions for keys the caller possesses
+	 * - possessor permissions are additive with other permissions
+	 */
+	if (is_key_possessed(key_ref))
+		kperm |= key->perm >> 24;
+
+	if ((kperm & mask) != mask)
+		return -EACCES;
+
+	/* let LSM be the final arbiter */
+lsm:
+	return security_key_permission(key_ref, cred, need_perm);
+}
+EXPORT_SYMBOL(key_task_permission);
+
+/**
+ * key_validate - Validate a key.
+ * @key: The key to be validated.
+ *
+ * Check that a key is valid, returning 0 if the key is okay, -ENOKEY if the
+ * key is invalidated, -EKEYREVOKED if the key's type has been removed or if
+ * the key has been revoked or -EKEYEXPIRED if the key has expired.
+ */
+int key_validate(const struct key *key)
+{
+	unsigned long flags = READ_ONCE(key->flags);
+	time64_t expiry = READ_ONCE(key->expiry);
+
+	if (flags & (1 << KEY_FLAG_INVALIDATED))
+		return -ENOKEY;
+
+	/* check it's still accessible */
+	if (flags & ((1 << KEY_FLAG_REVOKED) |
+		     (1 << KEY_FLAG_DEAD)))
+		return -EKEYREVOKED;
+
+	/* check it hasn't expired */
+	if (expiry) {
+		if (ktime_get_real_seconds() >= expiry)
+			return -EKEYEXPIRED;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(key_validate);
diff --git a/security/keys/persistent.c b/security/keys/persistent.c
new file mode 100644
index 000000000..97af230aa
--- /dev/null
+++ b/security/keys/persistent.c
@@ -0,0 +1,167 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* General persistent per-UID keyrings register
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/user_namespace.h>
+#include <linux/cred.h>
+
+#include "internal.h"
+
+unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
+
+/*
+ * Create the persistent keyring register for the current user namespace.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static int key_create_persistent_register(struct user_namespace *ns)
+{
+	struct key *reg = keyring_alloc(".persistent_register",
+					KUIDT_INIT(0), KGIDT_INIT(0),
+					current_cred(),
+					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					 KEY_USR_VIEW | KEY_USR_READ),
+					KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	ns->persistent_keyring_register = reg;
+	return 0;
+}
+
+/*
+ * Create the persistent keyring for the specified user.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid,
+				       struct keyring_index_key *index_key)
+{
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+
+	if (!ns->persistent_keyring_register) {
+		long err = key_create_persistent_register(ns);
+		if (err < 0)
+			return ERR_PTR(err);
+	} else {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		persistent_ref = find_key_to_update(reg_ref, index_key);
+		if (persistent_ref)
+			return persistent_ref;
+	}
+
+	persistent = keyring_alloc(index_key->description,
+				   uid, INVALID_GID, current_cred(),
+				   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				    KEY_USR_VIEW | KEY_USR_READ),
+				   KEY_ALLOC_NOT_IN_QUOTA, NULL,
+				   ns->persistent_keyring_register);
+	if (IS_ERR(persistent))
+		return ERR_CAST(persistent);
+
+	return make_key_ref(persistent, true);
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
+			       key_ref_t dest_ref)
+{
+	struct keyring_index_key index_key;
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+	char buf[32];
+	long ret;
+
+	/* Look in the register if it exists */
+	memset(&index_key, 0, sizeof(index_key));
+	index_key.type = &key_type_keyring;
+	index_key.description = buf;
+	index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid));
+	key_set_index_key(&index_key);
+
+	if (ns->persistent_keyring_register) {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		down_read(&ns->keyring_sem);
+		persistent_ref = find_key_to_update(reg_ref, &index_key);
+		up_read(&ns->keyring_sem);
+
+		if (persistent_ref)
+			goto found;
+	}
+
+	/* It wasn't in the register, so we'll need to create it.  We might
+	 * also need to create the register.
+	 */
+	down_write(&ns->keyring_sem);
+	persistent_ref = key_create_persistent(ns, uid, &index_key);
+	up_write(&ns->keyring_sem);
+	if (!IS_ERR(persistent_ref))
+		goto found;
+
+	return PTR_ERR(persistent_ref);
+
+found:
+	ret = key_task_permission(persistent_ref, current_cred(), KEY_NEED_LINK);
+	if (ret == 0) {
+		persistent = key_ref_to_ptr(persistent_ref);
+		ret = key_link(key_ref_to_ptr(dest_ref), persistent);
+		if (ret == 0) {
+			key_set_timeout(persistent, persistent_keyring_expiry);
+			ret = persistent->serial;
+		}
+	}
+
+	key_ref_put(persistent_ref);
+	return ret;
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
+{
+	struct user_namespace *ns = current_user_ns();
+	key_ref_t dest_ref;
+	kuid_t uid;
+	long ret;
+
+	/* -1 indicates the current user */
+	if (_uid == (uid_t)-1) {
+		uid = current_uid();
+	} else {
+		uid = make_kuid(ns, _uid);
+		if (!uid_valid(uid))
+			return -EINVAL;
+
+		/* You can only see your own persistent cache if you're not
+		 * sufficiently privileged.
+		 */
+		if (!uid_eq(uid, current_uid()) &&
+		    !uid_eq(uid, current_euid()) &&
+		    !ns_capable(ns, CAP_SETUID))
+			return -EPERM;
+	}
+
+	/* There must be a destination keyring */
+	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(dest_ref))
+		return PTR_ERR(dest_ref);
+	if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
+		ret = -ENOTDIR;
+		goto out_put_dest;
+	}
+
+	ret = key_get_persistent(ns, uid, dest_ref);
+
+out_put_dest:
+	key_ref_put(dest_ref);
+	return ret;
+}
diff --git a/security/keys/proc.c b/security/keys/proc.c
new file mode 100644
index 000000000..4f4e2c182
--- /dev/null
+++ b/security/keys/proc.c
@@ -0,0 +1,323 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* procfs files for key database enumeration
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <asm/errno.h>
+#include "internal.h"
+
+static void *proc_keys_start(struct seq_file *p, loff_t *_pos);
+static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos);
+static void proc_keys_stop(struct seq_file *p, void *v);
+static int proc_keys_show(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_keys_ops = {
+	.start	= proc_keys_start,
+	.next	= proc_keys_next,
+	.stop	= proc_keys_stop,
+	.show	= proc_keys_show,
+};
+
+static void *proc_key_users_start(struct seq_file *p, loff_t *_pos);
+static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos);
+static void proc_key_users_stop(struct seq_file *p, void *v);
+static int proc_key_users_show(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_key_users_ops = {
+	.start	= proc_key_users_start,
+	.next	= proc_key_users_next,
+	.stop	= proc_key_users_stop,
+	.show	= proc_key_users_show,
+};
+
+/*
+ * Declare the /proc files.
+ */
+static int __init key_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+	p = proc_create_seq("keys", 0, NULL, &proc_keys_ops);
+	if (!p)
+		panic("Cannot create /proc/keys\n");
+
+	p = proc_create_seq("key-users", 0, NULL, &proc_key_users_ops);
+	if (!p)
+		panic("Cannot create /proc/key-users\n");
+
+	return 0;
+}
+
+__initcall(key_proc_init);
+
+/*
+ * Implement "/proc/keys" to provide a list of the keys on the system that
+ * grant View permission to the caller.
+ */
+static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n)
+{
+	struct user_namespace *user_ns = seq_user_ns(p);
+
+	n = rb_next(n);
+	while (n) {
+		struct key *key = rb_entry(n, struct key, serial_node);
+		if (kuid_has_mapping(user_ns, key->user->uid))
+			break;
+		n = rb_next(n);
+	}
+	return n;
+}
+
+static struct key *find_ge_key(struct seq_file *p, key_serial_t id)
+{
+	struct user_namespace *user_ns = seq_user_ns(p);
+	struct rb_node *n = key_serial_tree.rb_node;
+	struct key *minkey = NULL;
+
+	while (n) {
+		struct key *key = rb_entry(n, struct key, serial_node);
+		if (id < key->serial) {
+			if (!minkey || minkey->serial > key->serial)
+				minkey = key;
+			n = n->rb_left;
+		} else if (id > key->serial) {
+			n = n->rb_right;
+		} else {
+			minkey = key;
+			break;
+		}
+		key = NULL;
+	}
+
+	if (!minkey)
+		return NULL;
+
+	for (;;) {
+		if (kuid_has_mapping(user_ns, minkey->user->uid))
+			return minkey;
+		n = rb_next(&minkey->serial_node);
+		if (!n)
+			return NULL;
+		minkey = rb_entry(n, struct key, serial_node);
+	}
+}
+
+static void *proc_keys_start(struct seq_file *p, loff_t *_pos)
+	__acquires(key_serial_lock)
+{
+	key_serial_t pos = *_pos;
+	struct key *key;
+
+	spin_lock(&key_serial_lock);
+
+	if (*_pos > INT_MAX)
+		return NULL;
+	key = find_ge_key(p, pos);
+	if (!key)
+		return NULL;
+	*_pos = key->serial;
+	return &key->serial_node;
+}
+
+static inline key_serial_t key_node_serial(struct rb_node *n)
+{
+	struct key *key = rb_entry(n, struct key, serial_node);
+	return key->serial;
+}
+
+static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos)
+{
+	struct rb_node *n;
+
+	n = key_serial_next(p, v);
+	if (n)
+		*_pos = key_node_serial(n);
+	else
+		(*_pos)++;
+	return n;
+}
+
+static void proc_keys_stop(struct seq_file *p, void *v)
+	__releases(key_serial_lock)
+{
+	spin_unlock(&key_serial_lock);
+}
+
+static int proc_keys_show(struct seq_file *m, void *v)
+{
+	struct rb_node *_p = v;
+	struct key *key = rb_entry(_p, struct key, serial_node);
+	unsigned long flags;
+	key_ref_t key_ref, skey_ref;
+	time64_t now, expiry;
+	char xbuf[16];
+	short state;
+	u64 timo;
+	int rc;
+
+	struct keyring_search_context ctx = {
+		.index_key		= key->index_key,
+		.cred			= m->file->f_cred,
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.raw_data	= key,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_RECURSE),
+	};
+
+	key_ref = make_key_ref(key, 0);
+
+	/* determine if the key is possessed by this process (a test we can
+	 * skip if the key does not indicate the possessor can view it
+	 */
+	if (key->perm & KEY_POS_VIEW) {
+		rcu_read_lock();
+		skey_ref = search_cred_keyrings_rcu(&ctx);
+		rcu_read_unlock();
+		if (!IS_ERR(skey_ref)) {
+			key_ref_put(skey_ref);
+			key_ref = make_key_ref(key, 1);
+		}
+	}
+
+	/* check whether the current task is allowed to view the key */
+	rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW);
+	if (rc < 0)
+		return 0;
+
+	now = ktime_get_real_seconds();
+
+	rcu_read_lock();
+
+	/* come up with a suitable timeout value */
+	expiry = READ_ONCE(key->expiry);
+	if (expiry == TIME64_MAX) {
+		memcpy(xbuf, "perm", 5);
+	} else if (now >= expiry) {
+		memcpy(xbuf, "expd", 5);
+	} else {
+		timo = expiry - now;
+
+		if (timo < 60)
+			sprintf(xbuf, "%llus", timo);
+		else if (timo < 60*60)
+			sprintf(xbuf, "%llum", div_u64(timo, 60));
+		else if (timo < 60*60*24)
+			sprintf(xbuf, "%lluh", div_u64(timo, 60 * 60));
+		else if (timo < 60*60*24*7)
+			sprintf(xbuf, "%llud", div_u64(timo, 60 * 60 * 24));
+		else
+			sprintf(xbuf, "%lluw", div_u64(timo, 60 * 60 * 24 * 7));
+	}
+
+	state = key_read_state(key);
+
+#define showflag(FLAGS, LETTER, FLAG) \
+	((FLAGS & (1 << FLAG)) ? LETTER : '-')
+
+	flags = READ_ONCE(key->flags);
+	seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ",
+		   key->serial,
+		   state != KEY_IS_UNINSTANTIATED ? 'I' : '-',
+		   showflag(flags, 'R', KEY_FLAG_REVOKED),
+		   showflag(flags, 'D', KEY_FLAG_DEAD),
+		   showflag(flags, 'Q', KEY_FLAG_IN_QUOTA),
+		   showflag(flags, 'U', KEY_FLAG_USER_CONSTRUCT),
+		   state < 0 ? 'N' : '-',
+		   showflag(flags, 'i', KEY_FLAG_INVALIDATED),
+		   refcount_read(&key->usage),
+		   xbuf,
+		   key->perm,
+		   from_kuid_munged(seq_user_ns(m), key->uid),
+		   from_kgid_munged(seq_user_ns(m), key->gid),
+		   key->type->name);
+
+#undef showflag
+
+	if (key->type->describe)
+		key->type->describe(key, m);
+	seq_putc(m, '\n');
+
+	rcu_read_unlock();
+	return 0;
+}
+
+static struct rb_node *__key_user_next(struct user_namespace *user_ns, struct rb_node *n)
+{
+	while (n) {
+		struct key_user *user = rb_entry(n, struct key_user, node);
+		if (kuid_has_mapping(user_ns, user->uid))
+			break;
+		n = rb_next(n);
+	}
+	return n;
+}
+
+static struct rb_node *key_user_next(struct user_namespace *user_ns, struct rb_node *n)
+{
+	return __key_user_next(user_ns, rb_next(n));
+}
+
+static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_root *r)
+{
+	struct rb_node *n = rb_first(r);
+	return __key_user_next(user_ns, n);
+}
+
+static void *proc_key_users_start(struct seq_file *p, loff_t *_pos)
+	__acquires(key_user_lock)
+{
+	struct rb_node *_p;
+	loff_t pos = *_pos;
+
+	spin_lock(&key_user_lock);
+
+	_p = key_user_first(seq_user_ns(p), &key_user_tree);
+	while (pos > 0 && _p) {
+		pos--;
+		_p = key_user_next(seq_user_ns(p), _p);
+	}
+
+	return _p;
+}
+
+static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos)
+{
+	(*_pos)++;
+	return key_user_next(seq_user_ns(p), (struct rb_node *)v);
+}
+
+static void proc_key_users_stop(struct seq_file *p, void *v)
+	__releases(key_user_lock)
+{
+	spin_unlock(&key_user_lock);
+}
+
+static int proc_key_users_show(struct seq_file *m, void *v)
+{
+	struct rb_node *_p = v;
+	struct key_user *user = rb_entry(_p, struct key_user, node);
+	unsigned maxkeys = uid_eq(user->uid, GLOBAL_ROOT_UID) ?
+		key_quota_root_maxkeys : key_quota_maxkeys;
+	unsigned maxbytes = uid_eq(user->uid, GLOBAL_ROOT_UID) ?
+		key_quota_root_maxbytes : key_quota_maxbytes;
+
+	seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n",
+		   from_kuid_munged(seq_user_ns(m), user->uid),
+		   refcount_read(&user->usage),
+		   atomic_read(&user->nkeys),
+		   atomic_read(&user->nikeys),
+		   user->qnkeys,
+		   maxkeys,
+		   user->qnbytes,
+		   maxbytes);
+
+	return 0;
+}
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
new file mode 100644
index 000000000..a63c46bb2
--- /dev/null
+++ b/security/keys/process_keys.c
@@ -0,0 +1,965 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Manage a process's keyrings
+ *
+ * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/sched/user.h>
+#include <linux/keyctl.h>
+#include <linux/fs.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/security.h>
+#include <linux/user_namespace.h>
+#include <linux/uaccess.h>
+#include <linux/init_task.h>
+#include <keys/request_key_auth-type.h>
+#include "internal.h"
+
+/* Session keyring create vs join semaphore */
+static DEFINE_MUTEX(key_session_mutex);
+
+/* The root user's tracking struct */
+struct key_user root_key_user = {
+	.usage		= REFCOUNT_INIT(3),
+	.cons_lock	= __MUTEX_INITIALIZER(root_key_user.cons_lock),
+	.lock		= __SPIN_LOCK_UNLOCKED(root_key_user.lock),
+	.nkeys		= ATOMIC_INIT(2),
+	.nikeys		= ATOMIC_INIT(2),
+	.uid		= GLOBAL_ROOT_UID,
+};
+
+/*
+ * Get or create a user register keyring.
+ */
+static struct key *get_user_register(struct user_namespace *user_ns)
+{
+	struct key *reg_keyring = READ_ONCE(user_ns->user_keyring_register);
+
+	if (reg_keyring)
+		return reg_keyring;
+
+	down_write(&user_ns->keyring_sem);
+
+	/* Make sure there's a register keyring.  It gets owned by the
+	 * user_namespace's owner.
+	 */
+	reg_keyring = user_ns->user_keyring_register;
+	if (!reg_keyring) {
+		reg_keyring = keyring_alloc(".user_reg",
+					    user_ns->owner, INVALID_GID,
+					    kernel_cred(),
+					    KEY_POS_WRITE | KEY_POS_SEARCH |
+					    KEY_USR_VIEW | KEY_USR_READ,
+					    0,
+					    NULL, NULL);
+		if (!IS_ERR(reg_keyring))
+			smp_store_release(&user_ns->user_keyring_register,
+					  reg_keyring);
+	}
+
+	up_write(&user_ns->keyring_sem);
+
+	/* We don't return a ref since the keyring is pinned by the user_ns */
+	return reg_keyring;
+}
+
+/*
+ * Look up the user and user session keyrings for the current process's UID,
+ * creating them if they don't exist.
+ */
+int look_up_user_keyrings(struct key **_user_keyring,
+			  struct key **_user_session_keyring)
+{
+	const struct cred *cred = current_cred();
+	struct user_namespace *user_ns = current_user_ns();
+	struct key *reg_keyring, *uid_keyring, *session_keyring;
+	key_perm_t user_keyring_perm;
+	key_ref_t uid_keyring_r, session_keyring_r;
+	uid_t uid = from_kuid(user_ns, cred->user->uid);
+	char buf[20];
+	int ret;
+
+	user_keyring_perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL;
+
+	kenter("%u", uid);
+
+	reg_keyring = get_user_register(user_ns);
+	if (IS_ERR(reg_keyring))
+		return PTR_ERR(reg_keyring);
+
+	down_write(&user_ns->keyring_sem);
+	ret = 0;
+
+	/* Get the user keyring.  Note that there may be one in existence
+	 * already as it may have been pinned by a session, but the user_struct
+	 * pointing to it may have been destroyed by setuid.
+	 */
+	snprintf(buf, sizeof(buf), "_uid.%u", uid);
+	uid_keyring_r = keyring_search(make_key_ref(reg_keyring, true),
+				       &key_type_keyring, buf, false);
+	kdebug("_uid %p", uid_keyring_r);
+	if (uid_keyring_r == ERR_PTR(-EAGAIN)) {
+		uid_keyring = keyring_alloc(buf, cred->user->uid, INVALID_GID,
+					    cred, user_keyring_perm,
+					    KEY_ALLOC_UID_KEYRING |
+					    KEY_ALLOC_IN_QUOTA,
+					    NULL, reg_keyring);
+		if (IS_ERR(uid_keyring)) {
+			ret = PTR_ERR(uid_keyring);
+			goto error;
+		}
+	} else if (IS_ERR(uid_keyring_r)) {
+		ret = PTR_ERR(uid_keyring_r);
+		goto error;
+	} else {
+		uid_keyring = key_ref_to_ptr(uid_keyring_r);
+	}
+
+	/* Get a default session keyring (which might also exist already) */
+	snprintf(buf, sizeof(buf), "_uid_ses.%u", uid);
+	session_keyring_r = keyring_search(make_key_ref(reg_keyring, true),
+					   &key_type_keyring, buf, false);
+	kdebug("_uid_ses %p", session_keyring_r);
+	if (session_keyring_r == ERR_PTR(-EAGAIN)) {
+		session_keyring = keyring_alloc(buf, cred->user->uid, INVALID_GID,
+						cred, user_keyring_perm,
+						KEY_ALLOC_UID_KEYRING |
+						KEY_ALLOC_IN_QUOTA,
+						NULL, NULL);
+		if (IS_ERR(session_keyring)) {
+			ret = PTR_ERR(session_keyring);
+			goto error_release;
+		}
+
+		/* We install a link from the user session keyring to
+		 * the user keyring.
+		 */
+		ret = key_link(session_keyring, uid_keyring);
+		if (ret < 0)
+			goto error_release_session;
+
+		/* And only then link the user-session keyring to the
+		 * register.
+		 */
+		ret = key_link(reg_keyring, session_keyring);
+		if (ret < 0)
+			goto error_release_session;
+	} else if (IS_ERR(session_keyring_r)) {
+		ret = PTR_ERR(session_keyring_r);
+		goto error_release;
+	} else {
+		session_keyring = key_ref_to_ptr(session_keyring_r);
+	}
+
+	up_write(&user_ns->keyring_sem);
+
+	if (_user_session_keyring)
+		*_user_session_keyring = session_keyring;
+	else
+		key_put(session_keyring);
+	if (_user_keyring)
+		*_user_keyring = uid_keyring;
+	else
+		key_put(uid_keyring);
+	kleave(" = 0");
+	return 0;
+
+error_release_session:
+	key_put(session_keyring);
+error_release:
+	key_put(uid_keyring);
+error:
+	up_write(&user_ns->keyring_sem);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Get the user session keyring if it exists, but don't create it if it
+ * doesn't.
+ */
+struct key *get_user_session_keyring_rcu(const struct cred *cred)
+{
+	struct key *reg_keyring = READ_ONCE(cred->user_ns->user_keyring_register);
+	key_ref_t session_keyring_r;
+	char buf[20];
+
+	struct keyring_search_context ctx = {
+		.index_key.type		= &key_type_keyring,
+		.index_key.description	= buf,
+		.cred			= cred,
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= buf,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
+	};
+
+	if (!reg_keyring)
+		return NULL;
+
+	ctx.index_key.desc_len = snprintf(buf, sizeof(buf), "_uid_ses.%u",
+					  from_kuid(cred->user_ns,
+						    cred->user->uid));
+
+	session_keyring_r = keyring_search_rcu(make_key_ref(reg_keyring, true),
+					       &ctx);
+	if (IS_ERR(session_keyring_r))
+		return NULL;
+	return key_ref_to_ptr(session_keyring_r);
+}
+
+/*
+ * Install a thread keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
+ */
+int install_thread_keyring_to_cred(struct cred *new)
+{
+	struct key *keyring;
+
+	if (new->thread_keyring)
+		return 0;
+
+	keyring = keyring_alloc("_tid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
+				KEY_ALLOC_QUOTA_OVERRUN,
+				NULL, NULL);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	new->thread_keyring = keyring;
+	return 0;
+}
+
+/*
+ * Install a thread keyring to the current task if it didn't have one already.
+ *
+ * Return: 0 if a thread keyring is now present; -errno on failure.
+ */
+static int install_thread_keyring(void)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = install_thread_keyring_to_cred(new);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Install a process keyring to the given credentials struct if it didn't have
+ * one already.  This is allowed to overrun the quota.
+ *
+ * Return: 0 if a process keyring is now present; -errno on failure.
+ */
+int install_process_keyring_to_cred(struct cred *new)
+{
+	struct key *keyring;
+
+	if (new->process_keyring)
+		return 0;
+
+	keyring = keyring_alloc("_pid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
+				KEY_ALLOC_QUOTA_OVERRUN,
+				NULL, NULL);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	new->process_keyring = keyring;
+	return 0;
+}
+
+/*
+ * Install a process keyring to the current task if it didn't have one already.
+ *
+ * Return: 0 if a process keyring is now present; -errno on failure.
+ */
+static int install_process_keyring(void)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = install_process_keyring_to_cred(new);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Install the given keyring as the session keyring of the given credentials
+ * struct, replacing the existing one if any.  If the given keyring is NULL,
+ * then install a new anonymous session keyring.
+ * @cred can not be in use by any task yet.
+ *
+ * Return: 0 on success; -errno on failure.
+ */
+int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
+{
+	unsigned long flags;
+	struct key *old;
+
+	might_sleep();
+
+	/* create an empty session keyring */
+	if (!keyring) {
+		flags = KEY_ALLOC_QUOTA_OVERRUN;
+		if (cred->session_keyring)
+			flags = KEY_ALLOC_IN_QUOTA;
+
+		keyring = keyring_alloc("_ses", cred->uid, cred->gid, cred,
+					KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
+					flags, NULL, NULL);
+		if (IS_ERR(keyring))
+			return PTR_ERR(keyring);
+	} else {
+		__key_get(keyring);
+	}
+
+	/* install the keyring */
+	old = cred->session_keyring;
+	cred->session_keyring = keyring;
+
+	if (old)
+		key_put(old);
+
+	return 0;
+}
+
+/*
+ * Install the given keyring as the session keyring of the current task,
+ * replacing the existing one if any.  If the given keyring is NULL, then
+ * install a new anonymous session keyring.
+ *
+ * Return: 0 on success; -errno on failure.
+ */
+static int install_session_keyring(struct key *keyring)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = install_session_keyring_to_cred(new, keyring);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Handle the fsuid changing.
+ */
+void key_fsuid_changed(struct cred *new_cred)
+{
+	/* update the ownership of the thread keyring */
+	if (new_cred->thread_keyring) {
+		down_write(&new_cred->thread_keyring->sem);
+		new_cred->thread_keyring->uid = new_cred->fsuid;
+		up_write(&new_cred->thread_keyring->sem);
+	}
+}
+
+/*
+ * Handle the fsgid changing.
+ */
+void key_fsgid_changed(struct cred *new_cred)
+{
+	/* update the ownership of the thread keyring */
+	if (new_cred->thread_keyring) {
+		down_write(&new_cred->thread_keyring->sem);
+		new_cred->thread_keyring->gid = new_cred->fsgid;
+		up_write(&new_cred->thread_keyring->sem);
+	}
+}
+
+/*
+ * Search the process keyrings attached to the supplied cred for the first
+ * matching key under RCU conditions (the caller must be holding the RCU read
+ * lock).
+ *
+ * The search criteria are the type and the match function.  The description is
+ * given to the match function as a parameter, but doesn't otherwise influence
+ * the search.  Typically the match function will compare the description
+ * parameter to the key's description.
+ *
+ * This can only search keyrings that grant Search permission to the supplied
+ * credentials.  Keyrings linked to searched keyrings will also be searched if
+ * they grant Search permission too.  Keys can only be found if they grant
+ * Search permission to the credentials.
+ *
+ * Returns a pointer to the key with the key usage count incremented if
+ * successful, -EAGAIN if we didn't find any matching key or -ENOKEY if we only
+ * matched negative keys.
+ *
+ * In the case of a successful return, the possession attribute is set on the
+ * returned key reference.
+ */
+key_ref_t search_cred_keyrings_rcu(struct keyring_search_context *ctx)
+{
+	struct key *user_session;
+	key_ref_t key_ref, ret, err;
+	const struct cred *cred = ctx->cred;
+
+	/* we want to return -EAGAIN or -ENOKEY if any of the keyrings were
+	 * searchable, but we failed to find a key or we found a negative key;
+	 * otherwise we want to return a sample error (probably -EACCES) if
+	 * none of the keyrings were searchable
+	 *
+	 * in terms of priority: success > -ENOKEY > -EAGAIN > other error
+	 */
+	key_ref = NULL;
+	ret = NULL;
+	err = ERR_PTR(-EAGAIN);
+
+	/* search the thread keyring first */
+	if (cred->thread_keyring) {
+		key_ref = keyring_search_rcu(
+			make_key_ref(cred->thread_keyring, 1), ctx);
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* search the process keyring second */
+	if (cred->process_keyring) {
+		key_ref = keyring_search_rcu(
+			make_key_ref(cred->process_keyring, 1), ctx);
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+			fallthrough;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* search the session keyring */
+	if (cred->session_keyring) {
+		key_ref = keyring_search_rcu(
+			make_key_ref(cred->session_keyring, 1), ctx);
+
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+			fallthrough;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+	/* or search the user-session keyring */
+	else if ((user_session = get_user_session_keyring_rcu(cred))) {
+		key_ref = keyring_search_rcu(make_key_ref(user_session, 1),
+					     ctx);
+		key_put(user_session);
+
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+			fallthrough;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* no key - decide on the error we're going to go for */
+	key_ref = ret ? ret : err;
+
+found:
+	return key_ref;
+}
+
+/*
+ * Search the process keyrings attached to the supplied cred for the first
+ * matching key in the manner of search_my_process_keyrings(), but also search
+ * the keys attached to the assumed authorisation key using its credentials if
+ * one is available.
+ *
+ * The caller must be holding the RCU read lock.
+ *
+ * Return same as search_cred_keyrings_rcu().
+ */
+key_ref_t search_process_keyrings_rcu(struct keyring_search_context *ctx)
+{
+	struct request_key_auth *rka;
+	key_ref_t key_ref, ret = ERR_PTR(-EACCES), err;
+
+	key_ref = search_cred_keyrings_rcu(ctx);
+	if (!IS_ERR(key_ref))
+		goto found;
+	err = key_ref;
+
+	/* if this process has an instantiation authorisation key, then we also
+	 * search the keyrings of the process mentioned there
+	 * - we don't permit access to request_key auth keys via this method
+	 */
+	if (ctx->cred->request_key_auth &&
+	    ctx->cred == current_cred() &&
+	    ctx->index_key.type != &key_type_request_key_auth
+	    ) {
+		const struct cred *cred = ctx->cred;
+
+		if (key_validate(cred->request_key_auth) == 0) {
+			rka = ctx->cred->request_key_auth->payload.data[0];
+
+			//// was search_process_keyrings() [ie. recursive]
+			ctx->cred = rka->cred;
+			key_ref = search_cred_keyrings_rcu(ctx);
+			ctx->cred = cred;
+
+			if (!IS_ERR(key_ref))
+				goto found;
+			ret = key_ref;
+		}
+	}
+
+	/* no key - decide on the error we're going to go for */
+	if (err == ERR_PTR(-ENOKEY) || ret == ERR_PTR(-ENOKEY))
+		key_ref = ERR_PTR(-ENOKEY);
+	else if (err == ERR_PTR(-EACCES))
+		key_ref = ret;
+	else
+		key_ref = err;
+
+found:
+	return key_ref;
+}
+/*
+ * See if the key we're looking at is the target key.
+ */
+bool lookup_user_key_possessed(const struct key *key,
+			       const struct key_match_data *match_data)
+{
+	return key == match_data->raw_data;
+}
+
+/*
+ * Look up a key ID given us by userspace with a given permissions mask to get
+ * the key it refers to.
+ *
+ * Flags can be passed to request that special keyrings be created if referred
+ * to directly, to permit partially constructed keys to be found and to skip
+ * validity and permission checks on the found key.
+ *
+ * Returns a pointer to the key with an incremented usage count if successful;
+ * -EINVAL if the key ID is invalid; -ENOKEY if the key ID does not correspond
+ * to a key or the best found key was a negative key; -EKEYREVOKED or
+ * -EKEYEXPIRED if the best found key was revoked or expired; -EACCES if the
+ * found key doesn't grant the requested permit or the LSM denied access to it;
+ * or -ENOMEM if a special keyring couldn't be created.
+ *
+ * In the case of a successful return, the possession attribute is set on the
+ * returned key reference.
+ */
+key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
+			  enum key_need_perm need_perm)
+{
+	struct keyring_search_context ctx = {
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_NO_STATE_CHECK |
+					   KEYRING_SEARCH_RECURSE),
+	};
+	struct request_key_auth *rka;
+	struct key *key, *user_session;
+	key_ref_t key_ref, skey_ref;
+	int ret;
+
+try_again:
+	ctx.cred = get_current_cred();
+	key_ref = ERR_PTR(-ENOKEY);
+
+	switch (id) {
+	case KEY_SPEC_THREAD_KEYRING:
+		if (!ctx.cred->thread_keyring) {
+			if (!(lflags & KEY_LOOKUP_CREATE))
+				goto error;
+
+			ret = install_thread_keyring();
+			if (ret < 0) {
+				key_ref = ERR_PTR(ret);
+				goto error;
+			}
+			goto reget_creds;
+		}
+
+		key = ctx.cred->thread_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_PROCESS_KEYRING:
+		if (!ctx.cred->process_keyring) {
+			if (!(lflags & KEY_LOOKUP_CREATE))
+				goto error;
+
+			ret = install_process_keyring();
+			if (ret < 0) {
+				key_ref = ERR_PTR(ret);
+				goto error;
+			}
+			goto reget_creds;
+		}
+
+		key = ctx.cred->process_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_SESSION_KEYRING:
+		if (!ctx.cred->session_keyring) {
+			/* always install a session keyring upon access if one
+			 * doesn't exist yet */
+			ret = look_up_user_keyrings(NULL, &user_session);
+			if (ret < 0)
+				goto error;
+			if (lflags & KEY_LOOKUP_CREATE)
+				ret = join_session_keyring(NULL);
+			else
+				ret = install_session_keyring(user_session);
+
+			key_put(user_session);
+			if (ret < 0)
+				goto error;
+			goto reget_creds;
+		} else if (test_bit(KEY_FLAG_UID_KEYRING,
+				    &ctx.cred->session_keyring->flags) &&
+			   lflags & KEY_LOOKUP_CREATE) {
+			ret = join_session_keyring(NULL);
+			if (ret < 0)
+				goto error;
+			goto reget_creds;
+		}
+
+		key = ctx.cred->session_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_USER_KEYRING:
+		ret = look_up_user_keyrings(&key, NULL);
+		if (ret < 0)
+			goto error;
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_USER_SESSION_KEYRING:
+		ret = look_up_user_keyrings(NULL, &key);
+		if (ret < 0)
+			goto error;
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_GROUP_KEYRING:
+		/* group keyrings are not yet supported */
+		key_ref = ERR_PTR(-EINVAL);
+		goto error;
+
+	case KEY_SPEC_REQKEY_AUTH_KEY:
+		key = ctx.cred->request_key_auth;
+		if (!key)
+			goto error;
+
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_REQUESTOR_KEYRING:
+		if (!ctx.cred->request_key_auth)
+			goto error;
+
+		down_read(&ctx.cred->request_key_auth->sem);
+		if (test_bit(KEY_FLAG_REVOKED,
+			     &ctx.cred->request_key_auth->flags)) {
+			key_ref = ERR_PTR(-EKEYREVOKED);
+			key = NULL;
+		} else {
+			rka = ctx.cred->request_key_auth->payload.data[0];
+			key = rka->dest_keyring;
+			__key_get(key);
+		}
+		up_read(&ctx.cred->request_key_auth->sem);
+		if (!key)
+			goto error;
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	default:
+		key_ref = ERR_PTR(-EINVAL);
+		if (id < 1)
+			goto error;
+
+		key = key_lookup(id);
+		if (IS_ERR(key)) {
+			key_ref = ERR_CAST(key);
+			goto error;
+		}
+
+		key_ref = make_key_ref(key, 0);
+
+		/* check to see if we possess the key */
+		ctx.index_key			= key->index_key;
+		ctx.match_data.raw_data		= key;
+		kdebug("check possessed");
+		rcu_read_lock();
+		skey_ref = search_process_keyrings_rcu(&ctx);
+		rcu_read_unlock();
+		kdebug("possessed=%p", skey_ref);
+
+		if (!IS_ERR(skey_ref)) {
+			key_put(key);
+			key_ref = skey_ref;
+		}
+
+		break;
+	}
+
+	/* unlink does not use the nominated key in any way, so can skip all
+	 * the permission checks as it is only concerned with the keyring */
+	if (need_perm != KEY_NEED_UNLINK) {
+		if (!(lflags & KEY_LOOKUP_PARTIAL)) {
+			ret = wait_for_key_construction(key, true);
+			switch (ret) {
+			case -ERESTARTSYS:
+				goto invalid_key;
+			default:
+				if (need_perm != KEY_AUTHTOKEN_OVERRIDE &&
+				    need_perm != KEY_DEFER_PERM_CHECK)
+					goto invalid_key;
+				break;
+			case 0:
+				break;
+			}
+		} else if (need_perm != KEY_DEFER_PERM_CHECK) {
+			ret = key_validate(key);
+			if (ret < 0)
+				goto invalid_key;
+		}
+
+		ret = -EIO;
+		if (!(lflags & KEY_LOOKUP_PARTIAL) &&
+		    key_read_state(key) == KEY_IS_UNINSTANTIATED)
+			goto invalid_key;
+	}
+
+	/* check the permissions */
+	ret = key_task_permission(key_ref, ctx.cred, need_perm);
+	if (ret < 0)
+		goto invalid_key;
+
+	key->last_used_at = ktime_get_real_seconds();
+
+error:
+	put_cred(ctx.cred);
+	return key_ref;
+
+invalid_key:
+	key_ref_put(key_ref);
+	key_ref = ERR_PTR(ret);
+	goto error;
+
+	/* if we attempted to install a keyring, then it may have caused new
+	 * creds to be installed */
+reget_creds:
+	put_cred(ctx.cred);
+	goto try_again;
+}
+EXPORT_SYMBOL(lookup_user_key);
+
+/*
+ * Join the named keyring as the session keyring if possible else attempt to
+ * create a new one of that name and join that.
+ *
+ * If the name is NULL, an empty anonymous keyring will be installed as the
+ * session keyring.
+ *
+ * Named session keyrings are joined with a semaphore held to prevent the
+ * keyrings from going away whilst the attempt is made to going them and also
+ * to prevent a race in creating compatible session keyrings.
+ */
+long join_session_keyring(const char *name)
+{
+	const struct cred *old;
+	struct cred *new;
+	struct key *keyring;
+	long ret, serial;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	old = current_cred();
+
+	/* if no name is provided, install an anonymous keyring */
+	if (!name) {
+		ret = install_session_keyring_to_cred(new, NULL);
+		if (ret < 0)
+			goto error;
+
+		serial = new->session_keyring->serial;
+		ret = commit_creds(new);
+		if (ret == 0)
+			ret = serial;
+		goto okay;
+	}
+
+	/* allow the user to join or create a named keyring */
+	mutex_lock(&key_session_mutex);
+
+	/* look for an existing keyring of this name */
+	keyring = find_keyring_by_name(name, false);
+	if (PTR_ERR(keyring) == -ENOKEY) {
+		/* not found - try and create a new one */
+		keyring = keyring_alloc(
+			name, old->uid, old->gid, old,
+			KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_LINK,
+			KEY_ALLOC_IN_QUOTA, NULL, NULL);
+		if (IS_ERR(keyring)) {
+			ret = PTR_ERR(keyring);
+			goto error2;
+		}
+	} else if (IS_ERR(keyring)) {
+		ret = PTR_ERR(keyring);
+		goto error2;
+	} else if (keyring == new->session_keyring) {
+		ret = 0;
+		goto error3;
+	}
+
+	/* we've got a keyring - now to install it */
+	ret = install_session_keyring_to_cred(new, keyring);
+	if (ret < 0)
+		goto error3;
+
+	commit_creds(new);
+	mutex_unlock(&key_session_mutex);
+
+	ret = keyring->serial;
+	key_put(keyring);
+okay:
+	return ret;
+
+error3:
+	key_put(keyring);
+error2:
+	mutex_unlock(&key_session_mutex);
+error:
+	abort_creds(new);
+	return ret;
+}
+
+/*
+ * Replace a process's session keyring on behalf of one of its children when
+ * the target  process is about to resume userspace execution.
+ */
+void key_change_session_keyring(struct callback_head *twork)
+{
+	const struct cred *old = current_cred();
+	struct cred *new = container_of(twork, struct cred, rcu);
+
+	if (unlikely(current->flags & PF_EXITING)) {
+		put_cred(new);
+		return;
+	}
+
+	/* If get_ucounts fails more bits are needed in the refcount */
+	if (unlikely(!get_ucounts(old->ucounts))) {
+		WARN_ONCE(1, "In %s get_ucounts failed\n", __func__);
+		put_cred(new);
+		return;
+	}
+
+	new->  uid	= old->  uid;
+	new-> euid	= old-> euid;
+	new-> suid	= old-> suid;
+	new->fsuid	= old->fsuid;
+	new->  gid	= old->  gid;
+	new-> egid	= old-> egid;
+	new-> sgid	= old-> sgid;
+	new->fsgid	= old->fsgid;
+	new->user	= get_uid(old->user);
+	new->ucounts	= old->ucounts;
+	new->user_ns	= get_user_ns(old->user_ns);
+	new->group_info	= get_group_info(old->group_info);
+
+	new->securebits	= old->securebits;
+	new->cap_inheritable	= old->cap_inheritable;
+	new->cap_permitted	= old->cap_permitted;
+	new->cap_effective	= old->cap_effective;
+	new->cap_ambient	= old->cap_ambient;
+	new->cap_bset		= old->cap_bset;
+
+	new->jit_keyring	= old->jit_keyring;
+	new->thread_keyring	= key_get(old->thread_keyring);
+	new->process_keyring	= key_get(old->process_keyring);
+
+	security_transfer_creds(new, old);
+
+	commit_creds(new);
+}
+
+/*
+ * Make sure that root's user and user-session keyrings exist.
+ */
+static int __init init_root_keyring(void)
+{
+	return look_up_user_keyrings(NULL, NULL);
+}
+
+late_initcall(init_root_keyring);
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
new file mode 100644
index 000000000..fa2bb9f2f
--- /dev/null
+++ b/security/keys/request_key.c
@@ -0,0 +1,821 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Request a key from userspace
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/security/keys/request-key.rst
+ */
+
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/kmod.h>
+#include <linux/err.h>
+#include <linux/keyctl.h>
+#include <linux/slab.h>
+#include <net/net_namespace.h>
+#include "internal.h"
+#include <keys/request_key_auth-type.h>
+
+#define key_negative_timeout	60	/* default timeout on a negative key's existence */
+
+static struct key *check_cached_key(struct keyring_search_context *ctx)
+{
+#ifdef CONFIG_KEYS_REQUEST_CACHE
+	struct key *key = current->cached_requested_key;
+
+	if (key &&
+	    ctx->match_data.cmp(key, &ctx->match_data) &&
+	    !(key->flags & ((1 << KEY_FLAG_INVALIDATED) |
+			    (1 << KEY_FLAG_REVOKED))))
+		return key_get(key);
+#endif
+	return NULL;
+}
+
+static void cache_requested_key(struct key *key)
+{
+#ifdef CONFIG_KEYS_REQUEST_CACHE
+	struct task_struct *t = current;
+
+	/* Do not cache key if it is a kernel thread */
+	if (!(t->flags & PF_KTHREAD)) {
+		key_put(t->cached_requested_key);
+		t->cached_requested_key = key_get(key);
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+	}
+#endif
+}
+
+/**
+ * complete_request_key - Complete the construction of a key.
+ * @authkey: The authorisation key.
+ * @error: The success or failute of the construction.
+ *
+ * Complete the attempt to construct a key.  The key will be negated
+ * if an error is indicated.  The authorisation key will be revoked
+ * unconditionally.
+ */
+void complete_request_key(struct key *authkey, int error)
+{
+	struct request_key_auth *rka = get_request_key_auth(authkey);
+	struct key *key = rka->target_key;
+
+	kenter("%d{%d},%d", authkey->serial, key->serial, error);
+
+	if (error < 0)
+		key_negate_and_link(key, key_negative_timeout, NULL, authkey);
+	else
+		key_revoke(authkey);
+}
+EXPORT_SYMBOL(complete_request_key);
+
+/*
+ * Initialise a usermode helper that is going to have a specific session
+ * keyring.
+ *
+ * This is called in context of freshly forked kthread before kernel_execve(),
+ * so we can simply install the desired session_keyring at this point.
+ */
+static int umh_keys_init(struct subprocess_info *info, struct cred *cred)
+{
+	struct key *keyring = info->data;
+
+	return install_session_keyring_to_cred(cred, keyring);
+}
+
+/*
+ * Clean up a usermode helper with session keyring.
+ */
+static void umh_keys_cleanup(struct subprocess_info *info)
+{
+	struct key *keyring = info->data;
+	key_put(keyring);
+}
+
+/*
+ * Call a usermode helper with a specific session keyring.
+ */
+static int call_usermodehelper_keys(const char *path, char **argv, char **envp,
+					struct key *session_keyring, int wait)
+{
+	struct subprocess_info *info;
+
+	info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL,
+					  umh_keys_init, umh_keys_cleanup,
+					  session_keyring);
+	if (!info)
+		return -ENOMEM;
+
+	key_get(session_keyring);
+	return call_usermodehelper_exec(info, wait);
+}
+
+/*
+ * Request userspace finish the construction of a key
+ * - execute "/sbin/request-key <op> <key> <uid> <gid> <keyring> <keyring> <keyring>"
+ */
+static int call_sbin_request_key(struct key *authkey, void *aux)
+{
+	static char const request_key[] = "/sbin/request-key";
+	struct request_key_auth *rka = get_request_key_auth(authkey);
+	const struct cred *cred = current_cred();
+	key_serial_t prkey, sskey;
+	struct key *key = rka->target_key, *keyring, *session, *user_session;
+	char *argv[9], *envp[3], uid_str[12], gid_str[12];
+	char key_str[12], keyring_str[3][12];
+	char desc[20];
+	int ret, i;
+
+	kenter("{%d},{%d},%s", key->serial, authkey->serial, rka->op);
+
+	ret = look_up_user_keyrings(NULL, &user_session);
+	if (ret < 0)
+		goto error_us;
+
+	/* allocate a new session keyring */
+	sprintf(desc, "_req.%u", key->serial);
+
+	cred = get_current_cred();
+	keyring = keyring_alloc(desc, cred->fsuid, cred->fsgid, cred,
+				KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
+				KEY_ALLOC_QUOTA_OVERRUN, NULL, NULL);
+	put_cred(cred);
+	if (IS_ERR(keyring)) {
+		ret = PTR_ERR(keyring);
+		goto error_alloc;
+	}
+
+	/* attach the auth key to the session keyring */
+	ret = key_link(keyring, authkey);
+	if (ret < 0)
+		goto error_link;
+
+	/* record the UID and GID */
+	sprintf(uid_str, "%d", from_kuid(&init_user_ns, cred->fsuid));
+	sprintf(gid_str, "%d", from_kgid(&init_user_ns, cred->fsgid));
+
+	/* we say which key is under construction */
+	sprintf(key_str, "%d", key->serial);
+
+	/* we specify the process's default keyrings */
+	sprintf(keyring_str[0], "%d",
+		cred->thread_keyring ? cred->thread_keyring->serial : 0);
+
+	prkey = 0;
+	if (cred->process_keyring)
+		prkey = cred->process_keyring->serial;
+	sprintf(keyring_str[1], "%d", prkey);
+
+	session = cred->session_keyring;
+	if (!session)
+		session = user_session;
+	sskey = session->serial;
+
+	sprintf(keyring_str[2], "%d", sskey);
+
+	/* set up a minimal environment */
+	i = 0;
+	envp[i++] = "HOME=/";
+	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[i] = NULL;
+
+	/* set up the argument list */
+	i = 0;
+	argv[i++] = (char *)request_key;
+	argv[i++] = (char *)rka->op;
+	argv[i++] = key_str;
+	argv[i++] = uid_str;
+	argv[i++] = gid_str;
+	argv[i++] = keyring_str[0];
+	argv[i++] = keyring_str[1];
+	argv[i++] = keyring_str[2];
+	argv[i] = NULL;
+
+	/* do it */
+	ret = call_usermodehelper_keys(request_key, argv, envp, keyring,
+				       UMH_WAIT_PROC);
+	kdebug("usermode -> 0x%x", ret);
+	if (ret >= 0) {
+		/* ret is the exit/wait code */
+		if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags) ||
+		    key_validate(key) < 0)
+			ret = -ENOKEY;
+		else
+			/* ignore any errors from userspace if the key was
+			 * instantiated */
+			ret = 0;
+	}
+
+error_link:
+	key_put(keyring);
+
+error_alloc:
+	key_put(user_session);
+error_us:
+	complete_request_key(authkey, ret);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Call out to userspace for key construction.
+ *
+ * Program failure is ignored in favour of key status.
+ */
+static int construct_key(struct key *key, const void *callout_info,
+			 size_t callout_len, void *aux,
+			 struct key *dest_keyring)
+{
+	request_key_actor_t actor;
+	struct key *authkey;
+	int ret;
+
+	kenter("%d,%p,%zu,%p", key->serial, callout_info, callout_len, aux);
+
+	/* allocate an authorisation key */
+	authkey = request_key_auth_new(key, "create", callout_info, callout_len,
+				       dest_keyring);
+	if (IS_ERR(authkey))
+		return PTR_ERR(authkey);
+
+	/* Make the call */
+	actor = call_sbin_request_key;
+	if (key->type->request_key)
+		actor = key->type->request_key;
+
+	ret = actor(authkey, aux);
+
+	/* check that the actor called complete_request_key() prior to
+	 * returning an error */
+	WARN_ON(ret < 0 &&
+		!test_bit(KEY_FLAG_INVALIDATED, &authkey->flags));
+
+	key_put(authkey);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Get the appropriate destination keyring for the request.
+ *
+ * The keyring selected is returned with an extra reference upon it which the
+ * caller must release.
+ */
+static int construct_get_dest_keyring(struct key **_dest_keyring)
+{
+	struct request_key_auth *rka;
+	const struct cred *cred = current_cred();
+	struct key *dest_keyring = *_dest_keyring, *authkey;
+	int ret;
+
+	kenter("%p", dest_keyring);
+
+	/* find the appropriate keyring */
+	if (dest_keyring) {
+		/* the caller supplied one */
+		key_get(dest_keyring);
+	} else {
+		bool do_perm_check = true;
+
+		/* use a default keyring; falling through the cases until we
+		 * find one that we actually have */
+		switch (cred->jit_keyring) {
+		case KEY_REQKEY_DEFL_DEFAULT:
+		case KEY_REQKEY_DEFL_REQUESTOR_KEYRING:
+			if (cred->request_key_auth) {
+				authkey = cred->request_key_auth;
+				down_read(&authkey->sem);
+				rka = get_request_key_auth(authkey);
+				if (!test_bit(KEY_FLAG_REVOKED,
+					      &authkey->flags))
+					dest_keyring =
+						key_get(rka->dest_keyring);
+				up_read(&authkey->sem);
+				if (dest_keyring) {
+					do_perm_check = false;
+					break;
+				}
+			}
+
+			fallthrough;
+		case KEY_REQKEY_DEFL_THREAD_KEYRING:
+			dest_keyring = key_get(cred->thread_keyring);
+			if (dest_keyring)
+				break;
+
+			fallthrough;
+		case KEY_REQKEY_DEFL_PROCESS_KEYRING:
+			dest_keyring = key_get(cred->process_keyring);
+			if (dest_keyring)
+				break;
+
+			fallthrough;
+		case KEY_REQKEY_DEFL_SESSION_KEYRING:
+			dest_keyring = key_get(cred->session_keyring);
+
+			if (dest_keyring)
+				break;
+
+			fallthrough;
+		case KEY_REQKEY_DEFL_USER_SESSION_KEYRING:
+			ret = look_up_user_keyrings(NULL, &dest_keyring);
+			if (ret < 0)
+				return ret;
+			break;
+
+		case KEY_REQKEY_DEFL_USER_KEYRING:
+			ret = look_up_user_keyrings(&dest_keyring, NULL);
+			if (ret < 0)
+				return ret;
+			break;
+
+		case KEY_REQKEY_DEFL_GROUP_KEYRING:
+		default:
+			return -EINVAL;
+		}
+
+		/*
+		 * Require Write permission on the keyring.  This is essential
+		 * because the default keyring may be the session keyring, and
+		 * joining a keyring only requires Search permission.
+		 *
+		 * However, this check is skipped for the "requestor keyring" so
+		 * that /sbin/request-key can itself use request_key() to add
+		 * keys to the original requestor's destination keyring.
+		 */
+		if (dest_keyring && do_perm_check) {
+			ret = key_permission(make_key_ref(dest_keyring, 1),
+					     KEY_NEED_WRITE);
+			if (ret) {
+				key_put(dest_keyring);
+				return ret;
+			}
+		}
+	}
+
+	*_dest_keyring = dest_keyring;
+	kleave(" [dk %d]", key_serial(dest_keyring));
+	return 0;
+}
+
+/*
+ * Allocate a new key in under-construction state and attempt to link it in to
+ * the requested keyring.
+ *
+ * May return a key that's already under construction instead if there was a
+ * race between two thread calling request_key().
+ */
+static int construct_alloc_key(struct keyring_search_context *ctx,
+			       struct key *dest_keyring,
+			       unsigned long flags,
+			       struct key_user *user,
+			       struct key **_key)
+{
+	struct assoc_array_edit *edit = NULL;
+	struct key *key;
+	key_perm_t perm;
+	key_ref_t key_ref;
+	int ret;
+
+	kenter("%s,%s,,,",
+	       ctx->index_key.type->name, ctx->index_key.description);
+
+	*_key = NULL;
+	mutex_lock(&user->cons_lock);
+
+	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
+	perm |= KEY_USR_VIEW;
+	if (ctx->index_key.type->read)
+		perm |= KEY_POS_READ;
+	if (ctx->index_key.type == &key_type_keyring ||
+	    ctx->index_key.type->update)
+		perm |= KEY_POS_WRITE;
+
+	key = key_alloc(ctx->index_key.type, ctx->index_key.description,
+			ctx->cred->fsuid, ctx->cred->fsgid, ctx->cred,
+			perm, flags, NULL);
+	if (IS_ERR(key))
+		goto alloc_failed;
+
+	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
+
+	if (dest_keyring) {
+		ret = __key_link_lock(dest_keyring, &key->index_key);
+		if (ret < 0)
+			goto link_lock_failed;
+	}
+
+	/*
+	 * Attach the key to the destination keyring under lock, but we do need
+	 * to do another check just in case someone beat us to it whilst we
+	 * waited for locks.
+	 *
+	 * The caller might specify a comparison function which looks for keys
+	 * that do not exactly match but are still equivalent from the caller's
+	 * perspective. The __key_link_begin() operation must be done only after
+	 * an actual key is determined.
+	 */
+	mutex_lock(&key_construction_mutex);
+
+	rcu_read_lock();
+	key_ref = search_process_keyrings_rcu(ctx);
+	rcu_read_unlock();
+	if (!IS_ERR(key_ref))
+		goto key_already_present;
+
+	if (dest_keyring) {
+		ret = __key_link_begin(dest_keyring, &key->index_key, &edit);
+		if (ret < 0)
+			goto link_alloc_failed;
+		__key_link(dest_keyring, key, &edit);
+	}
+
+	mutex_unlock(&key_construction_mutex);
+	if (dest_keyring)
+		__key_link_end(dest_keyring, &key->index_key, edit);
+	mutex_unlock(&user->cons_lock);
+	*_key = key;
+	kleave(" = 0 [%d]", key_serial(key));
+	return 0;
+
+	/* the key is now present - we tell the caller that we found it by
+	 * returning -EINPROGRESS  */
+key_already_present:
+	key_put(key);
+	mutex_unlock(&key_construction_mutex);
+	key = key_ref_to_ptr(key_ref);
+	if (dest_keyring) {
+		ret = __key_link_begin(dest_keyring, &key->index_key, &edit);
+		if (ret < 0)
+			goto link_alloc_failed_unlocked;
+		ret = __key_link_check_live_key(dest_keyring, key);
+		if (ret == 0)
+			__key_link(dest_keyring, key, &edit);
+		__key_link_end(dest_keyring, &key->index_key, edit);
+		if (ret < 0)
+			goto link_check_failed;
+	}
+	mutex_unlock(&user->cons_lock);
+	*_key = key;
+	kleave(" = -EINPROGRESS [%d]", key_serial(key));
+	return -EINPROGRESS;
+
+link_check_failed:
+	mutex_unlock(&user->cons_lock);
+	key_put(key);
+	kleave(" = %d [linkcheck]", ret);
+	return ret;
+
+link_alloc_failed:
+	mutex_unlock(&key_construction_mutex);
+link_alloc_failed_unlocked:
+	__key_link_end(dest_keyring, &key->index_key, edit);
+link_lock_failed:
+	mutex_unlock(&user->cons_lock);
+	key_put(key);
+	kleave(" = %d [prelink]", ret);
+	return ret;
+
+alloc_failed:
+	mutex_unlock(&user->cons_lock);
+	kleave(" = %ld", PTR_ERR(key));
+	return PTR_ERR(key);
+}
+
+/*
+ * Commence key construction.
+ */
+static struct key *construct_key_and_link(struct keyring_search_context *ctx,
+					  const char *callout_info,
+					  size_t callout_len,
+					  void *aux,
+					  struct key *dest_keyring,
+					  unsigned long flags)
+{
+	struct key_user *user;
+	struct key *key;
+	int ret;
+
+	kenter("");
+
+	if (ctx->index_key.type == &key_type_keyring)
+		return ERR_PTR(-EPERM);
+
+	ret = construct_get_dest_keyring(&dest_keyring);
+	if (ret)
+		goto error;
+
+	user = key_user_lookup(current_fsuid());
+	if (!user) {
+		ret = -ENOMEM;
+		goto error_put_dest_keyring;
+	}
+
+	ret = construct_alloc_key(ctx, dest_keyring, flags, user, &key);
+	key_user_put(user);
+
+	if (ret == 0) {
+		ret = construct_key(key, callout_info, callout_len, aux,
+				    dest_keyring);
+		if (ret < 0) {
+			kdebug("cons failed");
+			goto construction_failed;
+		}
+	} else if (ret == -EINPROGRESS) {
+		ret = 0;
+	} else {
+		goto error_put_dest_keyring;
+	}
+
+	key_put(dest_keyring);
+	kleave(" = key %d", key_serial(key));
+	return key;
+
+construction_failed:
+	key_negate_and_link(key, key_negative_timeout, NULL, NULL);
+	key_put(key);
+error_put_dest_keyring:
+	key_put(dest_keyring);
+error:
+	kleave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/**
+ * request_key_and_link - Request a key and cache it in a keyring.
+ * @type: The type of key we want.
+ * @description: The searchable description of the key.
+ * @domain_tag: The domain in which the key operates.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ * @aux: Auxiliary data for the upcall.
+ * @dest_keyring: Where to cache the key.
+ * @flags: Flags to key_alloc().
+ *
+ * A key matching the specified criteria (type, description, domain_tag) is
+ * searched for in the process's keyrings and returned with its usage count
+ * incremented if found.  Otherwise, if callout_info is not NULL, a key will be
+ * allocated and some service (probably in userspace) will be asked to
+ * instantiate it.
+ *
+ * If successfully found or created, the key will be linked to the destination
+ * keyring if one is provided.
+ *
+ * Returns a pointer to the key if successful; -EACCES, -ENOKEY, -EKEYREVOKED
+ * or -EKEYEXPIRED if an inaccessible, negative, revoked or expired key was
+ * found; -ENOKEY if no key was found and no @callout_info was given; -EDQUOT
+ * if insufficient key quota was available to create a new key; or -ENOMEM if
+ * insufficient memory was available.
+ *
+ * If the returned key was created, then it may still be under construction,
+ * and wait_for_key_construction() should be used to wait for that to complete.
+ */
+struct key *request_key_and_link(struct key_type *type,
+				 const char *description,
+				 struct key_tag *domain_tag,
+				 const void *callout_info,
+				 size_t callout_len,
+				 void *aux,
+				 struct key *dest_keyring,
+				 unsigned long flags)
+{
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.domain_tag	= domain_tag,
+		.index_key.description	= description,
+		.index_key.desc_len	= strlen(description),
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_DO_STATE_CHECK |
+					   KEYRING_SEARCH_SKIP_EXPIRED |
+					   KEYRING_SEARCH_RECURSE),
+	};
+	struct key *key;
+	key_ref_t key_ref;
+	int ret;
+
+	kenter("%s,%s,%p,%zu,%p,%p,%lx",
+	       ctx.index_key.type->name, ctx.index_key.description,
+	       callout_info, callout_len, aux, dest_keyring, flags);
+
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
+	key = check_cached_key(&ctx);
+	if (key)
+		goto error_free;
+
+	/* search all the process keyrings for a key */
+	rcu_read_lock();
+	key_ref = search_process_keyrings_rcu(&ctx);
+	rcu_read_unlock();
+
+	if (!IS_ERR(key_ref)) {
+		if (dest_keyring) {
+			ret = key_task_permission(key_ref, current_cred(),
+						  KEY_NEED_LINK);
+			if (ret < 0) {
+				key_ref_put(key_ref);
+				key = ERR_PTR(ret);
+				goto error_free;
+			}
+		}
+
+		key = key_ref_to_ptr(key_ref);
+		if (dest_keyring) {
+			ret = key_link(dest_keyring, key);
+			if (ret < 0) {
+				key_put(key);
+				key = ERR_PTR(ret);
+				goto error_free;
+			}
+		}
+
+		/* Only cache the key on immediate success */
+		cache_requested_key(key);
+	} else if (PTR_ERR(key_ref) != -EAGAIN) {
+		key = ERR_CAST(key_ref);
+	} else  {
+		/* the search failed, but the keyrings were searchable, so we
+		 * should consult userspace if we can */
+		key = ERR_PTR(-ENOKEY);
+		if (!callout_info)
+			goto error_free;
+
+		key = construct_key_and_link(&ctx, callout_info, callout_len,
+					     aux, dest_keyring, flags);
+	}
+
+error_free:
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
+error:
+	kleave(" = %p", key);
+	return key;
+}
+
+/**
+ * wait_for_key_construction - Wait for construction of a key to complete
+ * @key: The key being waited for.
+ * @intr: Whether to wait interruptibly.
+ *
+ * Wait for a key to finish being constructed.
+ *
+ * Returns 0 if successful; -ERESTARTSYS if the wait was interrupted; -ENOKEY
+ * if the key was negated; or -EKEYREVOKED or -EKEYEXPIRED if the key was
+ * revoked or expired.
+ */
+int wait_for_key_construction(struct key *key, bool intr)
+{
+	int ret;
+
+	ret = wait_on_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT,
+			  intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+	if (ret)
+		return -ERESTARTSYS;
+	ret = key_read_state(key);
+	if (ret < 0)
+		return ret;
+	return key_validate(key);
+}
+EXPORT_SYMBOL(wait_for_key_construction);
+
+/**
+ * request_key_tag - Request a key and wait for construction
+ * @type: Type of key.
+ * @description: The searchable description of the key.
+ * @domain_tag: The domain in which the key operates.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found, new keys are always allocated in the user's quota,
+ * the callout_info must be a NUL-terminated string and no auxiliary data can
+ * be passed.
+ *
+ * Furthermore, it then works as wait_for_key_construction() to wait for the
+ * completion of keys undergoing construction with a non-interruptible wait.
+ */
+struct key *request_key_tag(struct key_type *type,
+			    const char *description,
+			    struct key_tag *domain_tag,
+			    const char *callout_info)
+{
+	struct key *key;
+	size_t callout_len = 0;
+	int ret;
+
+	if (callout_info)
+		callout_len = strlen(callout_info);
+	key = request_key_and_link(type, description, domain_tag,
+				   callout_info, callout_len,
+				   NULL, NULL, KEY_ALLOC_IN_QUOTA);
+	if (!IS_ERR(key)) {
+		ret = wait_for_key_construction(key, false);
+		if (ret < 0) {
+			key_put(key);
+			return ERR_PTR(ret);
+		}
+	}
+	return key;
+}
+EXPORT_SYMBOL(request_key_tag);
+
+/**
+ * request_key_with_auxdata - Request a key with auxiliary data for the upcaller
+ * @type: The type of key we want.
+ * @description: The searchable description of the key.
+ * @domain_tag: The domain in which the key operates.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ * @aux: Auxiliary data for the upcall.
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found and new keys are always allocated in the user's quota.
+ *
+ * Furthermore, it then works as wait_for_key_construction() to wait for the
+ * completion of keys undergoing construction with a non-interruptible wait.
+ */
+struct key *request_key_with_auxdata(struct key_type *type,
+				     const char *description,
+				     struct key_tag *domain_tag,
+				     const void *callout_info,
+				     size_t callout_len,
+				     void *aux)
+{
+	struct key *key;
+	int ret;
+
+	key = request_key_and_link(type, description, domain_tag,
+				   callout_info, callout_len,
+				   aux, NULL, KEY_ALLOC_IN_QUOTA);
+	if (!IS_ERR(key)) {
+		ret = wait_for_key_construction(key, false);
+		if (ret < 0) {
+			key_put(key);
+			return ERR_PTR(ret);
+		}
+	}
+	return key;
+}
+EXPORT_SYMBOL(request_key_with_auxdata);
+
+/**
+ * request_key_rcu - Request key from RCU-read-locked context
+ * @type: The type of key we want.
+ * @description: The name of the key we want.
+ * @domain_tag: The domain in which the key operates.
+ *
+ * Request a key from a context that we may not sleep in (such as RCU-mode
+ * pathwalk).  Keys under construction are ignored.
+ *
+ * Return a pointer to the found key if successful, -ENOKEY if we couldn't find
+ * a key or some other error if the key found was unsuitable or inaccessible.
+ */
+struct key *request_key_rcu(struct key_type *type,
+			    const char *description,
+			    struct key_tag *domain_tag)
+{
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.domain_tag	= domain_tag,
+		.index_key.description	= description,
+		.index_key.desc_len	= strlen(description),
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_DO_STATE_CHECK |
+					   KEYRING_SEARCH_SKIP_EXPIRED),
+	};
+	struct key *key;
+	key_ref_t key_ref;
+
+	kenter("%s,%s", type->name, description);
+
+	key = check_cached_key(&ctx);
+	if (key)
+		return key;
+
+	/* search all the process keyrings for a key */
+	key_ref = search_process_keyrings_rcu(&ctx);
+	if (IS_ERR(key_ref)) {
+		key = ERR_CAST(key_ref);
+		if (PTR_ERR(key_ref) == -EAGAIN)
+			key = ERR_PTR(-ENOKEY);
+	} else {
+		key = key_ref_to_ptr(key_ref);
+		cache_requested_key(key);
+	}
+
+	kleave(" = %p", key);
+	return key;
+}
+EXPORT_SYMBOL(request_key_rcu);
diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c
new file mode 100644
index 000000000..282e09d8f
--- /dev/null
+++ b/security/keys/request_key_auth.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Request key authorisation token key definition.
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/security/keys/request-key.rst
+ */
+
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+#include <keys/request_key_auth-type.h>
+
+static int request_key_auth_preparse(struct key_preparsed_payload *);
+static void request_key_auth_free_preparse(struct key_preparsed_payload *);
+static int request_key_auth_instantiate(struct key *,
+					struct key_preparsed_payload *);
+static void request_key_auth_describe(const struct key *, struct seq_file *);
+static void request_key_auth_revoke(struct key *);
+static void request_key_auth_destroy(struct key *);
+static long request_key_auth_read(const struct key *, char *, size_t);
+static void request_key_auth_rcu_disposal(struct rcu_head *);
+
+/*
+ * The request-key authorisation key type definition.
+ */
+struct key_type key_type_request_key_auth = {
+	.name		= ".request_key_auth",
+	.def_datalen	= sizeof(struct request_key_auth),
+	.preparse	= request_key_auth_preparse,
+	.free_preparse	= request_key_auth_free_preparse,
+	.instantiate	= request_key_auth_instantiate,
+	.describe	= request_key_auth_describe,
+	.revoke		= request_key_auth_revoke,
+	.destroy	= request_key_auth_destroy,
+	.read		= request_key_auth_read,
+};
+
+static int request_key_auth_preparse(struct key_preparsed_payload *prep)
+{
+	return 0;
+}
+
+static void request_key_auth_free_preparse(struct key_preparsed_payload *prep)
+{
+}
+
+/*
+ * Instantiate a request-key authorisation key.
+ */
+static int request_key_auth_instantiate(struct key *key,
+					struct key_preparsed_payload *prep)
+{
+	rcu_assign_keypointer(key, (struct request_key_auth *)prep->data);
+	return 0;
+}
+
+/*
+ * Describe an authorisation token.
+ */
+static void request_key_auth_describe(const struct key *key,
+				      struct seq_file *m)
+{
+	struct request_key_auth *rka = dereference_key_rcu(key);
+
+	if (!rka)
+		return;
+
+	seq_puts(m, "key:");
+	seq_puts(m, key->description);
+	if (key_is_positive(key))
+		seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len);
+}
+
+/*
+ * Read the callout_info data (retrieves the callout information).
+ * - the key's semaphore is read-locked
+ */
+static long request_key_auth_read(const struct key *key,
+				  char *buffer, size_t buflen)
+{
+	struct request_key_auth *rka = dereference_key_locked(key);
+	size_t datalen;
+	long ret;
+
+	if (!rka)
+		return -EKEYREVOKED;
+
+	datalen = rka->callout_len;
+	ret = datalen;
+
+	/* we can return the data as is */
+	if (buffer && buflen > 0) {
+		if (buflen > datalen)
+			buflen = datalen;
+
+		memcpy(buffer, rka->callout_info, buflen);
+	}
+
+	return ret;
+}
+
+static void free_request_key_auth(struct request_key_auth *rka)
+{
+	if (!rka)
+		return;
+	key_put(rka->target_key);
+	key_put(rka->dest_keyring);
+	if (rka->cred)
+		put_cred(rka->cred);
+	kfree(rka->callout_info);
+	kfree(rka);
+}
+
+/*
+ * Take a reference to the request-key authorisation payload so callers can
+ * drop authkey->sem before doing operations that may sleep.
+ */
+struct request_key_auth *request_key_auth_get(struct key *authkey)
+{
+	struct request_key_auth *rka;
+
+	down_read(&authkey->sem);
+	rka = dereference_key_locked(authkey);
+	if (rka && !test_bit(KEY_FLAG_REVOKED, &authkey->flags))
+		refcount_inc(&rka->usage);
+	else
+		rka = NULL;
+	up_read(&authkey->sem);
+
+	return rka;
+}
+
+void request_key_auth_put(struct request_key_auth *rka)
+{
+	if (rka && refcount_dec_and_test(&rka->usage))
+		call_rcu(&rka->rcu, request_key_auth_rcu_disposal);
+}
+
+/*
+ * Dispose of the request_key_auth record under RCU conditions
+ */
+static void request_key_auth_rcu_disposal(struct rcu_head *rcu)
+{
+	struct request_key_auth *rka =
+		container_of(rcu, struct request_key_auth, rcu);
+
+	free_request_key_auth(rka);
+}
+
+/*
+ * Handle revocation of an authorisation token key.
+ *
+ * Called with the key sem write-locked.
+ */
+static void request_key_auth_revoke(struct key *key)
+{
+	struct request_key_auth *rka = dereference_key_locked(key);
+
+	kenter("{%d}", key->serial);
+	if (!rka)
+		return;
+	rcu_assign_keypointer(key, NULL);
+	request_key_auth_put(rka);
+}
+
+/*
+ * Destroy an instantiation authorisation token key.
+ */
+static void request_key_auth_destroy(struct key *key)
+{
+	struct request_key_auth *rka = rcu_access_pointer(key->payload.rcu_data0);
+
+	kenter("{%d}", key->serial);
+	if (rka) {
+		rcu_assign_keypointer(key, NULL);
+		request_key_auth_put(rka);
+	}
+}
+
+/*
+ * Create an authorisation token for /sbin/request-key or whoever to gain
+ * access to the caller's security data.
+ */
+struct key *request_key_auth_new(struct key *target, const char *op,
+				 const void *callout_info, size_t callout_len,
+				 struct key *dest_keyring)
+{
+	struct request_key_auth *rka, *irka;
+	const struct cred *cred = current_cred();
+	struct key *authkey = NULL;
+	char desc[20];
+	int ret = -ENOMEM;
+
+	kenter("%d,", target->serial);
+
+	/* allocate a auth record */
+	rka = kzalloc_obj(*rka);
+	if (!rka)
+		goto error;
+	refcount_set(&rka->usage, 1);
+	rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL);
+	if (!rka->callout_info)
+		goto error_free_rka;
+	rka->callout_len = callout_len;
+	strscpy(rka->op, op, sizeof(rka->op));
+
+	/* see if the calling process is already servicing the key request of
+	 * another process */
+	if (cred->request_key_auth) {
+		/* it is - use that instantiation context here too */
+		down_read(&cred->request_key_auth->sem);
+
+		/* if the auth key has been revoked, then the key we're
+		 * servicing is already instantiated */
+		if (test_bit(KEY_FLAG_REVOKED,
+			     &cred->request_key_auth->flags)) {
+			up_read(&cred->request_key_auth->sem);
+			ret = -EKEYREVOKED;
+			goto error_free_rka;
+		}
+
+		irka = cred->request_key_auth->payload.data[0];
+		rka->cred = get_cred(irka->cred);
+		rka->pid = irka->pid;
+
+		up_read(&cred->request_key_auth->sem);
+	}
+	else {
+		/* it isn't - use this process as the context */
+		rka->cred = get_cred(cred);
+		rka->pid = current->pid;
+	}
+
+	rka->target_key = key_get(target);
+	rka->dest_keyring = key_get(dest_keyring);
+
+	/* allocate the auth key */
+	sprintf(desc, "%x", target->serial);
+
+	authkey = key_alloc(&key_type_request_key_auth, desc,
+			    cred->fsuid, cred->fsgid, cred,
+			    KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | KEY_POS_LINK |
+			    KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(authkey)) {
+		ret = PTR_ERR(authkey);
+		goto error_free_rka;
+	}
+
+	/* construct the auth key */
+	ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL);
+	if (ret < 0)
+		goto error_put_authkey;
+
+	kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage));
+	return authkey;
+
+error_put_authkey:
+	key_put(authkey);
+error_free_rka:
+	free_request_key_auth(rka);
+error:
+	kleave("= %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Search the current process's keyrings for the authorisation key for
+ * instantiation of a key.
+ */
+struct key *key_get_instantiation_authkey(key_serial_t target_id)
+{
+	char description[16];
+	struct keyring_search_context ctx = {
+		.index_key.type		= &key_type_request_key_auth,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_DO_STATE_CHECK |
+					   KEYRING_SEARCH_RECURSE),
+	};
+	struct key *authkey;
+	key_ref_t authkey_ref;
+
+	ctx.index_key.desc_len = sprintf(description, "%x", target_id);
+
+	rcu_read_lock();
+	authkey_ref = search_process_keyrings_rcu(&ctx);
+	rcu_read_unlock();
+
+	if (IS_ERR(authkey_ref)) {
+		authkey = ERR_CAST(authkey_ref);
+		if (authkey == ERR_PTR(-EAGAIN))
+			authkey = ERR_PTR(-ENOKEY);
+		goto error;
+	}
+
+	authkey = key_ref_to_ptr(authkey_ref);
+	if (test_bit(KEY_FLAG_REVOKED, &authkey->flags)) {
+		key_put(authkey);
+		authkey = ERR_PTR(-EKEYREVOKED);
+	}
+
+error:
+	return authkey;
+}
diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c
new file mode 100644
index 000000000..cde08c478
--- /dev/null
+++ b/security/keys/sysctl.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key management controls
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/key.h>
+#include <linux/sysctl.h>
+#include "internal.h"
+
+static const struct ctl_table key_sysctls[] = {
+	{
+		.procname = "maxkeys",
+		.data = &key_quota_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "maxbytes",
+		.data = &key_quota_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "root_maxkeys",
+		.data = &key_quota_root_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "root_maxbytes",
+		.data = &key_quota_root_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ONE,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+	{
+		.procname = "gc_delay",
+		.data = &key_gc_delay,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ZERO,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	{
+		.procname = "persistent_keyring_expiry",
+		.data = &persistent_keyring_expiry,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) SYSCTL_ZERO,
+		.extra2 = (void *) SYSCTL_INT_MAX,
+	},
+#endif
+};
+
+static int __init init_security_keys_sysctls(void)
+{
+	register_sysctl_init("kernel/keys", key_sysctls);
+	return 0;
+}
+early_initcall(init_security_keys_sysctls);
diff --git a/security/keys/trusted-keys/Kconfig b/security/keys/trusted-keys/Kconfig
new file mode 100644
index 000000000..e5a4a53ae
--- /dev/null
+++ b/security/keys/trusted-keys/Kconfig
@@ -0,0 +1,82 @@
+config HAVE_TRUSTED_KEYS
+	bool
+
+config HAVE_TRUSTED_KEYS_DEBUG
+	bool
+
+config TRUSTED_KEYS_DEBUG
+	bool "Debug trusted keys"
+	depends on HAVE_TRUSTED_KEYS_DEBUG
+	default n
+	help
+	  Trusted key backends and core code that support debug traces can
+	  opt-in that feature here. Traces must only use debug level output, as
+	  sensitive data may pass by. In the kernel-command line traces can be
+	  enabled via trusted.dyndbg='+p'.
+
+	  SAFETY: Debug dumps are inactive at runtime until trusted.debug is set
+	  to a true value on the kernel command-line. Use at your utmost
+	  consideration when enabling this feature on a production build. The
+	  general advice is not to do this.
+
+config TRUSTED_KEYS_TPM
+	bool "TPM-based trusted keys"
+	depends on TCG_TPM >= TRUSTED_KEYS
+	default y
+	select HAVE_TRUSTED_KEYS_DEBUG
+	select CRYPTO_HASH_INFO
+	select CRYPTO_LIB_SHA1
+	select CRYPTO_LIB_UTILS
+	select ASN1_ENCODER
+	select OID_REGISTRY
+	select ASN1
+	select HAVE_TRUSTED_KEYS
+	help
+	  Enable use of the Trusted Platform Module (TPM) as trusted key
+	  backend. Trusted keys are random number symmetric keys,
+	  which will be generated and RSA-sealed by the TPM.
+	  The TPM only unseals the keys, if the boot PCRs and other
+	  criteria match.
+
+config TRUSTED_KEYS_TEE
+	bool "TEE-based trusted keys"
+	depends on TEE >= TRUSTED_KEYS
+	default y
+	select HAVE_TRUSTED_KEYS_DEBUG
+	select HAVE_TRUSTED_KEYS
+	help
+	  Enable use of the Trusted Execution Environment (TEE) as trusted
+	  key backend.
+
+config TRUSTED_KEYS_CAAM
+	bool "CAAM-based trusted keys"
+	depends on CRYPTO_DEV_FSL_CAAM_JR >= TRUSTED_KEYS
+	select CRYPTO_DEV_FSL_CAAM_BLOB_GEN
+	default y
+	select HAVE_TRUSTED_KEYS_DEBUG
+	select HAVE_TRUSTED_KEYS
+	help
+	  Enable use of NXP's Cryptographic Accelerator and Assurance Module
+	  (CAAM) as trusted key backend.
+
+config TRUSTED_KEYS_DCP
+	bool "DCP-based trusted keys"
+	depends on CRYPTO_DEV_MXS_DCP >= TRUSTED_KEYS
+	default y
+	select HAVE_TRUSTED_KEYS_DEBUG
+	select HAVE_TRUSTED_KEYS
+	help
+	  Enable use of NXP's DCP (Data Co-Processor) as trusted key backend.
+
+config TRUSTED_KEYS_PKWM
+	bool "PKWM-based trusted keys"
+	depends on PSERIES_PLPKS >= TRUSTED_KEYS
+	default y
+	select HAVE_TRUSTED_KEYS_DEBUG
+	select HAVE_TRUSTED_KEYS
+	help
+	  Enable use of IBM PowerVM Key Wrapping Module (PKWM) as a trusted key backend.
+
+if !HAVE_TRUSTED_KEYS
+	comment "No trust source selected!"
+endif
diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile
new file mode 100644
index 000000000..5fc053a21
--- /dev/null
+++ b/security/keys/trusted-keys/Makefile
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for trusted keys
+#
+
+obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
+trusted-y += trusted_core.o
+trusted-$(CONFIG_TRUSTED_KEYS_TPM) += trusted_tpm1.o
+
+$(obj)/trusted_tpm2.o: $(obj)/tpm2key.asn1.h
+trusted-$(CONFIG_TRUSTED_KEYS_TPM) += trusted_tpm2.o
+trusted-$(CONFIG_TRUSTED_KEYS_TPM) += tpm2key.asn1.o
+
+trusted-$(CONFIG_TRUSTED_KEYS_TEE) += trusted_tee.o
+
+trusted-$(CONFIG_TRUSTED_KEYS_CAAM) += trusted_caam.o
+
+trusted-$(CONFIG_TRUSTED_KEYS_DCP) += trusted_dcp.o
+
+trusted-$(CONFIG_TRUSTED_KEYS_PKWM) += trusted_pkwm.o
diff --git a/security/keys/trusted-keys/tpm2key.asn1 b/security/keys/trusted-keys/tpm2key.asn1
new file mode 100644
index 000000000..f57f869ad
--- /dev/null
+++ b/security/keys/trusted-keys/tpm2key.asn1
@@ -0,0 +1,11 @@
+---
+--- ASN.1 for TPM 2.0 keys
+---
+
+TPMKey ::= SEQUENCE {
+	type		OBJECT IDENTIFIER ({tpm2_key_type}),
+	emptyAuth	[0] EXPLICIT BOOLEAN OPTIONAL,
+	parent		INTEGER ({tpm2_key_parent}),
+	pubkey		OCTET STRING ({tpm2_key_pub}),
+	privkey		OCTET STRING ({tpm2_key_priv})
+	}
diff --git a/security/keys/trusted-keys/trusted_caam.c b/security/keys/trusted-keys/trusted_caam.c
new file mode 100644
index 000000000..6a33dbf2a
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_caam.c
@@ -0,0 +1,191 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Pengutronix, Ahmad Fatoum <kernel@pengutronix.de>
+ * Copyright 2025 NXP
+ */
+
+#include <keys/trusted_caam.h>
+#include <keys/trusted-type.h>
+#include <linux/build_bug.h>
+#include <linux/key-type.h>
+#include <linux/parser.h>
+#include <soc/fsl/caam-blob.h>
+
+static struct caam_blob_priv *blobifier;
+
+#define KEYMOD "SECURE_KEY"
+
+static_assert(MAX_KEY_SIZE + CAAM_BLOB_OVERHEAD <= CAAM_BLOB_MAX_LEN);
+static_assert(MAX_BLOB_SIZE <= CAAM_BLOB_MAX_LEN);
+
+enum {
+	opt_err,
+	opt_key_enc_algo,
+};
+
+static const match_table_t key_tokens = {
+	{opt_key_enc_algo, "key_enc_algo=%s"},
+	{opt_err, NULL}
+};
+
+#ifdef CONFIG_TRUSTED_KEYS_DEBUG
+static inline void dump_options(const struct caam_pkey_info *pkey_info)
+{
+	if (!trusted_debug)
+		return;
+
+	pr_debug("key encryption algo %d\n", pkey_info->key_enc_algo);
+}
+#else
+static inline void dump_options(const struct caam_pkey_info *pkey_info)
+{
+}
+#endif
+
+static int get_pkey_options(char *c,
+			    struct caam_pkey_info *pkey_info)
+{
+	substring_t args[MAX_OPT_ARGS];
+	unsigned long token_mask = 0;
+	u16 key_enc_algo;
+	char *p = c;
+	int token;
+	int res;
+
+	if (!c)
+		return 0;
+
+	while ((p = strsep(&c, " \t"))) {
+		if (*p == '\0' || *p == ' ' || *p == '\t')
+			continue;
+		token = match_token(p, key_tokens, args);
+		if (test_and_set_bit(token, &token_mask))
+			return -EINVAL;
+
+		switch (token) {
+		case opt_key_enc_algo:
+			res = kstrtou16(args[0].from, 16, &key_enc_algo);
+			if (res < 0)
+				return -EINVAL;
+			pkey_info->key_enc_algo = key_enc_algo;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static bool is_key_pkey(char **datablob)
+{
+	char *c = NULL;
+
+	do {
+		/* Second argument onwards,
+		 * determine if tied to HW
+		 */
+		c = strsep(datablob, " \t");
+		if (c && (strcmp(c, "pk") == 0))
+			return true;
+	} while (c);
+
+	return false;
+}
+
+static int trusted_caam_seal(struct trusted_key_payload *p, char *datablob)
+{
+	int ret;
+	struct caam_blob_info info = {
+		.input  = p->key,  .input_len   = p->key_len,
+		.output = p->blob, .output_len  = MAX_BLOB_SIZE,
+		.key_mod = KEYMOD, .key_mod_len = sizeof(KEYMOD) - 1,
+	};
+
+	/*
+	 * If it is to be treated as protected key,
+	 * read next arguments too.
+	 */
+	if (is_key_pkey(&datablob)) {
+		info.pkey_info.plain_key_sz = p->key_len;
+		info.pkey_info.is_pkey = 1;
+		ret = get_pkey_options(datablob, &info.pkey_info);
+		if (ret < 0)
+			return 0;
+		dump_options(&info.pkey_info);
+	}
+
+	ret = caam_encap_blob(blobifier, &info);
+	if (ret)
+		return ret;
+
+	p->blob_len = info.output_len;
+	if (info.pkey_info.is_pkey) {
+		p->key_len = p->blob_len + sizeof(struct caam_pkey_info);
+		memcpy(p->key, &info.pkey_info, sizeof(struct caam_pkey_info));
+		memcpy(p->key + sizeof(struct caam_pkey_info), p->blob, p->blob_len);
+	}
+
+	return 0;
+}
+
+static int trusted_caam_unseal(struct trusted_key_payload *p, char *datablob)
+{
+	int ret;
+	struct caam_blob_info info = {
+		.input   = p->blob,  .input_len  = p->blob_len,
+		.output  = p->key,   .output_len = MAX_KEY_SIZE,
+		.key_mod = KEYMOD,  .key_mod_len = sizeof(KEYMOD) - 1,
+	};
+
+	if (is_key_pkey(&datablob)) {
+		info.pkey_info.plain_key_sz = p->blob_len - CAAM_BLOB_OVERHEAD;
+		info.pkey_info.is_pkey = 1;
+		ret = get_pkey_options(datablob, &info.pkey_info);
+		if (ret < 0)
+			return 0;
+		dump_options(&info.pkey_info);
+
+		p->key_len = p->blob_len + sizeof(struct caam_pkey_info);
+		memcpy(p->key, &info.pkey_info, sizeof(struct caam_pkey_info));
+		memcpy(p->key + sizeof(struct caam_pkey_info), p->blob, p->blob_len);
+
+		return 0;
+	}
+
+	ret = caam_decap_blob(blobifier, &info);
+	if (ret)
+		return ret;
+
+	p->key_len = info.output_len;
+
+	return 0;
+}
+
+static int trusted_caam_init(void)
+{
+	int ret;
+
+	blobifier = caam_blob_gen_init();
+	if (IS_ERR(blobifier))
+		return PTR_ERR(blobifier);
+
+	ret = register_key_type(&key_type_trusted);
+	if (ret)
+		caam_blob_gen_exit(blobifier);
+
+	return ret;
+}
+
+static void trusted_caam_exit(void)
+{
+	unregister_key_type(&key_type_trusted);
+	caam_blob_gen_exit(blobifier);
+}
+
+struct trusted_key_ops trusted_key_caam_ops = {
+	.migratable = 0, /* non-migratable */
+	.init = trusted_caam_init,
+	.seal = trusted_caam_seal,
+	.unseal = trusted_caam_unseal,
+	.exit = trusted_caam_exit,
+};
diff --git a/security/keys/trusted-keys/trusted_core.c b/security/keys/trusted-keys/trusted_core.c
new file mode 100644
index 000000000..0509d9955
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_core.c
@@ -0,0 +1,410 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (c) 2019-2021, Linaro Limited
+ *
+ * See Documentation/security/keys/trusted-encrypted.rst
+ */
+
+#include <keys/user-type.h>
+#include <keys/trusted-type.h>
+#include <keys/trusted_tee.h>
+#include <keys/trusted_caam.h>
+#include <keys/trusted_dcp.h>
+#include <keys/trusted_tpm.h>
+#include <keys/trusted_pkwm.h>
+#include <linux/capability.h>
+#include <linux/err.h>
+#include <linux/hex.h>
+#include <linux/init.h>
+#include <linux/key-type.h>
+#include <linux/module.h>
+#include <linux/parser.h>
+#include <linux/random.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+#include <linux/static_call.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+static char *trusted_rng = "default";
+module_param_named(rng, trusted_rng, charp, 0);
+MODULE_PARM_DESC(rng, "Select trusted key RNG");
+
+#ifdef CONFIG_TRUSTED_KEYS_DEBUG
+bool trusted_debug;
+module_param_named(debug, trusted_debug, bool, 0);
+MODULE_PARM_DESC(debug, "Enable trusted keys debug traces (default: 0)");
+#endif
+
+static char *trusted_key_source;
+module_param_named(source, trusted_key_source, charp, 0);
+MODULE_PARM_DESC(source, "Select trusted keys source (tpm, tee, caam, dcp or pkwm)");
+
+static const struct trusted_key_source trusted_key_sources[] = {
+#if defined(CONFIG_TRUSTED_KEYS_TPM)
+	{ "tpm", &trusted_key_tpm_ops },
+#endif
+#if defined(CONFIG_TRUSTED_KEYS_TEE)
+	{ "tee", &trusted_key_tee_ops },
+#endif
+#if defined(CONFIG_TRUSTED_KEYS_CAAM)
+	{ "caam", &trusted_key_caam_ops },
+#endif
+#if defined(CONFIG_TRUSTED_KEYS_DCP)
+	{ "dcp", &dcp_trusted_key_ops },
+#endif
+#if defined(CONFIG_TRUSTED_KEYS_PKWM)
+	{ "pkwm", &pkwm_trusted_key_ops },
+#endif
+};
+
+DEFINE_STATIC_CALL_NULL(trusted_key_seal, *trusted_key_sources[0].ops->seal);
+DEFINE_STATIC_CALL_NULL(trusted_key_unseal,
+			*trusted_key_sources[0].ops->unseal);
+DEFINE_STATIC_CALL_NULL(trusted_key_get_random,
+			*trusted_key_sources[0].ops->get_random);
+static void (*trusted_key_exit)(void);
+static unsigned char migratable __ro_after_init;
+
+enum {
+	Opt_err,
+	Opt_new, Opt_load, Opt_update,
+};
+
+static const match_table_t key_tokens = {
+	{Opt_new, "new"},
+	{Opt_load, "load"},
+	{Opt_update, "update"},
+	{Opt_err, NULL}
+};
+
+/*
+ * datablob_parse - parse the keyctl data and fill in the
+ *                  payload structure
+ *
+ * On success returns 0, otherwise -EINVAL.
+ */
+static int datablob_parse(char **datablob, struct trusted_key_payload *p)
+{
+	substring_t args[MAX_OPT_ARGS];
+	long keylen;
+	int ret = -EINVAL;
+	int key_cmd;
+	char *c;
+
+	/* main command */
+	c = strsep(datablob, " \t");
+	if (!c)
+		return -EINVAL;
+	key_cmd = match_token(c, key_tokens, args);
+	switch (key_cmd) {
+	case Opt_new:
+		/* first argument is key size */
+		c = strsep(datablob, " \t");
+		if (!c)
+			return -EINVAL;
+		ret = kstrtol(c, 10, &keylen);
+		if (ret < 0 || keylen < MIN_KEY_SIZE || keylen > MAX_KEY_SIZE)
+			return -EINVAL;
+		p->key_len = keylen;
+		ret = Opt_new;
+		break;
+	case Opt_load:
+		/* first argument is sealed blob */
+		c = strsep(datablob, " \t");
+		if (!c)
+			return -EINVAL;
+		p->blob_len = strlen(c) / 2;
+		if (p->blob_len > MAX_BLOB_SIZE)
+			return -EINVAL;
+		ret = hex2bin(p->blob, c, p->blob_len);
+		if (ret < 0)
+			return -EINVAL;
+		ret = Opt_load;
+		break;
+	case Opt_update:
+		ret = Opt_update;
+		break;
+	case Opt_err:
+		return -EINVAL;
+	}
+	return ret;
+}
+
+static struct trusted_key_payload *trusted_payload_alloc(struct key *key)
+{
+	struct trusted_key_payload *p = NULL;
+	int ret;
+
+	ret = key_payload_reserve(key, sizeof(*p));
+	if (ret < 0)
+		goto err;
+	p = kzalloc_obj(*p);
+	if (!p)
+		goto err;
+
+	p->migratable = migratable;
+err:
+	return p;
+}
+
+/*
+ * trusted_instantiate - create a new trusted key
+ *
+ * Unseal an existing trusted blob or, for a new key, get a
+ * random key, then seal and create a trusted key-type key,
+ * adding it to the specified keyring.
+ *
+ * On success, return 0. Otherwise return errno.
+ */
+static int trusted_instantiate(struct key *key,
+			       struct key_preparsed_payload *prep)
+{
+	struct trusted_key_payload *payload = NULL;
+	size_t datalen = prep->datalen;
+	char *datablob, *orig_datablob;
+	int ret = 0;
+	int key_cmd;
+	size_t key_len;
+
+	if (datalen == 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!datablob)
+		return -ENOMEM;
+	memcpy(datablob, prep->data, datalen);
+	datablob[datalen] = '\0';
+
+	payload = trusted_payload_alloc(key);
+	if (!payload) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	key_cmd = datablob_parse(&datablob, payload);
+	if (key_cmd < 0) {
+		ret = key_cmd;
+		goto out;
+	}
+
+	dump_payload(payload);
+
+	switch (key_cmd) {
+	case Opt_load:
+		ret = static_call(trusted_key_unseal)(payload, datablob);
+		dump_payload(payload);
+		if (ret < 0)
+			pr_info("key_unseal failed (%d)\n", ret);
+		break;
+	case Opt_new:
+		key_len = payload->key_len;
+		ret = static_call(trusted_key_get_random)(payload->key,
+							  key_len);
+		if (ret < 0)
+			goto out;
+
+		if (ret != key_len) {
+			pr_info("key_create failed (%d)\n", ret);
+			ret = -EIO;
+			goto out;
+		}
+
+		ret = static_call(trusted_key_seal)(payload, datablob);
+		if (ret < 0)
+			pr_info("key_seal failed (%d)\n", ret);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+out:
+	kfree_sensitive(orig_datablob);
+	if (!ret)
+		rcu_assign_keypointer(key, payload);
+	else
+		kfree_sensitive(payload);
+	return ret;
+}
+
+static void trusted_rcu_free(struct rcu_head *rcu)
+{
+	struct trusted_key_payload *p;
+
+	p = container_of(rcu, struct trusted_key_payload, rcu);
+	kfree_sensitive(p);
+}
+
+/*
+ * trusted_update - reseal an existing key with new PCR values
+ */
+static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct trusted_key_payload *p;
+	struct trusted_key_payload *new_p;
+	size_t datalen = prep->datalen;
+	char *datablob, *orig_datablob;
+	int ret = 0;
+
+	if (key_is_negative(key))
+		return -ENOKEY;
+	p = key->payload.data[0];
+	if (!p->migratable)
+		return -EPERM;
+	if (datalen == 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!datablob)
+		return -ENOMEM;
+
+	new_p = trusted_payload_alloc(key);
+	if (!new_p) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memcpy(datablob, prep->data, datalen);
+	datablob[datalen] = '\0';
+	ret = datablob_parse(&datablob, new_p);
+	if (ret != Opt_update) {
+		ret = -EINVAL;
+		kfree_sensitive(new_p);
+		goto out;
+	}
+
+	/* copy old key values, and reseal with new pcrs */
+	new_p->migratable = p->migratable;
+	new_p->key_len = p->key_len;
+	memcpy(new_p->key, p->key, p->key_len);
+	dump_payload(p);
+	dump_payload(new_p);
+
+	ret = static_call(trusted_key_seal)(new_p, datablob);
+	if (ret < 0) {
+		pr_info("key_seal failed (%d)\n", ret);
+		kfree_sensitive(new_p);
+		goto out;
+	}
+
+	rcu_assign_keypointer(key, new_p);
+	call_rcu(&p->rcu, trusted_rcu_free);
+out:
+	kfree_sensitive(orig_datablob);
+	return ret;
+}
+
+/*
+ * trusted_read - copy the sealed blob data to userspace in hex.
+ * On success, return to userspace the trusted key datablob size.
+ */
+static long trusted_read(const struct key *key, char *buffer,
+			 size_t buflen)
+{
+	const struct trusted_key_payload *p;
+	char *bufp;
+	int i;
+
+	p = dereference_key_locked(key);
+	if (!p)
+		return -EINVAL;
+
+	if (buffer && buflen >= 2 * p->blob_len) {
+		bufp = buffer;
+		for (i = 0; i < p->blob_len; i++)
+			bufp = hex_byte_pack(bufp, p->blob[i]);
+	}
+	return 2 * p->blob_len;
+}
+
+/*
+ * trusted_destroy - clear and free the key's payload
+ */
+static void trusted_destroy(struct key *key)
+{
+	kfree_sensitive(key->payload.data[0]);
+}
+
+struct key_type key_type_trusted = {
+	.name = "trusted",
+	.instantiate = trusted_instantiate,
+	.update = trusted_update,
+	.destroy = trusted_destroy,
+	.describe = user_describe,
+	.read = trusted_read,
+};
+EXPORT_SYMBOL_GPL(key_type_trusted);
+
+static int kernel_get_random(unsigned char *key, size_t key_len)
+{
+	return get_random_bytes_wait(key, key_len) ?: key_len;
+}
+
+static int __init init_trusted(void)
+{
+	int (*get_random)(unsigned char *key, size_t key_len);
+	int i, ret = 0;
+
+	for (i = 0; i < ARRAY_SIZE(trusted_key_sources); i++) {
+		if (trusted_key_source &&
+		    strncmp(trusted_key_source, trusted_key_sources[i].name,
+			    strlen(trusted_key_sources[i].name)))
+			continue;
+
+		/*
+		 * We always support trusted.rng="kernel" and "default" as
+		 * well as trusted.rng=$trusted.source if the trust source
+		 * defines its own get_random callback.
+		 */
+		get_random = trusted_key_sources[i].ops->get_random;
+		if (trusted_rng && strcmp(trusted_rng, "default")) {
+			if (!strcmp(trusted_rng, "kernel")) {
+				get_random = kernel_get_random;
+			} else if (strcmp(trusted_rng, trusted_key_sources[i].name) ||
+				   !get_random) {
+				pr_warn("Unsupported RNG. Supported: kernel");
+				if (get_random)
+					pr_cont(", %s", trusted_key_sources[i].name);
+				pr_cont(", default\n");
+				return -EINVAL;
+			}
+		}
+
+		if (!get_random)
+			get_random = kernel_get_random;
+
+		ret = trusted_key_sources[i].ops->init();
+		if (!ret) {
+			static_call_update(trusted_key_seal, trusted_key_sources[i].ops->seal);
+			static_call_update(trusted_key_unseal, trusted_key_sources[i].ops->unseal);
+			static_call_update(trusted_key_get_random, get_random);
+
+			trusted_key_exit = trusted_key_sources[i].ops->exit;
+			migratable = trusted_key_sources[i].ops->migratable;
+		}
+
+		if (!ret || ret != -ENODEV)
+			break;
+	}
+
+	/*
+	 * encrypted_keys.ko depends on successful load of this module even if
+	 * trusted key implementation is not found.
+	 */
+	if (ret == -ENODEV)
+		return 0;
+
+	return ret;
+}
+
+static void __exit cleanup_trusted(void)
+{
+	if (trusted_key_exit)
+		(*trusted_key_exit)();
+}
+
+late_initcall(init_trusted);
+module_exit(cleanup_trusted);
+
+MODULE_DESCRIPTION("Trusted Key type");
+MODULE_LICENSE("GPL");
diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c
new file mode 100644
index 000000000..c078adebe
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_dcp.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 sigma star gmbh
+ */
+
+#include <crypto/aead.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/gcm.h>
+#include <crypto/skcipher.h>
+#include <keys/trusted-type.h>
+#include <linux/key-type.h>
+#include <linux/module.h>
+#include <linux/printk.h>
+#include <linux/random.h>
+#include <linux/scatterlist.h>
+#include <soc/fsl/dcp.h>
+
+#define DCP_BLOB_VERSION 1
+#define DCP_BLOB_AUTHLEN 16
+
+/**
+ * DOC: dcp blob format
+ *
+ * The Data Co-Processor (DCP) provides hardware-bound AES keys using its
+ * AES encryption engine only. It does not provide direct key sealing/unsealing.
+ * To make DCP hardware encryption keys usable as trust source, we define
+ * our own custom format that uses a hardware-bound key to secure the sealing
+ * key stored in the key blob.
+ *
+ * Whenever a new trusted key using DCP is generated, we generate a random 128-bit
+ * blob encryption key (BEK) and 128-bit nonce. The BEK and nonce are used to
+ * encrypt the trusted key payload using AES-128-GCM.
+ *
+ * The BEK itself is encrypted using the hardware-bound key using the DCP's AES
+ * encryption engine with AES-128-ECB. The encrypted BEK, generated nonce,
+ * BEK-encrypted payload and authentication tag make up the blob format together
+ * with a version number, payload length and authentication tag.
+ */
+
+/**
+ * struct dcp_blob_fmt - DCP BLOB format.
+ *
+ * @fmt_version: Format version, currently being %1.
+ * @blob_key: Random AES 128 key which is used to encrypt @payload,
+ *            @blob_key itself is encrypted with OTP or UNIQUE device key in
+ *            AES-128-ECB mode by DCP.
+ * @nonce: Random nonce used for @payload encryption.
+ * @payload_len: Length of the plain text @payload.
+ * @payload: The payload itself, encrypted using AES-128-GCM and @blob_key,
+ *           GCM auth tag of size DCP_BLOB_AUTHLEN is attached at the end of it.
+ *
+ * The total size of a DCP BLOB is sizeof(struct dcp_blob_fmt) + @payload_len +
+ * DCP_BLOB_AUTHLEN.
+ */
+struct dcp_blob_fmt {
+	__u8 fmt_version;
+	__u8 blob_key[AES_KEYSIZE_128];
+	__u8 nonce[AES_KEYSIZE_128];
+	__le32 payload_len;
+	__u8 payload[];
+} __packed;
+
+static bool use_otp_key;
+module_param_named(dcp_use_otp_key, use_otp_key, bool, 0);
+MODULE_PARM_DESC(dcp_use_otp_key, "Use OTP instead of UNIQUE key for sealing");
+
+static bool skip_zk_test;
+module_param_named(dcp_skip_zk_test, skip_zk_test, bool, 0);
+MODULE_PARM_DESC(dcp_skip_zk_test, "Don't test whether device keys are zero'ed");
+
+static size_t calc_blob_len(unsigned int payload_len)
+{
+	return sizeof(struct dcp_blob_fmt) + payload_len + DCP_BLOB_AUTHLEN;
+}
+
+static int do_dcp_crypto(u8 *in, u8 *out, bool do_encrypt)
+{
+	struct skcipher_request *req = NULL;
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_skcipher *tfm;
+	u8 paes_key[DCP_PAES_KEYSIZE];
+	DECLARE_CRYPTO_WAIT(wait);
+	int res = 0;
+
+	if (use_otp_key)
+		paes_key[0] = DCP_PAES_KEY_OTP;
+	else
+		paes_key[0] = DCP_PAES_KEY_UNIQUE;
+
+	tfm = crypto_alloc_skcipher("ecb-paes-dcp", CRYPTO_ALG_INTERNAL,
+				    CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(tfm)) {
+		res = PTR_ERR(tfm);
+		tfm = NULL;
+		goto out;
+	}
+
+	req = skcipher_request_alloc(tfm, GFP_NOFS);
+	if (!req) {
+		res = -ENOMEM;
+		goto out;
+	}
+
+	skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+				      CRYPTO_TFM_REQ_MAY_SLEEP,
+				      crypto_req_done, &wait);
+	res = crypto_skcipher_setkey(tfm, paes_key, sizeof(paes_key));
+	if (res < 0)
+		goto out;
+
+	sg_init_one(&src_sg, in, AES_KEYSIZE_128);
+	sg_init_one(&dst_sg, out, AES_KEYSIZE_128);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, AES_KEYSIZE_128,
+				   NULL);
+
+	if (do_encrypt)
+		res = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+	else
+		res = crypto_wait_req(crypto_skcipher_decrypt(req), &wait);
+
+out:
+	skcipher_request_free(req);
+	crypto_free_skcipher(tfm);
+
+	return res;
+}
+
+static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce,
+			  bool do_encrypt)
+{
+	struct aead_request *aead_req = NULL;
+	struct scatterlist src_sg, dst_sg;
+	struct crypto_aead *aead;
+	int ret;
+	DECLARE_CRYPTO_WAIT(wait);
+
+	aead = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(aead)) {
+		ret = PTR_ERR(aead);
+		goto out;
+	}
+
+	ret = crypto_aead_setauthsize(aead, DCP_BLOB_AUTHLEN);
+	if (ret < 0) {
+		pr_err("Can't set crypto auth tag len: %d\n", ret);
+		goto free_aead;
+	}
+
+	aead_req = aead_request_alloc(aead, GFP_KERNEL);
+	if (!aead_req) {
+		ret = -ENOMEM;
+		goto free_aead;
+	}
+
+	sg_init_one(&src_sg, in, len);
+	if (do_encrypt) {
+		/*
+		 * If we encrypt our buffer has extra space for the auth tag.
+		 */
+		sg_init_one(&dst_sg, out, len + DCP_BLOB_AUTHLEN);
+	} else {
+		sg_init_one(&dst_sg, out, len);
+	}
+
+	aead_request_set_crypt(aead_req, &src_sg, &dst_sg, len, nonce);
+	aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				  crypto_req_done, &wait);
+	aead_request_set_ad(aead_req, 0);
+
+	if (crypto_aead_setkey(aead, key, AES_KEYSIZE_128)) {
+		pr_err("Can't set crypto AEAD key\n");
+		ret = -EINVAL;
+		goto free_req;
+	}
+
+	if (do_encrypt)
+		ret = crypto_wait_req(crypto_aead_encrypt(aead_req), &wait);
+	else
+		ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &wait);
+
+free_req:
+	aead_request_free(aead_req);
+free_aead:
+	crypto_free_aead(aead);
+out:
+	return ret;
+}
+
+static int decrypt_blob_key(u8 *encrypted_key, u8 *plain_key)
+{
+	return do_dcp_crypto(encrypted_key, plain_key, false);
+}
+
+static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key)
+{
+	return do_dcp_crypto(plain_key, encrypted_key, true);
+}
+
+static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)
+{
+	struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
+	size_t blen;
+	int ret;
+	u8 *plain_blob_key;
+
+	blen = calc_blob_len(p->key_len);
+	if (blen > MAX_BLOB_SIZE)
+		return -E2BIG;
+
+	plain_blob_key = kmalloc(AES_KEYSIZE_128, GFP_KERNEL);
+	if (!plain_blob_key)
+		return -ENOMEM;
+
+	b->fmt_version = DCP_BLOB_VERSION;
+	get_random_bytes(b->nonce, AES_KEYSIZE_128);
+	get_random_bytes(plain_blob_key, AES_KEYSIZE_128);
+
+	ret = do_aead_crypto(p->key, b->payload, p->key_len, plain_blob_key,
+			     b->nonce, true);
+	if (ret) {
+		pr_err("Unable to encrypt blob payload: %i\n", ret);
+		goto out;
+	}
+
+	ret = encrypt_blob_key(plain_blob_key, b->blob_key);
+	if (ret) {
+		pr_err("Unable to encrypt blob key: %i\n", ret);
+		goto out;
+	}
+
+	put_unaligned_le32(p->key_len, &b->payload_len);
+	p->blob_len = blen;
+	ret = 0;
+
+out:
+	memzero_explicit(plain_blob_key, AES_KEYSIZE_128);
+	kfree(plain_blob_key);
+
+	return ret;
+}
+
+static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
+{
+	struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
+	size_t blen;
+	int ret;
+	u8 *plain_blob_key = NULL;
+
+	if (b->fmt_version != DCP_BLOB_VERSION) {
+		pr_err("DCP blob has bad version: %i, expected %i\n",
+		       b->fmt_version, DCP_BLOB_VERSION);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	p->key_len = le32_to_cpu(b->payload_len);
+	if (p->key_len < MIN_KEY_SIZE || p->key_len > MAX_KEY_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	blen = calc_blob_len(p->key_len);
+	if (blen != p->blob_len) {
+		pr_err("DCP blob has bad length: %zu != %u\n", blen,
+		       p->blob_len);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	plain_blob_key = kmalloc(AES_KEYSIZE_128, GFP_KERNEL);
+	if (!plain_blob_key) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = decrypt_blob_key(b->blob_key, plain_blob_key);
+	if (ret) {
+		pr_err("Unable to decrypt blob key: %i\n", ret);
+		goto out;
+	}
+
+	ret = do_aead_crypto(b->payload, p->key, p->key_len + DCP_BLOB_AUTHLEN,
+			     plain_blob_key, b->nonce, false);
+	if (ret) {
+		pr_err("Unwrap of DCP payload failed: %i\n", ret);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	if (plain_blob_key) {
+		memzero_explicit(plain_blob_key, AES_KEYSIZE_128);
+		kfree(plain_blob_key);
+	}
+
+	return ret;
+}
+
+static int test_for_zero_key(void)
+{
+	/*
+	 * Encrypting a plaintext of all 0x55 bytes will yield
+	 * this ciphertext in case the DCP test key is used.
+	 */
+	static const u8 bad[] = {0x9a, 0xda, 0xe0, 0x54, 0xf6, 0x3d, 0xfa, 0xff,
+				 0x5e, 0xa1, 0x8e, 0x45, 0xed, 0xf6, 0xea, 0x6f};
+	void *buf = NULL;
+	int ret = 0;
+
+	if (skip_zk_test)
+		goto out;
+
+	buf = kmalloc(AES_BLOCK_SIZE, GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memset(buf, 0x55, AES_BLOCK_SIZE);
+
+	ret = do_dcp_crypto(buf, buf, true);
+	if (ret)
+		goto out;
+
+	if (memcmp(buf, bad, AES_BLOCK_SIZE) == 0) {
+		pr_warn("Device neither in secure nor trusted mode!\n");
+		ret = -EINVAL;
+	}
+out:
+	kfree(buf);
+	return ret;
+}
+
+static int trusted_dcp_init(void)
+{
+	int ret;
+
+	if (use_otp_key)
+		pr_info("Using DCP OTP key\n");
+
+	ret = test_for_zero_key();
+	if (ret) {
+		pr_warn("Test for zero'ed keys failed: %i\n", ret);
+
+		return -EINVAL;
+	}
+
+	return register_key_type(&key_type_trusted);
+}
+
+static void trusted_dcp_exit(void)
+{
+	unregister_key_type(&key_type_trusted);
+}
+
+struct trusted_key_ops dcp_trusted_key_ops = {
+	.exit = trusted_dcp_exit,
+	.init = trusted_dcp_init,
+	.seal = trusted_dcp_seal,
+	.unseal = trusted_dcp_unseal,
+	.migratable = 0,
+};
diff --git a/security/keys/trusted-keys/trusted_pkwm.c b/security/keys/trusted-keys/trusted_pkwm.c
new file mode 100644
index 000000000..bf42c6679
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_pkwm.c
@@ -0,0 +1,190 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 IBM Corporation, Srish Srinivasan <ssrish@linux.ibm.com>
+ */
+
+#include <keys/trusted_pkwm.h>
+#include <keys/trusted-type.h>
+#include <linux/build_bug.h>
+#include <linux/key-type.h>
+#include <linux/parser.h>
+#include <asm/plpks.h>
+
+enum {
+	Opt_err,
+	Opt_wrap_flags,
+};
+
+static const match_table_t key_tokens = {
+	{Opt_wrap_flags, "wrap_flags=%s"},
+	{Opt_err, NULL}
+};
+
+static int getoptions(char *datablob, struct trusted_key_options *opt)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *p = datablob;
+	int token;
+	int res;
+	u16 wrap_flags;
+	unsigned long token_mask = 0;
+	struct trusted_pkwm_options *pkwm;
+
+	if (!datablob)
+		return 0;
+
+	pkwm = opt->private;
+
+	while ((p = strsep(&datablob, " \t"))) {
+		if (*p == '\0' || *p == ' ' || *p == '\t')
+			continue;
+
+		token = match_token(p, key_tokens, args);
+		if (test_and_set_bit(token, &token_mask))
+			return -EINVAL;
+
+		switch (token) {
+		case Opt_wrap_flags:
+			res = kstrtou16(args[0].from, 16, &wrap_flags);
+			if (res < 0 || wrap_flags > 2)
+				return -EINVAL;
+			pkwm->wrap_flags = wrap_flags;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static struct trusted_key_options *trusted_options_alloc(void)
+{
+	struct trusted_key_options *options;
+	struct trusted_pkwm_options *pkwm;
+
+	options = kzalloc_obj(*options);
+
+	if (options) {
+		pkwm = kzalloc_obj(*pkwm);
+
+		if (!pkwm) {
+			kfree_sensitive(options);
+			options = NULL;
+		} else {
+			options->private = pkwm;
+		}
+	}
+
+	return options;
+}
+
+static int trusted_pkwm_seal(struct trusted_key_payload *p, char *datablob)
+{
+	struct trusted_key_options *options = NULL;
+	struct trusted_pkwm_options *pkwm = NULL;
+	u8 *input_buf, *output_buf;
+	u32 output_len, input_len;
+	int rc;
+
+	options = trusted_options_alloc();
+
+	if (!options)
+		return -ENOMEM;
+
+	rc = getoptions(datablob, options);
+	if (rc < 0)
+		goto out;
+	dump_options(options);
+
+	input_len = p->key_len;
+	input_buf = kmalloc(ALIGN(input_len, 4096), GFP_KERNEL);
+	if (!input_buf) {
+		pr_err("Input buffer allocation failed. Returning -ENOMEM.");
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	memcpy(input_buf, p->key, p->key_len);
+
+	pkwm = options->private;
+
+	rc = plpks_wrap_object(&input_buf, input_len, pkwm->wrap_flags,
+			       &output_buf, &output_len);
+	if (!rc) {
+		memcpy(p->blob, output_buf, output_len);
+		p->blob_len = output_len;
+		dump_payload(p);
+	} else {
+		pr_err("Wrapping of payload key failed: %d\n", rc);
+	}
+
+	kfree(input_buf);
+	kfree(output_buf);
+
+out:
+	kfree_sensitive(options->private);
+	kfree_sensitive(options);
+	return rc;
+}
+
+static int trusted_pkwm_unseal(struct trusted_key_payload *p, char *datablob)
+{
+	u8 *input_buf, *output_buf;
+	u32 input_len, output_len;
+	int rc;
+
+	input_len = p->blob_len;
+	input_buf = kmalloc(ALIGN(input_len, 4096), GFP_KERNEL);
+	if (!input_buf) {
+		pr_err("Input buffer allocation failed. Returning -ENOMEM.");
+		return -ENOMEM;
+	}
+
+	memcpy(input_buf, p->blob, p->blob_len);
+
+	rc = plpks_unwrap_object(&input_buf, input_len, &output_buf,
+				 &output_len);
+	if (!rc) {
+		memcpy(p->key, output_buf, output_len);
+		p->key_len = output_len;
+		dump_payload(p);
+	} else {
+		pr_err("Unwrapping of payload failed: %d\n", rc);
+	}
+
+	kfree(input_buf);
+	kfree(output_buf);
+
+	return rc;
+}
+
+static int trusted_pkwm_init(void)
+{
+	int ret;
+
+	if (!plpks_wrapping_is_supported()) {
+		pr_err("H_PKS_WRAP_OBJECT interface not supported\n");
+		return -ENODEV;
+	}
+
+	ret = plpks_gen_wrapping_key();
+	if (ret) {
+		pr_err("Failed to generate default wrapping key\n");
+		return -EINVAL;
+	}
+
+	return register_key_type(&key_type_trusted);
+}
+
+static void trusted_pkwm_exit(void)
+{
+	unregister_key_type(&key_type_trusted);
+}
+
+struct trusted_key_ops pkwm_trusted_key_ops = {
+	.migratable = 0, /* non-migratable */
+	.init = trusted_pkwm_init,
+	.seal = trusted_pkwm_seal,
+	.unseal = trusted_pkwm_unseal,
+	.exit = trusted_pkwm_exit,
+};
diff --git a/security/keys/trusted-keys/trusted_tee.c b/security/keys/trusted-keys/trusted_tee.c
new file mode 100644
index 000000000..6e465c8be
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_tee.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2021 Linaro Ltd.
+ *
+ * Author:
+ * Sumit Garg <sumit.garg@linaro.org>
+ */
+
+#include <linux/err.h>
+#include <linux/key-type.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tee_drv.h>
+#include <linux/uuid.h>
+
+#include <keys/trusted_tee.h>
+
+#define DRIVER_NAME "trusted-key-tee"
+
+/*
+ * Get random data for symmetric key
+ *
+ * [out]     memref[0]        Random data
+ */
+#define TA_CMD_GET_RANDOM	0x0
+
+/*
+ * Seal trusted key using hardware unique key
+ *
+ * [in]      memref[0]        Plain key
+ * [out]     memref[1]        Sealed key datablob
+ */
+#define TA_CMD_SEAL		0x1
+
+/*
+ * Unseal trusted key using hardware unique key
+ *
+ * [in]      memref[0]        Sealed key datablob
+ * [out]     memref[1]        Plain key
+ */
+#define TA_CMD_UNSEAL		0x2
+
+/**
+ * struct trusted_key_tee_private - TEE Trusted key private data
+ * @dev:		TEE based Trusted key device.
+ * @ctx:		TEE context handler.
+ * @session_id:		Trusted key TA session identifier.
+ * @shm_pool:		Memory pool shared with TEE device.
+ */
+struct trusted_key_tee_private {
+	struct device *dev;
+	struct tee_context *ctx;
+	u32 session_id;
+	struct tee_shm *shm_pool;
+};
+
+static struct trusted_key_tee_private pvt_data;
+
+/*
+ * Have the TEE seal(encrypt) the symmetric key
+ */
+static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob)
+{
+	int ret;
+	struct tee_ioctl_invoke_arg inv_arg;
+	struct tee_param param[4];
+	struct tee_shm *reg_shm = NULL;
+
+	memset(&inv_arg, 0, sizeof(inv_arg));
+	memset(&param, 0, sizeof(param));
+
+	reg_shm = tee_shm_register_kernel_buf(pvt_data.ctx, p->key,
+					      sizeof(p->key) + sizeof(p->blob));
+	if (IS_ERR(reg_shm)) {
+		dev_err(pvt_data.dev, "shm register failed\n");
+		return PTR_ERR(reg_shm);
+	}
+
+	inv_arg.func = TA_CMD_SEAL;
+	inv_arg.session = pvt_data.session_id;
+	inv_arg.num_params = 4;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+	param[0].u.memref.shm = reg_shm;
+	param[0].u.memref.size = p->key_len;
+	param[0].u.memref.shm_offs = 0;
+	param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+	param[1].u.memref.shm = reg_shm;
+	param[1].u.memref.size = sizeof(p->blob);
+	param[1].u.memref.shm_offs = sizeof(p->key);
+
+	ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+	if ((ret < 0) || (inv_arg.ret != 0)) {
+		dev_err(pvt_data.dev, "TA_CMD_SEAL invoke err: %x\n",
+			inv_arg.ret);
+		ret = -EFAULT;
+	} else {
+		p->blob_len = param[1].u.memref.size;
+	}
+
+	tee_shm_free(reg_shm);
+
+	return ret;
+}
+
+/*
+ * Have the TEE unseal(decrypt) the symmetric key
+ */
+static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob)
+{
+	int ret;
+	struct tee_ioctl_invoke_arg inv_arg;
+	struct tee_param param[4];
+	struct tee_shm *reg_shm = NULL;
+
+	memset(&inv_arg, 0, sizeof(inv_arg));
+	memset(&param, 0, sizeof(param));
+
+	reg_shm = tee_shm_register_kernel_buf(pvt_data.ctx, p->key,
+					      sizeof(p->key) + sizeof(p->blob));
+	if (IS_ERR(reg_shm)) {
+		dev_err(pvt_data.dev, "shm register failed\n");
+		return PTR_ERR(reg_shm);
+	}
+
+	inv_arg.func = TA_CMD_UNSEAL;
+	inv_arg.session = pvt_data.session_id;
+	inv_arg.num_params = 4;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+	param[0].u.memref.shm = reg_shm;
+	param[0].u.memref.size = p->blob_len;
+	param[0].u.memref.shm_offs = sizeof(p->key);
+	param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+	param[1].u.memref.shm = reg_shm;
+	param[1].u.memref.size = sizeof(p->key);
+	param[1].u.memref.shm_offs = 0;
+
+	ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+	if ((ret < 0) || (inv_arg.ret != 0)) {
+		dev_err(pvt_data.dev, "TA_CMD_UNSEAL invoke err: %x\n",
+			inv_arg.ret);
+		ret = -EFAULT;
+	} else {
+		p->key_len = param[1].u.memref.size;
+	}
+
+	tee_shm_free(reg_shm);
+
+	return ret;
+}
+
+/*
+ * Have the TEE generate random symmetric key
+ */
+static int trusted_tee_get_random(unsigned char *key, size_t key_len)
+{
+	int ret;
+	struct tee_ioctl_invoke_arg inv_arg;
+	struct tee_param param[4];
+	struct tee_shm *reg_shm = NULL;
+
+	memset(&inv_arg, 0, sizeof(inv_arg));
+	memset(&param, 0, sizeof(param));
+
+	reg_shm = tee_shm_register_kernel_buf(pvt_data.ctx, key, key_len);
+	if (IS_ERR(reg_shm)) {
+		dev_err(pvt_data.dev, "key shm register failed\n");
+		return PTR_ERR(reg_shm);
+	}
+
+	inv_arg.func = TA_CMD_GET_RANDOM;
+	inv_arg.session = pvt_data.session_id;
+	inv_arg.num_params = 4;
+
+	param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+	param[0].u.memref.shm = reg_shm;
+	param[0].u.memref.size = key_len;
+	param[0].u.memref.shm_offs = 0;
+
+	ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+	if ((ret < 0) || (inv_arg.ret != 0)) {
+		dev_err(pvt_data.dev, "TA_CMD_GET_RANDOM invoke err: %x\n",
+			inv_arg.ret);
+		ret = -EFAULT;
+	} else {
+		ret = param[0].u.memref.size;
+	}
+
+	tee_shm_free(reg_shm);
+
+	return ret;
+}
+
+static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
+{
+	if (ver->impl_id == TEE_IMPL_ID_OPTEE &&
+	    ver->gen_caps & TEE_GEN_CAP_REG_MEM)
+		return 1;
+	else
+		return 0;
+}
+
+static int trusted_key_probe(struct tee_client_device *rng_device)
+{
+	struct device *dev = &rng_device->dev;
+	int ret;
+	struct tee_ioctl_open_session_arg sess_arg;
+
+	memset(&sess_arg, 0, sizeof(sess_arg));
+
+	pvt_data.ctx = tee_client_open_context(NULL, optee_ctx_match, NULL,
+					       NULL);
+	if (IS_ERR(pvt_data.ctx))
+		return -ENODEV;
+
+	memcpy(sess_arg.uuid, rng_device->id.uuid.b, TEE_IOCTL_UUID_LEN);
+	sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL;
+	sess_arg.num_params = 0;
+
+	ret = tee_client_open_session(pvt_data.ctx, &sess_arg, NULL);
+	if ((ret < 0) || (sess_arg.ret != 0)) {
+		dev_err(dev, "tee_client_open_session failed, err: %x\n",
+			sess_arg.ret);
+		ret = -EINVAL;
+		goto out_ctx;
+	}
+	pvt_data.session_id = sess_arg.session;
+
+	ret = register_key_type(&key_type_trusted);
+	if (ret < 0)
+		goto out_sess;
+
+	pvt_data.dev = dev;
+
+	return 0;
+
+out_sess:
+	tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
+out_ctx:
+	tee_client_close_context(pvt_data.ctx);
+
+	return ret;
+}
+
+static void trusted_key_remove(struct tee_client_device *dev)
+{
+	unregister_key_type(&key_type_trusted);
+	tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
+	tee_client_close_context(pvt_data.ctx);
+}
+
+static const struct tee_client_device_id trusted_key_id_table[] = {
+	{UUID_INIT(0xf04a0fe7, 0x1f5d, 0x4b9b,
+		   0xab, 0xf7, 0x61, 0x9b, 0x85, 0xb4, 0xce, 0x8c)},
+	{}
+};
+MODULE_DEVICE_TABLE(tee, trusted_key_id_table);
+
+static struct tee_client_driver trusted_key_driver = {
+	.probe		= trusted_key_probe,
+	.remove		= trusted_key_remove,
+	.id_table	= trusted_key_id_table,
+	.driver		= {
+		.name		= DRIVER_NAME,
+	},
+};
+
+static int trusted_tee_init(void)
+{
+	return tee_client_driver_register(&trusted_key_driver);
+}
+
+static void trusted_tee_exit(void)
+{
+	tee_client_driver_unregister(&trusted_key_driver);
+}
+
+struct trusted_key_ops trusted_key_tee_ops = {
+	.migratable = 0, /* non-migratable */
+	.init = trusted_tee_init,
+	.seal = trusted_tee_seal,
+	.unseal = trusted_tee_unseal,
+	.get_random = trusted_tee_get_random,
+	.exit = trusted_tee_exit,
+};
diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c
new file mode 100644
index 000000000..bf0bf7f36
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_tpm1.c
@@ -0,0 +1,998 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (c) 2019-2021, Linaro Limited
+ *
+ * See Documentation/security/keys/trusted-encrypted.rst
+ */
+
+#include <crypto/hash_info.h>
+#include <crypto/sha1.h>
+#include <crypto/utils.h>
+#include <linux/hex.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/parser.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <keys/trusted-type.h>
+#include <linux/key-type.h>
+#include <linux/tpm.h>
+
+#include <keys/trusted_tpm.h>
+
+static struct tpm_chip *chip;
+static struct tpm_digest *digests;
+
+/* implementation specific TPM constants */
+#define TPM_SIZE_OFFSET			2
+#define TPM_RETURN_OFFSET		6
+#define TPM_DATA_OFFSET			10
+
+#define LOAD32(buffer, offset)	(ntohl(*(uint32_t *)&buffer[offset]))
+#define LOAD32N(buffer, offset)	(*(uint32_t *)&buffer[offset])
+#define LOAD16(buffer, offset)	(ntohs(*(uint16_t *)&buffer[offset]))
+
+struct osapsess {
+	uint32_t handle;
+	unsigned char secret[SHA1_DIGEST_SIZE];
+	unsigned char enonce[TPM_NONCE_SIZE];
+};
+
+/* discrete values, but have to store in uint16_t for TPM use */
+enum {
+	SEAL_keytype = 1,
+	SRK_keytype = 4
+};
+
+#ifdef CONFIG_TRUSTED_KEYS_DEBUG
+static inline void dump_options(struct trusted_key_options *o)
+{
+	if (!trusted_debug)
+		return;
+
+	pr_debug("sealing key type %d\n", o->keytype);
+	pr_debug("sealing key handle %0X\n", o->keyhandle);
+	pr_debug("pcrlock %d\n", o->pcrlock);
+	pr_debug("pcrinfo %d\n", o->pcrinfo_len);
+	print_hex_dump_debug("pcrinfo ", DUMP_PREFIX_NONE,
+			     16, 1, o->pcrinfo, o->pcrinfo_len, 0);
+}
+
+static inline void dump_sess(struct osapsess *s)
+{
+	if (!trusted_debug)
+		return;
+
+	print_hex_dump_debug("trusted-key: handle ", DUMP_PREFIX_NONE,
+			     16, 1, &s->handle, 4, 0);
+	pr_debug("secret:\n");
+	print_hex_dump_debug("", DUMP_PREFIX_NONE,
+			     16, 1, &s->secret, SHA1_DIGEST_SIZE, 0);
+	pr_debug("trusted-key: enonce:\n");
+	print_hex_dump_debug("", DUMP_PREFIX_NONE,
+			     16, 1, &s->enonce, SHA1_DIGEST_SIZE, 0);
+}
+
+static inline void dump_tpm_buf(unsigned char *buf)
+{
+	int len;
+
+	if (!trusted_debug)
+		return;
+	pr_debug("\ntpm buffer\n");
+	len = LOAD32(buf, TPM_SIZE_OFFSET);
+	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, buf, len, 0);
+}
+#else
+static inline void dump_options(struct trusted_key_options *o)
+{
+}
+
+static inline void dump_sess(struct osapsess *s)
+{
+}
+
+static inline void dump_tpm_buf(unsigned char *buf)
+{
+}
+#endif
+
+static int TSS_rawhmac(unsigned char *digest, const unsigned char *key,
+		       unsigned int keylen, ...)
+{
+	struct hmac_sha1_ctx hmac_ctx;
+	va_list argp;
+	unsigned int dlen;
+	unsigned char *data;
+	int ret = 0;
+
+	hmac_sha1_init_usingrawkey(&hmac_ctx, key, keylen);
+
+	va_start(argp, keylen);
+	for (;;) {
+		dlen = va_arg(argp, unsigned int);
+		if (dlen == 0)
+			break;
+		data = va_arg(argp, unsigned char *);
+		if (data == NULL) {
+			ret = -EINVAL;
+			break;
+		}
+		hmac_sha1_update(&hmac_ctx, data, dlen);
+	}
+	va_end(argp);
+	if (!ret)
+		hmac_sha1_final(&hmac_ctx, digest);
+	return ret;
+}
+
+/*
+ * calculate authorization info fields to send to TPM
+ */
+static int TSS_authhmac(unsigned char *digest, const unsigned char *key,
+			unsigned int keylen, unsigned char *h1,
+			unsigned char *h2, unsigned int h3, ...)
+{
+	unsigned char paramdigest[SHA1_DIGEST_SIZE];
+	struct sha1_ctx sha_ctx;
+	unsigned int dlen;
+	unsigned char *data;
+	unsigned char c;
+	int ret = 0;
+	va_list argp;
+
+	if (!chip)
+		return -ENODEV;
+
+	c = !!h3;
+	sha1_init(&sha_ctx);
+	va_start(argp, h3);
+	for (;;) {
+		dlen = va_arg(argp, unsigned int);
+		if (dlen == 0)
+			break;
+		data = va_arg(argp, unsigned char *);
+		if (!data) {
+			ret = -EINVAL;
+			break;
+		}
+		sha1_update(&sha_ctx, data, dlen);
+	}
+	va_end(argp);
+	if (!ret)
+		sha1_final(&sha_ctx, paramdigest);
+	if (!ret)
+		ret = TSS_rawhmac(digest, key, keylen, SHA1_DIGEST_SIZE,
+				  paramdigest, TPM_NONCE_SIZE, h1,
+				  TPM_NONCE_SIZE, h2, 1, &c, 0, 0);
+	return ret;
+}
+
+/*
+ * verify the AUTH1_COMMAND (Seal) result from TPM
+ */
+static int TSS_checkhmac1(unsigned char *buffer,
+			  const uint32_t command,
+			  const unsigned char *ononce,
+			  const unsigned char *key,
+			  unsigned int keylen, ...)
+{
+	uint32_t bufsize;
+	uint16_t tag;
+	uint32_t ordinal;
+	uint32_t result;
+	unsigned char *enonce;
+	unsigned char *continueflag;
+	unsigned char *authdata;
+	unsigned char testhmac[SHA1_DIGEST_SIZE];
+	unsigned char paramdigest[SHA1_DIGEST_SIZE];
+	struct sha1_ctx sha_ctx;
+	unsigned int dlen;
+	unsigned int dpos;
+	va_list argp;
+	int ret;
+
+	if (!chip)
+		return -ENODEV;
+
+	bufsize = LOAD32(buffer, TPM_SIZE_OFFSET);
+	tag = LOAD16(buffer, 0);
+	ordinal = command;
+	result = LOAD32N(buffer, TPM_RETURN_OFFSET);
+	if (tag == TPM_TAG_RSP_COMMAND)
+		return 0;
+	if (tag != TPM_TAG_RSP_AUTH1_COMMAND)
+		return -EINVAL;
+	authdata = buffer + bufsize - SHA1_DIGEST_SIZE;
+	continueflag = authdata - 1;
+	enonce = continueflag - TPM_NONCE_SIZE;
+
+	sha1_init(&sha_ctx);
+	sha1_update(&sha_ctx, (const u8 *)&result, sizeof(result));
+	sha1_update(&sha_ctx, (const u8 *)&ordinal, sizeof(ordinal));
+	va_start(argp, keylen);
+	for (;;) {
+		dlen = va_arg(argp, unsigned int);
+		if (dlen == 0)
+			break;
+		dpos = va_arg(argp, unsigned int);
+		sha1_update(&sha_ctx, buffer + dpos, dlen);
+	}
+	va_end(argp);
+	sha1_final(&sha_ctx, paramdigest);
+
+	ret = TSS_rawhmac(testhmac, key, keylen, SHA1_DIGEST_SIZE, paramdigest,
+			  TPM_NONCE_SIZE, enonce, TPM_NONCE_SIZE, ononce,
+			  1, continueflag, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	if (crypto_memneq(testhmac, authdata, SHA1_DIGEST_SIZE))
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * verify the AUTH2_COMMAND (unseal) result from TPM
+ */
+static int TSS_checkhmac2(unsigned char *buffer,
+			  const uint32_t command,
+			  const unsigned char *ononce,
+			  const unsigned char *key1,
+			  unsigned int keylen1,
+			  const unsigned char *key2,
+			  unsigned int keylen2, ...)
+{
+	uint32_t bufsize;
+	uint16_t tag;
+	uint32_t ordinal;
+	uint32_t result;
+	unsigned char *enonce1;
+	unsigned char *continueflag1;
+	unsigned char *authdata1;
+	unsigned char *enonce2;
+	unsigned char *continueflag2;
+	unsigned char *authdata2;
+	unsigned char testhmac1[SHA1_DIGEST_SIZE];
+	unsigned char testhmac2[SHA1_DIGEST_SIZE];
+	unsigned char paramdigest[SHA1_DIGEST_SIZE];
+	struct sha1_ctx sha_ctx;
+	unsigned int dlen;
+	unsigned int dpos;
+	va_list argp;
+	int ret;
+
+	bufsize = LOAD32(buffer, TPM_SIZE_OFFSET);
+	tag = LOAD16(buffer, 0);
+	ordinal = command;
+	result = LOAD32N(buffer, TPM_RETURN_OFFSET);
+
+	if (tag == TPM_TAG_RSP_COMMAND)
+		return 0;
+	if (tag != TPM_TAG_RSP_AUTH2_COMMAND)
+		return -EINVAL;
+	authdata1 = buffer + bufsize - (SHA1_DIGEST_SIZE + 1
+			+ SHA1_DIGEST_SIZE + SHA1_DIGEST_SIZE);
+	authdata2 = buffer + bufsize - (SHA1_DIGEST_SIZE);
+	continueflag1 = authdata1 - 1;
+	continueflag2 = authdata2 - 1;
+	enonce1 = continueflag1 - TPM_NONCE_SIZE;
+	enonce2 = continueflag2 - TPM_NONCE_SIZE;
+
+	sha1_init(&sha_ctx);
+	sha1_update(&sha_ctx, (const u8 *)&result, sizeof(result));
+	sha1_update(&sha_ctx, (const u8 *)&ordinal, sizeof(ordinal));
+
+	va_start(argp, keylen2);
+	for (;;) {
+		dlen = va_arg(argp, unsigned int);
+		if (dlen == 0)
+			break;
+		dpos = va_arg(argp, unsigned int);
+		sha1_update(&sha_ctx, buffer + dpos, dlen);
+	}
+	va_end(argp);
+	sha1_final(&sha_ctx, paramdigest);
+
+	ret = TSS_rawhmac(testhmac1, key1, keylen1, SHA1_DIGEST_SIZE,
+			  paramdigest, TPM_NONCE_SIZE, enonce1,
+			  TPM_NONCE_SIZE, ononce, 1, continueflag1, 0, 0);
+	if (ret < 0)
+		return ret;
+	if (crypto_memneq(testhmac1, authdata1, SHA1_DIGEST_SIZE))
+		return -EINVAL;
+	ret = TSS_rawhmac(testhmac2, key2, keylen2, SHA1_DIGEST_SIZE,
+			  paramdigest, TPM_NONCE_SIZE, enonce2,
+			  TPM_NONCE_SIZE, ononce, 1, continueflag2, 0, 0);
+	if (ret < 0)
+		return ret;
+	if (crypto_memneq(testhmac2, authdata2, SHA1_DIGEST_SIZE))
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * For key specific tpm requests, we will generate and send our
+ * own TPM command packets using the drivers send function.
+ */
+static int trusted_tpm_send(struct tpm_buf *buf)
+{
+	int rc;
+
+	if (!chip)
+		return -ENODEV;
+
+	rc = tpm_try_get_ops(chip);
+	if (rc)
+		return rc;
+
+	dump_tpm_buf(buf->data);
+	rc = tpm_transmit_cmd(chip, buf, 4, "sending data");
+	dump_tpm_buf(buf->data);
+
+	if (rc > 0)
+		/* TPM error */
+		rc = -EPERM;
+
+	tpm_put_ops(chip);
+	return rc;
+}
+
+/*
+ * Lock a trusted key, by extending a selected PCR.
+ *
+ * Prevents a trusted key that is sealed to PCRs from being accessed.
+ * This uses the tpm driver's extend function.
+ */
+static int pcrlock(const int pcrnum)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return tpm_pcr_extend(chip, pcrnum, digests) ? -EINVAL : 0;
+}
+
+/*
+ * Create an object specific authorisation protocol (OSAP) session
+ */
+static int osap(struct tpm_buf *tb, struct osapsess *s,
+		const unsigned char *key, uint16_t type, uint32_t handle)
+{
+	unsigned char enonce[TPM_NONCE_SIZE];
+	unsigned char ononce[TPM_NONCE_SIZE];
+	int ret;
+
+	ret = tpm_get_random(chip, ononce, TPM_NONCE_SIZE);
+	if (ret < 0)
+		return ret;
+
+	if (ret != TPM_NONCE_SIZE)
+		return -EIO;
+
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OSAP);
+	tpm_buf_append_u16(tb, type);
+	tpm_buf_append_u32(tb, handle);
+	tpm_buf_append(tb, ononce, TPM_NONCE_SIZE);
+
+	ret = trusted_tpm_send(tb);
+	if (ret < 0)
+		return ret;
+
+	s->handle = LOAD32(tb->data, TPM_DATA_OFFSET);
+	memcpy(s->enonce, &(tb->data[TPM_DATA_OFFSET + sizeof(uint32_t)]),
+	       TPM_NONCE_SIZE);
+	memcpy(enonce, &(tb->data[TPM_DATA_OFFSET + sizeof(uint32_t) +
+				  TPM_NONCE_SIZE]), TPM_NONCE_SIZE);
+	return TSS_rawhmac(s->secret, key, SHA1_DIGEST_SIZE, TPM_NONCE_SIZE,
+			   enonce, TPM_NONCE_SIZE, ononce, 0, 0);
+}
+
+/*
+ * Create an object independent authorisation protocol (oiap) session
+ */
+static int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce)
+{
+	int ret;
+
+	if (!chip)
+		return -ENODEV;
+
+	tpm_buf_reset(tb, TPM_TAG_RQU_COMMAND, TPM_ORD_OIAP);
+	ret = trusted_tpm_send(tb);
+	if (ret < 0)
+		return ret;
+
+	*handle = LOAD32(tb->data, TPM_DATA_OFFSET);
+	memcpy(nonce, &tb->data[TPM_DATA_OFFSET + sizeof(uint32_t)],
+	       TPM_NONCE_SIZE);
+	return 0;
+}
+
+struct tpm_digests {
+	unsigned char encauth[SHA1_DIGEST_SIZE];
+	unsigned char pubauth[SHA1_DIGEST_SIZE];
+	unsigned char xorwork[SHA1_DIGEST_SIZE * 2];
+	unsigned char xorhash[SHA1_DIGEST_SIZE];
+	unsigned char nonceodd[TPM_NONCE_SIZE];
+};
+
+/*
+ * Have the TPM seal(encrypt) the trusted key, possibly based on
+ * Platform Configuration Registers (PCRs). AUTH1 for sealing key.
+ */
+static int tpm_seal(struct tpm_buf *tb, uint16_t keytype,
+		    uint32_t keyhandle, const unsigned char *keyauth,
+		    const unsigned char *data, uint32_t datalen,
+		    unsigned char *blob, uint32_t *bloblen,
+		    const unsigned char *blobauth,
+		    const unsigned char *pcrinfo, uint32_t pcrinfosize)
+{
+	struct osapsess sess;
+	struct tpm_digests *td;
+	unsigned char cont;
+	uint32_t ordinal;
+	uint32_t pcrsize;
+	uint32_t datsize;
+	int sealinfosize;
+	int encdatasize;
+	int storedsize;
+	int ret;
+	int i;
+
+	/* alloc some work space for all the hashes */
+	td = kmalloc_obj(*td);
+	if (!td)
+		return -ENOMEM;
+
+	/* get session for sealing key */
+	ret = osap(tb, &sess, keyauth, keytype, keyhandle);
+	if (ret < 0)
+		goto out;
+	dump_sess(&sess);
+
+	/* calculate encrypted authorization value */
+	memcpy(td->xorwork, sess.secret, SHA1_DIGEST_SIZE);
+	memcpy(td->xorwork + SHA1_DIGEST_SIZE, sess.enonce, SHA1_DIGEST_SIZE);
+	sha1(td->xorwork, SHA1_DIGEST_SIZE * 2, td->xorhash);
+
+	ret = tpm_get_random(chip, td->nonceodd, TPM_NONCE_SIZE);
+	if (ret < 0)
+		goto out;
+
+	if (ret != TPM_NONCE_SIZE) {
+		ret = -EIO;
+		goto out;
+	}
+
+	ordinal = htonl(TPM_ORD_SEAL);
+	datsize = htonl(datalen);
+	pcrsize = htonl(pcrinfosize);
+	cont = 0;
+
+	/* encrypt data authorization key */
+	for (i = 0; i < SHA1_DIGEST_SIZE; ++i)
+		td->encauth[i] = td->xorhash[i] ^ blobauth[i];
+
+	/* calculate authorization HMAC value */
+	if (pcrinfosize == 0) {
+		/* no pcr info specified */
+		ret = TSS_authhmac(td->pubauth, sess.secret, SHA1_DIGEST_SIZE,
+				   sess.enonce, td->nonceodd, cont,
+				   sizeof(uint32_t), &ordinal, SHA1_DIGEST_SIZE,
+				   td->encauth, sizeof(uint32_t), &pcrsize,
+				   sizeof(uint32_t), &datsize, datalen, data, 0,
+				   0);
+	} else {
+		/* pcr info specified */
+		ret = TSS_authhmac(td->pubauth, sess.secret, SHA1_DIGEST_SIZE,
+				   sess.enonce, td->nonceodd, cont,
+				   sizeof(uint32_t), &ordinal, SHA1_DIGEST_SIZE,
+				   td->encauth, sizeof(uint32_t), &pcrsize,
+				   pcrinfosize, pcrinfo, sizeof(uint32_t),
+				   &datsize, datalen, data, 0, 0);
+	}
+	if (ret < 0)
+		goto out;
+
+	/* build and send the TPM request packet */
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH1_COMMAND, TPM_ORD_SEAL);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, td->encauth, SHA1_DIGEST_SIZE);
+	tpm_buf_append_u32(tb, pcrinfosize);
+	tpm_buf_append(tb, pcrinfo, pcrinfosize);
+	tpm_buf_append_u32(tb, datalen);
+	tpm_buf_append(tb, data, datalen);
+	tpm_buf_append_u32(tb, sess.handle);
+	tpm_buf_append(tb, td->nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, td->pubauth, SHA1_DIGEST_SIZE);
+
+	ret = trusted_tpm_send(tb);
+	if (ret < 0)
+		goto out;
+
+	/* calculate the size of the returned Blob */
+	sealinfosize = LOAD32(tb->data, TPM_DATA_OFFSET + sizeof(uint32_t));
+	encdatasize = LOAD32(tb->data, TPM_DATA_OFFSET + sizeof(uint32_t) +
+			     sizeof(uint32_t) + sealinfosize);
+	storedsize = sizeof(uint32_t) + sizeof(uint32_t) + sealinfosize +
+	    sizeof(uint32_t) + encdatasize;
+
+	/* check the HMAC in the response */
+	ret = TSS_checkhmac1(tb->data, ordinal, td->nonceodd, sess.secret,
+			     SHA1_DIGEST_SIZE, storedsize, TPM_DATA_OFFSET, 0,
+			     0);
+
+	/* copy the returned blob to caller */
+	if (!ret) {
+		memcpy(blob, tb->data + TPM_DATA_OFFSET, storedsize);
+		*bloblen = storedsize;
+	}
+out:
+	kfree_sensitive(td);
+	return ret;
+}
+
+/*
+ * use the AUTH2_COMMAND form of unseal, to authorize both key and blob
+ */
+static int tpm_unseal(struct tpm_buf *tb,
+		      uint32_t keyhandle, const unsigned char *keyauth,
+		      const unsigned char *blob, int bloblen,
+		      const unsigned char *blobauth,
+		      unsigned char *data, unsigned int *datalen)
+{
+	unsigned char nonceodd[TPM_NONCE_SIZE];
+	unsigned char enonce1[TPM_NONCE_SIZE];
+	unsigned char enonce2[TPM_NONCE_SIZE];
+	unsigned char authdata1[SHA1_DIGEST_SIZE];
+	unsigned char authdata2[SHA1_DIGEST_SIZE];
+	uint32_t authhandle1 = 0;
+	uint32_t authhandle2 = 0;
+	unsigned char cont = 0;
+	uint32_t ordinal;
+	int ret;
+
+	/* sessions for unsealing key and data */
+	ret = oiap(tb, &authhandle1, enonce1);
+	if (ret < 0) {
+		pr_info("oiap failed (%d)\n", ret);
+		return ret;
+	}
+	ret = oiap(tb, &authhandle2, enonce2);
+	if (ret < 0) {
+		pr_info("oiap failed (%d)\n", ret);
+		return ret;
+	}
+
+	ordinal = htonl(TPM_ORD_UNSEAL);
+	ret = tpm_get_random(chip, nonceodd, TPM_NONCE_SIZE);
+	if (ret < 0)
+		return ret;
+
+	if (ret != TPM_NONCE_SIZE) {
+		pr_info("tpm_get_random failed (%d)\n", ret);
+		return -EIO;
+	}
+	ret = TSS_authhmac(authdata1, keyauth, TPM_NONCE_SIZE,
+			   enonce1, nonceodd, cont, sizeof(uint32_t),
+			   &ordinal, bloblen, blob, 0, 0);
+	if (ret < 0)
+		return ret;
+	ret = TSS_authhmac(authdata2, blobauth, TPM_NONCE_SIZE,
+			   enonce2, nonceodd, cont, sizeof(uint32_t),
+			   &ordinal, bloblen, blob, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	/* build and send TPM request packet */
+	tpm_buf_reset(tb, TPM_TAG_RQU_AUTH2_COMMAND, TPM_ORD_UNSEAL);
+	tpm_buf_append_u32(tb, keyhandle);
+	tpm_buf_append(tb, blob, bloblen);
+	tpm_buf_append_u32(tb, authhandle1);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata1, SHA1_DIGEST_SIZE);
+	tpm_buf_append_u32(tb, authhandle2);
+	tpm_buf_append(tb, nonceodd, TPM_NONCE_SIZE);
+	tpm_buf_append_u8(tb, cont);
+	tpm_buf_append(tb, authdata2, SHA1_DIGEST_SIZE);
+
+	ret = trusted_tpm_send(tb);
+	if (ret < 0) {
+		pr_info("authhmac failed (%d)\n", ret);
+		return ret;
+	}
+
+	*datalen = LOAD32(tb->data, TPM_DATA_OFFSET);
+	ret = TSS_checkhmac2(tb->data, ordinal, nonceodd,
+			     keyauth, SHA1_DIGEST_SIZE,
+			     blobauth, SHA1_DIGEST_SIZE,
+			     sizeof(uint32_t), TPM_DATA_OFFSET,
+			     *datalen, TPM_DATA_OFFSET + sizeof(uint32_t), 0,
+			     0);
+	if (ret < 0) {
+		pr_info("TSS_checkhmac2 failed (%d)\n", ret);
+		return ret;
+	}
+	memcpy(data, tb->data + TPM_DATA_OFFSET + sizeof(uint32_t), *datalen);
+	return 0;
+}
+
+/*
+ * Have the TPM seal(encrypt) the symmetric key
+ */
+static int key_seal(struct trusted_key_payload *p,
+		    struct trusted_key_options *o)
+{
+	int ret;
+
+	struct tpm_buf *tb __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!tb)
+		return -ENOMEM;
+
+	tpm_buf_init(tb, TPM_BUFSIZE);
+
+	/* include migratable flag at end of sealed key */
+	p->key[p->key_len] = p->migratable;
+
+	ret = tpm_seal(tb, o->keytype, o->keyhandle, o->keyauth,
+		       p->key, p->key_len + 1, p->blob, &p->blob_len,
+		       o->blobauth, o->pcrinfo, o->pcrinfo_len);
+	if (ret < 0)
+		pr_info("srkseal failed (%d)\n", ret);
+
+	return ret;
+}
+
+/*
+ * Have the TPM unseal(decrypt) the symmetric key
+ */
+static int key_unseal(struct trusted_key_payload *p,
+		      struct trusted_key_options *o)
+{
+	int ret;
+
+	struct tpm_buf *tb __free(kfree) = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!tb)
+		return -ENOMEM;
+
+	tpm_buf_init(tb, TPM_BUFSIZE);
+
+	ret = tpm_unseal(tb, o->keyhandle, o->keyauth, p->blob, p->blob_len,
+			 o->blobauth, p->key, &p->key_len);
+	if (ret < 0)
+		pr_info("srkunseal failed (%d)\n", ret);
+	else
+		/* pull migratable flag out of sealed key */
+		p->migratable = p->key[--p->key_len];
+
+	return ret;
+}
+
+enum {
+	Opt_err,
+	Opt_keyhandle, Opt_keyauth, Opt_blobauth,
+	Opt_pcrinfo, Opt_pcrlock, Opt_migratable,
+	Opt_hash,
+	Opt_policydigest,
+	Opt_policyhandle,
+};
+
+static const match_table_t key_tokens = {
+	{Opt_keyhandle, "keyhandle=%s"},
+	{Opt_keyauth, "keyauth=%s"},
+	{Opt_blobauth, "blobauth=%s"},
+	{Opt_pcrinfo, "pcrinfo=%s"},
+	{Opt_pcrlock, "pcrlock=%s"},
+	{Opt_migratable, "migratable=%s"},
+	{Opt_hash, "hash=%s"},
+	{Opt_policydigest, "policydigest=%s"},
+	{Opt_policyhandle, "policyhandle=%s"},
+	{Opt_err, NULL}
+};
+
+/* can have zero or more token= options */
+static int getoptions(char *c, struct trusted_key_payload *pay,
+		      struct trusted_key_options *opt)
+{
+	substring_t args[MAX_OPT_ARGS];
+	char *p = c;
+	int token;
+	int res;
+	unsigned long handle;
+	unsigned long lock;
+	unsigned long token_mask = 0;
+	unsigned int digest_len;
+	int i;
+	int tpm2;
+
+	tpm2 = tpm_is_tpm2(chip);
+	if (tpm2 < 0)
+		return tpm2;
+
+	opt->hash = tpm2 ? HASH_ALGO_SHA256 : HASH_ALGO_SHA1;
+
+	if (!c)
+		return 0;
+
+	while ((p = strsep(&c, " \t"))) {
+		if (*p == '\0' || *p == ' ' || *p == '\t')
+			continue;
+		token = match_token(p, key_tokens, args);
+		if (test_and_set_bit(token, &token_mask))
+			return -EINVAL;
+
+		switch (token) {
+		case Opt_pcrinfo:
+			opt->pcrinfo_len = strlen(args[0].from) / 2;
+			if (opt->pcrinfo_len > MAX_PCRINFO_SIZE)
+				return -EINVAL;
+			res = hex2bin(opt->pcrinfo, args[0].from,
+				      opt->pcrinfo_len);
+			if (res < 0)
+				return -EINVAL;
+			break;
+		case Opt_keyhandle:
+			res = kstrtoul(args[0].from, 16, &handle);
+			if (res < 0)
+				return -EINVAL;
+			opt->keytype = SEAL_keytype;
+			opt->keyhandle = handle;
+			break;
+		case Opt_keyauth:
+			if (strlen(args[0].from) != 2 * SHA1_DIGEST_SIZE)
+				return -EINVAL;
+			res = hex2bin(opt->keyauth, args[0].from,
+				      SHA1_DIGEST_SIZE);
+			if (res < 0)
+				return -EINVAL;
+			break;
+		case Opt_blobauth:
+			/*
+			 * TPM 1.2 authorizations are sha1 hashes passed in as
+			 * hex strings.  TPM 2.0 authorizations are simple
+			 * passwords (although it can take a hash as well)
+			 */
+			opt->blobauth_len = strlen(args[0].from);
+
+			if (opt->blobauth_len == 2 * TPM_DIGEST_SIZE) {
+				res = hex2bin(opt->blobauth, args[0].from,
+					      TPM_DIGEST_SIZE);
+				if (res < 0)
+					return -EINVAL;
+
+				opt->blobauth_len = TPM_DIGEST_SIZE;
+				break;
+			}
+
+			if (tpm2 && opt->blobauth_len <= sizeof(opt->blobauth)) {
+				memcpy(opt->blobauth, args[0].from,
+				       opt->blobauth_len);
+				break;
+			}
+
+			return -EINVAL;
+
+			break;
+
+		case Opt_migratable:
+			if (*args[0].from == '0')
+				pay->migratable = 0;
+			else if (*args[0].from != '1')
+				return -EINVAL;
+			break;
+		case Opt_pcrlock:
+			res = kstrtoul(args[0].from, 10, &lock);
+			if (res < 0)
+				return -EINVAL;
+			opt->pcrlock = lock;
+			break;
+		case Opt_hash:
+			if (test_bit(Opt_policydigest, &token_mask))
+				return -EINVAL;
+			for (i = 0; i < HASH_ALGO__LAST; i++) {
+				if (!strcmp(args[0].from, hash_algo_name[i])) {
+					opt->hash = i;
+					break;
+				}
+			}
+			if (i == HASH_ALGO__LAST)
+				return -EINVAL;
+			if  (!tpm2 && i != HASH_ALGO_SHA1) {
+				pr_info("TPM 1.x only supports SHA-1.\n");
+				return -EINVAL;
+			}
+			break;
+		case Opt_policydigest:
+			digest_len = hash_digest_size[opt->hash];
+			if (!tpm2 || strlen(args[0].from) != (2 * digest_len))
+				return -EINVAL;
+			res = hex2bin(opt->policydigest, args[0].from,
+				      digest_len);
+			if (res < 0)
+				return -EINVAL;
+			opt->policydigest_len = digest_len;
+			break;
+		case Opt_policyhandle:
+			if (!tpm2)
+				return -EINVAL;
+			res = kstrtoul(args[0].from, 16, &handle);
+			if (res < 0)
+				return -EINVAL;
+			opt->policyhandle = handle;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static struct trusted_key_options *trusted_options_alloc(void)
+{
+	struct trusted_key_options *options;
+	int tpm2;
+
+	tpm2 = tpm_is_tpm2(chip);
+	if (tpm2 < 0)
+		return NULL;
+
+	options = kzalloc_obj(*options);
+	if (options) {
+		/* set any non-zero defaults */
+		options->keytype = SRK_keytype;
+
+		if (!tpm2)
+			options->keyhandle = SRKHANDLE;
+	}
+	return options;
+}
+
+static int trusted_tpm_seal(struct trusted_key_payload *p, char *datablob)
+{
+	struct trusted_key_options *options = NULL;
+	int ret = 0;
+	int tpm2;
+
+	tpm2 = tpm_is_tpm2(chip);
+	if (tpm2 < 0)
+		return tpm2;
+
+	options = trusted_options_alloc();
+	if (!options)
+		return -ENOMEM;
+
+	ret = getoptions(datablob, p, options);
+	if (ret < 0)
+		goto out;
+	dump_options(options);
+
+	if (!options->keyhandle && !tpm2) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (tpm2)
+		ret = tpm2_seal_trusted(chip, p, options);
+	else
+		ret = key_seal(p, options);
+	if (ret < 0) {
+		pr_info("key_seal failed (%d)\n", ret);
+		goto out;
+	}
+
+	if (options->pcrlock) {
+		ret = pcrlock(options->pcrlock);
+		if (ret < 0) {
+			pr_info("pcrlock failed (%d)\n", ret);
+			goto out;
+		}
+	}
+out:
+	kfree_sensitive(options);
+	return ret;
+}
+
+static int trusted_tpm_unseal(struct trusted_key_payload *p, char *datablob)
+{
+	struct trusted_key_options *options = NULL;
+	int ret = 0;
+	int tpm2;
+
+	tpm2 = tpm_is_tpm2(chip);
+	if (tpm2 < 0)
+		return tpm2;
+
+	options = trusted_options_alloc();
+	if (!options)
+		return -ENOMEM;
+
+	ret = getoptions(datablob, p, options);
+	if (ret < 0)
+		goto out;
+	dump_options(options);
+
+	if (!options->keyhandle && !tpm2) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (tpm2)
+		ret = tpm2_unseal_trusted(chip, p, options);
+	else
+		ret = key_unseal(p, options);
+	if (ret < 0)
+		pr_info("key_unseal failed (%d)\n", ret);
+
+	if (options->pcrlock) {
+		ret = pcrlock(options->pcrlock);
+		if (ret < 0) {
+			pr_info("pcrlock failed (%d)\n", ret);
+			goto out;
+		}
+	}
+out:
+	kfree_sensitive(options);
+	return ret;
+}
+
+static int trusted_tpm_get_random(unsigned char *key, size_t key_len)
+{
+	return tpm_get_random(chip, key, key_len);
+}
+
+static int __init init_digests(void)
+{
+	int i;
+
+	digests = kzalloc_objs(*digests, chip->nr_allocated_banks);
+	if (!digests)
+		return -ENOMEM;
+
+	for (i = 0; i < chip->nr_allocated_banks; i++)
+		digests[i].alg_id = chip->allocated_banks[i].alg_id;
+
+	return 0;
+}
+
+static int __init trusted_tpm_init(void)
+{
+	int ret;
+
+	chip = tpm_default_chip();
+	if (!chip)
+		return -ENODEV;
+
+	ret = init_digests();
+	if (ret < 0)
+		goto err_put;
+	ret = register_key_type(&key_type_trusted);
+	if (ret < 0)
+		goto err_free;
+	return 0;
+err_free:
+	kfree(digests);
+err_put:
+	put_device(&chip->dev);
+	return ret;
+}
+
+static void trusted_tpm_exit(void)
+{
+	if (chip) {
+		unregister_key_type(&key_type_trusted);
+		put_device(&chip->dev);
+		kfree(digests);
+	}
+}
+
+struct trusted_key_ops trusted_key_tpm_ops = {
+	.migratable = 1, /* migratable by default */
+	.init = trusted_tpm_init,
+	.seal = trusted_tpm_seal,
+	.unseal = trusted_tpm_unseal,
+	.get_random = trusted_tpm_get_random,
+	.exit = trusted_tpm_exit,
+};
diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c
new file mode 100644
index 000000000..67225dd56
--- /dev/null
+++ b/security/keys/trusted-keys/trusted_tpm2.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004 IBM Corporation
+ * Copyright (C) 2014 Intel Corporation
+ */
+
+#include <linux/asn1_encoder.h>
+#include <linux/oid_registry.h>
+#include <linux/string.h>
+#include <linux/err.h>
+#include <linux/tpm.h>
+
+#include <keys/trusted-type.h>
+#include <keys/trusted_tpm.h>
+
+#include <linux/unaligned.h>
+
+#include "tpm2key.asn1.h"
+
+static u32 tpm2key_oid[] = { 2, 23, 133, 10, 1, 5 };
+
+static int tpm2_key_encode(struct trusted_key_payload *payload,
+			   struct trusted_key_options *options,
+			   u8 *src, u32 len)
+{
+	const int SCRATCH_SIZE = PAGE_SIZE;
+	u8 *scratch = kmalloc(SCRATCH_SIZE, GFP_KERNEL);
+	u8 *work = scratch, *work1;
+	u8 *end_work = scratch + SCRATCH_SIZE;
+	u8 *priv, *pub;
+	u16 priv_len, pub_len;
+	int ret;
+
+	priv_len = get_unaligned_be16(src) + 2;
+	priv = src;
+
+	src += priv_len;
+
+	pub_len = get_unaligned_be16(src) + 2;
+	pub = src;
+
+	if (!scratch)
+		return -ENOMEM;
+
+	work = asn1_encode_oid(work, end_work, tpm2key_oid,
+			       asn1_oid_len(tpm2key_oid));
+
+	if (options->blobauth_len == 0) {
+		unsigned char bool[3], *w = bool;
+		/* tag 0 is emptyAuth */
+		w = asn1_encode_boolean(w, w + sizeof(bool), true);
+		if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) {
+			ret = PTR_ERR(w);
+			goto err;
+		}
+		work = asn1_encode_tag(work, end_work, 0, bool, w - bool);
+	}
+
+	/*
+	 * Assume both octet strings will encode to a 2 byte definite length
+	 *
+	 * Note: For a well behaved TPM, this warning should never
+	 * trigger, so if it does there's something nefarious going on
+	 */
+	if (WARN(work - scratch + pub_len + priv_len + 14 > SCRATCH_SIZE,
+		 "BUG: scratch buffer is too small")) {
+		ret = -EINVAL;
+		goto err;
+	}
+
+	work = asn1_encode_integer(work, end_work, options->keyhandle);
+	work = asn1_encode_octet_string(work, end_work, pub, pub_len);
+	work = asn1_encode_octet_string(work, end_work, priv, priv_len);
+
+	work1 = payload->blob;
+	work1 = asn1_encode_sequence(work1, work1 + sizeof(payload->blob),
+				     scratch, work - scratch);
+	if (IS_ERR(work1)) {
+		ret = PTR_ERR(work1);
+		pr_err("BUG: ASN.1 encoder failed with %d\n", ret);
+		goto err;
+	}
+
+	kfree(scratch);
+	return work1 - payload->blob;
+
+err:
+	kfree(scratch);
+	return ret;
+}
+
+struct tpm2_key_context {
+	u32 parent;
+	const u8 *pub;
+	u32 pub_len;
+	const u8 *priv;
+	u32 priv_len;
+};
+
+static int tpm2_key_decode(struct trusted_key_payload *payload,
+			   struct trusted_key_options *options,
+			   u8 **buf)
+{
+	int ret;
+	struct tpm2_key_context ctx;
+	u8 *blob;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	ret = asn1_ber_decoder(&tpm2key_decoder, &ctx, payload->blob,
+			       payload->blob_len);
+	if (ret < 0)
+		return ret;
+
+	if (ctx.priv_len + ctx.pub_len > MAX_BLOB_SIZE)
+		return -EINVAL;
+
+	blob = kmalloc(ctx.priv_len + ctx.pub_len + 4, GFP_KERNEL);
+	if (!blob)
+		return -ENOMEM;
+
+	*buf = blob;
+	options->keyhandle = ctx.parent;
+
+	memcpy(blob, ctx.priv, ctx.priv_len);
+	blob += ctx.priv_len;
+
+	memcpy(blob, ctx.pub, ctx.pub_len);
+
+	return 0;
+}
+
+int tpm2_key_parent(void *context, size_t hdrlen,
+		  unsigned char tag,
+		  const void *value, size_t vlen)
+{
+	struct tpm2_key_context *ctx = context;
+	const u8 *v = value;
+	int i;
+
+	ctx->parent = 0;
+	for (i = 0; i < vlen; i++) {
+		ctx->parent <<= 8;
+		ctx->parent |= v[i];
+	}
+
+	return 0;
+}
+
+int tpm2_key_type(void *context, size_t hdrlen,
+		unsigned char tag,
+		const void *value, size_t vlen)
+{
+	enum OID oid = look_up_OID(value, vlen);
+
+	if (oid != OID_TPMSealedData) {
+		char buffer[50];
+
+		sprint_oid(value, vlen, buffer, sizeof(buffer));
+		pr_debug("OID is \"%s\" which is not TPMSealedData\n",
+			 buffer);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int tpm2_key_pub(void *context, size_t hdrlen,
+	       unsigned char tag,
+	       const void *value, size_t vlen)
+{
+	struct tpm2_key_context *ctx = context;
+
+	ctx->pub = value;
+	ctx->pub_len = vlen;
+
+	return 0;
+}
+
+int tpm2_key_priv(void *context, size_t hdrlen,
+		unsigned char tag,
+		const void *value, size_t vlen)
+{
+	struct tpm2_key_context *ctx = context;
+
+	ctx->priv = value;
+	ctx->priv_len = vlen;
+
+	return 0;
+}
+
+/**
+ * tpm2_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer.
+ *
+ * @buf: an allocated tpm_buf instance
+ * @session_handle: session handle
+ * @nonce: the session nonce, may be NULL if not used
+ * @nonce_len: the session nonce length, may be 0 if not used
+ * @attributes: the session attributes
+ * @hmac: the session HMAC or password, may be NULL if not used
+ * @hmac_len: the session HMAC or password length, maybe 0 if not used
+ */
+static void tpm2_buf_append_auth(struct tpm_buf *buf, u32 session_handle,
+				 const u8 *nonce, u16 nonce_len,
+				 u8 attributes,
+				 const u8 *hmac, u16 hmac_len)
+{
+	tpm_buf_append_u32(buf, 9 + nonce_len + hmac_len);
+	tpm_buf_append_u32(buf, session_handle);
+	tpm_buf_append_u16(buf, nonce_len);
+
+	if (nonce && nonce_len)
+		tpm_buf_append(buf, nonce, nonce_len);
+
+	tpm_buf_append_u8(buf, attributes);
+	tpm_buf_append_u16(buf, hmac_len);
+
+	if (hmac && hmac_len)
+		tpm_buf_append(buf, hmac, hmac_len);
+}
+
+/**
+ * tpm2_seal_trusted() - seal the payload of a trusted key
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: < 0 on error and 0 on success.
+ */
+int tpm2_seal_trusted(struct tpm_chip *chip,
+		      struct trusted_key_payload *payload,
+		      struct trusted_key_options *options)
+{
+	off_t offset = TPM_HEADER_SIZE;
+	struct tpm_buf *buf __free(kfree) = NULL;
+	struct tpm_buf *sized __free(kfree) = NULL;
+	int blob_len = 0;
+	int hash;
+	u32 flags;
+	int rc;
+
+	hash = tpm2_find_hash_alg(options->hash);
+	if (hash < 0)
+		return hash;
+
+	if (!options->keyhandle)
+		return -EINVAL;
+
+	rc = tpm_try_get_ops(chip);
+	if (rc)
+		return rc;
+
+	rc = tpm2_start_auth_session(chip);
+	if (rc)
+		goto out_put;
+
+	buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!buf) {
+		rc = -ENOMEM;
+		tpm2_end_auth_session(chip);
+		goto out_put;
+	}
+
+	tpm_buf_init(buf, TPM_BUFSIZE);
+	tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE);
+
+	sized = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!sized) {
+		rc = -ENOMEM;
+		tpm2_end_auth_session(chip);
+		goto out_put;
+	}
+
+	tpm_buf_init_sized(sized, TPM_BUFSIZE);
+
+	rc = tpm_buf_append_name(chip, buf, options->keyhandle, NULL);
+	if (rc)
+		goto out;
+
+	tpm_buf_append_hmac_session(chip, buf, TPM2_SA_DECRYPT,
+				    options->keyauth, TPM_DIGEST_SIZE);
+
+	/* sensitive */
+	tpm_buf_append_u16(sized, options->blobauth_len);
+
+	if (options->blobauth_len)
+		tpm_buf_append(sized, options->blobauth, options->blobauth_len);
+
+	tpm_buf_append_u16(sized, payload->key_len);
+	tpm_buf_append(sized, payload->key, payload->key_len);
+	tpm_buf_append(buf, sized->data, sized->length);
+
+	/* public */
+	tpm_buf_reset_sized(sized);
+	tpm_buf_append_u16(sized, TPM_ALG_KEYEDHASH);
+	tpm_buf_append_u16(sized, hash);
+
+	/* key properties */
+	flags = 0;
+	flags |= options->policydigest_len ? 0 : TPM2_OA_USER_WITH_AUTH;
+	flags |= payload->migratable ? 0 : (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT);
+	tpm_buf_append_u32(sized, flags);
+
+	/* policy */
+	tpm_buf_append_u16(sized, options->policydigest_len);
+	if (options->policydigest_len)
+		tpm_buf_append(sized, options->policydigest, options->policydigest_len);
+
+	/* public parameters */
+	tpm_buf_append_u16(sized, TPM_ALG_NULL);
+	tpm_buf_append_u16(sized, 0);
+
+	tpm_buf_append(buf, sized->data, sized->length);
+
+	/* outside info */
+	tpm_buf_append_u16(buf, 0);
+
+	/* creation PCR */
+	tpm_buf_append_u32(buf, 0);
+
+	if (buf->flags & TPM_BUF_INVALID) {
+		rc = -E2BIG;
+		tpm2_end_auth_session(chip);
+		goto out;
+	}
+
+	rc = tpm_buf_fill_hmac_session(chip, buf);
+	if (rc)
+		goto out;
+
+	rc = tpm_transmit_cmd(chip, buf, 4, "sealing data");
+	rc = tpm_buf_check_hmac_response(chip, buf, rc);
+	if (rc)
+		goto out;
+
+	blob_len = tpm_buf_read_u32(buf, &offset);
+	if (blob_len > MAX_BLOB_SIZE || buf->flags & TPM_BUF_INVALID) {
+		rc = -E2BIG;
+		goto out;
+	}
+	if (buf->length - offset < blob_len) {
+		rc = -EFAULT;
+		goto out;
+	}
+
+	blob_len = tpm2_key_encode(payload, options, &buf->data[offset], blob_len);
+	if (blob_len < 0)
+		rc = blob_len;
+
+out:
+	if (!rc)
+		payload->blob_len = blob_len;
+
+out_put:
+	tpm_put_ops(chip);
+	return tpm_ret_to_err(rc);
+}
+
+/**
+ * tpm2_load_cmd() - execute a TPM2_Load command
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ * @blob_handle: returned blob handle
+ *
+ * Return: 0 on success.
+ *        -E2BIG on wrong payload size.
+ *        -EPERM on tpm error status.
+ *        < 0 error from tpm_send.
+ */
+static int tpm2_load_cmd(struct tpm_chip *chip,
+			 struct trusted_key_payload *payload,
+			 struct trusted_key_options *options,
+			 u32 *blob_handle)
+{
+	u8 *blob_ref __free(kfree) = NULL;
+	struct tpm_buf *buf __free(kfree) = NULL;
+	unsigned int private_len;
+	unsigned int public_len;
+	unsigned int blob_len;
+	u8 *blob, *pub;
+	int rc;
+	u32 attrs;
+
+	rc = tpm2_key_decode(payload, options, &blob);
+	if (rc) {
+		/* old form */
+		blob = payload->blob;
+		payload->old_format = 1;
+	} else {
+		/* Bind for cleanup: */
+		blob_ref = blob;
+	}
+
+	/* new format carries keyhandle but old format doesn't */
+	if (!options->keyhandle)
+		return -EINVAL;
+
+	/* must be big enough for at least the two be16 size counts */
+	if (payload->blob_len < 4)
+		return -EINVAL;
+
+	private_len = get_unaligned_be16(blob);
+
+	/* must be big enough for following public_len */
+	if (private_len + 2 + 2 > (payload->blob_len))
+		return -E2BIG;
+
+	public_len = get_unaligned_be16(blob + 2 + private_len);
+	if (private_len + 2 + public_len + 2 > payload->blob_len)
+		return -E2BIG;
+
+	pub = blob + 2 + private_len + 2;
+	/* key attributes are always at offset 4 */
+	attrs = get_unaligned_be32(pub + 4);
+
+	if ((attrs & (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT)) ==
+	    (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT))
+		payload->migratable = 0;
+	else
+		payload->migratable = 1;
+
+	blob_len = private_len + public_len + 4;
+	if (blob_len > payload->blob_len)
+		return -E2BIG;
+
+	rc = tpm2_start_auth_session(chip);
+	if (rc)
+		return rc;
+
+	buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!buf) {
+		tpm2_end_auth_session(chip);
+		return -ENOMEM;
+	}
+
+	tpm_buf_init(buf, TPM_BUFSIZE);
+	tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_LOAD);
+
+	rc = tpm_buf_append_name(chip, buf, options->keyhandle, NULL);
+	if (rc)
+		return rc;
+
+	tpm_buf_append_hmac_session(chip, buf, 0, options->keyauth,
+				    TPM_DIGEST_SIZE);
+
+	tpm_buf_append(buf, blob, blob_len);
+
+	if (buf->flags & TPM_BUF_INVALID) {
+		tpm2_end_auth_session(chip);
+		return -E2BIG;
+	}
+
+	rc = tpm_buf_fill_hmac_session(chip, buf);
+	if (rc)
+		return rc;
+
+	rc = tpm_transmit_cmd(chip, buf, 4, "loading blob");
+	rc = tpm_buf_check_hmac_response(chip, buf, rc);
+	if (!rc)
+		*blob_handle = be32_to_cpup(
+			(__be32 *)&buf->data[TPM_HEADER_SIZE]);
+
+	return tpm_ret_to_err(rc);
+}
+
+/**
+ * tpm2_unseal_cmd() - execute a TPM2_Unseal command
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ * @blob_handle: blob handle
+ *
+ * Return: 0 on success
+ *         -EPERM on tpm error status
+ *         < 0 error from tpm_send
+ */
+static int tpm2_unseal_cmd(struct tpm_chip *chip,
+			   struct trusted_key_payload *payload,
+			   struct trusted_key_options *options,
+			   u32 blob_handle)
+{
+	struct tpm_header *head;
+	struct tpm_buf *buf __free(kfree) = NULL;
+	u16 data_len;
+	int offset;
+	u8 *data;
+	int rc;
+
+	rc = tpm2_start_auth_session(chip);
+	if (rc)
+		return rc;
+
+	buf = kzalloc(TPM_BUFSIZE, GFP_KERNEL);
+	if (!buf) {
+		tpm2_end_auth_session(chip);
+		return -ENOMEM;
+	}
+
+	tpm_buf_init(buf, TPM_BUFSIZE);
+	tpm_buf_reset(buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
+
+	rc = tpm_buf_append_name(chip, buf, blob_handle, NULL);
+	if (rc)
+		return rc;
+
+	if (!options->policyhandle) {
+		tpm_buf_append_hmac_session(chip, buf, TPM2_SA_ENCRYPT,
+					    options->blobauth,
+					    options->blobauth_len);
+	} else {
+		/*
+		 * FIXME: The policy session was generated outside the
+		 * kernel so we don't known the nonce and thus can't
+		 * calculate a HMAC on it.  Therefore, the user can
+		 * only really use TPM2_PolicyPassword and we must
+		 * send down the plain text password, which could be
+		 * intercepted.  We can still encrypt the returned
+		 * key, but that's small comfort since the interposer
+		 * could repeat our actions with the exfiltrated
+		 * password.
+		 */
+		tpm2_buf_append_auth(buf, options->policyhandle,
+				     NULL /* nonce */, 0, 0,
+				     options->blobauth, options->blobauth_len);
+		if (tpm2_chip_auth(chip)) {
+			tpm_buf_append_hmac_session(chip, buf, TPM2_SA_ENCRYPT,
+						    NULL, 0);
+		} else  {
+			offset = buf->handles * 4 + TPM_HEADER_SIZE;
+			head = (struct tpm_header *)buf->data;
+			if (tpm_buf_length(buf) == offset)
+				head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
+		}
+	}
+
+	rc = tpm_buf_fill_hmac_session(chip, buf);
+	if (rc)
+		return rc;
+
+	rc = tpm_transmit_cmd(chip, buf, 6, "unsealing");
+	rc = tpm_buf_check_hmac_response(chip, buf, rc);
+
+	if (!rc) {
+		data_len = be16_to_cpup(
+			(__be16 *)&buf->data[TPM_HEADER_SIZE + 4]);
+		if (data_len < MIN_KEY_SIZE ||  data_len > MAX_KEY_SIZE)
+			return -EFAULT;
+
+		if (tpm_buf_length(buf) < TPM_HEADER_SIZE + 6 + data_len)
+			return -EFAULT;
+		data = &buf->data[TPM_HEADER_SIZE + 6];
+
+		if (payload->old_format) {
+			/* migratable flag is at the end of the key */
+			memcpy(payload->key, data, data_len - 1);
+			payload->key_len = data_len - 1;
+			payload->migratable = data[data_len - 1];
+		} else {
+			/*
+			 * migratable flag already collected from key
+			 * attributes
+			 */
+			memcpy(payload->key, data, data_len);
+			payload->key_len = data_len;
+		}
+	}
+
+	return tpm_ret_to_err(rc);
+}
+
+/**
+ * tpm2_unseal_trusted() - unseal the payload of a trusted key
+ *
+ * @chip: TPM chip to use
+ * @payload: the key data in clear and encrypted form
+ * @options: authentication values and other options
+ *
+ * Return: Same as with tpm_send.
+ */
+int tpm2_unseal_trusted(struct tpm_chip *chip,
+			struct trusted_key_payload *payload,
+			struct trusted_key_options *options)
+{
+	u32 blob_handle;
+	int rc;
+
+	rc = tpm_try_get_ops(chip);
+	if (rc)
+		return rc;
+
+	rc = tpm2_load_cmd(chip, payload, options, &blob_handle);
+	if (rc)
+		goto out;
+
+	rc = tpm2_unseal_cmd(chip, payload, options, blob_handle);
+	tpm2_flush_context(chip, blob_handle);
+
+out:
+	tpm_put_ops(chip);
+	return tpm_ret_to_err(rc);
+}
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
new file mode 100644
index 000000000..6f88b507f
--- /dev/null
+++ b/security/keys/user_defined.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* user_defined.c: user defined key type
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+
+static int logon_vet_description(const char *desc);
+
+/*
+ * user defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_user = {
+	.name			= "user",
+	.preparse		= user_preparse,
+	.free_preparse		= user_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.update			= user_update,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.read			= user_read,
+};
+
+EXPORT_SYMBOL_GPL(key_type_user);
+
+/*
+ * This key type is essentially the same as key_type_user, but it does
+ * not define a .read op. This is suitable for storing username and
+ * password pairs in the keyring that you do not want to be readable
+ * from userspace.
+ */
+struct key_type key_type_logon = {
+	.name			= "logon",
+	.preparse		= user_preparse,
+	.free_preparse		= user_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.update			= user_update,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.vet_description	= logon_vet_description,
+};
+EXPORT_SYMBOL_GPL(key_type_logon);
+
+/*
+ * Preparse a user defined key payload
+ */
+int user_preparse(struct key_preparsed_payload *prep)
+{
+	struct user_key_payload *upayload;
+	size_t datalen = prep->datalen;
+
+	if (datalen == 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	upayload = kmalloc_flex(*upayload, data, datalen);
+	if (!upayload)
+		return -ENOMEM;
+
+	/* attach the data */
+	prep->quotalen = datalen;
+	prep->payload.data[0] = upayload;
+	upayload->datalen = datalen;
+	memcpy(upayload->data, prep->data, datalen);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(user_preparse);
+
+/*
+ * Free a preparse of a user defined key payload
+ */
+void user_free_preparse(struct key_preparsed_payload *prep)
+{
+	kfree_sensitive(prep->payload.data[0]);
+}
+EXPORT_SYMBOL_GPL(user_free_preparse);
+
+static void user_free_payload_rcu(struct rcu_head *head)
+{
+	struct user_key_payload *payload;
+
+	payload = container_of(head, struct user_key_payload, rcu);
+	kfree_sensitive(payload);
+}
+
+/*
+ * update a user defined key
+ * - the key's semaphore is write-locked
+ */
+int user_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct user_key_payload *zap = NULL;
+	int ret;
+
+	/* check the quota and attach the new data */
+	ret = key_payload_reserve(key, prep->datalen);
+	if (ret < 0)
+		return ret;
+
+	/* attach the new data, displacing the old */
+	key->expiry = prep->expiry;
+	if (key_is_positive(key))
+		zap = dereference_key_locked(key);
+	rcu_assign_keypointer(key, prep->payload.data[0]);
+	prep->payload.data[0] = NULL;
+
+	if (zap)
+		call_rcu(&zap->rcu, user_free_payload_rcu);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(user_update);
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void user_revoke(struct key *key)
+{
+	struct user_key_payload *upayload = user_key_payload_locked(key);
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+
+	if (upayload) {
+		rcu_assign_keypointer(key, NULL);
+		call_rcu(&upayload->rcu, user_free_payload_rcu);
+	}
+}
+
+EXPORT_SYMBOL(user_revoke);
+
+/*
+ * dispose of the data dangling from the corpse of a user key
+ */
+void user_destroy(struct key *key)
+{
+	struct user_key_payload *upayload = key->payload.data[0];
+
+	kfree_sensitive(upayload);
+}
+
+EXPORT_SYMBOL_GPL(user_destroy);
+
+/*
+ * describe the user key
+ */
+void user_describe(const struct key *key, struct seq_file *m)
+{
+	seq_puts(m, key->description);
+	if (key_is_positive(key))
+		seq_printf(m, ": %u", key->datalen);
+}
+
+EXPORT_SYMBOL_GPL(user_describe);
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long user_read(const struct key *key, char *buffer, size_t buflen)
+{
+	const struct user_key_payload *upayload;
+	long ret;
+
+	upayload = user_key_payload_locked(key);
+	ret = upayload->datalen;
+
+	/* we can return the data as is */
+	if (buffer && buflen > 0) {
+		if (buflen > upayload->datalen)
+			buflen = upayload->datalen;
+
+		memcpy(buffer, upayload->data, buflen);
+	}
+
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(user_read);
+
+/* Vet the description for a "logon" key */
+static int logon_vet_description(const char *desc)
+{
+	char *p;
+
+	/* require a "qualified" description string */
+	p = strchr(desc, ':');
+	if (!p)
+		return -EINVAL;
+
+	/* also reject description with ':' as first char */
+	if (p == desc)
+		return -EINVAL;
+
+	return 0;
+}
diff --git a/security/landlock/.kunitconfig b/security/landlock/.kunitconfig
new file mode 100644
index 000000000..f9423f01a
--- /dev/null
+++ b/security/landlock/.kunitconfig
@@ -0,0 +1,6 @@
+CONFIG_AUDIT=y
+CONFIG_KUNIT=y
+CONFIG_NET=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_LANDLOCK=y
+CONFIG_SECURITY_LANDLOCK_KUNIT_TEST=y
diff --git a/security/landlock/Kconfig b/security/landlock/Kconfig
new file mode 100644
index 000000000..7aeac2916
--- /dev/null
+++ b/security/landlock/Kconfig
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config SECURITY_LANDLOCK
+	bool "Landlock support"
+	depends on SECURITY
+	select SECURITY_NETWORK
+	select SECURITY_PATH
+	help
+	  Landlock is a sandboxing mechanism that enables processes to restrict
+	  themselves (and their future children) by gradually enforcing
+	  tailored access control policies.  A Landlock security policy is a
+	  set of access rights (e.g. open a file in read-only, make a
+	  directory, etc.) tied to a file hierarchy.  Such policy can be
+	  configured and enforced by any processes for themselves using the
+	  dedicated system calls: landlock_create_ruleset(),
+	  landlock_add_rule(), and landlock_restrict_self().
+
+	  See Documentation/userspace-api/landlock.rst for further information.
+
+	  If you are unsure how to answer this question, answer N.  Otherwise,
+	  you should also prepend "landlock," to the content of CONFIG_LSM to
+	  enable Landlock at boot time.
+
+config SECURITY_LANDLOCK_LOG
+	bool
+	depends on SECURITY_LANDLOCK
+	default y if AUDIT || TRACEPOINTS
+
+config SECURITY_LANDLOCK_KUNIT_TEST
+	bool "KUnit tests for Landlock" if !KUNIT_ALL_TESTS
+	depends on KUNIT=y
+	depends on SECURITY_LANDLOCK
+	default KUNIT_ALL_TESTS
+	help
+	  Build KUnit tests for Landlock.
+
+	  See the KUnit documentation in Documentation/dev-tools/kunit
+
+	  Run all KUnit tests for Landlock with:
+	  ./tools/testing/kunit/kunit.py run --kunitconfig security/landlock
+
+	  If you are unsure how to answer this question, answer N.
diff --git a/security/landlock/Makefile b/security/landlock/Makefile
new file mode 100644
index 000000000..2711f4876
--- /dev/null
+++ b/security/landlock/Makefile
@@ -0,0 +1,22 @@
+obj-$(CONFIG_SECURITY_LANDLOCK) := landlock.o
+
+landlock-y := \
+	setup.o \
+	syscalls.o \
+	object.o \
+	ruleset.o \
+	cred.o \
+	task.o \
+	fs.o \
+	tsync.o \
+	domain.o
+
+landlock-$(CONFIG_INET) += net.o
+
+landlock-$(CONFIG_SECURITY_LANDLOCK_LOG) += \
+	id.o \
+	log.o
+
+landlock-$(CONFIG_AUDIT) += audit.o
+
+landlock-$(CONFIG_TRACEPOINTS) += trace.o
diff --git a/security/landlock/access.h b/security/landlock/access.h
new file mode 100644
index 000000000..bbbb41f41
--- /dev/null
+++ b/security/landlock/access.h
@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Access types and helpers
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_ACCESS_H
+#define _SECURITY_LANDLOCK_ACCESS_H
+
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/kernel.h>
+#include <uapi/linux/landlock.h>
+
+#include "limits.h"
+
+/*
+ * All access rights that are denied by default whether they are handled or not
+ * by a ruleset/layer.  This must be ORed with all domain->handled_masks[]
+ * entries when we need to get the absolute handled access masks, see
+ * landlock_upgrade_handled_access_masks().
+ */
+/* clang-format off */
+#define _LANDLOCK_ACCESS_FS_INITIALLY_DENIED ( \
+	LANDLOCK_ACCESS_FS_REFER)
+/* clang-format on */
+
+/* clang-format off */
+#define _LANDLOCK_ACCESS_FS_OPTIONAL ( \
+	LANDLOCK_ACCESS_FS_TRUNCATE | \
+	LANDLOCK_ACCESS_FS_IOCTL_DEV)
+/* clang-format on */
+
+typedef u32 access_mask_t;
+
+/* Makes sure all filesystem access rights can be stored. */
+static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_FS);
+/* Makes sure all network access rights can be stored. */
+static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_ACCESS_NET);
+/* Makes sure all scoped rights can be stored. */
+static_assert(BITS_PER_TYPE(access_mask_t) >= LANDLOCK_NUM_SCOPE);
+/* Makes sure for_each_set_bit() and for_each_clear_bit() calls are OK. */
+static_assert(sizeof(unsigned long) >= sizeof(access_mask_t));
+
+/* Ruleset access masks. */
+struct access_masks {
+	access_mask_t fs : LANDLOCK_NUM_ACCESS_FS;
+	access_mask_t net : LANDLOCK_NUM_ACCESS_NET;
+	access_mask_t scope : LANDLOCK_NUM_SCOPE;
+} __packed __aligned(sizeof(u32));
+
+union access_masks_all {
+	struct access_masks masks;
+	u32 all;
+};
+
+/* Makes sure all fields are covered. */
+static_assert(sizeof(typeof_member(union access_masks_all, masks)) ==
+	      sizeof(typeof_member(union access_masks_all, all)));
+
+/**
+ * struct layer_mask - The access rights and rule flags for a layer.
+ *
+ * This has a bit for each access rights and rule flags.  During access checks,
+ * it is used to represent the access rights for each layer which still need to
+ * be fulfilled.  When all bits are 0, the access request is considered to be
+ * fulfilled.
+ */
+struct layer_mask {
+	/**
+	 * @access: The unfulfilled access rights for this layer.
+	 */
+	access_mask_t access : LANDLOCK_NUM_ACCESS_MAX;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	/**
+	 * @quiet: Whether we have encountered a rule with the quiet flag for
+	 * this layer.  Used to control logging.
+	 */
+	access_mask_t quiet : 1;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+} __packed __aligned(sizeof(access_mask_t));
+
+/*
+ * Make sure that we don't increase the size of struct layer_mask when storing
+ * rule flags.
+ */
+static_assert(sizeof(struct layer_mask) == sizeof(access_mask_t));
+
+/**
+ * struct layer_masks - An array of struct layer_mask, one per layer.
+ */
+struct layer_masks {
+	/**
+	 * @layers: The unfulfilled access rights for each layer.
+	 */
+	struct layer_mask layers[LANDLOCK_MAX_NUM_LAYERS];
+};
+
+/*
+ * Tracks domains responsible of a denied access.  This avoids storing in each
+ * object the full matrix of per-layer unfulfilled access rights, which is
+ * required by update_request().
+ *
+ * Each nibble represents the layer index of the newest layer which denied a
+ * certain access right.  For file system access rights, the upper four bits are
+ * the index of the layer which denies LANDLOCK_ACCESS_FS_IOCTL_DEV and the
+ * lower nibble represents LANDLOCK_ACCESS_FS_TRUNCATE.
+ */
+typedef u8 deny_masks_t;
+
+/*
+ * Makes sure all optional access rights can be tied to a layer index (cf.
+ * get_deny_mask).
+ */
+static_assert(BITS_PER_TYPE(deny_masks_t) >=
+	      (HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1) *
+	       HWEIGHT(_LANDLOCK_ACCESS_FS_OPTIONAL)));
+
+/* LANDLOCK_MAX_NUM_LAYERS must be a power of two (cf. deny_masks_t assert). */
+static_assert(HWEIGHT(LANDLOCK_MAX_NUM_LAYERS) == 1);
+
+/* Upgrades with all initially denied by default access rights. */
+static inline struct access_masks
+landlock_upgrade_handled_access_masks(struct access_masks access_masks)
+{
+	/*
+	 * All access rights that are denied by default whether they are
+	 * explicitly handled or not.
+	 */
+	if (access_masks.fs)
+		access_masks.fs |= _LANDLOCK_ACCESS_FS_INITIALLY_DENIED;
+
+	return access_masks;
+}
+
+/* Checks the subset relation between access masks. */
+static inline bool access_mask_subset(access_mask_t subset,
+				      access_mask_t superset)
+{
+	return (subset | superset) == superset;
+}
+
+/* A bitmask that is large enough to hold set of optional accesses. */
+typedef u8 optional_access_t;
+static_assert(BITS_PER_TYPE(optional_access_t) >=
+	      HWEIGHT(_LANDLOCK_ACCESS_FS_OPTIONAL));
+
+#endif /* _SECURITY_LANDLOCK_ACCESS_H */
diff --git a/security/landlock/audit.c b/security/landlock/audit.c
new file mode 100644
index 000000000..e02963834
--- /dev/null
+++ b/security/landlock/audit.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Audit helpers
+ *
+ * Copyright © 2023-2025 Microsoft Corporation
+ */
+
+#include <linux/audit.h>
+#include <linux/bitops.h>
+#include <linux/landlock.h>
+#include <linux/lsm_audit.h>
+#include <linux/pid.h>
+#include <uapi/linux/landlock.h>
+
+#include "access.h"
+#include "audit.h"
+#include "common.h"
+#include "cred.h"
+#include "domain.h"
+#include "limits.h"
+#include "log.h"
+
+/*
+ * Access-right and scope names are built from the lists shared with the trace
+ * events (see <linux/landlock.h>).  The designated initializer places each name
+ * at its bit index, so the lookup stays O(1) and does not depend on the entry
+ * order.  log_blockers() adds the "fs."/"net."/"scope." category prefix.
+ */
+#define _LANDLOCK_NAME_ENTRY(mask, name) [BIT_INDEX(mask)] = name
+
+static const char *const fs_access_strings[] = { _LANDLOCK_ACCESS_FS_NAMES };
+
+static_assert(ARRAY_SIZE(fs_access_strings) == LANDLOCK_NUM_ACCESS_FS);
+
+static const char *const net_access_strings[] = { _LANDLOCK_ACCESS_NET_NAMES };
+
+static_assert(ARRAY_SIZE(net_access_strings) == LANDLOCK_NUM_ACCESS_NET);
+
+static const char *const scope_strings[] = { _LANDLOCK_SCOPE_NAMES };
+
+static_assert(ARRAY_SIZE(scope_strings) == LANDLOCK_NUM_SCOPE);
+
+#undef _LANDLOCK_NAME_ENTRY
+
+static __attribute_const__ const char *
+get_blocker(const enum landlock_request_type type,
+	    const unsigned long access_bit)
+{
+	switch (type) {
+	case LANDLOCK_REQUEST_PTRACE:
+		WARN_ON_ONCE(access_bit != -1);
+		return "ptrace";
+
+	case LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY:
+		WARN_ON_ONCE(access_bit != -1);
+		return "change_topology";
+
+	case LANDLOCK_REQUEST_FS_ACCESS:
+		if (WARN_ON_ONCE(access_bit >= ARRAY_SIZE(fs_access_strings)))
+			return "unknown";
+		return fs_access_strings[access_bit];
+
+	case LANDLOCK_REQUEST_NET_ACCESS:
+		if (WARN_ON_ONCE(access_bit >= ARRAY_SIZE(net_access_strings)))
+			return "unknown";
+		return net_access_strings[access_bit];
+
+	case LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET:
+		WARN_ON_ONCE(access_bit != -1);
+		return scope_strings[BIT_INDEX(
+			LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET)];
+
+	case LANDLOCK_REQUEST_SCOPE_SIGNAL:
+		WARN_ON_ONCE(access_bit != -1);
+		return scope_strings[BIT_INDEX(LANDLOCK_SCOPE_SIGNAL)];
+	}
+
+	WARN_ON_ONCE(1);
+	return "unknown";
+}
+
+/*
+ * Returns the audit category prefix prepended to the unprefixed blocker name
+ * returned by get_blocker() (filesystem and network access rights,
+ * change_topology, and scopes).  The ptrace blocker is standalone and carries
+ * its full name in get_blocker(), so it uses no prefix.
+ */
+static __attribute_const__ const char *
+blocker_prefix(const enum landlock_request_type type)
+{
+	switch (type) {
+	case LANDLOCK_REQUEST_PTRACE:
+		return "";
+
+	case LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY:
+	case LANDLOCK_REQUEST_FS_ACCESS:
+		return "fs.";
+
+	case LANDLOCK_REQUEST_NET_ACCESS:
+		return "net.";
+
+	case LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET:
+	case LANDLOCK_REQUEST_SCOPE_SIGNAL:
+		return "scope.";
+	}
+
+	WARN_ON_ONCE(1);
+	return "";
+}
+
+static void log_blockers(struct audit_buffer *const ab,
+			 const enum landlock_request_type type,
+			 const access_mask_t access)
+{
+	const unsigned long access_mask = access;
+	const char *const prefix = blocker_prefix(type);
+	unsigned long access_bit;
+	bool is_first = true;
+
+	for_each_set_bit(access_bit, &access_mask, BITS_PER_TYPE(access)) {
+		audit_log_format(ab, "%s%s%s", is_first ? "" : ",", prefix,
+				 get_blocker(type, access_bit));
+		is_first = false;
+	}
+	if (is_first)
+		audit_log_format(ab, "%s%s", prefix, get_blocker(type, -1));
+}
+
+static void log_domain(struct landlock_hierarchy *const hierarchy)
+{
+	struct audit_buffer *ab;
+
+	/* Ignores already logged domains.  */
+	if (READ_ONCE(hierarchy->log_status) == LANDLOCK_LOG_RECORDED)
+		return;
+
+	/* Uses consistent allocation flags wrt common_lsm_audit(). */
+	ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN,
+			     AUDIT_LANDLOCK_DOMAIN);
+	if (!ab)
+		return;
+
+	WARN_ON_ONCE(hierarchy->id == 0);
+	audit_log_format(
+		ab,
+		"domain=%llx status=allocated mode=enforcing pid=%d uid=%u exe=",
+		hierarchy->id, pid_nr(hierarchy->details->pid),
+		hierarchy->details->uid);
+	audit_log_untrustedstring(ab, hierarchy->details->exe_path);
+	audit_log_format(ab, " comm=");
+	audit_log_untrustedstring(ab, hierarchy->details->comm);
+	audit_log_end(ab);
+
+	/*
+	 * There may be race condition leading to logging of the same domain
+	 * several times but that is OK.
+	 */
+	WRITE_ONCE(hierarchy->log_status, LANDLOCK_LOG_RECORDED);
+}
+
+/**
+ * landlock_audit_denial - Create an audit record for a denied access request
+ *
+ * @request: Detail of the user space request.
+ * @youngest_denied: The youngest hierarchy node that denied the access.
+ * @missing: The set of denied access rights.
+ * @logged: Whether the denial is selected for logging, as computed by
+ *          landlock_log_denial() (domain policy and quiet rules).
+ *
+ * Emits the record when audit is enabled and the denial is selected for
+ * logging.
+ */
+void landlock_audit_denial(const struct landlock_request *const request,
+			   struct landlock_hierarchy *const youngest_denied,
+			   const access_mask_t missing, const bool logged)
+{
+	struct audit_buffer *ab;
+
+	if (!audit_enabled)
+		return;
+
+	/*
+	 * Skips denials the domain's policy or a quiet rule excludes from
+	 * logging (folded into @logged by landlock_log_denial()).
+	 */
+	if (!logged)
+		return;
+
+	/* Uses consistent allocation flags wrt common_lsm_audit(). */
+	ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN,
+			     AUDIT_LANDLOCK_ACCESS);
+	if (!ab)
+		return;
+
+	audit_log_format(ab, "domain=%llx blockers=", youngest_denied->id);
+	log_blockers(ab, request->type, missing);
+	audit_log_lsm_data(ab, &request->audit);
+	audit_log_end(ab);
+
+	/* Logs this domain the first time it shows in log. */
+	log_domain(youngest_denied);
+}
+
+/**
+ * landlock_audit_free_domain - Create an audit record on domain deallocation
+ *
+ * @hierarchy: The domain's hierarchy being deallocated.
+ *
+ * Only domains which previously appeared in the audit logs are logged again.
+ * This is useful to know when a domain will never show again in the audit log.
+ *
+ * Called from landlock_log_free_domain().
+ */
+void landlock_audit_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+	struct audit_buffer *ab;
+
+	if (!audit_enabled)
+		return;
+
+	/* Ignores domains that were not logged.  */
+	if (READ_ONCE(hierarchy->log_status) != LANDLOCK_LOG_RECORDED)
+		return;
+
+	/*
+	 * If logging of domain allocation succeeded, warns about failure to log
+	 * domain deallocation to highlight unbalanced domain lifetime logs.
+	 */
+	ab = audit_log_start(audit_context(), GFP_KERNEL,
+			     AUDIT_LANDLOCK_DOMAIN);
+	if (!ab)
+		return;
+
+	audit_log_format(ab, "domain=%llx status=deallocated denials=%llu",
+			 hierarchy->id, atomic64_read(&hierarchy->num_denials));
+	audit_log_end(ab);
+}
diff --git a/security/landlock/audit.h b/security/landlock/audit.h
new file mode 100644
index 000000000..14a514065
--- /dev/null
+++ b/security/landlock/audit.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Audit helpers
+ *
+ * Copyright © 2023-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_AUDIT_H
+#define _SECURITY_LANDLOCK_AUDIT_H
+
+#include <linux/types.h>
+
+#include "access.h"
+
+struct landlock_hierarchy;
+struct landlock_request;
+
+#ifdef CONFIG_AUDIT
+
+void landlock_audit_denial(const struct landlock_request *const request,
+			   struct landlock_hierarchy *const youngest_denied,
+			   const access_mask_t missing, const bool logged);
+
+void landlock_audit_free_domain(
+	const struct landlock_hierarchy *const hierarchy);
+
+#else /* CONFIG_AUDIT */
+
+static inline void
+landlock_audit_denial(const struct landlock_request *const request,
+		      struct landlock_hierarchy *const youngest_denied,
+		      const access_mask_t missing, const bool logged)
+{
+}
+
+static inline void
+landlock_audit_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+}
+
+#endif /* CONFIG_AUDIT */
+
+#endif /* _SECURITY_LANDLOCK_AUDIT_H */
diff --git a/security/landlock/common.h b/security/landlock/common.h
new file mode 100644
index 000000000..0eb1d34c2
--- /dev/null
+++ b/security/landlock/common.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Common constants and helpers
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_COMMON_H
+#define _SECURITY_LANDLOCK_COMMON_H
+
+#define LANDLOCK_NAME "landlock"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) LANDLOCK_NAME ": " fmt
+
+#define BIT_INDEX(bit) HWEIGHT(bit - 1)
+
+#endif /* _SECURITY_LANDLOCK_COMMON_H */
diff --git a/security/landlock/cred.c b/security/landlock/cred.c
new file mode 100644
index 000000000..03449c262
--- /dev/null
+++ b/security/landlock/cred.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Credential hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#include <linux/binfmts.h>
+#include <linux/cred.h>
+#include <linux/lsm_hooks.h>
+
+#include "common.h"
+#include "cred.h"
+#include "ruleset.h"
+#include "setup.h"
+
+static void hook_cred_transfer(struct cred *const new,
+			       const struct cred *const old)
+{
+	const struct landlock_cred_security *const old_llcred =
+		landlock_cred(old);
+
+	landlock_get_domain(old_llcred->domain);
+	*landlock_cred(new) = *old_llcred;
+}
+
+static int hook_cred_prepare(struct cred *const new,
+			     const struct cred *const old, const gfp_t gfp)
+{
+	hook_cred_transfer(new, old);
+	return 0;
+}
+
+static void hook_cred_free(struct cred *const cred)
+{
+	struct landlock_domain *const dom = landlock_cred(cred)->domain;
+
+	if (dom)
+		landlock_put_domain_deferred(dom);
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+static int hook_bprm_creds_for_exec(struct linux_binprm *const bprm)
+{
+	/* Resets for each execution. */
+	landlock_cred(bprm->cred)->domain_exec = 0;
+	return 0;
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static struct security_hook_list landlock_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(cred_prepare, hook_cred_prepare),
+	LSM_HOOK_INIT(cred_transfer, hook_cred_transfer),
+	LSM_HOOK_INIT(cred_free, hook_cred_free),
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	LSM_HOOK_INIT(bprm_creds_for_exec, hook_bprm_creds_for_exec),
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+};
+
+__init void landlock_add_cred_hooks(void)
+{
+	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+			   &landlock_lsmid);
+}
diff --git a/security/landlock/cred.h b/security/landlock/cred.h
new file mode 100644
index 000000000..a5ff99579
--- /dev/null
+++ b/security/landlock/cred.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Credential hooks
+ *
+ * Copyright © 2019-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ * Copyright © 2021-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_CRED_H
+#define _SECURITY_LANDLOCK_CRED_H
+
+#include <linux/container_of.h>
+#include <linux/cred.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+
+#include "access.h"
+#include "domain.h"
+#include "limits.h"
+#include "ruleset.h"
+#include "setup.h"
+
+/**
+ * struct landlock_cred_security - Credential security blob
+ *
+ * This structure is packed to minimize the size of struct
+ * landlock_file_security.  However, it is always aligned in the LSM cred blob,
+ * see lsm_set_blob_size().
+ *
+ * When updating this, also update landlock_cred_copy() if needed.
+ */
+struct landlock_cred_security {
+	/**
+	 * @domain: Immutable domain enforced on a task.
+	 */
+	struct landlock_domain *domain;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	/**
+	 * @domain_exec: Bitmask identifying the domain layers that were enforced by
+	 * the current task's executed file (i.e. no new execve(2) since
+	 * landlock_restrict_self(2)).
+	 */
+	u16 domain_exec;
+	/**
+	 * @log_subdomains_off: Set if the domain descendants's log_status should be
+	 * set to %LANDLOCK_LOG_DISABLED.  This is not a landlock_hierarchy
+	 * configuration because it applies to future descendant domains and it does
+	 * not require a current domain.
+	 */
+	u8 log_subdomains_off : 1;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+} __packed;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+/* Makes sure all layer executions can be stored. */
+static_assert(BITS_PER_TYPE(typeof_member(struct landlock_cred_security,
+					  domain_exec)) >=
+	      LANDLOCK_MAX_NUM_LAYERS);
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static inline struct landlock_cred_security *
+landlock_cred(const struct cred *cred)
+{
+	return cred->security + landlock_blob_sizes.lbs_cred;
+}
+
+static inline void landlock_cred_copy(struct landlock_cred_security *dst,
+				      const struct landlock_cred_security *src)
+{
+	landlock_put_domain(dst->domain);
+
+	*dst = *src;
+
+	landlock_get_domain(src->domain);
+}
+
+static inline struct landlock_domain *landlock_get_current_domain(void)
+{
+	return landlock_cred(current_cred())->domain;
+}
+
+/* The call needs to come from an RCU read-side critical section. */
+static inline const struct landlock_domain *
+landlock_get_task_domain(const struct task_struct *const task)
+{
+	return landlock_cred(__task_cred(task))->domain;
+}
+
+static inline bool landlocked(const struct task_struct *const task)
+{
+	bool has_dom;
+
+	if (task == current)
+		return !!landlock_get_current_domain();
+
+	rcu_read_lock();
+	has_dom = !!landlock_get_task_domain(task);
+	rcu_read_unlock();
+	return has_dom;
+}
+
+/**
+ * landlock_get_applicable_subject - Return the subject's Landlock credential
+ *                                   if its enforced domain applies to (i.e.
+ *                                   handles) at least one of the access rights
+ *                                   specified in @masks
+ *
+ * @cred: credential
+ * @masks: access masks
+ * @handle_layer: returned youngest layer handling a subset of @masks.  Not set
+ *                if the function returns NULL.
+ *
+ * Return: landlock_cred(@cred) if any access rights specified in @masks is
+ * handled, or NULL otherwise.
+ */
+static inline const struct landlock_cred_security *
+landlock_get_applicable_subject(const struct cred *const cred,
+				const struct access_masks masks,
+				size_t *const handle_layer)
+{
+	const union access_masks_all masks_all = {
+		.masks = masks,
+	};
+	const struct landlock_domain *domain;
+	ssize_t layer_level;
+
+	if (!cred)
+		return NULL;
+
+	domain = landlock_cred(cred)->domain;
+	if (!domain)
+		return NULL;
+
+	for (layer_level = domain->num_layers - 1; layer_level >= 0;
+	     layer_level--) {
+		union access_masks_all layer = {
+			.masks = domain->handled_masks[layer_level],
+		};
+
+		if (layer.all & masks_all.all) {
+			if (handle_layer)
+				*handle_layer = layer_level;
+
+			return landlock_cred(cred);
+		}
+	}
+
+	return NULL;
+}
+
+__init void landlock_add_cred_hooks(void);
+
+#endif /* _SECURITY_LANDLOCK_CRED_H */
diff --git a/security/landlock/domain.c b/security/landlock/domain.c
new file mode 100644
index 000000000..93c7104fd
--- /dev/null
+++ b/security/landlock/domain.c
@@ -0,0 +1,775 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Domain management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#include <kunit/test.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/file.h>
+#include <linux/lockdep.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/path.h>
+#include <linux/pid.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/sched.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <linux/uidgid.h>
+#include <linux/workqueue.h>
+
+#include "access.h"
+#include "common.h"
+#include "domain.h"
+#include "id.h"
+#include "limits.h"
+#include "ruleset.h"
+
+static void build_check_domain(void)
+{
+	const struct landlock_domain domain = {
+		.num_layers = ~0,
+	};
+
+	BUILD_BUG_ON(domain.num_layers < LANDLOCK_MAX_NUM_LAYERS);
+}
+
+static struct landlock_domain *create_domain(const u32 num_layers)
+{
+	struct landlock_domain *new_domain;
+
+	build_check_domain();
+	new_domain = kzalloc_flex(*new_domain, handled_masks, num_layers,
+				  GFP_KERNEL_ACCOUNT);
+	if (!new_domain)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&new_domain->usage, 1);
+	new_domain->rules.root_inode = RB_ROOT;
+
+#if IS_ENABLED(CONFIG_INET)
+	new_domain->rules.root_net_port = RB_ROOT;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	new_domain->num_layers = num_layers;
+	return new_domain;
+}
+
+static void free_domain(struct landlock_domain *const domain)
+{
+	might_sleep();
+	landlock_free_rules(&domain->rules);
+	landlock_put_hierarchy(domain->hierarchy);
+	kfree(domain);
+}
+
+void landlock_put_domain(struct landlock_domain *const domain)
+{
+	might_sleep();
+	if (domain && refcount_dec_and_test(&domain->usage))
+		free_domain(domain);
+}
+
+static void free_domain_work(struct work_struct *const work)
+{
+	struct landlock_domain *domain;
+
+	domain = container_of(work, struct landlock_domain, work_free);
+	free_domain(domain);
+}
+
+void landlock_put_domain_deferred(struct landlock_domain *const domain)
+{
+	if (domain && refcount_dec_and_test(&domain->usage)) {
+		INIT_WORK(&domain->work_free, free_domain_work);
+		schedule_work(&domain->work_free);
+	}
+}
+
+/* The returned access has the same lifetime as the domain. */
+static const struct landlock_rule *
+find_rule(const struct landlock_domain *const domain,
+	  const struct landlock_id id)
+{
+	const struct rb_root *root;
+	const struct rb_node *node;
+
+	root = landlock_get_rule_root((struct landlock_rules *)&domain->rules,
+				      id.type);
+	if (IS_ERR(root))
+		return NULL;
+	node = root->rb_node;
+
+	while (node) {
+		struct landlock_rule *this =
+			rb_entry(node, struct landlock_rule, node);
+
+		if (this->key.data == id.key.data)
+			return this;
+		if (this->key.data < id.key.data)
+			node = node->rb_right;
+		else
+			node = node->rb_left;
+	}
+	return NULL;
+}
+
+/**
+ * landlock_unmask_layers - Remove the access rights in @masks which are
+ *                          granted by a matching rule
+ *
+ * Looks up the rule matching @id in @domain, then updates the set of
+ * (per-layer) unfulfilled access rights @masks so that all the access rights
+ * granted by that rule are removed (because they are now fulfilled).
+ *
+ * @domain: The Landlock domain to search for a matching rule.
+ * @id: Identifier for the rule target (e.g. inode, port).
+ * @masks: A matrix of unfulfilled access rights for each layer.
+ * @matched_rule: Optional output for the matched rule (for tracing); set to
+ *                the matching rule when non-NULL, unchanged otherwise.
+ *
+ * Return: True if the request is allowed (i.e. the access rights granted all
+ * remaining unfulfilled access rights and masks has no leftover set bits).
+ */
+bool landlock_unmask_layers(const struct landlock_domain *const domain,
+			    const struct landlock_id id,
+			    struct layer_masks *masks,
+			    const struct landlock_rule **matched_rule)
+{
+	const struct landlock_rule *rule;
+
+	if (!masks)
+		return true;
+
+	rule = find_rule(domain, id);
+	if (!rule)
+		return false;
+
+	if (matched_rule)
+		*matched_rule = rule;
+
+	/*
+	 * An access is granted if, for each policy layer, at least one rule
+	 * encountered on the pathwalk grants the requested access, regardless
+	 * of its position in the layer stack.  We must then check the remaining
+	 * layers for each inode, from the first added layer to the last one.
+	 * When there are multiple requested accesses, for each policy layer,
+	 * the full set of requested accesses may not be granted by only one
+	 * rule, but by the union (binary OR) of multiple rules.  For example,
+	 * /a/b <execute> + /a <read> grants /a/b <execute + read>.
+	 *
+	 * This function is called once per matching rule during the pathwalk,
+	 * progressively clearing bits in @masks.  The overall access decision
+	 * is per-layer: access is granted iff masks->layers[l].access == 0 for
+	 * all layers l.  When two independent mechanisms can each grant access
+	 * within a layer (e.g. a path rule OR a scope exception), the
+	 * composition must evaluate per-layer: FOR-ALL l (A(l) OR B(l)), not
+	 * (FOR-ALL l A(l)) OR (FOR-ALL l B(l)), to prevent bypass when
+	 * different layers grant via different mechanisms.
+	 */
+	for (size_t i = 0; i < rule->num_layers; i++) {
+		const struct landlock_layer *const layer = &rule->layers[i];
+
+		/* Clear the bits where the layer in the rule grants access. */
+		masks->layers[layer->level - 1].access &= ~layer->access;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		/* Collect rule flags for each layer. */
+		if (layer->flags.quiet)
+			masks->layers[layer->level - 1].quiet = true;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	for (size_t i = 0; i < ARRAY_SIZE(masks->layers); i++) {
+		if (masks->layers[i].access)
+			return false;
+	}
+	return true;
+}
+
+typedef access_mask_t
+get_access_mask_t(const struct landlock_domain *const domain,
+		  const u16 layer_level);
+
+/**
+ * landlock_init_layer_masks - Initialize layer masks from an access request
+ *
+ * Populates @masks such that for each access right in @access_request, the bits
+ * for all the layers are set where this access right is handled.  Rule flags
+ * are also zeroed.
+ *
+ * @domain: The domain that defines the current restrictions.
+ * @access_request: The requested access rights to check.
+ * @masks: Layer access masks to populate.
+ * @key_type: The key type to switch between access masks of different types.
+ *
+ * Return: An access mask where each access right bit is set which is handled in
+ * any of the active layers in @domain.
+ */
+access_mask_t
+landlock_init_layer_masks(const struct landlock_domain *const domain,
+			  const access_mask_t access_request,
+			  struct layer_masks *const masks,
+			  const enum landlock_key_type key_type)
+{
+	access_mask_t handled_accesses = 0;
+	get_access_mask_t *get_access_mask;
+
+	switch (key_type) {
+	case LANDLOCK_KEY_INODE:
+		get_access_mask = landlock_get_fs_access_mask;
+		break;
+
+#if IS_ENABLED(CONFIG_INET)
+	case LANDLOCK_KEY_NET_PORT:
+		get_access_mask = landlock_get_net_access_mask;
+		break;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	default:
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	/* An empty access request can happen because of O_WRONLY | O_RDWR. */
+	if (!access_request)
+		return 0;
+
+	for (size_t i = 0; i < domain->num_layers; i++) {
+		const access_mask_t handled = get_access_mask(domain, i);
+
+		masks->layers[i].access = access_request & handled;
+		handled_accesses |= masks->layers[i].access;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		masks->layers[i].quiet = false;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+	for (size_t i = domain->num_layers; i < ARRAY_SIZE(masks->layers);
+	     i++) {
+		masks->layers[i].access = 0;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		masks->layers[i].quiet = false;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	return handled_accesses;
+}
+
+static int merge_tree(struct landlock_domain *const dst,
+		      struct landlock_ruleset *const src,
+		      const enum landlock_key_type key_type)
+{
+	struct landlock_rule *walker_rule, *next_rule;
+	struct rb_root *src_root;
+	int err = 0;
+
+	might_sleep();
+	lockdep_assert_held(&src->lock);
+
+	src_root = landlock_get_rule_root(&src->rules, key_type);
+	if (IS_ERR(src_root))
+		return PTR_ERR(src_root);
+
+	/* Merges the @src tree. */
+	rbtree_postorder_for_each_entry_safe(walker_rule, next_rule, src_root,
+					     node) {
+		struct landlock_layer layers[] = { {
+			.level = dst->num_layers,
+		} };
+		const struct landlock_id id = {
+			.key = walker_rule->key,
+			.type = key_type,
+		};
+
+		if (WARN_ON_ONCE(walker_rule->num_layers != 1))
+			return -EINVAL;
+
+		if (WARN_ON_ONCE(walker_rule->layers[0].level != 0))
+			return -EINVAL;
+
+		layers[0].access = walker_rule->layers[0].access;
+		layers[0].flags = walker_rule->layers[0].flags;
+
+		err = landlock_store_rule(&dst->rules, id, &layers,
+					  ARRAY_SIZE(layers));
+		if (err)
+			return err;
+	}
+	return err;
+}
+
+static int merge_ruleset(struct landlock_domain *const dst,
+			 struct landlock_ruleset *const src)
+{
+	int err = 0;
+
+	might_sleep();
+	/* Should already be checked by landlock_merge_ruleset() */
+	if (WARN_ON_ONCE(!src))
+		return 0;
+	/* Only merge into a domain. */
+	if (WARN_ON_ONCE(!dst || !dst->hierarchy))
+		return -EINVAL;
+
+	lockdep_assert_held(&src->lock);
+
+	/* Stacks the new layer. */
+	if (WARN_ON_ONCE(dst->num_layers < 1))
+		return -EINVAL;
+
+	dst->handled_masks[dst->num_layers - 1] =
+		landlock_upgrade_handled_access_masks(src->handled_masks);
+
+	/* Merges the @src inode tree. */
+	err = merge_tree(dst, src, LANDLOCK_KEY_INODE);
+	if (err)
+		return err;
+
+#if IS_ENABLED(CONFIG_INET)
+	/* Merges the @src network port tree. */
+	err = merge_tree(dst, src, LANDLOCK_KEY_NET_PORT);
+	if (err)
+		return err;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	return 0;
+}
+
+static int inherit_tree(struct landlock_domain *const parent,
+			struct landlock_domain *const child,
+			const enum landlock_key_type key_type)
+{
+	struct landlock_rule *walker_rule, *next_rule;
+	struct rb_root *parent_root;
+	int err = 0;
+
+	might_sleep();
+
+	parent_root = landlock_get_rule_root(&parent->rules, key_type);
+	if (IS_ERR(parent_root))
+		return PTR_ERR(parent_root);
+
+	/* Copies the @parent inode or network tree. */
+	rbtree_postorder_for_each_entry_safe(walker_rule, next_rule,
+					     parent_root, node) {
+		const struct landlock_id id = {
+			.key = walker_rule->key,
+			.type = key_type,
+		};
+
+		err = landlock_store_rule(&child->rules, id,
+					  &walker_rule->layers,
+					  walker_rule->num_layers);
+		if (err)
+			return err;
+	}
+	return err;
+}
+
+static int inherit_ruleset(struct landlock_domain *const parent,
+			   struct landlock_domain *const child)
+{
+	int err = 0;
+
+	might_sleep();
+	if (!parent)
+		return 0;
+
+	/* Copies the @parent inode tree. */
+	err = inherit_tree(parent, child, LANDLOCK_KEY_INODE);
+	if (err)
+		return err;
+
+#if IS_ENABLED(CONFIG_INET)
+	/* Copies the @parent network port tree. */
+	err = inherit_tree(parent, child, LANDLOCK_KEY_NET_PORT);
+	if (err)
+		return err;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	if (WARN_ON_ONCE(child->num_layers <= parent->num_layers))
+		return -EINVAL;
+
+	/*
+	 * Copies the parent layer stack and leaves a space for the new layer.
+	 */
+	memcpy(child->handled_masks, parent->handled_masks,
+	       flex_array_size(parent, handled_masks, parent->num_layers));
+
+	if (WARN_ON_ONCE(!parent->hierarchy))
+		return -EINVAL;
+
+	landlock_get_hierarchy(parent->hierarchy);
+	child->hierarchy->parent = parent->hierarchy;
+
+	return 0;
+}
+
+/**
+ * landlock_merge_ruleset - Merge a ruleset with a domain
+ *
+ * @parent: Parent domain.
+ * @ruleset: New ruleset to be merged.
+ *
+ * The current task is requesting to be restricted.  The subjective credentials
+ * must not be in an overridden state. cf. landlock_init_hierarchy_log().
+ *
+ * The caller must hold @ruleset->lock.
+ *
+ * Return: A new domain merging @parent and @ruleset on success, or ERR_PTR() on
+ * failure.  If @parent is NULL, the new domain duplicates @ruleset.
+ */
+struct landlock_domain *
+landlock_merge_ruleset(struct landlock_domain *const parent,
+		       struct landlock_ruleset *const ruleset)
+{
+	struct landlock_domain *new_dom __free(landlock_put_domain) = NULL;
+	u32 num_layers;
+	int err;
+
+	might_sleep();
+	lockdep_assert_held(&ruleset->lock);
+	if (WARN_ON_ONCE(!ruleset))
+		return ERR_PTR(-EINVAL);
+
+	if (parent) {
+		if (parent->num_layers >= LANDLOCK_MAX_NUM_LAYERS)
+			return ERR_PTR(-E2BIG);
+		num_layers = parent->num_layers + 1;
+	} else {
+		num_layers = 1;
+	}
+
+	/* Creates a new domain... */
+	new_dom = create_domain(num_layers);
+	if (IS_ERR(new_dom))
+		return new_dom;
+
+	new_dom->hierarchy =
+		kzalloc_obj(*new_dom->hierarchy, GFP_KERNEL_ACCOUNT);
+	if (!new_dom->hierarchy)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&new_dom->hierarchy->usage, 1);
+
+	/* ...as a child of @parent... */
+	err = inherit_ruleset(parent, new_dom);
+	if (err)
+		return ERR_PTR(err);
+
+	/* ...and including @ruleset. */
+	err = merge_ruleset(new_dom, ruleset);
+	if (err)
+		return ERR_PTR(err);
+
+	err = landlock_init_hierarchy_log(new_dom->hierarchy);
+	if (err)
+		return ERR_PTR(err);
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	new_dom->hierarchy->quiet_masks = ruleset->quiet_masks;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	return no_free_ptr(new_dom);
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+/**
+ * get_current_exe - Get the current's executable path, if any
+ *
+ * @exe_str: Returned pointer to a path string with a lifetime tied to the
+ *           returned buffer, if any.
+ * @exe_size: Returned size of @exe_str (including the trailing null
+ *            character), if any.
+ *
+ * Return: A pointer to an allocated buffer where @exe_str point to, %NULL if
+ * there is no executable path, or an error otherwise.
+ */
+static const void *get_current_exe(const char **const exe_str,
+				   size_t *const exe_size)
+{
+	const size_t buffer_size = LANDLOCK_PATH_MAX_SIZE;
+	struct mm_struct *mm = current->mm;
+	struct file *file __free(fput) = NULL;
+	char *buffer __free(kfree) = NULL;
+	const char *exe;
+	ssize_t size;
+
+	if (!mm)
+		return NULL;
+
+	file = get_mm_exe_file(mm);
+	if (!file)
+		return NULL;
+
+	buffer = kmalloc(buffer_size, GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	exe = d_path(&file->f_path, buffer, buffer_size);
+	if (WARN_ON_ONCE(IS_ERR(exe)))
+		/* Should never happen according to LANDLOCK_PATH_MAX_SIZE. */
+		return ERR_CAST(exe);
+
+	size = buffer + buffer_size - exe;
+	if (WARN_ON_ONCE(size <= 0))
+		return ERR_PTR(-ENAMETOOLONG);
+
+	*exe_size = size;
+	*exe_str = exe;
+	return no_free_ptr(buffer);
+}
+
+/*
+ * Return: A newly allocated object describing a domain, or an error
+ * otherwise.
+ */
+static struct landlock_details *get_current_details(void)
+{
+	/* Cf. audit_log_d_path_exe() */
+	static const char null_path[] = "(null)";
+	const char *path_str = null_path;
+	size_t path_size = sizeof(null_path);
+	const void *buffer __free(kfree) = NULL;
+	struct landlock_details *details;
+
+	buffer = get_current_exe(&path_str, &path_size);
+	if (IS_ERR(buffer))
+		return ERR_CAST(buffer);
+
+	/*
+	 * Create the new details according to the path's length.  Account to
+	 * the calling task's memcg, like the other Landlock per-domain
+	 * allocations, even if it may not control the related size.
+	 */
+	details =
+		kzalloc_flex(*details, exe_path, path_size, GFP_KERNEL_ACCOUNT);
+	if (!details)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(details->exe_path, path_str, path_size);
+	details->pid = get_pid(task_tgid(current));
+	details->uid = from_kuid(&init_user_ns, current_uid());
+	get_task_comm(details->comm, current);
+	return details;
+}
+
+/**
+ * landlock_init_hierarchy_log - Partially initialize landlock_hierarchy
+ *
+ * @hierarchy: The hierarchy to initialize.
+ *
+ * The current task is referenced as the domain that is enforcing the
+ * restriction.  The subjective credentials must not be in an overridden state.
+ *
+ * @hierarchy->parent and @hierarchy->usage should already be set.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy)
+{
+	struct landlock_details *details;
+
+	details = get_current_details();
+	if (IS_ERR(details))
+		return PTR_ERR(details);
+
+	hierarchy->details = details;
+	hierarchy->id = landlock_get_id_range(1);
+	/*
+	 * The hierarchy is born unobservable: landlock_restrict_self() moves it
+	 * out of LANDLOCK_LOG_UNCOMMITTED once it has emitted the creation
+	 * event, so the matching free_domain event fires for it and not for a
+	 * hierarchy whose creation was never observed.
+	 */
+	hierarchy->log_status = LANDLOCK_LOG_UNCOMMITTED;
+	hierarchy->log_same_exec = true;
+	hierarchy->log_new_exec = false;
+	atomic64_set(&hierarchy->num_denials, 0);
+	return 0;
+}
+
+static deny_masks_t
+get_layer_deny_mask(const access_mask_t all_existing_optional_access,
+		    const unsigned long access_bit, const size_t layer)
+{
+	unsigned long access_weight;
+
+	/* This may require change with new object types. */
+	WARN_ON_ONCE(all_existing_optional_access !=
+		     _LANDLOCK_ACCESS_FS_OPTIONAL);
+
+	if (WARN_ON_ONCE(layer >= LANDLOCK_MAX_NUM_LAYERS))
+		return 0;
+
+	access_weight = hweight_long(all_existing_optional_access &
+				     GENMASK(access_bit, 0));
+	if (WARN_ON_ONCE(access_weight < 1))
+		return 0;
+
+	return layer
+	       << ((access_weight - 1) * HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1));
+}
+
+/**
+ * landlock_get_quiet_optional_accesses - Get optional accesses which are
+ *                                        covered by quiet rule flags.
+ *
+ * @all_existing_optional_access: Bitmask of valid optional accesses.
+ * @deny_masks: Domain layer levels that denied each optional access (the
+ *              deny_masks field on struct landlock_file_security).
+ * @masks: The struct layer_masks collected during the path walk.
+ *
+ * Return: a bitmask of which optional accesses are denied by layers for which
+ * the quiet flag was collected during the path walk.
+ */
+optional_access_t landlock_get_quiet_optional_accesses(
+	const access_mask_t all_existing_optional_access,
+	const deny_masks_t deny_masks, const struct layer_masks *const masks)
+{
+	const unsigned long access_opt = all_existing_optional_access;
+	size_t access_index = 0;
+	unsigned long access_bit;
+	optional_access_t quiet_optional_accesses = 0;
+
+	/* This will require change with new object types. */
+	WARN_ON_ONCE(access_opt != _LANDLOCK_ACCESS_FS_OPTIONAL);
+
+	for_each_set_bit(access_bit, &access_opt,
+			 BITS_PER_TYPE(access_mask_t)) {
+		const u8 layer =
+			(deny_masks >> (access_index *
+					HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1))) &
+			(LANDLOCK_MAX_NUM_LAYERS - 1);
+
+		if (masks->layers[layer].quiet)
+			quiet_optional_accesses |= BIT(access_index);
+		access_index++;
+	}
+	return quiet_optional_accesses;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_get_layer_deny_mask(struct kunit *const test)
+{
+	const unsigned long truncate = BIT_INDEX(LANDLOCK_ACCESS_FS_TRUNCATE);
+	const unsigned long ioctl_dev = BIT_INDEX(LANDLOCK_ACCESS_FS_IOCTL_DEV);
+
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL,
+					    truncate, 0));
+	KUNIT_EXPECT_EQ(test, 0x3,
+			get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL,
+					    truncate, 3));
+
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL,
+					    ioctl_dev, 0));
+	KUNIT_EXPECT_EQ(test, 0xf0,
+			get_layer_deny_mask(_LANDLOCK_ACCESS_FS_OPTIONAL,
+					    ioctl_dev, 15));
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+deny_masks_t
+landlock_get_deny_masks(const access_mask_t all_existing_optional_access,
+			const access_mask_t optional_access,
+			const struct layer_masks *const masks)
+{
+	const unsigned long access_opt = optional_access;
+	unsigned long access_bit;
+	deny_masks_t deny_masks = 0;
+	access_mask_t all_denied = 0;
+
+	/* This may require change with new object types. */
+	WARN_ON_ONCE(!access_mask_subset(optional_access,
+					 all_existing_optional_access));
+
+	if (WARN_ON_ONCE(!masks))
+		return 0;
+
+	if (WARN_ON_ONCE(!access_opt))
+		return 0;
+
+	for (ssize_t i = ARRAY_SIZE(masks->layers) - 1; i >= 0; i--) {
+		const access_mask_t denied = masks->layers[i].access &
+					     optional_access;
+		const unsigned long newly_denied = denied & ~all_denied;
+
+		if (!newly_denied)
+			continue;
+
+		for_each_set_bit(access_bit, &newly_denied,
+				 8 * sizeof(access_mask_t)) {
+			deny_masks |= get_layer_deny_mask(
+				all_existing_optional_access, access_bit, i);
+		}
+		all_denied |= denied;
+	}
+	return deny_masks;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_landlock_get_deny_masks(struct kunit *const test)
+{
+	const struct layer_masks layers1 = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE |
+				    LANDLOCK_ACCESS_FS_IOCTL_DEV,
+		.layers[1].access = LANDLOCK_ACCESS_FS_TRUNCATE,
+		.layers[2].access = LANDLOCK_ACCESS_FS_IOCTL_DEV,
+		.layers[9].access = LANDLOCK_ACCESS_FS_EXECUTE,
+	};
+
+	KUNIT_EXPECT_EQ(test, 0x1,
+			landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL,
+						LANDLOCK_ACCESS_FS_TRUNCATE,
+						&layers1));
+	KUNIT_EXPECT_EQ(test, 0x20,
+			landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL,
+						LANDLOCK_ACCESS_FS_IOCTL_DEV,
+						&layers1));
+	KUNIT_EXPECT_EQ(
+		test, 0x21,
+		landlock_get_deny_masks(_LANDLOCK_ACCESS_FS_OPTIONAL,
+					LANDLOCK_ACCESS_FS_TRUNCATE |
+						LANDLOCK_ACCESS_FS_IOCTL_DEV,
+					&layers1));
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static struct kunit_case test_cases[] = {
+	/* clang-format off */
+	KUNIT_CASE(test_get_layer_deny_mask),
+	KUNIT_CASE(test_landlock_get_deny_masks),
+	{}
+	/* clang-format on */
+};
+
+static struct kunit_suite test_suite = {
+	.name = "landlock_domain",
+	.test_cases = test_cases,
+};
+
+kunit_test_suite(test_suite);
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
diff --git a/security/landlock/domain.h b/security/landlock/domain.h
new file mode 100644
index 000000000..5ce2f9148
--- /dev/null
+++ b/security/landlock/domain.h
@@ -0,0 +1,326 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Domain management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#ifndef _SECURITY_LANDLOCK_DOMAIN_H
+#define _SECURITY_LANDLOCK_DOMAIN_H
+
+#include <linux/cleanup.h>
+#include <linux/limits.h>
+#include <linux/mm.h>
+#include <linux/path.h>
+#include <linux/pid.h>
+#include <linux/refcount.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#include "access.h"
+#include "log.h"
+#include "ruleset.h"
+
+enum landlock_log_status {
+	/*
+	 * Hierarchy whose creation event has not been emitted, so it is not yet
+	 * observable from user space.  A hierarchy is born in this state (the
+	 * zero value, so a partially initialized hierarchy defaults to "not
+	 * observable") and leaves it when landlock_restrict_self() emits its
+	 * creation event, right after the merge and before the thread-sync
+	 * wait.  No trace free_domain event (and no audit deallocation record)
+	 * fires while a hierarchy is in this state, so a hierarchy that never
+	 * became observable (e.g. its initialization failed) is freed silently.
+	 * A domain aborted by a thread-sync failure already emitted its
+	 * creation event, so it is no longer UNCOMMITTED and does fire
+	 * free_domain.
+	 */
+	LANDLOCK_LOG_UNCOMMITTED = 0,
+	LANDLOCK_LOG_PENDING,
+	LANDLOCK_LOG_RECORDED,
+	LANDLOCK_LOG_DISABLED,
+};
+
+/**
+ * struct landlock_details - Domain's creation information
+ *
+ * Rarely accessed, mainly when logging the first domain's denial.
+ *
+ * The contained pointers are initialized at the domain creation time and never
+ * changed again.
+ */
+struct landlock_details {
+	/**
+	 * @pid: PID of the task that initially restricted itself.  It still
+	 * identifies the same task.  Keeping a reference to this PID ensures that
+	 * it will not be recycled.
+	 */
+	struct pid *pid;
+	/**
+	 * @uid: UID of the task that initially restricted itself, at creation time.
+	 */
+	uid_t uid;
+	/**
+	 * @comm: Command line of the task that initially restricted itself, at
+	 * creation time.  Always NULL terminated.
+	 */
+	char comm[TASK_COMM_LEN];
+	/**
+	 * @exe_path: Executable path of the task that initially restricted
+	 * itself, at creation time.  Always NULL terminated, and never greater
+	 * than LANDLOCK_PATH_MAX_SIZE.
+	 */
+	char exe_path[];
+};
+
+/* Adds 11 extra characters for the potential " (deleted)" suffix. */
+#define LANDLOCK_PATH_MAX_SIZE (PATH_MAX + 11)
+
+/* Makes sure the greatest landlock_details can be allocated. */
+static_assert(struct_size_t(struct landlock_details, exe_path,
+			    LANDLOCK_PATH_MAX_SIZE) <= KMALLOC_MAX_SIZE);
+
+/**
+ * struct landlock_hierarchy - Node in a domain hierarchy
+ */
+struct landlock_hierarchy {
+	/**
+	 * @parent: Pointer to the parent node, or NULL if it is a root
+	 * Landlock domain.
+	 */
+	struct landlock_hierarchy *parent;
+	/**
+	 * @usage: Number of potential children domains plus their parent
+	 * domain.
+	 */
+	refcount_t usage;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	/**
+	 * @log_status: Whether this domain should be logged or not.  Because
+	 * concurrent log entries may be created at the same time, it is still
+	 * possible to have several domain records of the same domain.
+	 */
+	enum landlock_log_status log_status;
+	/**
+	 * @num_denials: Number of access requests denied by this domain.
+	 * Masked (i.e. never logged) denials are still counted.
+	 */
+	atomic64_t num_denials;
+	/**
+	 * @id: Landlock domain ID, set once at domain creation time.
+	 */
+	u64 id;
+	/**
+	 * @details: Information about the related domain.
+	 */
+	const struct landlock_details *details;
+	/**
+	 * @log_same_exec: Set if the domain is *not* configured with
+	 * %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF.  Set to true by default.
+	 */
+	u32 log_same_exec : 1,
+		/**
+		 * @log_new_exec: Set if the domain is configured with
+		 * %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON.  Set to false by default.
+		 */
+		log_new_exec : 1;
+	/**
+	 * @quiet_masks: Bitmasks of access that should be quieted (i.e. not
+	 * logged) if the related object is marked as quiet.
+	 */
+	struct access_masks quiet_masks;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+};
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+deny_masks_t
+landlock_get_deny_masks(const access_mask_t all_existing_optional_access,
+			const access_mask_t optional_access,
+			const struct layer_masks *const masks);
+
+optional_access_t landlock_get_quiet_optional_accesses(
+	const access_mask_t all_existing_optional_access,
+	const deny_masks_t deny_masks, const struct layer_masks *const masks);
+
+int landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy);
+
+static inline void
+landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
+{
+	if (!hierarchy || !hierarchy->details)
+		return;
+
+	put_pid(hierarchy->details->pid);
+	kfree(hierarchy->details);
+}
+
+#else /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static inline int
+landlock_init_hierarchy_log(struct landlock_hierarchy *const hierarchy)
+{
+	return 0;
+}
+
+static inline void
+landlock_free_hierarchy_details(struct landlock_hierarchy *const hierarchy)
+{
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static inline void
+landlock_get_hierarchy(struct landlock_hierarchy *const hierarchy)
+{
+	if (hierarchy)
+		refcount_inc(&hierarchy->usage);
+}
+
+static inline void landlock_put_hierarchy(struct landlock_hierarchy *hierarchy)
+{
+	while (hierarchy && refcount_dec_and_test(&hierarchy->usage)) {
+		const struct landlock_hierarchy *const freeme = hierarchy;
+
+		landlock_log_free_domain(hierarchy);
+		landlock_free_hierarchy_details(hierarchy);
+		hierarchy = hierarchy->parent;
+		kfree(freeme);
+	}
+}
+
+/**
+ * struct landlock_domain - Immutable Landlock domain
+ *
+ * A domain is created from a ruleset by landlock_merge_ruleset() and enforced
+ * on a task.  Once created, its rules and access masks are immutable.  Unlike
+ * &struct landlock_ruleset, a domain has no lock field.
+ */
+struct landlock_domain {
+	/**
+	 * @rules: Red-black tree storage for rules.
+	 */
+	struct landlock_rules rules;
+	/**
+	 * @hierarchy: Enables hierarchy identification even when a parent
+	 * domain vanishes.  This is needed for the ptrace and scope
+	 * restrictions.
+	 */
+	struct landlock_hierarchy *hierarchy;
+	union {
+		/**
+		 * @work_free: Enables to free a domain within a lockless
+		 * section.  This is only used by landlock_put_domain_deferred()
+		 * when @usage reaches zero.  The fields @usage, @num_layers and
+		 * @handled_masks are then unused.
+		 */
+		struct work_struct work_free;
+		struct {
+			/**
+			 * @usage: Number of credentials referencing this
+			 * domain.
+			 */
+			refcount_t usage;
+			/**
+			 * @num_layers: Number of layers that are used in this
+			 * domain.  This enables to check that all the layers
+			 * allow an access request.
+			 */
+			u32 num_layers;
+			/**
+			 * @handled_masks: Contains the subset of filesystem and
+			 * network actions that are restricted by a domain.  A
+			 * domain saves all layers of merged rulesets in a stack
+			 * (FAM), starting from the first layer to the last one.
+			 * These layers are used when merging rulesets, for user
+			 * space backward compatibility (i.e. future-proof), and
+			 * to properly handle merged rulesets without
+			 * overlapping access rights.  These layers are set once
+			 * and never changed for the lifetime of the domain.
+			 */
+			struct access_masks handled_masks[];
+		};
+	};
+};
+
+static inline access_mask_t
+landlock_get_fs_access_mask(const struct landlock_domain *const domain,
+			    const u16 layer_level)
+{
+	/* Handles all initially denied by default access rights. */
+	return domain->handled_masks[layer_level].fs |
+	       _LANDLOCK_ACCESS_FS_INITIALLY_DENIED;
+}
+
+static inline access_mask_t
+landlock_get_net_access_mask(const struct landlock_domain *const domain,
+			     const u16 layer_level)
+{
+	return domain->handled_masks[layer_level].net;
+}
+
+static inline access_mask_t
+landlock_get_scope_mask(const struct landlock_domain *const domain,
+			const u16 layer_level)
+{
+	return domain->handled_masks[layer_level].scope;
+}
+
+/**
+ * landlock_union_access_masks - Return all access rights handled in the
+ *				 domain
+ *
+ * @domain: Landlock domain
+ *
+ * Return: An access_masks result of the OR of all the domain's access masks.
+ */
+static inline struct access_masks
+landlock_union_access_masks(const struct landlock_domain *const domain)
+{
+	union access_masks_all matches = {};
+	size_t layer_level;
+
+	for (layer_level = 0; layer_level < domain->num_layers; layer_level++) {
+		union access_masks_all layer = {
+			.masks = domain->handled_masks[layer_level],
+		};
+
+		matches.all |= layer.all;
+	}
+
+	return matches.masks;
+}
+
+void landlock_put_domain(struct landlock_domain *const domain);
+void landlock_put_domain_deferred(struct landlock_domain *const domain);
+
+DEFINE_FREE(landlock_put_domain, struct landlock_domain *,
+	    if (!IS_ERR_OR_NULL(_T)) landlock_put_domain(_T))
+
+struct landlock_domain *
+landlock_merge_ruleset(struct landlock_domain *const parent,
+		       struct landlock_ruleset *const ruleset);
+
+bool landlock_unmask_layers(const struct landlock_domain *const domain,
+			    const struct landlock_id id,
+			    struct layer_masks *masks,
+			    const struct landlock_rule **matched_rule);
+
+access_mask_t
+landlock_init_layer_masks(const struct landlock_domain *const domain,
+			  const access_mask_t access_request,
+			  struct layer_masks *masks,
+			  const enum landlock_key_type key_type);
+
+static inline void landlock_get_domain(struct landlock_domain *const domain)
+{
+	if (domain)
+		refcount_inc(&domain->usage);
+}
+
+#endif /* _SECURITY_LANDLOCK_DOMAIN_H */
diff --git a/security/landlock/errata.h b/security/landlock/errata.h
new file mode 100644
index 000000000..8e626acca
--- /dev/null
+++ b/security/landlock/errata.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Errata information
+ *
+ * Copyright © 2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_ERRATA_H
+#define _SECURITY_LANDLOCK_ERRATA_H
+
+#include <linux/init.h>
+
+struct landlock_erratum {
+	const int abi;
+	const u8 number;
+};
+
+/* clang-format off */
+#define LANDLOCK_ERRATUM(NUMBER) \
+	{ \
+		.abi = LANDLOCK_ERRATA_ABI, \
+		.number = NUMBER, \
+	},
+/* clang-format on */
+
+/*
+ * Some fixes may require user space to check if they are applied on the running
+ * kernel before using a specific feature.  For instance, this applies when a
+ * restriction was previously too restrictive and is now getting relaxed (for
+ * compatibility or semantic reasons).  However, non-visible changes for
+ * legitimate use (e.g. security fixes) do not require an erratum.
+ */
+static const struct landlock_erratum landlock_errata_init[] __initconst = {
+
+/*
+ * Only Sparse may not implement __has_include.  If a compiler does not
+ * implement __has_include, a warning will be printed at boot time (see
+ * setup.c).
+ */
+#ifdef __has_include
+
+#define LANDLOCK_ERRATA_ABI 1
+#if __has_include("errata/abi-1.h")
+#include "errata/abi-1.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+#define LANDLOCK_ERRATA_ABI 2
+#if __has_include("errata/abi-2.h")
+#include "errata/abi-2.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+#define LANDLOCK_ERRATA_ABI 3
+#if __has_include("errata/abi-3.h")
+#include "errata/abi-3.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+#define LANDLOCK_ERRATA_ABI 4
+#if __has_include("errata/abi-4.h")
+#include "errata/abi-4.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+#define LANDLOCK_ERRATA_ABI 5
+#if __has_include("errata/abi-5.h")
+#include "errata/abi-5.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+#define LANDLOCK_ERRATA_ABI 6
+#if __has_include("errata/abi-6.h")
+#include "errata/abi-6.h"
+#endif
+#undef LANDLOCK_ERRATA_ABI
+
+/*
+ * For each new erratum, we need to include all the ABI files up to the impacted
+ * ABI to make all potential future intermediate errata easy to backport.
+ *
+ * If such change involves more than one ABI addition, then it must be in a
+ * dedicated commit with the same Fixes tag as used for the actual fix.
+ *
+ * Each commit creating a new security/landlock/errata/abi-*.h file must have a
+ * Depends-on tag to reference the commit that previously added the line to
+ * include this new file, except if the original Fixes tag is enough.
+ *
+ * Each erratum must be documented in its related ABI file, and a dedicated
+ * commit must update Documentation/userspace-api/landlock.rst to include this
+ * erratum.  This commit will not be backported.
+ */
+
+#endif
+
+	{}
+};
+
+#endif /* _SECURITY_LANDLOCK_ERRATA_H */
diff --git a/security/landlock/errata/abi-1.h b/security/landlock/errata/abi-1.h
new file mode 100644
index 000000000..315ea7e0f
--- /dev/null
+++ b/security/landlock/errata/abi-1.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/**
+ * DOC: erratum_3
+ *
+ * Erratum 3: Disconnected directory handling
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This fix addresses an issue with disconnected directories that occur when a
+ * directory is moved outside the scope of a bind mount.  The change ensures
+ * that evaluated access rights include both those from the disconnected file
+ * hierarchy down to its filesystem root and those from the related mount point
+ * hierarchy.  This prevents access right widening through rename or link
+ * actions.
+ *
+ * Impact:
+ *
+ * Without this fix, it was possible to widen access rights through rename or
+ * link actions involving disconnected directories, potentially bypassing
+ * ``LANDLOCK_ACCESS_FS_REFER`` restrictions.  This could allow privilege
+ * escalation in complex mount scenarios where directories become disconnected
+ * from their original mount points.
+ */
+LANDLOCK_ERRATUM(3)
+
+/**
+ * DOC: erratum_4
+ *
+ * Erratum 4: Creation of whiteout objects
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This fix changes the access rights required for the creation of whiteout
+ * objects through :manpage:`mknod(2)`, :manpage:`renameat2(2)`, or
+ * :manpage:`link(2)`.  Creating whiteout objects is now guarded by
+ * ``LANDLOCK_ACCESS_FS_MAKE_REG`` instead of ``LANDLOCK_ACCESS_FS_MAKE_CHAR``.
+ *
+ * Whiteout objects are used in OverlayFS to mark the absence of a file in an
+ * upper file system.  Despite being created with ``S_IFCHR``, whiteout objects
+ * do not count as character devices.
+ *
+ * Impact:
+ *
+ * Sandboxed programs that create OverlayFS whiteouts (such as fuse-overlayfs)
+ * now require ``LANDLOCK_ACCESS_FS_MAKE_REG`` instead of
+ * ``LANDLOCK_ACCESS_FS_MAKE_CHAR``.
+ */
+LANDLOCK_ERRATUM(4)
diff --git a/security/landlock/errata/abi-4.h b/security/landlock/errata/abi-4.h
new file mode 100644
index 000000000..fe11ec7d7
--- /dev/null
+++ b/security/landlock/errata/abi-4.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/**
+ * DOC: erratum_1
+ *
+ * Erratum 1: TCP socket identification
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This fix addresses an issue where IPv4 and IPv6 stream sockets (e.g., SMC,
+ * MPTCP, or SCTP) were incorrectly restricted by TCP access rights during
+ * :manpage:`bind(2)` and :manpage:`connect(2)` operations. This change ensures
+ * that only TCP sockets are subject to TCP access rights, allowing other
+ * protocols to operate without unnecessary restrictions.
+ *
+ * Impact:
+ *
+ * In kernels without this fix, using ``LANDLOCK_ACCESS_NET_BIND_TCP`` or
+ * ``LANDLOCK_ACCESS_NET_CONNECT_TCP`` would incorrectly restrict non-TCP
+ * stream protocols (SMC, MPTCP, SCTP), potentially breaking applications
+ * that rely on these protocols while using Landlock network restrictions.
+ */
+LANDLOCK_ERRATUM(1)
diff --git a/security/landlock/errata/abi-6.h b/security/landlock/errata/abi-6.h
new file mode 100644
index 000000000..5cb1475c7
--- /dev/null
+++ b/security/landlock/errata/abi-6.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/**
+ * DOC: erratum_2
+ *
+ * Erratum 2: Scoped signal handling
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ * This fix addresses an issue where signal scoping was overly restrictive,
+ * preventing sandboxed threads from signaling other threads within the same
+ * process if they belonged to different domains.  Because threads are not
+ * security boundaries, user space might assume that all threads within the same
+ * process can send signals between themselves (see :manpage:`nptl(7)` and
+ * :manpage:`libpsx(3)`).  Consistent with :manpage:`ptrace(2)` behavior, direct
+ * interaction between threads of the same process should always be allowed.
+ * This change ensures that any thread is allowed to send signals to any other
+ * thread within the same process, regardless of their domain.
+ *
+ * Impact:
+ *
+ * This problem only manifests when the userspace process is itself using
+ * :manpage:`libpsx(3)` or an equivalent mechanism to enforce a Landlock policy
+ * on multiple already-running threads at once.  Programs which enforce a
+ * Landlock policy at startup time and only then become multithreaded are not
+ * affected.  Without this fix, signal scoping could break multi-threaded
+ * applications that expect threads within the same process to freely signal
+ * each other.
+ */
+LANDLOCK_ERRATUM(2)
diff --git a/security/landlock/fs.c b/security/landlock/fs.c
new file mode 100644
index 000000000..30aa6ce13
--- /dev/null
+++ b/security/landlock/fs.c
@@ -0,0 +1,2136 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Filesystem management and hooks
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2021-2025 Microsoft Corporation
+ * Copyright © 2022 Günther Noack <gnoack3000@gmail.com>
+ * Copyright © 2023-2024 Google LLC
+ */
+
+#include <asm/ioctls.h>
+#include <kunit/test.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler_types.h>
+#include <linux/dcache.h>
+#include <linux/err.h>
+#include <linux/falloc.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/lsm_audit.h>
+#include <linux/lsm_hooks.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/net.h>
+#include <linux/path.h>
+#include <linux/pid.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
+#include <linux/spinlock.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+#include <linux/wait_bit.h>
+#include <linux/workqueue.h>
+#include <net/af_unix.h>
+#include <uapi/linux/fiemap.h>
+#include <uapi/linux/landlock.h>
+
+#include "access.h"
+#include "common.h"
+#include "cred.h"
+#include "domain.h"
+#include "fs.h"
+#include "limits.h"
+#include "log.h"
+#include "object.h"
+#include "ruleset.h"
+#include "setup.h"
+
+#include <trace/events/landlock.h>
+
+/* Underlying object management */
+
+static void release_inode(struct landlock_object *const object)
+	__releases(object->lock)
+{
+	struct inode *const inode = object->underobj;
+	struct super_block *sb;
+
+	if (!inode) {
+		spin_unlock(&object->lock);
+		return;
+	}
+
+	/*
+	 * Protects against concurrent use by hook_sb_delete() of the reference
+	 * to the underlying inode.
+	 */
+	object->underobj = NULL;
+	/*
+	 * Makes sure that if the filesystem is concurrently unmounted,
+	 * hook_sb_delete() will wait for us to finish iput().
+	 */
+	sb = inode->i_sb;
+	atomic_long_inc(&landlock_superblock(sb)->inode_refs);
+	spin_unlock(&object->lock);
+	/*
+	 * Because object->underobj was not NULL, hook_sb_delete() and
+	 * get_inode_object() guarantee that it is safe to reset
+	 * landlock_inode(inode)->object while it is not NULL.  It is therefore
+	 * not necessary to lock inode->i_lock.
+	 */
+	rcu_assign_pointer(landlock_inode(inode)->object, NULL);
+	/*
+	 * Now, new rules can safely be tied to @inode with get_inode_object().
+	 */
+
+	iput(inode);
+	if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs))
+		wake_up_var(&landlock_superblock(sb)->inode_refs);
+}
+
+static const struct landlock_object_underops landlock_fs_underops = {
+	.release = release_inode
+};
+
+/* IOCTL helpers */
+
+/**
+ * is_masked_device_ioctl - Determine whether an IOCTL command is always
+ * permitted with Landlock for device files.  These commands can not be
+ * restricted on device files by enforcing a Landlock policy.
+ *
+ * @cmd: The IOCTL command that is supposed to be run.
+ *
+ * By default, any IOCTL on a device file requires the
+ * LANDLOCK_ACCESS_FS_IOCTL_DEV right.  However, we blanket-permit some
+ * commands, if:
+ *
+ * 1. The command is implemented in fs/ioctl.c's do_vfs_ioctl(),
+ *    not in f_ops->unlocked_ioctl() or f_ops->compat_ioctl().
+ *
+ * 2. The command is harmless when invoked on devices.
+ *
+ * We also permit commands that do not make sense for devices, but where the
+ * do_vfs_ioctl() implementation returns a more conventional error code.
+ *
+ * Any new IOCTL commands that are implemented in fs/ioctl.c's do_vfs_ioctl()
+ * should be considered for inclusion here.
+ *
+ * Return: True if the IOCTL @cmd can not be restricted with Landlock for
+ * device files, false otherwise.
+ */
+static __attribute_const__ bool is_masked_device_ioctl(const unsigned int cmd)
+{
+	switch (cmd) {
+	/*
+	 * FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC manipulate the FD's
+	 * close-on-exec and the file's buffered-IO and async flags.  These
+	 * operations are also available through fcntl(2), and are
+	 * unconditionally permitted in Landlock.
+	 */
+	case FIOCLEX:
+	case FIONCLEX:
+	case FIONBIO:
+	case FIOASYNC:
+	/*
+	 * FIOQSIZE queries the size of a regular file, directory, or link.
+	 *
+	 * We still permit it, because it always returns -ENOTTY for
+	 * other file types.
+	 */
+	case FIOQSIZE:
+	/*
+	 * FIFREEZE and FITHAW freeze and thaw the file system which the
+	 * given file belongs to.  Requires CAP_SYS_ADMIN.
+	 *
+	 * These commands operate on the file system's superblock rather
+	 * than on the file itself.  The same operations can also be
+	 * done through any other file or directory on the same file
+	 * system, so it is safe to permit these.
+	 */
+	case FIFREEZE:
+	case FITHAW:
+	/*
+	 * FS_IOC_FIEMAP queries information about the allocation of
+	 * blocks within a file.
+	 *
+	 * This IOCTL command only makes sense for regular files and is
+	 * not implemented by devices. It is harmless to permit.
+	 */
+	case FS_IOC_FIEMAP:
+	/*
+	 * FIGETBSZ queries the file system's block size for a file or
+	 * directory.
+	 *
+	 * This command operates on the file system's superblock rather
+	 * than on the file itself.  The same operation can also be done
+	 * through any other file or directory on the same file system,
+	 * so it is safe to permit it.
+	 */
+	case FIGETBSZ:
+	/*
+	 * FICLONE, FICLONERANGE and FIDEDUPERANGE make files share
+	 * their underlying storage ("reflink") between source and
+	 * destination FDs, on file systems which support that.
+	 *
+	 * These IOCTL commands only apply to regular files
+	 * and are harmless to permit for device files.
+	 */
+	case FICLONE:
+	case FICLONERANGE:
+	case FIDEDUPERANGE:
+	/*
+	 * FS_IOC_GETFSUUID and FS_IOC_GETFSSYSFSPATH both operate on
+	 * the file system superblock, not on the specific file, so
+	 * these operations are available through any other file on the
+	 * same file system as well.
+	 */
+	case FS_IOC_GETFSUUID:
+	case FS_IOC_GETFSSYSFSPATH:
+		return true;
+
+	/*
+	 * FIONREAD, FS_IOC_GETFLAGS, FS_IOC_SETFLAGS, FS_IOC_FSGETXATTR and
+	 * FS_IOC_FSSETXATTR are forwarded to device implementations.
+	 */
+
+	/*
+	 * file_ioctl() commands (FIBMAP, FS_IOC_RESVSP, FS_IOC_RESVSP64,
+	 * FS_IOC_UNRESVSP, FS_IOC_UNRESVSP64 and FS_IOC_ZERO_RANGE) are
+	 * forwarded to device implementations, so not permitted.
+	 */
+
+	/* Other commands are guarded by the access right. */
+	default:
+		return false;
+	}
+}
+
+/*
+ * is_masked_device_ioctl_compat - same as the helper above, but checking the
+ * "compat" IOCTL commands.
+ *
+ * The IOCTL commands with special handling in compat-mode should behave the
+ * same as their non-compat counterparts.
+ */
+static __attribute_const__ bool
+is_masked_device_ioctl_compat(const unsigned int cmd)
+{
+	switch (cmd) {
+	/* FICLONE is permitted, same as in the non-compat variant. */
+	case FICLONE:
+		return true;
+
+#if defined(CONFIG_X86_64)
+	/*
+	 * FS_IOC_RESVSP_32, FS_IOC_RESVSP64_32, FS_IOC_UNRESVSP_32,
+	 * FS_IOC_UNRESVSP64_32, FS_IOC_ZERO_RANGE_32: not blanket-permitted,
+	 * for consistency with their non-compat variants.
+	 */
+	case FS_IOC_RESVSP_32:
+	case FS_IOC_RESVSP64_32:
+	case FS_IOC_UNRESVSP_32:
+	case FS_IOC_UNRESVSP64_32:
+	case FS_IOC_ZERO_RANGE_32:
+#endif
+
+	/*
+	 * FS_IOC32_GETFLAGS, FS_IOC32_SETFLAGS are forwarded to their device
+	 * implementations.
+	 */
+	case FS_IOC32_GETFLAGS:
+	case FS_IOC32_SETFLAGS:
+		return false;
+	default:
+		return is_masked_device_ioctl(cmd);
+	}
+}
+
+/* Ruleset management */
+
+static struct landlock_object *get_inode_object(struct inode *const inode)
+{
+	struct landlock_object *object, *new_object;
+	struct landlock_inode_security *inode_sec = landlock_inode(inode);
+
+	rcu_read_lock();
+retry:
+	object = rcu_dereference(inode_sec->object);
+	if (object) {
+		if (likely(refcount_inc_not_zero(&object->usage))) {
+			rcu_read_unlock();
+			return object;
+		}
+		/*
+		 * We are racing with release_inode(), the object is going
+		 * away.  Wait for release_inode(), then retry.
+		 */
+		spin_lock(&object->lock);
+		spin_unlock(&object->lock);
+		goto retry;
+	}
+	rcu_read_unlock();
+
+	/*
+	 * If there is no object tied to @inode, then create a new one (without
+	 * holding any locks).
+	 */
+	new_object = landlock_create_object(&landlock_fs_underops, inode);
+	if (IS_ERR(new_object))
+		return new_object;
+
+	/*
+	 * Protects against concurrent calls to get_inode_object() or
+	 * hook_sb_delete().
+	 */
+	spin_lock(&inode->i_lock);
+	if (unlikely(rcu_access_pointer(inode_sec->object))) {
+		/* Someone else just created the object, bail out and retry. */
+		spin_unlock(&inode->i_lock);
+		kfree(new_object);
+
+		rcu_read_lock();
+		goto retry;
+	}
+
+	/*
+	 * @inode will be released by hook_sb_delete() on its superblock
+	 * shutdown, or by release_inode() when no more ruleset references the
+	 * related object.
+	 */
+	ihold(inode);
+	rcu_assign_pointer(inode_sec->object, new_object);
+	spin_unlock(&inode->i_lock);
+	return new_object;
+}
+
+/* All access rights that can be tied to files. */
+/* clang-format off */
+#define ACCESS_FILE ( \
+	LANDLOCK_ACCESS_FS_EXECUTE | \
+	LANDLOCK_ACCESS_FS_WRITE_FILE | \
+	LANDLOCK_ACCESS_FS_READ_FILE | \
+	LANDLOCK_ACCESS_FS_TRUNCATE | \
+	LANDLOCK_ACCESS_FS_IOCTL_DEV | \
+	LANDLOCK_ACCESS_FS_RESOLVE_UNIX)
+/* clang-format on */
+
+/*
+ * @path: Should have been checked by get_path_from_fd().
+ */
+int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
+			    const struct path *const path,
+			    access_mask_t access_rights, const u32 flags)
+{
+	int err;
+	struct landlock_id id = {
+		.type = LANDLOCK_KEY_INODE,
+	};
+
+	/* Files only get access rights that make sense. */
+	if (!d_is_dir(path->dentry) &&
+	    !access_mask_subset(access_rights, ACCESS_FILE))
+		return -EINVAL;
+
+	/* Transforms relative access rights to absolute ones. */
+	access_rights |= LANDLOCK_MASK_ACCESS_FS &
+			 ~(ruleset->handled_masks.fs |
+			   _LANDLOCK_ACCESS_FS_INITIALLY_DENIED);
+	id.key.object = get_inode_object(d_backing_inode(path->dentry));
+	if (IS_ERR(id.key.object))
+		return PTR_ERR(id.key.object);
+	mutex_lock(&ruleset->lock);
+	err = landlock_insert_rule(ruleset, id, access_rights, flags);
+
+	/*
+	 * Emit after the rule insertion succeeds, so every event corresponds to
+	 * a rule that is actually in the ruleset.  The ruleset lock is still
+	 * held for BTF consistency (enforced by lockdep_assert_held in
+	 * TP_fast_assign).
+	 */
+	if (!err && trace_landlock_add_rule_fs_enabled()) {
+		char *buffer __free(__putname) = __getname();
+		const char *pathname =
+			buffer ? resolve_path_for_trace(path, buffer) :
+				 "<no_mem>";
+
+		trace_landlock_add_rule_fs(ruleset, access_rights, path,
+					   pathname);
+	}
+	mutex_unlock(&ruleset->lock);
+
+	/*
+	 * No need to check for an error because landlock_insert_rule()
+	 * increments the refcount for the new object if needed.
+	 */
+	landlock_put_object(id.key.object);
+	return err;
+}
+
+/* Access-control management */
+
+/**
+ * get_inode_id - Look up the Landlock object for a dentry
+ * @dentry: The dentry to look up.
+ * @id: Filled with the inode's Landlock object pointer on success.
+ *
+ * Extracts the Landlock object pointer from @dentry's inode security blob and
+ * stores it in @id for use as a rule-tree lookup key.
+ *
+ * When this returns false (negative dentry or no Landlock object), no rule can
+ * match this inode, so landlock_unmask_layers() need not be called.  Callers
+ * that gate landlock_unmask_layers() on this function must handle the NULL
+ * masks case independently, since the !masks-returns-true early-return in
+ * landlock_unmask_layers() will not be reached.  See the allowed_parent2
+ * initialization in is_access_to_paths_allowed().
+ *
+ * Return: True if a Landlock object exists for @dentry, false otherwise.
+ */
+static bool get_inode_id(const struct dentry *const dentry,
+			 struct landlock_id *id)
+{
+	/* Ignores nonexistent leafs. */
+	if (d_is_negative(dentry))
+		return false;
+
+	/*
+	 * rcu_access_pointer() is sufficient: the pointer is used only as a
+	 * numeric comparison key for rule lookup, not dereferenced.  The object
+	 * cannot be freed while the domain exists because the domain's rule
+	 * tree holds its own reference to it.
+	 */
+	id->key.object = rcu_access_pointer(
+		landlock_inode(d_backing_inode(dentry))->object);
+	return !!id->key.object;
+}
+
+static bool unmask_layers_fs(const struct landlock_domain *const domain,
+			     const struct landlock_id id,
+			     const access_mask_t access_request,
+			     struct layer_masks *masks,
+			     const struct dentry *const dentry)
+{
+	const struct landlock_rule *rule = NULL;
+	bool ret;
+
+	ret = landlock_unmask_layers(domain, id, masks, &rule);
+	if (rule)
+		trace_landlock_check_rule_fs(domain, rule, access_request,
+					     dentry);
+	return ret;
+}
+
+/*
+ * Allows access to pseudo filesystems that will never be mountable (e.g.
+ * sockfs, pipefs), but can still be reachable through
+ * /proc/<pid>/fd/<file-descriptor>
+ */
+static bool is_nouser_or_private(const struct dentry *dentry)
+{
+	return (dentry->d_sb->s_flags & SB_NOUSER) ||
+	       (d_is_positive(dentry) &&
+		unlikely(IS_PRIVATE(d_backing_inode(dentry))));
+}
+
+static const struct access_masks any_fs = {
+	.fs = ~0,
+};
+
+/*
+ * Returns true iff the child file with the given src_child access rights under
+ * src_parent would result in having the same or fewer access rights if it were
+ * moved under new_parent.
+ */
+static bool may_refer(const struct layer_masks *const src_parent,
+		      const struct layer_masks *const src_child,
+		      const struct layer_masks *const new_parent,
+		      const bool child_is_dir)
+{
+	for (size_t i = 0; i < ARRAY_SIZE(new_parent->layers); i++) {
+		access_mask_t child_access = src_parent->layers[i].access &
+					     src_child->layers[i].access;
+		access_mask_t parent_access = new_parent->layers[i].access;
+
+		if (!child_is_dir) {
+			child_access &= ACCESS_FILE;
+			parent_access &= ACCESS_FILE;
+		}
+
+		if (!access_mask_subset(child_access, parent_access))
+			return false;
+	}
+	return true;
+}
+
+/*
+ * Check that a destination file hierarchy has more restrictions than a source
+ * file hierarchy.  This is only used for link and rename actions.
+ *
+ * Return: True if child1 may be moved from parent1 to parent2 without
+ * increasing its access rights (if child2 is set, an additional condition is
+ * that child2 may be used from parent2 to parent1 without increasing its access
+ * rights), false otherwise.
+ */
+static bool no_more_access(const struct layer_masks *const parent1,
+			   const struct layer_masks *const child1,
+			   const bool child1_is_dir,
+			   const struct layer_masks *const parent2,
+			   const struct layer_masks *const child2,
+			   const bool child2_is_dir)
+{
+	if (!may_refer(parent1, child1, parent2, child1_is_dir))
+		return false;
+
+	if (!child2)
+		return true;
+
+	return may_refer(parent2, child2, parent1, child2_is_dir);
+}
+
+#define NMA_TRUE(...) KUNIT_EXPECT_TRUE(test, no_more_access(__VA_ARGS__))
+#define NMA_FALSE(...) KUNIT_EXPECT_FALSE(test, no_more_access(__VA_ARGS__))
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_no_more_access(struct kunit *const test)
+{
+	const struct layer_masks rx0 = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE |
+				    LANDLOCK_ACCESS_FS_READ_FILE,
+	};
+	const struct layer_masks mx0 = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE |
+				    LANDLOCK_ACCESS_FS_MAKE_REG,
+	};
+	const struct layer_masks x0 = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE,
+	};
+	const struct layer_masks x1 = {
+		.layers[1].access = LANDLOCK_ACCESS_FS_EXECUTE,
+	};
+	const struct layer_masks x01 = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE,
+		.layers[1].access = LANDLOCK_ACCESS_FS_EXECUTE,
+	};
+	const struct layer_masks allows_all = {};
+
+	/* Checks without restriction. */
+	NMA_TRUE(&x0, &allows_all, false, &allows_all, NULL, false);
+	NMA_TRUE(&allows_all, &x0, false, &allows_all, NULL, false);
+	NMA_FALSE(&x0, &x0, false, &allows_all, NULL, false);
+
+	/*
+	 * Checks that we can only refer a file if no more access could be
+	 * inherited.
+	 */
+	NMA_TRUE(&x0, &x0, false, &rx0, NULL, false);
+	NMA_TRUE(&rx0, &rx0, false, &rx0, NULL, false);
+	NMA_FALSE(&rx0, &rx0, false, &x0, NULL, false);
+	NMA_FALSE(&rx0, &rx0, false, &x1, NULL, false);
+
+	/* Checks allowed referring with different nested domains. */
+	NMA_TRUE(&x0, &x1, false, &x0, NULL, false);
+	NMA_TRUE(&x1, &x0, false, &x0, NULL, false);
+	NMA_TRUE(&x0, &x01, false, &x0, NULL, false);
+	NMA_TRUE(&x0, &x01, false, &rx0, NULL, false);
+	NMA_TRUE(&x01, &x0, false, &x0, NULL, false);
+	NMA_TRUE(&x01, &x0, false, &rx0, NULL, false);
+	NMA_FALSE(&x01, &x01, false, &x0, NULL, false);
+
+	/* Checks that file access rights are also enforced for a directory. */
+	NMA_FALSE(&rx0, &rx0, true, &x0, NULL, false);
+
+	/* Checks that directory access rights don't impact file referring... */
+	NMA_TRUE(&mx0, &mx0, false, &x0, NULL, false);
+	/* ...but only directory referring. */
+	NMA_FALSE(&mx0, &mx0, true, &x0, NULL, false);
+
+	/* Checks directory exchange. */
+	NMA_TRUE(&mx0, &mx0, true, &mx0, &mx0, true);
+	NMA_TRUE(&mx0, &mx0, true, &mx0, &x0, true);
+	NMA_FALSE(&mx0, &mx0, true, &x0, &mx0, true);
+	NMA_FALSE(&mx0, &mx0, true, &x0, &x0, true);
+	NMA_FALSE(&mx0, &mx0, true, &x1, &x1, true);
+
+	/* Checks file exchange with directory access rights... */
+	NMA_TRUE(&mx0, &mx0, false, &mx0, &mx0, false);
+	NMA_TRUE(&mx0, &mx0, false, &mx0, &x0, false);
+	NMA_TRUE(&mx0, &mx0, false, &x0, &mx0, false);
+	NMA_TRUE(&mx0, &mx0, false, &x0, &x0, false);
+	/* ...and with file access rights. */
+	NMA_TRUE(&rx0, &rx0, false, &rx0, &rx0, false);
+	NMA_TRUE(&rx0, &rx0, false, &rx0, &x0, false);
+	NMA_FALSE(&rx0, &rx0, false, &x0, &rx0, false);
+	NMA_FALSE(&rx0, &rx0, false, &x0, &x0, false);
+	NMA_FALSE(&rx0, &rx0, false, &x1, &x1, false);
+
+	/*
+	 * Allowing the following requests should not be a security risk
+	 * because domain 0 denies execute access, and domain 1 is always
+	 * nested with domain 0.  However, adding an exception for this case
+	 * would mean to check all nested domains to make sure none can get
+	 * more privileges (e.g. processes only sandboxed by domain 0).
+	 * Moreover, this behavior (i.e. composition of N domains) could then
+	 * be inconsistent compared to domain 1's ruleset alone (e.g. it might
+	 * be denied to link/rename with domain 1's ruleset, whereas it would
+	 * be allowed if nested on top of domain 0).  Another drawback would be
+	 * to create a cover channel that could enable sandboxed processes to
+	 * infer most of the filesystem restrictions from their domain.  To
+	 * make it simple, efficient, safe, and more consistent, this case is
+	 * always denied.
+	 */
+	NMA_FALSE(&x1, &x1, false, &x0, NULL, false);
+	NMA_FALSE(&x1, &x1, false, &rx0, NULL, false);
+	NMA_FALSE(&x1, &x1, true, &x0, NULL, false);
+	NMA_FALSE(&x1, &x1, true, &rx0, NULL, false);
+
+	/* Checks the same case of exclusive domains with a file... */
+	NMA_TRUE(&x1, &x1, false, &x01, NULL, false);
+	NMA_FALSE(&x1, &x1, false, &x01, &x0, false);
+	NMA_FALSE(&x1, &x1, false, &x01, &x01, false);
+	NMA_FALSE(&x1, &x1, false, &x0, &x0, false);
+	/* ...and with a directory. */
+	NMA_FALSE(&x1, &x1, false, &x0, &x0, true);
+	NMA_FALSE(&x1, &x1, true, &x0, &x0, false);
+	NMA_FALSE(&x1, &x1, true, &x0, &x0, true);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+#undef NMA_TRUE
+#undef NMA_FALSE
+
+static bool is_layer_masks_allowed(const struct layer_masks *masks)
+{
+	for (size_t i = 0; i < ARRAY_SIZE(masks->layers); i++) {
+		if (masks->layers[i].access)
+			return false;
+	}
+	return true;
+}
+
+/*
+ * Removes @masks accesses that are not requested.
+ *
+ * Returns true if the request is allowed, false otherwise.
+ */
+static bool scope_to_request(const access_mask_t access_request,
+			     struct layer_masks *masks)
+{
+	bool saw_unfulfilled_access = false;
+
+	if (WARN_ON_ONCE(!masks))
+		return true;
+
+	for (size_t i = 0; i < ARRAY_SIZE(masks->layers); i++) {
+		masks->layers[i].access &= access_request;
+		if (masks->layers[i].access)
+			saw_unfulfilled_access = true;
+	}
+	return !saw_unfulfilled_access;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_scope_to_request_with_exec_none(struct kunit *const test)
+{
+	/* Allows everything. */
+	struct layer_masks masks = {};
+
+	/* Checks and scopes with execute. */
+	KUNIT_EXPECT_TRUE(test,
+			  scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &masks));
+	KUNIT_EXPECT_EQ(test, 0, (access_mask_t)masks.layers[0].access);
+}
+
+static void test_scope_to_request_with_exec_some(struct kunit *const test)
+{
+	/* Denies execute and write. */
+	struct layer_masks masks = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE,
+		.layers[1].access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+	};
+
+	/* Checks and scopes with execute. */
+	KUNIT_EXPECT_FALSE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE,
+						  &masks));
+	/*
+	 * These casts to access_mask_t are needed because typeof(), used in
+	 * KUNIT_EXPECT_EQ(), does not work on bitfields.
+	 */
+	KUNIT_EXPECT_EQ(test, LANDLOCK_ACCESS_FS_EXECUTE,
+			(access_mask_t)masks.layers[0].access);
+	KUNIT_EXPECT_EQ(test, 0, (access_mask_t)masks.layers[1].access);
+}
+
+static void test_scope_to_request_without_access(struct kunit *const test)
+{
+	/* Denies execute and write. */
+	struct layer_masks masks = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE,
+		.layers[1].access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+	};
+
+	/* Checks and scopes without access request. */
+	KUNIT_EXPECT_TRUE(test, scope_to_request(0, &masks));
+	KUNIT_EXPECT_EQ(test, 0, (access_mask_t)masks.layers[0].access);
+	KUNIT_EXPECT_EQ(test, 0, (access_mask_t)masks.layers[1].access);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+/*
+ * Returns true if there is at least one access right different than
+ * LANDLOCK_ACCESS_FS_REFER.
+ */
+static bool is_eacces(const struct layer_masks *masks,
+		      const access_mask_t access_request)
+{
+	if (!masks)
+		return false;
+
+	for (size_t i = 0; i < ARRAY_SIZE(masks->layers); i++) {
+		/* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */
+		if (masks->layers[i].access & access_request &
+		    ~LANDLOCK_ACCESS_FS_REFER)
+			return true;
+	}
+	return false;
+}
+
+#define IE_TRUE(...) KUNIT_EXPECT_TRUE(test, is_eacces(__VA_ARGS__))
+#define IE_FALSE(...) KUNIT_EXPECT_FALSE(test, is_eacces(__VA_ARGS__))
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_is_eacces_with_none(struct kunit *const test)
+{
+	const struct layer_masks masks = {};
+
+	IE_FALSE(&masks, 0);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE);
+}
+
+static void test_is_eacces_with_refer(struct kunit *const test)
+{
+	const struct layer_masks masks = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_REFER,
+	};
+
+	IE_FALSE(&masks, 0);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE);
+}
+
+static void test_is_eacces_with_write(struct kunit *const test)
+{
+	const struct layer_masks masks = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+	};
+
+	IE_FALSE(&masks, 0);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_REFER);
+	IE_FALSE(&masks, LANDLOCK_ACCESS_FS_EXECUTE);
+
+	IE_TRUE(&masks, LANDLOCK_ACCESS_FS_WRITE_FILE);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+#undef IE_TRUE
+#undef IE_FALSE
+
+/**
+ * is_access_to_paths_allowed - Check accesses for requests with a common path
+ *
+ * @domain: Domain to check against.
+ * @path: File hierarchy to walk through.  For refer checks, this would be
+ *     the common mountpoint.
+ * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is
+ *     equal to @layer_masks_parent2 (if any).  This is tied to the unique
+ *     requested path for most actions, or the source in case of a refer action
+ *     (i.e. rename or link), or the source and destination in case of
+ *     RENAME_EXCHANGE.
+ * @layer_masks_parent1: Pointer to a matrix of layer masks per access
+ *     masks, identifying the layers that forbid a specific access.  Bits from
+ *     this matrix can be unset according to the @path walk.  An empty matrix
+ *     means that @domain allows all possible Landlock accesses (i.e. not only
+ *     those identified by @access_request_parent1).  This matrix can
+ *     initially refer to domain layer masks and, when the accesses for the
+ *     destination and source are the same, to requested layer masks.
+ * @log_request_parent1: Audit request to fill if the related access is denied.
+ * @dentry_child1: Dentry to the initial child of the parent1 path.  This
+ *     pointer must be NULL for non-refer actions (i.e. not link nor rename).
+ * @access_request_parent2: Similar to @access_request_parent1 but for a
+ *     request involving a source and a destination.  This refers to the
+ *     destination, except in case of RENAME_EXCHANGE where it also refers to
+ *     the source.  Must be set to 0 when using a simple path request.
+ * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer
+ *     action.  This must be NULL otherwise.
+ * @log_request_parent2: Audit request to fill if the related access is denied.
+ * @dentry_child2: Dentry to the initial child of the parent2 path.  This
+ *     pointer is only set for RENAME_EXCHANGE actions and must be NULL
+ *     otherwise.
+ *
+ * This helper first checks that the destination has a superset of restrictions
+ * compared to the source (if any) for a common path.  Because of
+ * RENAME_EXCHANGE actions, source and destinations may be swapped.  It then
+ * checks that the collected accesses and the remaining ones are enough to
+ * allow the request.
+ *
+ * Return: True if the access request is granted, false otherwise.
+ */
+static bool
+is_access_to_paths_allowed(const struct landlock_domain *const domain,
+			   const struct path *const path,
+			   const access_mask_t access_request_parent1,
+			   struct layer_masks *layer_masks_parent1,
+			   struct landlock_request *const log_request_parent1,
+			   struct dentry *const dentry_child1,
+			   const access_mask_t access_request_parent2,
+			   struct layer_masks *layer_masks_parent2,
+			   struct landlock_request *const log_request_parent2,
+			   struct dentry *const dentry_child2)
+{
+	bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check,
+	     child1_is_directory = true, child2_is_directory = true;
+	struct path walker_path;
+	struct landlock_id id = {
+		.type = LANDLOCK_KEY_INODE,
+	};
+	access_mask_t access_masked_parent1, access_masked_parent2;
+	struct layer_masks _layer_masks_child1, _layer_masks_child2;
+	struct layer_masks *layer_masks_child1 = NULL,
+			   *layer_masks_child2 = NULL;
+
+	if (!access_request_parent1 && !access_request_parent2)
+		return true;
+
+	if (WARN_ON_ONCE(!path))
+		return true;
+
+	if (is_nouser_or_private(path->dentry))
+		return true;
+
+	if (WARN_ON_ONCE(!layer_masks_parent1))
+		return false;
+
+	allowed_parent1 = is_layer_masks_allowed(layer_masks_parent1);
+
+	if (unlikely(layer_masks_parent2)) {
+		if (WARN_ON_ONCE(!dentry_child1))
+			return false;
+
+		allowed_parent2 = is_layer_masks_allowed(layer_masks_parent2);
+
+		/*
+		 * For a double request, first check for potential privilege
+		 * escalation by looking at domain handled accesses (which are
+		 * a superset of the meaningful requested accesses).
+		 */
+		access_masked_parent1 = access_masked_parent2 =
+			landlock_union_access_masks(domain).fs;
+		is_dom_check = true;
+	} else {
+		if (WARN_ON_ONCE(dentry_child1 || dentry_child2))
+			return false;
+		/* For a simple request, only check for requested accesses. */
+		access_masked_parent1 = access_request_parent1;
+		access_masked_parent2 = access_request_parent2;
+		/*
+		 * Simple requests have no parent2 to check, so parent2 is
+		 * trivially allowed.  This must be set explicitly because the
+		 * get_inode_id() gate in the pathwalk loop may prevent
+		 * landlock_unmask_layers() from being called (which would
+		 * otherwise return true for NULL masks as a side effect).
+		 */
+		allowed_parent2 = true;
+		is_dom_check = false;
+	}
+
+	if (unlikely(dentry_child1)) {
+		struct landlock_id id = {
+			.type = LANDLOCK_KEY_INODE,
+		};
+		access_mask_t handled;
+
+		handled = landlock_init_layer_masks(domain,
+						    LANDLOCK_MASK_ACCESS_FS,
+						    &_layer_masks_child1,
+						    LANDLOCK_KEY_INODE);
+		if (handled && get_inode_id(dentry_child1, &id))
+			unmask_layers_fs(domain, id, handled,
+					 &_layer_masks_child1, dentry_child1);
+		layer_masks_child1 = &_layer_masks_child1;
+		child1_is_directory = d_is_dir(dentry_child1);
+	}
+	if (unlikely(dentry_child2)) {
+		struct landlock_id id = {
+			.type = LANDLOCK_KEY_INODE,
+		};
+		access_mask_t handled;
+
+		handled = landlock_init_layer_masks(domain,
+						    LANDLOCK_MASK_ACCESS_FS,
+						    &_layer_masks_child2,
+						    LANDLOCK_KEY_INODE);
+		if (handled && get_inode_id(dentry_child2, &id))
+			unmask_layers_fs(domain, id, handled,
+					 &_layer_masks_child2, dentry_child2);
+		layer_masks_child2 = &_layer_masks_child2;
+		child2_is_directory = d_is_dir(dentry_child2);
+	}
+
+	walker_path = *path;
+	path_get(&walker_path);
+	/*
+	 * We need to walk through all the hierarchy to not miss any relevant
+	 * restriction.
+	 */
+	while (true) {
+		/*
+		 * If at least all accesses allowed on the destination are
+		 * already allowed on the source, respectively if there is at
+		 * least as much as restrictions on the destination than on the
+		 * source, then we can safely refer files from the source to
+		 * the destination without risking a privilege escalation.
+		 * This also applies in the case of RENAME_EXCHANGE, which
+		 * implies checks on both direction.  This is crucial for
+		 * standalone multilayered security policies.  Furthermore,
+		 * this helps avoid policy writers to shoot themselves in the
+		 * foot.
+		 */
+		if (unlikely(is_dom_check &&
+			     no_more_access(
+				     layer_masks_parent1, layer_masks_child1,
+				     child1_is_directory, layer_masks_parent2,
+				     layer_masks_child2,
+				     child2_is_directory))) {
+			/*
+			 * Now, downgrades the remaining checks from domain
+			 * handled accesses to requested accesses.
+			 */
+			is_dom_check = false;
+			access_masked_parent1 = access_request_parent1;
+			access_masked_parent2 = access_request_parent2;
+
+			allowed_parent1 =
+				allowed_parent1 ||
+				scope_to_request(access_masked_parent1,
+						 layer_masks_parent1);
+			allowed_parent2 =
+				allowed_parent2 ||
+				scope_to_request(access_masked_parent2,
+						 layer_masks_parent2);
+
+			/* Stops when all accesses are granted. */
+			if (allowed_parent1 && allowed_parent2)
+				break;
+		}
+
+		if (get_inode_id(walker_path.dentry, &id)) {
+			allowed_parent1 =
+				allowed_parent1 ||
+				unmask_layers_fs(domain, id,
+						 access_masked_parent1,
+						 layer_masks_parent1,
+						 walker_path.dentry);
+			allowed_parent2 =
+				allowed_parent2 ||
+				unmask_layers_fs(domain, id,
+						 access_masked_parent2,
+						 layer_masks_parent2,
+						 walker_path.dentry);
+		}
+
+		/* Stops when a rule from each layer grants access. */
+		if (allowed_parent1 && allowed_parent2)
+			break;
+
+jump_up:
+		if (walker_path.dentry == walker_path.mnt->mnt_root) {
+			if (follow_up(&walker_path)) {
+				/* Ignores hidden mount points. */
+				goto jump_up;
+			} else {
+				/*
+				 * Stops at the real root.  Denies access
+				 * because not all layers have granted access.
+				 */
+				break;
+			}
+		}
+
+		if (unlikely(IS_ROOT(walker_path.dentry))) {
+			if (likely(walker_path.mnt->mnt_flags & MNT_INTERNAL)) {
+				/*
+				 * Stops and allows access when reaching disconnected root
+				 * directories that are part of internal filesystems (e.g. nsfs,
+				 * which is reachable through /proc/<pid>/ns/<namespace>).
+				 */
+				allowed_parent1 = true;
+				allowed_parent2 = true;
+				break;
+			}
+
+			/*
+			 * We reached a disconnected root directory from a bind mount.
+			 * Let's continue the walk with the mount point we missed.
+			 */
+			dput(walker_path.dentry);
+			walker_path.dentry = walker_path.mnt->mnt_root;
+			dget(walker_path.dentry);
+		} else {
+			struct dentry *const parent_dentry =
+				dget_parent(walker_path.dentry);
+
+			dput(walker_path.dentry);
+			walker_path.dentry = parent_dentry;
+		}
+	}
+	path_put(&walker_path);
+
+	/*
+	 * Check CONFIG_SECURITY_LANDLOCK_LOG to enable elision of
+	 * log_request_parent* and associated caller's stack variables thanks to
+	 * dead code elimination.
+	 */
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	if (!allowed_parent1 && log_request_parent1) {
+		log_request_parent1->type = LANDLOCK_REQUEST_FS_ACCESS;
+		log_request_parent1->audit.type = LSM_AUDIT_DATA_PATH;
+		log_request_parent1->audit.u.path = *path;
+		log_request_parent1->access = access_masked_parent1;
+		log_request_parent1->layer_masks = layer_masks_parent1;
+	}
+
+	if (!allowed_parent2 && log_request_parent2) {
+		log_request_parent2->type = LANDLOCK_REQUEST_FS_ACCESS;
+		log_request_parent2->audit.type = LSM_AUDIT_DATA_PATH;
+		log_request_parent2->audit.u.path = *path;
+		log_request_parent2->access = access_masked_parent2;
+		log_request_parent2->layer_masks = layer_masks_parent2;
+	}
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	return allowed_parent1 && allowed_parent2;
+}
+
+static int current_check_access_path(const struct path *const path,
+				     access_mask_t access_request)
+{
+	const struct access_masks masks = {
+		.fs = access_request,
+	};
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), masks, NULL);
+	struct layer_masks layer_masks;
+	struct landlock_request request = {};
+
+	if (!subject)
+		return 0;
+
+	access_request = landlock_init_layer_masks(subject->domain,
+						   access_request, &layer_masks,
+						   LANDLOCK_KEY_INODE);
+	if (is_access_to_paths_allowed(subject->domain, path, access_request,
+				       &layer_masks, &request, NULL, 0, NULL,
+				       NULL, NULL))
+		return 0;
+
+	landlock_log_denial(subject, &request);
+	return -EACCES;
+}
+
+static __attribute_const__ access_mask_t get_mode_access(const umode_t mode,
+							 const dev_t dev)
+{
+	switch (mode & S_IFMT) {
+	case S_IFLNK:
+		return LANDLOCK_ACCESS_FS_MAKE_SYM;
+	case S_IFDIR:
+		return LANDLOCK_ACCESS_FS_MAKE_DIR;
+	case S_IFCHR:
+		/* Whiteout objects are guarded with MAKE_REG. */
+		if (dev == WHITEOUT_DEV)
+			return LANDLOCK_ACCESS_FS_MAKE_REG;
+		return LANDLOCK_ACCESS_FS_MAKE_CHAR;
+	case S_IFBLK:
+		return LANDLOCK_ACCESS_FS_MAKE_BLOCK;
+	case S_IFIFO:
+		return LANDLOCK_ACCESS_FS_MAKE_FIFO;
+	case S_IFSOCK:
+		return LANDLOCK_ACCESS_FS_MAKE_SOCK;
+	case S_IFREG:
+	case 0:
+		/* A zero mode translates to S_IFREG. */
+	default:
+		/* Treats weird files as regular files. */
+		return LANDLOCK_ACCESS_FS_MAKE_REG;
+	}
+}
+
+static access_mask_t get_dentry_access(const struct dentry *const dentry)
+{
+	const struct inode *const inode = d_backing_inode(dentry);
+
+	return get_mode_access(inode->i_mode, inode->i_rdev);
+}
+
+static access_mask_t maybe_remove(const struct dentry *const dentry)
+{
+	if (d_is_negative(dentry))
+		return 0;
+	return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR :
+				  LANDLOCK_ACCESS_FS_REMOVE_FILE;
+}
+
+/**
+ * collect_domain_accesses - Walk through a file path and collect accesses
+ *
+ * @domain: Domain to check against.
+ * @mnt_root: Last directory to check.
+ * @dir: Directory to start the walk from.
+ * @layer_masks_dom: Where to store the collected accesses.
+ *
+ * This helper is useful to begin a path walk from the @dir directory to a
+ * @mnt_root directory used as a mount point.  This mount point is the common
+ * ancestor between the source and the destination of a renamed and linked
+ * file.  While walking from @dir to @mnt_root, we record all the domain's
+ * allowed accesses in @layer_masks_dom.
+ *
+ * Because of disconnected directories, this walk may not reach @mnt_dir.  In
+ * this case, the walk will continue to @mnt_dir after this call.
+ *
+ * This is similar to is_access_to_paths_allowed() but much simpler because it
+ * only handles walking on the same mount point and only checks one set of
+ * accesses.
+ *
+ * Return: True if all the domain access rights are allowed for @dir, false if
+ * the walk reached @mnt_root.
+ */
+static bool collect_domain_accesses(const struct landlock_domain *const domain,
+				    const struct dentry *const mnt_root,
+				    struct dentry *dir,
+				    struct layer_masks *layer_masks_dom)
+{
+	bool ret = false;
+	access_mask_t access_masked_dom;
+
+	if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom))
+		return true;
+	if (is_nouser_or_private(dir))
+		return true;
+
+	access_masked_dom =
+		landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS,
+					  layer_masks_dom, LANDLOCK_KEY_INODE);
+	if (!access_masked_dom)
+		return true;
+
+	dget(dir);
+	while (true) {
+		struct dentry *parent_dentry;
+		struct landlock_id id = {
+			.type = LANDLOCK_KEY_INODE,
+		};
+
+		/* Gets all layers allowing all domain accesses. */
+		if (get_inode_id(dir, &id) &&
+		    unmask_layers_fs(domain, id, access_masked_dom,
+				     layer_masks_dom, dir)) {
+			/*
+			 * Stops when all handled accesses are allowed by at
+			 * least one rule in each layer.
+			 */
+			ret = true;
+			break;
+		}
+
+		/*
+		 * Stops at the mount point or the filesystem root for a disconnected
+		 * directory.
+		 */
+		if (dir == mnt_root || unlikely(IS_ROOT(dir)))
+			break;
+
+		parent_dentry = dget_parent(dir);
+		dput(dir);
+		dir = parent_dentry;
+	}
+	dput(dir);
+	return ret;
+}
+
+/**
+ * current_check_refer_path - Check if a rename or link action is allowed
+ *
+ * @old_dentry: File or directory requested to be moved or linked.
+ * @new_dir: Destination parent directory.
+ * @new_dentry: Destination file or directory.
+ * @removable: Sets to true if it is a rename operation.
+ * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE.
+ * @whiteout: Sets to true if it is a rename operation with RENAME_WHITEOUT.
+ *
+ * Because of its unprivileged constraints, Landlock relies on file hierarchies
+ * (and not only inodes) to tie access rights to files.  Being able to link or
+ * rename a file hierarchy brings some challenges.  Indeed, moving or linking a
+ * file (i.e. creating a new reference to an inode) can have an impact on the
+ * actions allowed for a set of files if it would change its parent directory
+ * (i.e. reparenting).
+ *
+ * To avoid trivial access right bypasses, Landlock first checks if the file or
+ * directory requested to be moved would gain new access rights inherited from
+ * its new hierarchy.  Before returning any error, Landlock then checks that
+ * the parent source hierarchy and the destination hierarchy would allow the
+ * link or rename action.  If it is not the case, an error with EACCES is
+ * returned to inform user space that there is no way to remove or create the
+ * requested source file type.  If it should be allowed but the new inherited
+ * access rights would be greater than the source access rights, then the
+ * kernel returns an error with EXDEV.  Prioritizing EACCES over EXDEV enables
+ * user space to abort the whole operation if there is no way to do it, or to
+ * manually copy the source to the destination if this remains allowed, e.g.
+ * because file creation is allowed on the destination directory but not direct
+ * linking.
+ *
+ * To achieve this goal, the kernel needs to compare two file hierarchies: the
+ * one identifying the source file or directory (including itself), and the
+ * destination one.  This can be seen as a multilayer partial ordering problem.
+ * The kernel walks through these paths and collects in a matrix the access
+ * rights that are denied per layer.  These matrices are then compared to see
+ * if the destination one has more (or the same) restrictions as the source
+ * one.  If this is the case, the requested action will not return EXDEV, which
+ * doesn't mean the action is allowed.  The parent hierarchy of the source
+ * (i.e. parent directory), and the destination hierarchy must also be checked
+ * to verify that they explicitly allow such action (i.e.  referencing,
+ * creation and potentially removal rights).  The kernel implementation is then
+ * required to rely on potentially four matrices of access rights: one for the
+ * source file or directory (i.e. the child), a potentially other one for the
+ * other source/destination (in case of RENAME_EXCHANGE), one for the source
+ * parent hierarchy and a last one for the destination hierarchy.  These
+ * ephemeral matrices take some space on the stack, which limits the number of
+ * layers to a deemed reasonable number: 16.
+ *
+ * Return: 0 if access is allowed, -EXDEV if @old_dentry would inherit new
+ * access rights from @new_dir, or -EACCES if file removal or creation is
+ * denied.
+ */
+static int current_check_refer_path(struct dentry *const old_dentry,
+				    const struct path *const new_dir,
+				    struct dentry *const new_dentry,
+				    const bool removable, const bool exchange,
+				    const bool whiteout)
+{
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs, NULL);
+	bool allow_parent1, allow_parent2;
+	access_mask_t access_request_parent1, access_request_parent2;
+	struct path mnt_dir;
+	struct dentry *old_parent;
+	struct layer_masks layer_masks_parent1 = {}, layer_masks_parent2 = {};
+	struct landlock_request request1 = {}, request2 = {};
+
+	if (!subject)
+		return 0;
+
+	if (unlikely(d_is_negative(old_dentry)))
+		return -ENOENT;
+	if (exchange) {
+		if (unlikely(d_is_negative(new_dentry)))
+			return -ENOENT;
+		access_request_parent1 = get_dentry_access(new_dentry);
+	} else {
+		access_request_parent1 = 0;
+	}
+	access_request_parent2 = get_dentry_access(old_dentry);
+	if (removable) {
+		access_request_parent1 |= maybe_remove(old_dentry);
+		access_request_parent2 |= maybe_remove(new_dentry);
+	}
+
+	/*
+	 * In case of renameat2(2) with RENAME_WHITEOUT, a whiteout object is
+	 * created in the source location, so we require an additional access
+	 * right there.
+	 */
+	if (whiteout)
+		access_request_parent1 |=
+			get_mode_access(S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
+
+	/* The mount points are the same for old and new paths, cf. EXDEV. */
+	if (old_dentry->d_parent == new_dir->dentry) {
+		/*
+		 * The LANDLOCK_ACCESS_FS_REFER access right is not required
+		 * for same-directory referer (i.e. no reparenting).
+		 */
+		access_request_parent1 = landlock_init_layer_masks(
+			subject->domain,
+			access_request_parent1 | access_request_parent2,
+			&layer_masks_parent1, LANDLOCK_KEY_INODE);
+		if (is_access_to_paths_allowed(subject->domain, new_dir,
+					       access_request_parent1,
+					       &layer_masks_parent1, &request1,
+					       NULL, 0, NULL, NULL, NULL))
+			return 0;
+
+		landlock_log_denial(subject, &request1);
+		return -EACCES;
+	}
+
+	access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER;
+	access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER;
+
+	/* Saves the common mount point. */
+	mnt_dir.mnt = new_dir->mnt;
+	mnt_dir.dentry = new_dir->mnt->mnt_root;
+
+	/*
+	 * old_dentry may be the root of the common mount point and
+	 * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and
+	 * OPEN_TREE_CLONE).  We do not need to call dget(old_parent) because
+	 * we keep a reference to old_dentry.
+	 */
+	old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry :
+						      old_dentry->d_parent;
+
+	/* new_dir->dentry is equal to new_dentry->d_parent */
+	allow_parent1 = collect_domain_accesses(subject->domain, mnt_dir.dentry,
+						old_parent,
+						&layer_masks_parent1);
+	allow_parent2 = collect_domain_accesses(subject->domain, mnt_dir.dentry,
+						new_dir->dentry,
+						&layer_masks_parent2);
+	if (allow_parent1 && allow_parent2)
+		return 0;
+
+	/*
+	 * To be able to compare source and destination domain access rights,
+	 * take into account the @old_dentry access rights aggregated with its
+	 * parent access rights.  This will be useful to compare with the
+	 * destination parent access rights.
+	 */
+	if (is_access_to_paths_allowed(
+		    subject->domain, &mnt_dir, access_request_parent1,
+		    &layer_masks_parent1, &request1, old_dentry,
+		    access_request_parent2, &layer_masks_parent2, &request2,
+		    exchange ? new_dentry : NULL))
+		return 0;
+
+	if (request1.access) {
+		request1.audit.u.path.dentry = old_parent;
+		landlock_log_denial(subject, &request1);
+	}
+	if (request2.access) {
+		request2.audit.u.path.dentry = new_dir->dentry;
+		landlock_log_denial(subject, &request2);
+	}
+
+	/*
+	 * This prioritizes EACCES over EXDEV for all actions, including
+	 * renames with RENAME_EXCHANGE.
+	 */
+	if (likely(is_eacces(&layer_masks_parent1, access_request_parent1) ||
+		   is_eacces(&layer_masks_parent2, access_request_parent2)))
+		return -EACCES;
+
+	/*
+	 * Gracefully forbids reparenting if the destination directory
+	 * hierarchy is not a superset of restrictions of the source directory
+	 * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the
+	 * source or the destination.
+	 */
+	return -EXDEV;
+}
+
+/* Inode hooks */
+
+static void hook_inode_free_security_rcu(void *inode_security)
+{
+	struct landlock_inode_security *inode_sec;
+
+	/*
+	 * All inodes must already have been untied from their object by
+	 * release_inode() or hook_sb_delete().
+	 */
+	inode_sec = inode_security + landlock_blob_sizes.lbs_inode;
+	WARN_ON_ONCE(inode_sec->object);
+}
+
+/* Super-block hooks */
+
+/*
+ * Release the inodes used in a security policy.
+ *
+ * Cf. fsnotify_unmount_inodes() and evict_inodes()
+ */
+static void hook_sb_delete(struct super_block *const sb)
+{
+	struct inode *inode, *prev_inode = NULL;
+
+	if (!landlock_initialized)
+		return;
+
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		struct landlock_object *object;
+
+		/* Only handles referenced inodes. */
+		if (!icount_read_once(inode))
+			continue;
+
+		/*
+		 * Protects against concurrent modification of inode (e.g.
+		 * from get_inode_object()).
+		 */
+		spin_lock(&inode->i_lock);
+		/*
+		 * Checks I_FREEING and I_WILL_FREE  to protect against a race
+		 * condition when release_inode() just called iput(), which
+		 * could lead to a NULL dereference of inode->security or a
+		 * second call to iput() for the same Landlock object.  Also
+		 * checks I_NEW because such inode cannot be tied to an object.
+		 */
+		if (inode_state_read(inode) &
+		    (I_FREEING | I_WILL_FREE | I_NEW)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+
+		rcu_read_lock();
+		object = rcu_dereference(landlock_inode(inode)->object);
+		if (!object) {
+			rcu_read_unlock();
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+		/* Keeps a reference to this inode until the next loop walk. */
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+
+		/*
+		 * If there is no concurrent release_inode() ongoing, then we
+		 * are in charge of calling iput() on this inode, otherwise we
+		 * will just wait for it to finish.
+		 */
+		spin_lock(&object->lock);
+		if (object->underobj == inode) {
+			object->underobj = NULL;
+			spin_unlock(&object->lock);
+			rcu_read_unlock();
+
+			/*
+			 * Because object->underobj was not NULL,
+			 * release_inode() and get_inode_object() guarantee
+			 * that it is safe to reset
+			 * landlock_inode(inode)->object while it is not NULL.
+			 * It is therefore not necessary to lock inode->i_lock.
+			 */
+			rcu_assign_pointer(landlock_inode(inode)->object, NULL);
+			/*
+			 * At this point, we own the ihold() reference that was
+			 * originally set up by get_inode_object() and the
+			 * __iget() reference that we just set in this loop
+			 * walk.  Therefore there are at least two references
+			 * on the inode.
+			 */
+			iput_not_last(inode);
+		} else {
+			spin_unlock(&object->lock);
+			rcu_read_unlock();
+		}
+
+		if (prev_inode) {
+			/*
+			 * At this point, we still own the __iget() reference
+			 * that we just set in this loop walk.  Therefore we
+			 * can drop the list lock and know that the inode won't
+			 * disappear from under us until the next loop walk.
+			 */
+			spin_unlock(&sb->s_inode_list_lock);
+			/*
+			 * We can now actually put the inode reference from the
+			 * previous loop walk, which is not needed anymore.
+			 */
+			iput(prev_inode);
+			cond_resched();
+			spin_lock(&sb->s_inode_list_lock);
+		}
+		prev_inode = inode;
+	}
+	spin_unlock(&sb->s_inode_list_lock);
+
+	/* Puts the inode reference from the last loop walk, if any. */
+	if (prev_inode)
+		iput(prev_inode);
+	/* Waits for pending iput() in release_inode(). */
+	wait_var_event(&landlock_superblock(sb)->inode_refs,
+		       !atomic_long_read(&landlock_superblock(sb)->inode_refs));
+}
+
+static void
+log_fs_change_topology_path(const struct landlock_cred_security *const subject,
+			    size_t handle_layer, const struct path *const path)
+{
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY,
+		.audit = {
+			.type = LSM_AUDIT_DATA_PATH,
+			.u.path = *path,
+		},
+		.layer_plus_one = handle_layer + 1,
+	});
+}
+
+static void log_fs_change_topology_dentry(
+	const struct landlock_cred_security *const subject, size_t handle_layer,
+	struct dentry *const dentry)
+{
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY,
+		.audit = {
+			.type = LSM_AUDIT_DATA_DENTRY,
+			.u.dentry = dentry,
+		},
+		.layer_plus_one = handle_layer + 1,
+	});
+}
+
+/*
+ * Because a Landlock security policy is defined according to the filesystem
+ * topology (i.e. the mount namespace), changing it may grant access to files
+ * not previously allowed.
+ *
+ * To make it simple, deny any filesystem topology modification by landlocked
+ * processes.  Non-landlocked processes may still change the namespace of a
+ * landlocked process, but this kind of threat must be handled by a system-wide
+ * access-control security policy.
+ *
+ * This could be lifted in the future if Landlock can safely handle mount
+ * namespace updates requested by a landlocked process.  Indeed, we could
+ * update the current domain (which is currently read-only) by taking into
+ * account the accesses of the source and the destination of a new mount point.
+ * However, it would also require to make all the child domains dynamically
+ * inherit these new constraints.  Anyway, for backward compatibility reasons,
+ * a dedicated user space option would be required (e.g. as a ruleset flag).
+ */
+static int hook_sb_mount(const char *const dev_name,
+			 const struct path *const path, const char *const type,
+			 const unsigned long flags, void *const data)
+{
+	size_t handle_layer;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	log_fs_change_topology_path(subject, handle_layer, path);
+	return -EPERM;
+}
+
+static int hook_move_mount(const struct path *const from_path,
+			   const struct path *const to_path)
+{
+	size_t handle_layer;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	log_fs_change_topology_path(subject, handle_layer, to_path);
+	return -EPERM;
+}
+
+/*
+ * Removing a mount point may reveal a previously hidden file hierarchy, which
+ * may then grant access to files, which may have previously been forbidden.
+ */
+static int hook_sb_umount(struct vfsmount *const mnt, const int flags)
+{
+	size_t handle_layer;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	log_fs_change_topology_dentry(subject, handle_layer, mnt->mnt_root);
+	return -EPERM;
+}
+
+static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts)
+{
+	size_t handle_layer;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	log_fs_change_topology_dentry(subject, handle_layer, sb->s_root);
+	return -EPERM;
+}
+
+/*
+ * pivot_root(2), like mount(2), changes the current mount namespace.  It must
+ * then be forbidden for a landlocked process.
+ *
+ * However, chroot(2) may be allowed because it only changes the relative root
+ * directory of the current process.  Moreover, it can be used to restrict the
+ * view of the filesystem.
+ */
+static int hook_sb_pivotroot(const struct path *const old_path,
+			     const struct path *const new_path)
+{
+	size_t handle_layer;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), any_fs,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	log_fs_change_topology_path(subject, handle_layer, new_path);
+	return -EPERM;
+}
+
+/* Path hooks */
+
+static int hook_path_link(struct dentry *const old_dentry,
+			  const struct path *const new_dir,
+			  struct dentry *const new_dentry)
+{
+	return current_check_refer_path(old_dentry, new_dir, new_dentry, false,
+					false, false);
+}
+
+static int hook_path_rename(const struct path *const old_dir,
+			    struct dentry *const old_dentry,
+			    const struct path *const new_dir,
+			    struct dentry *const new_dentry,
+			    const unsigned int flags)
+{
+	/* old_dir refers to old_dentry->d_parent and new_dir->mnt */
+	return current_check_refer_path(old_dentry, new_dir, new_dentry, true,
+					!!(flags & RENAME_EXCHANGE),
+					!!(flags & RENAME_WHITEOUT));
+}
+
+static int hook_path_mkdir(const struct path *const dir,
+			   struct dentry *const dentry, const umode_t mode)
+{
+	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR);
+}
+
+static int hook_path_mknod(const struct path *const dir,
+			   struct dentry *const dentry, const umode_t mode,
+			   const unsigned int dev)
+{
+	return current_check_access_path(
+		dir, get_mode_access(mode, new_decode_dev(dev)));
+}
+
+static int hook_path_symlink(const struct path *const dir,
+			     struct dentry *const dentry,
+			     const char *const old_name)
+{
+	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM);
+}
+
+static int hook_path_unlink(const struct path *const dir,
+			    struct dentry *const dentry)
+{
+	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE);
+}
+
+static int hook_path_rmdir(const struct path *const dir,
+			   struct dentry *const dentry)
+{
+	return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR);
+}
+
+static int hook_path_truncate(const struct path *const path)
+{
+	return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE);
+}
+
+/**
+ * unmask_scoped_access - Remove access right bits in @masks in all layers
+ *                        where @client and @server have the same domain
+ *
+ * This does the same as domain_is_scoped(), but unmasks bits in @masks.
+ * It can not return early as domain_is_scoped() does.
+ *
+ * A scoped access for a given access right bit is allowed iff, for all layer
+ * depths where the access bit is set, the client and server domain are the
+ * same.  This function clears the access rights @access in @masks at all layer
+ * depths where the client and server domain are the same, so that, when they
+ * are all cleared, the access is allowed.
+ *
+ * @client: Client domain
+ * @server: Server domain
+ * @masks: Layer access masks to unmask
+ * @access: Access bits that control scoping
+ */
+static void unmask_scoped_access(const struct landlock_domain *const client,
+				 const struct landlock_domain *const server,
+				 struct layer_masks *const masks,
+				 const access_mask_t access)
+{
+	int client_layer, server_layer;
+	const struct landlock_hierarchy *client_walker, *server_walker;
+
+	/* This should not happen. */
+	if (WARN_ON_ONCE(!client))
+		return;
+
+	/* Server has no Landlock domain; nothing to clear. */
+	if (!server)
+		return;
+
+	/*
+	 * client_layer must be able to represent all numbers from
+	 * LANDLOCK_MAX_NUM_LAYERS - 1 to -1 for the loop below to terminate.
+	 * (It must be large enough, and it must be signed.)
+	 */
+	BUILD_BUG_ON(!is_signed_type(typeof(client_layer)));
+	BUILD_BUG_ON(LANDLOCK_MAX_NUM_LAYERS - 1 >
+		     type_max(typeof(client_layer)));
+
+	client_layer = client->num_layers - 1;
+	client_walker = client->hierarchy;
+	server_layer = server->num_layers - 1;
+	server_walker = server->hierarchy;
+
+	/*
+	 * Clears the access bits at all layers where the client domain is the
+	 * same as the server domain.  We start the walk at min(client_layer,
+	 * server_layer).  The layer bits until there can not be cleared because
+	 * either the client or the server domain is missing.
+	 */
+	for (; client_layer > server_layer; client_layer--)
+		client_walker = client_walker->parent;
+
+	for (; server_layer > client_layer; server_layer--)
+		server_walker = server_walker->parent;
+
+	for (; client_layer >= 0; client_layer--) {
+		if (masks->layers[client_layer].access & access &&
+		    client_walker == server_walker)
+			masks->layers[client_layer].access &= ~access;
+
+		client_walker = client_walker->parent;
+		server_walker = server_walker->parent;
+	}
+}
+
+static int hook_unix_find(const struct path *const path, struct sock *other,
+			  int flags)
+{
+	const struct landlock_domain *dom_other;
+	const struct landlock_cred_security *subject;
+	struct layer_masks layer_masks;
+	struct landlock_request request = {};
+	static const struct access_masks fs_resolve_unix = {
+		.fs = LANDLOCK_ACCESS_FS_RESOLVE_UNIX,
+	};
+
+	/* Lookup for the purpose of saving coredumps is OK. */
+	if (unlikely(flags & SOCK_COREDUMP))
+		return 0;
+
+	subject = landlock_get_applicable_subject(current_cred(),
+						  fs_resolve_unix, NULL);
+
+	if (!subject)
+		return 0;
+
+	/*
+	 * Ignoring return value: that the domains apply was already checked in
+	 * landlock_get_applicable_subject() above.
+	 */
+	landlock_init_layer_masks(subject->domain, fs_resolve_unix.fs,
+				  &layer_masks, LANDLOCK_KEY_INODE);
+
+	/* Checks the layers in which we are connecting within the same domain. */
+	unix_state_lock(other);
+	if (unlikely(sock_flag(other, SOCK_DEAD) || !other->sk_socket ||
+		     !other->sk_socket->file)) {
+		unix_state_unlock(other);
+		/*
+		 * We rely on the caller to catch the (non-reversible) SOCK_DEAD
+		 * condition and retry the lookup.  If we returned an error
+		 * here, the lookup would not get retried.
+		 */
+		return 0;
+	}
+	dom_other = landlock_cred(other->sk_socket->file->f_cred)->domain;
+
+	/* Access to the same (or a lower) domain is always allowed. */
+	unmask_scoped_access(subject->domain, dom_other, &layer_masks,
+			     fs_resolve_unix.fs);
+	unix_state_unlock(other);
+
+	/* Checks the connections to allow-listed paths. */
+	if (is_access_to_paths_allowed(subject->domain, path,
+				       fs_resolve_unix.fs, &layer_masks,
+				       &request, NULL, 0, NULL, NULL, NULL))
+		return 0;
+
+	landlock_log_denial(subject, &request);
+	return -EACCES;
+}
+
+/* File hooks */
+
+/**
+ * get_required_file_open_access - Get access needed to open a file
+ *
+ * @file: File being opened.
+ *
+ * Return: The access rights that are required for opening the given file,
+ * depending on the file type and open mode.
+ */
+static access_mask_t
+get_required_file_open_access(const struct file *const file)
+{
+	access_mask_t access = 0;
+
+	if (file->f_mode & FMODE_READ) {
+		/* A directory can only be opened in read mode. */
+		if (S_ISDIR(file_inode(file)->i_mode))
+			return LANDLOCK_ACCESS_FS_READ_DIR;
+		access = LANDLOCK_ACCESS_FS_READ_FILE;
+	}
+	if (file->f_mode & FMODE_WRITE)
+		access |= LANDLOCK_ACCESS_FS_WRITE_FILE;
+	/* __FMODE_EXEC is indeed part of f_flags, not f_mode. */
+	if (file->f_flags & __FMODE_EXEC)
+		access |= LANDLOCK_ACCESS_FS_EXECUTE;
+	return access;
+}
+
+static int hook_file_alloc_security(struct file *const file)
+{
+	/*
+	 * Grants all access rights, even if most of them are not checked later
+	 * on. It is more consistent.
+	 *
+	 * Notably, file descriptors for regular files can also be acquired
+	 * without going through the file_open hook, for example when using
+	 * memfd_create(2).
+	 */
+	landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS;
+	return 0;
+}
+
+static bool is_device(const struct file *const file)
+{
+	const struct inode *inode = file_inode(file);
+
+	return S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode);
+}
+
+static int hook_file_open(struct file *const file)
+{
+	struct layer_masks layer_masks = {};
+	access_mask_t open_access_request, full_access_request, allowed_access,
+		optional_access;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(file->f_cred, any_fs, NULL);
+	struct landlock_request request = {};
+
+	if (!subject)
+		return 0;
+
+	/*
+	 * Because a file may be opened with O_PATH, get_required_file_open_access()
+	 * may return 0.  This case will be handled with a future Landlock
+	 * evolution.
+	 */
+	open_access_request = get_required_file_open_access(file);
+
+	/*
+	 * We look up more access than what we immediately need for open(), so
+	 * that we can later authorize operations on opened files.
+	 */
+	optional_access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	if (is_device(file))
+		optional_access |= LANDLOCK_ACCESS_FS_IOCTL_DEV;
+
+	full_access_request = open_access_request | optional_access;
+
+	if (is_access_to_paths_allowed(
+		    subject->domain, &file->f_path,
+		    landlock_init_layer_masks(subject->domain,
+					      full_access_request, &layer_masks,
+					      LANDLOCK_KEY_INODE),
+		    &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) {
+		allowed_access = full_access_request;
+	} else {
+		/*
+		 * Calculate the actual allowed access rights from layer_masks.
+		 * Remove the access rights from the full access request which
+		 * are still unfulfilled in any of the layers.
+		 */
+		allowed_access = full_access_request;
+		for (size_t i = 0; i < ARRAY_SIZE(layer_masks.layers); i++)
+			allowed_access &= ~layer_masks.layers[i].access;
+	}
+
+	/*
+	 * For operations on already opened files (i.e. ftruncate()), it is the
+	 * access rights at the time of open() which decide whether the
+	 * operation is permitted. Therefore, we record the relevant subset of
+	 * file access rights in the opened struct file.
+	 */
+	landlock_file(file)->allowed_access = allowed_access;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	landlock_file(file)->deny_masks = landlock_get_deny_masks(
+		_LANDLOCK_ACCESS_FS_OPTIONAL, optional_access, &layer_masks);
+	landlock_file(file)->quiet_optional_accesses =
+		landlock_get_quiet_optional_accesses(
+			_LANDLOCK_ACCESS_FS_OPTIONAL,
+			landlock_file(file)->deny_masks, &layer_masks);
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	if (access_mask_subset(open_access_request, allowed_access))
+		return 0;
+
+	/* Sets access to reflect the actual request. */
+	request.access = open_access_request;
+	landlock_log_denial(subject, &request);
+	return -EACCES;
+}
+
+static int hook_file_truncate(struct file *const file)
+{
+	/*
+	 * Allows truncation if the truncate right was available at the time of
+	 * opening the file, to get a consistent access check as for read, write
+	 * and execute operations.
+	 *
+	 * Note: For checks done based on the file's Landlock allowed access, we
+	 * enforce them independently of whether the current thread is in a
+	 * Landlock domain, so that open files passed between independent
+	 * processes retain their behaviour.
+	 */
+	if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE)
+		return 0;
+
+	landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_FS_ACCESS,
+		.audit = {
+			.type = LSM_AUDIT_DATA_FILE,
+			.u.file = file,
+		},
+		.all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL,
+		.access = LANDLOCK_ACCESS_FS_TRUNCATE,
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		.deny_masks = landlock_file(file)->deny_masks,
+		.quiet_optional_accesses = landlock_file(file)->quiet_optional_accesses,
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	});
+	return -EACCES;
+}
+
+static int hook_file_ioctl_common(const struct file *const file,
+				  const unsigned int cmd, const bool is_compat)
+{
+	access_mask_t allowed_access = landlock_file(file)->allowed_access;
+
+	/*
+	 * It is the access rights at the time of opening the file which
+	 * determine whether IOCTL can be used on the opened file later.
+	 *
+	 * The access right is attached to the opened file in hook_file_open().
+	 */
+	if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV)
+		return 0;
+
+	if (!is_device(file))
+		return 0;
+
+	if (unlikely(is_compat) ? is_masked_device_ioctl_compat(cmd) :
+				  is_masked_device_ioctl(cmd))
+		return 0;
+
+	landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_FS_ACCESS,
+		.audit = {
+			.type = LSM_AUDIT_DATA_IOCTL_OP,
+			.u.op = &(struct lsm_ioctlop_audit) {
+				.path = file->f_path,
+				.cmd = cmd,
+			},
+		},
+		.all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL,
+		.access = LANDLOCK_ACCESS_FS_IOCTL_DEV,
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		.deny_masks = landlock_file(file)->deny_masks,
+		.quiet_optional_accesses = landlock_file(file)->quiet_optional_accesses,
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	});
+	return -EACCES;
+}
+
+static int hook_file_ioctl(struct file *file, unsigned int cmd,
+			   unsigned long arg)
+{
+	return hook_file_ioctl_common(file, cmd, false);
+}
+
+static int hook_file_ioctl_compat(struct file *file, unsigned int cmd,
+				  unsigned long arg)
+{
+	return hook_file_ioctl_common(file, cmd, true);
+}
+
+/*
+ * Always allow sending signals between threads of the same process.  This
+ * ensures consistency with hook_task_kill().
+ */
+static bool control_current_fowner(struct fown_struct *const fown)
+{
+	struct task_struct *p;
+
+	/*
+	 * Lock already held by __f_setown(), see commit 26f204380a3c ("fs: Fix
+	 * file_set_fowner LSM hook inconsistencies").
+	 */
+	lockdep_assert_held(&fown->lock);
+
+	/*
+	 * A process-group or session owner (PIDTYPE_PGID/PIDTYPE_SID) fans the
+	 * signal out to every member at delivery time, so record the domain and
+	 * let hook_file_send_sigiotask() check the live scope per recipient.
+	 */
+	if (fown->pid_type != PIDTYPE_PID && fown->pid_type != PIDTYPE_TGID)
+		return true;
+
+	/*
+	 * Some callers (e.g. fcntl_dirnotify) may not be in an RCU read-side
+	 * critical section.
+	 */
+	guard(rcu)();
+	p = pid_task(fown->pid, fown->pid_type);
+	if (!p)
+		return true;
+
+	return !same_thread_group(p, current);
+}
+
+static void hook_file_set_fowner(struct file *file)
+{
+	struct landlock_domain *prev_dom;
+	struct landlock_cred_security fown_subject = {};
+	struct pid *prev_tg, *fown_tg = NULL;
+	size_t fown_layer = 0;
+
+	if (control_current_fowner(file_f_owner(file))) {
+		static const struct access_masks signal_scope = {
+			.scope = LANDLOCK_SCOPE_SIGNAL,
+		};
+		const struct landlock_cred_security *new_subject =
+			landlock_get_applicable_subject(
+				current_cred(), signal_scope, &fown_layer);
+		if (new_subject) {
+			landlock_get_domain(new_subject->domain);
+			fown_subject = *new_subject;
+			fown_tg = get_pid(task_tgid(current));
+		}
+	}
+
+	prev_dom = landlock_file(file)->fown_subject.domain;
+	prev_tg = landlock_file(file)->fown_tg;
+	landlock_file(file)->fown_subject = fown_subject;
+	landlock_file(file)->fown_tg = fown_tg;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	landlock_file(file)->fown_layer = fown_layer;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	/* May be called in an RCU read-side critical section. */
+	landlock_put_domain_deferred(prev_dom);
+	put_pid(prev_tg);
+}
+
+static void hook_file_free_security(struct file *file)
+{
+	put_pid(landlock_file(file)->fown_tg);
+	landlock_put_domain_deferred(landlock_file(file)->fown_subject.domain);
+}
+
+static struct security_hook_list landlock_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(inode_free_security_rcu, hook_inode_free_security_rcu),
+
+	LSM_HOOK_INIT(sb_delete, hook_sb_delete),
+	LSM_HOOK_INIT(sb_mount, hook_sb_mount),
+	LSM_HOOK_INIT(move_mount, hook_move_mount),
+	LSM_HOOK_INIT(sb_umount, hook_sb_umount),
+	LSM_HOOK_INIT(sb_remount, hook_sb_remount),
+	LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot),
+
+	LSM_HOOK_INIT(path_link, hook_path_link),
+	LSM_HOOK_INIT(path_rename, hook_path_rename),
+	LSM_HOOK_INIT(path_mkdir, hook_path_mkdir),
+	LSM_HOOK_INIT(path_mknod, hook_path_mknod),
+	LSM_HOOK_INIT(path_symlink, hook_path_symlink),
+	LSM_HOOK_INIT(path_unlink, hook_path_unlink),
+	LSM_HOOK_INIT(path_rmdir, hook_path_rmdir),
+	LSM_HOOK_INIT(path_truncate, hook_path_truncate),
+	LSM_HOOK_INIT(unix_find, hook_unix_find),
+
+	LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security),
+	LSM_HOOK_INIT(file_open, hook_file_open),
+	LSM_HOOK_INIT(file_truncate, hook_file_truncate),
+	LSM_HOOK_INIT(file_ioctl, hook_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, hook_file_ioctl_compat),
+	LSM_HOOK_INIT(file_set_fowner, hook_file_set_fowner),
+	LSM_HOOK_INIT(file_free_security, hook_file_free_security),
+};
+
+__init void landlock_add_fs_hooks(void)
+{
+	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+			   &landlock_lsmid);
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+/* clang-format off */
+static struct kunit_case test_cases[] = {
+	KUNIT_CASE(test_no_more_access),
+	KUNIT_CASE(test_scope_to_request_with_exec_none),
+	KUNIT_CASE(test_scope_to_request_with_exec_some),
+	KUNIT_CASE(test_scope_to_request_without_access),
+	KUNIT_CASE(test_is_eacces_with_none),
+	KUNIT_CASE(test_is_eacces_with_refer),
+	KUNIT_CASE(test_is_eacces_with_write),
+	{}
+};
+/* clang-format on */
+
+static struct kunit_suite test_suite = {
+	.name = "landlock_fs",
+	.test_cases = test_cases,
+};
+
+kunit_test_suite(test_suite);
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
diff --git a/security/landlock/fs.h b/security/landlock/fs.h
new file mode 100644
index 000000000..50b3ddb8a
--- /dev/null
+++ b/security/landlock/fs.h
@@ -0,0 +1,188 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Filesystem management and hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_FS_H
+#define _SECURITY_LANDLOCK_FS_H
+
+#include <linux/build_bug.h>
+#include <linux/cleanup.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+
+#include "access.h"
+#include "cred.h"
+#include "ruleset.h"
+#include "setup.h"
+
+DEFINE_FREE(__putname, char *, if (_T) __putname(_T))
+
+/**
+ * struct landlock_inode_security - Inode security blob
+ *
+ * Enable to reference a &struct landlock_object tied to an inode (i.e.
+ * underlying object).
+ */
+struct landlock_inode_security {
+	/**
+	 * @object: Weak pointer to an allocated object.  All assignments of a
+	 * new object are protected by the underlying inode->i_lock.  However,
+	 * atomically disassociating @object from the inode is only protected
+	 * by @object->lock, from the time @object's usage refcount drops to
+	 * zero to the time this pointer is nulled out (cf. release_inode() and
+	 * hook_sb_delete()).  Indeed, such disassociation doesn't require
+	 * inode->i_lock thanks to the careful rcu_access_pointer() check
+	 * performed by get_inode_object().
+	 */
+	struct landlock_object __rcu *object;
+};
+
+/**
+ * struct landlock_file_security - File security blob
+ *
+ * This information is populated when opening a file in hook_file_open, and
+ * tracks the relevant Landlock access rights that were available at the time
+ * of opening the file. Other LSM hooks use these rights in order to authorize
+ * operations on already opened files.
+ */
+struct landlock_file_security {
+	/**
+	 * @allowed_access: Access rights that were available at the time of
+	 * opening the file. This is not necessarily the full set of access
+	 * rights available at that time, but it's the necessary subset as
+	 * needed to authorize later operations on the open file.
+	 */
+	access_mask_t allowed_access;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	/**
+	 * @deny_masks: Domain layer levels that deny an optional access (see
+	 * _LANDLOCK_ACCESS_FS_OPTIONAL).
+	 */
+	deny_masks_t deny_masks;
+	/**
+	 * @quiet_optional_accesses: Stores which optional accesses are covered
+	 * by quiet rules within the layer referred to in deny_masks, one access
+	 * per bit.  Does not take into account whether the quiet access bits
+	 * are actually set in the layer's corresponding landlock_hierarchy.
+	 */
+	optional_access_t quiet_optional_accesses;
+	/**
+	 * @fown_layer: Layer level of @fown_subject->domain with
+	 * LANDLOCK_SCOPE_SIGNAL.
+	 */
+	u8 fown_layer;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	/**
+	 * @fown_subject: Landlock credential of the task that set the PID that
+	 * may receive a signal e.g., SIGURG when writing MSG_OOB to the
+	 * related socket.  This pointer is protected by the related
+	 * file->f_owner->lock, as for fown_struct's members: pid, uid, and
+	 * euid.
+	 */
+	struct landlock_cred_security fown_subject;
+	/**
+	 * @fown_tg: Thread group of the task that set the file owner, pinned
+	 * while @fown_subject holds a domain.  It lets
+	 * hook_file_send_sigiotask() always allow a SIGIO delivered to the
+	 * owner's own process -- e.g. the thread-group leader reached through a
+	 * process-group owner -- matching the same-process exemption of
+	 * hook_task_kill().  NULL when no domain is recorded.  Protected by
+	 * file->f_owner->lock, like @fown_subject.
+	 */
+	struct pid *fown_tg;
+};
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+/* Makes sure all layers can be identified. */
+/* clang-format off */
+static_assert((typeof_member(struct landlock_file_security, fown_layer))~0 >=
+	      LANDLOCK_MAX_NUM_LAYERS);
+/* clang-format on */
+
+/*
+ * Make sure quiet_optional_accesses has enough bits to cover all optional
+ * accesses.
+ */
+static_assert(BITS_PER_TYPE(typeof_member(struct landlock_file_security,
+					  quiet_optional_accesses)) >=
+	      HWEIGHT(_LANDLOCK_ACCESS_FS_OPTIONAL));
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+/**
+ * struct landlock_superblock_security - Superblock security blob
+ *
+ * Enable hook_sb_delete() to wait for concurrent calls to release_inode().
+ */
+struct landlock_superblock_security {
+	/**
+	 * @inode_refs: Number of pending inodes (from this superblock) that
+	 * are being released by release_inode().
+	 * Cf. struct super_block->s_fsnotify_inode_refs .
+	 */
+	atomic_long_t inode_refs;
+};
+
+static inline struct landlock_file_security *
+landlock_file(const struct file *const file)
+{
+	return file->f_security + landlock_blob_sizes.lbs_file;
+}
+
+static inline struct landlock_inode_security *
+landlock_inode(const struct inode *const inode)
+{
+	return inode->i_security + landlock_blob_sizes.lbs_inode;
+}
+
+static inline struct landlock_superblock_security *
+landlock_superblock(const struct super_block *const superblock)
+{
+	return superblock->s_security + landlock_blob_sizes.lbs_superblock;
+}
+
+__init void landlock_add_fs_hooks(void);
+
+int landlock_append_fs_rule(struct landlock_ruleset *const ruleset,
+			    const struct path *const path,
+			    access_mask_t access_hierarchy, const u32 flags);
+
+/**
+ * resolve_path_for_trace - Resolve a path for tracepoint display
+ *
+ * @path: The path to resolve.
+ * @buf: A buffer of at least PATH_MAX bytes for the resolved path.
+ *
+ * Uses d_absolute_path() to produce a namespace-independent absolute path,
+ * unlike d_path() which resolves relative to the process's chroot.  This
+ * ensures trace output is deterministic regardless of the tracer's mount
+ * namespace.
+ *
+ * Return: A pointer into @buf with the resolved path, or an error string
+ * ("<too_long>", "<unreachable>").
+ */
+static inline const char *resolve_path_for_trace(const struct path *path,
+						 char *buf)
+{
+	const char *p;
+
+	p = d_absolute_path(path, buf, PATH_MAX);
+	if (!IS_ERR_OR_NULL(p))
+		return p;
+
+	if (PTR_ERR(p) == -ENAMETOOLONG)
+		return "<too_long>";
+
+	return "<unreachable>";
+}
+
+#endif /* _SECURITY_LANDLOCK_FS_H */
diff --git a/security/landlock/id.c b/security/landlock/id.c
new file mode 100644
index 000000000..6c8769777
--- /dev/null
+++ b/security/landlock/id.c
@@ -0,0 +1,295 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Unique identification number generator
+ *
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#include <kunit/test.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/random.h>
+#include <linux/spinlock.h>
+
+#include "common.h"
+#include "id.h"
+
+#define COUNTER_PRE_INIT 0
+
+static atomic64_t next_id = ATOMIC64_INIT(COUNTER_PRE_INIT);
+
+static void __init init_id(atomic64_t *const counter, const u32 random_32bits)
+{
+	u64 init;
+
+	/*
+	 * Ensures sure 64-bit values are always used by user space (or may
+	 * fail with -EOVERFLOW), and makes this testable.
+	 */
+	init = BIT_ULL(32);
+
+	/*
+	 * Makes a large (2^32) boot-time value to limit ID collision in logs
+	 * from different boots, and to limit info leak about the number of
+	 * initially (relative to the reader) created elements (e.g. domains).
+	 */
+	init += random_32bits;
+
+	/* Sets first or ignores.  This will be the first ID. */
+	atomic64_cmpxchg(counter, COUNTER_PRE_INIT, init);
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void __init test_init_min(struct kunit *const test)
+{
+	atomic64_t counter = ATOMIC64_INIT(COUNTER_PRE_INIT);
+
+	init_id(&counter, 0);
+	KUNIT_EXPECT_EQ(test, atomic64_read(&counter), 1ULL + U32_MAX);
+}
+
+static void __init test_init_max(struct kunit *const test)
+{
+	atomic64_t counter = ATOMIC64_INIT(COUNTER_PRE_INIT);
+
+	init_id(&counter, ~0);
+	KUNIT_EXPECT_EQ(test, atomic64_read(&counter), 1 + (2ULL * U32_MAX));
+}
+
+static void __init test_init_once(struct kunit *const test)
+{
+	const u64 first_init = 1ULL + U32_MAX;
+	atomic64_t counter = ATOMIC64_INIT(COUNTER_PRE_INIT);
+
+	init_id(&counter, 0);
+	KUNIT_EXPECT_EQ(test, atomic64_read(&counter), first_init);
+
+	init_id(&counter, ~0);
+	KUNIT_EXPECT_EQ_MSG(
+		test, atomic64_read(&counter), first_init,
+		"Should still have the same value after the subsequent init_id()");
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+void __init landlock_init_id(void)
+{
+	return init_id(&next_id, get_random_u32());
+}
+
+/*
+ * It's not worth it to try to hide the monotonic counter because it can still
+ * be inferred (with N counter ranges), and if we are allowed to read the inode
+ * number we should also be allowed to read the time creation anyway, and it
+ * can be handy to store and sort domain IDs for user space.
+ *
+ * Returns the value of next_id and increment it to let some space for the next
+ * one.
+ */
+static u64 get_id_range(size_t number_of_ids, atomic64_t *const counter,
+			u8 random_4bits)
+{
+	u64 id, step;
+
+	/*
+	 * We should return at least 1 ID, and we may need a set of consecutive
+	 * ones (e.g. to generate a set of inodes).
+	 */
+	if (WARN_ON_ONCE(number_of_ids <= 0))
+		number_of_ids = 1;
+
+	/*
+	 * Blurs the next ID guess with 1/16 ratio.  We get 2^(64 - 4) -
+	 * (2 * 2^32), so a bit less than 2^60 available IDs, which should be
+	 * much more than enough considering the number of CPU cycles required
+	 * to get a new ID (e.g. a full landlock_restrict_self() call), and the
+	 * cost of draining all available IDs during the system's uptime.
+	 */
+	random_4bits &= 0b1111;
+	step = number_of_ids + random_4bits;
+
+	/* It is safe to cast a signed atomic to an unsigned value. */
+	id = atomic64_fetch_add(step, counter);
+
+	/* Warns if landlock_init_id() was not called. */
+	WARN_ON_ONCE(id == COUNTER_PRE_INIT);
+	return id;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static u8 get_random_u8_positive(void)
+{
+	/* max() evaluates its arguments once. */
+	return max(1, get_random_u8());
+}
+
+static void test_range1_rand0(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 0), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 1);
+}
+
+static void test_range1_rand1(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 1), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 2);
+}
+
+static void test_range1_rand15(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 15), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 16);
+}
+
+static void test_range1_rand16(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(1, &counter, 16), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 1);
+}
+
+static void test_range2_rand0(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 0), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 2);
+}
+
+static void test_range2_rand1(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 1), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 3);
+}
+
+static void test_range2_rand2(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 2), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 4);
+}
+
+static void test_range2_rand15(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 15), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 17);
+}
+
+static void test_range2_rand16(struct kunit *const test)
+{
+	atomic64_t counter;
+	u64 init;
+
+	init = get_random_u32();
+	atomic64_set(&counter, init);
+	KUNIT_EXPECT_EQ(test, get_id_range(2, &counter, 16), init);
+	KUNIT_EXPECT_EQ(test,
+			get_id_range(get_random_u8_positive(), &counter,
+				     get_random_u8()),
+			init + 2);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+/**
+ * landlock_get_id_range - Get a range of unique IDs
+ *
+ * @number_of_ids: Number of IDs to hold.  Must be greater than one.
+ *
+ * Return: The first ID in the range.
+ */
+u64 landlock_get_id_range(size_t number_of_ids)
+{
+	return get_id_range(number_of_ids, &next_id, get_random_u8());
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static struct kunit_case __refdata test_cases[] = {
+	/* clang-format off */
+	KUNIT_CASE(test_init_min),
+	KUNIT_CASE(test_init_max),
+	KUNIT_CASE(test_init_once),
+	KUNIT_CASE(test_range1_rand0),
+	KUNIT_CASE(test_range1_rand1),
+	KUNIT_CASE(test_range1_rand15),
+	KUNIT_CASE(test_range1_rand16),
+	KUNIT_CASE(test_range2_rand0),
+	KUNIT_CASE(test_range2_rand1),
+	KUNIT_CASE(test_range2_rand2),
+	KUNIT_CASE(test_range2_rand15),
+	KUNIT_CASE(test_range2_rand16),
+	{}
+	/* clang-format on */
+};
+
+static struct kunit_suite test_suite = {
+	.name = "landlock_id",
+	.test_cases = test_cases,
+};
+
+kunit_test_init_section_suite(test_suite);
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
diff --git a/security/landlock/id.h b/security/landlock/id.h
new file mode 100644
index 000000000..2a43c2b52
--- /dev/null
+++ b/security/landlock/id.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Unique identification number generator
+ *
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_ID_H
+#define _SECURITY_LANDLOCK_ID_H
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+void __init landlock_init_id(void);
+
+u64 landlock_get_id_range(size_t number_of_ids);
+
+#else /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static inline void __init landlock_init_id(void)
+{
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+#endif /* _SECURITY_LANDLOCK_ID_H */
diff --git a/security/landlock/limits.h b/security/landlock/limits.h
new file mode 100644
index 000000000..1a7c5fb8f
--- /dev/null
+++ b/security/landlock/limits.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Limits for different components
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2021-2025 Microsoft Corporation
+ */
+
+#ifndef _SECURITY_LANDLOCK_LIMITS_H
+#define _SECURITY_LANDLOCK_LIMITS_H
+
+#include <linux/bitops.h>
+#include <linux/limits.h>
+#include <uapi/linux/landlock.h>
+
+/* clang-format off */
+
+#define LANDLOCK_MAX_NUM_LAYERS		16
+#define LANDLOCK_MAX_NUM_RULES		U32_MAX
+
+#define LANDLOCK_LAST_ACCESS_FS		LANDLOCK_ACCESS_FS_RESOLVE_UNIX
+#define LANDLOCK_MASK_ACCESS_FS		((LANDLOCK_LAST_ACCESS_FS << 1) - 1)
+#define LANDLOCK_NUM_ACCESS_FS		__const_hweight64(LANDLOCK_MASK_ACCESS_FS)
+
+#define LANDLOCK_LAST_ACCESS_NET	LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP
+#define LANDLOCK_MASK_ACCESS_NET	((LANDLOCK_LAST_ACCESS_NET << 1) - 1)
+#define LANDLOCK_NUM_ACCESS_NET		__const_hweight64(LANDLOCK_MASK_ACCESS_NET)
+
+#define LANDLOCK_LAST_SCOPE		LANDLOCK_SCOPE_SIGNAL
+#define LANDLOCK_MASK_SCOPE		((LANDLOCK_LAST_SCOPE << 1) - 1)
+#define LANDLOCK_NUM_SCOPE		__const_hweight64(LANDLOCK_MASK_SCOPE)
+
+#define LANDLOCK_NUM_ACCESS_MAX \
+	MAX(MAX(LANDLOCK_NUM_ACCESS_FS, LANDLOCK_NUM_ACCESS_NET), LANDLOCK_NUM_SCOPE)
+
+#define LANDLOCK_LAST_RESTRICT_SELF	LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS
+#define LANDLOCK_MASK_RESTRICT_SELF	((LANDLOCK_LAST_RESTRICT_SELF << 1) - 1)
+
+/* clang-format on */
+
+#endif /* _SECURITY_LANDLOCK_LIMITS_H */
diff --git a/security/landlock/log.c b/security/landlock/log.c
new file mode 100644
index 000000000..a8578a6f2
--- /dev/null
+++ b/security/landlock/log.c
@@ -0,0 +1,587 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Log helpers
+ *
+ * Copyright © 2023-2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#include <kunit/test.h>
+#include <linux/bitops.h>
+#include <uapi/linux/landlock.h>
+
+#include "access.h"
+#include "audit.h"
+#include "common.h"
+#include "cred.h"
+#include "domain.h"
+#include "limits.h"
+#include "log.h"
+#include "ruleset.h"
+#include "trace.h"
+
+static struct landlock_hierarchy *
+get_hierarchy(const struct landlock_domain *const domain, const size_t layer)
+{
+	struct landlock_hierarchy *hierarchy = domain->hierarchy;
+	ssize_t i;
+
+	if (WARN_ON_ONCE(layer >= domain->num_layers))
+		return hierarchy;
+
+	for (i = domain->num_layers - 1; i > layer; i--) {
+		if (WARN_ON_ONCE(!hierarchy->parent))
+			break;
+
+		hierarchy = hierarchy->parent;
+	}
+
+	return hierarchy;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_get_hierarchy(struct kunit *const test)
+{
+	struct landlock_hierarchy dom0_hierarchy = {
+		.id = 10,
+	};
+	struct landlock_hierarchy dom1_hierarchy = {
+		.parent = &dom0_hierarchy,
+		.id = 20,
+	};
+	struct landlock_hierarchy dom2_hierarchy = {
+		.parent = &dom1_hierarchy,
+		.id = 30,
+	};
+	struct landlock_domain dom2 = {
+		.hierarchy = &dom2_hierarchy,
+		.num_layers = 3,
+	};
+
+	KUNIT_EXPECT_EQ(test, 10, get_hierarchy(&dom2, 0)->id);
+	KUNIT_EXPECT_EQ(test, 20, get_hierarchy(&dom2, 1)->id);
+	KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, 2)->id);
+	/* KUNIT_EXPECT_EQ(test, 30, get_hierarchy(&dom2, -1)->id); */
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+/* Get the youngest layer that denied the access_request. */
+static size_t get_denied_layer(const struct landlock_domain *const domain,
+			       access_mask_t *const access_request,
+			       const struct layer_masks *masks)
+{
+	for (ssize_t i = ARRAY_SIZE(masks->layers) - 1; i >= 0; i--) {
+		if (masks->layers[i].access & *access_request) {
+			*access_request &= masks->layers[i].access;
+			return i;
+		}
+	}
+
+	/* Not found - fall back to default values */
+	*access_request = 0;
+	return domain->num_layers - 1;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_get_denied_layer(struct kunit *const test)
+{
+	const struct landlock_domain dom = {
+		.num_layers = 5,
+	};
+	const struct layer_masks masks = {
+		.layers[0].access = LANDLOCK_ACCESS_FS_EXECUTE |
+				    LANDLOCK_ACCESS_FS_READ_DIR,
+		.layers[1].access = LANDLOCK_ACCESS_FS_READ_FILE |
+				    LANDLOCK_ACCESS_FS_READ_DIR,
+		.layers[2].access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
+	};
+	access_mask_t access;
+
+	access = LANDLOCK_ACCESS_FS_EXECUTE;
+	KUNIT_EXPECT_EQ(test, 0, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_EXECUTE);
+
+	access = LANDLOCK_ACCESS_FS_READ_FILE;
+	KUNIT_EXPECT_EQ(test, 1, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_READ_FILE);
+
+	access = LANDLOCK_ACCESS_FS_READ_DIR;
+	KUNIT_EXPECT_EQ(test, 1, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_READ_DIR);
+
+	access = LANDLOCK_ACCESS_FS_READ_FILE | LANDLOCK_ACCESS_FS_READ_DIR;
+	KUNIT_EXPECT_EQ(test, 1, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access,
+			LANDLOCK_ACCESS_FS_READ_FILE |
+				LANDLOCK_ACCESS_FS_READ_DIR);
+
+	access = LANDLOCK_ACCESS_FS_EXECUTE | LANDLOCK_ACCESS_FS_READ_DIR;
+	KUNIT_EXPECT_EQ(test, 1, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_READ_DIR);
+
+	access = LANDLOCK_ACCESS_FS_WRITE_FILE;
+	KUNIT_EXPECT_EQ(test, 4, get_denied_layer(&dom, &access, &masks));
+	KUNIT_EXPECT_EQ(test, access, 0);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+static size_t
+get_layer_from_deny_masks(access_mask_t *const access_request,
+			  const access_mask_t all_existing_optional_access,
+			  const deny_masks_t deny_masks,
+			  optional_access_t quiet_optional_accesses,
+			  bool *quiet)
+{
+	const unsigned long access_opt = all_existing_optional_access;
+	const unsigned long access_req = *access_request;
+	access_mask_t missing = 0;
+	size_t youngest_layer = 0;
+	size_t access_index = 0;
+	unsigned long access_bit;
+	bool should_quiet = false;
+
+	/* This will require change with new object types. */
+	WARN_ON_ONCE(access_opt != _LANDLOCK_ACCESS_FS_OPTIONAL);
+
+	for_each_set_bit(access_bit, &access_opt,
+			 BITS_PER_TYPE(access_mask_t)) {
+		if (access_req & BIT(access_bit)) {
+			const size_t layer =
+				(deny_masks >>
+				 (access_index *
+				  HWEIGHT(LANDLOCK_MAX_NUM_LAYERS - 1))) &
+				(LANDLOCK_MAX_NUM_LAYERS - 1);
+			const bool layer_has_quiet =
+				!!(quiet_optional_accesses & BIT(access_index));
+
+			if (layer > youngest_layer) {
+				youngest_layer = layer;
+				missing = BIT(access_bit);
+				should_quiet = layer_has_quiet;
+			} else if (layer == youngest_layer) {
+				missing |= BIT(access_bit);
+				/*
+				 * Whether the layer has rules with quiet flag
+				 * covering the file accessed does not depend on
+				 * the access, and so the following
+				 * WARN_ON_ONCE() should not fail.
+				 */
+				WARN_ON_ONCE(should_quiet && !layer_has_quiet);
+				should_quiet = layer_has_quiet;
+			}
+		}
+		access_index++;
+	}
+
+	*access_request = missing;
+	*quiet = should_quiet;
+	return youngest_layer;
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static void test_get_layer_from_deny_masks(struct kunit *const test)
+{
+	deny_masks_t deny_mask;
+	access_mask_t access;
+	optional_access_t quiet_optional_accesses;
+	bool quiet;
+
+	/* truncate:0 ioctl_dev:2 */
+	deny_mask = 0x20;
+	quiet_optional_accesses = 0;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	/* layer denying truncate: quiet, ioctl: not quiet */
+	quiet_optional_accesses = 0b01;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+
+	access = LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	/* Reverse order - truncate:2 ioctl_dev:0 */
+	deny_mask = 0x02;
+	quiet_optional_accesses = 0;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	/* layer denying truncate: quiet, ioctl: not quiet */
+	quiet_optional_accesses = 0b01;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+
+	access = LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+
+	/* layer denying truncate: not quiet, ioctl: quiet */
+	quiet_optional_accesses = 0b10;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 0,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 2,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	/* truncate:15 ioctl_dev:15 */
+	deny_mask = 0xff;
+	quiet_optional_accesses = 0;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 15,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 15,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access,
+			LANDLOCK_ACCESS_FS_TRUNCATE |
+				LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, false);
+
+	/* Both quiet (same layer so quietness must be the same) */
+	quiet_optional_accesses = 0b11;
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE;
+	KUNIT_EXPECT_EQ(test, 15,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access, LANDLOCK_ACCESS_FS_TRUNCATE);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+
+	access = LANDLOCK_ACCESS_FS_TRUNCATE | LANDLOCK_ACCESS_FS_IOCTL_DEV;
+	KUNIT_EXPECT_EQ(test, 15,
+			get_layer_from_deny_masks(
+				&access, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				deny_mask, quiet_optional_accesses, &quiet));
+	KUNIT_EXPECT_EQ(test, access,
+			LANDLOCK_ACCESS_FS_TRUNCATE |
+				LANDLOCK_ACCESS_FS_IOCTL_DEV);
+	KUNIT_EXPECT_EQ(test, quiet, true);
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
+
+static bool is_valid_request(const struct landlock_request *const request)
+{
+	if (WARN_ON_ONCE(request->layer_plus_one > LANDLOCK_MAX_NUM_LAYERS))
+		return false;
+
+	if (WARN_ON_ONCE(!(!!request->layer_plus_one ^ !!request->access)))
+		return false;
+
+	if (request->access) {
+		if (WARN_ON_ONCE(!(!!request->layer_masks ^
+				   !!request->all_existing_optional_access)))
+			return false;
+	} else {
+		if (WARN_ON_ONCE(request->layer_masks ||
+				 request->all_existing_optional_access))
+			return false;
+	}
+
+	if (request->deny_masks) {
+		if (WARN_ON_ONCE(!request->all_existing_optional_access))
+			return false;
+		static_assert(sizeof(request->all_existing_optional_access) ==
+			      sizeof(u32));
+		if (WARN_ON_ONCE(
+			    request->quiet_optional_accesses >=
+			    BIT(hweight32(
+				    request->all_existing_optional_access))))
+			return false;
+	}
+
+	return true;
+}
+
+static access_mask_t
+pick_access_mask_for_request_type(const enum landlock_request_type type,
+				  const struct access_masks access_masks)
+{
+	switch (type) {
+	case LANDLOCK_REQUEST_FS_ACCESS:
+		return access_masks.fs;
+	case LANDLOCK_REQUEST_NET_ACCESS:
+		return access_masks.net;
+	default:
+		WARN_ONCE(1, "Invalid request type %d passed to %s", type,
+			  __func__);
+		return 0;
+	}
+}
+
+/*
+ * Whether a quiet rule silences the denial: the rule must cover the whole
+ * denied access in the layer that denied it (a quiet rule in a non-denying
+ * layer does not suppress the denial).
+ */
+static bool
+is_denial_quieted(const struct landlock_request *const request,
+		  const struct landlock_hierarchy *const youngest_denied,
+		  const access_mask_t missing, const bool object_quiet_flag)
+{
+	if (object_quiet_flag) {
+		const access_mask_t quiet_mask =
+			pick_access_mask_for_request_type(
+				request->type, youngest_denied->quiet_masks);
+
+		return (quiet_mask & missing) == missing;
+	}
+
+	/*
+	 * Either the object is not quiet, or this is a scope request.  We check
+	 * request->type to distinguish between the two cases.
+	 */
+	switch (request->type) {
+	case LANDLOCK_REQUEST_SCOPE_SIGNAL:
+		return !!(youngest_denied->quiet_masks.scope &
+			  LANDLOCK_SCOPE_SIGNAL);
+	case LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET:
+		return !!(youngest_denied->quiet_masks.scope &
+			  LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET);
+	/*
+	 * Leave LANDLOCK_REQUEST_PTRACE and LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY
+	 * unhandled for now - they are never quiet.
+	 */
+	default:
+		return false;
+	}
+}
+
+/*
+ * Computes whether a denial from youngest_denied is selected for logging by the
+ * domain's policy: its logging must not be disabled (by both per-execution
+ * flags being off, or by an ancestor's
+ * LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF), the per-execution flag matching
+ * same_exec must be set, and no quiet rule may cover the denied access.
+ * landlock_log_denial() computes this once and passes it to
+ * landlock_audit_denial(), which additionally requires audit_enabled.
+ */
+static bool
+is_denial_logged(const struct landlock_request *const request,
+		 const struct landlock_hierarchy *const youngest_denied,
+		 const access_mask_t missing, const bool same_exec,
+		 const bool object_quiet_flag)
+{
+	if (READ_ONCE(youngest_denied->log_status) == LANDLOCK_LOG_DISABLED)
+		return false;
+
+	if (!(same_exec ? youngest_denied->log_same_exec :
+			  youngest_denied->log_new_exec))
+		return false;
+
+	return !is_denial_quieted(request, youngest_denied, missing,
+				  object_quiet_flag);
+}
+
+/**
+ * landlock_log_denial - Log a denied access
+ *
+ * @subject: The Landlock subject's credential denying an action.
+ * @request: Detail of the user space request.
+ */
+void landlock_log_denial(const struct landlock_cred_security *const subject,
+			 const struct landlock_request *const request)
+{
+	struct landlock_hierarchy *youngest_denied;
+	size_t youngest_layer;
+	access_mask_t missing;
+	bool object_quiet_flag = false;
+
+	if (WARN_ON_ONCE(!subject || !subject->domain ||
+			 !subject->domain->hierarchy || !request))
+		return;
+
+	if (!is_valid_request(request))
+		return;
+
+	missing = request->access;
+	if (missing) {
+		/* Gets the nearest domain that denies the request. */
+		if (request->layer_masks) {
+			youngest_layer = get_denied_layer(subject->domain,
+							  &missing,
+							  request->layer_masks);
+			object_quiet_flag =
+				request->layer_masks->layers[youngest_layer]
+					.quiet;
+		} else {
+			youngest_layer = get_layer_from_deny_masks(
+				&missing, _LANDLOCK_ACCESS_FS_OPTIONAL,
+				request->deny_masks,
+				request->quiet_optional_accesses,
+				&object_quiet_flag);
+		}
+		youngest_denied =
+			get_hierarchy(subject->domain, youngest_layer);
+	} else {
+		youngest_layer = request->layer_plus_one - 1;
+		youngest_denied =
+			get_hierarchy(subject->domain, youngest_layer);
+	}
+
+	const bool same_exec = !!(subject->domain_exec & BIT(youngest_layer));
+	const bool logged = is_denial_logged(request, youngest_denied, missing,
+					     same_exec, object_quiet_flag);
+
+	/*
+	 * Consistently keeps track of the number of denied access requests even
+	 * if audit is currently disabled, or if audit rules currently exclude
+	 * this record type, or if landlock_restrict_self(2)'s flags quiet logs.
+	 */
+	atomic64_inc(&youngest_denied->num_denials);
+
+	landlock_trace_denial(request, youngest_denied, missing, same_exec,
+			      logged);
+	landlock_audit_denial(request, youngest_denied, missing, logged);
+}
+
+/**
+ * landlock_log_free_domain - Log domain deallocation
+ *
+ * @hierarchy: The domain's hierarchy being deallocated.
+ *
+ * Called from landlock_put_domain_deferred() (via a work queue scheduled by
+ * hook_cred_free()) or directly from landlock_put_domain().
+ */
+void landlock_log_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+	if (WARN_ON_ONCE(!hierarchy))
+		return;
+
+	landlock_trace_free_domain(hierarchy);
+	landlock_audit_free_domain(hierarchy);
+}
+
+#ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST
+
+static struct kunit_case test_cases[] = {
+	/* clang-format off */
+	KUNIT_CASE(test_get_hierarchy),
+	KUNIT_CASE(test_get_denied_layer),
+	KUNIT_CASE(test_get_layer_from_deny_masks),
+	{}
+	/* clang-format on */
+};
+
+static struct kunit_suite test_suite = {
+	.name = "landlock_log",
+	.test_cases = test_cases,
+};
+
+kunit_test_suite(test_suite);
+
+#endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */
diff --git a/security/landlock/log.h b/security/landlock/log.h
new file mode 100644
index 000000000..e0a6e44f3
--- /dev/null
+++ b/security/landlock/log.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Log helpers
+ *
+ * Copyright © 2023-2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#ifndef _SECURITY_LANDLOCK_LOG_H
+#define _SECURITY_LANDLOCK_LOG_H
+
+#include <linux/lsm_audit.h>
+
+#include "access.h"
+
+struct landlock_cred_security;
+struct landlock_hierarchy;
+
+enum landlock_request_type {
+	LANDLOCK_REQUEST_PTRACE = 1,
+	LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY,
+	LANDLOCK_REQUEST_FS_ACCESS,
+	LANDLOCK_REQUEST_NET_ACCESS,
+	LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET,
+	LANDLOCK_REQUEST_SCOPE_SIGNAL,
+};
+
+/*
+ * We should be careful to only use a variable of this type for
+ * landlock_log_denial().  This way, the compiler can remove it entirely if
+ * CONFIG_SECURITY_LANDLOCK_LOG is not set.
+ */
+struct landlock_request {
+	/* Mandatory fields. */
+	enum landlock_request_type type;
+	struct common_audit_data audit;
+
+	/**
+	 * layer_plus_one: First layer level that denies the request + 1.  The
+	 * extra one is useful to detect uninitialized field.
+	 */
+	size_t layer_plus_one;
+
+	/* Required field for configurable access control. */
+	access_mask_t access;
+
+	/* Required fields for requests with layer masks. */
+	const struct layer_masks *layer_masks;
+
+	/* Required fields for requests with deny masks. */
+	const access_mask_t all_existing_optional_access;
+	deny_masks_t deny_masks;
+	optional_access_t quiet_optional_accesses;
+
+	/*
+	 * Other-party domain ID for a relational (scope/ptrace) denial, or 0 if
+	 * that party is unsandboxed.  An ID, not a pointer: the other task can
+	 * replace its credential and free the domain it referenced.  Trace path
+	 * only; audit ignores it.
+	 */
+	u64 other_domain_id;
+};
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+
+void landlock_log_free_domain(const struct landlock_hierarchy *const hierarchy);
+
+void landlock_log_denial(const struct landlock_cred_security *const subject,
+			 const struct landlock_request *const request);
+
+#else /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+static inline void
+landlock_log_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+}
+
+static inline void
+landlock_log_denial(const struct landlock_cred_security *const subject,
+		    const struct landlock_request *const request)
+{
+}
+
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+#endif /* _SECURITY_LANDLOCK_LOG_H */
diff --git a/security/landlock/net.c b/security/landlock/net.c
new file mode 100644
index 000000000..8f2aaac54
--- /dev/null
+++ b/security/landlock/net.c
@@ -0,0 +1,413 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Network management and hooks
+ *
+ * Copyright © 2022-2023 Huawei Tech. Co., Ltd.
+ * Copyright © 2022-2025 Microsoft Corporation
+ */
+
+#include <linux/in.h>
+#include <linux/lsm_audit.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+#include <net/ipv6.h>
+
+#include "common.h"
+#include "cred.h"
+#include "domain.h"
+#include "limits.h"
+#include "log.h"
+#include "net.h"
+#include "ruleset.h"
+
+#include <trace/events/landlock.h>
+
+int landlock_append_net_rule(struct landlock_ruleset *const ruleset,
+			     const u16 port, access_mask_t access_rights,
+			     const u32 flags)
+{
+	int err;
+	const struct landlock_id id = {
+		.key.data = (__force uintptr_t)htons(port),
+		.type = LANDLOCK_KEY_NET_PORT,
+	};
+
+	BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data));
+
+	/* Transforms relative access rights to absolute ones. */
+	access_rights |= LANDLOCK_MASK_ACCESS_NET & ~ruleset->handled_masks.net;
+
+	mutex_lock(&ruleset->lock);
+	err = landlock_insert_rule(ruleset, id, access_rights, flags);
+
+	/*
+	 * Emit after the rule insertion succeeds, so every event corresponds to
+	 * a rule that is actually in the ruleset.  The ruleset lock is still
+	 * held for BTF consistency (enforced by lockdep_assert_held in
+	 * TP_fast_assign).
+	 */
+	if (!err)
+		trace_landlock_add_rule_net(ruleset, access_rights, port);
+	mutex_unlock(&ruleset->lock);
+
+	return err;
+}
+
+static bool unmask_layers_net(const struct landlock_domain *const domain,
+			      const struct landlock_id id,
+			      struct layer_masks *masks,
+			      access_mask_t access_request)
+{
+	const struct landlock_rule *rule = NULL;
+	bool ret;
+
+	ret = landlock_unmask_layers(domain, id, masks, &rule);
+	if (rule)
+		trace_landlock_check_rule_net(
+			domain, rule, access_request,
+			ntohs((__force __be16)id.key.data));
+	return ret;
+}
+
+static int current_check_access_socket(struct socket *const sock,
+				       struct sockaddr *const address,
+				       const int addrlen,
+				       access_mask_t access_request,
+				       bool connecting)
+{
+	unsigned short sock_family;
+	__be16 port;
+	struct layer_masks layer_masks = {};
+	struct landlock_id id = {
+		.type = LANDLOCK_KEY_NET_PORT,
+	};
+	const struct access_masks masks = {
+		.net = access_request,
+	};
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), masks, NULL);
+	struct lsm_network_audit audit_net = {};
+
+	if (!subject)
+		return 0;
+
+	/* Checks for minimal header length to safely read sa_family. */
+	if (addrlen < offsetofend(typeof(*address), sa_family))
+		return -EINVAL;
+
+	/*
+	 * The socket is not locked, so sk_family can change concurrently due to
+	 * e.g. setsockopt(IPV6_ADDRFORM).
+	 */
+	sock_family = READ_ONCE(sock->sk->sk_family);
+
+	switch (address->sa_family) {
+	case AF_UNSPEC:
+		if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP ||
+		    (access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP &&
+		     connecting)) {
+			/*
+			 * Connecting to an address with AF_UNSPEC dissolves the
+			 * remote association while retaining the socket object
+			 * (i.e., the file descriptor). For TCP, it has the same
+			 * effect as closing the connection. For UDP, it removes
+			 * any preset remote address. As for dropping
+			 * privileges, these actions are always allowed.  Let
+			 * the network stack handle potential inconsistencies
+			 * and return -EINVAL if needed.
+			 */
+			return 0;
+		} else if (access_request ==
+			   LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) {
+			if (sock_family == AF_INET6) {
+				/*
+				 * We cannot allow sending UDP datagrams to an
+				 * explicit AF_UNSPEC address on IPv6 sockets,
+				 * even if AF_UNSPEC is treated as "no address"
+				 * on such sockets (so it should always be
+				 * allowed).  That's because the socket's family
+				 * can change under our feet (if another thread
+				 * calls setsockopt(IPV6_ADDRFORM)) to IPv4,
+				 * which would then treat AF_UNSPEC as AF_INET.
+				 */
+				audit_net.family = AF_UNSPEC;
+				audit_net.sk = sock->sk;
+				landlock_init_layer_masks(
+					subject->domain, access_request,
+					&layer_masks, LANDLOCK_KEY_NET_PORT);
+				landlock_log_denial(
+					subject,
+					&(struct landlock_request){
+						.type = LANDLOCK_REQUEST_NET_ACCESS,
+						.audit.type =
+							LSM_AUDIT_DATA_NET,
+						.audit.u.net = &audit_net,
+						.access = access_request,
+						.layer_masks = &layer_masks,
+					});
+				return -EACCES;
+			}
+		} else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP ||
+			   access_request == LANDLOCK_ACCESS_NET_BIND_UDP) {
+			/*
+			 * Binding to an AF_UNSPEC address is treated
+			 * differently by IPv4 and IPv6 sockets. The socket's
+			 * family may change under our feet due to
+			 * setsockopt(IPV6_ADDRFORM), but that's ok: we either
+			 * reject entirely for IPv6 or require
+			 * %LANDLOCK_ACCESS_NET_BIND_TCP or
+			 * %LANDLOCK_ACCESS_NET_BIND_UDP for IPv4, so it cannot
+			 * be used to bypass the policy.
+			 *
+			 * IPv4 sockets map AF_UNSPEC to AF_INET for
+			 * retrocompatibility for bind accesses, only if the
+			 * address is INADDR_ANY (cf. __inet_bind). IPv6
+			 * sockets always reject it.
+			 *
+			 * Checking the address is required to not wrongfully
+			 * return -EACCES instead of -EAFNOSUPPORT or -EINVAL.
+			 * We could return 0 and let the network stack handle
+			 * these checks, but it is safer to return a proper
+			 * error and test consistency thanks to kselftest.
+			 */
+			if (sock_family == AF_INET) {
+				const struct sockaddr_in *const sockaddr =
+					(struct sockaddr_in *)address;
+
+				if (addrlen < sizeof(struct sockaddr_in))
+					return -EINVAL;
+
+				if (sockaddr->sin_addr.s_addr !=
+				    htonl(INADDR_ANY))
+					return -EAFNOSUPPORT;
+			} else {
+				if (addrlen < SIN6_LEN_RFC2133)
+					return -EINVAL;
+				else
+					return -EAFNOSUPPORT;
+			}
+		} else {
+			WARN_ON_ONCE(1);
+		}
+		/*
+		 * AF_UNSPEC is treated as AF_INET only in
+		 * bind(AF_UNSPEC+INADDR_ANY) on IPv4 sockets and when sending
+		 * to AF_UNSPEC addresses on IPv4 sockets.
+		 */
+		fallthrough;
+	case AF_INET: {
+		const struct sockaddr_in *addr4;
+
+		if (addrlen < sizeof(struct sockaddr_in))
+			return -EINVAL;
+
+		addr4 = (struct sockaddr_in *)address;
+		port = addr4->sin_port;
+
+		if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP ||
+		    access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) {
+			audit_net.dport = port;
+			audit_net.v4info.daddr = addr4->sin_addr.s_addr;
+		} else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP ||
+			   access_request == LANDLOCK_ACCESS_NET_BIND_UDP) {
+			audit_net.sport = port;
+			audit_net.v4info.saddr = addr4->sin_addr.s_addr;
+		} else {
+			WARN_ON_ONCE(1);
+		}
+		break;
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6: {
+		const struct sockaddr_in6 *addr6;
+
+		if (addrlen < SIN6_LEN_RFC2133)
+			return -EINVAL;
+
+		addr6 = (struct sockaddr_in6 *)address;
+		port = addr6->sin6_port;
+
+		if (access_request == LANDLOCK_ACCESS_NET_CONNECT_TCP ||
+		    access_request == LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP) {
+			audit_net.dport = port;
+			audit_net.v6info.daddr = addr6->sin6_addr;
+		} else if (access_request == LANDLOCK_ACCESS_NET_BIND_TCP ||
+			   access_request == LANDLOCK_ACCESS_NET_BIND_UDP) {
+			audit_net.sport = port;
+			audit_net.v6info.saddr = addr6->sin6_addr;
+		} else {
+			WARN_ON_ONCE(1);
+		}
+		break;
+	}
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
+	default:
+		return 0;
+	}
+
+	/*
+	 * Checks sa_family consistency to not wrongfully return
+	 * -EACCES instead of -EINVAL.  Valid sa_family changes are
+	 * only (from AF_INET or AF_INET6) to AF_UNSPEC.
+	 *
+	 * We could return 0 and let the network stack handle this
+	 * check, but it is safer to return a proper error and test
+	 * consistency thanks to kselftest.
+	 */
+	if (address->sa_family != sock_family &&
+	    address->sa_family != AF_UNSPEC)
+		return -EINVAL;
+
+	id.key.data = (__force uintptr_t)port;
+	BUILD_BUG_ON(sizeof(port) > sizeof(id.key.data));
+
+	access_request = landlock_init_layer_masks(subject->domain,
+						   access_request, &layer_masks,
+						   LANDLOCK_KEY_NET_PORT);
+	if (!access_request)
+		return 0;
+
+	if (unmask_layers_net(subject->domain, id, &layer_masks,
+			      access_request))
+		return 0;
+
+	audit_net.family = address->sa_family;
+	audit_net.sk = sock->sk;
+	landlock_log_denial(subject,
+			    &(struct landlock_request){
+				    .type = LANDLOCK_REQUEST_NET_ACCESS,
+				    .audit.type = LSM_AUDIT_DATA_NET,
+				    .audit.u.net = &audit_net,
+				    .access = access_request,
+				    .layer_masks = &layer_masks,
+			    });
+	return -EACCES;
+}
+
+static int current_check_autobind_udp_socket(struct socket *const sock)
+{
+	const struct access_masks bind_udp = {
+		.net = LANDLOCK_ACCESS_NET_BIND_UDP,
+	};
+	struct sockaddr_storage port0 = {};
+	unsigned short num;
+	bool slow;
+
+	/* Quick return for non-Landlocked tasks. */
+	if (!landlock_get_applicable_subject(current_cred(), bind_udp, NULL))
+		return 0;
+
+	/*
+	 * On UDP sockets, if a local port has not already been bound, calling
+	 * connect() or sending a first datagram has the side effect of
+	 * autobinding an ephemeral port: we also have to check that the process
+	 * would have had the right to bind(0) explicitly.  Hold the socket lock
+	 * around the inet_num read to exclude udp_lib_get_port()'s transient
+	 * inet_num = snum write that is reverted to 0 on a failing reuseport
+	 * bind.
+	 */
+	slow = lock_sock_fast(sock->sk);
+	num = inet_sk(sock->sk)->inet_num;
+	unlock_sock_fast(sock->sk, slow);
+	if (num != 0)
+		return 0;
+
+	/*
+	 * Construct a struct sockaddr* with port 0 to pretend the process tried
+	 * to bind() on that address.
+	 */
+	port0.ss_family = READ_ONCE(sock->sk->sk_family);
+
+	return current_check_access_socket(sock, (struct sockaddr *)&port0,
+					   sizeof(port0), bind_udp.net, false);
+}
+
+static int hook_socket_bind(struct socket *const sock,
+			    struct sockaddr *const address, const int addrlen)
+{
+	access_mask_t access_request;
+
+	if (sk_is_tcp(sock->sk))
+		access_request = LANDLOCK_ACCESS_NET_BIND_TCP;
+	else if (sk_is_udp(sock->sk))
+		access_request = LANDLOCK_ACCESS_NET_BIND_UDP;
+	else
+		return 0;
+
+	return current_check_access_socket(sock, address, addrlen,
+					   access_request, false);
+}
+
+static int hook_socket_connect(struct socket *const sock,
+			       struct sockaddr *const address,
+			       const int addrlen)
+{
+	access_mask_t access_request;
+	int ret = 0;
+
+	if (sk_is_tcp(sock->sk))
+		access_request = LANDLOCK_ACCESS_NET_CONNECT_TCP;
+	else if (sk_is_udp(sock->sk))
+		access_request = LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP;
+	else
+		return 0;
+
+	ret = current_check_access_socket(sock, address, addrlen,
+					  access_request, true);
+
+	/*
+	 * connect()ing to an AF_UNSPEC address does not trigger an autobind and
+	 * should never be restricted.
+	 */
+	if (ret == 0 && sk_is_udp(sock->sk) &&
+	    addrlen >= offsetofend(typeof(*address), sa_family) &&
+	    address->sa_family != AF_UNSPEC)
+		ret = current_check_autobind_udp_socket(sock);
+
+	return ret;
+}
+
+static int hook_socket_sendmsg(struct socket *const sock,
+			       struct msghdr *const msg, const int size)
+{
+	struct sockaddr *const address = msg->msg_name;
+	const int addrlen = msg->msg_namelen;
+	access_mask_t access_request;
+	int ret = 0;
+
+	if ((msg->msg_flags & MSG_FASTOPEN) && address && sk_is_tcp(sock->sk)) {
+		ret = current_check_access_socket(
+			sock, address, addrlen, LANDLOCK_ACCESS_NET_CONNECT_TCP,
+			true);
+		if (ret != 0)
+			return ret;
+	}
+
+	if (sk_is_udp(sock->sk))
+		access_request = LANDLOCK_ACCESS_NET_CONNECT_SEND_UDP;
+	else
+		return 0;
+
+	if (address != NULL)
+		ret = current_check_access_socket(sock, address, addrlen,
+						  access_request, false);
+
+	if (ret == 0)
+		ret = current_check_autobind_udp_socket(sock);
+
+	return ret;
+}
+
+static struct security_hook_list landlock_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(socket_bind, hook_socket_bind),
+	LSM_HOOK_INIT(socket_connect, hook_socket_connect),
+	LSM_HOOK_INIT(socket_sendmsg, hook_socket_sendmsg),
+};
+
+__init void landlock_add_net_hooks(void)
+{
+	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+			   &landlock_lsmid);
+}
diff --git a/security/landlock/net.h b/security/landlock/net.h
new file mode 100644
index 000000000..5c0e3b409
--- /dev/null
+++ b/security/landlock/net.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Network management and hooks
+ *
+ * Copyright © 2022-2023 Huawei Tech. Co., Ltd.
+ */
+
+#ifndef _SECURITY_LANDLOCK_NET_H
+#define _SECURITY_LANDLOCK_NET_H
+
+#include "common.h"
+#include "ruleset.h"
+#include "setup.h"
+
+#if IS_ENABLED(CONFIG_INET)
+__init void landlock_add_net_hooks(void);
+
+int landlock_append_net_rule(struct landlock_ruleset *const ruleset,
+			     const u16 port, access_mask_t access_rights,
+			     const u32 flags);
+#else /* IS_ENABLED(CONFIG_INET) */
+static inline void landlock_add_net_hooks(void)
+{
+}
+
+static inline int
+landlock_append_net_rule(struct landlock_ruleset *const ruleset, const u16 port,
+			 access_mask_t access_rights, const u32 flags)
+{
+	return -EAFNOSUPPORT;
+}
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+#endif /* _SECURITY_LANDLOCK_NET_H */
diff --git a/security/landlock/object.c b/security/landlock/object.c
new file mode 100644
index 000000000..0d6e159ef
--- /dev/null
+++ b/security/landlock/object.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Object management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/bug.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "object.h"
+
+struct landlock_object *
+landlock_create_object(const struct landlock_object_underops *const underops,
+		       void *const underobj)
+{
+	struct landlock_object *new_object;
+
+	if (WARN_ON_ONCE(!underops || !underobj))
+		return ERR_PTR(-ENOENT);
+	new_object = kzalloc_obj(*new_object, GFP_KERNEL_ACCOUNT);
+	if (!new_object)
+		return ERR_PTR(-ENOMEM);
+	refcount_set(&new_object->usage, 1);
+	spin_lock_init(&new_object->lock);
+	new_object->underops = underops;
+	new_object->underobj = underobj;
+	return new_object;
+}
+
+/*
+ * The caller must own the object (i.e. thanks to object->usage) to safely put
+ * it.
+ */
+void landlock_put_object(struct landlock_object *const object)
+{
+	/*
+	 * The call to @object->underops->release(object) might sleep, e.g.
+	 * because of iput().
+	 */
+	might_sleep();
+	if (!object)
+		return;
+
+	/*
+	 * If the @object's refcount cannot drop to zero, we can just decrement
+	 * the refcount without holding a lock. Otherwise, the decrement must
+	 * happen under @object->lock for synchronization with things like
+	 * get_inode_object().
+	 */
+	if (refcount_dec_and_lock(&object->usage, &object->lock)) {
+		__acquire(&object->lock);
+		/*
+		 * With @object->lock initially held, remove the reference from
+		 * @object->underobj to @object (if it still exists).
+		 */
+		object->underops->release(object);
+		kfree_rcu(object, rcu_free);
+	}
+}
diff --git a/security/landlock/object.h b/security/landlock/object.h
new file mode 100644
index 000000000..5f28c35e8
--- /dev/null
+++ b/security/landlock/object.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Object management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_OBJECT_H
+#define _SECURITY_LANDLOCK_OBJECT_H
+
+#include <linux/compiler_types.h>
+#include <linux/refcount.h>
+#include <linux/spinlock.h>
+
+struct landlock_object;
+
+/**
+ * struct landlock_object_underops - Operations on an underlying object
+ */
+struct landlock_object_underops {
+	/**
+	 * @release: Releases the underlying object (e.g. iput() for an inode).
+	 */
+	void (*release)(struct landlock_object *const object)
+		__releases(object->lock);
+};
+
+/**
+ * struct landlock_object - Security blob tied to a kernel object
+ *
+ * The goal of this structure is to enable to tie a set of ephemeral access
+ * rights (pertaining to different domains) to a kernel object (e.g an inode)
+ * in a safe way.  This implies to handle concurrent use and modification.
+ *
+ * The lifetime of a &struct landlock_object depends on the rules referring to
+ * it.
+ */
+struct landlock_object {
+	/**
+	 * @usage: This counter is used to tie an object to the rules matching
+	 * it or to keep it alive while adding a new rule.  If this counter
+	 * reaches zero, this struct must not be modified, but this counter can
+	 * still be read from within an RCU read-side critical section.  When
+	 * adding a new rule to an object with a usage counter of zero, we must
+	 * wait until the pointer to this object is set to NULL (or recycled).
+	 */
+	refcount_t usage;
+	/**
+	 * @lock: Protects against concurrent modifications.  This lock must be
+	 * held from the time @usage drops to zero until any weak references
+	 * from @underobj to this object have been cleaned up.
+	 *
+	 * Lock ordering: inode->i_lock nests inside this.
+	 */
+	spinlock_t lock;
+	/**
+	 * @underobj: Used when cleaning up an object and to mark an object as
+	 * tied to its underlying kernel structure.  This pointer is protected
+	 * by @lock.  Cf. landlock_release_inodes() and release_inode().
+	 */
+	void *underobj;
+	union {
+		/**
+		 * @rcu_free: Enables lockless use of @usage, @lock and
+		 * @underobj from within an RCU read-side critical section.
+		 * @rcu_free and @underops are only used by
+		 * landlock_put_object().
+		 */
+		struct rcu_head rcu_free;
+		/**
+		 * @underops: Enables landlock_put_object() to release the
+		 * underlying object (e.g. inode).
+		 */
+		const struct landlock_object_underops *underops;
+	};
+};
+
+struct landlock_object *
+landlock_create_object(const struct landlock_object_underops *const underops,
+		       void *const underobj);
+
+void landlock_put_object(struct landlock_object *const object);
+
+static inline void landlock_get_object(struct landlock_object *const object)
+{
+	if (object)
+		refcount_inc(&object->usage);
+}
+
+#endif /* _SECURITY_LANDLOCK_OBJECT_H */
diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
new file mode 100644
index 000000000..0d0770752
--- /dev/null
+++ b/security/landlock/ruleset.c
@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Ruleset management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/cleanup.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <uapi/linux/landlock.h>
+
+#include "access.h"
+#include "id.h"
+#include "limits.h"
+#include "object.h"
+#include "ruleset.h"
+
+#include <trace/events/landlock.h>
+
+struct landlock_ruleset *
+landlock_create_ruleset(const access_mask_t fs_access_mask,
+			const access_mask_t net_access_mask,
+			const access_mask_t scope_mask)
+{
+	struct landlock_ruleset *new_ruleset;
+
+	/* Informs about useless ruleset. */
+	if (!fs_access_mask && !net_access_mask && !scope_mask)
+		return ERR_PTR(-ENOMSG);
+
+	new_ruleset = kzalloc_obj(*new_ruleset, GFP_KERNEL_ACCOUNT);
+	if (!new_ruleset)
+		return ERR_PTR(-ENOMEM);
+
+	refcount_set(&new_ruleset->usage, 1);
+	mutex_init(&new_ruleset->lock);
+	new_ruleset->rules.root_inode = RB_ROOT;
+
+#if IS_ENABLED(CONFIG_INET)
+	new_ruleset->rules.root_net_port = RB_ROOT;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+#ifdef CONFIG_TRACEPOINTS
+	new_ruleset->id = landlock_get_id_range(1);
+#endif /* CONFIG_TRACEPOINTS */
+
+	/* Should already be checked in landlock_create_ruleset(). */
+	if (fs_access_mask) {
+		const access_mask_t mask = fs_access_mask &
+					   LANDLOCK_MASK_ACCESS_FS;
+
+		WARN_ON_ONCE(fs_access_mask != mask);
+		new_ruleset->handled_masks.fs |= mask;
+	}
+	if (net_access_mask) {
+		const access_mask_t mask = net_access_mask &
+					   LANDLOCK_MASK_ACCESS_NET;
+
+		WARN_ON_ONCE(net_access_mask != mask);
+		new_ruleset->handled_masks.net |= mask;
+	}
+	if (scope_mask) {
+		const access_mask_t mask = scope_mask & LANDLOCK_MASK_SCOPE;
+
+		WARN_ON_ONCE(scope_mask != mask);
+		new_ruleset->handled_masks.scope |= mask;
+	}
+	return new_ruleset;
+}
+
+static void build_check_rule(void)
+{
+	const struct landlock_rule rule = {
+		.num_layers = ~0,
+	};
+
+	/*
+	 * Checks that .num_layers is large enough for at least
+	 * LANDLOCK_MAX_NUM_LAYERS layers.
+	 */
+	BUILD_BUG_ON(rule.num_layers < LANDLOCK_MAX_NUM_LAYERS);
+}
+
+static bool is_object_pointer(const enum landlock_key_type key_type)
+{
+	switch (key_type) {
+	case LANDLOCK_KEY_INODE:
+		return true;
+
+#if IS_ENABLED(CONFIG_INET)
+	case LANDLOCK_KEY_NET_PORT:
+		return false;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	default:
+		WARN_ON_ONCE(1);
+		return false;
+	}
+}
+
+static struct landlock_rule *
+create_rule(const struct landlock_id id,
+	    const struct landlock_layer (*layers)[], const u32 num_layers,
+	    const struct landlock_layer *const new_layer)
+{
+	struct landlock_rule *new_rule;
+	u32 new_num_layers;
+
+	build_check_rule();
+	if (new_layer) {
+		/* Should already be checked by landlock_merge_ruleset(). */
+		if (WARN_ON_ONCE(num_layers >= LANDLOCK_MAX_NUM_LAYERS))
+			return ERR_PTR(-E2BIG);
+		new_num_layers = num_layers + 1;
+	} else {
+		new_num_layers = num_layers;
+	}
+	new_rule = kzalloc_flex(*new_rule, layers, new_num_layers,
+				GFP_KERNEL_ACCOUNT);
+	if (!new_rule)
+		return ERR_PTR(-ENOMEM);
+	RB_CLEAR_NODE(&new_rule->node);
+	if (is_object_pointer(id.type)) {
+		/* This should have been caught by landlock_store_rule(). */
+		WARN_ON_ONCE(!id.key.object);
+		landlock_get_object(id.key.object);
+	}
+
+	new_rule->key = id.key;
+	new_rule->num_layers = new_num_layers;
+	/* Copies the original layer stack. */
+	memcpy(new_rule->layers, layers,
+	       flex_array_size(new_rule, layers, num_layers));
+	if (new_layer)
+		/* Adds a copy of @new_layer on the layer stack. */
+		new_rule->layers[new_rule->num_layers - 1] = *new_layer;
+	return new_rule;
+}
+
+static void free_rule(struct landlock_rule *const rule,
+		      const enum landlock_key_type key_type)
+{
+	might_sleep();
+	if (!rule)
+		return;
+	if (is_object_pointer(key_type))
+		landlock_put_object(rule->key.object);
+	kfree(rule);
+}
+
+static void build_check_ruleset(void)
+{
+	const struct landlock_rules rules = {
+		.num_rules = ~0,
+	};
+
+	BUILD_BUG_ON(rules.num_rules < LANDLOCK_MAX_NUM_RULES);
+}
+
+/**
+ * landlock_store_rule - Create and insert a rule into the rule storage
+ *
+ * @rules: The rule storage to be updated.  The caller is responsible for
+ *         any required locking.  For rulesets, this means holding
+ *         &landlock_ruleset.lock.  For domains under construction, no lock is
+ *         needed because the domain is not yet visible to other tasks.
+ * @id: The ID to build the new rule with.  The underlying kernel object, if
+ *      any, must be held by the caller.
+ * @layers: One or multiple layers to be copied into the new rule.
+ * @num_layers: The number of @layers entries.
+ *
+ * When user space requests to add a new rule to a ruleset, @layers only
+ * contains one entry and this entry is not assigned to any level.  In this
+ * case, the new rule will extend @rules, similarly to a boolean OR between
+ * access rights.
+ *
+ * When merging a ruleset in a domain, or copying a domain, @layers will be
+ * added to @rules as new constraints, similarly to a boolean AND between access
+ * rights.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int landlock_store_rule(struct landlock_rules *const rules,
+			const struct landlock_id id,
+			const struct landlock_layer (*layers)[],
+			const size_t num_layers)
+{
+	struct rb_node **walker_node;
+	struct rb_node *parent_node = NULL;
+	struct landlock_rule *new_rule;
+	struct rb_root *root;
+
+	might_sleep();
+	if (WARN_ON_ONCE(!layers))
+		return -ENOENT;
+
+	if (is_object_pointer(id.type) && WARN_ON_ONCE(!id.key.object))
+		return -ENOENT;
+
+	root = landlock_get_rule_root(rules, id.type);
+	if (IS_ERR(root))
+		return PTR_ERR(root);
+
+	walker_node = &root->rb_node;
+	while (*walker_node) {
+		struct landlock_rule *const this =
+			rb_entry(*walker_node, struct landlock_rule, node);
+
+		if (this->key.data != id.key.data) {
+			parent_node = *walker_node;
+			if (this->key.data < id.key.data)
+				walker_node = &((*walker_node)->rb_right);
+			else
+				walker_node = &((*walker_node)->rb_left);
+			continue;
+		}
+
+		/* Only a single-level layer should match an existing rule. */
+		if (WARN_ON_ONCE(num_layers != 1))
+			return -EINVAL;
+
+		/* If there is a matching rule, updates it. */
+		if ((*layers)[0].level == 0) {
+			/*
+			 * Extends access rights when the request comes from
+			 * landlock_add_rule(2), i.e. @rules is not a domain.
+			 */
+			if (WARN_ON_ONCE(this->num_layers != 1))
+				return -EINVAL;
+			if (WARN_ON_ONCE(this->layers[0].level != 0))
+				return -EINVAL;
+			this->layers[0].access |= (*layers)[0].access;
+			this->layers[0].flags.quiet |= (*layers)[0].flags.quiet;
+			return 0;
+		}
+
+		if (WARN_ON_ONCE(this->layers[0].level == 0))
+			return -EINVAL;
+
+		/*
+		 * Intersects access rights when it is a merge between a
+		 * ruleset and a domain.
+		 */
+		new_rule = create_rule(id, &this->layers, this->num_layers,
+				       &(*layers)[0]);
+		if (IS_ERR(new_rule))
+			return PTR_ERR(new_rule);
+		rb_replace_node(&this->node, &new_rule->node, root);
+		free_rule(this, id.type);
+		return 0;
+	}
+
+	/* There is no match for @id. */
+	build_check_ruleset();
+	if (rules->num_rules >= LANDLOCK_MAX_NUM_RULES)
+		return -E2BIG;
+	new_rule = create_rule(id, layers, num_layers, NULL);
+	if (IS_ERR(new_rule))
+		return PTR_ERR(new_rule);
+	rb_link_node(&new_rule->node, parent_node, walker_node);
+	rb_insert_color(&new_rule->node, root);
+	rules->num_rules++;
+	return 0;
+}
+
+static void build_check_layer(void)
+{
+	const struct landlock_layer layer = {
+		.level = ~0,
+		.access = ~0,
+	};
+
+	/*
+	 * Checks that .level and .access are large enough to contain their expected
+	 * maximum values.
+	 */
+	BUILD_BUG_ON(layer.level < LANDLOCK_MAX_NUM_LAYERS);
+	BUILD_BUG_ON(layer.access < LANDLOCK_MASK_ACCESS_FS);
+}
+
+/* @ruleset must be locked by the caller. */
+int landlock_insert_rule(struct landlock_ruleset *const ruleset,
+			 const struct landlock_id id,
+			 const access_mask_t access, const u32 flags)
+{
+	struct landlock_layer layers[] = { {
+		.access = access,
+		/*
+		 * When @level is zero, landlock_store_rule() extends @ruleset.
+		 */
+		.level = 0,
+		.flags = {
+			.quiet = !!(flags & LANDLOCK_ADD_RULE_QUIET),
+		},
+	} };
+	int err;
+
+	build_check_layer();
+	lockdep_assert_held(&ruleset->lock);
+	err = landlock_store_rule(&ruleset->rules, id, &layers,
+				  ARRAY_SIZE(layers));
+
+#ifdef CONFIG_TRACEPOINTS
+	if (!err)
+		ruleset->version++;
+#endif /* CONFIG_TRACEPOINTS */
+
+	return err;
+}
+
+void landlock_free_rules(struct landlock_rules *const rules)
+{
+	struct landlock_rule *freeme, *next;
+
+	might_sleep();
+	rbtree_postorder_for_each_entry_safe(freeme, next, &rules->root_inode,
+					     node)
+		free_rule(freeme, LANDLOCK_KEY_INODE);
+
+#if IS_ENABLED(CONFIG_INET)
+	rbtree_postorder_for_each_entry_safe(freeme, next,
+					     &rules->root_net_port, node)
+		free_rule(freeme, LANDLOCK_KEY_NET_PORT);
+#endif /* IS_ENABLED(CONFIG_INET) */
+}
+
+static void free_ruleset(struct landlock_ruleset *const ruleset)
+{
+	might_sleep();
+	trace_landlock_free_ruleset(ruleset);
+	landlock_free_rules(&ruleset->rules);
+	kfree(ruleset);
+}
+
+void landlock_put_ruleset(struct landlock_ruleset *const ruleset)
+{
+	might_sleep();
+	if (ruleset && refcount_dec_and_test(&ruleset->usage))
+		free_ruleset(ruleset);
+}
diff --git a/security/landlock/ruleset.h b/security/landlock/ruleset.h
new file mode 100644
index 000000000..b536fa042
--- /dev/null
+++ b/security/landlock/ruleset.h
@@ -0,0 +1,250 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Ruleset management
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#ifndef _SECURITY_LANDLOCK_RULESET_H
+#define _SECURITY_LANDLOCK_RULESET_H
+
+#include <linux/cleanup.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+
+#include "access.h"
+#include "limits.h"
+#include "object.h"
+
+/**
+ * struct landlock_layer - Access rights for a given layer
+ */
+struct landlock_layer {
+	/**
+	 * @level: Position of this layer in the layer stack.  Starts from 1.
+	 */
+	u8 level;
+	/**
+	 * @flags: Bitfield for special flags attached to this rule.
+	 */
+	struct {
+		/**
+		 * @flags.quiet: Suppresses denial logs for the object covered by
+		 * this rule in this domain.  For filesystem rules, this inherits
+		 * down the file hierarchy.
+		 */
+		u8 quiet : 1;
+	} flags;
+	/**
+	 * @access: Bitfield of allowed actions on the kernel object.  They are
+	 * relative to the object type (e.g. %LANDLOCK_ACTION_FS_READ).
+	 */
+	access_mask_t access;
+};
+
+/**
+ * union landlock_key - Key of a ruleset's red-black tree
+ */
+union landlock_key {
+	/**
+	 * @object: Pointer to identify a kernel object (e.g. an inode).
+	 */
+	struct landlock_object *object;
+	/**
+	 * @data: Raw data to identify an arbitrary 32-bit value
+	 * (e.g. a TCP port).
+	 */
+	uintptr_t data;
+};
+
+/**
+ * enum landlock_key_type - Type of &union landlock_key
+ */
+enum landlock_key_type {
+	/**
+	 * @LANDLOCK_KEY_INODE: Type of &landlock_rules.root_inode's node keys.
+	 */
+	LANDLOCK_KEY_INODE = 1,
+	/**
+	 * @LANDLOCK_KEY_NET_PORT: Type of &landlock_rules.root_net_port's node
+	 * keys.
+	 */
+	LANDLOCK_KEY_NET_PORT,
+};
+
+/**
+ * struct landlock_id - Unique rule identifier for a ruleset
+ */
+struct landlock_id {
+	/**
+	 * @key: Identifies either a kernel object (e.g. an inode) or
+	 * a raw value (e.g. a TCP port).
+	 */
+	union landlock_key key;
+	/**
+	 * @type: Type of a landlock_ruleset's root tree.
+	 */
+	const enum landlock_key_type type;
+};
+
+/**
+ * struct landlock_rule - Access rights tied to an object
+ */
+struct landlock_rule {
+	/**
+	 * @node: Node in the ruleset's red-black tree.
+	 */
+	struct rb_node node;
+	/**
+	 * @key: A union to identify either a kernel object (e.g. an inode) or
+	 * a raw data value (e.g. a network socket port). This is used as a key
+	 * for this ruleset element.  The pointer is set once and never
+	 * modified.  It always points to an allocated object because each rule
+	 * increments the refcount of its object.
+	 */
+	union landlock_key key;
+	/**
+	 * @num_layers: Number of entries in @layers.
+	 */
+	u32 num_layers;
+	/**
+	 * @layers: Stack of layers, from the latest to the newest, implemented
+	 * as a flexible array member (FAM).
+	 */
+	struct landlock_layer layers[] __counted_by(num_layers);
+};
+
+/**
+ * struct landlock_rules - Red-black tree storage for Landlock rules
+ *
+ * This structure holds the rule trees shared by both rulesets and domains.
+ */
+struct landlock_rules {
+	/**
+	 * @root_inode: Root of a red-black tree containing &struct
+	 * landlock_rule nodes with inode object.  Immutable for domains.
+	 */
+	struct rb_root root_inode;
+
+#if IS_ENABLED(CONFIG_INET)
+	/**
+	 * @root_net_port: Root of a red-black tree containing &struct
+	 * landlock_rule nodes with network port.  Immutable for domains.
+	 */
+	struct rb_root root_net_port;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	/**
+	 * @num_rules: Number of non-overlapping (i.e. not for the same object)
+	 * rules in this tree storage.
+	 */
+	u32 num_rules;
+};
+
+/**
+ * struct landlock_ruleset - Landlock ruleset
+ *
+ * This data structure must contain unique entries, be updatable, and quick to
+ * match an object.
+ */
+struct landlock_ruleset {
+	/**
+	 * @rules: Red-black tree storage for rules.
+	 */
+	struct landlock_rules rules;
+	/**
+	 * @lock: Protects against concurrent modifications of @rules, if @usage
+	 * is greater than zero.
+	 */
+	struct mutex lock;
+	/**
+	 * @usage: Number of file descriptors referencing this ruleset.
+	 */
+	refcount_t usage;
+
+#ifdef CONFIG_TRACEPOINTS
+	/**
+	 * @version: Counter incremented on each successful
+	 * landlock_add_rule(2), including when it only extends an existing
+	 * rule's access rights.  Used by tracepoints to correlate a domain with
+	 * the exact ruleset state it was created from.  Protected by @lock.
+	 */
+	u32 version;
+	/**
+	 * @id: Unique identifier for this ruleset, used for tracing.
+	 */
+	u64 id;
+#endif /* CONFIG_TRACEPOINTS */
+
+	/**
+	 * @quiet_masks: Stores the quiet flags for an unmerged ruleset.  For a
+	 * merged domain, this is stored in each layer's struct
+	 * landlock_hierarchy instead.
+	 */
+	struct access_masks quiet_masks;
+	/**
+	 * @handled_masks: Contains the subset of filesystem and network actions
+	 * that are handled by this ruleset.
+	 */
+	struct access_masks handled_masks;
+};
+
+struct landlock_ruleset *
+landlock_create_ruleset(const access_mask_t access_mask_fs,
+			const access_mask_t access_mask_net,
+			const access_mask_t scope_mask);
+
+void landlock_put_ruleset(struct landlock_ruleset *const ruleset);
+
+DEFINE_FREE(landlock_put_ruleset, struct landlock_ruleset *,
+	    if (!IS_ERR_OR_NULL(_T)) landlock_put_ruleset(_T))
+
+int landlock_insert_rule(struct landlock_ruleset *const ruleset,
+			 const struct landlock_id id,
+			 const access_mask_t access, const u32 flags);
+
+int landlock_store_rule(struct landlock_rules *const rules,
+			const struct landlock_id id,
+			const struct landlock_layer (*layers)[],
+			const size_t num_layers);
+
+void landlock_free_rules(struct landlock_rules *const rules);
+
+/**
+ * landlock_get_rule_root - Get the root of a rule tree by key type
+ *
+ * @rules: The rules storage to look up.
+ * @key_type: The type of key to select the tree for.
+ *
+ * Return: A pointer to the rb_root, or ERR_PTR(-EINVAL) on unknown type.
+ */
+static inline struct rb_root *
+landlock_get_rule_root(struct landlock_rules *const rules,
+		       const enum landlock_key_type key_type)
+{
+	switch (key_type) {
+	case LANDLOCK_KEY_INODE:
+		return &rules->root_inode;
+
+#if IS_ENABLED(CONFIG_INET)
+	case LANDLOCK_KEY_NET_PORT:
+		return &rules->root_net_port;
+#endif /* IS_ENABLED(CONFIG_INET) */
+
+	default:
+		WARN_ON_ONCE(1);
+		return ERR_PTR(-EINVAL);
+	}
+}
+
+static inline void landlock_get_ruleset(struct landlock_ruleset *const ruleset)
+{
+	if (ruleset)
+		refcount_inc(&ruleset->usage);
+}
+
+#endif /* _SECURITY_LANDLOCK_RULESET_H */
diff --git a/security/landlock/setup.c b/security/landlock/setup.c
new file mode 100644
index 000000000..47dac1736
--- /dev/null
+++ b/security/landlock/setup.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock LSM - Security framework setup
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#include <linux/bits.h>
+#include <linux/init.h>
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+
+#include "common.h"
+#include "cred.h"
+#include "errata.h"
+#include "fs.h"
+#include "id.h"
+#include "net.h"
+#include "setup.h"
+#include "task.h"
+
+bool landlock_initialized __ro_after_init = false;
+
+const struct lsm_id landlock_lsmid = {
+	.name = LANDLOCK_NAME,
+	.id = LSM_ID_LANDLOCK,
+};
+
+struct lsm_blob_sizes landlock_blob_sizes __ro_after_init = {
+	.lbs_cred = sizeof(struct landlock_cred_security),
+	.lbs_file = sizeof(struct landlock_file_security),
+	.lbs_inode = sizeof(struct landlock_inode_security),
+	.lbs_superblock = sizeof(struct landlock_superblock_security),
+};
+
+int landlock_errata __ro_after_init;
+
+static void __init compute_errata(void)
+{
+	size_t i;
+
+#ifndef __has_include
+	/*
+	 * This is a safeguard to make sure the compiler implements
+	 * __has_include (see errata.h).
+	 */
+	WARN_ON_ONCE(1);
+	return;
+#endif
+
+	for (i = 0; landlock_errata_init[i].number; i++) {
+		const int prev_errata = landlock_errata;
+
+		if (WARN_ON_ONCE(landlock_errata_init[i].abi >
+				 landlock_abi_version))
+			continue;
+
+		landlock_errata |= BIT(landlock_errata_init[i].number - 1);
+		WARN_ON_ONCE(prev_errata == landlock_errata);
+	}
+}
+
+static int __init landlock_init(void)
+{
+	compute_errata();
+	landlock_add_cred_hooks();
+	landlock_add_task_hooks();
+	landlock_add_fs_hooks();
+	landlock_add_net_hooks();
+	landlock_init_id();
+	landlock_initialized = true;
+	pr_info("Up and running.\n");
+	return 0;
+}
+
+DEFINE_LSM(LANDLOCK_NAME) = {
+	.id = &landlock_lsmid,
+	.init = landlock_init,
+	.blobs = &landlock_blob_sizes,
+};
diff --git a/security/landlock/setup.h b/security/landlock/setup.h
new file mode 100644
index 000000000..fca307c35
--- /dev/null
+++ b/security/landlock/setup.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Security framework setup
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_SETUP_H
+#define _SECURITY_LANDLOCK_SETUP_H
+
+#include <linux/lsm_hooks.h>
+
+extern const int landlock_abi_version;
+
+extern bool landlock_initialized;
+extern int landlock_errata;
+
+extern struct lsm_blob_sizes landlock_blob_sizes;
+extern const struct lsm_id landlock_lsmid;
+
+#endif /* _SECURITY_LANDLOCK_SETUP_H */
diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c
new file mode 100644
index 000000000..1d02d57f4
--- /dev/null
+++ b/security/landlock/syscalls.c
@@ -0,0 +1,706 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - System call implementations and user space interfaces
+ *
+ * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2018-2020 ANSSI
+ * Copyright © 2021-2025 Microsoft Corporation
+ */
+
+#include <asm/current.h>
+#include <linux/anon_inodes.h>
+#include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/capability.h>
+#include <linux/cleanup.h>
+#include <linux/compiler_types.h>
+#include <linux/dcache.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/limits.h>
+#include <linux/mount.h>
+#include <linux/path.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/security.h>
+#include <linux/stddef.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/landlock.h>
+
+#include "cred.h"
+#include "domain.h"
+#include "fs.h"
+#include "limits.h"
+#include "net.h"
+#include "ruleset.h"
+#include "setup.h"
+#include "tsync.h"
+
+#include <trace/events/landlock.h>
+
+static bool is_initialized(void)
+{
+	if (likely(landlock_initialized))
+		return true;
+
+	pr_warn_once(
+		"Disabled but requested by user space. "
+		"You should enable Landlock at boot time: "
+		"https://docs.kernel.org/userspace-api/landlock.html#boot-time-configuration\n");
+	return false;
+}
+
+/**
+ * copy_min_struct_from_user - Safe future-proof argument copying
+ *
+ * Extend copy_struct_from_user() to check for consistent user buffer.
+ *
+ * @dst: Kernel space pointer or NULL.
+ * @ksize: Actual size of the data pointed to by @dst.
+ * @ksize_min: Minimal required size to be copied.
+ * @src: User space pointer or NULL.
+ * @usize: (Alleged) size of the data pointed to by @src.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+static __always_inline int
+copy_min_struct_from_user(void *const dst, const size_t ksize,
+			  const size_t ksize_min, const void __user *const src,
+			  const size_t usize)
+{
+	/* Checks buffer inconsistencies. */
+	BUILD_BUG_ON(!dst);
+	if (!src)
+		return -EFAULT;
+
+	/* Checks size ranges. */
+	BUILD_BUG_ON(ksize <= 0);
+	BUILD_BUG_ON(ksize < ksize_min);
+	if (usize < ksize_min)
+		return -EINVAL;
+	if (usize > PAGE_SIZE)
+		return -E2BIG;
+
+	/* Copies user buffer and fills with zeros. */
+	return copy_struct_from_user(dst, ksize, src, usize);
+}
+
+/*
+ * This function only contains arithmetic operations with constants, leading to
+ * BUILD_BUG_ON().  The related code is evaluated and checked at build time,
+ * but it is then ignored thanks to compiler optimizations.
+ */
+static void build_check_abi(void)
+{
+	struct landlock_ruleset_attr ruleset_attr;
+	struct landlock_path_beneath_attr path_beneath_attr;
+	struct landlock_net_port_attr net_port_attr;
+	size_t ruleset_size, path_beneath_size, net_port_size;
+
+	/*
+	 * For each user space ABI structures, first checks that there is no
+	 * hole in them, then checks that all architectures have the same
+	 * struct size.
+	 */
+	ruleset_size = sizeof(ruleset_attr.handled_access_fs);
+	ruleset_size += sizeof(ruleset_attr.handled_access_net);
+	ruleset_size += sizeof(ruleset_attr.scoped);
+	ruleset_size += sizeof(ruleset_attr.quiet_access_fs);
+	ruleset_size += sizeof(ruleset_attr.quiet_access_net);
+	ruleset_size += sizeof(ruleset_attr.quiet_scoped);
+	BUILD_BUG_ON(sizeof(ruleset_attr) != ruleset_size);
+	BUILD_BUG_ON(sizeof(ruleset_attr) != 48);
+
+	path_beneath_size = sizeof(path_beneath_attr.allowed_access);
+	path_beneath_size += sizeof(path_beneath_attr.parent_fd);
+	BUILD_BUG_ON(sizeof(path_beneath_attr) != path_beneath_size);
+	BUILD_BUG_ON(sizeof(path_beneath_attr) != 12);
+
+	net_port_size = sizeof(net_port_attr.allowed_access);
+	net_port_size += sizeof(net_port_attr.port);
+	BUILD_BUG_ON(sizeof(net_port_attr) != net_port_size);
+	BUILD_BUG_ON(sizeof(net_port_attr) != 16);
+}
+
+/* Ruleset handling */
+
+static int fop_ruleset_release(struct inode *const inode,
+			       struct file *const filp)
+{
+	struct landlock_ruleset *ruleset = filp->private_data;
+
+	landlock_put_ruleset(ruleset);
+	return 0;
+}
+
+static ssize_t fop_dummy_read(struct file *const filp, char __user *const buf,
+			      const size_t size, loff_t *const ppos)
+{
+	/* Dummy handler to enable FMODE_CAN_READ. */
+	return -EINVAL;
+}
+
+static ssize_t fop_dummy_write(struct file *const filp,
+			       const char __user *const buf, const size_t size,
+			       loff_t *const ppos)
+{
+	/* Dummy handler to enable FMODE_CAN_WRITE. */
+	return -EINVAL;
+}
+
+/*
+ * A ruleset file descriptor enables to build a ruleset by adding (i.e.
+ * writing) rule after rule, without relying on the task's context.  This
+ * reentrant design is also used in a read way to enforce the ruleset on the
+ * current task.
+ */
+static const struct file_operations ruleset_fops = {
+	.release = fop_ruleset_release,
+	.read = fop_dummy_read,
+	.write = fop_dummy_write,
+};
+
+/*
+ * The Landlock ABI version should be incremented for each new Landlock-related
+ * user space visible change (e.g. Landlock syscalls).  This version should
+ * only be incremented once per Linux release.  When incrementing, the date in
+ * Documentation/userspace-api/landlock.rst should be updated to reflect the
+ * UAPI change.
+ * If the change involves a fix that requires userspace awareness, also update
+ * the errata documentation in Documentation/userspace-api/landlock.rst .
+ */
+const int landlock_abi_version = 11;
+
+/**
+ * sys_landlock_create_ruleset - Create a new ruleset
+ *
+ * @attr: Pointer to a &struct landlock_ruleset_attr identifying the scope of
+ *        the new ruleset.
+ * @size: Size of the pointed &struct landlock_ruleset_attr (needed for
+ *        backward and forward compatibility).
+ * @flags: Supported values:
+ *
+ *         - %LANDLOCK_CREATE_RULESET_VERSION
+ *         - %LANDLOCK_CREATE_RULESET_ERRATA
+ *
+ * This system call enables to create a new Landlock ruleset.
+ *
+ * If %LANDLOCK_CREATE_RULESET_VERSION or %LANDLOCK_CREATE_RULESET_ERRATA is
+ * set, then @attr must be NULL and @size must be 0.
+ *
+ * Return: The ruleset file descriptor on success, the Landlock ABI version if
+ * %LANDLOCK_CREATE_RULESET_VERSION is set, the errata value if
+ * %LANDLOCK_CREATE_RULESET_ERRATA is set, or -errno on failure.  Possible
+ * returned errors are:
+ *
+ * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - %EINVAL: unknown @flags, or unknown access, or unknown scope, or too small
+ *   @size;
+ * - %EINVAL: quiet_access_fs, quiet_access_net, or quiet_scoped is not a
+ *   subset of the corresponding handled_access_fs, handled_access_net, or
+ *   scoped;
+ * - %E2BIG: @attr or @size inconsistencies;
+ * - %EFAULT: @attr or @size inconsistencies;
+ * - %ENOMSG: empty &landlock_ruleset_attr.handled_access_fs.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_create_ruleset_flags
+ */
+SYSCALL_DEFINE3(landlock_create_ruleset,
+		const struct landlock_ruleset_attr __user *const, attr,
+		const size_t, size, const __u32, flags)
+{
+	struct landlock_ruleset_attr ruleset_attr;
+	struct landlock_ruleset *ruleset;
+	int err, ruleset_fd;
+
+	/* Build-time checks. */
+	build_check_abi();
+
+	if (!is_initialized())
+		return -EOPNOTSUPP;
+
+	if (flags) {
+		if (attr || size)
+			return -EINVAL;
+
+		if (flags == LANDLOCK_CREATE_RULESET_VERSION)
+			return landlock_abi_version;
+
+		if (flags == LANDLOCK_CREATE_RULESET_ERRATA)
+			return landlock_errata;
+
+		return -EINVAL;
+	}
+
+	/* Copies raw user space buffer. */
+	err = copy_min_struct_from_user(&ruleset_attr, sizeof(ruleset_attr),
+					offsetofend(typeof(ruleset_attr),
+						    handled_access_fs),
+					attr, size);
+	if (err)
+		return err;
+
+	/* Checks content (and 32-bits cast). */
+	if ((ruleset_attr.handled_access_fs | LANDLOCK_MASK_ACCESS_FS) !=
+	    LANDLOCK_MASK_ACCESS_FS)
+		return -EINVAL;
+
+	/* Checks network content (and 32-bits cast). */
+	if ((ruleset_attr.handled_access_net | LANDLOCK_MASK_ACCESS_NET) !=
+	    LANDLOCK_MASK_ACCESS_NET)
+		return -EINVAL;
+
+	/* Checks IPC scoping content (and 32-bits cast). */
+	if ((ruleset_attr.scoped | LANDLOCK_MASK_SCOPE) != LANDLOCK_MASK_SCOPE)
+		return -EINVAL;
+
+	/*
+	 * Check that quiet masks are subsets of the respective handled masks.
+	 * Because of the checks above this is sufficient to also ensure that
+	 * the quiet masks are valid access masks.
+	 */
+	if ((ruleset_attr.quiet_access_fs | ruleset_attr.handled_access_fs) !=
+	    ruleset_attr.handled_access_fs)
+		return -EINVAL;
+	if ((ruleset_attr.quiet_access_net | ruleset_attr.handled_access_net) !=
+	    ruleset_attr.handled_access_net)
+		return -EINVAL;
+	if ((ruleset_attr.quiet_scoped | ruleset_attr.scoped) !=
+	    ruleset_attr.scoped)
+		return -EINVAL;
+
+	/* Checks arguments and transforms to kernel struct. */
+	ruleset = landlock_create_ruleset(ruleset_attr.handled_access_fs,
+					  ruleset_attr.handled_access_net,
+					  ruleset_attr.scoped);
+	if (IS_ERR(ruleset))
+		return PTR_ERR(ruleset);
+
+	ruleset->quiet_masks.fs = ruleset_attr.quiet_access_fs;
+	ruleset->quiet_masks.net = ruleset_attr.quiet_access_net;
+	ruleset->quiet_masks.scope = ruleset_attr.quiet_scoped;
+
+	/*
+	 * Emits before anon_inode_getfd() installs the file descriptor, while
+	 * the ruleset is still private to this thread: no lock is needed, and
+	 * the event cannot race a concurrent close() freeing the ruleset under
+	 * the tracepoint's BTF read.  This is the last point at which the
+	 * ruleset is guaranteed alive and unshared.
+	 */
+	trace_landlock_create_ruleset(ruleset);
+
+	/* Creates anonymous FD referring to the ruleset. */
+	ruleset_fd = anon_inode_getfd("[landlock-ruleset]", &ruleset_fops,
+				      ruleset, O_RDWR | O_CLOEXEC);
+	if (ruleset_fd < 0)
+		landlock_put_ruleset(ruleset);
+	return ruleset_fd;
+}
+
+/*
+ * Returns an owned ruleset from a FD. It is thus needed to call
+ * landlock_put_ruleset() on the return value.
+ */
+static struct landlock_ruleset *get_ruleset_from_fd(const int fd,
+						    const fmode_t mode)
+{
+	CLASS(fd, ruleset_f)(fd);
+	struct landlock_ruleset *ruleset;
+
+	if (fd_empty(ruleset_f))
+		return ERR_PTR(-EBADF);
+
+	/* Checks FD type and access right. */
+	if (fd_file(ruleset_f)->f_op != &ruleset_fops)
+		return ERR_PTR(-EBADFD);
+	if (!(fd_file(ruleset_f)->f_mode & mode))
+		return ERR_PTR(-EPERM);
+	ruleset = fd_file(ruleset_f)->private_data;
+	landlock_get_ruleset(ruleset);
+	return ruleset;
+}
+
+/* Path handling */
+
+/*
+ * @path: Must call put_path(@path) after the call if it succeeded.
+ */
+static int get_path_from_fd(const s32 fd, struct path *const path)
+{
+	CLASS(fd_raw, f)(fd);
+
+	BUILD_BUG_ON(!__same_type(
+		fd, ((struct landlock_path_beneath_attr *)NULL)->parent_fd));
+
+	if (fd_empty(f))
+		return -EBADF;
+	/*
+	 * Forbids ruleset FDs, internal filesystems (e.g. nsfs), including
+	 * pseudo filesystems that will never be mountable (e.g. sockfs,
+	 * pipefs).
+	 */
+	if ((fd_file(f)->f_op == &ruleset_fops) ||
+	    (fd_file(f)->f_path.mnt->mnt_flags & MNT_INTERNAL) ||
+	    (fd_file(f)->f_path.dentry->d_sb->s_flags & SB_NOUSER) ||
+	    IS_PRIVATE(d_backing_inode(fd_file(f)->f_path.dentry)))
+		return -EBADFD;
+
+	*path = fd_file(f)->f_path;
+	path_get(path);
+	return 0;
+}
+
+static int add_rule_path_beneath(struct landlock_ruleset *const ruleset,
+				 const void __user *const rule_attr, u32 flags)
+{
+	struct landlock_path_beneath_attr path_beneath_attr;
+	struct path path;
+	int res, err;
+	access_mask_t mask;
+
+	/* Copies raw user space buffer. */
+	res = copy_from_user(&path_beneath_attr, rule_attr,
+			     sizeof(path_beneath_attr));
+	if (res)
+		return -EFAULT;
+
+	/*
+	 * Informs about useless rule: empty allowed_access (i.e. deny rules)
+	 * are ignored in path walks.  However, the rule is not useless if it is
+	 * there to hold a quiet flag.
+	 */
+	if (!flags && !path_beneath_attr.allowed_access)
+		return -ENOMSG;
+
+	/* Checks that allowed_access matches the @ruleset constraints. */
+	mask = ruleset->handled_masks.fs;
+	if ((path_beneath_attr.allowed_access | mask) != mask)
+		return -EINVAL;
+
+	/* Checks for useless quiet flag. */
+	if (flags & LANDLOCK_ADD_RULE_QUIET && !ruleset->quiet_masks.fs)
+		return -EINVAL;
+
+	/* Gets and checks the new rule. */
+	err = get_path_from_fd(path_beneath_attr.parent_fd, &path);
+	if (err)
+		return err;
+
+	/* Imports the new rule. */
+	err = landlock_append_fs_rule(ruleset, &path,
+				      path_beneath_attr.allowed_access, flags);
+	path_put(&path);
+	return err;
+}
+
+static int add_rule_net_port(struct landlock_ruleset *ruleset,
+			     const void __user *const rule_attr, u32 flags)
+{
+	struct landlock_net_port_attr net_port_attr;
+	int res;
+	access_mask_t mask;
+
+	/* Copies raw user space buffer. */
+	res = copy_from_user(&net_port_attr, rule_attr, sizeof(net_port_attr));
+	if (res)
+		return -EFAULT;
+
+	/*
+	 * Informs about useless rule: empty allowed_access (i.e. deny rules)
+	 * are ignored by network actions.  However, the rule is not useless if
+	 * it is there to hold a quiet flag.
+	 */
+	if (!flags && !net_port_attr.allowed_access)
+		return -ENOMSG;
+
+	/* Checks that allowed_access matches the @ruleset constraints. */
+	mask = ruleset->handled_masks.net;
+	if ((net_port_attr.allowed_access | mask) != mask)
+		return -EINVAL;
+
+	/* Checks for useless quiet flag. */
+	if (flags & LANDLOCK_ADD_RULE_QUIET && !ruleset->quiet_masks.net)
+		return -EINVAL;
+
+	/* Denies inserting a rule with port greater than 65535. */
+	if (net_port_attr.port > U16_MAX)
+		return -EINVAL;
+
+	/* Imports the new rule. */
+	return landlock_append_net_rule(ruleset, net_port_attr.port,
+					net_port_attr.allowed_access, flags);
+}
+
+/**
+ * sys_landlock_add_rule - Add a new rule to a ruleset
+ *
+ * @ruleset_fd: File descriptor tied to the ruleset that should be extended
+ *		with the new rule.
+ * @rule_type: Identify the structure type pointed to by @rule_attr:
+ *             %LANDLOCK_RULE_PATH_BENEATH or %LANDLOCK_RULE_NET_PORT.
+ * @rule_attr: Pointer to a rule (matching the @rule_type).
+ * @flags: Must be 0 or %LANDLOCK_ADD_RULE_QUIET.
+ *
+ * This system call enables to define a new rule and add it to an existing
+ * ruleset.
+ *
+ * Return: 0 on success, or -errno on failure.  Possible returned errors are:
+ *
+ * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - %EAFNOSUPPORT: @rule_type is %LANDLOCK_RULE_NET_PORT but TCP/IP is not
+ *   supported by the running kernel;
+ * - %EINVAL: @flags is not valid;
+ * - %EINVAL: The rule accesses are inconsistent (i.e.
+ *   &landlock_path_beneath_attr.allowed_access or
+ *   &landlock_net_port_attr.allowed_access is not a subset of the ruleset
+ *   handled accesses)
+ * - %EINVAL: &landlock_net_port_attr.port is greater than 65535;
+ * - %EINVAL: LANDLOCK_ADD_RULE_QUIET is passed but the ruleset has no
+ *   quiet access bits set for the corresponding rule type.
+ * - %ENOMSG: Empty accesses (e.g. &landlock_path_beneath_attr.allowed_access is
+ *   0) and no flags;
+ * - %EBADF: @ruleset_fd is not a file descriptor for the current thread, or a
+ *   member of @rule_attr is not a file descriptor as expected;
+ * - %EBADFD: @ruleset_fd is not a ruleset file descriptor, or a member of
+ *   @rule_attr is not the expected file descriptor type;
+ * - %EPERM: @ruleset_fd has no write access to the underlying ruleset;
+ * - %EFAULT: @rule_attr was not a valid address.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_add_rule_flags
+ */
+SYSCALL_DEFINE4(landlock_add_rule, const int, ruleset_fd,
+		const enum landlock_rule_type, rule_type,
+		const void __user *const, rule_attr, const __u32, flags)
+{
+	struct landlock_ruleset *ruleset __free(landlock_put_ruleset) = NULL;
+
+	if (!is_initialized())
+		return -EOPNOTSUPP;
+
+	if (flags && flags != LANDLOCK_ADD_RULE_QUIET)
+		return -EINVAL;
+
+	/* Gets and checks the ruleset. */
+	ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_WRITE);
+	if (IS_ERR(ruleset))
+		return PTR_ERR(ruleset);
+
+	switch (rule_type) {
+	case LANDLOCK_RULE_PATH_BENEATH:
+		return add_rule_path_beneath(ruleset, rule_attr, flags);
+	case LANDLOCK_RULE_NET_PORT:
+		return add_rule_net_port(ruleset, rule_attr, flags);
+	default:
+		return -EINVAL;
+	}
+}
+
+/* Enforcement */
+
+/**
+ * sys_landlock_restrict_self - Enforce a ruleset on the calling thread
+ *
+ * @ruleset_fd: File descriptor tied to the ruleset to merge with the target.
+ * @flags: Supported values:
+ *
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON
+ *         - %LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF
+ *         - %LANDLOCK_RESTRICT_SELF_TSYNC
+ *         - %LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS
+ *
+ * This system call enforces a Landlock ruleset on the current thread.
+ * Enforcing a ruleset requires that the task has %CAP_SYS_ADMIN in its
+ * namespace or is running with no_new_privs.  This avoids scenarios where
+ * unprivileged tasks can affect the behavior of privileged children.
+ *
+ * With %LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS, the no_new_privs attribute of the
+ * calling thread is set only once the enforcement of the ruleset succeeded,
+ * which fulfills the above requirement: no_new_privs is set if and only if the
+ * call succeeds.
+ *
+ * Return: 0 on success, or -errno on failure.  Possible returned errors are:
+ *
+ * - %EOPNOTSUPP: Landlock is supported by the kernel but disabled at boot time;
+ * - %EINVAL: @flags contains an unknown bit.
+ * - %EBADF: @ruleset_fd is not a file descriptor for the current thread;
+ * - %EBADFD: @ruleset_fd is not a ruleset file descriptor;
+ * - %EPERM: @ruleset_fd has no read access to the underlying ruleset, or
+ *   %LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS is not set while the current thread
+ *   is not running with no_new_privs and doesn't have %CAP_SYS_ADMIN in its
+ *   namespace.
+ * - %E2BIG: The maximum number of stacked rulesets is reached for the current
+ *   thread.
+ *
+ * .. kernel-doc:: include/uapi/linux/landlock.h
+ *     :identifiers: landlock_restrict_self_flags
+ */
+SYSCALL_DEFINE2(landlock_restrict_self, const int, ruleset_fd, const __u32,
+		flags)
+{
+	struct landlock_ruleset *ruleset __free(landlock_put_ruleset) = NULL;
+	struct landlock_domain *new_dom = NULL;
+	struct cred *new_cred;
+	struct landlock_cred_security *new_llcred;
+	bool process_wide;
+	bool __maybe_unused log_same_exec, log_new_exec, log_subdomains,
+		prev_log_subdomains;
+
+	if (!is_initialized())
+		return -EOPNOTSUPP;
+
+	if ((flags | LANDLOCK_MASK_RESTRICT_SELF) !=
+	    LANDLOCK_MASK_RESTRICT_SELF)
+		return -EINVAL;
+
+	/*
+	 * Similar checks as for seccomp(2), except that an -EPERM may be
+	 * returned.  LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS fulfills this
+	 * requirement.
+	 */
+	if (!(flags & LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS) &&
+	    !task_no_new_privs(current) &&
+	    !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* Translates "off" flag to boolean. */
+	log_same_exec = !(flags & LANDLOCK_RESTRICT_SELF_LOG_SAME_EXEC_OFF);
+	/* Translates "on" flag to boolean. */
+	log_new_exec = !!(flags & LANDLOCK_RESTRICT_SELF_LOG_NEW_EXEC_ON);
+	/* Translates "off" flag to boolean. */
+	log_subdomains = !(flags & LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF);
+
+	/*
+	 * It is allowed to set LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF with
+	 * -1 as ruleset_fd, optionally combined with
+	 * LANDLOCK_RESTRICT_SELF_TSYNC to propagate this configuration to all
+	 * threads.  No other flag must be set.
+	 */
+	if (!(ruleset_fd == -1 &&
+	      (flags & ~LANDLOCK_RESTRICT_SELF_TSYNC) ==
+		      LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF)) {
+		/* Gets and checks the ruleset. */
+		ruleset = get_ruleset_from_fd(ruleset_fd, FMODE_CAN_READ);
+		if (IS_ERR(ruleset))
+			return PTR_ERR(ruleset);
+	}
+
+	/* Prepares new credentials. */
+	new_cred = prepare_creds();
+	if (!new_cred)
+		return -ENOMEM;
+
+	new_llcred = landlock_cred(new_cred);
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	prev_log_subdomains = !new_llcred->log_subdomains_off;
+	new_llcred->log_subdomains_off = !prev_log_subdomains ||
+					 !log_subdomains;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	/*
+	 * The only case when a ruleset may not be set is if
+	 * LANDLOCK_RESTRICT_SELF_LOG_SUBDOMAINS_OFF is set (optionally with
+	 * LANDLOCK_RESTRICT_SELF_TSYNC) and ruleset_fd is -1.  We could
+	 * optimize this case by not calling commit_creds() if this flag was
+	 * already set, but it is not worth the complexity.
+	 */
+	if (ruleset) {
+		/*
+		 * There is no possible race condition while copying and
+		 * manipulating the current credentials because they are
+		 * dedicated per thread.
+		 */
+		mutex_lock(&ruleset->lock);
+		new_dom = landlock_merge_ruleset(new_llcred->domain, ruleset);
+		if (IS_ERR(new_dom)) {
+			mutex_unlock(&ruleset->lock);
+			abort_creds(new_cred);
+			return PTR_ERR(new_dom);
+		}
+		/*
+		 * Emits the domain-creation event while @ruleset->lock is still
+		 * held, right after the merge, so an eBPF program attached to
+		 * the tracepoint reads the exact ruleset that was merged into
+		 * the domain: a consistent snapshot that a concurrent
+		 * landlock_add_rule() (which holds the same lock) cannot
+		 * modify.
+		 *
+		 * This must come before the thread-sync wait below.  Holding
+		 * @ruleset->lock across landlock_restrict_sibling_threads()
+		 * would hang: a sibling thread blocked in landlock_add_rule()
+		 * on the same @ruleset->lock cannot run the task_work that
+		 * thread-sync waits for (the lock wait is uninterruptible).
+		 * Emitting here keeps the lock off the thread-sync path.
+		 *
+		 * The trade-off is that the event fires for a domain that a
+		 * later (rare) thread-sync failure aborts.  That path emits the
+		 * matching free_domain event so the create/free pair stays
+		 * balanced (see the thread-sync error path below).
+		 */
+		trace_landlock_create_domain(new_dom, ruleset);
+		mutex_unlock(&ruleset->lock);
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		new_dom->hierarchy->log_same_exec = log_same_exec;
+		new_dom->hierarchy->log_new_exec = log_new_exec;
+		/*
+		 * The creation event fired above, so move the domain out of
+		 * LANDLOCK_LOG_UNCOMMITTED: its free_domain event must fire
+		 * too, even if a thread-sync failure aborts it below.  Audit
+		 * logging may still be disabled (DISABLED); tracing observes it
+		 * anyway.
+		 */
+		if ((!log_same_exec && !log_new_exec) || !prev_log_subdomains)
+			new_dom->hierarchy->log_status = LANDLOCK_LOG_DISABLED;
+		else
+			new_dom->hierarchy->log_status = LANDLOCK_LOG_PENDING;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+		/* Replaces the old (prepared) domain. */
+		landlock_put_domain(new_llcred->domain);
+		new_llcred->domain = new_dom;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		new_llcred->domain_exec |= BIT(new_dom->num_layers - 1);
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	if (flags & LANDLOCK_RESTRICT_SELF_TSYNC) {
+		const int err = landlock_restrict_sibling_threads(
+			current_cred(), new_cred, flags);
+		if (err) {
+			/*
+			 * Thread-sync failed (rare), so the new domain is
+			 * aborted instead of committed.  Its creation event
+			 * already fired above, so the imminent free must emit
+			 * the matching free_domain event to keep the
+			 * create/free pair balanced; no special log_status is
+			 * set here.
+			 */
+			abort_creds(new_cred);
+			return err;
+		}
+	}
+
+	/* Sets no_new_privs past the last point of failure. */
+	if (flags & LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS)
+		task_set_no_new_privs(current);
+
+	/* Whole process: thread-sync swept siblings, or single-threaded. */
+	process_wide = (flags & LANDLOCK_RESTRICT_SELF_TSYNC) ||
+		       get_nr_threads(current) == 1;
+	commit_creds(new_cred);
+
+	/* The caller commits last, so its event concludes the operation. */
+	if (ruleset)
+		trace_landlock_enforce_domain(new_dom, true, process_wide,
+					      task_no_new_privs(current));
+
+	return 0;
+}
diff --git a/security/landlock/task.c b/security/landlock/task.c
new file mode 100644
index 000000000..4491ce31a
--- /dev/null
+++ b/security/landlock/task.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Ptrace and scope hooks
+ *
+ * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019-2020 ANSSI
+ * Copyright © 2024-2025 Microsoft Corporation
+ */
+
+#include <asm/current.h>
+#include <linux/cleanup.h>
+#include <linux/cred.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/lsm_audit.h>
+#include <linux/lsm_hooks.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <net/af_unix.h>
+#include <net/sock.h>
+
+#include "common.h"
+#include "cred.h"
+#include "domain.h"
+#include "fs.h"
+#include "log.h"
+#include "ruleset.h"
+#include "setup.h"
+#include "task.h"
+
+/**
+ * domain_scope_le - Checks domain ordering for scoped ptrace
+ *
+ * @parent: Parent domain.
+ * @child: Potential child of @parent.
+ *
+ * Checks if the @parent domain is less or equal to (i.e. an ancestor, which
+ * means a subset of) the @child domain.
+ *
+ * Return: True if @parent is an ancestor of or equal to @child, false
+ * otherwise.
+ */
+static bool domain_scope_le(const struct landlock_domain *const parent,
+			    const struct landlock_domain *const child)
+{
+	const struct landlock_hierarchy *walker;
+
+	/* Quick return for non-landlocked tasks. */
+	if (!parent)
+		return true;
+
+	if (!child)
+		return false;
+
+	for (walker = child->hierarchy; walker; walker = walker->parent) {
+		if (walker == parent->hierarchy)
+			/* @parent is in the scoped hierarchy of @child. */
+			return true;
+	}
+
+	/* There is no relationship between @parent and @child. */
+	return false;
+}
+
+static int domain_ptrace(const struct landlock_domain *const parent,
+			 const struct landlock_domain *const child)
+{
+	if (domain_scope_le(parent, child))
+		return 0;
+
+	return -EPERM;
+}
+
+/**
+ * hook_ptrace_access_check - Determines whether the current process may access
+ *			      another
+ *
+ * @child: Process to be accessed.
+ * @mode: Mode of attachment.
+ *
+ * If the current task has Landlock rules, then the child must have at least
+ * the same rules.  Else denied.
+ *
+ * Return: 0 if permission is granted, -errno if denied.
+ */
+static int hook_ptrace_access_check(struct task_struct *const child,
+				    const unsigned int mode)
+{
+	const struct landlock_cred_security *parent_subject;
+	u64 tracee_domain_id = 0;
+	int err;
+
+	/* Quick return for non-landlocked tasks. */
+	parent_subject = landlock_cred(current_cred());
+	if (!parent_subject)
+		return 0;
+
+	scoped_guard(rcu) {
+		const struct landlock_domain *const child_dom =
+			landlock_get_task_domain(child);
+		err = domain_ptrace(parent_subject->domain, child_dom);
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		if (child_dom)
+			tracee_domain_id = child_dom->hierarchy->id;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	if (!err)
+		return 0;
+
+	/*
+	 * For the ptrace_access_check case, we log the current/parent domain
+	 * and the child task.
+	 */
+	if (!(mode & PTRACE_MODE_NOAUDIT))
+		landlock_log_denial(parent_subject, &(struct landlock_request) {
+			.type = LANDLOCK_REQUEST_PTRACE,
+			.audit = {
+				.type = LSM_AUDIT_DATA_TASK,
+				.u.tsk = child,
+			},
+			.layer_plus_one = parent_subject->domain->num_layers,
+			.other_domain_id = tracee_domain_id,
+		});
+
+	return err;
+}
+
+/**
+ * hook_ptrace_traceme - Determines whether another process may trace the
+ *			 current one
+ *
+ * @parent: Task proposed to be the tracer.
+ *
+ * If the parent has Landlock rules, then the current task must have the same
+ * or more rules.  Else denied.
+ *
+ * Return: 0 if permission is granted, -errno if denied.
+ */
+static int hook_ptrace_traceme(struct task_struct *const parent)
+{
+	const struct landlock_cred_security *parent_subject;
+	const struct landlock_domain *child_dom;
+	u64 tracee_domain_id = 0;
+	int err;
+
+	child_dom = landlock_get_current_domain();
+
+	guard(rcu)();
+	parent_subject = landlock_cred(__task_cred(parent));
+	err = domain_ptrace(parent_subject->domain, child_dom);
+
+	if (!err)
+		return 0;
+
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	/* The tracee is the current task; its domain is stable here. */
+	if (child_dom)
+		tracee_domain_id = child_dom->hierarchy->id;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+
+	/*
+	 * For the ptrace_traceme case, we log the domain which is the cause of
+	 * the denial, which means the parent domain instead of the current
+	 * domain.  This may look unusual because the ptrace_traceme action is a
+	 * request to be traced, but the semantic is consistent with
+	 * hook_ptrace_access_check().
+	 */
+	landlock_log_denial(parent_subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_PTRACE,
+		.audit = {
+			.type = LSM_AUDIT_DATA_TASK,
+			.u.tsk = current,
+		},
+		.layer_plus_one = parent_subject->domain->num_layers,
+		.other_domain_id = tracee_domain_id,
+	});
+	return err;
+}
+
+/**
+ * domain_is_scoped - Check if an interaction from a client/sender to a
+ *		      server/receiver should be restricted based on scope controls.
+ *
+ * @client: IPC sender domain.
+ * @server: IPC receiver domain.
+ * @scope: The scope restriction criteria.
+ *
+ * Return: True if @server is in a different domain from @client and @client
+ * is scoped to access @server (i.e. access should be denied), false otherwise.
+ */
+static bool domain_is_scoped(const struct landlock_domain *const client,
+			     const struct landlock_domain *const server,
+			     access_mask_t scope)
+{
+	int client_layer, server_layer;
+	const struct landlock_hierarchy *client_walker, *server_walker;
+
+	/* Quick return if client has no domain */
+	if (WARN_ON_ONCE(!client))
+		return false;
+
+	client_layer = client->num_layers - 1;
+	client_walker = client->hierarchy;
+	/*
+	 * client_layer must be able to represent all numbers from
+	 * LANDLOCK_MAX_NUM_LAYERS - 1 to -1 for the loop below to terminate.
+	 * (It must be large enough, and it must be signed.)
+	 */
+	BUILD_BUG_ON(!is_signed_type(typeof(client_layer)));
+	BUILD_BUG_ON(LANDLOCK_MAX_NUM_LAYERS - 1 >
+		     type_max(typeof(client_layer)));
+
+	server_layer = server ? (server->num_layers - 1) : -1;
+	server_walker = server ? server->hierarchy : NULL;
+
+	/*
+	 * Walks client's parent domains down to the same hierarchy level
+	 * as the server's domain, and checks that none of these client's
+	 * parent domains are scoped.
+	 */
+	for (; client_layer > server_layer; client_layer--) {
+		if (landlock_get_scope_mask(client, client_layer) & scope)
+			return true;
+
+		client_walker = client_walker->parent;
+	}
+	/*
+	 * Walks server's parent domains down to the same hierarchy level as
+	 * the client's domain.
+	 */
+	for (; server_layer > client_layer; server_layer--)
+		server_walker = server_walker->parent;
+
+	for (; client_layer >= 0; client_layer--) {
+		if (landlock_get_scope_mask(client, client_layer) & scope) {
+			/*
+			 * Client and server are at the same level in the
+			 * hierarchy. If the client is scoped, the request is
+			 * only allowed if this domain is also a server's
+			 * ancestor.
+			 */
+			return server_walker != client_walker;
+		}
+		client_walker = client_walker->parent;
+		server_walker = server_walker->parent;
+	}
+	return false;
+}
+
+static bool sock_is_scoped(struct sock *const other,
+			   const struct landlock_domain *const domain,
+			   u64 *const peer_domain_id)
+{
+	const struct landlock_domain *dom_other;
+
+	/* The credentials will not change. */
+	lockdep_assert_held(&unix_sk(other)->lock);
+
+	/*
+	 * A live kernel socket (e.g. from sock_create_kern()) has no backing
+	 * file, hence no Landlock domain, so treat it as unscoped.  The
+	 * sk_socket check only guards that dereference; sk_socket is NULL
+	 * solely for a dead peer, which the caller already excludes under the
+	 * held lock, so no separate SOCK_DEAD check is needed.
+	 */
+	if (unlikely(!other->sk_socket || !other->sk_socket->file))
+		return false;
+
+	dom_other = landlock_cred(other->sk_socket->file->f_cred)->domain;
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+	*peer_domain_id = dom_other ? dom_other->hierarchy->id : 0;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	return domain_is_scoped(domain, dom_other,
+				LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET);
+}
+
+static bool is_abstract_socket(struct sock *const sock)
+{
+	struct unix_address *addr = unix_sk(sock)->addr;
+
+	if (!addr)
+		return false;
+
+	if (addr->len >= offsetof(struct sockaddr_un, sun_path) + 1 &&
+	    addr->name->sun_path[0] == '\0')
+		return true;
+
+	return false;
+}
+
+static const struct access_masks unix_scope = {
+	.scope = LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET,
+};
+
+static int hook_unix_stream_connect(struct sock *const sock,
+				    struct sock *const other,
+				    struct sock *const newsk)
+{
+	size_t handle_layer;
+	u64 peer_domain_id = 0;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), unix_scope,
+						&handle_layer);
+
+	/* Quick return for non-landlocked tasks. */
+	if (!subject)
+		return 0;
+
+	if (!is_abstract_socket(other))
+		return 0;
+
+	if (!sock_is_scoped(other, subject->domain, &peer_domain_id))
+		return 0;
+
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET,
+		.audit = {
+			.type = LSM_AUDIT_DATA_NET,
+			.u.net = &(struct lsm_network_audit) {
+				.sk = other,
+			},
+		},
+		.layer_plus_one = handle_layer + 1,
+		.other_domain_id = peer_domain_id,
+	});
+	return -EPERM;
+}
+
+static int hook_unix_may_send(struct socket *const sock,
+			      struct socket *const other)
+{
+	size_t handle_layer;
+	u64 peer_domain_id = 0;
+	const struct landlock_cred_security *const subject =
+		landlock_get_applicable_subject(current_cred(), unix_scope,
+						&handle_layer);
+
+	if (!subject)
+		return 0;
+
+	/*
+	 * Checks if this datagram socket was already allowed to be connected
+	 * to other.
+	 */
+	if (unix_peer(sock->sk) == other->sk)
+		return 0;
+
+	if (!is_abstract_socket(other->sk))
+		return 0;
+
+	if (!sock_is_scoped(other->sk, subject->domain, &peer_domain_id))
+		return 0;
+
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET,
+		.audit = {
+			.type = LSM_AUDIT_DATA_NET,
+			.u.net = &(struct lsm_network_audit) {
+				.sk = other->sk,
+			},
+		},
+		.layer_plus_one = handle_layer + 1,
+		.other_domain_id = peer_domain_id,
+	});
+	return -EPERM;
+}
+
+static const struct access_masks signal_scope = {
+	.scope = LANDLOCK_SCOPE_SIGNAL,
+};
+
+static int hook_task_kill(struct task_struct *const p,
+			  struct kernel_siginfo *const info, const int sig,
+			  const struct cred *cred)
+{
+	bool is_scoped;
+	size_t handle_layer;
+	u64 target_domain_id = 0;
+	const struct landlock_cred_security *subject;
+
+	if (!cred) {
+		/*
+		 * Always allow sending signals between threads of the same process.
+		 * This is required for process credential changes by the Native POSIX
+		 * Threads Library and implemented by the set*id(2) wrappers and
+		 * libcap(3) with tgkill(2).  See nptl(7) and libpsx(3).
+		 *
+		 * This exception is similar to the __ptrace_may_access() one.
+		 */
+		if (same_thread_group(p, current))
+			return 0;
+
+		/* Not dealing with USB IO. */
+		cred = current_cred();
+	}
+
+	subject = landlock_get_applicable_subject(cred, signal_scope,
+						  &handle_layer);
+
+	/* Quick return for non-landlocked tasks. */
+	if (!subject)
+		return 0;
+
+	scoped_guard(rcu) {
+		const struct landlock_domain *const other =
+			landlock_get_task_domain(p);
+
+		is_scoped = domain_is_scoped(subject->domain, other,
+					     signal_scope.scope);
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		if (other)
+			target_domain_id = other->hierarchy->id;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	if (!is_scoped)
+		return 0;
+
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_SCOPE_SIGNAL,
+		.audit = {
+			.type = LSM_AUDIT_DATA_TASK,
+			.u.tsk = p,
+		},
+		.layer_plus_one = handle_layer + 1,
+		.other_domain_id = target_domain_id,
+	});
+	return -EPERM;
+}
+
+static int hook_file_send_sigiotask(struct task_struct *tsk,
+				    struct fown_struct *fown, int signum)
+{
+	const struct landlock_cred_security *subject;
+	bool is_scoped = false;
+	u64 target_domain_id = 0;
+
+	/* Lock already held by send_sigio() and send_sigurg(). */
+	lockdep_assert_held(&fown->lock);
+	subject = &landlock_file(fown->file)->fown_subject;
+
+	/*
+	 * Quick return for unowned socket.
+	 *
+	 * subject->domain has already been filtered when saved by
+	 * hook_file_set_fowner(), so there is no need to call
+	 * landlock_get_applicable_subject() here.
+	 */
+	if (!subject->domain)
+		return 0;
+
+	/*
+	 * Always allow delivery to the file owner's own process, including a
+	 * thread-group leader reached through a process-group owner.  This
+	 * mirrors hook_task_kill()'s same-process exemption and preserves the
+	 * guarantee of commit 18eb75f3af40 ("landlock: Always allow signals
+	 * between threads of the same process"), which the registration-time
+	 * check cannot honor for a process-group target.
+	 */
+	if (task_tgid(tsk) == landlock_file(fown->file)->fown_tg)
+		return 0;
+
+	scoped_guard(rcu) {
+		const struct landlock_domain *const other =
+			landlock_get_task_domain(tsk);
+
+		is_scoped = domain_is_scoped(subject->domain, other,
+					     signal_scope.scope);
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		if (other)
+			target_domain_id = other->hierarchy->id;
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+	}
+
+	if (!is_scoped)
+		return 0;
+
+	landlock_log_denial(subject, &(struct landlock_request) {
+		.type = LANDLOCK_REQUEST_SCOPE_SIGNAL,
+		.audit = {
+			.type = LSM_AUDIT_DATA_TASK,
+			.u.tsk = tsk,
+		},
+#ifdef CONFIG_SECURITY_LANDLOCK_LOG
+		.layer_plus_one = landlock_file(fown->file)->fown_layer + 1,
+#endif /* CONFIG_SECURITY_LANDLOCK_LOG */
+		.other_domain_id = target_domain_id,
+	});
+	return -EPERM;
+}
+
+static struct security_hook_list landlock_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(ptrace_access_check, hook_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, hook_ptrace_traceme),
+
+	LSM_HOOK_INIT(unix_stream_connect, hook_unix_stream_connect),
+	LSM_HOOK_INIT(unix_may_send, hook_unix_may_send),
+
+	LSM_HOOK_INIT(task_kill, hook_task_kill),
+	LSM_HOOK_INIT(file_send_sigiotask, hook_file_send_sigiotask),
+};
+
+__init void landlock_add_task_hooks(void)
+{
+	security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks),
+			   &landlock_lsmid);
+}
diff --git a/security/landlock/task.h b/security/landlock/task.h
new file mode 100644
index 000000000..7c0036021
--- /dev/null
+++ b/security/landlock/task.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock LSM - Ptrace hooks
+ *
+ * Copyright © 2017-2019 Mickaël Salaün <mic@digikod.net>
+ * Copyright © 2019 ANSSI
+ */
+
+#ifndef _SECURITY_LANDLOCK_TASK_H
+#define _SECURITY_LANDLOCK_TASK_H
+
+__init void landlock_add_task_hooks(void);
+
+#endif /* _SECURITY_LANDLOCK_TASK_H */
diff --git a/security/landlock/trace.c b/security/landlock/trace.c
new file mode 100644
index 000000000..2ea7aac8d
--- /dev/null
+++ b/security/landlock/trace.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Tracepoint helpers
+ *
+ * Copyright © 2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#include <linux/cleanup.h>
+#include <linux/dcache.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/lsm_audit.h>
+#include <net/sock.h>
+
+#include "access.h"
+#include "domain.h"
+#include "fs.h"
+#include "log.h"
+#include "ruleset.h"
+#include "trace.h"
+
+/*
+ * Generates the tracepoint definitions in this translation unit.  The trace
+ * event header dereferences the traced objects in TP_fast_assign, so the full
+ * struct definitions (e.g. ruleset.h, domain.h) must be included before it.
+ */
+#define CREATE_TRACE_POINTS
+#include <trace/events/landlock.h>
+
+/**
+ * landlock_trace_free_domain - Emit a tracepoint on domain deallocation
+ *
+ * @hierarchy: The domain's hierarchy being deallocated.
+ *
+ * Fires only for a hierarchy whose creation event was emitted, i.e. one that
+ * left LANDLOCK_LOG_UNCOMMITTED in landlock_restrict_self().  This keeps the
+ * create/free pair balanced: a hierarchy that never became observable is freed
+ * silently, while a domain that landlock_restrict_self() created and a
+ * thread-sync failure then aborted still fires free_domain, because its
+ * creation event already fired.
+ *
+ * Called from landlock_log_free_domain().
+ */
+void landlock_trace_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+	/*
+	 * The log_status read is a correctness guard (keep the create/free pair
+	 * balanced), not a cost guard, so this cold path needs no
+	 * trace_..._enabled() check: the tracepoint is a static-branch no-op
+	 * when disabled.  The denial path guards trace_..._enabled() instead
+	 * because it does expensive __getname()/path work before emitting.
+	 */
+	if (READ_ONCE(hierarchy->log_status) != LANDLOCK_LOG_UNCOMMITTED)
+		trace_landlock_free_domain(hierarchy);
+}
+
+/**
+ * landlock_trace_denial - Emit a tracepoint for a denied access request
+ *
+ * @request: Detail of the user space request.
+ * @youngest_denied: The youngest hierarchy node that denied the access.
+ * @missing: The set of denied access rights.
+ * @same_exec: Whether the current task is the same executable that called
+ *             landlock_restrict_self() for the denying domain, as computed
+ *             by landlock_log_denial().
+ * @logged: Whether the domain's policy selects this denial for logging, as
+ *          computed by landlock_log_denial().
+ *
+ * Emits the tracepoint matching @request->type when its event is enabled.
+ * Unlike audit, fires regardless of @logged; the value is recorded in the event
+ * so consumers can filter on it.
+ *
+ * Called from landlock_log_denial().
+ */
+void landlock_trace_denial(
+	const struct landlock_request *const request,
+	const struct landlock_hierarchy *const youngest_denied,
+	const access_mask_t missing, const bool same_exec, const bool logged)
+{
+	switch (request->type) {
+	case LANDLOCK_REQUEST_FS_ACCESS:
+	case LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY:
+		if (trace_landlock_deny_access_fs_enabled()) {
+			char *buf __free(__putname) = __getname();
+			struct path dentry_path;
+			const char *pathname;
+			const struct path *path = NULL;
+
+			/*
+			 * Selects the path from the audit data type, as
+			 * dump_common_audit_data() does.  A FS_ACCESS denial
+			 * carries a file (hook_file_truncate) or an ioctl op
+			 * (hook_file_ioctl) rather than a path;
+			 * FS_CHANGE_TOPOLOGY carries a path or a bare dentry.
+			 * Reading the wrong union member would dereference
+			 * garbage, so every reachable type is handled here.
+			 */
+			switch (request->audit.type) {
+			case LSM_AUDIT_DATA_FILE:
+				path = &request->audit.u.file->f_path;
+				break;
+			case LSM_AUDIT_DATA_IOCTL_OP:
+				path = &request->audit.u.op->path;
+				break;
+			case LSM_AUDIT_DATA_DENTRY:
+				/*
+				 * Build a path on the stack with the real
+				 * dentry so TP_fast_assign can extract dev and
+				 * ino; the mnt field is unused there.
+				 */
+				dentry_path = (struct path){
+					.dentry = request->audit.u.dentry,
+				};
+				path = &dentry_path;
+				break;
+			case LSM_AUDIT_DATA_PATH:
+				path = &request->audit.u.path;
+				break;
+			default:
+				WARN_ONCE(1,
+					  "Unhandled Landlock FS audit type %d",
+					  request->audit.type);
+				break;
+			}
+
+			if (!path)
+				break;
+
+			if (!buf) {
+				pathname = "<no_mem>";
+			} else if (request->audit.type ==
+				   LSM_AUDIT_DATA_DENTRY) {
+				/* No vfsmount: render the dentry path alone. */
+				pathname = dentry_path_raw(
+					request->audit.u.dentry, buf, PATH_MAX);
+				if (IS_ERR(pathname))
+					pathname =
+						PTR_ERR(pathname) ==
+								-ENAMETOOLONG ?
+							"<too_long>" :
+							"<unreachable>";
+			} else {
+				pathname = resolve_path_for_trace(path, buf);
+			}
+
+			trace_landlock_deny_access_fs(youngest_denied,
+						      same_exec, logged,
+						      missing, path, pathname);
+		}
+		break;
+	case LANDLOCK_REQUEST_NET_ACCESS:
+		if (trace_landlock_deny_access_net_enabled())
+			trace_landlock_deny_access_net(
+				youngest_denied, same_exec, logged, missing,
+				request->audit.u.net->sk,
+				ntohs(request->audit.u.net->sport),
+				ntohs(request->audit.u.net->dport));
+		break;
+	case LANDLOCK_REQUEST_PTRACE:
+		if (trace_landlock_deny_ptrace_enabled())
+			trace_landlock_deny_ptrace(youngest_denied, same_exec,
+						   logged,
+						   request->other_domain_id,
+						   request->audit.u.tsk);
+		break;
+	case LANDLOCK_REQUEST_SCOPE_SIGNAL:
+		if (trace_landlock_deny_scope_signal_enabled())
+			trace_landlock_deny_scope_signal(
+				youngest_denied, same_exec, logged,
+				request->other_domain_id, request->audit.u.tsk);
+		break;
+	case LANDLOCK_REQUEST_SCOPE_ABSTRACT_UNIX_SOCKET:
+		if (trace_landlock_deny_scope_abstract_unix_socket_enabled())
+			trace_landlock_deny_scope_abstract_unix_socket(
+				youngest_denied, same_exec, logged,
+				request->other_domain_id,
+				request->audit.u.net->sk);
+		break;
+	default:
+		WARN_ONCE(1, "Unhandled Landlock request type %d",
+			  request->type);
+		break;
+	}
+}
diff --git a/security/landlock/trace.h b/security/landlock/trace.h
new file mode 100644
index 000000000..7be98e748
--- /dev/null
+++ b/security/landlock/trace.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Tracepoint helpers
+ *
+ * Copyright © 2025 Microsoft Corporation
+ * Copyright © 2026 Cloudflare, Inc.
+ */
+
+#ifndef _SECURITY_LANDLOCK_TRACE_H
+#define _SECURITY_LANDLOCK_TRACE_H
+
+#include "access.h"
+
+struct landlock_hierarchy;
+struct landlock_request;
+
+#ifdef CONFIG_TRACEPOINTS
+
+void landlock_trace_free_domain(
+	const struct landlock_hierarchy *const hierarchy);
+
+void landlock_trace_denial(
+	const struct landlock_request *const request,
+	const struct landlock_hierarchy *const youngest_denied,
+	const access_mask_t missing, const bool same_exec, const bool logged);
+
+#else /* CONFIG_TRACEPOINTS */
+
+static inline void
+landlock_trace_free_domain(const struct landlock_hierarchy *const hierarchy)
+{
+}
+
+static inline void
+landlock_trace_denial(const struct landlock_request *const request,
+		      const struct landlock_hierarchy *const youngest_denied,
+		      const access_mask_t missing, const bool same_exec,
+		      const bool logged)
+{
+}
+
+#endif /* CONFIG_TRACEPOINTS */
+
+#endif /* _SECURITY_LANDLOCK_TRACE_H */
diff --git a/security/landlock/tsync.c b/security/landlock/tsync.c
new file mode 100644
index 000000000..cfa73a2a6
--- /dev/null
+++ b/security/landlock/tsync.c
@@ -0,0 +1,639 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Landlock - Cross-thread ruleset enforcement
+ *
+ * Copyright © 2025 Google LLC
+ */
+
+#include <linux/atomic.h>
+#include <linux/cleanup.h>
+#include <linux/completion.h>
+#include <linux/cred.h>
+#include <linux/errno.h>
+#include <linux/overflow.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/task_work.h>
+#include <uapi/linux/landlock.h>
+
+#include "cred.h"
+#include "tsync.h"
+
+#include <trace/events/landlock.h>
+
+/*
+ * Shared state between multiple threads which are enforcing Landlock rulesets
+ * in lockstep with each other.
+ */
+struct tsync_shared_context {
+	/* The old and tentative new creds of the calling thread. */
+	const struct cred *old_cred;
+	const struct cred *new_cred;
+
+	/* True if sibling tasks need to set the no_new_privs flag. */
+	bool set_no_new_privs;
+
+	/* An error encountered in preparation step, or 0. */
+	atomic_t preparation_error;
+
+	/*
+	 * Barrier after preparation step in restrict_one_thread.
+	 * The calling thread waits for completion.
+	 *
+	 * Re-initialized on every round of looking for newly spawned threads.
+	 */
+	atomic_t num_preparing;
+	struct completion all_prepared;
+
+	/* Sibling threads wait for completion. */
+	struct completion ready_to_commit;
+
+	/*
+	 * Barrier after commit step (used by syscall impl to wait for
+	 * completion).
+	 */
+	atomic_t num_unfinished;
+	struct completion all_finished;
+};
+
+struct tsync_work {
+	struct callback_head work;
+	struct task_struct *task;
+	struct tsync_shared_context *shared_ctx;
+};
+
+/*
+ * restrict_one_thread - update a thread's Landlock domain in lockstep with the
+ * other threads in the same process
+ *
+ * When this is run, the same function gets run in all other threads in the same
+ * process (except for the calling thread which called landlock_restrict_self).
+ * The concurrently running invocations of restrict_one_thread coordinate
+ * through the shared ctx object to do their work in lockstep to implement
+ * all-or-nothing semantics for enforcing the new Landlock domain.
+ *
+ * Afterwards, depending on the presence of an error, all threads either commit
+ * or abort the prepared credentials.  The commit operation can not fail any
+ * more.
+ */
+static void restrict_one_thread(struct tsync_shared_context *ctx)
+{
+	const struct landlock_domain *new_dom =
+		landlock_cred(ctx->new_cred)->domain;
+	int err;
+	struct cred *cred = NULL;
+
+	if (current_cred() == ctx->old_cred) {
+		/*
+		 * Switch out old_cred with new_cred, if possible.
+		 *
+		 * In the common case, where all threads initially point to the
+		 * same struct cred, this optimization avoids creating separate
+		 * redundant credentials objects for each, which would all have
+		 * the same contents.
+		 *
+		 * Note: We are intentionally dropping the const qualifier
+		 * here, because it is required by commit_creds() and
+		 * abort_creds().
+		 */
+		cred = (struct cred *)get_cred(ctx->new_cred);
+	} else {
+		/* Else, prepare new creds and populate them. */
+		cred = prepare_creds();
+
+		if (!cred) {
+			atomic_set(&ctx->preparation_error, -ENOMEM);
+
+			/*
+			 * Even on error, we need to adhere to the protocol and
+			 * coordinate with concurrently running invocations.
+			 */
+			if (atomic_dec_return(&ctx->num_preparing) == 0)
+				complete_all(&ctx->all_prepared);
+
+			goto out;
+		}
+
+		landlock_cred_copy(landlock_cred(cred),
+				   landlock_cred(ctx->new_cred));
+	}
+
+	/*
+	 * Barrier: Wait until all threads are done preparing.
+	 * After this point, we can have no more failures.
+	 */
+	if (atomic_dec_return(&ctx->num_preparing) == 0)
+		complete_all(&ctx->all_prepared);
+
+	/*
+	 * Wait for signal from calling thread that it's safe to read the
+	 * preparation error now and we are ready to commit (or abort).
+	 */
+	wait_for_completion(&ctx->ready_to_commit);
+
+	/* Abort the commit if any of the other threads had an error. */
+	err = atomic_read(&ctx->preparation_error);
+	if (err) {
+		abort_creds(cred);
+		goto out;
+	}
+
+	/*
+	 * Make sure that all sibling tasks fulfill the no_new_privs
+	 * prerequisite.  (This is in line with Seccomp's
+	 * SECCOMP_FILTER_FLAG_TSYNC logic in kernel/seccomp.c)
+	 */
+	if (ctx->set_no_new_privs)
+		task_set_no_new_privs(current);
+
+	commit_creds(cred);
+
+	/*
+	 * Emitted strictly after commit_creds() and before the out: label, so
+	 * it fires only for a thread now enforcing new_dom, and every
+	 * non-concluding (complete == false) event happens-before the
+	 * operation's single concluding one.  Skipped on the flags-only path,
+	 * where old_cred and new_cred carry the same domain.  A sibling never
+	 * concludes the operation and its enforcement is always process-wide.
+	 */
+	if (new_dom != landlock_cred(ctx->old_cred)->domain)
+		trace_landlock_enforce_domain(new_dom, false, true,
+					      task_no_new_privs(current));
+
+out:
+	/* Notify the calling thread once all threads are done */
+	if (atomic_dec_return(&ctx->num_unfinished) == 0)
+		complete_all(&ctx->all_finished);
+}
+
+/*
+ * restrict_one_thread_callback - task_work callback for restricting a thread
+ *
+ * Calls restrict_one_thread with the struct landlock_shared_tsync_context.
+ */
+static void restrict_one_thread_callback(struct callback_head *work)
+{
+	struct tsync_work *ctx = container_of(work, struct tsync_work, work);
+
+	restrict_one_thread(ctx->shared_ctx);
+}
+
+/*
+ * struct tsync_works - a growable array of per-task contexts
+ *
+ * The zero-initialized struct represents the empty array.
+ */
+struct tsync_works {
+	struct tsync_work **works;
+	size_t size;
+	size_t capacity;
+};
+
+/*
+ * tsync_works_provide - provides a preallocated tsync_work for the given task
+ *
+ * This also stores a task pointer in the context and increments the reference
+ * count of the task.
+ *
+ * This function may fail in the case where we did not preallocate sufficient
+ * capacity.  This can legitimately happen if new threads get started after we
+ * grew the capacity.
+ *
+ * Return: A pointer to the preallocated context struct with task filled in, or
+ * NULL if preallocated context structs ran out.
+ */
+static struct tsync_work *tsync_works_provide(struct tsync_works *s,
+					      struct task_struct *task)
+{
+	struct tsync_work *ctx;
+
+	if (s->size >= s->capacity)
+		return NULL;
+
+	ctx = s->works[s->size];
+	s->size++;
+
+	ctx->task = get_task_struct(task);
+	return ctx;
+}
+
+/**
+ * tsync_works_trim - Put the last tsync_work element
+ *
+ * @s: TSYNC works to trim.
+ *
+ * Put the last task and decrement the size of @s.
+ *
+ * This helper does not cancel a running task, but just reset the last element
+ * to zero.
+ */
+static void tsync_works_trim(struct tsync_works *s)
+{
+	struct tsync_work *ctx;
+
+	if (WARN_ON_ONCE(s->size <= 0))
+		return;
+
+	ctx = s->works[s->size - 1];
+
+	/*
+	 * For consistency, remove the task from ctx so that it does not look
+	 * like we handed it a task_work.
+	 */
+	put_task_struct(ctx->task);
+	*ctx = (typeof(*ctx)){};
+
+	/*
+	 * Cancel the tsync_works_provide() change to recycle the reserved
+	 * memory for the next thread, if any.  This also ensures that
+	 * cancel_tsync_works() and tsync_works_release() do not see any NULL
+	 * task pointers.
+	 */
+	s->size--;
+}
+
+/*
+ * tsync_works_grow_by - preallocates space for n more contexts in s
+ *
+ * On a successful return, the subsequent n calls to tsync_works_provide() are
+ * guaranteed to succeed.  (size + n <= capacity)
+ *
+ * Return: 0 if sufficient space for n more elements could be provided, -ENOMEM
+ * on allocation errors, -EOVERFLOW in case of integer overflow.
+ */
+static int tsync_works_grow_by(struct tsync_works *s, size_t n, gfp_t flags)
+{
+	size_t i;
+	size_t new_capacity;
+	struct tsync_work **works;
+	struct tsync_work *work;
+
+	if (check_add_overflow(s->size, n, &new_capacity))
+		return -EOVERFLOW;
+
+	/* No need to reallocate if s already has sufficient capacity. */
+	if (new_capacity <= s->capacity)
+		return 0;
+
+	works = krealloc_array(s->works, new_capacity, sizeof(s->works[0]),
+			       flags);
+	if (!works)
+		return -ENOMEM;
+
+	s->works = works;
+
+	for (i = s->capacity; i < new_capacity; i++) {
+		work = kzalloc_obj(*work, flags);
+		if (!work) {
+			/*
+			 * Leave the object in a consistent state,
+			 * but return an error.
+			 */
+			s->capacity = i;
+			return -ENOMEM;
+		}
+		s->works[i] = work;
+	}
+	s->capacity = new_capacity;
+	return 0;
+}
+
+/*
+ * tsync_works_contains - checks for presence of task in s
+ */
+static bool tsync_works_contains_task(const struct tsync_works *s,
+				      const struct task_struct *task)
+{
+	size_t i;
+
+	for (i = 0; i < s->size; i++)
+		if (s->works[i]->task == task)
+			return true;
+
+	return false;
+}
+
+/*
+ * tsync_works_release - frees memory held by s and drops all task references
+ *
+ * This does not free s itself, only the data structures held by it.
+ */
+static void tsync_works_release(struct tsync_works *s)
+{
+	size_t i;
+
+	for (i = 0; i < s->size; i++) {
+		if (WARN_ON_ONCE(!s->works[i]->task))
+			continue;
+
+		put_task_struct(s->works[i]->task);
+	}
+
+	for (i = 0; i < s->capacity; i++)
+		kfree(s->works[i]);
+
+	kfree(s->works);
+	s->works = NULL;
+	s->size = 0;
+	s->capacity = 0;
+}
+
+/*
+ * count_additional_threads - counts the sibling threads that are not in works
+ */
+static size_t count_additional_threads(const struct tsync_works *works)
+{
+	const struct task_struct *caller, *thread;
+	size_t n = 0;
+
+	caller = current;
+
+	guard(rcu)();
+
+	for_each_thread(caller, thread) {
+		/* Skip current, since it is initiating the sync. */
+		if (thread == caller)
+			continue;
+
+		/* Skip exited threads. */
+		if (thread->flags & PF_EXITING)
+			continue;
+
+		/* Skip threads that we have already seen. */
+		if (tsync_works_contains_task(works, thread))
+			continue;
+
+		n++;
+	}
+	return n;
+}
+
+/*
+ * schedule_task_work - adds task_work for all eligible sibling threads
+ *                      which have not been scheduled yet
+ *
+ * For each added task_work, atomically increments shared_ctx->num_preparing and
+ * shared_ctx->num_unfinished.
+ *
+ * Return: True if at least one eligible sibling thread was found, false
+ * otherwise.
+ */
+static bool schedule_task_work(struct tsync_works *works,
+			       struct tsync_shared_context *shared_ctx)
+{
+	int err;
+	const struct task_struct *caller;
+	struct task_struct *thread;
+	struct tsync_work *ctx;
+	bool found_more_threads = false;
+
+	caller = current;
+
+	guard(rcu)();
+
+	for_each_thread(caller, thread) {
+		/* Skip current, since it is initiating the sync. */
+		if (thread == caller)
+			continue;
+
+		/* Skip exited threads. */
+		if (thread->flags & PF_EXITING)
+			continue;
+
+		/* Skip threads that we already looked at. */
+		if (tsync_works_contains_task(works, thread))
+			continue;
+
+		/*
+		 * We found a sibling thread that is not doing its task_work
+		 * yet, and which might spawn new threads before our task work
+		 * runs, so we need at least one more round in the outer loop.
+		 */
+		found_more_threads = true;
+
+		ctx = tsync_works_provide(works, thread);
+		if (!ctx) {
+			/*
+			 * We ran out of preallocated contexts -- we need to
+			 * try again with this thread at a later time!
+			 * found_more_threads is already true at this point.
+			 */
+			break;
+		}
+
+		ctx->shared_ctx = shared_ctx;
+
+		atomic_inc(&shared_ctx->num_preparing);
+		atomic_inc(&shared_ctx->num_unfinished);
+
+		init_task_work(&ctx->work, restrict_one_thread_callback);
+		err = task_work_add(thread, &ctx->work, TWA_SIGNAL);
+		if (unlikely(err)) {
+			/*
+			 * task_work_add() only fails if the task is about to
+			 * exit.  We checked that earlier, but it can happen as
+			 * a race.  Resume without setting an error, as the
+			 * task is probably gone in the next loop iteration.
+			 */
+			tsync_works_trim(works);
+
+			atomic_dec(&shared_ctx->num_preparing);
+			atomic_dec(&shared_ctx->num_unfinished);
+		}
+	}
+
+	return found_more_threads;
+}
+
+/*
+ * cancel_tsync_works - cancel all task works where it is possible
+ *
+ * Task works can be canceled as long as they are still queued and have not
+ * started running.  If they get canceled, we decrement
+ * shared_ctx->num_preparing and shared_ctx->num_unfished and mark the two
+ * completions if needed, as if the task was never scheduled.
+ */
+static void cancel_tsync_works(const struct tsync_works *works,
+			       struct tsync_shared_context *shared_ctx)
+{
+	size_t i;
+
+	for (i = 0; i < works->size; i++) {
+		if (WARN_ON_ONCE(!works->works[i]->task))
+			continue;
+
+		if (!task_work_cancel(works->works[i]->task,
+				      &works->works[i]->work))
+			continue;
+
+		/* After dequeueing, act as if the task work had executed. */
+
+		if (atomic_dec_return(&shared_ctx->num_preparing) == 0)
+			complete_all(&shared_ctx->all_prepared);
+
+		if (atomic_dec_return(&shared_ctx->num_unfinished) == 0)
+			complete_all(&shared_ctx->all_finished);
+	}
+}
+
+/*
+ * restrict_sibling_threads - enables a Landlock policy for all sibling threads
+ */
+int landlock_restrict_sibling_threads(const struct cred *old_cred,
+				      const struct cred *new_cred,
+				      const u32 restrict_flags)
+{
+	int err;
+	struct tsync_shared_context shared_ctx;
+	struct tsync_works works = {};
+	size_t newly_discovered_threads;
+	bool found_more_threads;
+
+	atomic_set(&shared_ctx.preparation_error, 0);
+	init_completion(&shared_ctx.all_prepared);
+	init_completion(&shared_ctx.ready_to_commit);
+	atomic_set(&shared_ctx.num_unfinished, 1);
+	init_completion(&shared_ctx.all_finished);
+	shared_ctx.old_cred = old_cred;
+	shared_ctx.new_cred = new_cred;
+	shared_ctx.set_no_new_privs =
+		(restrict_flags & LANDLOCK_RESTRICT_SELF_NO_NEW_PRIVS) ||
+		task_no_new_privs(current);
+
+	/*
+	 * Serialize concurrent TSYNC operations to prevent deadlocks when
+	 * multiple threads call landlock_restrict_self() simultaneously.
+	 * If the lock is already held, we gracefully yield by restarting the
+	 * syscall. This allows the current thread to process pending
+	 * task_works before retrying.
+	 */
+	if (!down_write_trylock(&current->signal->exec_update_lock))
+		return restart_syscall();
+
+	/*
+	 * We schedule a pseudo-signal task_work for each of the calling task's
+	 * sibling threads.  In the task work, each thread:
+	 *
+	 * 1) runs prepare_creds() and writes back the error to
+	 *    shared_ctx.preparation_error, if needed.
+	 *
+	 * 2) signals that it's done with prepare_creds() to the calling task.
+	 *    (completion "all_prepared").
+	 *
+	 * 3) waits for the completion "ready_to_commit".  This is sent by the
+	 *    calling task after ensuring that all sibling threads have done
+	 *    with the "preparation" stage.
+	 *
+	 *    After this barrier is reached, it's safe to read
+	 *    shared_ctx.preparation_error.
+	 *
+	 * 4) reads shared_ctx.preparation_error and then either does
+	 *    commit_creds() or abort_creds().
+	 *
+	 * 5) signals that it's done altogether (barrier synchronization
+	 *    "all_finished")
+	 *
+	 * Unlike seccomp, which modifies sibling tasks directly, we do not
+	 * need to acquire the cred_guard_mutex and sighand->siglock:
+	 *
+	 * - As in our case, all threads are themselves exchanging their own
+	 *   struct cred through the credentials API, no locks are needed for
+	 *   that.
+	 * - Our for_each_thread() loops are protected by RCU.
+	 * - We do not acquire a lock to keep the list of sibling threads
+	 *   stable between our for_each_thread loops.  If the list of
+	 *   available sibling threads changes between these for_each_thread
+	 *   loops, we make up for that by continuing to look for threads until
+	 *   they are all discovered and have entered their task_work, where
+	 *   they are unable to spawn new threads.
+	 */
+	do {
+		/* In RCU read-lock, count the threads we need. */
+		newly_discovered_threads = count_additional_threads(&works);
+
+		if (newly_discovered_threads == 0)
+			break; /* done */
+
+		err = tsync_works_grow_by(&works, newly_discovered_threads,
+					  GFP_KERNEL_ACCOUNT);
+		if (err) {
+			atomic_set(&shared_ctx.preparation_error, err);
+			break;
+		}
+
+		/*
+		 * The "all_prepared" barrier is used locally to the loop body,
+		 * this use of for_each_thread().  We can reset it on each loop
+		 * iteration because all previous loop iterations are done with
+		 * it already.
+		 *
+		 * num_preparing is initialized to 1 so that the counter can
+		 * not go to 0 and mark the completion as done before all task
+		 * works are registered.  We decrement it at the end of the
+		 * loop body.
+		 */
+		atomic_set(&shared_ctx.num_preparing, 1);
+		reinit_completion(&shared_ctx.all_prepared);
+
+		/*
+		 * In RCU read-lock, schedule task work on newly discovered
+		 * sibling tasks.
+		 */
+		found_more_threads = schedule_task_work(&works, &shared_ctx);
+
+		/*
+		 * Decrement num_preparing for current, to undo that we
+		 * initialized it to 1 a few lines above.
+		 */
+		if (atomic_dec_return(&shared_ctx.num_preparing) > 0) {
+			if (wait_for_completion_interruptible(
+				    &shared_ctx.all_prepared)) {
+				/*
+				 * In case of interruption, we need to retry
+				 * the system call.
+				 */
+				atomic_set(&shared_ctx.preparation_error,
+					   -ERESTARTNOINTR);
+
+				/*
+				 * Opportunistic improvement: try to cancel task
+				 * works for tasks that did not start running
+				 * yet. We do not have a guarantee that it
+				 * cancels any of the enqueued task works
+				 * because task_work_run() might already have
+				 * dequeued them.
+				 */
+				cancel_tsync_works(&works, &shared_ctx);
+
+				/*
+				 * Break the loop with error. The cleanup code
+				 * after the loop unblocks the remaining
+				 * task_works.
+				 */
+				break;
+			}
+		}
+	} while (found_more_threads &&
+		 !atomic_read(&shared_ctx.preparation_error));
+
+	/*
+	 * We now have either (a) all sibling threads blocking and in "prepared"
+	 * state in the task work, or (b) the preparation error is set. Ask all
+	 * threads to commit (or abort).
+	 */
+	complete_all(&shared_ctx.ready_to_commit);
+
+	/*
+	 * Decrement num_unfinished for current, to undo that we initialized it
+	 * to 1 at the beginning.
+	 */
+	if (atomic_dec_return(&shared_ctx.num_unfinished) > 0)
+		wait_for_completion(&shared_ctx.all_finished);
+
+	tsync_works_release(&works);
+	up_write(&current->signal->exec_update_lock);
+	return atomic_read(&shared_ctx.preparation_error);
+}
diff --git a/security/landlock/tsync.h b/security/landlock/tsync.h
new file mode 100644
index 000000000..2ae4f938c
--- /dev/null
+++ b/security/landlock/tsync.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Landlock - Cross-thread ruleset enforcement
+ *
+ * Copyright © 2025 Google LLC
+ */
+
+#ifndef _SECURITY_LANDLOCK_TSYNC_H
+#define _SECURITY_LANDLOCK_TSYNC_H
+
+#include <linux/cred.h>
+#include <linux/types.h>
+
+int landlock_restrict_sibling_threads(const struct cred *old_cred,
+				      const struct cred *new_cred,
+				      u32 restrict_flags);
+
+#endif /* _SECURITY_LANDLOCK_TSYNC_H */
diff --git a/security/loadpin/Kconfig b/security/loadpin/Kconfig
new file mode 100644
index 000000000..aef63d3e3
--- /dev/null
+++ b/security/loadpin/Kconfig
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_LOADPIN
+	bool "Pin load of kernel files (modules, fw, etc) to one filesystem"
+	depends on SECURITY && BLOCK
+	help
+	  Any files read through the kernel file reading interface
+	  (kernel modules, firmware, kexec images, security policy)
+	  can be pinned to the first filesystem used for loading. When
+	  enabled, any files that come from other filesystems will be
+	  rejected. This is best used on systems without an initrd that
+	  have a root filesystem backed by a read-only device such as
+	  dm-verity or a CDROM.
+
+config SECURITY_LOADPIN_ENFORCE
+	bool "Enforce LoadPin at boot"
+	depends on SECURITY_LOADPIN
+	# Module compression breaks LoadPin unless modules are decompressed in
+	# the kernel.
+	depends on !MODULE_COMPRESS || MODULE_DECOMPRESS
+	help
+	  If selected, LoadPin will enforce pinning at boot. If not
+	  selected, it can be enabled at boot with the kernel parameter
+	  "loadpin.enforce=1".
+
+config SECURITY_LOADPIN_VERITY
+	bool "Allow reading files from certain other filesystems that use dm-verity"
+	depends on SECURITY_LOADPIN && DM_VERITY=y && SECURITYFS
+	help
+	  If selected LoadPin can allow reading files from filesystems
+	  that use dm-verity. LoadPin maintains a list of verity root
+	  digests it considers trusted. A verity backed filesystem is
+	  considered trusted if its root digest is found in the list
+	  of trusted digests.
+
+	  The list of trusted verity can be populated through an ioctl
+	  on the LoadPin securityfs entry 'dm-verity'. The ioctl
+	  expects a file descriptor of a file with verity digests as
+	  parameter. The file must be located on the pinned root and
+	  start with the line:
+
+	  # LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS
+
+	  This is followed by the verity digests, with one digest per
+	  line.
diff --git a/security/loadpin/Makefile b/security/loadpin/Makefile
new file mode 100644
index 000000000..0ead1c310
--- /dev/null
+++ b/security/loadpin/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SECURITY_LOADPIN) += loadpin.o
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
new file mode 100644
index 000000000..f71861f98
--- /dev/null
+++ b/security/loadpin/loadpin.c
@@ -0,0 +1,442 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Module and Firmware Pinning Security Module
+ *
+ * Copyright 2011-2016 Google Inc.
+ *
+ * Author: Kees Cook <keescook@chromium.org>
+ */
+
+#define pr_fmt(fmt) "LoadPin: " fmt
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/hex.h>
+#include <linux/kernel_read_file.h>
+#include <linux/lsm_hooks.h>
+#include <linux/mount.h>
+#include <linux/blkdev.h>
+#include <linux/path.h>
+#include <linux/sched.h>	/* current */
+#include <linux/string_helpers.h>
+#include <linux/dm-verity-loadpin.h>
+#include <uapi/linux/loadpin.h>
+#include <uapi/linux/lsm.h>
+
+#define VERITY_DIGEST_FILE_HEADER "# LOADPIN_TRUSTED_VERITY_ROOT_DIGESTS"
+
+static void report_load(const char *origin, struct file *file, char *operation)
+{
+	char *cmdline, *pathname;
+
+	pathname = kstrdup_quotable_file(file, GFP_KERNEL);
+	cmdline = kstrdup_quotable_cmdline(current, GFP_KERNEL);
+
+	pr_notice("%s %s obj=%s%s%s pid=%d cmdline=%s%s%s\n",
+		  origin, operation,
+		  (pathname && pathname[0] != '<') ? "\"" : "",
+		  pathname,
+		  (pathname && pathname[0] != '<') ? "\"" : "",
+		  task_pid_nr(current),
+		  cmdline ? "\"" : "", cmdline, cmdline ? "\"" : "");
+
+	kfree(cmdline);
+	kfree(pathname);
+}
+
+static int enforce = IS_ENABLED(CONFIG_SECURITY_LOADPIN_ENFORCE);
+static char *exclude_read_files[READING_MAX_ID];
+static int ignore_read_file_id[READING_MAX_ID] __ro_after_init;
+static struct super_block *pinned_root;
+static DEFINE_SPINLOCK(pinned_root_spinlock);
+#ifdef CONFIG_SECURITY_LOADPIN_VERITY
+static bool deny_reading_verity_digests;
+#endif
+
+// initialized to false
+static bool loadpin_root_writable;
+#ifdef CONFIG_SYSCTL
+
+static int proc_handler_loadpin(const struct ctl_table *table, int dir,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	if (!loadpin_root_writable && SYSCTL_USER_TO_KERN(dir))
+		return -EINVAL;
+	return proc_dointvec_minmax(table, dir, buffer, lenp, ppos);
+}
+
+static const struct ctl_table loadpin_sysctl_table[] = {
+	{
+		.procname       = "enforce",
+		.data           = &enforce,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_handler_loadpin,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+};
+#endif
+
+static void report_writable(struct super_block *mnt_sb, bool writable)
+{
+	if (mnt_sb->s_bdev) {
+		pr_info("%pg (%u:%u): %s\n", mnt_sb->s_bdev,
+			MAJOR(mnt_sb->s_bdev->bd_dev),
+			MINOR(mnt_sb->s_bdev->bd_dev),
+			writable ? "writable" : "read-only");
+	} else
+		pr_info("mnt_sb lacks block device, treating as: writable\n");
+
+	if (!writable)
+		pr_info("load pinning engaged.\n");
+}
+
+/*
+ * This must be called after early kernel init, since then the rootdev
+ * is available.
+ */
+static bool sb_is_writable(struct super_block *mnt_sb)
+{
+	bool writable = true;
+
+	if (mnt_sb->s_bdev)
+		writable = !bdev_read_only(mnt_sb->s_bdev);
+
+	return writable;
+}
+
+static void loadpin_sb_free_security(struct super_block *mnt_sb)
+{
+	/*
+	 * When unmounting the filesystem we were using for load
+	 * pinning, we acknowledge the superblock release, but make sure
+	 * no other modules or firmware can be loaded when we are in
+	 * enforcing mode. Otherwise, allow the root to be reestablished.
+	 */
+	if (!IS_ERR_OR_NULL(pinned_root) && mnt_sb == pinned_root) {
+		if (enforce) {
+			pinned_root = ERR_PTR(-EIO);
+			pr_info("umount pinned fs: refusing further loads\n");
+		} else {
+			pinned_root = NULL;
+		}
+	}
+}
+
+static int loadpin_check(struct file *file, enum kernel_read_file_id id)
+{
+	struct super_block *load_root;
+	const char *origin = kernel_read_file_id_str(id);
+	bool first_root_pin = false;
+
+	/* If the file id is excluded, ignore the pinning. */
+	if ((unsigned int)id < ARRAY_SIZE(ignore_read_file_id) &&
+	    ignore_read_file_id[id]) {
+		report_load(origin, file, "pinning-excluded");
+		return 0;
+	}
+
+	/* This handles the older init_module API that has a NULL file. */
+	if (!file) {
+		if (!enforce) {
+			report_load(origin, NULL, "old-api-pinning-ignored");
+			return 0;
+		}
+
+		report_load(origin, NULL, "old-api-denied");
+		return -EPERM;
+	}
+
+	load_root = file->f_path.mnt->mnt_sb;
+
+	/* First loaded module/firmware defines the root for all others. */
+	spin_lock(&pinned_root_spinlock);
+	/*
+	 * pinned_root is only NULL at startup or when the pinned root has
+	 * been unmounted while we are not in enforcing mode. Otherwise, it
+	 * is either a valid reference, or an ERR_PTR.
+	 */
+	if (!pinned_root) {
+		pinned_root = load_root;
+		first_root_pin = true;
+	}
+	spin_unlock(&pinned_root_spinlock);
+
+	if (first_root_pin) {
+		loadpin_root_writable = sb_is_writable(pinned_root);
+		report_writable(pinned_root, loadpin_root_writable);
+		report_load(origin, file, "pinned");
+	}
+
+	if (IS_ERR_OR_NULL(pinned_root) ||
+	    ((load_root != pinned_root) && !dm_verity_loadpin_is_bdev_trusted(load_root->s_bdev))) {
+		if (unlikely(!enforce)) {
+			report_load(origin, file, "pinning-ignored");
+			return 0;
+		}
+
+		report_load(origin, file, "denied");
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+static int loadpin_read_file(struct file *file, enum kernel_read_file_id id,
+			     bool contents)
+{
+	/*
+	 * LoadPin only cares about the _origin_ of a file, not its
+	 * contents, so we can ignore the "are full contents available"
+	 * argument here.
+	 */
+	return loadpin_check(file, id);
+}
+
+static int loadpin_load_data(enum kernel_load_data_id id, bool contents)
+{
+	/*
+	 * LoadPin only cares about the _origin_ of a file, not its
+	 * contents, so a NULL file is passed, and we can ignore the
+	 * state of "contents".
+	 */
+	return loadpin_check(NULL, (enum kernel_read_file_id) id);
+}
+
+static const struct lsm_id loadpin_lsmid = {
+	.name = "loadpin",
+	.id = LSM_ID_LOADPIN,
+};
+
+static struct security_hook_list loadpin_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(sb_free_security, loadpin_sb_free_security),
+	LSM_HOOK_INIT(kernel_read_file, loadpin_read_file),
+	LSM_HOOK_INIT(kernel_load_data, loadpin_load_data),
+};
+
+static void __init parse_exclude(void)
+{
+	int i, j;
+	char *cur;
+
+	/*
+	 * Make sure all the arrays stay within expected sizes. This
+	 * is slightly weird because kernel_read_file_str[] includes
+	 * READING_MAX_ID, which isn't actually meaningful here.
+	 */
+	BUILD_BUG_ON(ARRAY_SIZE(exclude_read_files) !=
+		     ARRAY_SIZE(ignore_read_file_id));
+	BUILD_BUG_ON(ARRAY_SIZE(kernel_read_file_str) <
+		     ARRAY_SIZE(ignore_read_file_id));
+
+	for (i = 0; i < ARRAY_SIZE(exclude_read_files); i++) {
+		cur = exclude_read_files[i];
+		if (!cur)
+			break;
+		if (*cur == '\0')
+			continue;
+
+		for (j = 0; j < ARRAY_SIZE(ignore_read_file_id); j++) {
+			if (strcmp(cur, kernel_read_file_str[j]) == 0) {
+				pr_info("excluding: %s\n",
+					kernel_read_file_str[j]);
+				ignore_read_file_id[j] = 1;
+				/*
+				 * Can not break, because one read_file_str
+				 * may map to more than on read_file_id.
+				 */
+			}
+		}
+	}
+}
+
+static int __init loadpin_init(void)
+{
+	pr_info("ready to pin (currently %senforcing)\n",
+		enforce ? "" : "not ");
+	parse_exclude();
+#ifdef CONFIG_SYSCTL
+	if (!register_sysctl("kernel/loadpin", loadpin_sysctl_table))
+		pr_notice("sysctl registration failed!\n");
+#endif
+	security_add_hooks(loadpin_hooks, ARRAY_SIZE(loadpin_hooks),
+			   &loadpin_lsmid);
+
+	return 0;
+}
+
+#ifdef CONFIG_SECURITY_LOADPIN_VERITY
+
+enum loadpin_securityfs_interface_index {
+	LOADPIN_DM_VERITY,
+};
+
+static int read_trusted_verity_root_digests(unsigned int fd)
+{
+	void *data;
+	int rc;
+	char *p, *d;
+
+	if (deny_reading_verity_digests)
+		return -EPERM;
+
+	/* The list of trusted root digests can only be set up once */
+	if (!list_empty(&dm_verity_loadpin_trusted_root_digests))
+		return -EPERM;
+
+	CLASS(fd, f)(fd);
+	if (fd_empty(f))
+		return -EINVAL;
+
+	data = kzalloc(SZ_4K, GFP_KERNEL);
+	if (!data) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	rc = kernel_read_file(fd_file(f), 0, (void **)&data, SZ_4K - 1, NULL, READING_POLICY);
+	if (rc < 0)
+		goto err;
+
+	p = data;
+	p[rc] = '\0';
+	p = strim(p);
+
+	p = strim(data);
+	while ((d = strsep(&p, "\n")) != NULL) {
+		int len;
+		struct dm_verity_loadpin_trusted_root_digest *trd;
+
+		if (d == data) {
+			/* first line, validate header */
+			if (strcmp(d, VERITY_DIGEST_FILE_HEADER)) {
+				rc = -EPROTO;
+				goto err;
+			}
+
+			continue;
+		}
+
+		len = strlen(d);
+
+		if (len % 2) {
+			rc = -EPROTO;
+			goto err;
+		}
+
+		len /= 2;
+
+		trd = kzalloc_flex(*trd, data, len);
+		if (!trd) {
+			rc = -ENOMEM;
+			goto err;
+		}
+		trd->len = len;
+
+		if (hex2bin(trd->data, d, len)) {
+			kfree(trd);
+			rc = -EPROTO;
+			goto err;
+		}
+
+		list_add_tail(&trd->node, &dm_verity_loadpin_trusted_root_digests);
+	}
+
+	if (list_empty(&dm_verity_loadpin_trusted_root_digests)) {
+		rc = -EPROTO;
+		goto err;
+	}
+
+	kfree(data);
+
+	return 0;
+
+err:
+	kfree(data);
+
+	/* any failure in loading/parsing invalidates the entire list */
+	{
+		struct dm_verity_loadpin_trusted_root_digest *trd, *tmp;
+
+		list_for_each_entry_safe(trd, tmp, &dm_verity_loadpin_trusted_root_digests, node) {
+			list_del(&trd->node);
+			kfree(trd);
+		}
+	}
+
+	/* disallow further attempts after reading a corrupt/invalid file */
+	deny_reading_verity_digests = true;
+
+	return rc;
+}
+
+/******************************** securityfs ********************************/
+
+static long dm_verity_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	void __user *uarg = (void __user *)arg;
+	unsigned int fd;
+
+	switch (cmd) {
+	case LOADPIN_IOC_SET_TRUSTED_VERITY_DIGESTS:
+		if (copy_from_user(&fd, uarg, sizeof(fd)))
+			return -EFAULT;
+
+		return read_trusted_verity_root_digests(fd);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct file_operations loadpin_dm_verity_ops = {
+	.unlocked_ioctl = dm_verity_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+};
+
+/**
+ * init_loadpin_securityfs - create the securityfs directory for LoadPin
+ *
+ * We can not put this method normally under the loadpin_init() code path since
+ * the security subsystem gets initialized before the vfs caches.
+ *
+ * Returns 0 if the securityfs directory creation was successful.
+ */
+static int __init init_loadpin_securityfs(void)
+{
+	struct dentry *loadpin_dir, *dentry;
+
+	loadpin_dir = securityfs_create_dir("loadpin", NULL);
+	if (IS_ERR(loadpin_dir)) {
+		pr_err("LoadPin: could not create securityfs dir: %ld\n",
+		       PTR_ERR(loadpin_dir));
+		return PTR_ERR(loadpin_dir);
+	}
+
+	dentry = securityfs_create_file("dm-verity", 0600, loadpin_dir,
+					(void *)LOADPIN_DM_VERITY, &loadpin_dm_verity_ops);
+	if (IS_ERR(dentry)) {
+		pr_err("LoadPin: could not create securityfs entry 'dm-verity': %ld\n",
+		       PTR_ERR(dentry));
+		return PTR_ERR(dentry);
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_SECURITY_LOADPIN_VERITY */
+
+DEFINE_LSM(loadpin) = {
+	.id = &loadpin_lsmid,
+	.init = loadpin_init,
+#ifdef CONFIG_SECURITY_LOADPIN_VERITY
+	.initcall_fs = init_loadpin_securityfs,
+#endif /* CONFIG_SECURITY_LOADPIN_VERITY */
+};
+
+/* Should not be mutable after boot, so not listed in sysfs (perm == 0). */
+module_param(enforce, int, 0);
+MODULE_PARM_DESC(enforce, "Enforce module/firmware pinning");
+module_param_array_named(exclude, exclude_read_files, charp, NULL, 0);
+MODULE_PARM_DESC(exclude, "Exclude pinning specific read file types");
diff --git a/security/lockdown/Kconfig b/security/lockdown/Kconfig
new file mode 100644
index 000000000..e84ddf484
--- /dev/null
+++ b/security/lockdown/Kconfig
@@ -0,0 +1,47 @@
+config SECURITY_LOCKDOWN_LSM
+	bool "Basic module for enforcing kernel lockdown"
+	depends on SECURITY
+	select MODULE_SIG if MODULES
+	help
+	  Build support for an LSM that enforces a coarse kernel lockdown
+	  behaviour.
+
+config SECURITY_LOCKDOWN_LSM_EARLY
+	bool "Enable lockdown LSM early in init"
+	depends on SECURITY_LOCKDOWN_LSM
+	help
+	  Enable the lockdown LSM early in boot. This is necessary in order
+	  to ensure that lockdown enforcement can be carried out on kernel
+	  boot parameters that are otherwise parsed before the security
+	  subsystem is fully initialised. If enabled, lockdown will
+	  unconditionally be called before any other LSMs.
+
+choice
+	prompt "Kernel default lockdown mode"
+	default LOCK_DOWN_KERNEL_FORCE_NONE
+	depends on SECURITY_LOCKDOWN_LSM
+	help
+	  The kernel can be configured to default to differing levels of
+	  lockdown.
+
+config LOCK_DOWN_KERNEL_FORCE_NONE
+	bool "None"
+	help
+	  No lockdown functionality is enabled by default. Lockdown may be
+	  enabled via the kernel commandline or /sys/kernel/security/lockdown.
+
+config LOCK_DOWN_KERNEL_FORCE_INTEGRITY
+	bool "Integrity"
+	help
+	 The kernel runs in integrity mode by default. Features that allow
+	 the kernel to be modified at runtime are disabled.
+
+config LOCK_DOWN_KERNEL_FORCE_CONFIDENTIALITY
+	bool "Confidentiality"
+	help
+	 The kernel runs in confidentiality mode by default. Features that
+	 allow the kernel to be modified at runtime or that permit userland
+	 code to read confidential material held inside the kernel are
+	 disabled.
+
+endchoice
diff --git a/security/lockdown/Makefile b/security/lockdown/Makefile
new file mode 100644
index 000000000..e3634b901
--- /dev/null
+++ b/security/lockdown/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_SECURITY_LOCKDOWN_LSM) += lockdown.o
diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c
new file mode 100644
index 000000000..8d46886d2
--- /dev/null
+++ b/security/lockdown/lockdown.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Lock down the kernel
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/security.h>
+#include <linux/export.h>
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+
+static enum lockdown_reason kernel_locked_down;
+
+static const enum lockdown_reason lockdown_levels[] = {LOCKDOWN_NONE,
+						 LOCKDOWN_INTEGRITY_MAX,
+						 LOCKDOWN_CONFIDENTIALITY_MAX};
+
+/*
+ * Put the kernel into lock-down mode.
+ */
+static int lock_kernel_down(const char *where, enum lockdown_reason level)
+{
+	if (kernel_locked_down >= level)
+		return -EPERM;
+
+	kernel_locked_down = level;
+	pr_notice("Kernel is locked down from %s; see man kernel_lockdown.7\n",
+		  where);
+	return 0;
+}
+
+static int __init lockdown_param(char *level)
+{
+	if (!level)
+		return -EINVAL;
+
+	if (strcmp(level, "integrity") == 0)
+		lock_kernel_down("command line", LOCKDOWN_INTEGRITY_MAX);
+	else if (strcmp(level, "confidentiality") == 0)
+		lock_kernel_down("command line", LOCKDOWN_CONFIDENTIALITY_MAX);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+early_param("lockdown", lockdown_param);
+
+/**
+ * lockdown_is_locked_down - Find out if the kernel is locked down
+ * @what: Tag to use in notice generated if lockdown is in effect
+ */
+static int lockdown_is_locked_down(enum lockdown_reason what)
+{
+	if (WARN(what >= LOCKDOWN_CONFIDENTIALITY_MAX,
+		 "Invalid lockdown reason"))
+		return -EPERM;
+
+	if (kernel_locked_down >= what) {
+		if (lockdown_reasons[what])
+			pr_notice_ratelimited("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n",
+				  current->comm, lockdown_reasons[what]);
+		return -EPERM;
+	}
+
+	return 0;
+}
+
+static struct security_hook_list lockdown_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(locked_down, lockdown_is_locked_down),
+};
+
+static const struct lsm_id lockdown_lsmid = {
+	.name = "lockdown",
+	.id = LSM_ID_LOCKDOWN,
+};
+
+static int __init lockdown_lsm_init(void)
+{
+#if defined(CONFIG_LOCK_DOWN_KERNEL_FORCE_INTEGRITY)
+	lock_kernel_down("Kernel configuration", LOCKDOWN_INTEGRITY_MAX);
+#elif defined(CONFIG_LOCK_DOWN_KERNEL_FORCE_CONFIDENTIALITY)
+	lock_kernel_down("Kernel configuration", LOCKDOWN_CONFIDENTIALITY_MAX);
+#endif
+	security_add_hooks(lockdown_hooks, ARRAY_SIZE(lockdown_hooks),
+			   &lockdown_lsmid);
+	return 0;
+}
+
+static ssize_t lockdown_read(struct file *filp, char __user *buf, size_t count,
+			     loff_t *ppos)
+{
+	char temp[80] = "";
+	int i, offset = 0;
+
+	for (i = 0; i < ARRAY_SIZE(lockdown_levels); i++) {
+		enum lockdown_reason level = lockdown_levels[i];
+
+		if (lockdown_reasons[level]) {
+			const char *label = lockdown_reasons[level];
+
+			if (kernel_locked_down == level)
+				offset += sprintf(temp+offset, "[%s] ", label);
+			else
+				offset += sprintf(temp+offset, "%s ", label);
+		}
+	}
+
+	/* Convert the last space to a newline if needed. */
+	if (offset > 0)
+		temp[offset-1] = '\n';
+
+	return simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+}
+
+static ssize_t lockdown_write(struct file *file, const char __user *buf,
+			      size_t n, loff_t *ppos)
+{
+	char *state;
+	int i, len, err = -EINVAL;
+
+	state = memdup_user_nul(buf, n);
+	if (IS_ERR(state))
+		return PTR_ERR(state);
+
+	len = strlen(state);
+	if (len && state[len-1] == '\n') {
+		state[len-1] = '\0';
+		len--;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(lockdown_levels); i++) {
+		enum lockdown_reason level = lockdown_levels[i];
+		const char *label = lockdown_reasons[level];
+
+		if (label && !strcmp(state, label))
+			err = lock_kernel_down("securityfs", level);
+	}
+
+	kfree(state);
+	return err ? err : n;
+}
+
+static const struct file_operations lockdown_ops = {
+	.read  = lockdown_read,
+	.write = lockdown_write,
+};
+
+static int __init lockdown_secfs_init(void)
+{
+	struct dentry *dentry;
+
+	dentry = securityfs_create_file("lockdown", 0644, NULL, NULL,
+					&lockdown_ops);
+	return PTR_ERR_OR_ZERO(dentry);
+}
+
+#ifdef CONFIG_SECURITY_LOCKDOWN_LSM_EARLY
+DEFINE_EARLY_LSM(lockdown) = {
+#else
+DEFINE_LSM(lockdown) = {
+#endif
+	.id = &lockdown_lsmid,
+	.init = lockdown_lsm_init,
+	.initcall_core = lockdown_secfs_init,
+};
diff --git a/security/lsm.h b/security/lsm.h
new file mode 100644
index 000000000..32f808ad4
--- /dev/null
+++ b/security/lsm.h
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LSM functions
+ */
+
+#ifndef _LSM_H_
+#define _LSM_H_
+
+#include <linux/printk.h>
+#include <linux/lsm_hooks.h>
+#include <linux/lsm_count.h>
+
+/* LSM debugging */
+extern bool lsm_debug;
+#define lsm_pr(...)		pr_info(__VA_ARGS__)
+#define lsm_pr_cont(...)	pr_cont(__VA_ARGS__)
+#define lsm_pr_dbg(...)							\
+	do {								\
+		if (lsm_debug)						\
+			pr_info(__VA_ARGS__);				\
+	} while (0)
+
+/* List of configured LSMs */
+extern unsigned int lsm_active_cnt;
+extern const struct lsm_id *lsm_idlist[];
+
+/* LSM blob configuration */
+extern struct lsm_blob_sizes blob_sizes;
+
+/* LSM blob caches */
+extern struct kmem_cache *lsm_file_cache;
+extern struct kmem_cache *lsm_backing_file_cache;
+extern struct kmem_cache *lsm_inode_cache;
+
+/* LSM blob allocators */
+int lsm_cred_alloc(struct cred *cred, gfp_t gfp);
+int lsm_task_alloc(struct task_struct *task);
+
+/* LSM framework initializers */
+
+#ifdef CONFIG_SECURITYFS
+int securityfs_init(void);
+#else
+static inline int securityfs_init(void)
+{
+	return 0;
+}
+#endif /* CONFIG_SECURITYFS */
+
+#endif /* _LSM_H_ */
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
new file mode 100644
index 000000000..737f5a263
--- /dev/null
+++ b/security/lsm_audit.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * common LSM auditing functions
+ *
+ * Based on code written for SELinux by :
+ *			Stephen Smalley
+ * 			James Morris <jmorris@redhat.com>
+ * Author : Etienne Basset, <etienne.basset@ensta.org>
+ */
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <net/sock.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <linux/audit.h>
+#include <linux/ipv6.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/sctp.h>
+#include <linux/lsm_audit.h>
+#include <linux/security.h>
+
+/**
+ * ipv4_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int ret = 0;
+	struct iphdr *ih;
+
+	ih = ip_hdr(skb);
+	ad->u.net->v4info.saddr = ih->saddr;
+	ad->u.net->v4info.daddr = ih->daddr;
+
+	if (proto)
+		*proto = ih->protocol;
+	/* non initial fragment */
+	if (ntohs(ih->frag_off) & IP_OFFSET)
+		return 0;
+
+	switch (ih->protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr *th = tcp_hdr(skb);
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr *uh = udp_hdr(skb);
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr *sh = sctp_hdr(skb);
+
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * ipv6_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int offset, ret = 0;
+	struct ipv6hdr *ip6;
+	u8 nexthdr;
+	__be16 frag_off;
+
+	ip6 = ipv6_hdr(skb);
+	ad->u.net->v6info.saddr = ip6->saddr;
+	ad->u.net->v6info.daddr = ip6->daddr;
+	/* IPv6 can have several extension header before the Transport header
+	 * skip them */
+	offset = skb_network_offset(skb);
+	offset += sizeof(*ip6);
+	nexthdr = ip6->nexthdr;
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+	if (offset < 0)
+		return 0;
+	if (proto)
+		*proto = nexthdr;
+	switch (nexthdr) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			break;
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			break;
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr _sctph, *sh;
+
+		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+		if (sh == NULL)
+			break;
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#endif
+
+
+static inline void print_ipv6_addr(struct audit_buffer *ab,
+				   const struct in6_addr *addr, __be16 port,
+				   const char *name1, const char *name2)
+{
+	if (!ipv6_addr_any(addr))
+		audit_log_format(ab, " %s=%pI6c", name1, addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
+				   __be16 port, const char *name1, const char *name2)
+{
+	if (addr)
+		audit_log_format(ab, " %s=%pI4", name1, &addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+/**
+ * audit_log_lsm_data - helper to log common LSM audit data
+ * @ab : the audit buffer
+ * @a : common audit data
+ */
+void audit_log_lsm_data(struct audit_buffer *ab,
+			const struct common_audit_data *a)
+{
+	/*
+	 * To keep stack sizes in check force programmers to notice if they
+	 * start making this union too large!  See struct lsm_network_audit
+	 * as an example of how to deal with large data.
+	 */
+	BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2);
+
+	switch (a->type) {
+	case LSM_AUDIT_DATA_NONE:
+		return;
+	case LSM_AUDIT_DATA_IPC:
+		audit_log_format(ab, " ipc_key=%d ", a->u.ipc_id);
+		break;
+	case LSM_AUDIT_DATA_CAP:
+		audit_log_format(ab, " capability=%d ", a->u.cap);
+		break;
+	case LSM_AUDIT_DATA_PATH: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.path);
+
+		inode = d_backing_inode(a->u.path.dentry);
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%llu", inode->i_ino);
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_FILE: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.file->f_path);
+
+		inode = file_inode(a->u.file);
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%llu", inode->i_ino);
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_IOCTL_OP: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.op->path);
+
+		inode = a->u.op->path.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%llu", inode->i_ino);
+		}
+
+		audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd);
+		break;
+	}
+	case LSM_AUDIT_DATA_DENTRY: {
+		struct inode *inode;
+
+		audit_log_format(ab, " name=");
+		spin_lock(&a->u.dentry->d_lock);
+		audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
+		spin_unlock(&a->u.dentry->d_lock);
+
+		inode = d_backing_inode(a->u.dentry);
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%llu", inode->i_ino);
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_INODE: {
+		struct dentry *dentry;
+		struct inode *inode;
+
+		rcu_read_lock();
+		inode = a->u.inode;
+		dentry = d_find_alias_rcu(inode);
+		if (dentry) {
+			audit_log_format(ab, " name=");
+			spin_lock(&dentry->d_lock);
+			audit_log_untrustedstring(ab, dentry->d_name.name);
+			spin_unlock(&dentry->d_lock);
+		}
+		audit_log_format(ab, " dev=");
+		audit_log_untrustedstring(ab, inode->i_sb->s_id);
+		audit_log_format(ab, " ino=%llu", inode->i_ino);
+		rcu_read_unlock();
+		break;
+	}
+	case LSM_AUDIT_DATA_TASK: {
+		struct task_struct *tsk = a->u.tsk;
+		if (tsk) {
+			pid_t pid = task_tgid_nr(tsk);
+			if (pid) {
+				char tskcomm[sizeof(tsk->comm)];
+				audit_log_format(ab, " opid=%d ocomm=", pid);
+				audit_log_untrustedstring(ab,
+				    get_task_comm(tskcomm, tsk));
+			}
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_NET:
+		if (a->u.net->sk) {
+			const struct sock *sk = a->u.net->sk;
+			const struct unix_sock *u;
+			struct unix_address *addr;
+			int len = 0;
+			char *p = NULL;
+
+			switch (sk->sk_family) {
+			case AF_INET: {
+				const struct inet_sock *inet = inet_sk(sk);
+
+				print_ipv4_addr(ab, inet->inet_rcv_saddr,
+						inet->inet_sport,
+						"laddr", "lport");
+				print_ipv4_addr(ab, inet->inet_daddr,
+						inet->inet_dport,
+						"faddr", "fport");
+				break;
+			}
+#if IS_ENABLED(CONFIG_IPV6)
+			case AF_INET6: {
+				const struct inet_sock *inet = inet_sk(sk);
+
+				print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr,
+						inet->inet_sport,
+						"laddr", "lport");
+				print_ipv6_addr(ab, &sk->sk_v6_daddr,
+						inet->inet_dport,
+						"faddr", "fport");
+				break;
+			}
+#endif
+			case AF_UNIX:
+				u = unix_sk(sk);
+				addr = smp_load_acquire(&u->addr);
+				if (!addr)
+					break;
+				if (u->path.dentry) {
+					audit_log_d_path(ab, " path=", &u->path);
+					break;
+				}
+				len = addr->len-sizeof(short);
+				p = &addr->name->sun_path[0];
+				audit_log_format(ab, " path=");
+				if (*p)
+					audit_log_untrustedstring(ab, p);
+				else
+					audit_log_n_hex(ab, p, len);
+				break;
+			}
+		}
+
+		switch (a->u.net->family) {
+		case AF_INET:
+			print_ipv4_addr(ab, a->u.net->v4info.saddr,
+					a->u.net->sport,
+					"saddr", "src");
+			print_ipv4_addr(ab, a->u.net->v4info.daddr,
+					a->u.net->dport,
+					"daddr", "dest");
+			break;
+		case AF_INET6:
+			print_ipv6_addr(ab, &a->u.net->v6info.saddr,
+					a->u.net->sport,
+					"saddr", "src");
+			print_ipv6_addr(ab, &a->u.net->v6info.daddr,
+					a->u.net->dport,
+					"daddr", "dest");
+			break;
+		}
+		if (a->u.net->netif > 0) {
+			struct net_device *dev;
+
+			/* NOTE: we always use init's namespace */
+			dev = dev_get_by_index(&init_net, a->u.net->netif);
+			if (dev) {
+				audit_log_format(ab, " netif=%s", dev->name);
+				dev_put(dev);
+			}
+		}
+		break;
+#ifdef CONFIG_KEYS
+	case LSM_AUDIT_DATA_KEY:
+		audit_log_format(ab, " key_serial=%u", a->u.key_struct.key);
+		if (a->u.key_struct.key_desc) {
+			audit_log_format(ab, " key_desc=");
+			audit_log_untrustedstring(ab, a->u.key_struct.key_desc);
+		}
+		break;
+#endif
+	case LSM_AUDIT_DATA_KMOD:
+		audit_log_format(ab, " kmod=");
+		audit_log_untrustedstring(ab, a->u.kmod_name);
+		break;
+	case LSM_AUDIT_DATA_IBPKEY: {
+		struct in6_addr sbn_pfx;
+
+		memset(&sbn_pfx.s6_addr, 0,
+		       sizeof(sbn_pfx.s6_addr));
+		memcpy(&sbn_pfx.s6_addr, &a->u.ibpkey->subnet_prefix,
+		       sizeof(a->u.ibpkey->subnet_prefix));
+		audit_log_format(ab, " pkey=0x%x subnet_prefix=%pI6c",
+				 a->u.ibpkey->pkey, &sbn_pfx);
+		break;
+	}
+	case LSM_AUDIT_DATA_IBENDPORT:
+		audit_log_format(ab, " device=%s port_num=%u",
+				 a->u.ibendport->dev_name,
+				 a->u.ibendport->port);
+		break;
+	case LSM_AUDIT_DATA_LOCKDOWN:
+		audit_log_format(ab, " lockdown_reason=\"%s\"",
+				 lockdown_reasons[a->u.reason]);
+		break;
+	case LSM_AUDIT_DATA_ANONINODE:
+		audit_log_format(ab, " anonclass=%s", a->u.anonclass);
+		break;
+	case LSM_AUDIT_DATA_NLMSGTYPE:
+		audit_log_format(ab, " nl-msgtype=%hu", a->u.nlmsg_type);
+		break;
+	} /* switch (a->type) */
+}
+
+/**
+ * dump_common_audit_data - helper to dump common audit data
+ * @ab : the audit buffer
+ * @a : common audit data
+ */
+static void dump_common_audit_data(struct audit_buffer *ab,
+				   const struct common_audit_data *a)
+{
+	char comm[sizeof(current->comm)];
+
+	audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current));
+	audit_log_untrustedstring(ab, get_task_comm(comm, current));
+	audit_log_lsm_data(ab, a);
+}
+
+/**
+ * common_lsm_audit - generic LSM auditing function
+ * @a:  auxiliary audit data
+ * @pre_audit: lsm-specific pre-audit callback
+ * @post_audit: lsm-specific post-audit callback
+ *
+ * setup the audit buffer for common security information
+ * uses callback to print LSM specific information
+ */
+void common_lsm_audit(struct common_audit_data *a,
+	void (*pre_audit)(struct audit_buffer *, void *),
+	void (*post_audit)(struct audit_buffer *, void *))
+{
+	struct audit_buffer *ab;
+
+	if (a == NULL)
+		return;
+	/* we use GFP_ATOMIC so we won't sleep */
+	ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN,
+			     AUDIT_AVC);
+
+	if (ab == NULL)
+		return;
+
+	if (pre_audit)
+		pre_audit(ab, a);
+
+	dump_common_audit_data(ab, a);
+
+	if (post_audit)
+		post_audit(ab, a);
+
+	audit_log_end(ab);
+}
diff --git a/security/lsm_init.c b/security/lsm_init.c
new file mode 100644
index 000000000..a1ad64181
--- /dev/null
+++ b/security/lsm_init.c
@@ -0,0 +1,577 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LSM initialization functions
+ */
+
+#define pr_fmt(fmt) "LSM: " fmt
+
+#include <linux/init.h>
+#include <linux/lsm_hooks.h>
+
+#include "lsm.h"
+
+/* LSM enabled constants. */
+static __initdata int lsm_enabled_true = 1;
+static __initdata int lsm_enabled_false = 0;
+
+/* Pointers to LSM sections defined in include/asm-generic/vmlinux.lds.h */
+extern struct lsm_info __start_lsm_info[], __end_lsm_info[];
+extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
+
+/* Number of "early" LSMs */
+static __initdata unsigned int lsm_count_early;
+
+/* Build and boot-time LSM ordering. */
+static __initconst const char *const lsm_order_builtin = CONFIG_LSM;
+static __initdata const char *lsm_order_cmdline;
+static __initdata const char *lsm_order_legacy;
+
+/* Ordered list of LSMs to initialize. */
+static __initdata struct lsm_info *lsm_order[MAX_LSM_COUNT + 1];
+static __initdata struct lsm_info *lsm_exclusive;
+
+#define lsm_order_for_each(iter)					\
+	for ((iter) = lsm_order; *(iter); (iter)++)
+#define lsm_for_each_raw(iter)						\
+	for ((iter) = __start_lsm_info;					\
+	     (iter) < __end_lsm_info; (iter)++)
+#define lsm_early_for_each_raw(iter)					\
+	for ((iter) = __start_early_lsm_info;				\
+	     (iter) < __end_early_lsm_info; (iter)++)
+
+#define lsm_initcall(level)						\
+	({								\
+		int _r, _rc = 0;					\
+		struct lsm_info **_lp, *_l;				\
+		lsm_order_for_each(_lp) {				\
+			_l = *_lp;					\
+			if (!_l->initcall_##level)			\
+				continue;				\
+			lsm_pr_dbg("running %s %s initcall",		\
+				   _l->id->name, #level);		\
+			_r = _l->initcall_##level();			\
+			if (_r) {					\
+				pr_warn("failed LSM %s %s initcall with errno %d\n", \
+					_l->id->name, #level, _r);	\
+				if (!_rc)				\
+					_rc = _r;			\
+			}						\
+		}							\
+		_rc;							\
+	})
+
+/**
+ * lsm_choose_security - Legacy "major" LSM selection
+ * @str: kernel command line parameter
+ */
+static int __init lsm_choose_security(char *str)
+{
+	lsm_order_legacy = str;
+	return 1;
+}
+__setup("security=", lsm_choose_security);
+
+/**
+ * lsm_choose_lsm - Modern LSM selection
+ * @str: kernel command line parameter
+ */
+static int __init lsm_choose_lsm(char *str)
+{
+	lsm_order_cmdline = str;
+	return 1;
+}
+__setup("lsm=", lsm_choose_lsm);
+
+/**
+ * lsm_debug_enable - Enable LSM framework debugging
+ * @str: kernel command line parameter
+ *
+ * Currently we only provide debug info during LSM initialization, but we may
+ * want to expand this in the future.
+ */
+static int __init lsm_debug_enable(char *str)
+{
+	lsm_debug = true;
+	return 1;
+}
+__setup("lsm.debug", lsm_debug_enable);
+
+/**
+ * lsm_enabled_set - Mark a LSM as enabled
+ * @lsm: LSM definition
+ * @enabled: enabled flag
+ */
+static void __init lsm_enabled_set(struct lsm_info *lsm, bool enabled)
+{
+	/*
+	 * When an LSM hasn't configured an enable variable, we can use
+	 * a hard-coded location for storing the default enabled state.
+	 */
+	if (!lsm->enabled ||
+	    lsm->enabled == &lsm_enabled_true ||
+	    lsm->enabled == &lsm_enabled_false) {
+		lsm->enabled = enabled ? &lsm_enabled_true : &lsm_enabled_false;
+	} else {
+		*lsm->enabled = enabled;
+	}
+}
+
+/**
+ * lsm_is_enabled - Determine if a LSM is enabled
+ * @lsm: LSM definition
+ */
+static inline bool lsm_is_enabled(struct lsm_info *lsm)
+{
+	return (lsm->enabled ? *lsm->enabled : false);
+}
+
+/**
+ * lsm_order_exists - Determine if a LSM exists in the ordered list
+ * @lsm: LSM definition
+ */
+static bool __init lsm_order_exists(struct lsm_info *lsm)
+{
+	struct lsm_info **check;
+
+	lsm_order_for_each(check) {
+		if (*check == lsm)
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * lsm_order_append - Append a LSM to the ordered list
+ * @lsm: LSM definition
+ * @src: source of the addition
+ *
+ * Append @lsm to the enabled LSM array after ensuring that it hasn't been
+ * explicitly disabled, is a duplicate entry, or would run afoul of the
+ * LSM_FLAG_EXCLUSIVE logic.
+ */
+static void __init lsm_order_append(struct lsm_info *lsm, const char *src)
+{
+	/* Ignore duplicate selections. */
+	if (lsm_order_exists(lsm))
+		return;
+
+	/* Skip explicitly disabled LSMs. */
+	if (lsm->enabled && !lsm_is_enabled(lsm)) {
+		lsm_pr_dbg("skip previously disabled LSM %s:%s\n",
+			   src, lsm->id->name);
+		return;
+	}
+
+	if (lsm_active_cnt == MAX_LSM_COUNT) {
+		pr_warn("exceeded maximum LSM count on %s:%s\n",
+			src, lsm->id->name);
+		lsm_enabled_set(lsm, false);
+		return;
+	}
+
+	if (lsm->flags & LSM_FLAG_EXCLUSIVE) {
+		if (lsm_exclusive) {
+			lsm_pr_dbg("skip exclusive LSM conflict %s:%s\n",
+				   src, lsm->id->name);
+			lsm_enabled_set(lsm, false);
+			return;
+		} else {
+			lsm_pr_dbg("select exclusive LSM %s:%s\n",
+				   src, lsm->id->name);
+			lsm_exclusive = lsm;
+		}
+	}
+
+	lsm_enabled_set(lsm, true);
+	lsm_order[lsm_active_cnt] = lsm;
+	lsm_idlist[lsm_active_cnt++] = lsm->id;
+
+	lsm_pr_dbg("enabling LSM %s:%s\n", src, lsm->id->name);
+}
+
+/**
+ * lsm_order_parse - Parse the comma delimited LSM list
+ * @list: LSM list
+ * @src: source of the list
+ */
+static void __init lsm_order_parse(const char *list, const char *src)
+{
+	struct lsm_info *lsm;
+	char *sep, *name, *next;
+
+	/* Handle any Legacy LSM exclusions if one was specified. */
+	if (lsm_order_legacy) {
+		/*
+		 * To match the original "security=" behavior, this explicitly
+		 * does NOT fallback to another Legacy Major if the selected
+		 * one was separately disabled: disable all non-matching
+		 * Legacy Major LSMs.
+		 */
+		lsm_for_each_raw(lsm) {
+			if ((lsm->flags & LSM_FLAG_LEGACY_MAJOR) &&
+			     strcmp(lsm->id->name, lsm_order_legacy)) {
+				lsm_enabled_set(lsm, false);
+				lsm_pr_dbg("skip legacy LSM conflict %s:%s\n",
+					   src, lsm->id->name);
+			}
+		}
+	}
+
+	/* LSM_ORDER_FIRST */
+	lsm_for_each_raw(lsm) {
+		if (lsm->order == LSM_ORDER_FIRST)
+			lsm_order_append(lsm, "first");
+	}
+
+	/* Normal or "mutable" LSMs */
+	sep = kstrdup(list, GFP_KERNEL);
+	next = sep;
+	/* Walk the list, looking for matching LSMs. */
+	while ((name = strsep(&next, ",")) != NULL) {
+		lsm_for_each_raw(lsm) {
+			if (!strcmp(lsm->id->name, name) &&
+			    lsm->order == LSM_ORDER_MUTABLE)
+				lsm_order_append(lsm, src);
+		}
+	}
+	kfree(sep);
+
+	/* Legacy LSM if specified. */
+	if (lsm_order_legacy) {
+		lsm_for_each_raw(lsm) {
+			if (!strcmp(lsm->id->name, lsm_order_legacy))
+				lsm_order_append(lsm, src);
+		}
+	}
+
+	/* LSM_ORDER_LAST */
+	lsm_for_each_raw(lsm) {
+		if (lsm->order == LSM_ORDER_LAST)
+			lsm_order_append(lsm, "last");
+	}
+
+	/* Disable all LSMs not previously enabled. */
+	lsm_for_each_raw(lsm) {
+		if (lsm_order_exists(lsm))
+			continue;
+		lsm_enabled_set(lsm, false);
+		lsm_pr_dbg("skip disabled LSM %s:%s\n", src, lsm->id->name);
+	}
+}
+
+/**
+ * lsm_blob_size_update - Update the LSM blob size and offset information
+ * @sz_req: the requested additional blob size
+ * @sz_cur: the existing blob size
+ */
+static void __init lsm_blob_size_update(unsigned int *sz_req,
+					unsigned int *sz_cur)
+{
+	unsigned int offset;
+
+	if (*sz_req == 0)
+		return;
+
+	offset = ALIGN(*sz_cur, sizeof(void *));
+	*sz_cur = offset + *sz_req;
+	*sz_req = offset;
+}
+
+/**
+ * lsm_prepare - Prepare the LSM framework for a new LSM
+ * @lsm: LSM definition
+ */
+static void __init lsm_prepare(struct lsm_info *lsm)
+{
+	struct lsm_blob_sizes *blobs = lsm->blobs;
+
+	if (!blobs)
+		return;
+
+	/* Register the LSM blob sizes. */
+	blobs = lsm->blobs;
+	lsm_blob_size_update(&blobs->lbs_cred, &blob_sizes.lbs_cred);
+	lsm_blob_size_update(&blobs->lbs_file, &blob_sizes.lbs_file);
+	lsm_blob_size_update(&blobs->lbs_backing_file,
+			     &blob_sizes.lbs_backing_file);
+	lsm_blob_size_update(&blobs->lbs_ib, &blob_sizes.lbs_ib);
+	/* inode blob gets an rcu_head in addition to LSM blobs. */
+	if (blobs->lbs_inode && blob_sizes.lbs_inode == 0)
+		blob_sizes.lbs_inode = sizeof(struct rcu_head);
+	lsm_blob_size_update(&blobs->lbs_inode, &blob_sizes.lbs_inode);
+	lsm_blob_size_update(&blobs->lbs_ipc, &blob_sizes.lbs_ipc);
+	lsm_blob_size_update(&blobs->lbs_key, &blob_sizes.lbs_key);
+	lsm_blob_size_update(&blobs->lbs_msg_msg, &blob_sizes.lbs_msg_msg);
+	lsm_blob_size_update(&blobs->lbs_perf_event,
+			     &blob_sizes.lbs_perf_event);
+	lsm_blob_size_update(&blobs->lbs_sock, &blob_sizes.lbs_sock);
+	lsm_blob_size_update(&blobs->lbs_superblock,
+			     &blob_sizes.lbs_superblock);
+	lsm_blob_size_update(&blobs->lbs_task, &blob_sizes.lbs_task);
+	lsm_blob_size_update(&blobs->lbs_tun_dev, &blob_sizes.lbs_tun_dev);
+	lsm_blob_size_update(&blobs->lbs_xattr_count,
+			     &blob_sizes.lbs_xattr_count);
+	lsm_blob_size_update(&blobs->lbs_bdev, &blob_sizes.lbs_bdev);
+	lsm_blob_size_update(&blobs->lbs_bpf_map, &blob_sizes.lbs_bpf_map);
+	lsm_blob_size_update(&blobs->lbs_bpf_prog, &blob_sizes.lbs_bpf_prog);
+	lsm_blob_size_update(&blobs->lbs_bpf_token, &blob_sizes.lbs_bpf_token);
+}
+
+/**
+ * lsm_init_single - Initialize a given LSM
+ * @lsm: LSM definition
+ */
+static void __init lsm_init_single(struct lsm_info *lsm)
+{
+	int ret;
+
+	if (!lsm_is_enabled(lsm))
+		return;
+
+	lsm_pr_dbg("initializing %s\n", lsm->id->name);
+	ret = lsm->init();
+	WARN(ret, "%s failed to initialize: %d\n", lsm->id->name, ret);
+}
+
+/**
+ * lsm_static_call_init - Initialize a LSM's static calls
+ * @hl: LSM hook list
+ */
+static int __init lsm_static_call_init(struct security_hook_list *hl)
+{
+	struct lsm_static_call *scall = hl->scalls;
+	int i;
+
+	for (i = 0; i < MAX_LSM_COUNT; i++) {
+		/* Update the first static call that is not used yet */
+		if (!scall->hl) {
+			__static_call_update(scall->key, scall->trampoline,
+					     hl->hook.lsm_func_addr);
+			scall->hl = hl;
+			static_branch_enable(scall->active);
+			return 0;
+		}
+		scall++;
+	}
+
+	return -ENOSPC;
+}
+
+/**
+ * security_add_hooks - Add a LSM's hooks to the LSM framework's hook lists
+ * @hooks: LSM hooks to add
+ * @count: number of hooks to add
+ * @lsmid: identification information for the LSM
+ *
+ * Each LSM has to register its hooks with the LSM framework.
+ */
+void __init security_add_hooks(struct security_hook_list *hooks, int count,
+			       const struct lsm_id *lsmid)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		hooks[i].lsmid = lsmid;
+		if (lsm_static_call_init(&hooks[i]))
+			panic("exhausted LSM callback slots with LSM %s\n",
+			      lsmid->name);
+	}
+}
+
+/**
+ * early_security_init - Initialize the early LSMs
+ */
+int __init early_security_init(void)
+{
+	struct lsm_info *lsm;
+
+	/* NOTE: lsm_pr_dbg() doesn't work here as lsm_debug is not yet set */
+
+	lsm_early_for_each_raw(lsm) {
+		lsm_enabled_set(lsm, true);
+		lsm_order_append(lsm, "early");
+		lsm_prepare(lsm);
+		lsm_init_single(lsm);
+		lsm_count_early++;
+	}
+
+	return 0;
+}
+
+/**
+ * security_init - Initializes the LSM framework
+ *
+ * This should be called early in the kernel initialization sequence.
+ */
+int __init security_init(void)
+{
+	unsigned int cnt;
+	struct lsm_info **lsm;
+
+	if (lsm_debug) {
+		struct lsm_info *i;
+
+		cnt = 0;
+		lsm_pr("available LSMs: ");
+		lsm_early_for_each_raw(i)
+			lsm_pr_cont("%s%s(E)", (cnt++ ? "," : ""), i->id->name);
+		lsm_for_each_raw(i)
+			lsm_pr_cont("%s%s", (cnt++ ? "," : ""), i->id->name);
+		lsm_pr_cont("\n");
+
+		lsm_pr("built-in LSM config: %s\n", lsm_order_builtin);
+
+		lsm_pr("legacy LSM parameter: %s\n", lsm_order_legacy);
+		lsm_pr("boot LSM parameter: %s\n", lsm_order_cmdline);
+
+		/* see the note about lsm_pr_dbg() in early_security_init() */
+		lsm_early_for_each_raw(i)
+			lsm_pr("enabled LSM early:%s\n", i->id->name);
+	}
+
+	if (lsm_order_cmdline) {
+		if (lsm_order_legacy)
+			lsm_order_legacy = NULL;
+		lsm_order_parse(lsm_order_cmdline, "cmdline");
+	} else
+		lsm_order_parse(lsm_order_builtin, "builtin");
+
+	lsm_order_for_each(lsm)
+		lsm_prepare(*lsm);
+
+	if (lsm_debug) {
+		lsm_pr("blob(cred) size %d\n", blob_sizes.lbs_cred);
+		lsm_pr("blob(file) size %d\n", blob_sizes.lbs_file);
+		lsm_pr("blob(backing_file) size %d\n",
+		       blob_sizes.lbs_backing_file);
+		lsm_pr("blob(ib) size %d\n", blob_sizes.lbs_ib);
+		lsm_pr("blob(inode) size %d\n", blob_sizes.lbs_inode);
+		lsm_pr("blob(ipc) size %d\n", blob_sizes.lbs_ipc);
+		lsm_pr("blob(key) size %d\n", blob_sizes.lbs_key);
+		lsm_pr("blob(msg_msg)_size %d\n", blob_sizes.lbs_msg_msg);
+		lsm_pr("blob(sock) size %d\n", blob_sizes.lbs_sock);
+		lsm_pr("blob(superblock) size %d\n", blob_sizes.lbs_superblock);
+		lsm_pr("blob(perf_event) size %d\n", blob_sizes.lbs_perf_event);
+		lsm_pr("blob(task) size %d\n", blob_sizes.lbs_task);
+		lsm_pr("blob(tun_dev) size %d\n", blob_sizes.lbs_tun_dev);
+		lsm_pr("blob(xattr) count %d\n", blob_sizes.lbs_xattr_count);
+		lsm_pr("blob(bdev) size %d\n", blob_sizes.lbs_bdev);
+		lsm_pr("blob(bpf_map) size %d\n", blob_sizes.lbs_bpf_map);
+		lsm_pr("blob(bpf_prog) size %d\n", blob_sizes.lbs_bpf_prog);
+		lsm_pr("blob(bpf_token) size %d\n", blob_sizes.lbs_bpf_token);
+	}
+
+	if (blob_sizes.lbs_file)
+		lsm_file_cache = kmem_cache_create("lsm_file_cache",
+						   blob_sizes.lbs_file, 0,
+						   SLAB_PANIC, NULL);
+	if (blob_sizes.lbs_backing_file)
+		lsm_backing_file_cache = kmem_cache_create(
+						   "lsm_backing_file_cache",
+						   blob_sizes.lbs_backing_file,
+						   0, SLAB_PANIC, NULL);
+	if (blob_sizes.lbs_inode)
+		lsm_inode_cache = kmem_cache_create("lsm_inode_cache",
+						    blob_sizes.lbs_inode, 0,
+						    SLAB_PANIC, NULL);
+
+	if (lsm_cred_alloc((struct cred *)unrcu_pointer(current->cred),
+			   GFP_KERNEL))
+		panic("early LSM cred alloc failed\n");
+	if (lsm_task_alloc(current))
+		panic("early LSM task alloc failed\n");
+
+	cnt = 0;
+	lsm_order_for_each(lsm) {
+		/* skip the "early" LSMs as they have already been setup */
+		if (cnt++ < lsm_count_early)
+			continue;
+		lsm_init_single(*lsm);
+	}
+
+	return 0;
+}
+
+/**
+ * security_initcall_pure - Run the LSM pure initcalls
+ */
+static int __init security_initcall_pure(void)
+{
+	return lsm_initcall(pure);
+}
+pure_initcall(security_initcall_pure);
+
+/**
+ * security_initcall_early - Run the LSM early initcalls
+ */
+static int __init security_initcall_early(void)
+{
+	return lsm_initcall(early);
+}
+early_initcall(security_initcall_early);
+
+/**
+ * security_initcall_core - Run the LSM core initcalls
+ */
+static int __init security_initcall_core(void)
+{
+	int rc_sfs, rc_lsm;
+
+	rc_sfs = securityfs_init();
+	rc_lsm = lsm_initcall(core);
+
+	return (rc_sfs ? rc_sfs : rc_lsm);
+}
+core_initcall(security_initcall_core);
+
+/**
+ * security_initcall_subsys - Run the LSM subsys initcalls
+ */
+static int __init security_initcall_subsys(void)
+{
+	return lsm_initcall(subsys);
+}
+subsys_initcall(security_initcall_subsys);
+
+/**
+ * security_initcall_fs - Run the LSM fs initcalls
+ */
+static int __init security_initcall_fs(void)
+{
+	return lsm_initcall(fs);
+}
+fs_initcall(security_initcall_fs);
+
+/**
+ * security_initcall_device - Run the LSM device initcalls
+ */
+static int __init security_initcall_device(void)
+{
+	return lsm_initcall(device);
+}
+device_initcall(security_initcall_device);
+
+/**
+ * security_initcall_late - Run the LSM late initcalls
+ */
+static int __init security_initcall_late(void)
+{
+	return lsm_initcall(late);
+}
+late_initcall(security_initcall_late);
+
+/**
+ * security_initcall_late_sync - Run the LSM late initcalls sync
+ */
+static int __init security_initcall_late_sync(void)
+{
+	int rc;
+
+	rc = lsm_initcall(late_sync);
+	lsm_pr_dbg("all enabled LSMs fully activated\n");
+	call_blocking_lsm_notifier(LSM_STARTED_ALL, NULL);
+
+	return rc;
+}
+late_initcall_sync(security_initcall_late_sync);
diff --git a/security/lsm_notifier.c b/security/lsm_notifier.c
new file mode 100644
index 000000000..c92fad5d5
--- /dev/null
+++ b/security/lsm_notifier.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * LSM notifier functions
+ *
+ */
+
+#include <linux/notifier.h>
+#include <linux/security.h>
+
+static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain);
+
+int call_blocking_lsm_notifier(enum lsm_event event, void *data)
+{
+	return blocking_notifier_call_chain(&blocking_lsm_notifier_chain,
+					    event, data);
+}
+EXPORT_SYMBOL(call_blocking_lsm_notifier);
+
+int register_blocking_lsm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&blocking_lsm_notifier_chain,
+						nb);
+}
+EXPORT_SYMBOL(register_blocking_lsm_notifier);
+
+int unregister_blocking_lsm_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain,
+						  nb);
+}
+EXPORT_SYMBOL(unregister_blocking_lsm_notifier);
diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c
new file mode 100644
index 000000000..08a017669
--- /dev/null
+++ b/security/lsm_syscalls.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * System calls implementing the Linux Security Module API.
+ *
+ *  Copyright (C) 2022 Casey Schaufler <casey@schaufler-ca.com>
+ *  Copyright (C) 2022 Intel Corporation
+ */
+
+#include <asm/current.h>
+#include <linux/compiler_types.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/security.h>
+#include <linux/stddef.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+
+#include "lsm.h"
+
+/**
+ * lsm_name_to_attr - map an LSM attribute name to its ID
+ * @name: name of the attribute
+ *
+ * Returns the LSM attribute value associated with @name, or 0 if
+ * there is no mapping.
+ */
+u64 lsm_name_to_attr(const char *name)
+{
+	if (!strcmp(name, "current"))
+		return LSM_ATTR_CURRENT;
+	if (!strcmp(name, "exec"))
+		return LSM_ATTR_EXEC;
+	if (!strcmp(name, "fscreate"))
+		return LSM_ATTR_FSCREATE;
+	if (!strcmp(name, "keycreate"))
+		return LSM_ATTR_KEYCREATE;
+	if (!strcmp(name, "prev"))
+		return LSM_ATTR_PREV;
+	if (!strcmp(name, "sockcreate"))
+		return LSM_ATTR_SOCKCREATE;
+	return LSM_ATTR_UNDEF;
+}
+
+/**
+ * sys_lsm_set_self_attr - Set current task's security module attribute
+ * @attr: which attribute to set
+ * @ctx: the LSM contexts
+ * @size: size of @ctx
+ * @flags: reserved for future use
+ *
+ * Sets the calling task's LSM context. On success this function
+ * returns 0. If the attribute specified cannot be set a negative
+ * value indicating the reason for the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, u32, size, u32, flags)
+{
+	int rc;
+
+	rc = mutex_lock_interruptible(&current->signal->cred_guard_mutex);
+	if (rc < 0)
+		return rc;
+	rc = security_setselfattr(attr, ctx, size, flags);
+	mutex_unlock(&current->signal->cred_guard_mutex);
+	return rc;
+}
+
+/**
+ * sys_lsm_get_self_attr - Return current task's security module attributes
+ * @attr: which attribute to return
+ * @ctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * Returns the calling task's LSM contexts. On success this
+ * function returns the number of @ctx array elements. This value
+ * may be zero if there are no LSM contexts assigned. If @size is
+ * insufficient to contain the return data -E2BIG is returned and
+ * @size is set to the minimum required size. In all other cases
+ * a negative value indicating the error is returned.
+ */
+SYSCALL_DEFINE4(lsm_get_self_attr, unsigned int, attr, struct lsm_ctx __user *,
+		ctx, u32 __user *, size, u32, flags)
+{
+	return security_getselfattr(attr, ctx, size, flags);
+}
+
+/**
+ * sys_lsm_list_modules - Return a list of the active security modules
+ * @ids: the LSM module ids
+ * @size: pointer to size of @ids, updated on return
+ * @flags: reserved for future use, must be zero
+ *
+ * Returns a list of the active LSM ids. On success this function
+ * returns the number of @ids array elements. This value may be zero
+ * if there are no LSMs active. If @size is insufficient to contain
+ * the return data -E2BIG is returned and @size is set to the minimum
+ * required size. In all other cases a negative value indicating the
+ * error is returned.
+ */
+SYSCALL_DEFINE3(lsm_list_modules, u64 __user *, ids, u32 __user *, size,
+		u32, flags)
+{
+	u32 total_size = lsm_active_cnt * sizeof(*ids);
+	u32 usize;
+	int i;
+
+	if (flags)
+		return -EINVAL;
+
+	if (get_user(usize, size))
+		return -EFAULT;
+
+	if (put_user(total_size, size) != 0)
+		return -EFAULT;
+
+	if (usize < total_size)
+		return -E2BIG;
+
+	for (i = 0; i < lsm_active_cnt; i++)
+		if (put_user(lsm_idlist[i]->id, ids++))
+			return -EFAULT;
+
+	return lsm_active_cnt;
+}
diff --git a/security/min_addr.c b/security/min_addr.c
new file mode 100644
index 000000000..56e4f9d25
--- /dev/null
+++ b/security/min_addr.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/security.h>
+#include <linux/sysctl.h>
+#include <linux/minmax.h>
+
+/* amount of vm to protect from userspace access by both DAC and the LSM*/
+unsigned long mmap_min_addr;
+/* amount of vm to protect from userspace using CAP_SYS_RAWIO (DAC) */
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+/* amount of vm to protect from userspace using the LSM = CONFIG_LSM_MMAP_MIN_ADDR */
+
+/*
+ * Update mmap_min_addr = max(dac_mmap_min_addr, CONFIG_LSM_MMAP_MIN_ADDR)
+ */
+static void update_mmap_min_addr(void)
+{
+#ifdef CONFIG_LSM_MMAP_MIN_ADDR
+	mmap_min_addr = umax(dac_mmap_min_addr, CONFIG_LSM_MMAP_MIN_ADDR);
+#else
+	mmap_min_addr = dac_mmap_min_addr;
+#endif
+}
+
+/*
+ * sysctl handler which just sets dac_mmap_min_addr = the new value and then
+ * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly
+ */
+int mmap_min_addr_handler(const struct ctl_table *table, int write,
+			  void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	if (write && !capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+
+	update_mmap_min_addr();
+
+	return ret;
+}
+
+static const struct ctl_table min_addr_sysctl_table[] = {
+	{
+		.procname	= "mmap_min_addr",
+		.data		= &dac_mmap_min_addr,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= mmap_min_addr_handler,
+	},
+};
+
+static int __init mmap_min_addr_init(void)
+{
+	register_sysctl_init("vm", min_addr_sysctl_table);
+	update_mmap_min_addr();
+
+	return 0;
+}
+pure_initcall(mmap_min_addr_init);
diff --git a/security/safesetid/Kconfig b/security/safesetid/Kconfig
new file mode 100644
index 000000000..18b5fb904
--- /dev/null
+++ b/security/safesetid/Kconfig
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_SAFESETID
+        bool "Gate setid transitions to limit CAP_SET{U/G}ID capabilities"
+        depends on SECURITY
+        select SECURITYFS
+        default n
+        help
+          SafeSetID is an LSM module that gates the setid family of syscalls to
+          restrict UID/GID transitions from a given UID/GID to only those
+          approved by a system-wide whitelist. These restrictions also prohibit
+          the given UIDs/GIDs from obtaining auxiliary privileges associated
+          with CAP_SET{U/G}ID, such as allowing a user to set up user namespace
+          UID mappings.
+
+          If you are unsure how to answer this question, answer N.
diff --git a/security/safesetid/Makefile b/security/safesetid/Makefile
new file mode 100644
index 000000000..6b0660321
--- /dev/null
+++ b/security/safesetid/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the safesetid LSM.
+#
+
+obj-$(CONFIG_SECURITY_SAFESETID) := safesetid.o
+safesetid-y := lsm.o securityfs.o
diff --git a/security/safesetid/lsm.c b/security/safesetid/lsm.c
new file mode 100644
index 000000000..d5fb94905
--- /dev/null
+++ b/security/safesetid/lsm.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SafeSetID Linux Security Module
+ *
+ * Author: Micah Morton <mortonm@chromium.org>
+ *
+ * Copyright (C) 2018 The Chromium OS Authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define pr_fmt(fmt) "SafeSetID: " fmt
+
+#include <linux/lsm_hooks.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/sched/task_stack.h>
+#include <linux/security.h>
+#include <uapi/linux/lsm.h>
+#include "lsm.h"
+
+/* Flag indicating whether initialization completed */
+int safesetid_initialized __initdata;
+
+struct setid_ruleset __rcu *safesetid_setuid_rules;
+struct setid_ruleset __rcu *safesetid_setgid_rules;
+
+
+/* Compute a decision for a transition from @src to @dst under @policy. */
+enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy,
+		kid_t src, kid_t dst)
+{
+	struct setid_rule *rule;
+	enum sid_policy_type result = SIDPOL_DEFAULT;
+
+	if (policy->type == UID) {
+		hash_for_each_possible(policy->rules, rule, next, __kuid_val(src.uid)) {
+			if (!uid_eq(rule->src_id.uid, src.uid))
+				continue;
+			if (uid_eq(rule->dst_id.uid, dst.uid))
+				return SIDPOL_ALLOWED;
+			result = SIDPOL_CONSTRAINED;
+		}
+	} else if (policy->type == GID) {
+		hash_for_each_possible(policy->rules, rule, next, __kgid_val(src.gid)) {
+			if (!gid_eq(rule->src_id.gid, src.gid))
+				continue;
+			if (gid_eq(rule->dst_id.gid, dst.gid)){
+				return SIDPOL_ALLOWED;
+			}
+			result = SIDPOL_CONSTRAINED;
+		}
+	} else {
+		/* Should not reach here, report the ID as contrainsted */
+		result = SIDPOL_CONSTRAINED;
+	}
+	return result;
+}
+
+/*
+ * Compute a decision for a transition from @src to @dst under the active
+ * policy.
+ */
+static enum sid_policy_type setid_policy_lookup(kid_t src, kid_t dst, enum setid_type new_type)
+{
+	enum sid_policy_type result = SIDPOL_DEFAULT;
+	struct setid_ruleset *pol;
+
+	rcu_read_lock();
+	if (new_type == UID)
+		pol = rcu_dereference(safesetid_setuid_rules);
+	else if (new_type == GID)
+		pol = rcu_dereference(safesetid_setgid_rules);
+	else { /* Should not reach here */
+		result = SIDPOL_CONSTRAINED;
+		rcu_read_unlock();
+		return result;
+	}
+
+	if (pol) {
+		pol->type = new_type;
+		result = _setid_policy_lookup(pol, src, dst);
+	}
+	rcu_read_unlock();
+	return result;
+}
+
+static int safesetid_security_capable(const struct cred *cred,
+				      struct user_namespace *ns,
+				      int cap,
+				      unsigned int opts)
+{
+	/* We're only interested in CAP_SETUID and CAP_SETGID. */
+	if (cap != CAP_SETUID && cap != CAP_SETGID)
+		return 0;
+
+	/*
+	 * If CAP_SET{U/G}ID is currently used for a setid or setgroups syscall, we
+	 * want to let it go through here; the real security check happens later, in
+	 * the task_fix_set{u/g}id or task_fix_setgroups hooks.
+	 */
+	if ((opts & CAP_OPT_INSETID) != 0)
+		return 0;
+
+	switch (cap) {
+	case CAP_SETUID:
+		/*
+		* If no policy applies to this task, allow the use of CAP_SETUID for
+		* other purposes.
+		*/
+		if (setid_policy_lookup((kid_t){.uid = cred->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT)
+			return 0;
+		/*
+		 * Reject use of CAP_SETUID for functionality other than calling
+		 * set*uid() (e.g. setting up userns uid mappings).
+		 */
+		pr_warn("Operation requires CAP_SETUID, which is not available to UID %u for operations besides approved set*uid transitions\n",
+			__kuid_val(cred->uid));
+		return -EPERM;
+	case CAP_SETGID:
+		/*
+		* If no policy applies to this task, allow the use of CAP_SETGID for
+		* other purposes.
+		*/
+		if (setid_policy_lookup((kid_t){.gid = cred->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
+			return 0;
+		/*
+		 * Reject use of CAP_SETUID for functionality other than calling
+		 * set*gid() (e.g. setting up userns gid mappings).
+		 */
+		pr_warn("Operation requires CAP_SETGID, which is not available to GID %u for operations besides approved set*gid transitions\n",
+			__kgid_val(cred->gid));
+		return -EPERM;
+	default:
+		/* Error, the only capabilities were checking for is CAP_SETUID/GID */
+		return 0;
+	}
+	return 0;
+}
+
+/*
+ * Check whether a caller with old credentials @old is allowed to switch to
+ * credentials that contain @new_id.
+ */
+static bool id_permitted_for_cred(const struct cred *old, kid_t new_id, enum setid_type new_type)
+{
+	bool permitted;
+
+	/* If our old creds already had this ID in it, it's fine. */
+	if (new_type == UID) {
+		if (uid_eq(new_id.uid, old->uid) || uid_eq(new_id.uid, old->euid) ||
+			uid_eq(new_id.uid, old->suid))
+			return true;
+	} else if (new_type == GID){
+		if (gid_eq(new_id.gid, old->gid) || gid_eq(new_id.gid, old->egid) ||
+			gid_eq(new_id.gid, old->sgid))
+			return true;
+	} else /* Error, new_type is an invalid type */
+		return false;
+
+	/*
+	 * Transitions to new UIDs require a check against the policy of the old
+	 * RUID.
+	 */
+	permitted =
+	    setid_policy_lookup((kid_t){.uid = old->uid}, new_id, new_type) != SIDPOL_CONSTRAINED;
+
+	if (!permitted) {
+		if (new_type == UID) {
+			pr_warn("UID transition ((%d,%d,%d) -> %d) blocked\n",
+				__kuid_val(old->uid), __kuid_val(old->euid),
+				__kuid_val(old->suid), __kuid_val(new_id.uid));
+		} else if (new_type == GID) {
+			pr_warn("GID transition ((%d,%d,%d) -> %d) blocked\n",
+				__kgid_val(old->gid), __kgid_val(old->egid),
+				__kgid_val(old->sgid), __kgid_val(new_id.gid));
+		} else /* Error, new_type is an invalid type */
+			return false;
+	}
+	return permitted;
+}
+
+/*
+ * Check whether there is either an exception for user under old cred struct to
+ * set*uid to user under new cred struct, or the UID transition is allowed (by
+ * Linux set*uid rules) even without CAP_SETUID.
+ */
+static int safesetid_task_fix_setuid(struct cred *new,
+				     const struct cred *old,
+				     int flags)
+{
+
+	/* Do nothing if there are no setuid restrictions for our old RUID. */
+	if (setid_policy_lookup((kid_t){.uid = old->uid}, INVALID_ID, UID) == SIDPOL_DEFAULT)
+		return 0;
+
+	if (id_permitted_for_cred(old, (kid_t){.uid = new->uid}, UID) &&
+	    id_permitted_for_cred(old, (kid_t){.uid = new->euid}, UID) &&
+	    id_permitted_for_cred(old, (kid_t){.uid = new->suid}, UID) &&
+	    id_permitted_for_cred(old, (kid_t){.uid = new->fsuid}, UID))
+		return 0;
+
+	/*
+	 * Kill this process to avoid potential security vulnerabilities
+	 * that could arise from a missing allowlist entry preventing a
+	 * privileged process from dropping to a lesser-privileged one.
+	 */
+	force_sig(SIGKILL);
+	return -EACCES;
+}
+
+static int safesetid_task_fix_setgid(struct cred *new,
+				     const struct cred *old,
+				     int flags)
+{
+
+	/* Do nothing if there are no setgid restrictions for our old RGID. */
+	if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
+		return 0;
+
+	if (id_permitted_for_cred(old, (kid_t){.gid = new->gid}, GID) &&
+	    id_permitted_for_cred(old, (kid_t){.gid = new->egid}, GID) &&
+	    id_permitted_for_cred(old, (kid_t){.gid = new->sgid}, GID) &&
+	    id_permitted_for_cred(old, (kid_t){.gid = new->fsgid}, GID))
+		return 0;
+
+	/*
+	 * Kill this process to avoid potential security vulnerabilities
+	 * that could arise from a missing allowlist entry preventing a
+	 * privileged process from dropping to a lesser-privileged one.
+	 */
+	force_sig(SIGKILL);
+	return -EACCES;
+}
+
+static int safesetid_task_fix_setgroups(struct cred *new, const struct cred *old)
+{
+	int i;
+
+	/* Do nothing if there are no setgid restrictions for our old RGID. */
+	if (setid_policy_lookup((kid_t){.gid = old->gid}, INVALID_ID, GID) == SIDPOL_DEFAULT)
+		return 0;
+
+	get_group_info(new->group_info);
+	for (i = 0; i < new->group_info->ngroups; i++) {
+		if (!id_permitted_for_cred(old, (kid_t){.gid = new->group_info->gid[i]}, GID)) {
+			put_group_info(new->group_info);
+			/*
+			 * Kill this process to avoid potential security vulnerabilities
+			 * that could arise from a missing allowlist entry preventing a
+			 * privileged process from dropping to a lesser-privileged one.
+			 */
+			force_sig(SIGKILL);
+			return -EACCES;
+		}
+	}
+
+	put_group_info(new->group_info);
+	return 0;
+}
+
+static const struct lsm_id safesetid_lsmid = {
+	.name = "safesetid",
+	.id = LSM_ID_SAFESETID,
+};
+
+static struct security_hook_list safesetid_security_hooks[] = {
+	LSM_HOOK_INIT(task_fix_setuid, safesetid_task_fix_setuid),
+	LSM_HOOK_INIT(task_fix_setgid, safesetid_task_fix_setgid),
+	LSM_HOOK_INIT(task_fix_setgroups, safesetid_task_fix_setgroups),
+	LSM_HOOK_INIT(capable, safesetid_security_capable)
+};
+
+static int __init safesetid_security_init(void)
+{
+	security_add_hooks(safesetid_security_hooks,
+			   ARRAY_SIZE(safesetid_security_hooks),
+			   &safesetid_lsmid);
+
+	/* Report that SafeSetID successfully initialized */
+	safesetid_initialized = 1;
+
+	return 0;
+}
+
+DEFINE_LSM(safesetid_security_init) = {
+	.id = &safesetid_lsmid,
+	.init = safesetid_security_init,
+	.initcall_fs = safesetid_init_securityfs,
+};
diff --git a/security/safesetid/lsm.h b/security/safesetid/lsm.h
new file mode 100644
index 000000000..bf5172e2c
--- /dev/null
+++ b/security/safesetid/lsm.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * SafeSetID Linux Security Module
+ *
+ * Author: Micah Morton <mortonm@chromium.org>
+ *
+ * Copyright (C) 2018 The Chromium OS Authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+#ifndef _SAFESETID_H
+#define _SAFESETID_H
+
+#include <linux/types.h>
+#include <linux/uidgid.h>
+#include <linux/hashtable.h>
+
+/* Flag indicating whether initialization completed */
+extern int safesetid_initialized __initdata;
+
+enum sid_policy_type {
+	SIDPOL_DEFAULT, /* source ID is unaffected by policy */
+	SIDPOL_CONSTRAINED, /* source ID is affected by policy */
+	SIDPOL_ALLOWED /* target ID explicitly allowed */
+};
+
+typedef union {
+	kuid_t uid;
+	kgid_t gid;
+} kid_t;
+
+enum setid_type {
+	UID,
+	GID
+};
+
+/*
+ * Hash table entry to store safesetid policy signifying that 'src_id'
+ * can set*id to 'dst_id'.
+ */
+struct setid_rule {
+	struct hlist_node next;
+	kid_t src_id;
+	kid_t dst_id;
+
+	/* Flag to signal if rule is for UID's or GID's */
+	enum setid_type type;
+};
+
+#define SETID_HASH_BITS 8 /* 256 buckets in hash table */
+
+/* Extension of INVALID_UID/INVALID_GID for kid_t type */
+#define INVALID_ID (kid_t){.uid = INVALID_UID}
+
+struct setid_ruleset {
+	DECLARE_HASHTABLE(rules, SETID_HASH_BITS);
+	char *policy_str;
+	struct rcu_head rcu;
+
+	//Flag to signal if ruleset is for UID's or GID's
+	enum setid_type type;
+};
+
+enum sid_policy_type _setid_policy_lookup(struct setid_ruleset *policy,
+		kid_t src, kid_t dst);
+
+extern struct setid_ruleset __rcu *safesetid_setuid_rules;
+extern struct setid_ruleset __rcu *safesetid_setgid_rules;
+
+int safesetid_init_securityfs(void);
+
+#endif /* _SAFESETID_H */
diff --git a/security/safesetid/securityfs.c b/security/safesetid/securityfs.c
new file mode 100644
index 000000000..a71e54806
--- /dev/null
+++ b/security/safesetid/securityfs.c
@@ -0,0 +1,347 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * SafeSetID Linux Security Module
+ *
+ * Author: Micah Morton <mortonm@chromium.org>
+ *
+ * Copyright (C) 2018 The Chromium OS Authors.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2, as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define pr_fmt(fmt) "SafeSetID: " fmt
+
+#include <linux/security.h>
+#include <linux/cred.h>
+
+#include "lsm.h"
+
+static DEFINE_MUTEX(uid_policy_update_lock);
+static DEFINE_MUTEX(gid_policy_update_lock);
+
+/*
+ * In the case the input buffer contains one or more invalid IDs, the kid_t
+ * variables pointed to by @parent and @child will get updated but this
+ * function will return an error.
+ * Contents of @buf may be modified.
+ */
+static int parse_policy_line(struct file *file, char *buf,
+	struct setid_rule *rule)
+{
+	char *child_str;
+	int ret;
+	u32 parsed_parent, parsed_child;
+
+	/* Format of |buf| string should be <UID>:<UID> or <GID>:<GID> */
+	child_str = strchr(buf, ':');
+	if (child_str == NULL)
+		return -EINVAL;
+	*child_str = '\0';
+	child_str++;
+
+	ret = kstrtou32(buf, 0, &parsed_parent);
+	if (ret)
+		return ret;
+
+	ret = kstrtou32(child_str, 0, &parsed_child);
+	if (ret)
+		return ret;
+
+	if (rule->type == UID){
+		rule->src_id.uid = make_kuid(file->f_cred->user_ns, parsed_parent);
+		rule->dst_id.uid = make_kuid(file->f_cred->user_ns, parsed_child);
+		if (!uid_valid(rule->src_id.uid) || !uid_valid(rule->dst_id.uid))
+			return -EINVAL;
+	} else if (rule->type == GID){
+		rule->src_id.gid = make_kgid(file->f_cred->user_ns, parsed_parent);
+		rule->dst_id.gid = make_kgid(file->f_cred->user_ns, parsed_child);
+		if (!gid_valid(rule->src_id.gid) || !gid_valid(rule->dst_id.gid))
+			return -EINVAL;
+	} else {
+		/* Error, rule->type is an invalid type */
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void __release_ruleset(struct rcu_head *rcu)
+{
+	struct setid_ruleset *pol =
+		container_of(rcu, struct setid_ruleset, rcu);
+	int bucket;
+	struct setid_rule *rule;
+	struct hlist_node *tmp;
+
+	hash_for_each_safe(pol->rules, bucket, tmp, rule, next)
+		kfree(rule);
+	kfree(pol->policy_str);
+	kfree(pol);
+}
+
+static void release_ruleset(struct setid_ruleset *pol){
+	call_rcu(&pol->rcu, __release_ruleset);
+}
+
+static void insert_rule(struct setid_ruleset *pol, struct setid_rule *rule)
+{
+	if (pol->type == UID)
+		hash_add(pol->rules, &rule->next, __kuid_val(rule->src_id.uid));
+	else if (pol->type == GID)
+		hash_add(pol->rules, &rule->next, __kgid_val(rule->src_id.gid));
+	else /* Error, pol->type is neither UID or GID */
+		return;
+}
+
+static int verify_ruleset(struct setid_ruleset *pol)
+{
+	int bucket;
+	struct setid_rule *rule, *nrule;
+	int res = 0;
+
+	hash_for_each(pol->rules, bucket, rule, next) {
+		if (_setid_policy_lookup(pol, rule->dst_id, INVALID_ID) == SIDPOL_DEFAULT) {
+			if (pol->type == UID) {
+				pr_warn("insecure policy detected: uid %d is constrained but transitively unconstrained through uid %d\n",
+					__kuid_val(rule->src_id.uid),
+					__kuid_val(rule->dst_id.uid));
+			} else if (pol->type == GID) {
+				pr_warn("insecure policy detected: gid %d is constrained but transitively unconstrained through gid %d\n",
+					__kgid_val(rule->src_id.gid),
+					__kgid_val(rule->dst_id.gid));
+			} else { /* pol->type is an invalid type */
+				res = -EINVAL;
+				return res;
+			}
+			res = -EINVAL;
+
+			/* fix it up */
+			nrule = kmalloc_obj(struct setid_rule);
+			if (!nrule)
+				return -ENOMEM;
+			if (pol->type == UID){
+				nrule->src_id.uid = rule->dst_id.uid;
+				nrule->dst_id.uid = rule->dst_id.uid;
+				nrule->type = UID;
+			} else { /* pol->type must be GID if we've made it to here */
+				nrule->src_id.gid = rule->dst_id.gid;
+				nrule->dst_id.gid = rule->dst_id.gid;
+				nrule->type = GID;
+			}
+			insert_rule(pol, nrule);
+		}
+	}
+	return res;
+}
+
+static ssize_t handle_policy_update(struct file *file,
+				    const char __user *ubuf, size_t len, enum setid_type policy_type)
+{
+	struct setid_ruleset *pol;
+	char *buf, *p, *end;
+	int err;
+
+	if (len >= KMALLOC_MAX_SIZE)
+		return -EINVAL;
+
+	pol = kmalloc_obj(struct setid_ruleset);
+	if (!pol)
+		return -ENOMEM;
+	pol->policy_str = NULL;
+	pol->type = policy_type;
+	hash_init(pol->rules);
+
+	p = buf = memdup_user_nul(ubuf, len);
+	if (IS_ERR(buf)) {
+		err = PTR_ERR(buf);
+		goto out_free_pol;
+	}
+	pol->policy_str = kstrdup(buf, GFP_KERNEL);
+	if (pol->policy_str == NULL) {
+		err = -ENOMEM;
+		goto out_free_buf;
+	}
+
+	/* policy lines, including the last one, end with \n */
+	while (*p != '\0') {
+		struct setid_rule *rule;
+
+		end = strchr(p, '\n');
+		if (end == NULL) {
+			err = -EINVAL;
+			goto out_free_buf;
+		}
+		*end = '\0';
+
+		rule = kmalloc_obj(struct setid_rule);
+		if (!rule) {
+			err = -ENOMEM;
+			goto out_free_buf;
+		}
+
+		rule->type = policy_type;
+		err = parse_policy_line(file, p, rule);
+		if (err)
+			goto out_free_rule;
+
+		if (_setid_policy_lookup(pol, rule->src_id, rule->dst_id) == SIDPOL_ALLOWED) {
+			pr_warn("bad policy: duplicate entry\n");
+			err = -EEXIST;
+			goto out_free_rule;
+		}
+
+		insert_rule(pol, rule);
+		p = end + 1;
+		continue;
+
+out_free_rule:
+		kfree(rule);
+		goto out_free_buf;
+	}
+
+	err = verify_ruleset(pol);
+	/* bogus policy falls through after fixing it up */
+	if (err && err != -EINVAL)
+		goto out_free_buf;
+
+	/*
+	 * Everything looks good, apply the policy and release the old one.
+	 * What we really want here is an xchg() wrapper for RCU, but since that
+	 * doesn't currently exist, just use a spinlock for now.
+	 */
+	if (policy_type == UID) {
+		mutex_lock(&uid_policy_update_lock);
+		pol = rcu_replace_pointer(safesetid_setuid_rules, pol,
+					  lockdep_is_held(&uid_policy_update_lock));
+		mutex_unlock(&uid_policy_update_lock);
+	} else if (policy_type == GID) {
+		mutex_lock(&gid_policy_update_lock);
+		pol = rcu_replace_pointer(safesetid_setgid_rules, pol,
+					  lockdep_is_held(&gid_policy_update_lock));
+		mutex_unlock(&gid_policy_update_lock);
+	} else {
+		/* Error, policy type is neither UID or GID */
+		pr_warn("error: bad policy type");
+	}
+	err = len;
+
+out_free_buf:
+	kfree(buf);
+out_free_pol:
+	if (pol)
+		release_ruleset(pol);
+	return err;
+}
+
+static ssize_t safesetid_uid_file_write(struct file *file,
+				    const char __user *buf,
+				    size_t len,
+				    loff_t *ppos)
+{
+	if (!file_ns_capable(file, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (*ppos != 0)
+		return -EINVAL;
+
+	return handle_policy_update(file, buf, len, UID);
+}
+
+static ssize_t safesetid_gid_file_write(struct file *file,
+				    const char __user *buf,
+				    size_t len,
+				    loff_t *ppos)
+{
+	if (!file_ns_capable(file, &init_user_ns, CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (*ppos != 0)
+		return -EINVAL;
+
+	return handle_policy_update(file, buf, len, GID);
+}
+
+static ssize_t safesetid_file_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *ppos, struct mutex *policy_update_lock, struct __rcu setid_ruleset* ruleset)
+{
+	ssize_t res = 0;
+	struct setid_ruleset *pol;
+	const char *kbuf;
+
+	mutex_lock(policy_update_lock);
+	pol = rcu_dereference_protected(ruleset, lockdep_is_held(policy_update_lock));
+	if (pol) {
+		kbuf = pol->policy_str;
+		res = simple_read_from_buffer(buf, len, ppos,
+					      kbuf, strlen(kbuf));
+	}
+	mutex_unlock(policy_update_lock);
+
+	return res;
+}
+
+static ssize_t safesetid_uid_file_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *ppos)
+{
+	return safesetid_file_read(file, buf, len, ppos,
+				   &uid_policy_update_lock, safesetid_setuid_rules);
+}
+
+static ssize_t safesetid_gid_file_read(struct file *file, char __user *buf,
+				   size_t len, loff_t *ppos)
+{
+	return safesetid_file_read(file, buf, len, ppos,
+				   &gid_policy_update_lock, safesetid_setgid_rules);
+}
+
+
+
+static const struct file_operations safesetid_uid_file_fops = {
+	.read = safesetid_uid_file_read,
+	.write = safesetid_uid_file_write,
+};
+
+static const struct file_operations safesetid_gid_file_fops = {
+	.read = safesetid_gid_file_read,
+	.write = safesetid_gid_file_write,
+};
+
+int __init safesetid_init_securityfs(void)
+{
+	int ret;
+	struct dentry *policy_dir;
+	struct dentry *uid_policy_file;
+	struct dentry *gid_policy_file;
+
+	if (!safesetid_initialized)
+		return 0;
+
+	policy_dir = securityfs_create_dir("safesetid", NULL);
+	if (IS_ERR(policy_dir)) {
+		ret = PTR_ERR(policy_dir);
+		goto error;
+	}
+
+	uid_policy_file = securityfs_create_file("uid_allowlist_policy", 0600,
+			policy_dir, NULL, &safesetid_uid_file_fops);
+	if (IS_ERR(uid_policy_file)) {
+		ret = PTR_ERR(uid_policy_file);
+		goto error;
+	}
+
+	gid_policy_file = securityfs_create_file("gid_allowlist_policy", 0600,
+			policy_dir, NULL, &safesetid_gid_file_fops);
+	if (IS_ERR(gid_policy_file)) {
+		ret = PTR_ERR(gid_policy_file);
+		goto error;
+	}
+
+
+	return 0;
+
+error:
+	securityfs_remove(policy_dir);
+	return ret;
+}
diff --git a/security/security.c b/security/security.c
new file mode 100644
index 000000000..2ee276ab1
--- /dev/null
+++ b/security/security.c
@@ -0,0 +1,5717 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Security plug functions
+ *
+ * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com>
+ * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com>
+ * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com>
+ * Copyright (C) 2016 Mellanox Technologies
+ * Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com>
+ */
+
+#define pr_fmt(fmt) "LSM: " fmt
+
+#include <linux/bpf.h>
+#include <linux/capability.h>
+#include <linux/dcache.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
+#include <linux/lsm_hooks.h>
+#include <linux/mman.h>
+#include <linux/mount.h>
+#include <linux/personality.h>
+#include <linux/backing-dev.h>
+#include <linux/string.h>
+#include <linux/xattr.h>
+#include <linux/msg.h>
+#include <linux/overflow.h>
+#include <linux/perf_event.h>
+#include <linux/fs.h>
+#include <net/flow.h>
+#include <net/sock.h>
+
+#include "lsm.h"
+
+/*
+ * These are descriptions of the reasons that can be passed to the
+ * security_locked_down() LSM hook. Placing this array here allows
+ * all security modules to use the same descriptions for auditing
+ * purposes.
+ */
+const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = {
+	[LOCKDOWN_NONE] = "none",
+	[LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading",
+	[LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port",
+	[LOCKDOWN_EFI_TEST] = "/dev/efi_test access",
+	[LOCKDOWN_KEXEC] = "kexec of unsigned images",
+	[LOCKDOWN_HIBERNATION] = "hibernation",
+	[LOCKDOWN_PCI_ACCESS] = "direct PCI access",
+	[LOCKDOWN_IOPORT] = "raw io port access",
+	[LOCKDOWN_MSR] = "raw MSR access",
+	[LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables",
+	[LOCKDOWN_DEVICE_TREE] = "modifying device tree contents",
+	[LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage",
+	[LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO",
+	[LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters",
+	[LOCKDOWN_MMIOTRACE] = "unsafe mmio",
+	[LOCKDOWN_DEBUGFS] = "debugfs access",
+	[LOCKDOWN_XMON_WR] = "xmon write access",
+	[LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM",
+	[LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM",
+	[LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection",
+	[LOCKDOWN_XEN_USER_ACTIONS] = "Xen guest user action",
+	[LOCKDOWN_INTEGRITY_MAX] = "integrity",
+	[LOCKDOWN_KCORE] = "/proc/kcore access",
+	[LOCKDOWN_KPROBES] = "use of kprobes",
+	[LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM",
+	[LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM",
+	[LOCKDOWN_PERF] = "unsafe use of perf",
+	[LOCKDOWN_TRACEFS] = "use of tracefs",
+	[LOCKDOWN_XMON_RW] = "xmon read and write access",
+	[LOCKDOWN_XFRM_SECRET] = "xfrm SA secret",
+	[LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality",
+};
+
+bool lsm_debug __ro_after_init;
+
+unsigned int lsm_active_cnt __ro_after_init;
+const struct lsm_id *lsm_idlist[MAX_LSM_COUNT];
+
+struct lsm_blob_sizes blob_sizes;
+
+struct kmem_cache *lsm_file_cache;
+struct kmem_cache *lsm_backing_file_cache;
+struct kmem_cache *lsm_inode_cache;
+
+#define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX
+
+/*
+ * Identifier for the LSM static calls.
+ * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h
+ * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT
+ */
+#define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX
+
+/*
+ * Call the macro M for each LSM hook MAX_LSM_COUNT times.
+ */
+#define LSM_LOOP_UNROLL(M, ...) 		\
+do {						\
+	UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__)	\
+} while (0)
+
+#define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__)
+
+#ifdef CONFIG_HAVE_STATIC_CALL
+#define LSM_HOOK_TRAMP(NAME, NUM) \
+	&STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM))
+#else
+#define LSM_HOOK_TRAMP(NAME, NUM) NULL
+#endif
+
+/*
+ * Define static calls and static keys for each LSM hook.
+ */
+#define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...)			\
+	DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM),		\
+				*((RET(*)(__VA_ARGS__))NULL));		\
+	static DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM));
+
+#define LSM_HOOK(RET, DEFAULT, NAME, ...)				\
+	LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__)
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+#undef DEFINE_LSM_STATIC_CALL
+
+/*
+ * Initialise a table of static calls for each LSM hook.
+ * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY)
+ * and a trampoline (STATIC_CALL_TRAMP) which are used to call
+ * __static_call_update when updating the static call.
+ *
+ * The static calls table is used by early LSMs, some architectures can fault on
+ * unaligned accesses and the fault handling code may not be ready by then.
+ * Thus, the static calls table should be aligned to avoid any unhandled faults
+ * in early init.
+ */
+struct lsm_static_calls_table
+	static_calls_table __ro_after_init __aligned(sizeof(u64)) = {
+#define INIT_LSM_STATIC_CALL(NUM, NAME)					\
+	(struct lsm_static_call) {					\
+		.key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)),	\
+		.trampoline = LSM_HOOK_TRAMP(NAME, NUM),		\
+		.active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM),		\
+	},
+#define LSM_HOOK(RET, DEFAULT, NAME, ...)				\
+	.NAME = {							\
+		LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME)		\
+	},
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+#undef INIT_LSM_STATIC_CALL
+	};
+
+/**
+ * lsm_file_alloc - allocate a composite file blob
+ * @file: the file that needs a blob
+ *
+ * Allocate the file blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_file_alloc(struct file *file)
+{
+	if (!lsm_file_cache) {
+		file->f_security = NULL;
+		return 0;
+	}
+
+	file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL);
+	if (file->f_security == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * lsm_backing_file_alloc - allocate a composite backing file blob
+ * @backing_file: the backing file
+ *
+ * Allocate the backing file blob for all the modules.
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_backing_file_alloc(struct file *backing_file)
+{
+	void *blob;
+
+	if (!lsm_backing_file_cache) {
+		backing_file_set_security(backing_file, NULL);
+		return 0;
+	}
+
+	blob = kmem_cache_zalloc(lsm_backing_file_cache, GFP_KERNEL);
+	backing_file_set_security(backing_file, blob);
+	if (!blob)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * lsm_blob_alloc - allocate a composite blob
+ * @dest: the destination for the blob
+ * @size: the size of the blob
+ * @gfp: allocation type
+ *
+ * Allocate a blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp)
+{
+	if (size == 0) {
+		*dest = NULL;
+		return 0;
+	}
+
+	*dest = kzalloc(size, gfp);
+	if (*dest == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * lsm_cred_alloc - allocate a composite cred blob
+ * @cred: the cred that needs a blob
+ * @gfp: allocation type
+ *
+ * Allocate the cred blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+int lsm_cred_alloc(struct cred *cred, gfp_t gfp)
+{
+	return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp);
+}
+
+/**
+ * lsm_inode_alloc - allocate a composite inode blob
+ * @inode: the inode that needs a blob
+ * @gfp: allocation flags
+ *
+ * Allocate the inode blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_inode_alloc(struct inode *inode, gfp_t gfp)
+{
+	if (!lsm_inode_cache) {
+		inode->i_security = NULL;
+		return 0;
+	}
+
+	inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp);
+	if (inode->i_security == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+/**
+ * lsm_task_alloc - allocate a composite task blob
+ * @task: the task that needs a blob
+ *
+ * Allocate the task blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+int lsm_task_alloc(struct task_struct *task)
+{
+	return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL);
+}
+
+/**
+ * lsm_ipc_alloc - allocate a composite ipc blob
+ * @kip: the ipc that needs a blob
+ *
+ * Allocate the ipc blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_ipc_alloc(struct kern_ipc_perm *kip)
+{
+	return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL);
+}
+
+#ifdef CONFIG_KEYS
+/**
+ * lsm_key_alloc - allocate a composite key blob
+ * @key: the key that needs a blob
+ *
+ * Allocate the key blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_key_alloc(struct key *key)
+{
+	return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL);
+}
+#endif /* CONFIG_KEYS */
+
+/**
+ * lsm_msg_msg_alloc - allocate a composite msg_msg blob
+ * @mp: the msg_msg that needs a blob
+ *
+ * Allocate the ipc blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_msg_msg_alloc(struct msg_msg *mp)
+{
+	return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg,
+			      GFP_KERNEL);
+}
+
+/**
+ * lsm_bdev_alloc - allocate a composite block_device blob
+ * @bdev: the block_device that needs a blob
+ *
+ * Allocate the block_device blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_bdev_alloc(struct block_device *bdev)
+{
+	return lsm_blob_alloc(&bdev->bd_security, blob_sizes.lbs_bdev,
+			      GFP_KERNEL);
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+/**
+ * lsm_bpf_map_alloc - allocate a composite bpf_map blob
+ * @map: the bpf_map that needs a blob
+ *
+ * Allocate the bpf_map blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_bpf_map_alloc(struct bpf_map *map)
+{
+	return lsm_blob_alloc(&map->security, blob_sizes.lbs_bpf_map, GFP_KERNEL);
+}
+
+/**
+ * lsm_bpf_prog_alloc - allocate a composite bpf_prog blob
+ * @prog: the bpf_prog that needs a blob
+ *
+ * Allocate the bpf_prog blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_bpf_prog_alloc(struct bpf_prog *prog)
+{
+	return lsm_blob_alloc(&prog->aux->security, blob_sizes.lbs_bpf_prog, GFP_KERNEL);
+}
+
+/**
+ * lsm_bpf_token_alloc - allocate a composite bpf_token blob
+ * @token: the bpf_token that needs a blob
+ *
+ * Allocate the bpf_token blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_bpf_token_alloc(struct bpf_token *token)
+{
+	return lsm_blob_alloc(&token->security, blob_sizes.lbs_bpf_token, GFP_KERNEL);
+}
+#endif /* CONFIG_BPF_SYSCALL */
+
+/**
+ * lsm_superblock_alloc - allocate a composite superblock blob
+ * @sb: the superblock that needs a blob
+ *
+ * Allocate the superblock blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_superblock_alloc(struct super_block *sb)
+{
+	return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock,
+			      GFP_KERNEL);
+}
+
+/**
+ * lsm_fill_user_ctx - Fill a user space lsm_ctx structure
+ * @uctx: a userspace LSM context to be filled
+ * @uctx_len: available uctx size (input), used uctx size (output)
+ * @val: the new LSM context value
+ * @val_len: the size of the new LSM context value
+ * @id: LSM id
+ * @flags: LSM defined flags
+ *
+ * Fill all of the fields in a userspace lsm_ctx structure.  If @uctx is NULL
+ * simply calculate the required size to output via @utc_len and return
+ * success.
+ *
+ * Returns 0 on success, -E2BIG if userspace buffer is not large enough,
+ * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated.
+ */
+int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len,
+		      void *val, size_t val_len,
+		      u64 id, u64 flags)
+{
+	struct lsm_ctx *nctx = NULL;
+	size_t nctx_len;
+	int rc = 0;
+
+	nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *));
+	if (nctx_len > *uctx_len) {
+		rc = -E2BIG;
+		goto out;
+	}
+
+	/* no buffer - return success/0 and set @uctx_len to the req size */
+	if (!uctx)
+		goto out;
+
+	nctx = kzalloc(nctx_len, GFP_KERNEL);
+	if (nctx == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	nctx->id = id;
+	nctx->flags = flags;
+	nctx->len = nctx_len;
+	nctx->ctx_len = val_len;
+	memcpy(nctx->ctx, val, val_len);
+
+	if (copy_to_user(uctx, nctx, nctx_len))
+		rc = -EFAULT;
+
+out:
+	kfree(nctx);
+	*uctx_len = nctx_len;
+	return rc;
+}
+
+/*
+ * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and
+ * can be accessed with:
+ *
+ *	LSM_RET_DEFAULT(<hook_name>)
+ *
+ * The macros below define static constants for the default value of each
+ * LSM hook.
+ */
+#define LSM_RET_DEFAULT(NAME) (NAME##_default)
+#define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME)
+#define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \
+	static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT);
+#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
+	DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME)
+
+#include <linux/lsm_hook_defs.h>
+#undef LSM_HOOK
+
+/*
+ * Hook list operation macros.
+ *
+ * call_void_hook:
+ *	This is a hook that does not return a value.
+ *
+ * call_int_hook:
+ *	This is a hook that returns a value.
+ */
+#define __CALL_STATIC_VOID(NUM, HOOK, ...)				     \
+do {									     \
+	if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) {    \
+		static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__);	     \
+	}								     \
+} while (0);
+
+#define call_void_hook(HOOK, ...)                                 \
+	do {                                                      \
+		LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \
+	} while (0)
+
+
+#define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...)			     \
+do {									     \
+	if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) {  \
+		R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__);    \
+		if (R != LSM_RET_DEFAULT(HOOK))				     \
+			goto LABEL;					     \
+	}								     \
+} while (0);
+
+#define call_int_hook(HOOK, ...)					\
+({									\
+	__label__ OUT;							\
+	int RC = LSM_RET_DEFAULT(HOOK);					\
+									\
+	LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__);	\
+OUT:									\
+	RC;								\
+})
+
+#define lsm_for_each_hook(scall, NAME)					\
+	for (scall = static_calls_table.NAME;				\
+	     scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++)  \
+		if (static_key_enabled(&scall->active->key))
+
+/* Security operations */
+
+/**
+ * security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok
+ * @mgr: task credentials of current binder process
+ *
+ * Check whether @mgr is allowed to be the binder context manager.
+ *
+ * Return: Return 0 if permission is granted.
+ */
+int security_binder_set_context_mgr(const struct cred *mgr)
+{
+	return call_int_hook(binder_set_context_mgr, mgr);
+}
+
+/**
+ * security_binder_transaction() - Check if a binder transaction is allowed
+ * @from: sending process
+ * @to: receiving process
+ *
+ * Check whether @from is allowed to invoke a binder transaction call to @to.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_binder_transaction(const struct cred *from,
+				const struct cred *to)
+{
+	return call_int_hook(binder_transaction, from, to);
+}
+
+/**
+ * security_binder_transfer_binder() - Check if a binder transfer is allowed
+ * @from: sending process
+ * @to: receiving process
+ *
+ * Check whether @from is allowed to transfer a binder reference to @to.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_binder_transfer_binder(const struct cred *from,
+				    const struct cred *to)
+{
+	return call_int_hook(binder_transfer_binder, from, to);
+}
+
+/**
+ * security_binder_transfer_file() - Check if a binder file xfer is allowed
+ * @from: sending process
+ * @to: receiving process
+ * @file: file being transferred
+ *
+ * Check whether @from is allowed to transfer @file to @to.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_binder_transfer_file(const struct cred *from,
+				  const struct cred *to, const struct file *file)
+{
+	return call_int_hook(binder_transfer_file, from, to, file);
+}
+
+/**
+ * security_ptrace_access_check() - Check if tracing is allowed
+ * @child: target process
+ * @mode: PTRACE_MODE flags
+ *
+ * Check permission before allowing the current process to trace the @child
+ * process.  Security modules may also want to perform a process tracing check
+ * during an execve in the set_security or apply_creds hooks of tracing check
+ * during an execve in the bprm_set_creds hook of binprm_security_ops if the
+ * process is being traced and its security attributes would be changed by the
+ * execve.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_ptrace_access_check(struct task_struct *child, unsigned int mode)
+{
+	return call_int_hook(ptrace_access_check, child, mode);
+}
+
+/**
+ * security_ptrace_traceme() - Check if tracing is allowed
+ * @parent: tracing process
+ *
+ * Check that the @parent process has sufficient permission to trace the
+ * current process before allowing the current process to present itself to the
+ * @parent process for tracing.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_ptrace_traceme(struct task_struct *parent)
+{
+	return call_int_hook(ptrace_traceme, parent);
+}
+
+/**
+ * security_capget() - Get the capability sets for a process
+ * @target: target process
+ * @effective: effective capability set
+ * @inheritable: inheritable capability set
+ * @permitted: permitted capability set
+ *
+ * Get the @effective, @inheritable, and @permitted capability sets for the
+ * @target process.  The hook may also perform permission checking to determine
+ * if the current process is allowed to see the capability sets of the @target
+ * process.
+ *
+ * Return: Returns 0 if the capability sets were successfully obtained.
+ */
+int security_capget(const struct task_struct *target,
+		    kernel_cap_t *effective,
+		    kernel_cap_t *inheritable,
+		    kernel_cap_t *permitted)
+{
+	return call_int_hook(capget, target, effective, inheritable, permitted);
+}
+
+/**
+ * security_capset() - Set the capability sets for a process
+ * @new: new credentials for the target process
+ * @old: current credentials of the target process
+ * @effective: effective capability set
+ * @inheritable: inheritable capability set
+ * @permitted: permitted capability set
+ *
+ * Set the @effective, @inheritable, and @permitted capability sets for the
+ * current process.
+ *
+ * Return: Returns 0 and update @new if permission is granted.
+ */
+int security_capset(struct cred *new, const struct cred *old,
+		    const kernel_cap_t *effective,
+		    const kernel_cap_t *inheritable,
+		    const kernel_cap_t *permitted)
+{
+	return call_int_hook(capset, new, old, effective, inheritable,
+			     permitted);
+}
+
+/**
+ * security_capable() - Check if a process has the necessary capability
+ * @cred: credentials to examine
+ * @ns: user namespace
+ * @cap: capability requested
+ * @opts: capability check options
+ *
+ * Check whether the @tsk process has the @cap capability in the indicated
+ * credentials.  @cap contains the capability <include/linux/capability.h>.
+ * @opts contains options for the capable check <include/linux/security.h>.
+ *
+ * Return: Returns 0 if the capability is granted.
+ */
+int security_capable(const struct cred *cred,
+		     struct user_namespace *ns,
+		     int cap,
+		     unsigned int opts)
+{
+	return call_int_hook(capable, cred, ns, cap, opts);
+}
+
+/**
+ * security_quotactl() - Check if a quotactl() syscall is allowed for this fs
+ * @cmds: commands
+ * @type: type
+ * @id: id
+ * @sb: filesystem
+ *
+ * Check whether the quotactl syscall is allowed for this @sb.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_quotactl(int cmds, int type, int id, const struct super_block *sb)
+{
+	return call_int_hook(quotactl, cmds, type, id, sb);
+}
+
+/**
+ * security_quota_on() - Check if QUOTAON is allowed for a dentry
+ * @dentry: dentry
+ *
+ * Check whether QUOTAON is allowed for @dentry.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_quota_on(struct dentry *dentry)
+{
+	return call_int_hook(quota_on, dentry);
+}
+
+/**
+ * security_syslog() - Check if accessing the kernel message ring is allowed
+ * @type: SYSLOG_ACTION_* type
+ *
+ * Check permission before accessing the kernel message ring or changing
+ * logging to the console.  See the syslog(2) manual page for an explanation of
+ * the @type values.
+ *
+ * Return: Return 0 if permission is granted.
+ */
+int security_syslog(int type)
+{
+	return call_int_hook(syslog, type);
+}
+
+/**
+ * security_settime64() - Check if changing the system time is allowed
+ * @ts: new time
+ * @tz: timezone
+ *
+ * Check permission to change the system time, struct timespec64 is defined in
+ * <include/linux/time64.h> and timezone is defined in <include/linux/time.h>.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_settime64(const struct timespec64 *ts, const struct timezone *tz)
+{
+	return call_int_hook(settime, ts, tz);
+}
+
+/**
+ * security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed
+ * @mm: mm struct
+ * @pages: number of pages
+ *
+ * Check permissions for allocating a new virtual mapping.  If all LSMs return
+ * a positive value, __vm_enough_memory() will be called with cap_sys_admin
+ * set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be
+ * called with cap_sys_admin cleared.
+ *
+ * Return: Returns 0 if permission is granted by the LSM infrastructure to the
+ *         caller.
+ */
+int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
+{
+	struct lsm_static_call *scall;
+	int cap_sys_admin = 1;
+	int rc;
+
+	/*
+	 * The module will respond with 0 if it thinks the __vm_enough_memory()
+	 * call should be made with the cap_sys_admin set. If all of the modules
+	 * agree that it should be set it will. If any module thinks it should
+	 * not be set it won't.
+	 */
+	lsm_for_each_hook(scall, vm_enough_memory) {
+		rc = scall->hl->hook.vm_enough_memory(mm, pages);
+		if (rc < 0) {
+			cap_sys_admin = 0;
+			break;
+		}
+	}
+	return __vm_enough_memory(mm, pages, cap_sys_admin);
+}
+
+/**
+ * security_bprm_creds_for_exec() - Prepare the credentials for exec()
+ * @bprm: binary program information
+ *
+ * If the setup in prepare_exec_creds did not setup @bprm->cred->security
+ * properly for executing @bprm->file, update the LSM's portion of
+ * @bprm->cred->security to be what commit_creds needs to install for the new
+ * program.  This hook may also optionally check permissions (e.g. for
+ * transitions between security domains).  The hook must set @bprm->secureexec
+ * to 1 if AT_SECURE should be set to request libc enable secure mode.  @bprm
+ * contains the linux_binprm structure.
+ *
+ * If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is
+ * set.  The result must be the same as without this flag even if the execution
+ * will never really happen and @bprm will always be dropped.
+ *
+ * This hook must not change current->cred, only @bprm->cred.
+ *
+ * Return: Returns 0 if the hook is successful and permission is granted.
+ */
+int security_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	return call_int_hook(bprm_creds_for_exec, bprm);
+}
+
+/**
+ * security_bprm_creds_from_file() - Update linux_binprm creds based on file
+ * @bprm: binary program information
+ * @file: associated file
+ *
+ * If @file is setpcap, suid, sgid or otherwise marked to change privilege upon
+ * exec, update @bprm->cred to reflect that change. This is called after
+ * finding the binary that will be executed without an interpreter.  This
+ * ensures that the credentials will not be derived from a script that the
+ * binary will need to reopen, which when reopend may end up being a completely
+ * different file.  This hook may also optionally check permissions (e.g. for
+ * transitions between security domains).  The hook must set @bprm->secureexec
+ * to 1 if AT_SECURE should be set to request libc enable secure mode.  The
+ * hook must add to @bprm->per_clear any personality flags that should be
+ * cleared from current->personality.  @bprm contains the linux_binprm
+ * structure.
+ *
+ * Return: Returns 0 if the hook is successful and permission is granted.
+ */
+int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file)
+{
+	return call_int_hook(bprm_creds_from_file, bprm, file);
+}
+
+/**
+ * security_bprm_check() - Mediate binary handler search
+ * @bprm: binary program information
+ *
+ * This hook mediates the point when a search for a binary handler will begin.
+ * It allows a check against the @bprm->cred->security value which was set in
+ * the preceding creds_for_exec call.  The argv list and envp list are reliably
+ * available in @bprm.  This hook may be called multiple times during a single
+ * execve.  @bprm contains the linux_binprm structure.
+ *
+ * Return: Returns 0 if the hook is successful and permission is granted.
+ */
+int security_bprm_check(struct linux_binprm *bprm)
+{
+	return call_int_hook(bprm_check_security, bprm);
+}
+
+/**
+ * security_bprm_committing_creds() - Install creds for a process during exec()
+ * @bprm: binary program information
+ *
+ * Prepare to install the new security attributes of a process being
+ * transformed by an execve operation, based on the old credentials pointed to
+ * by @current->cred and the information set in @bprm->cred by the
+ * bprm_creds_for_exec hook.  @bprm points to the linux_binprm structure.  This
+ * hook is a good place to perform state changes on the process such as closing
+ * open file descriptors to which access will no longer be granted when the
+ * attributes are changed.  This is called immediately before commit_creds().
+ */
+void security_bprm_committing_creds(const struct linux_binprm *bprm)
+{
+	call_void_hook(bprm_committing_creds, bprm);
+}
+
+/**
+ * security_bprm_committed_creds() - Tidy up after cred install during exec()
+ * @bprm: binary program information
+ *
+ * Tidy up after the installation of the new security attributes of a process
+ * being transformed by an execve operation.  The new credentials have, by this
+ * point, been set to @current->cred.  @bprm points to the linux_binprm
+ * structure.  This hook is a good place to perform state changes on the
+ * process such as clearing out non-inheritable signal state.  This is called
+ * immediately after commit_creds().
+ */
+void security_bprm_committed_creds(const struct linux_binprm *bprm)
+{
+	call_void_hook(bprm_committed_creds, bprm);
+}
+
+/**
+ * security_fs_context_submount() - Initialise fc->security
+ * @fc: new filesystem context
+ * @reference: dentry reference for submount/remount
+ *
+ * Fill out the ->security field for a new fs_context.
+ *
+ * Return: Returns 0 on success or negative error code on failure.
+ */
+int security_fs_context_submount(struct fs_context *fc, struct super_block *reference)
+{
+	return call_int_hook(fs_context_submount, fc, reference);
+}
+
+/**
+ * security_fs_context_dup() - Duplicate a fs_context LSM blob
+ * @fc: destination filesystem context
+ * @src_fc: source filesystem context
+ *
+ * Allocate and attach a security structure to sc->security.  This pointer is
+ * initialised to NULL by the caller.  @fc indicates the new filesystem context.
+ * @src_fc indicates the original filesystem context.
+ *
+ * Return: Returns 0 on success or a negative error code on failure.
+ */
+int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc)
+{
+	return call_int_hook(fs_context_dup, fc, src_fc);
+}
+
+/**
+ * security_fs_context_parse_param() - Configure a filesystem context
+ * @fc: filesystem context
+ * @param: filesystem parameter
+ *
+ * Userspace provided a parameter to configure a superblock.  The LSM can
+ * consume the parameter or return it to the caller for use elsewhere.
+ *
+ * Return: If the parameter is used by the LSM it should return 0, if it is
+ *         returned to the caller -ENOPARAM is returned, otherwise a negative
+ *         error code is returned.
+ */
+int security_fs_context_parse_param(struct fs_context *fc,
+				    struct fs_parameter *param)
+{
+	struct lsm_static_call *scall;
+	int trc;
+	int rc = -ENOPARAM;
+
+	lsm_for_each_hook(scall, fs_context_parse_param) {
+		trc = scall->hl->hook.fs_context_parse_param(fc, param);
+		if (trc == 0)
+			rc = 0;
+		else if (trc != -ENOPARAM)
+			return trc;
+	}
+	return rc;
+}
+
+/**
+ * security_sb_alloc() - Allocate a super_block LSM blob
+ * @sb: filesystem superblock
+ *
+ * Allocate and attach a security structure to the sb->s_security field.  The
+ * s_security field is initialized to NULL when the structure is allocated.
+ * @sb contains the super_block structure to be modified.
+ *
+ * Return: Returns 0 if operation was successful.
+ */
+int security_sb_alloc(struct super_block *sb)
+{
+	int rc = lsm_superblock_alloc(sb);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(sb_alloc_security, sb);
+	if (unlikely(rc))
+		security_sb_free(sb);
+	return rc;
+}
+
+/**
+ * security_sb_delete() - Release super_block LSM associated objects
+ * @sb: filesystem superblock
+ *
+ * Release objects tied to a superblock (e.g. inodes).  @sb contains the
+ * super_block structure being released.
+ */
+void security_sb_delete(struct super_block *sb)
+{
+	call_void_hook(sb_delete, sb);
+}
+
+/**
+ * security_sb_free() - Free a super_block LSM blob
+ * @sb: filesystem superblock
+ *
+ * Deallocate and clear the sb->s_security field.  @sb contains the super_block
+ * structure to be modified.
+ */
+void security_sb_free(struct super_block *sb)
+{
+	call_void_hook(sb_free_security, sb);
+	kfree(sb->s_security);
+	sb->s_security = NULL;
+}
+
+/**
+ * security_free_mnt_opts() - Free memory associated with mount options
+ * @mnt_opts: LSM processed mount options
+ *
+ * Free memory associated with @mnt_ops.
+ */
+void security_free_mnt_opts(void **mnt_opts)
+{
+	if (!*mnt_opts)
+		return;
+	call_void_hook(sb_free_mnt_opts, *mnt_opts);
+	*mnt_opts = NULL;
+}
+EXPORT_SYMBOL(security_free_mnt_opts);
+
+/**
+ * security_sb_eat_lsm_opts() - Consume LSM mount options
+ * @options: mount options
+ * @mnt_opts: LSM processed mount options
+ *
+ * Eat (scan @options) and save them in @mnt_opts.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_sb_eat_lsm_opts(char *options, void **mnt_opts)
+{
+	return call_int_hook(sb_eat_lsm_opts, options, mnt_opts);
+}
+EXPORT_SYMBOL(security_sb_eat_lsm_opts);
+
+/**
+ * security_sb_mnt_opts_compat() - Check if new mount options are allowed
+ * @sb: filesystem superblock
+ * @mnt_opts: new mount options
+ *
+ * Determine if the new mount options in @mnt_opts are allowed given the
+ * existing mounted filesystem at @sb.  @sb superblock being compared.
+ *
+ * Return: Returns 0 if options are compatible.
+ */
+int security_sb_mnt_opts_compat(struct super_block *sb,
+				void *mnt_opts)
+{
+	return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts);
+}
+EXPORT_SYMBOL(security_sb_mnt_opts_compat);
+
+/**
+ * security_sb_remount() - Verify no incompatible mount changes during remount
+ * @sb: filesystem superblock
+ * @mnt_opts: (re)mount options
+ *
+ * Extracts security system specific mount options and verifies no changes are
+ * being made to those options.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_remount(struct super_block *sb,
+			void *mnt_opts)
+{
+	return call_int_hook(sb_remount, sb, mnt_opts);
+}
+EXPORT_SYMBOL(security_sb_remount);
+
+/**
+ * security_sb_kern_mount() - Check if a kernel mount is allowed
+ * @sb: filesystem superblock
+ *
+ * Mount this @sb if allowed by permissions.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_kern_mount(const struct super_block *sb)
+{
+	return call_int_hook(sb_kern_mount, sb);
+}
+
+/**
+ * security_sb_show_options() - Output the mount options for a superblock
+ * @m: output file
+ * @sb: filesystem superblock
+ *
+ * Show (print on @m) mount options for this @sb.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_sb_show_options(struct seq_file *m, struct super_block *sb)
+{
+	return call_int_hook(sb_show_options, m, sb);
+}
+
+/**
+ * security_sb_statfs() - Check if accessing fs stats is allowed
+ * @dentry: superblock handle
+ *
+ * Check permission before obtaining filesystem statistics for the @mnt
+ * mountpoint.  @dentry is a handle on the superblock for the filesystem.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_statfs(struct dentry *dentry)
+{
+	return call_int_hook(sb_statfs, dentry);
+}
+
+/**
+ * security_sb_mount() - Check permission for mounting a filesystem
+ * @dev_name: filesystem backing device
+ * @path: mount point
+ * @type: filesystem type
+ * @flags: mount flags
+ * @data: filesystem specific data
+ *
+ * Check permission before an object specified by @dev_name is mounted on the
+ * mount point named by @nd.  For an ordinary mount, @dev_name identifies a
+ * device if the file system type requires a device.  For a remount
+ * (@flags & MS_REMOUNT), @dev_name is irrelevant.  For a loopback/bind mount
+ * (@flags & MS_BIND), @dev_name identifies the	pathname of the object being
+ * mounted.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_mount(const char *dev_name, const struct path *path,
+		      const char *type, unsigned long flags, void *data)
+{
+	return call_int_hook(sb_mount, dev_name, path, type, flags, data);
+}
+
+/**
+ * security_sb_umount() - Check permission for unmounting a filesystem
+ * @mnt: mounted filesystem
+ * @flags: unmount flags
+ *
+ * Check permission before the @mnt file system is unmounted.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_umount(struct vfsmount *mnt, int flags)
+{
+	return call_int_hook(sb_umount, mnt, flags);
+}
+
+/**
+ * security_sb_pivotroot() - Check permissions for pivoting the rootfs
+ * @old_path: new location for current rootfs
+ * @new_path: location of the new rootfs
+ *
+ * Check permission before pivoting the root filesystem.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sb_pivotroot(const struct path *old_path,
+			  const struct path *new_path)
+{
+	return call_int_hook(sb_pivotroot, old_path, new_path);
+}
+
+/**
+ * security_sb_set_mnt_opts() - Set the mount options for a filesystem
+ * @sb: filesystem superblock
+ * @mnt_opts: binary mount options
+ * @kern_flags: kernel flags (in)
+ * @set_kern_flags: kernel flags (out)
+ *
+ * Set the security relevant mount options used for a superblock.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_sb_set_mnt_opts(struct super_block *sb,
+			     void *mnt_opts,
+			     unsigned long kern_flags,
+			     unsigned long *set_kern_flags)
+{
+	struct lsm_static_call *scall;
+	int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts);
+
+	lsm_for_each_hook(scall, sb_set_mnt_opts) {
+		rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags,
+					      set_kern_flags);
+		if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts))
+			break;
+	}
+	return rc;
+}
+EXPORT_SYMBOL(security_sb_set_mnt_opts);
+
+/**
+ * security_sb_clone_mnt_opts() - Duplicate superblock mount options
+ * @oldsb: source superblock
+ * @newsb: destination superblock
+ * @kern_flags: kernel flags (in)
+ * @set_kern_flags: kernel flags (out)
+ *
+ * Copy all security options from a given superblock to another.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_sb_clone_mnt_opts(const struct super_block *oldsb,
+			       struct super_block *newsb,
+			       unsigned long kern_flags,
+			       unsigned long *set_kern_flags)
+{
+	return call_int_hook(sb_clone_mnt_opts, oldsb, newsb,
+			     kern_flags, set_kern_flags);
+}
+EXPORT_SYMBOL(security_sb_clone_mnt_opts);
+
+/**
+ * security_move_mount() - Check permissions for moving a mount
+ * @from_path: source mount point
+ * @to_path: destination mount point
+ *
+ * Check permission before a mount is moved.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_move_mount(const struct path *from_path,
+			const struct path *to_path)
+{
+	return call_int_hook(move_mount, from_path, to_path);
+}
+
+/**
+ * security_path_notify() - Check if setting a watch is allowed
+ * @path: file path
+ * @mask: event mask
+ * @obj_type: file path type
+ *
+ * Check permissions before setting a watch on events as defined by @mask, on
+ * an object at @path, whose type is defined by @obj_type.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_notify(const struct path *path, u64 mask,
+			 unsigned int obj_type)
+{
+	return call_int_hook(path_notify, path, mask, obj_type);
+}
+
+/**
+ * security_inode_alloc() - Allocate an inode LSM blob
+ * @inode: the inode
+ * @gfp: allocation flags
+ *
+ * Allocate and attach a security structure to @inode->i_security.  The
+ * i_security field is initialized to NULL when the inode structure is
+ * allocated.
+ *
+ * Return: Return 0 if operation was successful.
+ */
+int security_inode_alloc(struct inode *inode, gfp_t gfp)
+{
+	int rc = lsm_inode_alloc(inode, gfp);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(inode_alloc_security, inode);
+	if (unlikely(rc))
+		security_inode_free(inode);
+	return rc;
+}
+
+static void inode_free_by_rcu(struct rcu_head *head)
+{
+	/* The rcu head is at the start of the inode blob */
+	call_void_hook(inode_free_security_rcu, head);
+	kmem_cache_free(lsm_inode_cache, head);
+}
+
+/**
+ * security_inode_free() - Free an inode's LSM blob
+ * @inode: the inode
+ *
+ * Release any LSM resources associated with @inode, although due to the
+ * inode's RCU protections it is possible that the resources will not be
+ * fully released until after the current RCU grace period has elapsed.
+ *
+ * It is important for LSMs to note that despite being present in a call to
+ * security_inode_free(), @inode may still be referenced in a VFS path walk
+ * and calls to security_inode_permission() may be made during, or after,
+ * a call to security_inode_free().  For this reason the inode->i_security
+ * field is released via a call_rcu() callback and any LSMs which need to
+ * retain inode state for use in security_inode_permission() should only
+ * release that state in the inode_free_security_rcu() LSM hook callback.
+ */
+void security_inode_free(struct inode *inode)
+{
+	call_void_hook(inode_free_security, inode);
+	if (!inode->i_security)
+		return;
+	call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu);
+}
+
+/**
+ * security_dentry_init_security() - Perform dentry initialization
+ * @dentry: the dentry to initialize
+ * @mode: mode used to determine resource type
+ * @name: name of the last path component
+ * @xattr_name: name of the security/LSM xattr
+ * @lsmctx: pointer to the resulting LSM context
+ *
+ * Compute a context for a dentry as the inode is not yet available since NFSv4
+ * has no label backed by an EA anyway.  It is important to note that
+ * @xattr_name does not need to be free'd by the caller, it is a static string.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_dentry_init_security(struct dentry *dentry, int mode,
+				  const struct qstr *name,
+				  const char **xattr_name,
+				  struct lsm_context *lsmctx)
+{
+	return call_int_hook(dentry_init_security, dentry, mode, name,
+			     xattr_name, lsmctx);
+}
+EXPORT_SYMBOL(security_dentry_init_security);
+
+/**
+ * security_dentry_create_files_as() - Perform dentry initialization
+ * @dentry: the dentry to initialize
+ * @mode: mode used to determine resource type
+ * @name: name of the last path component
+ * @old: creds to use for LSM context calculations
+ * @new: creds to modify
+ *
+ * Compute a context for a dentry as the inode is not yet available and set
+ * that context in passed in creds so that new files are created using that
+ * context. Context is calculated using the passed in creds and not the creds
+ * of the caller.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_dentry_create_files_as(struct dentry *dentry, int mode,
+				    const struct qstr *name,
+				    const struct cred *old, struct cred *new)
+{
+	return call_int_hook(dentry_create_files_as, dentry, mode,
+			     name, old, new);
+}
+EXPORT_SYMBOL(security_dentry_create_files_as);
+
+/**
+ * security_inode_init_security() - Initialize an inode's LSM context
+ * @inode: the inode
+ * @dir: parent directory
+ * @qstr: last component of the pathname
+ * @initxattrs: callback function to write xattrs
+ * @fs_data: filesystem specific data
+ *
+ * Obtain the security attribute name suffix and value to set on a newly
+ * created inode and set up the incore security field for the new inode.  This
+ * hook is called by the fs code as part of the inode creation transaction and
+ * provides for atomic labeling of the inode, unlike the post_create/mkdir/...
+ * hooks called by the VFS.
+ *
+ * The hook function is expected to populate the xattrs array, by calling
+ * lsm_get_xattr_slot() to retrieve the slots reserved by the security module
+ * with the lbs_xattr_count field of the lsm_blob_sizes structure.  For each
+ * slot, the hook function should set ->name to the attribute name suffix
+ * (e.g. selinux), to allocate ->value (will be freed by the caller) and set it
+ * to the attribute value, to set ->value_len to the length of the value.  If
+ * the security module does not use security attributes or does not wish to put
+ * a security attribute on this particular inode, then it should return
+ * -EOPNOTSUPP to skip this processing.
+ *
+ * Return: Returns 0 if the LSM successfully initialized all of the inode
+ *         security attributes that are required, negative values otherwise.
+ */
+int security_inode_init_security(struct inode *inode, struct inode *dir,
+				 const struct qstr *qstr,
+				 const initxattrs initxattrs, void *fs_data)
+{
+	struct lsm_static_call *scall;
+	struct xattr *new_xattrs = NULL;
+	int ret = -EOPNOTSUPP, xattr_count = 0;
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	if (!blob_sizes.lbs_xattr_count)
+		return 0;
+
+	if (initxattrs) {
+		/* Allocate +1 as terminator. */
+		new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1,
+				     sizeof(*new_xattrs), GFP_NOFS);
+		if (!new_xattrs)
+			return -ENOMEM;
+	}
+
+	lsm_for_each_hook(scall, inode_init_security) {
+		ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs,
+						  &xattr_count);
+		if (ret && ret != -EOPNOTSUPP)
+			goto out;
+		/*
+		 * As documented in lsm_hooks.h, -EOPNOTSUPP in this context
+		 * means that the LSM is not willing to provide an xattr, not
+		 * that it wants to signal an error. Thus, continue to invoke
+		 * the remaining LSMs.
+		 */
+	}
+
+	/* If initxattrs() is NULL, xattr_count is zero, skip the call. */
+	if (!xattr_count)
+		goto out;
+
+	ret = initxattrs(inode, new_xattrs, fs_data);
+out:
+	for (; xattr_count > 0; xattr_count--)
+		kfree(new_xattrs[xattr_count - 1].value);
+	kfree(new_xattrs);
+	return (ret == -EOPNOTSUPP) ? 0 : ret;
+}
+EXPORT_SYMBOL(security_inode_init_security);
+
+/**
+ * security_inode_init_security_anon() - Initialize an anonymous inode
+ * @inode: the inode
+ * @name: the anonymous inode class
+ * @context_inode: an optional related inode
+ *
+ * Set up the incore security field for the new anonymous inode and return
+ * whether the inode creation is permitted by the security module or not.
+ *
+ * Return: Returns 0 on success, -EACCES if the security module denies the
+ * creation of this inode, or another -errno upon other errors.
+ */
+int security_inode_init_security_anon(struct inode *inode,
+				      const struct qstr *name,
+				      const struct inode *context_inode)
+{
+	return call_int_hook(inode_init_security_anon, inode, name,
+			     context_inode);
+}
+
+#ifdef CONFIG_SECURITY_PATH
+/**
+ * security_path_mknod() - Check if creating a special file is allowed
+ * @dir: parent directory
+ * @dentry: new file
+ * @mode: new file mode
+ * @dev: device number
+ *
+ * Check permissions when creating a file. Note that this hook is called even
+ * if mknod operation is being done for a regular file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_mknod(const struct path *dir, struct dentry *dentry,
+			umode_t mode, unsigned int dev)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
+		return 0;
+	return call_int_hook(path_mknod, dir, dentry, mode, dev);
+}
+EXPORT_SYMBOL(security_path_mknod);
+
+/**
+ * security_path_post_mknod() - Update inode security after reg file creation
+ * @idmap: idmap of the mount
+ * @dentry: new file
+ *
+ * Update inode security field after a regular file has been created.
+ */
+void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(path_post_mknod, idmap, dentry);
+}
+
+/**
+ * security_path_mkdir() - Check if creating a new directory is allowed
+ * @dir: parent directory
+ * @dentry: new directory
+ * @mode: new directory mode
+ *
+ * Check permissions to create a new directory in the existing directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_mkdir(const struct path *dir, struct dentry *dentry,
+			umode_t mode)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
+		return 0;
+	return call_int_hook(path_mkdir, dir, dentry, mode);
+}
+EXPORT_SYMBOL(security_path_mkdir);
+
+/**
+ * security_path_rmdir() - Check if removing a directory is allowed
+ * @dir: parent directory
+ * @dentry: directory to remove
+ *
+ * Check the permission to remove a directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_rmdir(const struct path *dir, struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
+		return 0;
+	return call_int_hook(path_rmdir, dir, dentry);
+}
+
+/**
+ * security_path_unlink() - Check if removing a hard link is allowed
+ * @dir: parent directory
+ * @dentry: file
+ *
+ * Check the permission to remove a hard link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_unlink(const struct path *dir, struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
+		return 0;
+	return call_int_hook(path_unlink, dir, dentry);
+}
+EXPORT_SYMBOL(security_path_unlink);
+
+/**
+ * security_path_symlink() - Check if creating a symbolic link is allowed
+ * @dir: parent directory
+ * @dentry: symbolic link
+ * @old_name: file pathname
+ *
+ * Check the permission to create a symbolic link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_symlink(const struct path *dir, struct dentry *dentry,
+			  const char *old_name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry))))
+		return 0;
+	return call_int_hook(path_symlink, dir, dentry, old_name);
+}
+
+/**
+ * security_path_link - Check if creating a hard link is allowed
+ * @old_dentry: existing file
+ * @new_dir: new parent directory
+ * @new_dentry: new link
+ *
+ * Check permission before creating a new hard link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_link(struct dentry *old_dentry, const struct path *new_dir,
+		       struct dentry *new_dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry))))
+		return 0;
+	return call_int_hook(path_link, old_dentry, new_dir, new_dentry);
+}
+
+/**
+ * security_path_rename() - Check if renaming a file is allowed
+ * @old_dir: parent directory of the old file
+ * @old_dentry: the old file
+ * @new_dir: parent directory of the new file
+ * @new_dentry: the new file
+ * @flags: flags
+ *
+ * Check for permission to rename a file or directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_rename(const struct path *old_dir, struct dentry *old_dentry,
+			 const struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) ||
+		     (d_is_positive(new_dentry) &&
+		      IS_PRIVATE(d_backing_inode(new_dentry)))))
+		return 0;
+
+	return call_int_hook(path_rename, old_dir, old_dentry, new_dir,
+			     new_dentry, flags);
+}
+EXPORT_SYMBOL(security_path_rename);
+
+/**
+ * security_path_truncate() - Check if truncating a file is allowed
+ * @path: file
+ *
+ * Check permission before truncating the file indicated by path.  Note that
+ * truncation permissions may also be checked based on already opened files,
+ * using the security_file_truncate() hook.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_truncate(const struct path *path)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
+		return 0;
+	return call_int_hook(path_truncate, path);
+}
+
+/**
+ * security_path_chmod() - Check if changing the file's mode is allowed
+ * @path: file
+ * @mode: new mode
+ *
+ * Check for permission to change a mode of the file @path. The new mode is
+ * specified in @mode which is a bitmask of constants from
+ * <include/uapi/linux/stat.h>.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_chmod(const struct path *path, umode_t mode)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
+		return 0;
+	return call_int_hook(path_chmod, path, mode);
+}
+
+/**
+ * security_path_chown() - Check if changing the file's owner/group is allowed
+ * @path: file
+ * @uid: file owner
+ * @gid: file group
+ *
+ * Check for permission to change owner/group of a file or directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
+		return 0;
+	return call_int_hook(path_chown, path, uid, gid);
+}
+
+/**
+ * security_path_chroot() - Check if changing the root directory is allowed
+ * @path: directory
+ *
+ * Check for permission to change root directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_path_chroot(const struct path *path)
+{
+	return call_int_hook(path_chroot, path);
+}
+#endif /* CONFIG_SECURITY_PATH */
+
+/**
+ * security_inode_create() - Check if creating a file is allowed
+ * @dir: the parent directory
+ * @dentry: the file being created
+ * @mode: requested file mode
+ *
+ * Check permission to create a regular file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_create(struct inode *dir, struct dentry *dentry,
+			  umode_t mode)
+{
+	if (unlikely(IS_PRIVATE(dir)))
+		return 0;
+	return call_int_hook(inode_create, dir, dentry, mode);
+}
+EXPORT_SYMBOL_GPL(security_inode_create);
+
+/**
+ * security_inode_post_create_tmpfile() - Update inode security of new tmpfile
+ * @idmap: idmap of the mount
+ * @inode: inode of the new tmpfile
+ *
+ * Update inode security data after a tmpfile has been created.
+ */
+void security_inode_post_create_tmpfile(struct mnt_idmap *idmap,
+					struct inode *inode)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return;
+	call_void_hook(inode_post_create_tmpfile, idmap, inode);
+}
+
+/**
+ * security_inode_link() - Check if creating a hard link is allowed
+ * @old_dentry: existing file
+ * @dir: new parent directory
+ * @new_dentry: new link
+ *
+ * Check permission before creating a new hard link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_link(struct dentry *old_dentry, struct inode *dir,
+			struct dentry *new_dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry))))
+		return 0;
+	return call_int_hook(inode_link, old_dentry, dir, new_dentry);
+}
+
+/**
+ * security_inode_unlink() - Check if removing a hard link is allowed
+ * @dir: parent directory
+ * @dentry: file
+ *
+ * Check the permission to remove a hard link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_unlink(struct inode *dir, struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_unlink, dir, dentry);
+}
+
+/**
+ * security_inode_symlink() - Check if creating a symbolic link is allowed
+ * @dir: parent directory
+ * @dentry: symbolic link
+ * @old_name: existing filename
+ *
+ * Check the permission to create a symbolic link to a file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_symlink(struct inode *dir, struct dentry *dentry,
+			   const char *old_name)
+{
+	if (unlikely(IS_PRIVATE(dir)))
+		return 0;
+	return call_int_hook(inode_symlink, dir, dentry, old_name);
+}
+
+/**
+ * security_inode_mkdir() - Check if creating a new directory is allowed
+ * @dir: parent directory
+ * @dentry: new directory
+ * @mode: new directory mode
+ *
+ * Check permissions to create a new directory in the existing directory
+ * associated with inode structure @dir.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	if (unlikely(IS_PRIVATE(dir)))
+		return 0;
+	return call_int_hook(inode_mkdir, dir, dentry, mode);
+}
+EXPORT_SYMBOL_GPL(security_inode_mkdir);
+
+/**
+ * security_inode_rmdir() - Check if removing a directory is allowed
+ * @dir: parent directory
+ * @dentry: directory to be removed
+ *
+ * Check the permission to remove a directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_rmdir, dir, dentry);
+}
+
+/**
+ * security_inode_mknod() - Check if creating a special file is allowed
+ * @dir: parent directory
+ * @dentry: new file
+ * @mode: new file mode
+ * @dev: device number
+ *
+ * Check permissions when creating a special file (or a socket or a fifo file
+ * created via the mknod system call).  Note that if mknod operation is being
+ * done for a regular file, then the create hook will be called and not this
+ * hook.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_mknod(struct inode *dir, struct dentry *dentry,
+			 umode_t mode, dev_t dev)
+{
+	if (unlikely(IS_PRIVATE(dir)))
+		return 0;
+	return call_int_hook(inode_mknod, dir, dentry, mode, dev);
+}
+
+/**
+ * security_inode_rename() - Check if renaming a file is allowed
+ * @old_dir: parent directory of the old file
+ * @old_dentry: the old file
+ * @new_dir: parent directory of the new file
+ * @new_dentry: the new file
+ * @flags: flags
+ *
+ * Check for permission to rename a file or directory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
+			  struct inode *new_dir, struct dentry *new_dentry,
+			  unsigned int flags)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(old_dentry)) ||
+		     (d_is_positive(new_dentry) &&
+		      IS_PRIVATE(d_backing_inode(new_dentry)))))
+		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = call_int_hook(inode_rename, new_dir, new_dentry,
+					old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
+	return call_int_hook(inode_rename, old_dir, old_dentry,
+			     new_dir, new_dentry);
+}
+
+/**
+ * security_inode_readlink() - Check if reading a symbolic link is allowed
+ * @dentry: link
+ *
+ * Check the permission to read the symbolic link.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_readlink(struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_readlink, dentry);
+}
+
+/**
+ * security_inode_follow_link() - Check if following a symbolic link is allowed
+ * @dentry: link dentry
+ * @inode: link inode
+ * @rcu: true if in RCU-walk mode
+ *
+ * Check permission to follow a symbolic link when looking up a pathname.  If
+ * @rcu is true, @inode is not stable.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_follow_link(struct dentry *dentry, struct inode *inode,
+			       bool rcu)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+	return call_int_hook(inode_follow_link, dentry, inode, rcu);
+}
+
+/**
+ * security_inode_permission() - Check if accessing an inode is allowed
+ * @inode: inode
+ * @mask: access mask
+ *
+ * Check permission before accessing an inode.  This hook is called by the
+ * existing Linux permission function, so a security module can use it to
+ * provide additional checking for existing Linux permission checks.  Notice
+ * that this hook is called when a file is opened (as well as many other
+ * operations), whereas the file_security_ops permission hook is called when
+ * the actual read/write operations are performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_permission(struct inode *inode, int mask)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+	return call_int_hook(inode_permission, inode, mask);
+}
+
+/**
+ * security_inode_setattr() - Check if setting file attributes is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @attr: new attributes
+ *
+ * Check permission before setting file attributes.  Note that the kernel call
+ * to notify_change is performed from several locations, whenever file
+ * attributes change (such as when a file is truncated, chown/chmod operations,
+ * transferring disk quotas, etc).
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_setattr(struct mnt_idmap *idmap,
+			   struct dentry *dentry, struct iattr *attr)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_setattr, idmap, dentry, attr);
+}
+EXPORT_SYMBOL_GPL(security_inode_setattr);
+
+/**
+ * security_inode_post_setattr() - Update the inode after a setattr operation
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @ia_valid: file attributes set
+ *
+ * Update inode security field after successful setting file attributes.
+ */
+void security_inode_post_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+				 int ia_valid)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(inode_post_setattr, idmap, dentry, ia_valid);
+}
+
+/**
+ * security_inode_getattr() - Check if getting file attributes is allowed
+ * @path: file
+ *
+ * Check permission before obtaining file attributes.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_getattr(const struct path *path)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(path->dentry))))
+		return 0;
+	return call_int_hook(inode_getattr, path);
+}
+
+/**
+ * security_inode_setxattr() - Check if setting file xattrs is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @name: xattr name
+ * @value: xattr value
+ * @size: size of xattr value
+ * @flags: flags
+ *
+ * This hook performs the desired permission checks before setting the extended
+ * attributes (xattrs) on @dentry.  It is important to note that we have some
+ * additional logic before the main LSM implementation calls to detect if we
+ * need to perform an additional capability check at the LSM layer.
+ *
+ * Normally we enforce a capability check prior to executing the various LSM
+ * hook implementations, but if a LSM wants to avoid this capability check,
+ * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
+ * xattrs that it wants to avoid the capability check, leaving the LSM fully
+ * responsible for enforcing the access control for the specific xattr.  If all
+ * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
+ * or return a 0 (the default return value), the capability check is still
+ * performed.  If no 'inode_xattr_skipcap' hooks are registered the capability
+ * check is performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_setxattr(struct mnt_idmap *idmap,
+			    struct dentry *dentry, const char *name,
+			    const void *value, size_t size, int flags)
+{
+	int rc;
+
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+
+	/* enforce the capability checks at the lsm layer, if needed */
+	if (!call_int_hook(inode_xattr_skipcap, name)) {
+		rc = cap_inode_setxattr(dentry, name, value, size, flags);
+		if (rc)
+			return rc;
+	}
+
+	return call_int_hook(inode_setxattr, idmap, dentry, name, value, size,
+			     flags);
+}
+
+/**
+ * security_inode_set_acl() - Check if setting posix acls is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @acl_name: acl name
+ * @kacl: acl struct
+ *
+ * Check permission before setting posix acls, the posix acls in @kacl are
+ * identified by @acl_name.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_set_acl(struct mnt_idmap *idmap,
+			   struct dentry *dentry, const char *acl_name,
+			   struct posix_acl *kacl)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_set_acl, idmap, dentry, acl_name, kacl);
+}
+
+/**
+ * security_inode_post_set_acl() - Update inode security from posix acls set
+ * @dentry: file
+ * @acl_name: acl name
+ * @kacl: acl struct
+ *
+ * Update inode security data after successfully setting posix acls on @dentry.
+ * The posix acls in @kacl are identified by @acl_name.
+ */
+void security_inode_post_set_acl(struct dentry *dentry, const char *acl_name,
+				 struct posix_acl *kacl)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(inode_post_set_acl, dentry, acl_name, kacl);
+}
+
+/**
+ * security_inode_get_acl() - Check if reading posix acls is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @acl_name: acl name
+ *
+ * Check permission before getting osix acls, the posix acls are identified by
+ * @acl_name.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_get_acl(struct mnt_idmap *idmap,
+			   struct dentry *dentry, const char *acl_name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_get_acl, idmap, dentry, acl_name);
+}
+
+/**
+ * security_inode_remove_acl() - Check if removing a posix acl is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @acl_name: acl name
+ *
+ * Check permission before removing posix acls, the posix acls are identified
+ * by @acl_name.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_remove_acl(struct mnt_idmap *idmap,
+			      struct dentry *dentry, const char *acl_name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_remove_acl, idmap, dentry, acl_name);
+}
+
+/**
+ * security_inode_post_remove_acl() - Update inode security after rm posix acls
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @acl_name: acl name
+ *
+ * Update inode security data after successfully removing posix acls on
+ * @dentry in @idmap. The posix acls are identified by @acl_name.
+ */
+void security_inode_post_remove_acl(struct mnt_idmap *idmap,
+				    struct dentry *dentry, const char *acl_name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(inode_post_remove_acl, idmap, dentry, acl_name);
+}
+
+/**
+ * security_inode_post_setxattr() - Update the inode after a setxattr operation
+ * @dentry: file
+ * @name: xattr name
+ * @value: xattr value
+ * @size: xattr value size
+ * @flags: flags
+ *
+ * Update inode security field after successful setxattr operation.
+ */
+void security_inode_post_setxattr(struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(inode_post_setxattr, dentry, name, value, size, flags);
+}
+
+/**
+ * security_inode_getxattr() - Check if xattr access is allowed
+ * @dentry: file
+ * @name: xattr name
+ *
+ * Check permission before obtaining the extended attributes identified by
+ * @name for @dentry.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_getxattr(struct dentry *dentry, const char *name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_getxattr, dentry, name);
+}
+
+/**
+ * security_inode_listxattr() - Check if listing xattrs is allowed
+ * @dentry: file
+ *
+ * Check permission before obtaining the list of extended attribute names for
+ * @dentry.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_listxattr(struct dentry *dentry)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+	return call_int_hook(inode_listxattr, dentry);
+}
+
+/**
+ * security_inode_removexattr() - Check if removing an xattr is allowed
+ * @idmap: idmap of the mount
+ * @dentry: file
+ * @name: xattr name
+ *
+ * This hook performs the desired permission checks before setting the extended
+ * attributes (xattrs) on @dentry.  It is important to note that we have some
+ * additional logic before the main LSM implementation calls to detect if we
+ * need to perform an additional capability check at the LSM layer.
+ *
+ * Normally we enforce a capability check prior to executing the various LSM
+ * hook implementations, but if a LSM wants to avoid this capability check,
+ * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
+ * xattrs that it wants to avoid the capability check, leaving the LSM fully
+ * responsible for enforcing the access control for the specific xattr.  If all
+ * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
+ * or return a 0 (the default return value), the capability check is still
+ * performed.  If no 'inode_xattr_skipcap' hooks are registered the capability
+ * check is performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_removexattr(struct mnt_idmap *idmap,
+			       struct dentry *dentry, const char *name)
+{
+	int rc;
+
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+
+	/* enforce the capability checks at the lsm layer, if needed */
+	if (!call_int_hook(inode_xattr_skipcap, name)) {
+		rc = cap_inode_removexattr(idmap, dentry, name);
+		if (rc)
+			return rc;
+	}
+
+	return call_int_hook(inode_removexattr, idmap, dentry, name);
+}
+
+/**
+ * security_inode_post_removexattr() - Update the inode after a removexattr op
+ * @dentry: file
+ * @name: xattr name
+ *
+ * Update the inode after a successful removexattr operation.
+ */
+void security_inode_post_removexattr(struct dentry *dentry, const char *name)
+{
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return;
+	call_void_hook(inode_post_removexattr, dentry, name);
+}
+
+/**
+ * security_inode_file_setattr() - check if setting fsxattr is allowed
+ * @dentry: file to set filesystem extended attributes on
+ * @fa: extended attributes to set on the inode
+ *
+ * Called when file_setattr() syscall or FS_IOC_FSSETXATTR ioctl() is called on
+ * inode
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_file_setattr(struct dentry *dentry, struct file_kattr *fa)
+{
+	return call_int_hook(inode_file_setattr, dentry, fa);
+}
+
+/**
+ * security_inode_file_getattr() - check if retrieving fsxattr is allowed
+ * @dentry: file to retrieve filesystem extended attributes from
+ * @fa: extended attributes to get
+ *
+ * Called when file_getattr() syscall or FS_IOC_FSGETXATTR ioctl() is called on
+ * inode
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_file_getattr(struct dentry *dentry, struct file_kattr *fa)
+{
+	return call_int_hook(inode_file_getattr, dentry, fa);
+}
+
+/**
+ * security_inode_need_killpriv() - Check if security_inode_killpriv() required
+ * @dentry: associated dentry
+ *
+ * Called when an inode has been changed to determine if
+ * security_inode_killpriv() should be called.
+ *
+ * Return: Return <0 on error to abort the inode change operation, return 0 if
+ *         security_inode_killpriv() does not need to be called, return >0 if
+ *         security_inode_killpriv() does need to be called.
+ */
+int security_inode_need_killpriv(struct dentry *dentry)
+{
+	return call_int_hook(inode_need_killpriv, dentry);
+}
+
+/**
+ * security_inode_killpriv() - The setuid bit is removed, update LSM state
+ * @idmap: idmap of the mount
+ * @dentry: associated dentry
+ *
+ * The @dentry's setuid bit is being removed.  Remove similar security labels.
+ * Called with the dentry->d_inode->i_mutex held.
+ *
+ * Return: Return 0 on success.  If error is returned, then the operation
+ *         causing setuid bit removal is failed.
+ */
+int security_inode_killpriv(struct mnt_idmap *idmap,
+			    struct dentry *dentry)
+{
+	return call_int_hook(inode_killpriv, idmap, dentry);
+}
+
+/**
+ * security_inode_getsecurity() - Get the xattr security label of an inode
+ * @idmap: idmap of the mount
+ * @inode: inode
+ * @name: xattr name
+ * @buffer: security label buffer
+ * @alloc: allocation flag
+ *
+ * Retrieve a copy of the extended attribute representation of the security
+ * label associated with @name for @inode via @buffer.  Note that @name is the
+ * remainder of the attribute name after the security prefix has been removed.
+ * @alloc is used to specify if the call should return a value via the buffer
+ * or just the value length.
+ *
+ * Return: Returns size of buffer on success.
+ */
+int security_inode_getsecurity(struct mnt_idmap *idmap,
+			       struct inode *inode, const char *name,
+			       void **buffer, bool alloc)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return LSM_RET_DEFAULT(inode_getsecurity);
+
+	return call_int_hook(inode_getsecurity, idmap, inode, name, buffer,
+			     alloc);
+}
+
+/**
+ * security_inode_setsecurity() - Set the xattr security label of an inode
+ * @inode: inode
+ * @name: xattr name
+ * @value: security label
+ * @size: length of security label
+ * @flags: flags
+ *
+ * Set the security label associated with @name for @inode from the extended
+ * attribute value @value.  @size indicates the size of the @value in bytes.
+ * @flags may be XATTR_CREATE, XATTR_REPLACE, or 0. Note that @name is the
+ * remainder of the attribute name after the security. prefix has been removed.
+ *
+ * Return: Returns 0 on success.
+ */
+int security_inode_setsecurity(struct inode *inode, const char *name,
+			       const void *value, size_t size, int flags)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return LSM_RET_DEFAULT(inode_setsecurity);
+
+	return call_int_hook(inode_setsecurity, inode, name, value, size,
+			     flags);
+}
+
+/**
+ * security_inode_listsecurity() - List the xattr security label names
+ * @inode: inode
+ * @buffer: pointer to buffer
+ * @remaining_size: pointer to remaining size of buffer
+ *
+ * Copy the extended attribute names for the security labels associated with
+ * @inode into *(@buffer).  The remaining size of @buffer is specified by
+ * *(@remaining_size).  *(@buffer) may be NULL to request the size of the
+ * buffer required. Updates *(@buffer) and *(@remaining_size).
+ *
+ * Return: Returns 0 on success, or -errno on failure.
+ */
+int security_inode_listsecurity(struct inode *inode,
+				char **buffer, ssize_t *remaining_size)
+{
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+	return call_int_hook(inode_listsecurity, inode, buffer, remaining_size);
+}
+EXPORT_SYMBOL(security_inode_listsecurity);
+
+/**
+ * security_inode_getlsmprop() - Get an inode's LSM data
+ * @inode: inode
+ * @prop: lsm specific information to return
+ *
+ * Get the lsm specific information associated with the node.
+ */
+void security_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop)
+{
+	call_void_hook(inode_getlsmprop, inode, prop);
+}
+
+/**
+ * security_inode_copy_up() - Create new creds for an overlayfs copy-up op
+ * @src: union dentry of copy-up file
+ * @new: newly created creds
+ *
+ * A file is about to be copied up from lower layer to upper layer of overlay
+ * filesystem. Security module can prepare a set of new creds and modify as
+ * need be and return new creds. Caller will switch to new creds temporarily to
+ * create new file and release newly allocated creds.
+ *
+ * Return: Returns 0 on success or a negative error code on error.
+ */
+int security_inode_copy_up(struct dentry *src, struct cred **new)
+{
+	return call_int_hook(inode_copy_up, src, new);
+}
+EXPORT_SYMBOL(security_inode_copy_up);
+
+/**
+ * security_inode_copy_up_xattr() - Filter xattrs in an overlayfs copy-up op
+ * @src: union dentry of copy-up file
+ * @name: xattr name
+ *
+ * Filter the xattrs being copied up when a unioned file is copied up from a
+ * lower layer to the union/overlay layer.   The caller is responsible for
+ * reading and writing the xattrs, this hook is merely a filter.
+ *
+ * Return: Returns 0 to accept the xattr, -ECANCELED to discard the xattr,
+ *         -EOPNOTSUPP if the security module does not know about attribute,
+ *         or a negative error code to abort the copy up.
+ */
+int security_inode_copy_up_xattr(struct dentry *src, const char *name)
+{
+	int rc;
+
+	rc = call_int_hook(inode_copy_up_xattr, src, name);
+	if (rc != LSM_RET_DEFAULT(inode_copy_up_xattr))
+		return rc;
+
+	return LSM_RET_DEFAULT(inode_copy_up_xattr);
+}
+EXPORT_SYMBOL(security_inode_copy_up_xattr);
+
+/**
+ * security_inode_setintegrity() - Set the inode's integrity data
+ * @inode: inode
+ * @type: type of integrity, e.g. hash digest, signature, etc
+ * @value: the integrity value
+ * @size: size of the integrity value
+ *
+ * Register a verified integrity measurement of a inode with LSMs.
+ * LSMs should free the previously saved data if @value is NULL.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_inode_setintegrity(const struct inode *inode,
+				enum lsm_integrity_type type, const void *value,
+				size_t size)
+{
+	return call_int_hook(inode_setintegrity, inode, type, value, size);
+}
+EXPORT_SYMBOL(security_inode_setintegrity);
+
+/**
+ * security_kernfs_init_security() - Init LSM context for a kernfs node
+ * @kn_dir: parent kernfs node
+ * @kn: the kernfs node to initialize
+ *
+ * Initialize the security context of a newly created kernfs node based on its
+ * own and its parent's attributes.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_kernfs_init_security(struct kernfs_node *kn_dir,
+				  struct kernfs_node *kn)
+{
+	return call_int_hook(kernfs_init_security, kn_dir, kn);
+}
+
+/**
+ * security_file_permission() - Check file permissions
+ * @file: file
+ * @mask: requested permissions
+ *
+ * Check file permissions before accessing an open file.  This hook is called
+ * by various operations that read or write files.  A security module can use
+ * this hook to perform additional checking on these operations, e.g. to
+ * revalidate permissions on use to support privilege bracketing or policy
+ * changes.  Notice that this hook is used when the actual read/write
+ * operations are performed, whereas the inode_security_ops hook is called when
+ * a file is opened (as well as many other operations).  Although this hook can
+ * be used to revalidate permissions for various system call operations that
+ * read or write files, it does not address the revalidation of permissions for
+ * memory-mapped files.  Security modules must handle this separately if they
+ * need such revalidation.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_permission(struct file *file, int mask)
+{
+	return call_int_hook(file_permission, file, mask);
+}
+
+/**
+ * security_file_alloc() - Allocate and init a file's LSM blob
+ * @file: the file
+ *
+ * Allocate and attach a security structure to the file->f_security field.  The
+ * security field is initialized to NULL when the structure is first created.
+ *
+ * Return: Return 0 if the hook is successful and permission is granted.
+ */
+int security_file_alloc(struct file *file)
+{
+	int rc = lsm_file_alloc(file);
+
+	if (rc)
+		return rc;
+	rc = call_int_hook(file_alloc_security, file);
+	if (unlikely(rc))
+		security_file_free(file);
+	return rc;
+}
+
+/**
+ * security_file_release() - Perform actions before releasing the file ref
+ * @file: the file
+ *
+ * Perform actions before releasing the last reference to a file.
+ */
+void security_file_release(struct file *file)
+{
+	call_void_hook(file_release, file);
+}
+
+/**
+ * security_file_free() - Free a file's LSM blob
+ * @file: the file
+ *
+ * Deallocate and free any security structures stored in file->f_security.
+ */
+void security_file_free(struct file *file)
+{
+	void *blob;
+
+	call_void_hook(file_free_security, file);
+
+	blob = file->f_security;
+	if (blob) {
+		file->f_security = NULL;
+		kmem_cache_free(lsm_file_cache, blob);
+	}
+}
+
+/**
+ * security_backing_file_alloc() - Allocate and setup a backing file blob
+ * @backing_file: the backing file
+ * @user_file: the associated user visible file
+ *
+ * Allocate a backing file LSM blob and perform any necessary initialization of
+ * the LSM blob.  There will be some operations where the LSM will not have
+ * access to @user_file after this point, so any important state associated
+ * with @user_file that is important to the LSM should be captured in the
+ * backing file's LSM blob.
+ *
+ * LSM's should avoid taking a reference to @user_file in this hook as it will
+ * result in problems later when the system attempts to drop/put the file
+ * references due to a circular dependency.
+ *
+ * Return: Return 0 if the hook is successful, negative values otherwise.
+ */
+int security_backing_file_alloc(struct file *backing_file,
+				const struct file *user_file)
+{
+	int rc;
+
+	rc = lsm_backing_file_alloc(backing_file);
+	if (rc)
+		return rc;
+	rc = call_int_hook(backing_file_alloc, backing_file, user_file);
+	if (unlikely(rc))
+		security_backing_file_free(backing_file);
+
+	return rc;
+}
+
+/**
+ * security_backing_file_free() - Free a backing file blob
+ * @backing_file: the backing file
+ *
+ * Free any LSM state associate with a backing file's LSM blob, including the
+ * blob itself.
+ */
+void security_backing_file_free(struct file *backing_file)
+{
+	void *blob = backing_file_security(backing_file);
+
+	call_void_hook(backing_file_free, backing_file);
+
+	if (blob) {
+		backing_file_set_security(backing_file, NULL);
+		kmem_cache_free(lsm_backing_file_cache, blob);
+	}
+}
+
+/**
+ * security_file_ioctl() - Check if an ioctl is allowed
+ * @file: associated file
+ * @cmd: ioctl cmd
+ * @arg: ioctl arguments
+ *
+ * Check permission for an ioctl operation on @file.  Note that @arg sometimes
+ * represents a user space pointer; in other cases, it may be a simple integer
+ * value.  When @arg represents a user space pointer, it should never be used
+ * by the security module.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return call_int_hook(file_ioctl, file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(security_file_ioctl);
+
+/**
+ * security_file_ioctl_compat() - Check if an ioctl is allowed in compat mode
+ * @file: associated file
+ * @cmd: ioctl cmd
+ * @arg: ioctl arguments
+ *
+ * Compat version of security_file_ioctl() that correctly handles 32-bit
+ * processes running on 64-bit kernels.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_ioctl_compat(struct file *file, unsigned int cmd,
+			       unsigned long arg)
+{
+	return call_int_hook(file_ioctl_compat, file, cmd, arg);
+}
+EXPORT_SYMBOL_GPL(security_file_ioctl_compat);
+
+static inline unsigned long mmap_prot(struct file *file, unsigned long prot)
+{
+	/*
+	 * Does we have PROT_READ and does the application expect
+	 * it to imply PROT_EXEC?  If not, nothing to talk about...
+	 */
+	if ((prot & (PROT_READ | PROT_EXEC)) != PROT_READ)
+		return prot;
+	if (!(current->personality & READ_IMPLIES_EXEC))
+		return prot;
+	/*
+	 * if that's an anonymous mapping, let it.
+	 */
+	if (!file)
+		return prot | PROT_EXEC;
+	/*
+	 * ditto if it's not on noexec mount, except that on !MMU we need
+	 * NOMMU_MAP_EXEC (== VM_MAYEXEC) in this case
+	 */
+	if (!path_noexec(&file->f_path)) {
+#ifndef CONFIG_MMU
+		if (file->f_op->mmap_capabilities) {
+			unsigned caps = file->f_op->mmap_capabilities(file);
+			if (!(caps & NOMMU_MAP_EXEC))
+				return prot;
+		}
+#endif
+		return prot | PROT_EXEC;
+	}
+	/* anything on noexec mount won't get PROT_EXEC */
+	return prot;
+}
+
+/**
+ * security_mmap_file() - Check if mmap'ing a file is allowed
+ * @file: file
+ * @prot: protection applied by the kernel
+ * @flags: flags
+ *
+ * Check permissions for a mmap operation.  The @file may be NULL, e.g. if
+ * mapping anonymous memory.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_mmap_file(struct file *file, unsigned long prot,
+		       unsigned long flags)
+{
+	return call_int_hook(mmap_file, file, prot, mmap_prot(file, prot),
+			     flags);
+}
+
+/**
+ * security_mmap_backing_file - Check if mmap'ing a backing file is allowed
+ * @vma: the vm_area_struct for the mmap'd region
+ * @backing_file: the backing file being mmap'd
+ * @user_file: the user file being mmap'd
+ *
+ * Check permissions for a mmap operation on a stacked filesystem.  This hook
+ * is called after the security_mmap_file() and is responsible for authorizing
+ * the mmap on @backing_file.  It is important to note that the mmap operation
+ * on @user_file has already been authorized and the @vma->vm_file has been
+ * set to @backing_file.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_mmap_backing_file(struct vm_area_struct *vma,
+			       struct file *backing_file,
+			       struct file *user_file)
+{
+	/* recommended by the stackable filesystem devs */
+	if (WARN_ON_ONCE(!(backing_file->f_mode & FMODE_BACKING)))
+		return -EIO;
+
+	return call_int_hook(mmap_backing_file, vma, backing_file, user_file);
+}
+EXPORT_SYMBOL_GPL(security_mmap_backing_file);
+
+/**
+ * security_mmap_addr() - Check if mmap'ing an address is allowed
+ * @addr: address
+ *
+ * Check permissions for a mmap operation at @addr.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_mmap_addr(unsigned long addr)
+{
+	return call_int_hook(mmap_addr, addr);
+}
+
+/**
+ * security_file_mprotect() - Check if changing memory protections is allowed
+ * @vma: memory region
+ * @reqprot: application requested protection
+ * @prot: protection applied by the kernel
+ *
+ * Check permissions before changing memory access permissions.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
+			   unsigned long prot)
+{
+	return call_int_hook(file_mprotect, vma, reqprot, prot);
+}
+
+/**
+ * security_file_lock() - Check if a file lock is allowed
+ * @file: file
+ * @cmd: lock operation (e.g. F_RDLCK, F_WRLCK)
+ *
+ * Check permission before performing file locking operations.  Note the hook
+ * mediates both flock and fcntl style locks.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_lock(struct file *file, unsigned int cmd)
+{
+	return call_int_hook(file_lock, file, cmd);
+}
+
+/**
+ * security_file_fcntl() - Check if fcntl() op is allowed
+ * @file: file
+ * @cmd: fcntl command
+ * @arg: command argument
+ *
+ * Check permission before allowing the file operation specified by @cmd from
+ * being performed on the file @file.  Note that @arg sometimes represents a
+ * user space pointer; in other cases, it may be a simple integer value.  When
+ * @arg represents a user space pointer, it should never be used by the
+ * security module.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return call_int_hook(file_fcntl, file, cmd, arg);
+}
+
+/**
+ * security_file_set_fowner() - Set the file owner info in the LSM blob
+ * @file: the file
+ *
+ * Save owner security information (typically from current->security) in
+ * file->f_security for later use by the send_sigiotask hook.
+ *
+ * This hook is called with file->f_owner.lock held.
+ *
+ * Return: Returns 0 on success.
+ */
+void security_file_set_fowner(struct file *file)
+{
+	call_void_hook(file_set_fowner, file);
+}
+
+/**
+ * security_file_send_sigiotask() - Check if sending SIGIO/SIGURG is allowed
+ * @tsk: target task
+ * @fown: signal sender
+ * @sig: signal to be sent, SIGIO is sent if 0
+ *
+ * Check permission for the file owner @fown to send SIGIO or SIGURG to the
+ * process @tsk.  Note that this hook is sometimes called from interrupt.  Note
+ * that the fown_struct, @fown, is never outside the context of a struct file,
+ * so the file structure (and associated security information) can always be
+ * obtained: container_of(fown, struct file, f_owner).
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_send_sigiotask(struct task_struct *tsk,
+				 struct fown_struct *fown, int sig)
+{
+	return call_int_hook(file_send_sigiotask, tsk, fown, sig);
+}
+
+/**
+ * security_file_receive() - Check if receiving a file via IPC is allowed
+ * @file: file being received
+ *
+ * This hook allows security modules to control the ability of a process to
+ * receive an open file descriptor via socket IPC.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_receive(struct file *file)
+{
+	return call_int_hook(file_receive, file);
+}
+
+/**
+ * security_file_open() - Save open() time state for late use by the LSM
+ * @file:
+ *
+ * Save open-time permission checking state for later use upon file_permission,
+ * and recheck access if anything has changed since inode_permission.
+ *
+ * We can check if a file is opened for execution (e.g. execve(2) call), either
+ * directly or indirectly (e.g. ELF's ld.so) by checking file->f_flags &
+ * __FMODE_EXEC .
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_open(struct file *file)
+{
+	return call_int_hook(file_open, file);
+}
+
+/**
+ * security_file_post_open() - Evaluate a file after it has been opened
+ * @file: the file
+ * @mask: access mask
+ *
+ * Evaluate an opened file and the access mask requested with open(). The hook
+ * is useful for LSMs that require the file content to be available in order to
+ * make decisions.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_post_open(struct file *file, int mask)
+{
+	return call_int_hook(file_post_open, file, mask);
+}
+EXPORT_SYMBOL_GPL(security_file_post_open);
+
+/**
+ * security_file_truncate() - Check if truncating a file is allowed
+ * @file: file
+ *
+ * Check permission before truncating a file, i.e. using ftruncate.  Note that
+ * truncation permission may also be checked based on the path, using the
+ * @path_truncate hook.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_file_truncate(struct file *file)
+{
+	return call_int_hook(file_truncate, file);
+}
+
+/**
+ * security_task_alloc() - Allocate a task's LSM blob
+ * @task: the task
+ * @clone_flags: flags indicating what is being shared
+ *
+ * Handle allocation of task-related resources.
+ *
+ * Return: Returns a zero on success, negative values on failure.
+ */
+int security_task_alloc(struct task_struct *task, u64 clone_flags)
+{
+	int rc = lsm_task_alloc(task);
+
+	if (rc)
+		return rc;
+	rc = call_int_hook(task_alloc, task, clone_flags);
+	if (unlikely(rc))
+		security_task_free(task);
+	return rc;
+}
+
+/**
+ * security_task_free() - Free a task's LSM blob and related resources
+ * @task: task
+ *
+ * Handle release of task-related resources.  Note that this can be called from
+ * interrupt context.
+ */
+void security_task_free(struct task_struct *task)
+{
+	call_void_hook(task_free, task);
+
+	kfree(task->security);
+	task->security = NULL;
+}
+
+/**
+ * security_cred_alloc_blank() - Allocate the min memory to allow cred_transfer
+ * @cred: credentials
+ * @gfp: gfp flags
+ *
+ * Only allocate sufficient memory and attach to @cred such that
+ * cred_transfer() will not get ENOMEM.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_cred_alloc_blank(struct cred *cred, gfp_t gfp)
+{
+	int rc = lsm_cred_alloc(cred, gfp);
+
+	if (rc)
+		return rc;
+
+	rc = call_int_hook(cred_alloc_blank, cred, gfp);
+	if (unlikely(rc))
+		security_cred_free(cred);
+	return rc;
+}
+
+/**
+ * security_cred_free() - Free the cred's LSM blob and associated resources
+ * @cred: credentials
+ *
+ * Deallocate and clear the cred->security field in a set of credentials.
+ */
+void security_cred_free(struct cred *cred)
+{
+	/*
+	 * There is a failure case in prepare_creds() that
+	 * may result in a call here with ->security being NULL.
+	 */
+	if (unlikely(cred->security == NULL))
+		return;
+
+	call_void_hook(cred_free, cred);
+
+	kfree(cred->security);
+	cred->security = NULL;
+}
+
+/**
+ * security_prepare_creds() - Prepare a new set of credentials
+ * @new: new credentials
+ * @old: original credentials
+ * @gfp: gfp flags
+ *
+ * Prepare a new set of credentials by copying the data from the old set.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp)
+{
+	int rc = lsm_cred_alloc(new, gfp);
+
+	if (rc)
+		return rc;
+
+	rc = call_int_hook(cred_prepare, new, old, gfp);
+	if (unlikely(rc))
+		security_cred_free(new);
+	return rc;
+}
+
+/**
+ * security_transfer_creds() - Transfer creds
+ * @new: target credentials
+ * @old: original credentials
+ *
+ * Transfer data from original creds to new creds.
+ */
+void security_transfer_creds(struct cred *new, const struct cred *old)
+{
+	call_void_hook(cred_transfer, new, old);
+}
+
+/**
+ * security_cred_getsecid() - Get the secid from a set of credentials
+ * @c: credentials
+ * @secid: secid value
+ *
+ * Retrieve the security identifier of the cred structure @c.  In case of
+ * failure, @secid will be set to zero.
+ */
+void security_cred_getsecid(const struct cred *c, u32 *secid)
+{
+	*secid = 0;
+	call_void_hook(cred_getsecid, c, secid);
+}
+EXPORT_SYMBOL(security_cred_getsecid);
+
+/**
+ * security_cred_getlsmprop() - Get the LSM data from a set of credentials
+ * @c: credentials
+ * @prop: destination for the LSM data
+ *
+ * Retrieve the security data of the cred structure @c.  In case of
+ * failure, @prop will be cleared.
+ */
+void security_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop)
+{
+	lsmprop_init(prop);
+	call_void_hook(cred_getlsmprop, c, prop);
+}
+EXPORT_SYMBOL(security_cred_getlsmprop);
+
+/**
+ * security_kernel_act_as() - Set the kernel credentials to act as secid
+ * @new: credentials
+ * @secid: secid
+ *
+ * Set the credentials for a kernel service to act as (subjective context).
+ * The current task must be the one that nominated @secid.
+ *
+ * Return: Returns 0 if successful.
+ */
+int security_kernel_act_as(struct cred *new, u32 secid)
+{
+	return call_int_hook(kernel_act_as, new, secid);
+}
+
+/**
+ * security_kernel_create_files_as() - Set file creation context using an inode
+ * @new: target credentials
+ * @inode: reference inode
+ *
+ * Set the file creation context in a set of credentials to be the same as the
+ * objective context of the specified inode.  The current task must be the one
+ * that nominated @inode.
+ *
+ * Return: Returns 0 if successful.
+ */
+int security_kernel_create_files_as(struct cred *new, struct inode *inode)
+{
+	return call_int_hook(kernel_create_files_as, new, inode);
+}
+
+/**
+ * security_kernel_module_request() - Check if loading a module is allowed
+ * @kmod_name: module name
+ *
+ * Ability to trigger the kernel to automatically upcall to userspace for
+ * userspace to load a kernel module with the given name.
+ *
+ * Return: Returns 0 if successful.
+ */
+int security_kernel_module_request(char *kmod_name)
+{
+	return call_int_hook(kernel_module_request, kmod_name);
+}
+
+/**
+ * security_kernel_read_file() - Read a file specified by userspace
+ * @file: file
+ * @id: file identifier
+ * @contents: trust if security_kernel_post_read_file() will be called
+ *
+ * Read a file specified by userspace.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_kernel_read_file(struct file *file, enum kernel_read_file_id id,
+			      bool contents)
+{
+	return call_int_hook(kernel_read_file, file, id, contents);
+}
+EXPORT_SYMBOL_GPL(security_kernel_read_file);
+
+/**
+ * security_kernel_post_read_file() - Read a file specified by userspace
+ * @file: file
+ * @buf: file contents
+ * @size: size of file contents
+ * @id: file identifier
+ *
+ * Read a file specified by userspace.  This must be paired with a prior call
+ * to security_kernel_read_file() call that indicated this hook would also be
+ * called, see security_kernel_read_file() for more information.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
+				   enum kernel_read_file_id id)
+{
+	return call_int_hook(kernel_post_read_file, file, buf, size, id);
+}
+EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
+
+/**
+ * security_kernel_load_data() - Load data provided by userspace
+ * @id: data identifier
+ * @contents: true if security_kernel_post_load_data() will be called
+ *
+ * Load data provided by userspace.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	return call_int_hook(kernel_load_data, id, contents);
+}
+EXPORT_SYMBOL_GPL(security_kernel_load_data);
+
+/**
+ * security_kernel_post_load_data() - Load userspace data from a non-file source
+ * @buf: data
+ * @size: size of data
+ * @id: data identifier
+ * @description: text description of data, specific to the id value
+ *
+ * Load data provided by a non-file source (usually userspace buffer).  This
+ * must be paired with a prior security_kernel_load_data() call that indicated
+ * this hook would also be called, see security_kernel_load_data() for more
+ * information.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_kernel_post_load_data(char *buf, loff_t size,
+				   enum kernel_load_data_id id,
+				   char *description)
+{
+	return call_int_hook(kernel_post_load_data, buf, size, id, description);
+}
+EXPORT_SYMBOL_GPL(security_kernel_post_load_data);
+
+/**
+ * security_task_fix_setuid() - Update LSM with new user id attributes
+ * @new: updated credentials
+ * @old: credentials being replaced
+ * @flags: LSM_SETID_* flag values
+ *
+ * Update the module's state after setting one or more of the user identity
+ * attributes of the current process.  The @flags parameter indicates which of
+ * the set*uid system calls invoked this hook.  If @new is the set of
+ * credentials that will be installed.  Modifications should be made to this
+ * rather than to @current->cred.
+ *
+ * Return: Returns 0 on success.
+ */
+int security_task_fix_setuid(struct cred *new, const struct cred *old,
+			     int flags)
+{
+	return call_int_hook(task_fix_setuid, new, old, flags);
+}
+
+/**
+ * security_task_fix_setgid() - Update LSM with new group id attributes
+ * @new: updated credentials
+ * @old: credentials being replaced
+ * @flags: LSM_SETID_* flag value
+ *
+ * Update the module's state after setting one or more of the group identity
+ * attributes of the current process.  The @flags parameter indicates which of
+ * the set*gid system calls invoked this hook.  @new is the set of credentials
+ * that will be installed.  Modifications should be made to this rather than to
+ * @current->cred.
+ *
+ * Return: Returns 0 on success.
+ */
+int security_task_fix_setgid(struct cred *new, const struct cred *old,
+			     int flags)
+{
+	return call_int_hook(task_fix_setgid, new, old, flags);
+}
+
+/**
+ * security_task_fix_setgroups() - Update LSM with new supplementary groups
+ * @new: updated credentials
+ * @old: credentials being replaced
+ *
+ * Update the module's state after setting the supplementary group identity
+ * attributes of the current process.  @new is the set of credentials that will
+ * be installed.  Modifications should be made to this rather than to
+ * @current->cred.
+ *
+ * Return: Returns 0 on success.
+ */
+int security_task_fix_setgroups(struct cred *new, const struct cred *old)
+{
+	return call_int_hook(task_fix_setgroups, new, old);
+}
+
+/**
+ * security_task_setpgid() - Check if setting the pgid is allowed
+ * @p: task being modified
+ * @pgid: new pgid
+ *
+ * Check permission before setting the process group identifier of the process
+ * @p to @pgid.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_setpgid(struct task_struct *p, pid_t pgid)
+{
+	return call_int_hook(task_setpgid, p, pgid);
+}
+
+/**
+ * security_task_getpgid() - Check if getting the pgid is allowed
+ * @p: task
+ *
+ * Check permission before getting the process group identifier of the process
+ * @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_getpgid(struct task_struct *p)
+{
+	return call_int_hook(task_getpgid, p);
+}
+
+/**
+ * security_task_getsid() - Check if getting the session id is allowed
+ * @p: task
+ *
+ * Check permission before getting the session identifier of the process @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_getsid(struct task_struct *p)
+{
+	return call_int_hook(task_getsid, p);
+}
+
+/**
+ * security_current_getlsmprop_subj() - Current task's subjective LSM data
+ * @prop: lsm specific information
+ *
+ * Retrieve the subjective security identifier of the current task and return
+ * it in @prop.
+ */
+void security_current_getlsmprop_subj(struct lsm_prop *prop)
+{
+	lsmprop_init(prop);
+	call_void_hook(current_getlsmprop_subj, prop);
+}
+EXPORT_SYMBOL(security_current_getlsmprop_subj);
+
+/**
+ * security_task_getlsmprop_obj() - Get a task's objective LSM data
+ * @p: target task
+ * @prop: lsm specific information
+ *
+ * Retrieve the objective security identifier of the task_struct in @p and
+ * return it in @prop.
+ */
+void security_task_getlsmprop_obj(struct task_struct *p, struct lsm_prop *prop)
+{
+	lsmprop_init(prop);
+	call_void_hook(task_getlsmprop_obj, p, prop);
+}
+EXPORT_SYMBOL(security_task_getlsmprop_obj);
+
+/**
+ * security_task_setnice() - Check if setting a task's nice value is allowed
+ * @p: target task
+ * @nice: nice value
+ *
+ * Check permission before setting the nice value of @p to @nice.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_setnice(struct task_struct *p, int nice)
+{
+	return call_int_hook(task_setnice, p, nice);
+}
+
+/**
+ * security_task_setioprio() - Check if setting a task's ioprio is allowed
+ * @p: target task
+ * @ioprio: ioprio value
+ *
+ * Check permission before setting the ioprio value of @p to @ioprio.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_setioprio(struct task_struct *p, int ioprio)
+{
+	return call_int_hook(task_setioprio, p, ioprio);
+}
+
+/**
+ * security_task_getioprio() - Check if getting a task's ioprio is allowed
+ * @p: task
+ *
+ * Check permission before getting the ioprio value of @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_getioprio(struct task_struct *p)
+{
+	return call_int_hook(task_getioprio, p);
+}
+
+/**
+ * security_task_prlimit() - Check if get/setting resources limits is allowed
+ * @cred: current task credentials
+ * @tcred: target task credentials
+ * @flags: LSM_PRLIMIT_* flag bits indicating a get/set/both
+ *
+ * Check permission before getting and/or setting the resource limits of
+ * another task.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_prlimit(const struct cred *cred, const struct cred *tcred,
+			  unsigned int flags)
+{
+	return call_int_hook(task_prlimit, cred, tcred, flags);
+}
+
+/**
+ * security_task_setrlimit() - Check if setting a new rlimit value is allowed
+ * @p: target task's group leader
+ * @resource: resource whose limit is being set
+ * @new_rlim: new resource limit
+ *
+ * Check permission before setting the resource limits of process @p for
+ * @resource to @new_rlim.  The old resource limit values can be examined by
+ * dereferencing (p->signal->rlim + resource).
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_setrlimit(struct task_struct *p, unsigned int resource,
+			    struct rlimit *new_rlim)
+{
+	return call_int_hook(task_setrlimit, p, resource, new_rlim);
+}
+
+/**
+ * security_task_setscheduler() - Check if setting sched policy/param is allowed
+ * @p: target task
+ *
+ * Check permission before setting scheduling policy and/or parameters of
+ * process @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_setscheduler(struct task_struct *p)
+{
+	return call_int_hook(task_setscheduler, p);
+}
+
+/**
+ * security_task_getscheduler() - Check if getting scheduling info is allowed
+ * @p: target task
+ *
+ * Check permission before obtaining scheduling information for process @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_getscheduler(struct task_struct *p)
+{
+	return call_int_hook(task_getscheduler, p);
+}
+
+/**
+ * security_task_movememory() - Check if moving memory is allowed
+ * @p: task
+ *
+ * Check permission before moving memory owned by process @p.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_movememory(struct task_struct *p)
+{
+	return call_int_hook(task_movememory, p);
+}
+
+/**
+ * security_task_kill() - Check if sending a signal is allowed
+ * @p: target process
+ * @info: signal information
+ * @sig: signal value
+ * @cred: credentials of the signal sender, NULL if @current
+ *
+ * Check permission before sending signal @sig to @p.  @info can be NULL, the
+ * constant 1, or a pointer to a kernel_siginfo structure.  If @info is 1 or
+ * SI_FROMKERNEL(info) is true, then the signal should be viewed as coming from
+ * the kernel and should typically be permitted.  SIGIO signals are handled
+ * separately by the send_sigiotask hook in file_security_ops.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_task_kill(struct task_struct *p, struct kernel_siginfo *info,
+		       int sig, const struct cred *cred)
+{
+	return call_int_hook(task_kill, p, info, sig, cred);
+}
+
+/**
+ * security_task_prctl() - Handle an LSM specific prctl() call
+ * @option: operation
+ * @arg2: argument
+ * @arg3: argument
+ * @arg4: argument
+ * @arg5: argument
+ *
+ * Handle lsm specific prctl() operations.
+ *
+ * Return: Return -ENOSYS if no-one wanted to handle this op, any other value
+ *         to cause prctl() to return immediately with that value.
+ */
+int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+			unsigned long arg4, unsigned long arg5)
+{
+	int thisrc;
+	int rc = LSM_RET_DEFAULT(task_prctl);
+	struct lsm_static_call *scall;
+
+	lsm_for_each_hook(scall, task_prctl) {
+		thisrc = scall->hl->hook.task_prctl(option, arg2, arg3, arg4, arg5);
+		if (thisrc != LSM_RET_DEFAULT(task_prctl)) {
+			rc = thisrc;
+			if (thisrc != 0)
+				break;
+		}
+	}
+	return rc;
+}
+
+/**
+ * security_task_to_inode() - Set the security attributes of a task's inode
+ * @p: task
+ * @inode: inode
+ *
+ * Set the security attributes for an inode based on an associated task's
+ * security attributes, e.g. for /proc/pid inodes.
+ */
+void security_task_to_inode(struct task_struct *p, struct inode *inode)
+{
+	call_void_hook(task_to_inode, p, inode);
+}
+
+/**
+ * security_create_user_ns() - Check if creating a new userns is allowed
+ * @cred: prepared creds
+ *
+ * Check permission prior to creating a new user namespace.
+ *
+ * Return: Returns 0 if successful, otherwise < 0 error code.
+ */
+int security_create_user_ns(const struct cred *cred)
+{
+	return call_int_hook(userns_create, cred);
+}
+
+/**
+ * security_ipc_permission() - Check if sysv ipc access is allowed
+ * @ipcp: ipc permission structure
+ * @flag: requested permissions
+ *
+ * Check permissions for access to IPC.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag)
+{
+	return call_int_hook(ipc_permission, ipcp, flag);
+}
+
+/**
+ * security_ipc_getlsmprop() - Get the sysv ipc object LSM data
+ * @ipcp: ipc permission structure
+ * @prop: pointer to lsm information
+ *
+ * Get the lsm information associated with the ipc object.
+ */
+
+void security_ipc_getlsmprop(struct kern_ipc_perm *ipcp, struct lsm_prop *prop)
+{
+	lsmprop_init(prop);
+	call_void_hook(ipc_getlsmprop, ipcp, prop);
+}
+
+/**
+ * security_msg_msg_alloc() - Allocate a sysv ipc message LSM blob
+ * @msg: message structure
+ *
+ * Allocate and attach a security structure to the msg->security field.  The
+ * security field is initialized to NULL when the structure is first created.
+ *
+ * Return: Return 0 if operation was successful and permission is granted.
+ */
+int security_msg_msg_alloc(struct msg_msg *msg)
+{
+	int rc = lsm_msg_msg_alloc(msg);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(msg_msg_alloc_security, msg);
+	if (unlikely(rc))
+		security_msg_msg_free(msg);
+	return rc;
+}
+
+/**
+ * security_msg_msg_free() - Free a sysv ipc message LSM blob
+ * @msg: message structure
+ *
+ * Deallocate the security structure for this message.
+ */
+void security_msg_msg_free(struct msg_msg *msg)
+{
+	call_void_hook(msg_msg_free_security, msg);
+	kfree(msg->security);
+	msg->security = NULL;
+}
+
+/**
+ * security_msg_queue_alloc() - Allocate a sysv ipc msg queue LSM blob
+ * @msq: sysv ipc permission structure
+ *
+ * Allocate and attach a security structure to @msg. The security field is
+ * initialized to NULL when the structure is first created.
+ *
+ * Return: Returns 0 if operation was successful and permission is granted.
+ */
+int security_msg_queue_alloc(struct kern_ipc_perm *msq)
+{
+	int rc = lsm_ipc_alloc(msq);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(msg_queue_alloc_security, msq);
+	if (unlikely(rc))
+		security_msg_queue_free(msq);
+	return rc;
+}
+
+/**
+ * security_msg_queue_free() - Free a sysv ipc msg queue LSM blob
+ * @msq: sysv ipc permission structure
+ *
+ * Deallocate security field @perm->security for the message queue.
+ */
+void security_msg_queue_free(struct kern_ipc_perm *msq)
+{
+	call_void_hook(msg_queue_free_security, msq);
+	kfree(msq->security);
+	msq->security = NULL;
+}
+
+/**
+ * security_msg_queue_associate() - Check if a msg queue operation is allowed
+ * @msq: sysv ipc permission structure
+ * @msqflg: operation flags
+ *
+ * Check permission when a message queue is requested through the msgget system
+ * call. This hook is only called when returning the message queue identifier
+ * for an existing message queue, not when a new message queue is created.
+ *
+ * Return: Return 0 if permission is granted.
+ */
+int security_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg)
+{
+	return call_int_hook(msg_queue_associate, msq, msqflg);
+}
+
+/**
+ * security_msg_queue_msgctl() - Check if a msg queue operation is allowed
+ * @msq: sysv ipc permission structure
+ * @cmd: operation
+ *
+ * Check permission when a message control operation specified by @cmd is to be
+ * performed on the message queue with permissions.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd)
+{
+	return call_int_hook(msg_queue_msgctl, msq, cmd);
+}
+
+/**
+ * security_msg_queue_msgsnd() - Check if sending a sysv ipc message is allowed
+ * @msq: sysv ipc permission structure
+ * @msg: message
+ * @msqflg: operation flags
+ *
+ * Check permission before a message, @msg, is enqueued on the message queue
+ * with permissions specified in @msq.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_msg_queue_msgsnd(struct kern_ipc_perm *msq,
+			      struct msg_msg *msg, int msqflg)
+{
+	return call_int_hook(msg_queue_msgsnd, msq, msg, msqflg);
+}
+
+/**
+ * security_msg_queue_msgrcv() - Check if receiving a sysv ipc msg is allowed
+ * @msq: sysv ipc permission structure
+ * @msg: message
+ * @target: target task
+ * @type: type of message requested
+ * @mode: operation flags
+ *
+ * Check permission before a message, @msg, is removed from the message	queue.
+ * The @target task structure contains a pointer to the process that will be
+ * receiving the message (not equal to the current process when inline receives
+ * are being performed).
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg,
+			      struct task_struct *target, long type, int mode)
+{
+	return call_int_hook(msg_queue_msgrcv, msq, msg, target, type, mode);
+}
+
+/**
+ * security_shm_alloc() - Allocate a sysv shm LSM blob
+ * @shp: sysv ipc permission structure
+ *
+ * Allocate and attach a security structure to the @shp security field.  The
+ * security field is initialized to NULL when the structure is first created.
+ *
+ * Return: Returns 0 if operation was successful and permission is granted.
+ */
+int security_shm_alloc(struct kern_ipc_perm *shp)
+{
+	int rc = lsm_ipc_alloc(shp);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(shm_alloc_security, shp);
+	if (unlikely(rc))
+		security_shm_free(shp);
+	return rc;
+}
+
+/**
+ * security_shm_free() - Free a sysv shm LSM blob
+ * @shp: sysv ipc permission structure
+ *
+ * Deallocate the security structure @perm->security for the memory segment.
+ */
+void security_shm_free(struct kern_ipc_perm *shp)
+{
+	call_void_hook(shm_free_security, shp);
+	kfree(shp->security);
+	shp->security = NULL;
+}
+
+/**
+ * security_shm_associate() - Check if a sysv shm operation is allowed
+ * @shp: sysv ipc permission structure
+ * @shmflg: operation flags
+ *
+ * Check permission when a shared memory region is requested through the shmget
+ * system call. This hook is only called when returning the shared memory
+ * region identifier for an existing region, not when a new shared memory
+ * region is created.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_shm_associate(struct kern_ipc_perm *shp, int shmflg)
+{
+	return call_int_hook(shm_associate, shp, shmflg);
+}
+
+/**
+ * security_shm_shmctl() - Check if a sysv shm operation is allowed
+ * @shp: sysv ipc permission structure
+ * @cmd: operation
+ *
+ * Check permission when a shared memory control operation specified by @cmd is
+ * to be performed on the shared memory region with permissions in @shp.
+ *
+ * Return: Return 0 if permission is granted.
+ */
+int security_shm_shmctl(struct kern_ipc_perm *shp, int cmd)
+{
+	return call_int_hook(shm_shmctl, shp, cmd);
+}
+
+/**
+ * security_shm_shmat() - Check if a sysv shm attach operation is allowed
+ * @shp: sysv ipc permission structure
+ * @shmaddr: address of memory region to attach
+ * @shmflg: operation flags
+ *
+ * Check permissions prior to allowing the shmat system call to attach the
+ * shared memory segment with permissions @shp to the data segment of the
+ * calling process. The attaching address is specified by @shmaddr.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_shm_shmat(struct kern_ipc_perm *shp,
+		       char __user *shmaddr, int shmflg)
+{
+	return call_int_hook(shm_shmat, shp, shmaddr, shmflg);
+}
+
+/**
+ * security_sem_alloc() - Allocate a sysv semaphore LSM blob
+ * @sma: sysv ipc permission structure
+ *
+ * Allocate and attach a security structure to the @sma security field. The
+ * security field is initialized to NULL when the structure is first created.
+ *
+ * Return: Returns 0 if operation was successful and permission is granted.
+ */
+int security_sem_alloc(struct kern_ipc_perm *sma)
+{
+	int rc = lsm_ipc_alloc(sma);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(sem_alloc_security, sma);
+	if (unlikely(rc))
+		security_sem_free(sma);
+	return rc;
+}
+
+/**
+ * security_sem_free() - Free a sysv semaphore LSM blob
+ * @sma: sysv ipc permission structure
+ *
+ * Deallocate security structure @sma->security for the semaphore.
+ */
+void security_sem_free(struct kern_ipc_perm *sma)
+{
+	call_void_hook(sem_free_security, sma);
+	kfree(sma->security);
+	sma->security = NULL;
+}
+
+/**
+ * security_sem_associate() - Check if a sysv semaphore operation is allowed
+ * @sma: sysv ipc permission structure
+ * @semflg: operation flags
+ *
+ * Check permission when a semaphore is requested through the semget system
+ * call. This hook is only called when returning the semaphore identifier for
+ * an existing semaphore, not when a new one must be created.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sem_associate(struct kern_ipc_perm *sma, int semflg)
+{
+	return call_int_hook(sem_associate, sma, semflg);
+}
+
+/**
+ * security_sem_semctl() - Check if a sysv semaphore operation is allowed
+ * @sma: sysv ipc permission structure
+ * @cmd: operation
+ *
+ * Check permission when a semaphore operation specified by @cmd is to be
+ * performed on the semaphore.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sem_semctl(struct kern_ipc_perm *sma, int cmd)
+{
+	return call_int_hook(sem_semctl, sma, cmd);
+}
+
+/**
+ * security_sem_semop() - Check if a sysv semaphore operation is allowed
+ * @sma: sysv ipc permission structure
+ * @sops: operations to perform
+ * @nsops: number of operations
+ * @alter: flag indicating changes will be made
+ *
+ * Check permissions before performing operations on members of the semaphore
+ * set. If the @alter flag is nonzero, the semaphore set may be modified.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sem_semop(struct kern_ipc_perm *sma, struct sembuf *sops,
+		       unsigned nsops, int alter)
+{
+	return call_int_hook(sem_semop, sma, sops, nsops, alter);
+}
+
+/**
+ * security_d_instantiate() - Populate an inode's LSM state based on a dentry
+ * @dentry: dentry
+ * @inode: inode
+ *
+ * Fill in @inode security information for a @dentry if allowed.
+ */
+void security_d_instantiate(struct dentry *dentry, struct inode *inode)
+{
+	if (unlikely(inode && IS_PRIVATE(inode)))
+		return;
+	call_void_hook(d_instantiate, dentry, inode);
+}
+EXPORT_SYMBOL(security_d_instantiate);
+
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_getselfattr - Read an LSM attribute of the current process.
+ * @attr: which attribute to return
+ * @uctx: the user-space destination for the information, or NULL
+ * @size: pointer to the size of space available to receive the data
+ * @flags: special handling options. LSM_FLAG_SINGLE indicates that only
+ * attributes associated with the LSM identified in the passed @ctx be
+ * reported.
+ *
+ * A NULL value for @uctx can be used to get both the number of attributes
+ * and the size of the data.
+ *
+ * Returns the number of attributes found on success, negative value
+ * on error. @size is reset to the total size of the data.
+ * If @size is insufficient to contain the data -E2BIG is returned.
+ */
+int security_getselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 u32 __user *size, u32 flags)
+{
+	struct lsm_static_call *scall;
+	struct lsm_ctx lctx = { .id = LSM_ID_UNDEF, };
+	u8 __user *base = (u8 __user *)uctx;
+	u32 entrysize;
+	u32 total = 0;
+	u32 left;
+	bool toobig = false;
+	bool single = false;
+	int count = 0;
+	int rc;
+
+	if (attr == LSM_ATTR_UNDEF)
+		return -EINVAL;
+	if (size == NULL)
+		return -EINVAL;
+	if (get_user(left, size))
+		return -EFAULT;
+
+	if (flags) {
+		/*
+		 * Only flag supported is LSM_FLAG_SINGLE
+		 */
+		if (flags != LSM_FLAG_SINGLE || !uctx)
+			return -EINVAL;
+		if (copy_from_user(&lctx, uctx, sizeof(lctx)))
+			return -EFAULT;
+		/*
+		 * If the LSM ID isn't specified it is an error.
+		 */
+		if (lctx.id == LSM_ID_UNDEF)
+			return -EINVAL;
+		single = true;
+	}
+
+	/*
+	 * In the usual case gather all the data from the LSMs.
+	 * In the single case only get the data from the LSM specified.
+	 */
+	lsm_for_each_hook(scall, getselfattr) {
+		if (single && lctx.id != scall->hl->lsmid->id)
+			continue;
+		entrysize = left;
+		if (base)
+			uctx = (struct lsm_ctx __user *)(base + total);
+		rc = scall->hl->hook.getselfattr(attr, uctx, &entrysize, flags);
+		if (rc == -EOPNOTSUPP)
+			continue;
+		if (rc == -E2BIG) {
+			rc = 0;
+			left = 0;
+			toobig = true;
+		} else if (rc < 0)
+			return rc;
+		else
+			left -= entrysize;
+
+		total += entrysize;
+		count += rc;
+		if (single)
+			break;
+	}
+	if (put_user(total, size))
+		return -EFAULT;
+	if (toobig)
+		return -E2BIG;
+	if (count == 0)
+		return LSM_RET_DEFAULT(getselfattr);
+	return count;
+}
+
+/*
+ * Please keep this in sync with it's counterpart in security/lsm_syscalls.c
+ */
+
+/**
+ * security_setselfattr - Set an LSM attribute on the current process.
+ * @attr: which attribute to set
+ * @uctx: the user-space source for the information
+ * @size: the size of the data
+ * @flags: reserved for future use, must be 0
+ *
+ * Set an LSM attribute for the current process. The LSM, attribute
+ * and new value are included in @uctx.
+ *
+ * Returns 0 on success, -EINVAL if the input is inconsistent, -EFAULT
+ * if the user buffer is inaccessible, E2BIG if size is too big, or an
+ * LSM specific failure.
+ */
+int security_setselfattr(unsigned int attr, struct lsm_ctx __user *uctx,
+			 u32 size, u32 flags)
+{
+	struct lsm_static_call *scall;
+	struct lsm_ctx *lctx;
+	int rc = LSM_RET_DEFAULT(setselfattr);
+	u64 required_len;
+
+	if (flags)
+		return -EINVAL;
+	if (size < sizeof(*lctx))
+		return -EINVAL;
+	if (size > PAGE_SIZE)
+		return -E2BIG;
+
+	lctx = memdup_user(uctx, size);
+	if (IS_ERR(lctx))
+		return PTR_ERR(lctx);
+
+	if (size < lctx->len ||
+	    check_add_overflow(sizeof(*lctx), lctx->ctx_len, &required_len) ||
+	    lctx->len < required_len) {
+		rc = -EINVAL;
+		goto free_out;
+	}
+
+	lsm_for_each_hook(scall, setselfattr)
+		if ((scall->hl->lsmid->id) == lctx->id) {
+			rc = scall->hl->hook.setselfattr(attr, lctx, size, flags);
+			break;
+		}
+
+free_out:
+	kfree(lctx);
+	return rc;
+}
+
+/**
+ * security_getprocattr() - Read an attribute for a task
+ * @p: the task
+ * @lsmid: LSM identification
+ * @name: attribute name
+ * @value: attribute value
+ *
+ * Read attribute @name for task @p and store it into @value if allowed.
+ *
+ * Return: Returns the length of @value on success, a negative value otherwise.
+ */
+int security_getprocattr(struct task_struct *p, int lsmid, const char *name,
+			 char **value)
+{
+	struct lsm_static_call *scall;
+
+	lsm_for_each_hook(scall, getprocattr) {
+		if (lsmid != 0 && lsmid != scall->hl->lsmid->id)
+			continue;
+		return scall->hl->hook.getprocattr(p, name, value);
+	}
+	return LSM_RET_DEFAULT(getprocattr);
+}
+
+/**
+ * security_setprocattr() - Set an attribute for a task
+ * @lsmid: LSM identification
+ * @name: attribute name
+ * @value: attribute value
+ * @size: attribute value size
+ *
+ * Write (set) the current task's attribute @name to @value, size @size if
+ * allowed.
+ *
+ * Return: Returns bytes written on success, a negative value otherwise.
+ */
+int security_setprocattr(int lsmid, const char *name, void *value, size_t size)
+{
+	struct lsm_static_call *scall;
+
+	lsm_for_each_hook(scall, setprocattr) {
+		if (lsmid != 0 && lsmid != scall->hl->lsmid->id)
+			continue;
+		return scall->hl->hook.setprocattr(name, value, size);
+	}
+	return LSM_RET_DEFAULT(setprocattr);
+}
+
+/**
+ * security_ismaclabel() - Check if the named attribute is a MAC label
+ * @name: full extended attribute name
+ *
+ * Check if the extended attribute specified by @name represents a MAC label.
+ *
+ * Return: Returns 1 if name is a MAC attribute otherwise returns 0.
+ */
+int security_ismaclabel(const char *name)
+{
+	return call_int_hook(ismaclabel, name);
+}
+EXPORT_SYMBOL(security_ismaclabel);
+
+/**
+ * security_secid_to_secctx() - Convert a secid to a secctx
+ * @secid: secid
+ * @cp: the LSM context
+ *
+ * Convert secid to security context.  If @cp is NULL the length of the
+ * result will be returned, but no data will be returned.  This
+ * does mean that the length could change between calls to check the length and
+ * the next call which actually allocates and returns the data.
+ *
+ * Return: Return length of data on success, error on failure.
+ */
+int security_secid_to_secctx(u32 secid, struct lsm_context *cp)
+{
+	return call_int_hook(secid_to_secctx, secid, cp);
+}
+EXPORT_SYMBOL(security_secid_to_secctx);
+
+/**
+ * security_lsmprop_to_secctx() - Convert a lsm_prop to a secctx
+ * @prop: lsm specific information
+ * @cp: the LSM context
+ * @lsmid: which security module to report
+ *
+ * Convert a @prop entry to security context.  If @cp is NULL the
+ * length of the result will be returned. This does mean that the
+ * length could change between calls to check the length and the
+ * next call which actually allocates and returns the @cp.
+ *
+ * @lsmid identifies which LSM should supply the context.
+ * A value of LSM_ID_UNDEF indicates that the first LSM suppling
+ * the hook should be used. This is used in cases where the
+ * ID of the supplying LSM is unambiguous.
+ *
+ * Return: Return length of data on success, error on failure.
+ */
+int security_lsmprop_to_secctx(struct lsm_prop *prop, struct lsm_context *cp,
+			       int lsmid)
+{
+	struct lsm_static_call *scall;
+
+	lsm_for_each_hook(scall, lsmprop_to_secctx) {
+		if (lsmid != LSM_ID_UNDEF && lsmid != scall->hl->lsmid->id)
+			continue;
+		return scall->hl->hook.lsmprop_to_secctx(prop, cp);
+	}
+	return LSM_RET_DEFAULT(lsmprop_to_secctx);
+}
+EXPORT_SYMBOL(security_lsmprop_to_secctx);
+
+/**
+ * security_secctx_to_secid() - Convert a secctx to a secid
+ * @secdata: secctx
+ * @seclen: length of secctx
+ * @secid: secid
+ *
+ * Convert security context to secid.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
+{
+	*secid = 0;
+	return call_int_hook(secctx_to_secid, secdata, seclen, secid);
+}
+EXPORT_SYMBOL(security_secctx_to_secid);
+
+/**
+ * security_release_secctx() - Free a secctx buffer
+ * @cp: the security context
+ *
+ * Release the security context.
+ */
+void security_release_secctx(struct lsm_context *cp)
+{
+	call_void_hook(release_secctx, cp);
+	memset(cp, 0, sizeof(*cp));
+}
+EXPORT_SYMBOL(security_release_secctx);
+
+/**
+ * security_inode_invalidate_secctx() - Invalidate an inode's security label
+ * @inode: inode
+ *
+ * Notify the security module that it must revalidate the security context of
+ * an inode.
+ */
+void security_inode_invalidate_secctx(struct inode *inode)
+{
+	call_void_hook(inode_invalidate_secctx, inode);
+}
+EXPORT_SYMBOL(security_inode_invalidate_secctx);
+
+/**
+ * security_inode_notifysecctx() - Notify the LSM of an inode's security label
+ * @inode: inode
+ * @ctx: secctx
+ * @ctxlen: length of secctx
+ *
+ * Notify the security module of what the security context of an inode should
+ * be.  Initializes the incore security context managed by the security module
+ * for this inode.  Example usage: NFS client invokes this hook to initialize
+ * the security context in its incore inode to the value provided by the server
+ * for the file when the server returned the file's attributes to the client.
+ * Must be called with inode->i_mutex locked.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
+{
+	return call_int_hook(inode_notifysecctx, inode, ctx, ctxlen);
+}
+EXPORT_SYMBOL(security_inode_notifysecctx);
+
+/**
+ * security_inode_setsecctx() - Change the security label of an inode
+ * @dentry: inode
+ * @ctx: secctx
+ * @ctxlen: length of secctx
+ *
+ * Change the security context of an inode.  Updates the incore security
+ * context managed by the security module and invokes the fs code as needed
+ * (via __vfs_setxattr_noperm) to update any backing xattrs that represent the
+ * context.  Example usage: NFS server invokes this hook to change the security
+ * context in its incore inode and on the backing filesystem to a value
+ * provided by the client on a SETATTR operation.  Must be called with
+ * inode->i_mutex locked.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
+{
+	return call_int_hook(inode_setsecctx, dentry, ctx, ctxlen);
+}
+EXPORT_SYMBOL(security_inode_setsecctx);
+
+/**
+ * security_inode_getsecctx() - Get the security label of an inode
+ * @inode: inode
+ * @cp: security context
+ *
+ * On success, returns 0 and fills out @cp with the security context
+ * for the given @inode.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_inode_getsecctx(struct inode *inode, struct lsm_context *cp)
+{
+	memset(cp, 0, sizeof(*cp));
+	return call_int_hook(inode_getsecctx, inode, cp);
+}
+EXPORT_SYMBOL(security_inode_getsecctx);
+
+#ifdef CONFIG_WATCH_QUEUE
+/**
+ * security_post_notification() - Check if a watch notification can be posted
+ * @w_cred: credentials of the task that set the watch
+ * @cred: credentials of the task which triggered the watch
+ * @n: the notification
+ *
+ * Check to see if a watch notification can be posted to a particular queue.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_post_notification(const struct cred *w_cred,
+			       const struct cred *cred,
+			       struct watch_notification *n)
+{
+	return call_int_hook(post_notification, w_cred, cred, n);
+}
+#endif /* CONFIG_WATCH_QUEUE */
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+/**
+ * security_watch_key() - Check if a task is allowed to watch for key events
+ * @key: the key to watch
+ *
+ * Check to see if a process is allowed to watch for event notifications from
+ * a key or keyring.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_watch_key(struct key *key)
+{
+	return call_int_hook(watch_key, key);
+}
+#endif /* CONFIG_KEY_NOTIFICATIONS */
+
+#ifdef CONFIG_SECURITY_NETWORK
+/**
+ * security_netlink_send() - Save info and check if netlink sending is allowed
+ * @sk: sending socket
+ * @skb: netlink message
+ *
+ * Save security information for a netlink message so that permission checking
+ * can be performed when the message is processed.  The security information
+ * can be saved using the eff_cap field of the netlink_skb_parms structure.
+ * Also may be used to provide fine grained control over message transmission.
+ *
+ * Return: Returns 0 if the information was successfully saved and message is
+ *         allowed to be transmitted.
+ */
+int security_netlink_send(struct sock *sk, struct sk_buff *skb)
+{
+	return call_int_hook(netlink_send, sk, skb);
+}
+
+/**
+ * security_unix_stream_connect() - Check if a AF_UNIX stream is allowed
+ * @sock: originating sock
+ * @other: peer sock
+ * @newsk: new sock
+ *
+ * Check permissions before establishing a Unix domain stream connection
+ * between @sock and @other.
+ *
+ * The @unix_stream_connect and @unix_may_send hooks were necessary because
+ * Linux provides an alternative to the conventional file name space for Unix
+ * domain sockets.  Whereas binding and connecting to sockets in the file name
+ * space is mediated by the typical file permissions (and caught by the mknod
+ * and permission hooks in inode_security_ops), binding and connecting to
+ * sockets in the abstract name space is completely unmediated.  Sufficient
+ * control of Unix domain sockets in the abstract name space isn't possible
+ * using only the socket layer hooks, since we need to know the actual target
+ * socket, which is not looked up until we are inside the af_unix code.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_unix_stream_connect(struct sock *sock, struct sock *other,
+				 struct sock *newsk)
+{
+	return call_int_hook(unix_stream_connect, sock, other, newsk);
+}
+EXPORT_SYMBOL(security_unix_stream_connect);
+
+/**
+ * security_unix_may_send() - Check if AF_UNIX socket can send datagrams
+ * @sock: originating sock
+ * @other: peer sock
+ *
+ * Check permissions before connecting or sending datagrams from @sock to
+ * @other.
+ *
+ * The @unix_stream_connect and @unix_may_send hooks were necessary because
+ * Linux provides an alternative to the conventional file name space for Unix
+ * domain sockets.  Whereas binding and connecting to sockets in the file name
+ * space is mediated by the typical file permissions (and caught by the mknod
+ * and permission hooks in inode_security_ops), binding and connecting to
+ * sockets in the abstract name space is completely unmediated.  Sufficient
+ * control of Unix domain sockets in the abstract name space isn't possible
+ * using only the socket layer hooks, since we need to know the actual target
+ * socket, which is not looked up until we are inside the af_unix code.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_unix_may_send(struct socket *sock,  struct socket *other)
+{
+	return call_int_hook(unix_may_send, sock, other);
+}
+EXPORT_SYMBOL(security_unix_may_send);
+
+/**
+ * security_socket_create() - Check if creating a new socket is allowed
+ * @family: protocol family
+ * @type: communications type
+ * @protocol: requested protocol
+ * @kern: set to 1 if a kernel socket is requested
+ *
+ * Check permissions prior to creating a new socket.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_create(int family, int type, int protocol, int kern)
+{
+	return call_int_hook(socket_create, family, type, protocol, kern);
+}
+
+/**
+ * security_socket_post_create() - Initialize a newly created socket
+ * @sock: socket
+ * @family: protocol family
+ * @type: communications type
+ * @protocol: requested protocol
+ * @kern: set to 1 if a kernel socket is requested
+ *
+ * This hook allows a module to update or allocate a per-socket security
+ * structure. Note that the security field was not added directly to the socket
+ * structure, but rather, the socket security information is stored in the
+ * associated inode.  Typically, the inode alloc_security hook will allocate
+ * and attach security information to SOCK_INODE(sock)->i_security.  This hook
+ * may be used to update the SOCK_INODE(sock)->i_security field with additional
+ * information that wasn't available when the inode was allocated.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_post_create(struct socket *sock, int family,
+				int type, int protocol, int kern)
+{
+	return call_int_hook(socket_post_create, sock, family, type,
+			     protocol, kern);
+}
+
+/**
+ * security_socket_socketpair() - Check if creating a socketpair is allowed
+ * @socka: first socket
+ * @sockb: second socket
+ *
+ * Check permissions before creating a fresh pair of sockets.
+ *
+ * Return: Returns 0 if permission is granted and the connection was
+ *         established.
+ */
+int security_socket_socketpair(struct socket *socka, struct socket *sockb)
+{
+	return call_int_hook(socket_socketpair, socka, sockb);
+}
+EXPORT_SYMBOL(security_socket_socketpair);
+
+/**
+ * security_socket_bind() - Check if a socket bind operation is allowed
+ * @sock: socket
+ * @address: requested bind address
+ * @addrlen: length of address
+ *
+ * Check permission before socket protocol layer bind operation is performed
+ * and the socket @sock is bound to the address specified in the @address
+ * parameter.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_bind(struct socket *sock,
+			 struct sockaddr *address, int addrlen)
+{
+	return call_int_hook(socket_bind, sock, address, addrlen);
+}
+
+/**
+ * security_socket_connect() - Check if a socket connect operation is allowed
+ * @sock: socket
+ * @address: address of remote connection point
+ * @addrlen: length of address
+ *
+ * Check permission before socket protocol layer connect operation attempts to
+ * connect socket @sock to a remote address, @address.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_connect(struct socket *sock,
+			    struct sockaddr *address, int addrlen)
+{
+	return call_int_hook(socket_connect, sock, address, addrlen);
+}
+
+/**
+ * security_socket_listen() - Check if a socket is allowed to listen
+ * @sock: socket
+ * @backlog: connection queue size
+ *
+ * Check permission before socket protocol layer listen operation.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_listen(struct socket *sock, int backlog)
+{
+	return call_int_hook(socket_listen, sock, backlog);
+}
+
+/**
+ * security_socket_accept() - Check if a socket is allowed to accept connections
+ * @sock: listening socket
+ * @newsock: newly creation connection socket
+ *
+ * Check permission before accepting a new connection.  Note that the new
+ * socket, @newsock, has been created and some information copied to it, but
+ * the accept operation has not actually been performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_accept(struct socket *sock, struct socket *newsock)
+{
+	return call_int_hook(socket_accept, sock, newsock);
+}
+
+/**
+ * security_socket_sendmsg() - Check if sending a message is allowed
+ * @sock: sending socket
+ * @msg: message to send
+ * @size: size of message
+ *
+ * Check permission before transmitting a message to another socket.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_sendmsg(struct socket *sock, struct msghdr *msg, int size)
+{
+	return call_int_hook(socket_sendmsg, sock, msg, size);
+}
+
+/**
+ * security_socket_recvmsg() - Check if receiving a message is allowed
+ * @sock: receiving socket
+ * @msg: message to receive
+ * @size: size of message
+ * @flags: operational flags
+ *
+ * Check permission before receiving a message from a socket.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_recvmsg(struct socket *sock, struct msghdr *msg,
+			    int size, int flags)
+{
+	return call_int_hook(socket_recvmsg, sock, msg, size, flags);
+}
+
+/**
+ * security_socket_getsockname() - Check if reading the socket addr is allowed
+ * @sock: socket
+ *
+ * Check permission before reading the local address (name) of the socket
+ * object.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_getsockname(struct socket *sock)
+{
+	return call_int_hook(socket_getsockname, sock);
+}
+
+/**
+ * security_socket_getpeername() - Check if reading the peer's addr is allowed
+ * @sock: socket
+ *
+ * Check permission before the remote address (name) of a socket object.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_getpeername(struct socket *sock)
+{
+	return call_int_hook(socket_getpeername, sock);
+}
+
+/**
+ * security_socket_getsockopt() - Check if reading a socket option is allowed
+ * @sock: socket
+ * @level: option's protocol level
+ * @optname: option name
+ *
+ * Check permissions before retrieving the options associated with socket
+ * @sock.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_getsockopt(struct socket *sock, int level, int optname)
+{
+	return call_int_hook(socket_getsockopt, sock, level, optname);
+}
+
+/**
+ * security_socket_setsockopt() - Check if setting a socket option is allowed
+ * @sock: socket
+ * @level: option's protocol level
+ * @optname: option name
+ *
+ * Check permissions before setting the options associated with socket @sock.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_setsockopt(struct socket *sock, int level, int optname)
+{
+	return call_int_hook(socket_setsockopt, sock, level, optname);
+}
+
+/**
+ * security_socket_shutdown() - Checks if shutting down the socket is allowed
+ * @sock: socket
+ * @how: flag indicating how sends and receives are handled
+ *
+ * Checks permission before all or part of a connection on the socket @sock is
+ * shut down.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_socket_shutdown(struct socket *sock, int how)
+{
+	return call_int_hook(socket_shutdown, sock, how);
+}
+
+/**
+ * security_sock_rcv_skb() - Check if an incoming network packet is allowed
+ * @sk: destination sock
+ * @skb: incoming packet
+ *
+ * Check permissions on incoming network packets.  This hook is distinct from
+ * Netfilter's IP input hooks since it is the first time that the incoming
+ * sk_buff @skb has been associated with a particular socket, @sk.  Must not
+ * sleep inside this hook because some callers hold spinlocks.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	return call_int_hook(socket_sock_rcv_skb, sk, skb);
+}
+EXPORT_SYMBOL(security_sock_rcv_skb);
+
+/**
+ * security_socket_getpeersec_stream() - Get the remote peer label
+ * @sock: socket
+ * @optval: destination buffer
+ * @optlen: size of peer label copied into the buffer
+ * @len: maximum size of the destination buffer
+ *
+ * This hook allows the security module to provide peer socket security state
+ * for unix or connected tcp sockets to userspace via getsockopt SO_GETPEERSEC.
+ * For tcp sockets this can be meaningful if the socket is associated with an
+ * ipsec SA.
+ *
+ * Return: Returns 0 if all is well, otherwise, typical getsockopt return
+ *         values.
+ */
+int security_socket_getpeersec_stream(struct socket *sock, sockptr_t optval,
+				      sockptr_t optlen, unsigned int len)
+{
+	return call_int_hook(socket_getpeersec_stream, sock, optval, optlen,
+			     len);
+}
+
+/**
+ * security_socket_getpeersec_dgram() - Get the remote peer label
+ * @sock: socket
+ * @skb: datagram packet
+ * @secid: remote peer label secid
+ *
+ * This hook allows the security module to provide peer socket security state
+ * for udp sockets on a per-packet basis to userspace via getsockopt
+ * SO_GETPEERSEC. The application must first have indicated the IP_PASSSEC
+ * option via getsockopt. It can then retrieve the security state returned by
+ * this hook for a packet via the SCM_SECURITY ancillary message type.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_socket_getpeersec_dgram(struct socket *sock,
+				     struct sk_buff *skb, u32 *secid)
+{
+	return call_int_hook(socket_getpeersec_dgram, sock, skb, secid);
+}
+EXPORT_SYMBOL(security_socket_getpeersec_dgram);
+
+/**
+ * lsm_sock_alloc - allocate a composite sock blob
+ * @sock: the sock that needs a blob
+ * @gfp: allocation mode
+ *
+ * Allocate the sock blob for all the modules
+ *
+ * Returns 0, or -ENOMEM if memory can't be allocated.
+ */
+static int lsm_sock_alloc(struct sock *sock, gfp_t gfp)
+{
+	return lsm_blob_alloc(&sock->sk_security, blob_sizes.lbs_sock, gfp);
+}
+
+/**
+ * security_sk_alloc() - Allocate and initialize a sock's LSM blob
+ * @sk: sock
+ * @family: protocol family
+ * @priority: gfp flags
+ *
+ * Allocate and attach a security structure to the sk->sk_security field, which
+ * is used to copy security attributes between local stream sockets.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
+{
+	int rc = lsm_sock_alloc(sk, priority);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(sk_alloc_security, sk, family, priority);
+	if (unlikely(rc))
+		security_sk_free(sk);
+	return rc;
+}
+
+/**
+ * security_sk_free() - Free the sock's LSM blob
+ * @sk: sock
+ *
+ * Deallocate security structure.
+ */
+void security_sk_free(struct sock *sk)
+{
+	call_void_hook(sk_free_security, sk);
+	kfree(sk->sk_security);
+	sk->sk_security = NULL;
+}
+
+/**
+ * security_sk_clone() - Clone a sock's LSM state
+ * @sk: original sock
+ * @newsk: target sock
+ *
+ * Clone/copy security structure.
+ */
+void security_sk_clone(const struct sock *sk, struct sock *newsk)
+{
+	call_void_hook(sk_clone_security, sk, newsk);
+}
+EXPORT_SYMBOL(security_sk_clone);
+
+/**
+ * security_sk_classify_flow() - Set a flow's secid based on socket
+ * @sk: original socket
+ * @flic: target flow
+ *
+ * Set the target flow's secid to socket's secid.
+ */
+void security_sk_classify_flow(const struct sock *sk, struct flowi_common *flic)
+{
+	call_void_hook(sk_getsecid, sk, &flic->flowic_secid);
+}
+EXPORT_SYMBOL(security_sk_classify_flow);
+
+/**
+ * security_req_classify_flow() - Set a flow's secid based on request_sock
+ * @req: request_sock
+ * @flic: target flow
+ *
+ * Sets @flic's secid to @req's secid.
+ */
+void security_req_classify_flow(const struct request_sock *req,
+				struct flowi_common *flic)
+{
+	call_void_hook(req_classify_flow, req, flic);
+}
+EXPORT_SYMBOL(security_req_classify_flow);
+
+/**
+ * security_sock_graft() - Reconcile LSM state when grafting a sock on a socket
+ * @sk: sock being grafted
+ * @parent: target parent socket
+ *
+ * Sets @parent's inode secid to @sk's secid and update @sk with any necessary
+ * LSM state from @parent.
+ */
+void security_sock_graft(struct sock *sk, struct socket *parent)
+{
+	call_void_hook(sock_graft, sk, parent);
+}
+EXPORT_SYMBOL(security_sock_graft);
+
+/**
+ * security_inet_conn_request() - Set request_sock state using incoming connect
+ * @sk: parent listening sock
+ * @skb: incoming connection
+ * @req: new request_sock
+ *
+ * Initialize the @req LSM state based on @sk and the incoming connect in @skb.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inet_conn_request(const struct sock *sk,
+			       struct sk_buff *skb, struct request_sock *req)
+{
+	return call_int_hook(inet_conn_request, sk, skb, req);
+}
+EXPORT_SYMBOL(security_inet_conn_request);
+
+/**
+ * security_inet_csk_clone() - Set new sock LSM state based on request_sock
+ * @newsk: new sock
+ * @req: connection request_sock
+ *
+ * Set that LSM state of @sock using the LSM state from @req.
+ */
+void security_inet_csk_clone(struct sock *newsk,
+			     const struct request_sock *req)
+{
+	call_void_hook(inet_csk_clone, newsk, req);
+}
+
+/**
+ * security_inet_conn_established() - Update sock's LSM state with connection
+ * @sk: sock
+ * @skb: connection packet
+ *
+ * Update @sock's LSM state to represent a new connection from @skb.
+ */
+void security_inet_conn_established(struct sock *sk,
+				    struct sk_buff *skb)
+{
+	call_void_hook(inet_conn_established, sk, skb);
+}
+EXPORT_SYMBOL(security_inet_conn_established);
+
+/**
+ * security_secmark_relabel_packet() - Check if setting a secmark is allowed
+ * @secid: new secmark value
+ *
+ * Check if the process should be allowed to relabel packets to @secid.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_secmark_relabel_packet(u32 secid)
+{
+	return call_int_hook(secmark_relabel_packet, secid);
+}
+EXPORT_SYMBOL(security_secmark_relabel_packet);
+
+/**
+ * security_secmark_refcount_inc() - Increment the secmark labeling rule count
+ *
+ * Tells the LSM to increment the number of secmark labeling rules loaded.
+ */
+void security_secmark_refcount_inc(void)
+{
+	call_void_hook(secmark_refcount_inc);
+}
+EXPORT_SYMBOL(security_secmark_refcount_inc);
+
+/**
+ * security_secmark_refcount_dec() - Decrement the secmark labeling rule count
+ *
+ * Tells the LSM to decrement the number of secmark labeling rules loaded.
+ */
+void security_secmark_refcount_dec(void)
+{
+	call_void_hook(secmark_refcount_dec);
+}
+EXPORT_SYMBOL(security_secmark_refcount_dec);
+
+/**
+ * security_tun_dev_alloc_security() - Allocate a LSM blob for a TUN device
+ * @security: pointer to the LSM blob
+ *
+ * This hook allows a module to allocate a security structure for a TUN	device,
+ * returning the pointer in @security.
+ *
+ * Return: Returns a zero on success, negative values on failure.
+ */
+int security_tun_dev_alloc_security(void **security)
+{
+	int rc;
+
+	rc = lsm_blob_alloc(security, blob_sizes.lbs_tun_dev, GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	rc = call_int_hook(tun_dev_alloc_security, *security);
+	if (rc) {
+		kfree(*security);
+		*security = NULL;
+	}
+	return rc;
+}
+EXPORT_SYMBOL(security_tun_dev_alloc_security);
+
+/**
+ * security_tun_dev_free_security() - Free a TUN device LSM blob
+ * @security: LSM blob
+ *
+ * This hook allows a module to free the security structure for a TUN device.
+ */
+void security_tun_dev_free_security(void *security)
+{
+	kfree(security);
+}
+EXPORT_SYMBOL(security_tun_dev_free_security);
+
+/**
+ * security_tun_dev_create() - Check if creating a TUN device is allowed
+ *
+ * Check permissions prior to creating a new TUN device.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_tun_dev_create(void)
+{
+	return call_int_hook(tun_dev_create);
+}
+EXPORT_SYMBOL(security_tun_dev_create);
+
+/**
+ * security_tun_dev_attach_queue() - Check if attaching a TUN queue is allowed
+ * @security: TUN device LSM blob
+ *
+ * Check permissions prior to attaching to a TUN device queue.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_tun_dev_attach_queue(void *security)
+{
+	return call_int_hook(tun_dev_attach_queue, security);
+}
+EXPORT_SYMBOL(security_tun_dev_attach_queue);
+
+/**
+ * security_tun_dev_attach() - Update TUN device LSM state on attach
+ * @sk: associated sock
+ * @security: TUN device LSM blob
+ *
+ * This hook can be used by the module to update any security state associated
+ * with the TUN device's sock structure.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_tun_dev_attach(struct sock *sk, void *security)
+{
+	return call_int_hook(tun_dev_attach, sk, security);
+}
+EXPORT_SYMBOL(security_tun_dev_attach);
+
+/**
+ * security_tun_dev_open() - Update TUN device LSM state on open
+ * @security: TUN device LSM blob
+ *
+ * This hook can be used by the module to update any security state associated
+ * with the TUN device's security structure.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_tun_dev_open(void *security)
+{
+	return call_int_hook(tun_dev_open, security);
+}
+EXPORT_SYMBOL(security_tun_dev_open);
+
+/**
+ * security_sctp_assoc_request() - Update the LSM on a SCTP association req
+ * @asoc: SCTP association
+ * @skb: packet requesting the association
+ *
+ * Passes the @asoc and @chunk->skb of the association INIT packet to the LSM.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_sctp_assoc_request(struct sctp_association *asoc,
+				struct sk_buff *skb)
+{
+	return call_int_hook(sctp_assoc_request, asoc, skb);
+}
+EXPORT_SYMBOL(security_sctp_assoc_request);
+
+/**
+ * security_sctp_bind_connect() - Validate a list of addrs for a SCTP option
+ * @sk: socket
+ * @optname: SCTP option to validate
+ * @address: list of IP addresses to validate
+ * @addrlen: length of the address list
+ *
+ * Validiate permissions required for each address associated with sock	@sk.
+ * Depending on @optname, the addresses will be treated as either a connect or
+ * bind service. The @addrlen is calculated on each IPv4 and IPv6 address using
+ * sizeof(struct sockaddr_in) or sizeof(struct sockaddr_in6).
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_sctp_bind_connect(struct sock *sk, int optname,
+			       struct sockaddr *address, int addrlen)
+{
+	return call_int_hook(sctp_bind_connect, sk, optname, address, addrlen);
+}
+EXPORT_SYMBOL(security_sctp_bind_connect);
+
+/**
+ * security_sctp_sk_clone() - Clone a SCTP sock's LSM state
+ * @asoc: SCTP association
+ * @sk: original sock
+ * @newsk: target sock
+ *
+ * Called whenever a new socket is created by accept(2) (i.e. a TCP style
+ * socket) or when a socket is 'peeled off' e.g userspace calls
+ * sctp_peeloff(3).
+ */
+void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
+			    struct sock *newsk)
+{
+	call_void_hook(sctp_sk_clone, asoc, sk, newsk);
+}
+EXPORT_SYMBOL(security_sctp_sk_clone);
+
+/**
+ * security_sctp_assoc_established() - Update LSM state when assoc established
+ * @asoc: SCTP association
+ * @skb: packet establishing the association
+ *
+ * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet to the
+ * security module.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_sctp_assoc_established(struct sctp_association *asoc,
+				    struct sk_buff *skb)
+{
+	return call_int_hook(sctp_assoc_established, asoc, skb);
+}
+EXPORT_SYMBOL(security_sctp_assoc_established);
+
+/**
+ * security_mptcp_add_subflow() - Inherit the LSM label from the MPTCP socket
+ * @sk: the owning MPTCP socket
+ * @ssk: the new subflow
+ *
+ * Update the labeling for the given MPTCP subflow, to match the one of the
+ * owning MPTCP socket. This hook has to be called after the socket creation and
+ * initialization via the security_socket_create() and
+ * security_socket_post_create() LSM hooks.
+ *
+ * Return: Returns 0 on success or a negative error code on failure.
+ */
+int security_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+{
+	return call_int_hook(mptcp_add_subflow, sk, ssk);
+}
+
+#endif	/* CONFIG_SECURITY_NETWORK */
+
+#if defined(CONFIG_SECURITY_NETWORK) && defined(CONFIG_SECURITY_PATH)
+/**
+ * security_unix_find() - Check if a named AF_UNIX socket can connect
+ * @path: path of the socket being connected to
+ * @other: peer sock
+ * @flags: flags associated with the socket
+ *
+ * This hook is called to check permissions before connecting to a named
+ * AF_UNIX socket. The caller does not hold any locks on @other.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_unix_find(const struct path *path, struct sock *other, int flags)
+{
+	return call_int_hook(unix_find, path, other, flags);
+}
+EXPORT_SYMBOL(security_unix_find);
+
+#endif	/* CONFIG_SECURITY_NETWORK && CONFIG_SECURITY_PATH */
+
+#ifdef CONFIG_SECURITY_INFINIBAND
+/**
+ * security_ib_pkey_access() - Check if access to an IB pkey is allowed
+ * @sec: LSM blob
+ * @subnet_prefix: subnet prefix of the port
+ * @pkey: IB pkey
+ *
+ * Check permission to access a pkey when modifying a QP.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_ib_pkey_access(void *sec, u64 subnet_prefix, u16 pkey)
+{
+	return call_int_hook(ib_pkey_access, sec, subnet_prefix, pkey);
+}
+EXPORT_SYMBOL(security_ib_pkey_access);
+
+/**
+ * security_ib_endport_manage_subnet() - Check if SMPs traffic is allowed
+ * @sec: LSM blob
+ * @dev_name: IB device name
+ * @port_num: port number
+ *
+ * Check permissions to send and receive SMPs on a end port.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_ib_endport_manage_subnet(void *sec,
+				      const char *dev_name, u8 port_num)
+{
+	return call_int_hook(ib_endport_manage_subnet, sec, dev_name, port_num);
+}
+EXPORT_SYMBOL(security_ib_endport_manage_subnet);
+
+/**
+ * security_ib_alloc_security() - Allocate an Infiniband LSM blob
+ * @sec: LSM blob
+ *
+ * Allocate a security structure for Infiniband objects.
+ *
+ * Return: Returns 0 on success, non-zero on failure.
+ */
+int security_ib_alloc_security(void **sec)
+{
+	int rc;
+
+	rc = lsm_blob_alloc(sec, blob_sizes.lbs_ib, GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	rc = call_int_hook(ib_alloc_security, *sec);
+	if (rc) {
+		kfree(*sec);
+		*sec = NULL;
+	}
+	return rc;
+}
+EXPORT_SYMBOL(security_ib_alloc_security);
+
+/**
+ * security_ib_free_security() - Free an Infiniband LSM blob
+ * @sec: LSM blob
+ *
+ * Deallocate an Infiniband security structure.
+ */
+void security_ib_free_security(void *sec)
+{
+	kfree(sec);
+}
+EXPORT_SYMBOL(security_ib_free_security);
+#endif	/* CONFIG_SECURITY_INFINIBAND */
+
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+/**
+ * security_xfrm_policy_alloc() - Allocate a xfrm policy LSM blob
+ * @ctxp: xfrm security context being added to the SPD
+ * @sec_ctx: security label provided by userspace
+ * @gfp: gfp flags
+ *
+ * Allocate a security structure to the xp->security field; the security field
+ * is initialized to NULL when the xfrm_policy is allocated.
+ *
+ * Return:  Return 0 if operation was successful.
+ */
+int security_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+			       struct xfrm_user_sec_ctx *sec_ctx,
+			       gfp_t gfp)
+{
+	return call_int_hook(xfrm_policy_alloc_security, ctxp, sec_ctx, gfp);
+}
+EXPORT_SYMBOL(security_xfrm_policy_alloc);
+
+/**
+ * security_xfrm_policy_clone() - Clone xfrm policy LSM state
+ * @old_ctx: xfrm security context
+ * @new_ctxp: target xfrm security context
+ *
+ * Allocate a security structure in new_ctxp that contains the information from
+ * the old_ctx structure.
+ *
+ * Return: Return 0 if operation was successful.
+ */
+int security_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
+			       struct xfrm_sec_ctx **new_ctxp)
+{
+	return call_int_hook(xfrm_policy_clone_security, old_ctx, new_ctxp);
+}
+
+/**
+ * security_xfrm_policy_free() - Free a xfrm security context
+ * @ctx: xfrm security context
+ *
+ * Free LSM resources associated with @ctx.
+ */
+void security_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
+{
+	call_void_hook(xfrm_policy_free_security, ctx);
+}
+EXPORT_SYMBOL(security_xfrm_policy_free);
+
+/**
+ * security_xfrm_policy_delete() - Check if deleting a xfrm policy is allowed
+ * @ctx: xfrm security context
+ *
+ * Authorize deletion of a SPD entry.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
+{
+	return call_int_hook(xfrm_policy_delete_security, ctx);
+}
+
+/**
+ * security_xfrm_state_alloc() - Allocate a xfrm state LSM blob
+ * @x: xfrm state being added to the SAD
+ * @sec_ctx: security label provided by userspace
+ *
+ * Allocate a security structure to the @x->security field; the security field
+ * is initialized to NULL when the xfrm_state is allocated. Set the context to
+ * correspond to @sec_ctx.
+ *
+ * Return: Return 0 if operation was successful.
+ */
+int security_xfrm_state_alloc(struct xfrm_state *x,
+			      struct xfrm_user_sec_ctx *sec_ctx)
+{
+	return call_int_hook(xfrm_state_alloc, x, sec_ctx);
+}
+EXPORT_SYMBOL(security_xfrm_state_alloc);
+
+/**
+ * security_xfrm_state_alloc_acquire() - Allocate a xfrm state LSM blob
+ * @x: xfrm state being added to the SAD
+ * @polsec: associated policy's security context
+ * @secid: secid from the flow
+ *
+ * Allocate a security structure to the x->security field; the security field
+ * is initialized to NULL when the xfrm_state is allocated.  Set the context to
+ * correspond to secid.
+ *
+ * Return: Returns 0 if operation was successful.
+ */
+int security_xfrm_state_alloc_acquire(struct xfrm_state *x,
+				      struct xfrm_sec_ctx *polsec, u32 secid)
+{
+	return call_int_hook(xfrm_state_alloc_acquire, x, polsec, secid);
+}
+
+/**
+ * security_xfrm_state_delete() - Check if deleting a xfrm state is allowed
+ * @x: xfrm state
+ *
+ * Authorize deletion of x->security.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_xfrm_state_delete(struct xfrm_state *x)
+{
+	return call_int_hook(xfrm_state_delete_security, x);
+}
+EXPORT_SYMBOL(security_xfrm_state_delete);
+
+/**
+ * security_xfrm_state_free() - Free a xfrm state
+ * @x: xfrm state
+ *
+ * Deallocate x->security.
+ */
+void security_xfrm_state_free(struct xfrm_state *x)
+{
+	call_void_hook(xfrm_state_free_security, x);
+}
+
+/**
+ * security_xfrm_policy_lookup() - Check if using a xfrm policy is allowed
+ * @ctx: target xfrm security context
+ * @fl_secid: flow secid used to authorize access
+ *
+ * Check permission when a flow selects a xfrm_policy for processing XFRMs on a
+ * packet.  The hook is called when selecting either a per-socket policy or a
+ * generic xfrm policy.
+ *
+ * Return: Return 0 if permission is granted, -ESRCH otherwise, or -errno on
+ *         other errors.
+ */
+int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid)
+{
+	return call_int_hook(xfrm_policy_lookup, ctx, fl_secid);
+}
+
+/**
+ * security_xfrm_state_pol_flow_match() - Check for a xfrm match
+ * @x: xfrm state to match
+ * @xp: xfrm policy to check for a match
+ * @flic: flow to check for a match.
+ *
+ * Check @xp and @flic for a match with @x.
+ *
+ * Return: Returns 1 if there is a match.
+ */
+int security_xfrm_state_pol_flow_match(struct xfrm_state *x,
+				       struct xfrm_policy *xp,
+				       const struct flowi_common *flic)
+{
+	struct lsm_static_call *scall;
+	int rc = LSM_RET_DEFAULT(xfrm_state_pol_flow_match);
+
+	/*
+	 * Since this function is expected to return 0 or 1, the judgment
+	 * becomes difficult if multiple LSMs supply this call. Fortunately,
+	 * we can use the first LSM's judgment because currently only SELinux
+	 * supplies this call.
+	 *
+	 * For speed optimization, we explicitly break the loop rather than
+	 * using the macro
+	 */
+	lsm_for_each_hook(scall, xfrm_state_pol_flow_match) {
+		rc = scall->hl->hook.xfrm_state_pol_flow_match(x, xp, flic);
+		break;
+	}
+	return rc;
+}
+
+/**
+ * security_xfrm_decode_session() - Determine the xfrm secid for a packet
+ * @skb: xfrm packet
+ * @secid: secid
+ *
+ * Decode the packet in @skb and return the security label in @secid.
+ *
+ * Return: Return 0 if all xfrms used have the same secid.
+ */
+int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid)
+{
+	return call_int_hook(xfrm_decode_session, skb, secid, 1);
+}
+
+void security_skb_classify_flow(struct sk_buff *skb, struct flowi_common *flic)
+{
+	int rc = call_int_hook(xfrm_decode_session, skb, &flic->flowic_secid,
+			       0);
+
+	BUG_ON(rc);
+}
+EXPORT_SYMBOL(security_skb_classify_flow);
+#endif	/* CONFIG_SECURITY_NETWORK_XFRM */
+
+#ifdef CONFIG_KEYS
+/**
+ * security_key_alloc() - Allocate and initialize a kernel key LSM blob
+ * @key: key
+ * @cred: credentials
+ * @flags: allocation flags
+ *
+ * Permit allocation of a key and assign security data. Note that key does not
+ * have a serial number assigned at this point.
+ *
+ * Return: Return 0 if permission is granted, -ve error otherwise.
+ */
+int security_key_alloc(struct key *key, const struct cred *cred,
+		       unsigned long flags)
+{
+	int rc = lsm_key_alloc(key);
+
+	if (unlikely(rc))
+		return rc;
+	rc = call_int_hook(key_alloc, key, cred, flags);
+	if (unlikely(rc))
+		security_key_free(key);
+	return rc;
+}
+
+/**
+ * security_key_free() - Free a kernel key LSM blob
+ * @key: key
+ *
+ * Notification of destruction; free security data.
+ */
+void security_key_free(struct key *key)
+{
+	kfree(key->security);
+	key->security = NULL;
+}
+
+/**
+ * security_key_permission() - Check if a kernel key operation is allowed
+ * @key_ref: key reference
+ * @cred: credentials of actor requesting access
+ * @need_perm: requested permissions
+ *
+ * See whether a specific operational right is granted to a process on a key.
+ *
+ * Return: Return 0 if permission is granted, -ve error otherwise.
+ */
+int security_key_permission(key_ref_t key_ref, const struct cred *cred,
+			    enum key_need_perm need_perm)
+{
+	return call_int_hook(key_permission, key_ref, cred, need_perm);
+}
+
+/**
+ * security_key_getsecurity() - Get the key's security label
+ * @key: key
+ * @buffer: security label buffer
+ *
+ * Get a textual representation of the security context attached to a key for
+ * the purposes of honouring KEYCTL_GETSECURITY.  This function allocates the
+ * storage for the NUL-terminated string and the caller should free it.
+ *
+ * Return: Returns the length of @buffer (including terminating NUL) or -ve if
+ *         an error occurs.  May also return 0 (and a NULL buffer pointer) if
+ *         there is no security label assigned to the key.
+ */
+int security_key_getsecurity(struct key *key, char **buffer)
+{
+	*buffer = NULL;
+	return call_int_hook(key_getsecurity, key, buffer);
+}
+
+/**
+ * security_key_post_create_or_update() - Notification of key create or update
+ * @keyring: keyring to which the key is linked to
+ * @key: created or updated key
+ * @payload: data used to instantiate or update the key
+ * @payload_len: length of payload
+ * @flags: key flags
+ * @create: flag indicating whether the key was created or updated
+ *
+ * Notify the caller of a key creation or update.
+ */
+void security_key_post_create_or_update(struct key *keyring, struct key *key,
+					const void *payload, size_t payload_len,
+					unsigned long flags, bool create)
+{
+	call_void_hook(key_post_create_or_update, keyring, key, payload,
+		       payload_len, flags, create);
+}
+#endif	/* CONFIG_KEYS */
+
+#ifdef CONFIG_AUDIT
+/**
+ * security_audit_rule_init() - Allocate and init an LSM audit rule struct
+ * @field: audit action
+ * @op: rule operator
+ * @rulestr: rule context
+ * @lsmrule: receive buffer for audit rule struct
+ * @gfp: GFP flag used for kmalloc
+ *
+ * Allocate and initialize an LSM audit rule structure.
+ *
+ * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of
+ *         an invalid rule.
+ */
+int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule,
+			     gfp_t gfp)
+{
+	return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp);
+}
+
+/**
+ * security_audit_rule_known() - Check if an audit rule contains LSM fields
+ * @krule: audit rule
+ *
+ * Specifies whether given @krule contains any fields related to the current
+ * LSM.
+ *
+ * Return: Returns 1 in case of relation found, 0 otherwise.
+ */
+int security_audit_rule_known(struct audit_krule *krule)
+{
+	return call_int_hook(audit_rule_known, krule);
+}
+
+/**
+ * security_audit_rule_free() - Free an LSM audit rule struct
+ * @lsmrule: audit rule struct
+ *
+ * Deallocate the LSM audit rule structure previously allocated by
+ * audit_rule_init().
+ */
+void security_audit_rule_free(void *lsmrule)
+{
+	call_void_hook(audit_rule_free, lsmrule);
+}
+
+/**
+ * security_audit_rule_match() - Check if a label matches an audit rule
+ * @prop: security label
+ * @field: LSM audit field
+ * @op: matching operator
+ * @lsmrule: audit rule
+ *
+ * Determine if given @secid matches a rule previously approved by
+ * security_audit_rule_known().
+ *
+ * Return: Returns 1 if secid matches the rule, 0 if it does not, -ERRNO on
+ *         failure.
+ */
+int security_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op,
+			      void *lsmrule)
+{
+	return call_int_hook(audit_rule_match, prop, field, op, lsmrule);
+}
+#endif /* CONFIG_AUDIT */
+
+#ifdef CONFIG_BPF_SYSCALL
+/**
+ * security_bpf() - Check if the bpf syscall operation is allowed
+ * @cmd: command
+ * @attr: bpf attribute
+ * @size: size
+ * @kernel: whether or not call originated from kernel
+ *
+ * Do a initial check for all bpf syscalls after the attribute is copied into
+ * the kernel. The actual security module can implement their own rules to
+ * check the specific cmd they need.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_bpf(int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
+{
+	return call_int_hook(bpf, cmd, attr, size, kernel);
+}
+
+/**
+ * security_bpf_map() - Check if access to a bpf map is allowed
+ * @map: bpf map
+ * @fmode: mode
+ *
+ * Do a check when the kernel generates and returns a file descriptor for eBPF
+ * maps.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	return call_int_hook(bpf_map, map, fmode);
+}
+
+/**
+ * security_bpf_prog() - Check if access to a bpf program is allowed
+ * @prog: bpf program
+ *
+ * Do a check when the kernel generates and returns a file descriptor for eBPF
+ * programs.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_bpf_prog(struct bpf_prog *prog)
+{
+	return call_int_hook(bpf_prog, prog);
+}
+
+/**
+ * security_bpf_map_create() - Check if BPF map creation is allowed
+ * @map: BPF map object
+ * @attr: BPF syscall attributes used to create BPF map
+ * @token: BPF token used to grant user access
+ * @kernel: whether or not call originated from kernel
+ *
+ * Do a check when the kernel creates a new BPF map. This is also the
+ * point where LSM blob is allocated for LSMs that need them.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+			    struct bpf_token *token, bool kernel)
+{
+	int rc;
+
+	rc = lsm_bpf_map_alloc(map);
+	if (unlikely(rc))
+		return rc;
+
+	rc = call_int_hook(bpf_map_create, map, attr, token, kernel);
+	if (unlikely(rc))
+		security_bpf_map_free(map);
+	return rc;
+}
+
+/**
+ * security_bpf_prog_load() - Check if loading of BPF program is allowed
+ * @prog: BPF program object
+ * @attr: BPF syscall attributes used to create BPF program
+ * @token: BPF token used to grant user access to BPF subsystem
+ * @kernel: whether or not call originated from kernel
+ *
+ * Perform an access control check when the kernel loads a BPF program and
+ * allocates associated BPF program object. This hook is also responsible for
+ * allocating any required LSM state for the BPF program.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+			   struct bpf_token *token, bool kernel)
+{
+	int rc;
+
+	rc = lsm_bpf_prog_alloc(prog);
+	if (unlikely(rc))
+		return rc;
+
+	rc = call_int_hook(bpf_prog_load, prog, attr, token, kernel);
+	if (unlikely(rc))
+		security_bpf_prog_free(prog);
+	return rc;
+}
+
+/**
+ * security_bpf_token_create() - Check if creating of BPF token is allowed
+ * @token: BPF token object
+ * @attr: BPF syscall attributes used to create BPF token
+ * @path: path pointing to BPF FS mount point from which BPF token is created
+ *
+ * Do a check when the kernel instantiates a new BPF token object from BPF FS
+ * instance. This is also the point where LSM blob can be allocated for LSMs.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr,
+			      const struct path *path)
+{
+	int rc;
+
+	rc = lsm_bpf_token_alloc(token);
+	if (unlikely(rc))
+		return rc;
+
+	rc = call_int_hook(bpf_token_create, token, attr, path);
+	if (unlikely(rc))
+		security_bpf_token_free(token);
+	return rc;
+}
+
+/**
+ * security_bpf_token_cmd() - Check if BPF token is allowed to delegate
+ * requested BPF syscall command
+ * @token: BPF token object
+ * @cmd: BPF syscall command requested to be delegated by BPF token
+ *
+ * Do a check when the kernel decides whether provided BPF token should allow
+ * delegation of requested BPF syscall command.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd)
+{
+	return call_int_hook(bpf_token_cmd, token, cmd);
+}
+
+/**
+ * security_bpf_token_capable() - Check if BPF token is allowed to delegate
+ * requested BPF-related capability
+ * @token: BPF token object
+ * @cap: capabilities requested to be delegated by BPF token
+ *
+ * Do a check when the kernel decides whether provided BPF token should allow
+ * delegation of requested BPF-related capabilities.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return call_int_hook(bpf_token_capable, token, cap);
+}
+
+/**
+ * security_bpf_map_free() - Free a bpf map's LSM blob
+ * @map: bpf map
+ *
+ * Clean up the security information stored inside bpf map.
+ */
+void security_bpf_map_free(struct bpf_map *map)
+{
+	call_void_hook(bpf_map_free, map);
+	kfree(map->security);
+	map->security = NULL;
+}
+
+/**
+ * security_bpf_prog_free() - Free a BPF program's LSM blob
+ * @prog: BPF program struct
+ *
+ * Clean up the security information stored inside BPF program.
+ */
+void security_bpf_prog_free(struct bpf_prog *prog)
+{
+	call_void_hook(bpf_prog_free, prog);
+	kfree(prog->aux->security);
+	prog->aux->security = NULL;
+}
+
+/**
+ * security_bpf_token_free() - Free a BPF token's LSM blob
+ * @token: BPF token struct
+ *
+ * Clean up the security information stored inside BPF token.
+ */
+void security_bpf_token_free(struct bpf_token *token)
+{
+	call_void_hook(bpf_token_free, token);
+	kfree(token->security);
+	token->security = NULL;
+}
+#endif /* CONFIG_BPF_SYSCALL */
+
+/**
+ * security_locked_down() - Check if a kernel feature is allowed
+ * @what: requested kernel feature
+ *
+ * Determine whether a kernel feature that potentially enables arbitrary code
+ * execution in kernel space should be permitted.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_locked_down(enum lockdown_reason what)
+{
+	return call_int_hook(locked_down, what);
+}
+EXPORT_SYMBOL(security_locked_down);
+
+/**
+ * security_bdev_alloc() - Allocate a block device LSM blob
+ * @bdev: block device
+ *
+ * Allocate and attach a security structure to @bdev->bd_security.  The
+ * security field is initialized to NULL when the bdev structure is
+ * allocated.
+ *
+ * Return: Return 0 if operation was successful.
+ */
+int security_bdev_alloc(struct block_device *bdev)
+{
+	int rc = 0;
+
+	rc = lsm_bdev_alloc(bdev);
+	if (unlikely(rc))
+		return rc;
+
+	rc = call_int_hook(bdev_alloc_security, bdev);
+	if (unlikely(rc))
+		security_bdev_free(bdev);
+
+	return rc;
+}
+EXPORT_SYMBOL(security_bdev_alloc);
+
+/**
+ * security_bdev_free() - Free a block device's LSM blob
+ * @bdev: block device
+ *
+ * Deallocate the bdev security structure and set @bdev->bd_security to NULL.
+ */
+void security_bdev_free(struct block_device *bdev)
+{
+	if (!bdev->bd_security)
+		return;
+
+	call_void_hook(bdev_free_security, bdev);
+
+	kfree(bdev->bd_security);
+	bdev->bd_security = NULL;
+}
+EXPORT_SYMBOL(security_bdev_free);
+
+/**
+ * security_bdev_setintegrity() - Set the device's integrity data
+ * @bdev: block device
+ * @type: type of integrity, e.g. hash digest, signature, etc
+ * @value: the integrity value
+ * @size: size of the integrity value
+ *
+ * Register a verified integrity measurement of a bdev with LSMs.
+ * LSMs should free the previously saved data if @value is NULL.
+ * Please note that the new hook should be invoked every time the security
+ * information is updated to keep these data current. For example, in dm-verity,
+ * if the mapping table is reloaded and configured to use a different dm-verity
+ * target with a new roothash and signing information, the previously stored
+ * data in the LSM blob will become obsolete. It is crucial to re-invoke the
+ * hook to refresh these data and ensure they are up to date. This necessity
+ * arises from the design of device-mapper, where a device-mapper device is
+ * first created, and then targets are subsequently loaded into it. These
+ * targets can be modified multiple times during the device's lifetime.
+ * Therefore, while the LSM blob is allocated during the creation of the block
+ * device, its actual contents are not initialized at this stage and can change
+ * substantially over time. This includes alterations from data that the LSMs
+ * 'trusts' to those they do not, making it essential to handle these changes
+ * correctly. Failure to address this dynamic aspect could potentially allow
+ * for bypassing LSM checks.
+ *
+ * Return: Returns 0 on success, negative values on failure.
+ */
+int security_bdev_setintegrity(struct block_device *bdev,
+			       enum lsm_integrity_type type, const void *value,
+			       size_t size)
+{
+	return call_int_hook(bdev_setintegrity, bdev, type, value, size);
+}
+EXPORT_SYMBOL(security_bdev_setintegrity);
+
+#ifdef CONFIG_PERF_EVENTS
+/**
+ * security_perf_event_open() - Check if a perf event open is allowed
+ * @type: type of event
+ *
+ * Check whether the @type of perf_event_open syscall is allowed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_perf_event_open(int type)
+{
+	return call_int_hook(perf_event_open, type);
+}
+
+/**
+ * security_perf_event_alloc() - Allocate a perf event LSM blob
+ * @event: perf event
+ *
+ * Allocate and save perf_event security info.
+ *
+ * Return: Returns 0 on success, error on failure.
+ */
+int security_perf_event_alloc(struct perf_event *event)
+{
+	int rc;
+
+	rc = lsm_blob_alloc(&event->security, blob_sizes.lbs_perf_event,
+			    GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	rc = call_int_hook(perf_event_alloc, event);
+	if (rc) {
+		kfree(event->security);
+		event->security = NULL;
+	}
+	return rc;
+}
+
+/**
+ * security_perf_event_free() - Free a perf event LSM blob
+ * @event: perf event
+ *
+ * Release (free) perf_event security info.
+ */
+void security_perf_event_free(struct perf_event *event)
+{
+	kfree(event->security);
+	event->security = NULL;
+}
+
+/**
+ * security_perf_event_read() - Check if reading a perf event label is allowed
+ * @event: perf event
+ *
+ * Read perf_event security info if allowed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_perf_event_read(struct perf_event *event)
+{
+	return call_int_hook(perf_event_read, event);
+}
+
+/**
+ * security_perf_event_write() - Check if writing a perf event label is allowed
+ * @event: perf event
+ *
+ * Write perf_event security info if allowed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_perf_event_write(struct perf_event *event)
+{
+	return call_int_hook(perf_event_write, event);
+}
+#endif /* CONFIG_PERF_EVENTS */
+
+#ifdef CONFIG_IO_URING
+/**
+ * security_uring_override_creds() - Check if overriding creds is allowed
+ * @new: new credentials
+ *
+ * Check if the current task, executing an io_uring operation, is allowed to
+ * override it's credentials with @new.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_uring_override_creds(const struct cred *new)
+{
+	return call_int_hook(uring_override_creds, new);
+}
+
+/**
+ * security_uring_sqpoll() - Check if IORING_SETUP_SQPOLL is allowed
+ *
+ * Check whether the current task is allowed to spawn a io_uring polling thread
+ * (IORING_SETUP_SQPOLL).
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_uring_sqpoll(void)
+{
+	return call_int_hook(uring_sqpoll);
+}
+
+/**
+ * security_uring_cmd() - Check if a io_uring passthrough command is allowed
+ * @ioucmd: command
+ *
+ * Check whether the file_operations uring_cmd is allowed to run.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	return call_int_hook(uring_cmd, ioucmd);
+}
+
+/**
+ * security_uring_allowed() - Check if io_uring_setup() is allowed
+ *
+ * Check whether the current task is allowed to call io_uring_setup().
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_uring_allowed(void)
+{
+	return call_int_hook(uring_allowed);
+}
+#endif /* CONFIG_IO_URING */
+
+/**
+ * security_initramfs_populated() - Notify LSMs that initramfs has been loaded
+ *
+ * Tells the LSMs the initramfs has been unpacked into the rootfs.
+ */
+void security_initramfs_populated(void)
+{
+	call_void_hook(initramfs_populated);
+}
diff --git a/security/selinux/.gitignore b/security/selinux/.gitignore
new file mode 100644
index 000000000..01c0df8ab
--- /dev/null
+++ b/security/selinux/.gitignore
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+av_permissions.h
+flask.h
+/genheaders
diff --git a/security/selinux/Kconfig b/security/selinux/Kconfig
new file mode 100644
index 000000000..5588c4d57
--- /dev/null
+++ b/security/selinux/Kconfig
@@ -0,0 +1,100 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_SELINUX
+	bool "SELinux Support"
+	depends on SECURITY_NETWORK && AUDIT && NET && INET
+	select NETWORK_SECMARK
+	default n
+	help
+	  This selects Security-Enhanced Linux (SELinux).
+	  You will also need a policy configuration and a labeled filesystem.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_SELINUX_BOOTPARAM
+	bool "SELinux boot parameter"
+	depends on SECURITY_SELINUX
+	default n
+	help
+	  This option adds a kernel parameter 'selinux', which allows SELinux
+	  to be disabled at boot.  If this option is selected, SELinux
+	  functionality can be disabled with selinux=0 on the kernel
+	  command line.  The purpose of this option is to allow a single
+	  kernel image to be distributed with SELinux built in, but not
+	  necessarily enabled.
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_SELINUX_DEVELOP
+	bool "SELinux Development Support"
+	depends on SECURITY_SELINUX
+	default y
+	help
+	  This enables the development support option of SELinux,
+	  which is useful for experimenting with SELinux and developing
+	  policies.  If unsure, say Y.  With this option enabled, the
+	  kernel will start in permissive mode (log everything, deny nothing)
+	  unless you specify enforcing=1 on the kernel command line.  You
+	  can interactively toggle the kernel between enforcing mode and
+	  permissive mode (if permitted by the policy) via
+	  /sys/fs/selinux/enforce.
+
+config SECURITY_SELINUX_AVC_STATS
+	bool "SELinux AVC Statistics"
+	depends on SECURITY_SELINUX
+	default y
+	help
+	  This option collects access vector cache statistics to
+	  /sys/fs/selinux/avc/cache_stats, which may be monitored via
+	  tools such as avcstat.
+
+config SECURITY_SELINUX_SIDTAB_HASH_BITS
+	int "SELinux sidtab hashtable size"
+	depends on SECURITY_SELINUX
+	range 8 13
+	default 9
+	help
+	  This option sets the number of buckets used in the sidtab hashtable
+	  to 2^SECURITY_SELINUX_SIDTAB_HASH_BITS buckets. The number of hash
+	  collisions may be viewed at /sys/fs/selinux/ss/sidtab_hash_stats. If
+	  chain lengths are high (e.g. > 20) then selecting a higher value here
+	  will ensure that lookups times are short and stable.
+
+config SECURITY_SELINUX_SID2STR_CACHE_SIZE
+	int "SELinux SID to context string translation cache size"
+	depends on SECURITY_SELINUX
+	default 256
+	help
+	  This option defines the size of the internal SID -> context string
+	  cache, which improves the performance of context to string
+	  conversion.  Setting this option to 0 disables the cache completely.
+
+	  If unsure, keep the default value.
+
+config SECURITY_SELINUX_AVC_HASH_BITS
+	int "SELinux avc hashtable size"
+	depends on SECURITY_SELINUX
+	range 9 14
+	default 9
+	help
+	  This option sets the number of buckets used in the AVC hash table
+	  to 2^SECURITY_SELINUX_AVC_HASH_BITS. A higher value helps maintain
+	  shorter chain lengths especially when expanding AVC nodes via
+	  /sys/fs/selinux/avc/cache_threshold.
+
+config SECURITY_SELINUX_DEBUG
+	bool "SELinux kernel debugging support"
+	depends on SECURITY_SELINUX
+	default n
+	help
+	  This enables debugging code designed to help SELinux kernel
+	  developers, unless you know what this does in the kernel code you
+	  should leave this disabled.
+
+	  To fine control the messages to be printed enable
+	  CONFIG_DYNAMIC_DEBUG and see
+	  Documentation/admin-guide/dynamic-debug-howto.rst for additional
+	  information.
+
+	  Example usage:
+
+		echo -n 'file "security/selinux/*" +p' > \
+			/proc/dynamic_debug/control
diff --git a/security/selinux/Makefile b/security/selinux/Makefile
new file mode 100644
index 000000000..72d3baf79
--- /dev/null
+++ b/security/selinux/Makefile
@@ -0,0 +1,44 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for building the SELinux module as part of the kernel tree.
+#
+
+# NOTE: There are a number of improvements that can be made to this Makefile
+# once the kernel requires make v4.3 or greater; the most important feature
+# lacking in older versions of make is support for grouped targets.  These
+# improvements are noted inline in the Makefile below ...
+
+obj-$(CONFIG_SECURITY_SELINUX) := selinux.o
+
+ccflags-y := -I$(srctree)/security/selinux -I$(srctree)/security/selinux/include
+
+ccflags-$(CONFIG_SECURITY_SELINUX_DEBUG) += -DDEBUG
+
+selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o \
+	     netnode.o netport.o status.o initcalls.o \
+	     ss/ebitmap.o ss/hashtab.o ss/symtab.o ss/sidtab.o ss/avtab.o \
+	     ss/policydb.o ss/services.o ss/conditional.o ss/mls.o ss/context.o
+
+selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o
+selinux-$(CONFIG_NETLABEL) += netlabel.o
+selinux-$(CONFIG_SECURITY_INFINIBAND) += ibpkey.o
+selinux-$(CONFIG_IMA) += ima.o
+
+genhdrs := flask.h av_permissions.h
+
+# see the note above, replace the dependency rule with the one below:
+#  $(addprefix $(obj)/,$(selinux-y)): $(addprefix $(obj)/,$(genhdrs))
+$(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h
+
+quiet_cmd_genhdrs = GEN     $(addprefix $(obj)/,$(genhdrs))
+      cmd_genhdrs = $< $(addprefix $(obj)/,$(genhdrs))
+
+targets += $(genhdrs)
+
+# see the note above, replace the 'flask.h' rule with the line below:
+#  $(addprefix $(obj)/,$(genhdrs)) &: $(obj)/genheaders FORCE
+$(obj)/flask.h: $(obj)/genheaders FORCE
+	$(call if_changed,genhdrs)
+
+hostprogs := genheaders
+HOST_EXTRACFLAGS += -I$(srctree)/security/selinux/include
diff --git a/security/selinux/avc.c b/security/selinux/avc.c
new file mode 100644
index 000000000..a9401d6c2
--- /dev/null
+++ b/security/selinux/avc.c
@@ -0,0 +1,1207 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implementation of the kernel access vector cache (AVC).
+ *
+ * Authors:  Stephen Smalley, <stephen.smalley.work@gmail.com>
+ *	     James Morris <jmorris@redhat.com>
+ *
+ * Update:   KaiGai, Kohei <kaigai@ak.jp.nec.com>
+ *	Replaced the avc_lock spinlock by RCU.
+ *
+ * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ */
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/dcache.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/percpu.h>
+#include <linux/list.h>
+#include <net/sock.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <linux/ip.h>
+#include <linux/audit.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include "avc.h"
+#include "avc_ss.h"
+#include "classmap.h"
+#include "hash.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/avc.h>
+
+#define AVC_CACHE_SLOTS		(1 << CONFIG_SECURITY_SELINUX_AVC_HASH_BITS)
+#define AVC_DEF_CACHE_THRESHOLD	AVC_CACHE_SLOTS
+#define AVC_CACHE_RECLAIM	16
+
+#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
+#define avc_cache_stats_incr(field)	this_cpu_inc(avc_cache_stats.field)
+#else
+#define avc_cache_stats_incr(field)	do {} while (0)
+#endif
+
+struct avc_entry {
+	u32			ssid;
+	u32			tsid;
+	u16			tclass;
+	struct av_decision	avd;
+	struct avc_xperms_node	*xp_node;
+};
+
+struct avc_node {
+	struct avc_entry	ae;
+	struct hlist_node	list; /* anchored in avc_cache->slots[i] */
+	struct rcu_head		rhead;
+};
+
+struct avc_xperms_decision_node {
+	struct extended_perms_decision xpd;
+	struct list_head xpd_list; /* list of extended_perms_decision */
+};
+
+struct avc_xperms_node {
+	struct extended_perms xp;
+	struct list_head xpd_head; /* list head of extended_perms_decision */
+};
+
+struct avc_cache {
+	struct hlist_head	slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */
+	spinlock_t		slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */
+	atomic_t		lru_hint;	/* LRU hint for reclaim scan */
+	atomic_t		active_nodes;
+	u32			latest_notif;	/* latest revocation notification */
+};
+
+struct avc_callback_node {
+	int (*callback) (u32 event);
+	u32 events;
+	struct avc_callback_node *next;
+};
+
+#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
+DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 };
+#endif
+
+struct selinux_avc {
+	unsigned int avc_cache_threshold;
+	struct avc_cache avc_cache;
+};
+
+static struct selinux_avc selinux_avc;
+
+void selinux_avc_init(void)
+{
+	int i;
+
+	selinux_avc.avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD;
+	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
+		INIT_HLIST_HEAD(&selinux_avc.avc_cache.slots[i]);
+		spin_lock_init(&selinux_avc.avc_cache.slots_lock[i]);
+	}
+	atomic_set(&selinux_avc.avc_cache.active_nodes, 0);
+	atomic_set(&selinux_avc.avc_cache.lru_hint, 0);
+}
+
+unsigned int avc_get_cache_threshold(void)
+{
+	return selinux_avc.avc_cache_threshold;
+}
+
+void avc_set_cache_threshold(unsigned int cache_threshold)
+{
+	selinux_avc.avc_cache_threshold = cache_threshold;
+}
+
+static struct avc_callback_node *avc_callbacks __ro_after_init;
+static struct kmem_cache *avc_node_cachep __ro_after_init;
+static struct kmem_cache *avc_xperms_data_cachep __ro_after_init;
+static struct kmem_cache *avc_xperms_decision_cachep __ro_after_init;
+static struct kmem_cache *avc_xperms_cachep __ro_after_init;
+
+static inline u32 avc_hash(u32 ssid, u32 tsid, u16 tclass)
+{
+	return av_hash(ssid, tsid, (u32)tclass, (u32)(AVC_CACHE_SLOTS - 1));
+}
+
+/**
+ * avc_init - Initialize the AVC.
+ *
+ * Initialize the access vector cache.
+ */
+void __init avc_init(void)
+{
+	avc_node_cachep = KMEM_CACHE(avc_node, SLAB_PANIC);
+	avc_xperms_cachep = KMEM_CACHE(avc_xperms_node, SLAB_PANIC);
+	avc_xperms_decision_cachep = KMEM_CACHE(avc_xperms_decision_node, SLAB_PANIC);
+	avc_xperms_data_cachep = KMEM_CACHE(extended_perms_data, SLAB_PANIC);
+}
+
+int avc_get_hash_stats(char *page)
+{
+	int i, chain_len, max_chain_len, slots_used;
+	struct avc_node *node;
+	struct hlist_head *head;
+
+	rcu_read_lock();
+
+	slots_used = 0;
+	max_chain_len = 0;
+	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
+		head = &selinux_avc.avc_cache.slots[i];
+		if (!hlist_empty(head)) {
+			slots_used++;
+			chain_len = 0;
+			hlist_for_each_entry_rcu(node, head, list)
+				chain_len++;
+			if (chain_len > max_chain_len)
+				max_chain_len = chain_len;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n"
+			 "longest chain: %d\n",
+			 atomic_read(&selinux_avc.avc_cache.active_nodes),
+			 slots_used, AVC_CACHE_SLOTS, max_chain_len);
+}
+
+/*
+ * using a linked list for extended_perms_decision lookup because the list is
+ * always small. i.e. less than 5, typically 1
+ */
+static struct extended_perms_decision *
+avc_xperms_decision_lookup(u8 driver, u8 base_perm,
+			   struct avc_xperms_node *xp_node)
+{
+	struct avc_xperms_decision_node *xpd_node;
+
+	list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) {
+		if (xpd_node->xpd.driver == driver &&
+		    xpd_node->xpd.base_perm == base_perm)
+			return &xpd_node->xpd;
+	}
+	return NULL;
+}
+
+static inline unsigned int
+avc_xperms_has_perm(struct extended_perms_decision *xpd,
+					u8 perm, u8 which)
+{
+	unsigned int rc = 0;
+
+	if ((which == XPERMS_ALLOWED) &&
+			(xpd->used & XPERMS_ALLOWED))
+		rc = security_xperm_test(xpd->allowed->p, perm);
+	else if ((which == XPERMS_AUDITALLOW) &&
+			(xpd->used & XPERMS_AUDITALLOW))
+		rc = security_xperm_test(xpd->auditallow->p, perm);
+	else if ((which == XPERMS_DONTAUDIT) &&
+			(xpd->used & XPERMS_DONTAUDIT))
+		rc = security_xperm_test(xpd->dontaudit->p, perm);
+	return rc;
+}
+
+static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node,
+				  u8 driver, u8 base_perm, u8 perm)
+{
+	struct extended_perms_decision *xpd;
+	security_xperm_set(xp_node->xp.drivers.p, driver);
+	xp_node->xp.base_perms |= base_perm;
+	xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node);
+	if (xpd && xpd->allowed)
+		security_xperm_set(xpd->allowed->p, perm);
+}
+
+static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node)
+{
+	struct extended_perms_decision *xpd;
+
+	xpd = &xpd_node->xpd;
+	if (xpd->allowed)
+		kmem_cache_free(avc_xperms_data_cachep, xpd->allowed);
+	if (xpd->auditallow)
+		kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow);
+	if (xpd->dontaudit)
+		kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit);
+	kmem_cache_free(avc_xperms_decision_cachep, xpd_node);
+}
+
+static void avc_xperms_free(struct avc_xperms_node *xp_node)
+{
+	struct avc_xperms_decision_node *xpd_node, *tmp;
+
+	if (!xp_node)
+		return;
+
+	list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) {
+		list_del(&xpd_node->xpd_list);
+		avc_xperms_decision_free(xpd_node);
+	}
+	kmem_cache_free(avc_xperms_cachep, xp_node);
+}
+
+static void avc_copy_xperms_decision(struct extended_perms_decision *dest,
+					struct extended_perms_decision *src)
+{
+	dest->base_perm = src->base_perm;
+	dest->driver = src->driver;
+	dest->used = src->used;
+	if (dest->used & XPERMS_ALLOWED)
+		memcpy(dest->allowed->p, src->allowed->p,
+				sizeof(src->allowed->p));
+	if (dest->used & XPERMS_AUDITALLOW)
+		memcpy(dest->auditallow->p, src->auditallow->p,
+				sizeof(src->auditallow->p));
+	if (dest->used & XPERMS_DONTAUDIT)
+		memcpy(dest->dontaudit->p, src->dontaudit->p,
+				sizeof(src->dontaudit->p));
+}
+
+/*
+ * similar to avc_copy_xperms_decision, but only copy decision
+ * information relevant to this perm
+ */
+static inline void avc_quick_copy_xperms_decision(u8 perm,
+			struct extended_perms_decision *dest,
+			struct extended_perms_decision *src)
+{
+	/*
+	 * compute index of the u32 of the 256 bits (8 u32s) that contain this
+	 * command permission
+	 */
+	u8 i = perm >> 5;
+
+	dest->base_perm = src->base_perm;
+	dest->used = src->used;
+	if (dest->used & XPERMS_ALLOWED)
+		dest->allowed->p[i] = src->allowed->p[i];
+	if (dest->used & XPERMS_AUDITALLOW)
+		dest->auditallow->p[i] = src->auditallow->p[i];
+	if (dest->used & XPERMS_DONTAUDIT)
+		dest->dontaudit->p[i] = src->dontaudit->p[i];
+}
+
+static struct avc_xperms_decision_node
+		*avc_xperms_decision_alloc(u8 which)
+{
+	struct avc_xperms_decision_node *xpd_node;
+	struct extended_perms_decision *xpd;
+
+	xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT);
+	if (!xpd_node)
+		return NULL;
+
+	xpd = &xpd_node->xpd;
+	if (which & XPERMS_ALLOWED) {
+		xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep,
+						 GFP_NOWAIT);
+		if (!xpd->allowed)
+			goto error;
+	}
+	if (which & XPERMS_AUDITALLOW) {
+		xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep,
+						    GFP_NOWAIT);
+		if (!xpd->auditallow)
+			goto error;
+	}
+	if (which & XPERMS_DONTAUDIT) {
+		xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep,
+						   GFP_NOWAIT);
+		if (!xpd->dontaudit)
+			goto error;
+	}
+	return xpd_node;
+error:
+	avc_xperms_decision_free(xpd_node);
+	return NULL;
+}
+
+static int avc_add_xperms_decision(struct avc_node *node,
+			struct extended_perms_decision *src)
+{
+	struct avc_xperms_decision_node *dest_xpd;
+
+	dest_xpd = avc_xperms_decision_alloc(src->used);
+	if (!dest_xpd)
+		return -ENOMEM;
+	avc_copy_xperms_decision(&dest_xpd->xpd, src);
+	list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head);
+	node->ae.xp_node->xp.len++;
+	return 0;
+}
+
+static struct avc_xperms_node *avc_xperms_alloc(void)
+{
+	struct avc_xperms_node *xp_node;
+
+	xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT);
+	if (!xp_node)
+		return xp_node;
+	INIT_LIST_HEAD(&xp_node->xpd_head);
+	return xp_node;
+}
+
+static int avc_xperms_populate(struct avc_node *node,
+				struct avc_xperms_node *src)
+{
+	struct avc_xperms_node *dest;
+	struct avc_xperms_decision_node *dest_xpd;
+	struct avc_xperms_decision_node *src_xpd;
+
+	if (src->xp.len == 0)
+		return 0;
+	dest = avc_xperms_alloc();
+	if (!dest)
+		return -ENOMEM;
+
+	memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p));
+	dest->xp.len = src->xp.len;
+	dest->xp.base_perms = src->xp.base_perms;
+
+	/* for each source xpd allocate a destination xpd and copy */
+	list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) {
+		dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used);
+		if (!dest_xpd)
+			goto error;
+		avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd);
+		list_add(&dest_xpd->xpd_list, &dest->xpd_head);
+	}
+	node->ae.xp_node = dest;
+	return 0;
+error:
+	avc_xperms_free(dest);
+	return -ENOMEM;
+
+}
+
+static inline u32 avc_xperms_audit_required(u32 requested,
+					struct av_decision *avd,
+					struct extended_perms_decision *xpd,
+					u8 perm,
+					int result,
+					u32 *deniedp)
+{
+	u32 denied, audited;
+
+	denied = requested & ~avd->allowed;
+	if (unlikely(denied)) {
+		audited = denied & avd->auditdeny;
+		if (audited && xpd) {
+			if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT))
+				audited = 0;
+		}
+	} else if (result) {
+		audited = denied = requested;
+	} else {
+		audited = requested & avd->auditallow;
+		if (audited && xpd) {
+			if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW))
+				audited = 0;
+		}
+	}
+
+	*deniedp = denied;
+	return audited;
+}
+
+static inline int avc_xperms_audit(u32 ssid, u32 tsid, u16 tclass,
+				   u32 requested, struct av_decision *avd,
+				   struct extended_perms_decision *xpd,
+				   u8 perm, int result,
+				   struct common_audit_data *ad)
+{
+	u32 audited, denied;
+
+	audited = avc_xperms_audit_required(
+			requested, avd, xpd, perm, result, &denied);
+	if (likely(!audited))
+		return 0;
+	return slow_avc_audit(ssid, tsid, tclass, requested,
+			audited, denied, result, ad);
+}
+
+static void avc_node_free(struct rcu_head *rhead)
+{
+	struct avc_node *node = container_of(rhead, struct avc_node, rhead);
+	avc_xperms_free(node->ae.xp_node);
+	kmem_cache_free(avc_node_cachep, node);
+	avc_cache_stats_incr(frees);
+}
+
+static void avc_node_delete(struct avc_node *node)
+{
+	hlist_del_rcu(&node->list);
+	call_rcu(&node->rhead, avc_node_free);
+	atomic_dec(&selinux_avc.avc_cache.active_nodes);
+}
+
+static void avc_node_kill(struct avc_node *node)
+{
+	avc_xperms_free(node->ae.xp_node);
+	kmem_cache_free(avc_node_cachep, node);
+	avc_cache_stats_incr(frees);
+	atomic_dec(&selinux_avc.avc_cache.active_nodes);
+}
+
+static void avc_node_replace(struct avc_node *new, struct avc_node *old)
+{
+	hlist_replace_rcu(&old->list, &new->list);
+	call_rcu(&old->rhead, avc_node_free);
+	atomic_dec(&selinux_avc.avc_cache.active_nodes);
+}
+
+static inline int avc_reclaim_node(void)
+{
+	struct avc_node *node;
+	int hvalue, try, ecx;
+	unsigned long flags;
+	struct hlist_head *head;
+	spinlock_t *lock;
+
+	for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) {
+		hvalue = atomic_inc_return(&selinux_avc.avc_cache.lru_hint) &
+			(AVC_CACHE_SLOTS - 1);
+		head = &selinux_avc.avc_cache.slots[hvalue];
+		lock = &selinux_avc.avc_cache.slots_lock[hvalue];
+
+		if (!spin_trylock_irqsave(lock, flags))
+			continue;
+
+		rcu_read_lock();
+		hlist_for_each_entry(node, head, list) {
+			avc_node_delete(node);
+			avc_cache_stats_incr(reclaims);
+			ecx++;
+			if (ecx >= AVC_CACHE_RECLAIM) {
+				rcu_read_unlock();
+				spin_unlock_irqrestore(lock, flags);
+				goto out;
+			}
+		}
+		rcu_read_unlock();
+		spin_unlock_irqrestore(lock, flags);
+	}
+out:
+	return ecx;
+}
+
+static struct avc_node *avc_alloc_node(void)
+{
+	struct avc_node *node;
+
+	node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT);
+	if (!node)
+		return NULL;
+
+	INIT_HLIST_NODE(&node->list);
+	avc_cache_stats_incr(allocations);
+
+	if (atomic_inc_return(&selinux_avc.avc_cache.active_nodes) >
+	    selinux_avc.avc_cache_threshold)
+		avc_reclaim_node();
+
+	return node;
+}
+
+static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd)
+{
+	node->ae.ssid = ssid;
+	node->ae.tsid = tsid;
+	node->ae.tclass = tclass;
+	memcpy(&node->ae.avd, avd, sizeof(node->ae.avd));
+}
+
+static inline struct avc_node *avc_search_node(u32 ssid, u32 tsid, u16 tclass)
+{
+	struct avc_node *node, *ret = NULL;
+	u32 hvalue;
+	struct hlist_head *head;
+
+	hvalue = avc_hash(ssid, tsid, tclass);
+	head = &selinux_avc.avc_cache.slots[hvalue];
+	hlist_for_each_entry_rcu(node, head, list) {
+		if (ssid == node->ae.ssid &&
+		    tclass == node->ae.tclass &&
+		    tsid == node->ae.tsid) {
+			ret = node;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * avc_lookup - Look up an AVC entry.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ *
+ * Look up an AVC entry that is valid for the
+ * (@ssid, @tsid), interpreting the permissions
+ * based on @tclass.  If a valid AVC entry exists,
+ * then this function returns the avc_node.
+ * Otherwise, this function returns NULL.
+ */
+static struct avc_node *avc_lookup(u32 ssid, u32 tsid, u16 tclass)
+{
+	struct avc_node *node;
+
+	avc_cache_stats_incr(lookups);
+	node = avc_search_node(ssid, tsid, tclass);
+
+	if (node)
+		return node;
+
+	avc_cache_stats_incr(misses);
+	return NULL;
+}
+
+static int avc_latest_notif_update(u32 seqno, int is_insert)
+{
+	int ret = 0;
+	static DEFINE_SPINLOCK(notif_lock);
+	unsigned long flag;
+
+	spin_lock_irqsave(&notif_lock, flag);
+	if (is_insert) {
+		if (seqno < selinux_avc.avc_cache.latest_notif) {
+			pr_warn("SELinux: avc:  seqno %d < latest_notif %d\n",
+			       seqno, selinux_avc.avc_cache.latest_notif);
+			ret = -EAGAIN;
+		}
+	} else {
+		if (seqno > selinux_avc.avc_cache.latest_notif)
+			selinux_avc.avc_cache.latest_notif = seqno;
+	}
+	spin_unlock_irqrestore(&notif_lock, flag);
+
+	return ret;
+}
+
+/**
+ * avc_insert - Insert an AVC entry.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @avd: resulting av decision
+ * @xp_node: resulting extended permissions
+ *
+ * Insert an AVC entry for the SID pair
+ * (@ssid, @tsid) and class @tclass.
+ * The access vectors and the sequence number are
+ * normally provided by the security server in
+ * response to a security_compute_av() call.  If the
+ * sequence number @avd->seqno is not less than the latest
+ * revocation notification, then the function copies
+ * the access vectors into a cache entry.
+ */
+static void avc_insert(u32 ssid, u32 tsid, u16 tclass,
+		       struct av_decision *avd, struct avc_xperms_node *xp_node)
+{
+	struct avc_node *pos, *node = NULL;
+	u32 hvalue;
+	unsigned long flag;
+	spinlock_t *lock;
+	struct hlist_head *head;
+
+	if (avc_latest_notif_update(avd->seqno, 1))
+		return;
+
+	node = avc_alloc_node();
+	if (!node)
+		return;
+
+	avc_node_populate(node, ssid, tsid, tclass, avd);
+	if (avc_xperms_populate(node, xp_node)) {
+		avc_node_kill(node);
+		return;
+	}
+
+	hvalue = avc_hash(ssid, tsid, tclass);
+	head = &selinux_avc.avc_cache.slots[hvalue];
+	lock = &selinux_avc.avc_cache.slots_lock[hvalue];
+	spin_lock_irqsave(lock, flag);
+	hlist_for_each_entry(pos, head, list) {
+		if (pos->ae.ssid == ssid &&
+			pos->ae.tsid == tsid &&
+			pos->ae.tclass == tclass) {
+			avc_node_replace(node, pos);
+			goto found;
+		}
+	}
+	hlist_add_head_rcu(&node->list, head);
+found:
+	spin_unlock_irqrestore(lock, flag);
+}
+
+/**
+ * avc_audit_pre_callback - SELinux specific information
+ * will be called by generic audit code
+ * @ab: the audit buffer
+ * @a: audit_data
+ */
+static void avc_audit_pre_callback(struct audit_buffer *ab, void *a)
+{
+	struct common_audit_data *ad = a;
+	struct selinux_audit_data *sad = ad->selinux_audit_data;
+	u32 av = sad->audited, perm;
+	const char *const *perms;
+	u32 i;
+
+	audit_log_format(ab, "avc:  %s ", sad->denied ? "denied" : "granted");
+
+	if (av == 0) {
+		audit_log_format(ab, " null");
+		return;
+	}
+
+	perms = secclass_map[sad->tclass-1].perms;
+
+	audit_log_format(ab, " {");
+	i = 0;
+	perm = 1;
+	while (i < (sizeof(av) * 8)) {
+		if ((perm & av) && perms[i]) {
+			audit_log_format(ab, " %s", perms[i]);
+			av &= ~perm;
+		}
+		i++;
+		perm <<= 1;
+	}
+
+	if (av)
+		audit_log_format(ab, " 0x%x", av);
+
+	audit_log_format(ab, " } for ");
+}
+
+/**
+ * avc_audit_post_callback - SELinux specific information
+ * will be called by generic audit code
+ * @ab: the audit buffer
+ * @a: audit_data
+ */
+static void avc_audit_post_callback(struct audit_buffer *ab, void *a)
+{
+	struct common_audit_data *ad = a;
+	struct selinux_audit_data *sad = ad->selinux_audit_data;
+	char *scontext = NULL;
+	char *tcontext = NULL;
+	const char *tclass = NULL;
+	u32 scontext_len;
+	u32 tcontext_len;
+	int rc;
+
+	rc = security_sid_to_context(sad->ssid, &scontext,
+				     &scontext_len);
+	if (rc)
+		audit_log_format(ab, " ssid=%d", sad->ssid);
+	else
+		audit_log_format(ab, " scontext=%s", scontext);
+
+	rc = security_sid_to_context(sad->tsid, &tcontext,
+				     &tcontext_len);
+	if (rc)
+		audit_log_format(ab, " tsid=%d", sad->tsid);
+	else
+		audit_log_format(ab, " tcontext=%s", tcontext);
+
+	tclass = secclass_map[sad->tclass-1].name;
+	audit_log_format(ab, " tclass=%s", tclass);
+
+	if (sad->denied)
+		audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1);
+
+	trace_selinux_audited(sad, scontext, tcontext, tclass);
+	kfree(tcontext);
+	kfree(scontext);
+
+	/* in case of invalid context report also the actual context string */
+	rc = security_sid_to_context_inval(sad->ssid, &scontext,
+					   &scontext_len);
+	if (!rc && scontext) {
+		if (scontext_len && scontext[scontext_len - 1] == '\0')
+			scontext_len--;
+		audit_log_format(ab, " srawcon=");
+		audit_log_n_untrustedstring(ab, scontext, scontext_len);
+		kfree(scontext);
+	}
+
+	rc = security_sid_to_context_inval(sad->tsid, &scontext,
+					   &scontext_len);
+	if (!rc && scontext) {
+		if (scontext_len && scontext[scontext_len - 1] == '\0')
+			scontext_len--;
+		audit_log_format(ab, " trawcon=");
+		audit_log_n_untrustedstring(ab, scontext, scontext_len);
+		kfree(scontext);
+	}
+}
+
+/*
+ * This is the slow part of avc audit with big stack footprint.
+ * Note that it is non-blocking and can be called from under
+ * rcu_read_lock().
+ */
+noinline int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass,
+			    u32 requested, u32 audited, u32 denied, int result,
+			    struct common_audit_data *a)
+{
+	struct common_audit_data stack_data;
+	struct selinux_audit_data sad;
+
+	if (WARN_ON(!tclass || tclass >= ARRAY_SIZE(secclass_map)))
+		return -EINVAL;
+
+	if (!a) {
+		a = &stack_data;
+		a->type = LSM_AUDIT_DATA_NONE;
+	}
+
+	sad.tclass = tclass;
+	sad.requested = requested;
+	sad.ssid = ssid;
+	sad.tsid = tsid;
+	sad.audited = audited;
+	sad.denied = denied;
+	sad.result = result;
+
+	a->selinux_audit_data = &sad;
+
+	common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback);
+	return 0;
+}
+
+/**
+ * avc_add_callback - Register a callback for security events.
+ * @callback: callback function
+ * @events: security events
+ *
+ * Register a callback function for events in the set @events.
+ * Returns %0 on success or -%ENOMEM if insufficient memory
+ * exists to add the callback.
+ */
+int __init avc_add_callback(int (*callback)(u32 event), u32 events)
+{
+	struct avc_callback_node *c;
+	int rc = 0;
+
+	c = kmalloc_obj(*c);
+	if (!c) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	c->callback = callback;
+	c->events = events;
+	c->next = avc_callbacks;
+	avc_callbacks = c;
+out:
+	return rc;
+}
+
+/**
+ * avc_update_node - Update an AVC entry
+ * @event : Updating event
+ * @perms : Permission mask bits
+ * @driver: xperm driver information
+ * @base_perm: the base permission associated with the extended permission
+ * @xperm: xperm permissions
+ * @ssid: AVC entry source sid
+ * @tsid: AVC entry target sid
+ * @tclass : AVC entry target object class
+ * @seqno : sequence number when decision was made
+ * @xpd: extended_perms_decision to be added to the node
+ * @flags: the AVC_* flags, e.g. AVC_EXTENDED_PERMS, or 0.
+ *
+ * if a valid AVC entry doesn't exist,this function returns -ENOENT.
+ * if kmalloc() called internal returns NULL, this function returns -ENOMEM.
+ * otherwise, this function updates the AVC entry. The original AVC-entry object
+ * will release later by RCU.
+ */
+static int avc_update_node(u32 event, u32 perms, u8 driver, u8 base_perm,
+			   u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno,
+			   struct extended_perms_decision *xpd, u32 flags)
+{
+	u32 hvalue;
+	int rc = 0;
+	unsigned long flag;
+	struct avc_node *pos, *node, *orig = NULL;
+	struct hlist_head *head;
+	spinlock_t *lock;
+
+	node = avc_alloc_node();
+	if (!node) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Lock the target slot */
+	hvalue = avc_hash(ssid, tsid, tclass);
+
+	head = &selinux_avc.avc_cache.slots[hvalue];
+	lock = &selinux_avc.avc_cache.slots_lock[hvalue];
+
+	spin_lock_irqsave(lock, flag);
+
+	hlist_for_each_entry(pos, head, list) {
+		if (ssid == pos->ae.ssid &&
+		    tsid == pos->ae.tsid &&
+		    tclass == pos->ae.tclass &&
+		    seqno == pos->ae.avd.seqno){
+			orig = pos;
+			break;
+		}
+	}
+
+	if (!orig) {
+		rc = -ENOENT;
+		avc_node_kill(node);
+		goto out_unlock;
+	}
+
+	/*
+	 * Copy and replace original node.
+	 */
+
+	avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd);
+
+	if (orig->ae.xp_node) {
+		rc = avc_xperms_populate(node, orig->ae.xp_node);
+		if (rc) {
+			avc_node_kill(node);
+			goto out_unlock;
+		}
+	}
+
+	switch (event) {
+	case AVC_CALLBACK_GRANT:
+		node->ae.avd.allowed |= perms;
+		if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS))
+			avc_xperms_allow_perm(node->ae.xp_node, driver, base_perm, xperm);
+		break;
+	case AVC_CALLBACK_TRY_REVOKE:
+	case AVC_CALLBACK_REVOKE:
+		node->ae.avd.allowed &= ~perms;
+		break;
+	case AVC_CALLBACK_AUDITALLOW_ENABLE:
+		node->ae.avd.auditallow |= perms;
+		break;
+	case AVC_CALLBACK_AUDITALLOW_DISABLE:
+		node->ae.avd.auditallow &= ~perms;
+		break;
+	case AVC_CALLBACK_AUDITDENY_ENABLE:
+		node->ae.avd.auditdeny |= perms;
+		break;
+	case AVC_CALLBACK_AUDITDENY_DISABLE:
+		node->ae.avd.auditdeny &= ~perms;
+		break;
+	case AVC_CALLBACK_ADD_XPERMS:
+		rc = avc_add_xperms_decision(node, xpd);
+		if (rc) {
+			avc_node_kill(node);
+			goto out_unlock;
+		}
+		break;
+	}
+	avc_node_replace(node, orig);
+out_unlock:
+	spin_unlock_irqrestore(lock, flag);
+out:
+	return rc;
+}
+
+/**
+ * avc_flush - Flush the cache
+ */
+static void avc_flush(void)
+{
+	struct hlist_head *head;
+	struct avc_node *node;
+	spinlock_t *lock;
+	unsigned long flag;
+	int i;
+
+	for (i = 0; i < AVC_CACHE_SLOTS; i++) {
+		head = &selinux_avc.avc_cache.slots[i];
+		lock = &selinux_avc.avc_cache.slots_lock[i];
+
+		spin_lock_irqsave(lock, flag);
+		/*
+		 * With preemptible RCU, the outer spinlock does not
+		 * prevent RCU grace periods from ending.
+		 */
+		rcu_read_lock();
+		hlist_for_each_entry(node, head, list)
+			avc_node_delete(node);
+		rcu_read_unlock();
+		spin_unlock_irqrestore(lock, flag);
+	}
+}
+
+/**
+ * avc_ss_reset - Flush the cache and revalidate migrated permissions.
+ * @seqno: policy sequence number
+ */
+int avc_ss_reset(u32 seqno)
+{
+	struct avc_callback_node *c;
+	int rc = 0, tmprc;
+
+	avc_flush();
+
+	for (c = avc_callbacks; c; c = c->next) {
+		if (c->events & AVC_CALLBACK_RESET) {
+			tmprc = c->callback(AVC_CALLBACK_RESET);
+			/* save the first error encountered for the return
+			   value and continue processing the callbacks */
+			if (!rc)
+				rc = tmprc;
+		}
+	}
+
+	avc_latest_notif_update(seqno, 0);
+	return rc;
+}
+
+/**
+ * avc_compute_av - Add an entry to the AVC based on the security policy
+ * @ssid: subject
+ * @tsid: object/target
+ * @tclass: object class
+ * @avd: access vector decision
+ * @xp_node: AVC extended permissions node
+ *
+ * Slow-path helper function for avc_has_perm_noaudit, when the avc_node lookup
+ * fails.  Don't inline this, since it's the slow-path and just results in a
+ * bigger stack frame.
+ */
+static noinline void avc_compute_av(u32 ssid, u32 tsid, u16 tclass,
+				    struct av_decision *avd,
+				    struct avc_xperms_node *xp_node)
+{
+	INIT_LIST_HEAD(&xp_node->xpd_head);
+	security_compute_av(ssid, tsid, tclass, avd, &xp_node->xp);
+	avc_insert(ssid, tsid, tclass, avd, xp_node);
+}
+
+static noinline int avc_denied(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			       u8 driver, u8 base_perm, u8 xperm,
+			       unsigned int flags, struct av_decision *avd)
+{
+	if (flags & AVC_STRICT)
+		return -EACCES;
+
+	if (enforcing_enabled() &&
+	    !(avd->flags & AVD_FLAGS_PERMISSIVE))
+		return -EACCES;
+
+	avc_update_node(AVC_CALLBACK_GRANT, requested, driver, base_perm,
+			xperm, ssid, tsid, tclass, avd->seqno, NULL, flags);
+	return 0;
+}
+
+/*
+ * The avc extended permissions logic adds an additional 256 bits of
+ * permissions to an avc node when extended permissions for that node are
+ * specified in the avtab. If the additional 256 permissions is not adequate,
+ * as-is the case with ioctls, then multiple may be chained together and the
+ * driver field is used to specify which set contains the permission.
+ */
+int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			   u8 driver, u8 base_perm, u8 xperm,
+			   struct common_audit_data *ad)
+{
+	struct avc_node *node;
+	struct av_decision avd;
+	u32 denied;
+	struct extended_perms_decision local_xpd;
+	struct extended_perms_decision *xpd = NULL;
+	struct extended_perms_data allowed;
+	struct extended_perms_data auditallow;
+	struct extended_perms_data dontaudit;
+	struct avc_xperms_node local_xp_node;
+	struct avc_xperms_node *xp_node;
+	int rc = 0, rc2;
+
+	xp_node = &local_xp_node;
+	if (WARN_ON(!requested))
+		return -EACCES;
+
+	rcu_read_lock();
+
+	node = avc_lookup(ssid, tsid, tclass);
+	if (unlikely(!node)) {
+		avc_compute_av(ssid, tsid, tclass, &avd, xp_node);
+	} else {
+		memcpy(&avd, &node->ae.avd, sizeof(avd));
+		xp_node = node->ae.xp_node;
+	}
+	/* if extended permissions are not defined, only consider av_decision */
+	if (!xp_node || !xp_node->xp.len)
+		goto decision;
+
+	local_xpd.allowed = &allowed;
+	local_xpd.auditallow = &auditallow;
+	local_xpd.dontaudit = &dontaudit;
+
+	xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node);
+	if (unlikely(!xpd)) {
+		/*
+		 * Compute the extended_perms_decision only if the driver
+		 * is flagged and the base permission is known.
+		 */
+		if (!security_xperm_test(xp_node->xp.drivers.p, driver) ||
+		    !(xp_node->xp.base_perms & base_perm)) {
+			avd.allowed &= ~requested;
+			goto decision;
+		}
+		rcu_read_unlock();
+		security_compute_xperms_decision(ssid, tsid, tclass, driver,
+						 base_perm, &local_xpd);
+		rcu_read_lock();
+		avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver,
+				base_perm, xperm, ssid, tsid, tclass, avd.seqno,
+				&local_xpd, 0);
+	} else {
+		avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd);
+	}
+	xpd = &local_xpd;
+
+	if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED))
+		avd.allowed &= ~requested;
+
+decision:
+	denied = requested & ~(avd.allowed);
+	if (unlikely(denied))
+		rc = avc_denied(ssid, tsid, tclass, requested, driver,
+				base_perm, xperm, AVC_EXTENDED_PERMS, &avd);
+
+	rcu_read_unlock();
+
+	rc2 = avc_xperms_audit(ssid, tsid, tclass, requested,
+			&avd, xpd, xperm, rc, ad);
+	if (rc2)
+		return rc2;
+	return rc;
+}
+
+/**
+ * avc_perm_nonode - Add an entry to the AVC
+ * @ssid: subject
+ * @tsid: object/target
+ * @tclass: object class
+ * @requested: requested permissions
+ * @flags: AVC flags
+ * @avd: access vector decision
+ *
+ * This is the "we have no node" part of avc_has_perm_noaudit(), which is
+ * unlikely and needs extra stack space for the new node that we generate, so
+ * don't inline it.
+ */
+static noinline int avc_perm_nonode(u32 ssid, u32 tsid, u16 tclass,
+				    u32 requested, unsigned int flags,
+				    struct av_decision *avd)
+{
+	u32 denied;
+	struct avc_xperms_node xp_node;
+
+	avc_compute_av(ssid, tsid, tclass, avd, &xp_node);
+	denied = requested & ~(avd->allowed);
+	if (unlikely(denied))
+		return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0,
+				  flags, avd);
+	return 0;
+}
+
+/**
+ * avc_has_perm_noaudit - Check permissions but perform no auditing.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @requested: requested permissions, interpreted based on @tclass
+ * @flags:  AVC_STRICT or 0
+ * @avd: access vector decisions
+ *
+ * Check the AVC to determine whether the @requested permissions are granted
+ * for the SID pair (@ssid, @tsid), interpreting the permissions
+ * based on @tclass, and call the security server on a cache miss to obtain
+ * a new decision and add it to the cache.  Return a copy of the decisions
+ * in @avd.  Return %0 if all @requested permissions are granted,
+ * -%EACCES if any permissions are denied, or another -errno upon
+ * other errors.  This function is typically called by avc_has_perm(),
+ * but may also be called directly to separate permission checking from
+ * auditing, e.g. in cases where a lock must be held for the check but
+ * should be released for the auditing.
+ */
+inline int avc_has_perm_noaudit(u32 ssid, u32 tsid,
+				u16 tclass, u32 requested,
+				unsigned int flags,
+				struct av_decision *avd)
+{
+	u32 denied;
+	struct avc_node *node;
+
+	if (WARN_ON(!requested))
+		return -EACCES;
+
+	rcu_read_lock();
+	node = avc_lookup(ssid, tsid, tclass);
+	if (unlikely(!node)) {
+		rcu_read_unlock();
+		return avc_perm_nonode(ssid, tsid, tclass, requested,
+				       flags, avd);
+	}
+	denied = requested & ~node->ae.avd.allowed;
+	memcpy(avd, &node->ae.avd, sizeof(*avd));
+	rcu_read_unlock();
+
+	if (unlikely(denied))
+		return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0,
+				  flags, avd);
+	return 0;
+}
+
+/**
+ * avc_has_perm - Check permissions and perform any appropriate auditing.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @requested: requested permissions, interpreted based on @tclass
+ * @auditdata: auxiliary audit data
+ *
+ * Check the AVC to determine whether the @requested permissions are granted
+ * for the SID pair (@ssid, @tsid), interpreting the permissions
+ * based on @tclass, and call the security server on a cache miss to obtain
+ * a new decision and add it to the cache.  Audit the granting or denial of
+ * permissions in accordance with the policy.  Return %0 if all @requested
+ * permissions are granted, -%EACCES if any permissions are denied, or
+ * another -errno upon other errors.
+ */
+int avc_has_perm(u32 ssid, u32 tsid, u16 tclass,
+		 u32 requested, struct common_audit_data *auditdata)
+{
+	struct av_decision avd;
+	int rc, rc2;
+
+	rc = avc_has_perm_noaudit(ssid, tsid, tclass, requested, 0,
+				  &avd);
+
+	rc2 = avc_audit(ssid, tsid, tclass, requested, &avd, rc,
+			auditdata);
+	if (rc2)
+		return rc2;
+	return rc;
+}
+
+u32 avc_policy_seqno(void)
+{
+	return selinux_avc.avc_cache.latest_notif;
+}
diff --git a/security/selinux/genheaders.c b/security/selinux/genheaders.c
new file mode 100644
index 000000000..3834d7eb0
--- /dev/null
+++ b/security/selinux/genheaders.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <ctype.h>
+
+struct security_class_mapping {
+	const char *name;
+	const char *perms[sizeof(unsigned) * 8 + 1];
+};
+
+#include "classmap.h"
+#include "initial_sid_to_string.h"
+
+const char *progname;
+
+static void usage(void)
+{
+	printf("usage: %s flask.h av_permissions.h\n", progname);
+	exit(1);
+}
+
+static char *stoupperx(const char *s)
+{
+	char *s2 = strdup(s);
+	char *p;
+
+	if (!s2) {
+		fprintf(stderr, "%s:  out of memory\n", progname);
+		exit(3);
+	}
+
+	for (p = s2; *p; p++)
+		*p = toupper(*p);
+	return s2;
+}
+
+int main(int argc, char *argv[])
+{
+	int i, j;
+	int isids_len;
+	FILE *fout;
+
+	progname = argv[0];
+
+	if (argc < 3)
+		usage();
+
+	fout = fopen(argv[1], "w");
+	if (!fout) {
+		fprintf(stderr, "Could not open %s for writing:  %s\n",
+			argv[1], strerror(errno));
+		exit(2);
+	}
+
+	fprintf(fout, "/* This file is automatically generated.  Do not edit. */\n");
+	fprintf(fout, "#ifndef _SELINUX_FLASK_H_\n#define _SELINUX_FLASK_H_\n\n");
+
+	for (i = 0; secclass_map[i].name; i++) {
+		char *name = stoupperx(secclass_map[i].name);
+
+		fprintf(fout, "#define SECCLASS_%-39s %2d\n", name, i+1);
+		free(name);
+	}
+
+	fprintf(fout, "\n");
+
+	isids_len = sizeof(initial_sid_to_string) / sizeof(char *);
+	for (i = 1; i < isids_len; i++) {
+		const char *s = initial_sid_to_string[i];
+		if (s) {
+			char *sidname = stoupperx(s);
+
+			fprintf(fout, "#define SECINITSID_%-39s %2d\n", sidname, i);
+			free(sidname);
+		}
+	}
+	fprintf(fout, "\n#define SECINITSID_NUM %d\n", i-1);
+	fprintf(fout, "\nstatic inline bool security_is_socket_class(u16 kern_tclass)\n");
+	fprintf(fout, "{\n");
+	fprintf(fout, "\tbool sock = false;\n\n");
+	fprintf(fout, "\tswitch (kern_tclass) {\n");
+	for (i = 0; secclass_map[i].name; i++) {
+		static char s[] = "SOCKET";
+		int len, l;
+		char *name = stoupperx(secclass_map[i].name);
+
+		len = strlen(name);
+		l = sizeof(s) - 1;
+		if (len >= l && memcmp(name + len - l, s, l) == 0)
+			fprintf(fout, "\tcase SECCLASS_%s:\n", name);
+		free(name);
+	}
+	fprintf(fout, "\t\tsock = true;\n");
+	fprintf(fout, "\t\tbreak;\n");
+	fprintf(fout, "\tdefault:\n");
+	fprintf(fout, "\t\tbreak;\n");
+	fprintf(fout, "\t}\n\n");
+	fprintf(fout, "\treturn sock;\n");
+	fprintf(fout, "}\n");
+
+	fprintf(fout, "\n#endif\n");
+
+	if (fclose(fout) != 0) {
+		fprintf(stderr, "Could not successfully close %s:  %s\n",
+			argv[1], strerror(errno));
+		exit(4);
+	}
+
+	fout = fopen(argv[2], "w");
+	if (!fout) {
+		fprintf(stderr, "Could not open %s for writing:  %s\n",
+			argv[2], strerror(errno));
+		exit(5);
+	}
+
+	fprintf(fout, "/* This file is automatically generated.  Do not edit. */\n");
+	fprintf(fout, "#ifndef _SELINUX_AV_PERMISSIONS_H_\n#define _SELINUX_AV_PERMISSIONS_H_\n\n");
+
+	for (i = 0; secclass_map[i].name; i++) {
+		const struct security_class_mapping *map = &secclass_map[i];
+		int len;
+		char *name = stoupperx(map->name);
+
+		len = strlen(name);
+		for (j = 0; map->perms[j]; j++) {
+			char *permname;
+
+			if (j >= 32) {
+				fprintf(stderr, "Too many permissions to fit into an access vector at (%s, %s).\n",
+					map->name, map->perms[j]);
+				exit(5);
+			}
+			permname = stoupperx(map->perms[j]);
+			fprintf(fout, "#define %s__%-*s 0x%08xU\n", name,
+				39-len, permname, 1U<<j);
+			free(permname);
+		}
+		free(name);
+	}
+
+	fprintf(fout, "\n#endif\n");
+
+	if (fclose(fout) != 0) {
+		fprintf(stderr, "Could not successfully close %s:  %s\n",
+			argv[2], strerror(errno));
+		exit(6);
+	}
+
+	exit(0);
+}
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
new file mode 100644
index 000000000..035aaf113
--- /dev/null
+++ b/security/selinux/hooks.c
@@ -0,0 +1,8008 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Security-Enhanced Linux (SELinux) security module
+ *
+ *  This file contains the SELinux hook function implementations.
+ *
+ *  Authors:  Stephen Smalley, <stephen.smalley.work@gmail.com>
+ *	      Chris Vance, <cvance@nai.com>
+ *	      Wayne Salamon, <wsalamon@nai.com>
+ *	      James Morris <jmorris@redhat.com>
+ *
+ *  Copyright (C) 2001,2002 Networks Associates Technology, Inc.
+ *  Copyright (C) 2003-2008 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ *					   Eric Paris <eparis@redhat.com>
+ *  Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
+ *			    <dgoeddel@trustedcs.com>
+ *  Copyright (C) 2006, 2007, 2009 Hewlett-Packard Development Company, L.P.
+ *	Paul Moore <paul@paul-moore.com>
+ *  Copyright (C) 2007 Hitachi Software Engineering Co., Ltd.
+ *		       Yuichi Nakamura <ynakam@hitachisoft.jp>
+ *  Copyright (C) 2016 Mellanox Technologies
+ */
+
+#include <linux/init.h>
+#include <linux/kd.h>
+#include <linux/kernel.h>
+#include <linux/kernel_read_file.h>
+#include <linux/errno.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/lsm_hooks.h>
+#include <linux/xattr.h>
+#include <linux/capability.h>
+#include <linux/unistd.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+#include <linux/proc_fs.h>
+#include <linux/swap.h>
+#include <linux/spinlock.h>
+#include <linux/syscalls.h>
+#include <linux/dcache.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/tty.h>
+#include <net/icmp.h>
+#include <net/ip.h>		/* for local_port_range[] */
+#include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
+#include <net/inet_connection_sock.h>
+#include <net/net_namespace.h>
+#include <net/netlabel.h>
+#include <linux/uaccess.h>
+#include <asm/ioctls.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>	/* for network interface checks */
+#include <net/netlink.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/sctp.h>
+#include <net/sctp/structs.h>
+#include <linux/quota.h>
+#include <linux/un.h>		/* for Unix socket types */
+#include <net/af_unix.h>	/* for Unix socket types */
+#include <linux/parser.h>
+#include <linux/nfs_mount.h>
+#include <net/ipv6.h>
+#include <linux/hugetlb.h>
+#include <linux/personality.h>
+#include <linux/audit.h>
+#include <linux/string.h>
+#include <linux/mutex.h>
+#include <linux/posix-timers.h>
+#include <linux/syslog.h>
+#include <linux/user_namespace.h>
+#include <linux/export.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <uapi/linux/shm.h>
+#include <linux/bpf.h>
+#include <linux/kernfs.h>
+#include <linux/stringhash.h>	/* for hashlen_string() */
+#include <uapi/linux/mount.h>
+#include <linux/fsnotify.h>
+#include <linux/fanotify.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/lsm.h>
+#include <linux/memfd.h>
+#include <uapi/linux/inet_diag.h>
+
+#include "initcalls.h"
+#include "avc.h"
+#include "objsec.h"
+#include "netif.h"
+#include "netnode.h"
+#include "netport.h"
+#include "ibpkey.h"
+#include "xfrm.h"
+#include "netlabel.h"
+#include "audit.h"
+#include "avc_ss.h"
+#include "ima.h"
+
+#define SELINUX_INODE_INIT_XATTRS 1
+
+struct selinux_state selinux_state;
+
+/* SECMARK reference count */
+static atomic_t selinux_secmark_refcount = ATOMIC_INIT(0);
+
+#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
+static int selinux_enforcing_boot __initdata;
+
+static int __init enforcing_setup(char *str)
+{
+	unsigned long enforcing;
+	if (!kstrtoul(str, 0, &enforcing))
+		selinux_enforcing_boot = enforcing ? 1 : 0;
+	return 1;
+}
+__setup("enforcing=", enforcing_setup);
+#else
+#define selinux_enforcing_boot 1
+#endif
+
+int selinux_enabled_boot __initdata = 1;
+#ifdef CONFIG_SECURITY_SELINUX_BOOTPARAM
+static int __init selinux_enabled_setup(char *str)
+{
+	unsigned long enabled;
+	if (!kstrtoul(str, 0, &enabled))
+		selinux_enabled_boot = enabled ? 1 : 0;
+	return 1;
+}
+__setup("selinux=", selinux_enabled_setup);
+#endif
+
+static int __init checkreqprot_setup(char *str)
+{
+	unsigned long checkreqprot;
+
+	if (!kstrtoul(str, 0, &checkreqprot)) {
+		if (checkreqprot)
+			pr_err("SELinux: checkreqprot set to 1 via kernel parameter.  This is no longer supported.\n");
+	}
+	return 1;
+}
+__setup("checkreqprot=", checkreqprot_setup);
+
+/**
+ * selinux_secmark_enabled - Check to see if SECMARK is currently enabled
+ *
+ * Description:
+ * This function checks the SECMARK reference counter to see if any SECMARK
+ * targets are currently configured, if the reference counter is greater than
+ * zero SECMARK is considered to be enabled.  Returns true (1) if SECMARK is
+ * enabled, false (0) if SECMARK is disabled.  If the always_check_network
+ * policy capability is enabled, SECMARK is always considered enabled.
+ *
+ */
+static int selinux_secmark_enabled(void)
+{
+	return (selinux_policycap_alwaysnetwork() ||
+		atomic_read(&selinux_secmark_refcount));
+}
+
+/**
+ * selinux_peerlbl_enabled - Check to see if peer labeling is currently enabled
+ *
+ * Description:
+ * This function checks if NetLabel or labeled IPSEC is enabled.  Returns true
+ * (1) if any are enabled or false (0) if neither are enabled.  If the
+ * always_check_network policy capability is enabled, peer labeling
+ * is always considered enabled.
+ *
+ */
+static int selinux_peerlbl_enabled(void)
+{
+	return (selinux_policycap_alwaysnetwork() ||
+		netlbl_enabled() || selinux_xfrm_enabled());
+}
+
+static int selinux_netcache_avc_callback(u32 event)
+{
+	if (event == AVC_CALLBACK_RESET) {
+		sel_netif_flush();
+		sel_netnode_flush();
+		sel_netport_flush();
+		synchronize_net();
+	}
+	return 0;
+}
+
+static int selinux_lsm_notifier_avc_callback(u32 event)
+{
+	if (event == AVC_CALLBACK_RESET) {
+		sel_ib_pkey_flush();
+		call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL);
+	}
+
+	return 0;
+}
+
+/*
+ * initialise the security for the init task
+ */
+static void cred_init_security(void)
+{
+	struct cred_security_struct *crsec;
+
+	/* NOTE: the lsm framework zeros out the buffer on allocation */
+
+	crsec = selinux_cred(unrcu_pointer(current->real_cred));
+	crsec->osid = crsec->sid = SECINITSID_KERNEL;
+}
+
+/*
+ * get the security ID of a set of credentials
+ */
+static inline u32 cred_sid(const struct cred *cred)
+{
+	const struct cred_security_struct *crsec;
+
+	crsec = selinux_cred(cred);
+	return crsec->sid;
+}
+
+static void __ad_net_init(struct common_audit_data *ad,
+			  struct lsm_network_audit *net,
+			  int ifindex, struct sock *sk, u16 family)
+{
+	ad->type = LSM_AUDIT_DATA_NET;
+	ad->u.net = net;
+	net->netif = ifindex;
+	net->sk = sk;
+	net->family = family;
+}
+
+static void ad_net_init_from_sk(struct common_audit_data *ad,
+				struct lsm_network_audit *net,
+				struct sock *sk)
+{
+	__ad_net_init(ad, net, 0, sk, 0);
+}
+
+static void ad_net_init_from_iif(struct common_audit_data *ad,
+				 struct lsm_network_audit *net,
+				 int ifindex, u16 family)
+{
+	__ad_net_init(ad, net, ifindex, NULL, family);
+}
+
+/*
+ * get the objective security ID of a task
+ */
+static inline u32 task_sid_obj(const struct task_struct *task)
+{
+	u32 sid;
+
+	rcu_read_lock();
+	sid = cred_sid(__task_cred(task));
+	rcu_read_unlock();
+	return sid;
+}
+
+static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry);
+
+/*
+ * Try reloading inode security labels that have been marked as invalid.  The
+ * @may_sleep parameter indicates when sleeping and thus reloading labels is
+ * allowed; when set to false, returns -ECHILD when the label is
+ * invalid.  The @dentry parameter should be set to a dentry of the inode.
+ */
+static int __inode_security_revalidate(struct inode *inode,
+				       struct dentry *dentry,
+				       bool may_sleep)
+{
+	if (!selinux_initialized())
+		return 0;
+
+	if (may_sleep)
+		might_sleep();
+	else
+		return -ECHILD;
+
+	/*
+	 * Check to ensure that an inode's SELinux state is valid and try
+	 * reloading the inode security label if necessary.  This will fail if
+	 * @dentry is NULL and no dentry for this inode can be found; in that
+	 * case, continue using the old label.
+	 */
+	inode_doinit_with_dentry(inode, dentry);
+	return 0;
+}
+
+static struct inode_security_struct *inode_security_novalidate(struct inode *inode)
+{
+	return selinux_inode(inode);
+}
+
+static inline struct inode_security_struct *inode_security_rcu(struct inode *inode,
+							       bool rcu)
+{
+	int rc;
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	/* check below is racy, but revalidate will recheck with lock held */
+	if (data_race(likely(isec->initialized == LABEL_INITIALIZED)))
+		return isec;
+	rc = __inode_security_revalidate(inode, NULL, !rcu);
+	if (rc)
+		return ERR_PTR(rc);
+	return isec;
+}
+
+/*
+ * Get the security label of an inode.
+ */
+static inline struct inode_security_struct *inode_security(struct inode *inode)
+{
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	/* check below is racy, but revalidate will recheck with lock held */
+	if (data_race(likely(isec->initialized == LABEL_INITIALIZED)))
+		return isec;
+	__inode_security_revalidate(inode, NULL, true);
+	return isec;
+}
+
+static inline struct inode_security_struct *backing_inode_security_novalidate(struct dentry *dentry)
+{
+	return selinux_inode(d_backing_inode(dentry));
+}
+
+/*
+ * Get the security label of a dentry's backing inode.
+ */
+static inline struct inode_security_struct *backing_inode_security(struct dentry *dentry)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	/* check below is racy, but revalidate will recheck with lock held */
+	if (data_race(likely(isec->initialized == LABEL_INITIALIZED)))
+		return isec;
+	__inode_security_revalidate(inode, dentry, true);
+	return isec;
+}
+
+static void inode_free_security(struct inode *inode)
+{
+	struct inode_security_struct *isec = selinux_inode(inode);
+	struct superblock_security_struct *sbsec;
+
+	if (!isec)
+		return;
+	sbsec = selinux_superblock(inode->i_sb);
+	/*
+	 * As not all inode security structures are in a list, we check for
+	 * empty list outside of the lock to make sure that we won't waste
+	 * time taking a lock doing nothing.
+	 *
+	 * The list_del_init() function can be safely called more than once.
+	 * It should not be possible for this function to be called with
+	 * concurrent list_add(), but for better safety against future changes
+	 * in the code, we use list_empty_careful() here.
+	 */
+	if (!list_empty_careful(&isec->list)) {
+		spin_lock(&sbsec->isec_lock);
+		list_del_init(&isec->list);
+		spin_unlock(&sbsec->isec_lock);
+	}
+}
+
+struct selinux_mnt_opts {
+	u32 fscontext_sid;
+	u32 context_sid;
+	u32 rootcontext_sid;
+	u32 defcontext_sid;
+};
+
+static void selinux_free_mnt_opts(void *mnt_opts)
+{
+	kfree(mnt_opts);
+}
+
+enum {
+	Opt_error = -1,
+	Opt_context = 0,
+	Opt_defcontext = 1,
+	Opt_fscontext = 2,
+	Opt_rootcontext = 3,
+	Opt_seclabel = 4,
+};
+
+#define A(s, has_arg) {#s, sizeof(#s) - 1, Opt_##s, has_arg}
+static const struct {
+	const char *name;
+	int len;
+	int opt;
+	bool has_arg;
+} tokens[] = {
+	A(context, true),
+	A(fscontext, true),
+	A(defcontext, true),
+	A(rootcontext, true),
+	A(seclabel, false),
+};
+#undef A
+
+static int match_opt_prefix(char *s, int l, char **arg)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(tokens); i++) {
+		size_t len = tokens[i].len;
+		if (len > l || memcmp(s, tokens[i].name, len))
+			continue;
+		if (tokens[i].has_arg) {
+			if (len == l || s[len] != '=')
+				continue;
+			*arg = s + len + 1;
+		} else if (len != l)
+			continue;
+		return tokens[i].opt;
+	}
+	return Opt_error;
+}
+
+#define SEL_MOUNT_FAIL_MSG "SELinux:  duplicate or incompatible mount options\n"
+
+static int may_context_mount_sb_relabel(u32 sid,
+			struct superblock_security_struct *sbsec,
+			const struct cred *cred)
+{
+	const struct cred_security_struct *crsec = selinux_cred(cred);
+	int rc;
+
+	rc = avc_has_perm(crsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
+			  FILESYSTEM__RELABELFROM, NULL);
+	if (rc)
+		return rc;
+
+	rc = avc_has_perm(crsec->sid, sid, SECCLASS_FILESYSTEM,
+			  FILESYSTEM__RELABELTO, NULL);
+	return rc;
+}
+
+static int may_context_mount_inode_relabel(u32 sid,
+			struct superblock_security_struct *sbsec,
+			const struct cred *cred)
+{
+	const struct cred_security_struct *crsec = selinux_cred(cred);
+	int rc;
+	rc = avc_has_perm(crsec->sid, sbsec->sid, SECCLASS_FILESYSTEM,
+			  FILESYSTEM__RELABELFROM, NULL);
+	if (rc)
+		return rc;
+
+	rc = avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM,
+			  FILESYSTEM__ASSOCIATE, NULL);
+	return rc;
+}
+
+static int selinux_is_genfs_special_handling(struct super_block *sb)
+{
+	/* Special handling. Genfs but also in-core setxattr handler */
+	return	!strcmp(sb->s_type->name, "sysfs") ||
+		!strcmp(sb->s_type->name, "pstore") ||
+		!strcmp(sb->s_type->name, "debugfs") ||
+		!strcmp(sb->s_type->name, "tracefs") ||
+		!strcmp(sb->s_type->name, "rootfs") ||
+		(selinux_policycap_cgroupseclabel() &&
+		 (!strcmp(sb->s_type->name, "cgroup") ||
+		  !strcmp(sb->s_type->name, "cgroup2"))) ||
+		(selinux_policycap_functionfs_seclabel() &&
+		 !strcmp(sb->s_type->name, "functionfs"));
+}
+
+static int selinux_is_sblabel_mnt(struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+
+	/*
+	 * IMPORTANT: Double-check logic in this function when adding a new
+	 * SECURITY_FS_USE_* definition!
+	 */
+	BUILD_BUG_ON(SECURITY_FS_USE_MAX != 7);
+
+	switch (sbsec->behavior) {
+	case SECURITY_FS_USE_XATTR:
+	case SECURITY_FS_USE_TRANS:
+	case SECURITY_FS_USE_TASK:
+	case SECURITY_FS_USE_NATIVE:
+		return 1;
+
+	case SECURITY_FS_USE_GENFS:
+		return selinux_is_genfs_special_handling(sb);
+
+	/* Never allow relabeling on context mounts */
+	case SECURITY_FS_USE_MNTPOINT:
+	case SECURITY_FS_USE_NONE:
+	default:
+		return 0;
+	}
+}
+
+static int sb_check_xattr_support(struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+	struct dentry *root = sb->s_root;
+	struct inode *root_inode = d_backing_inode(root);
+	u32 sid;
+	int rc;
+
+	/*
+	 * Make sure that the xattr handler exists and that no
+	 * error other than -ENODATA is returned by getxattr on
+	 * the root directory.  -ENODATA is ok, as this may be
+	 * the first boot of the SELinux kernel before we have
+	 * assigned xattr values to the filesystem.
+	 */
+	if (!(root_inode->i_opflags & IOP_XATTR)) {
+		pr_warn("SELinux: (dev %s, type %s) has no xattr support\n",
+			sb->s_id, sb->s_type->name);
+		goto fallback;
+	}
+
+	rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0);
+	if (rc < 0 && rc != -ENODATA) {
+		if (rc == -EOPNOTSUPP) {
+			pr_warn("SELinux: (dev %s, type %s) has no security xattr handler\n",
+				sb->s_id, sb->s_type->name);
+			goto fallback;
+		} else {
+			pr_warn("SELinux: (dev %s, type %s) getxattr errno %d\n",
+				sb->s_id, sb->s_type->name, -rc);
+			return rc;
+		}
+	}
+	return 0;
+
+fallback:
+	/* No xattr support - try to fallback to genfs if possible. */
+	rc = security_genfs_sid(sb->s_type->name, "/",
+				SECCLASS_DIR, &sid);
+	if (rc)
+		return -EOPNOTSUPP;
+
+	pr_warn("SELinux: (dev %s, type %s) falling back to genfs\n",
+		sb->s_id, sb->s_type->name);
+	sbsec->behavior = SECURITY_FS_USE_GENFS;
+	sbsec->sid = sid;
+	return 0;
+}
+
+static int sb_finish_set_opts(struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+	struct dentry *root = sb->s_root;
+	struct inode *root_inode = d_backing_inode(root);
+	int rc = 0;
+
+	if (sbsec->behavior == SECURITY_FS_USE_XATTR) {
+		rc = sb_check_xattr_support(sb);
+		if (rc)
+			return rc;
+	}
+
+	sbsec->flags |= SE_SBINITIALIZED;
+
+	/*
+	 * Explicitly set or clear SBLABEL_MNT.  It's not sufficient to simply
+	 * leave the flag untouched because sb_clone_mnt_opts might be handing
+	 * us a superblock that needs the flag to be cleared.
+	 */
+	if (selinux_is_sblabel_mnt(sb))
+		sbsec->flags |= SBLABEL_MNT;
+	else
+		sbsec->flags &= ~SBLABEL_MNT;
+
+	/* Initialize the root inode. */
+	rc = inode_doinit_with_dentry(root_inode, root);
+
+	/* Initialize any other inodes associated with the superblock, e.g.
+	   inodes created prior to initial policy load or inodes created
+	   during get_sb by a pseudo filesystem that directly
+	   populates itself. */
+	spin_lock(&sbsec->isec_lock);
+	while (!list_empty(&sbsec->isec_head)) {
+		struct inode_security_struct *isec =
+				list_first_entry(&sbsec->isec_head,
+					   struct inode_security_struct, list);
+		struct inode *inode = isec->inode;
+		list_del_init(&isec->list);
+		spin_unlock(&sbsec->isec_lock);
+		inode = igrab(inode);
+		if (inode) {
+			if (!IS_PRIVATE(inode))
+				inode_doinit_with_dentry(inode, NULL);
+			iput(inode);
+		}
+		spin_lock(&sbsec->isec_lock);
+	}
+	spin_unlock(&sbsec->isec_lock);
+	return rc;
+}
+
+static int bad_option(struct superblock_security_struct *sbsec, char flag,
+		      u32 old_sid, u32 new_sid)
+{
+	char mnt_flags = sbsec->flags & SE_MNTMASK;
+
+	/* check if the old mount command had the same options */
+	if (sbsec->flags & SE_SBINITIALIZED)
+		if (!(sbsec->flags & flag) ||
+		    (old_sid != new_sid))
+			return 1;
+
+	/* check if we were passed the same options twice,
+	 * aka someone passed context=a,context=b
+	 */
+	if (!(sbsec->flags & SE_SBINITIALIZED))
+		if (mnt_flags & flag)
+			return 1;
+	return 0;
+}
+
+/*
+ * Allow filesystems with binary mount data to explicitly set mount point
+ * labeling information.
+ */
+static int selinux_set_mnt_opts(struct super_block *sb,
+				void *mnt_opts,
+				unsigned long kern_flags,
+				unsigned long *set_kern_flags)
+{
+	const struct cred *cred = current_cred();
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+	struct dentry *root = sb->s_root;
+	struct selinux_mnt_opts *opts = mnt_opts;
+	struct inode_security_struct *root_isec;
+	u32 fscontext_sid = 0, context_sid = 0, rootcontext_sid = 0;
+	u32 defcontext_sid = 0;
+	int rc = 0;
+
+	/*
+	 * Specifying internal flags without providing a place to
+	 * place the results is not allowed
+	 */
+	if (kern_flags && !set_kern_flags)
+		return -EINVAL;
+
+	mutex_lock(&sbsec->lock);
+
+	if (!selinux_initialized()) {
+		if (!opts) {
+			/* Defer initialization until selinux_complete_init,
+			   after the initial policy is loaded and the security
+			   server is ready to handle calls. */
+			if (kern_flags & SECURITY_LSM_NATIVE_LABELS) {
+				sbsec->flags |= SE_SBNATIVE;
+				*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+			}
+			goto out;
+		}
+		rc = -EINVAL;
+		pr_warn("SELinux: Unable to set superblock options "
+			"before the security server is initialized\n");
+		goto out;
+	}
+
+	/*
+	 * Binary mount data FS will come through this function twice.  Once
+	 * from an explicit call and once from the generic calls from the vfs.
+	 * Since the generic VFS calls will not contain any security mount data
+	 * we need to skip the double mount verification.
+	 *
+	 * This does open a hole in which we will not notice if the first
+	 * mount using this sb set explicit options and a second mount using
+	 * this sb does not set any security options.  (The first options
+	 * will be used for both mounts)
+	 */
+	if ((sbsec->flags & SE_SBINITIALIZED) && (sb->s_type->fs_flags & FS_BINARY_MOUNTDATA)
+	    && !opts)
+		goto out;
+
+	root_isec = backing_inode_security_novalidate(root);
+
+	/*
+	 * parse the mount options, check if they are valid sids.
+	 * also check if someone is trying to mount the same sb more
+	 * than once with different security options.
+	 */
+	if (opts) {
+		if (opts->fscontext_sid) {
+			fscontext_sid = opts->fscontext_sid;
+			if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
+					fscontext_sid))
+				goto out_double_mount;
+			sbsec->flags |= FSCONTEXT_MNT;
+		}
+		if (opts->context_sid) {
+			context_sid = opts->context_sid;
+			if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
+					context_sid))
+				goto out_double_mount;
+			sbsec->flags |= CONTEXT_MNT;
+		}
+		if (opts->rootcontext_sid) {
+			rootcontext_sid = opts->rootcontext_sid;
+			if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
+					rootcontext_sid))
+				goto out_double_mount;
+			sbsec->flags |= ROOTCONTEXT_MNT;
+		}
+		if (opts->defcontext_sid) {
+			defcontext_sid = opts->defcontext_sid;
+			if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
+					defcontext_sid))
+				goto out_double_mount;
+			sbsec->flags |= DEFCONTEXT_MNT;
+		}
+	}
+
+	if (sbsec->flags & SE_SBINITIALIZED) {
+		/* previously mounted with options, but not on this attempt? */
+		if ((sbsec->flags & SE_MNTMASK) && !opts)
+			goto out_double_mount;
+		rc = 0;
+		goto out;
+	}
+
+	sbsec->creator_sid = current_sid();
+
+	if (strcmp(sb->s_type->name, "proc") == 0)
+		sbsec->flags |= SE_SBPROC | SE_SBGENFS;
+
+	if (!strcmp(sb->s_type->name, "debugfs") ||
+	    !strcmp(sb->s_type->name, "tracefs") ||
+	    !strcmp(sb->s_type->name, "binder") ||
+	    !strcmp(sb->s_type->name, "bpf") ||
+	    !strcmp(sb->s_type->name, "pstore") ||
+	    !strcmp(sb->s_type->name, "securityfs") ||
+	    (selinux_policycap_functionfs_seclabel() &&
+	     !strcmp(sb->s_type->name, "functionfs")))
+		sbsec->flags |= SE_SBGENFS;
+
+	if (!strcmp(sb->s_type->name, "sysfs") ||
+	    !strcmp(sb->s_type->name, "cgroup") ||
+	    !strcmp(sb->s_type->name, "cgroup2"))
+		sbsec->flags |= SE_SBGENFS | SE_SBGENFS_XATTR;
+
+	if (!sbsec->behavior) {
+		/*
+		 * Determine the labeling behavior to use for this
+		 * filesystem type.
+		 */
+		rc = security_fs_use(sb);
+		if (rc) {
+			pr_warn("%s: security_fs_use(%s) returned %d\n",
+					__func__, sb->s_type->name, rc);
+			goto out;
+		}
+	}
+
+	/*
+	 * If this is a user namespace mount and the filesystem type is not
+	 * explicitly whitelisted, then no contexts are allowed on the command
+	 * line and security labels must be ignored.
+	 */
+	if (sb->s_user_ns != &init_user_ns &&
+	    strcmp(sb->s_type->name, "tmpfs") &&
+	    strcmp(sb->s_type->name, "ramfs") &&
+	    strcmp(sb->s_type->name, "devpts") &&
+	    strcmp(sb->s_type->name, "overlay")) {
+		if (context_sid || fscontext_sid || rootcontext_sid ||
+		    defcontext_sid) {
+			rc = -EACCES;
+			goto out;
+		}
+		if (sbsec->behavior == SECURITY_FS_USE_XATTR) {
+			sbsec->behavior = SECURITY_FS_USE_MNTPOINT;
+			rc = security_transition_sid(current_sid(),
+						     current_sid(),
+						     SECCLASS_FILE, NULL,
+						     &sbsec->mntpoint_sid);
+			if (rc)
+				goto out;
+		}
+		goto out_set_opts;
+	}
+
+	/* sets the context of the superblock for the fs being mounted. */
+	if (fscontext_sid) {
+		rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred);
+		if (rc)
+			goto out;
+
+		sbsec->sid = fscontext_sid;
+	}
+
+	/*
+	 * Switch to using mount point labeling behavior.
+	 * sets the label used on all file below the mountpoint, and will set
+	 * the superblock context if not already set.
+	 */
+	if (sbsec->flags & SE_SBNATIVE) {
+		/*
+		 * This means we are initializing a superblock that has been
+		 * mounted before the SELinux was initialized and the
+		 * filesystem requested native labeling. We had already
+		 * returned SECURITY_LSM_NATIVE_LABELS in *set_kern_flags
+		 * in the original mount attempt, so now we just need to set
+		 * the SECURITY_FS_USE_NATIVE behavior.
+		 */
+		sbsec->behavior = SECURITY_FS_USE_NATIVE;
+	} else if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !context_sid) {
+		sbsec->behavior = SECURITY_FS_USE_NATIVE;
+		*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+	}
+
+	if (context_sid) {
+		if (!fscontext_sid) {
+			rc = may_context_mount_sb_relabel(context_sid, sbsec,
+							  cred);
+			if (rc)
+				goto out;
+			sbsec->sid = context_sid;
+		} else {
+			rc = may_context_mount_inode_relabel(context_sid, sbsec,
+							     cred);
+			if (rc)
+				goto out;
+		}
+		if (!rootcontext_sid)
+			rootcontext_sid = context_sid;
+
+		sbsec->mntpoint_sid = context_sid;
+		sbsec->behavior = SECURITY_FS_USE_MNTPOINT;
+	}
+
+	if (rootcontext_sid) {
+		rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec,
+						     cred);
+		if (rc)
+			goto out;
+
+		root_isec->sid = rootcontext_sid;
+		root_isec->initialized = LABEL_INITIALIZED;
+	}
+
+	if (defcontext_sid) {
+		if (sbsec->behavior != SECURITY_FS_USE_XATTR &&
+			sbsec->behavior != SECURITY_FS_USE_NATIVE) {
+			rc = -EINVAL;
+			pr_warn("SELinux: defcontext option is "
+			       "invalid for this filesystem type\n");
+			goto out;
+		}
+
+		if (defcontext_sid != sbsec->def_sid) {
+			rc = may_context_mount_inode_relabel(defcontext_sid,
+							     sbsec, cred);
+			if (rc)
+				goto out;
+		}
+
+		sbsec->def_sid = defcontext_sid;
+	}
+
+out_set_opts:
+	rc = sb_finish_set_opts(sb);
+out:
+	mutex_unlock(&sbsec->lock);
+	return rc;
+out_double_mount:
+	rc = -EINVAL;
+	pr_warn("SELinux: mount invalid.  Same superblock, different "
+	       "security settings for (dev %s, type %s)\n", sb->s_id,
+	       sb->s_type->name);
+	goto out;
+}
+
+static int selinux_cmp_sb_context(const struct super_block *oldsb,
+				    const struct super_block *newsb)
+{
+	struct superblock_security_struct *old = selinux_superblock(oldsb);
+	struct superblock_security_struct *new = selinux_superblock(newsb);
+	char oldflags = old->flags & SE_MNTMASK;
+	char newflags = new->flags & SE_MNTMASK;
+
+	if (oldflags != newflags)
+		goto mismatch;
+	if ((oldflags & FSCONTEXT_MNT) && old->sid != new->sid)
+		goto mismatch;
+	if ((oldflags & CONTEXT_MNT) && old->mntpoint_sid != new->mntpoint_sid)
+		goto mismatch;
+	if ((oldflags & DEFCONTEXT_MNT) && old->def_sid != new->def_sid)
+		goto mismatch;
+	if (oldflags & ROOTCONTEXT_MNT) {
+		struct inode_security_struct *oldroot = backing_inode_security(oldsb->s_root);
+		struct inode_security_struct *newroot = backing_inode_security(newsb->s_root);
+		if (oldroot->sid != newroot->sid)
+			goto mismatch;
+	}
+	if (old->creator_sid != new->creator_sid)
+		goto mismatch;
+	return 0;
+mismatch:
+	pr_warn("SELinux: mount invalid.  Same superblock, "
+			    "different security settings for (dev %s, "
+			    "type %s)\n", newsb->s_id, newsb->s_type->name);
+	return -EBUSY;
+}
+
+static int selinux_sb_clone_mnt_opts(const struct super_block *oldsb,
+					struct super_block *newsb,
+					unsigned long kern_flags,
+					unsigned long *set_kern_flags)
+{
+	int rc = 0;
+	const struct superblock_security_struct *oldsbsec =
+						selinux_superblock(oldsb);
+	struct superblock_security_struct *newsbsec = selinux_superblock(newsb);
+
+	int set_fscontext =	(oldsbsec->flags & FSCONTEXT_MNT);
+	int set_context =	(oldsbsec->flags & CONTEXT_MNT);
+	int set_rootcontext =	(oldsbsec->flags & ROOTCONTEXT_MNT);
+
+	/*
+	 * Specifying internal flags without providing a place to
+	 * place the results is not allowed.
+	 */
+	if (kern_flags && !set_kern_flags)
+		return -EINVAL;
+
+	mutex_lock(&newsbsec->lock);
+
+	/*
+	 * if the parent was able to be mounted it clearly had no special lsm
+	 * mount options.  thus we can safely deal with this superblock later
+	 */
+	if (!selinux_initialized()) {
+		if (kern_flags & SECURITY_LSM_NATIVE_LABELS) {
+			newsbsec->flags |= SE_SBNATIVE;
+			*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+		}
+		goto out;
+	}
+
+	/* how can we clone if the old one wasn't set up?? */
+	BUG_ON(!(oldsbsec->flags & SE_SBINITIALIZED));
+
+	/* if fs is reusing a sb, make sure that the contexts match */
+	if (newsbsec->flags & SE_SBINITIALIZED) {
+		mutex_unlock(&newsbsec->lock);
+		if ((kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context)
+			*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+		return selinux_cmp_sb_context(oldsb, newsb);
+	}
+
+	newsbsec->flags = oldsbsec->flags;
+
+	newsbsec->sid = oldsbsec->sid;
+	newsbsec->def_sid = oldsbsec->def_sid;
+	newsbsec->behavior = oldsbsec->behavior;
+	newsbsec->creator_sid = oldsbsec->creator_sid;
+
+	if (newsbsec->behavior == SECURITY_FS_USE_NATIVE &&
+		!(kern_flags & SECURITY_LSM_NATIVE_LABELS) && !set_context) {
+		rc = security_fs_use(newsb);
+		if (rc)
+			goto out;
+	}
+
+	if (kern_flags & SECURITY_LSM_NATIVE_LABELS && !set_context) {
+		newsbsec->behavior = SECURITY_FS_USE_NATIVE;
+		*set_kern_flags |= SECURITY_LSM_NATIVE_LABELS;
+	}
+
+	if (set_context) {
+		u32 sid = oldsbsec->mntpoint_sid;
+
+		if (!set_fscontext)
+			newsbsec->sid = sid;
+		if (!set_rootcontext) {
+			struct inode_security_struct *newisec = backing_inode_security(newsb->s_root);
+			newisec->sid = sid;
+		}
+		newsbsec->mntpoint_sid = sid;
+	}
+	if (set_rootcontext) {
+		const struct inode_security_struct *oldisec = backing_inode_security(oldsb->s_root);
+		struct inode_security_struct *newisec = backing_inode_security(newsb->s_root);
+
+		newisec->sid = oldisec->sid;
+	}
+
+	sb_finish_set_opts(newsb);
+out:
+	mutex_unlock(&newsbsec->lock);
+	return rc;
+}
+
+/*
+ * NOTE: the caller is responsible for freeing the memory even if on error.
+ */
+static int selinux_add_opt(int token, const char *s, void **mnt_opts)
+{
+	struct selinux_mnt_opts *opts = *mnt_opts;
+	u32 *dst_sid;
+	int rc;
+
+	if (token == Opt_seclabel)
+		/* eaten and completely ignored */
+		return 0;
+	if (!s)
+		return -EINVAL;
+
+	if (!selinux_initialized()) {
+		pr_warn("SELinux: Unable to set superblock options before the security server is initialized\n");
+		return -EINVAL;
+	}
+
+	if (!opts) {
+		opts = kzalloc_obj(*opts);
+		if (!opts)
+			return -ENOMEM;
+		*mnt_opts = opts;
+	}
+
+	switch (token) {
+	case Opt_context:
+		if (opts->context_sid || opts->defcontext_sid)
+			goto err;
+		dst_sid = &opts->context_sid;
+		break;
+	case Opt_fscontext:
+		if (opts->fscontext_sid)
+			goto err;
+		dst_sid = &opts->fscontext_sid;
+		break;
+	case Opt_rootcontext:
+		if (opts->rootcontext_sid)
+			goto err;
+		dst_sid = &opts->rootcontext_sid;
+		break;
+	case Opt_defcontext:
+		if (opts->context_sid || opts->defcontext_sid)
+			goto err;
+		dst_sid = &opts->defcontext_sid;
+		break;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	rc = security_context_str_to_sid(s, dst_sid, GFP_KERNEL);
+	if (rc)
+		pr_warn("SELinux: security_context_str_to_sid (%s) failed with errno=%d\n",
+			s, rc);
+	return rc;
+
+err:
+	pr_warn(SEL_MOUNT_FAIL_MSG);
+	return -EINVAL;
+}
+
+static int show_sid(struct seq_file *m, u32 sid)
+{
+	char *context = NULL;
+	u32 len;
+	int rc;
+
+	rc = security_sid_to_context(sid, &context, &len);
+	if (!rc) {
+		bool has_comma = strchr(context, ',');
+
+		seq_putc(m, '=');
+		if (has_comma)
+			seq_putc(m, '\"');
+		seq_escape(m, context, "\"\n\\");
+		if (has_comma)
+			seq_putc(m, '\"');
+	}
+	kfree(context);
+	return rc;
+}
+
+static int selinux_sb_show_options(struct seq_file *m, struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+	int rc;
+
+	if (!(sbsec->flags & SE_SBINITIALIZED))
+		return 0;
+
+	if (!selinux_initialized())
+		return 0;
+
+	if (sbsec->flags & FSCONTEXT_MNT) {
+		seq_putc(m, ',');
+		seq_puts(m, FSCONTEXT_STR);
+		rc = show_sid(m, sbsec->sid);
+		if (rc)
+			return rc;
+	}
+	if (sbsec->flags & CONTEXT_MNT) {
+		seq_putc(m, ',');
+		seq_puts(m, CONTEXT_STR);
+		rc = show_sid(m, sbsec->mntpoint_sid);
+		if (rc)
+			return rc;
+	}
+	if (sbsec->flags & DEFCONTEXT_MNT) {
+		seq_putc(m, ',');
+		seq_puts(m, DEFCONTEXT_STR);
+		rc = show_sid(m, sbsec->def_sid);
+		if (rc)
+			return rc;
+	}
+	if (sbsec->flags & ROOTCONTEXT_MNT) {
+		struct dentry *root = sb->s_root;
+		struct inode_security_struct *isec = backing_inode_security(root);
+		seq_putc(m, ',');
+		seq_puts(m, ROOTCONTEXT_STR);
+		rc = show_sid(m, isec->sid);
+		if (rc)
+			return rc;
+	}
+	if (sbsec->flags & SBLABEL_MNT) {
+		seq_putc(m, ',');
+		seq_puts(m, SECLABEL_STR);
+	}
+	return 0;
+}
+
+static inline u16 inode_mode_to_security_class(umode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFSOCK:
+		return SECCLASS_SOCK_FILE;
+	case S_IFLNK:
+		return SECCLASS_LNK_FILE;
+	case S_IFREG:
+		return SECCLASS_FILE;
+	case S_IFBLK:
+		return SECCLASS_BLK_FILE;
+	case S_IFDIR:
+		return SECCLASS_DIR;
+	case S_IFCHR:
+		return SECCLASS_CHR_FILE;
+	case S_IFIFO:
+		return SECCLASS_FIFO_FILE;
+
+	}
+
+	return SECCLASS_FILE;
+}
+
+static inline int default_protocol_stream(int protocol)
+{
+	return (protocol == IPPROTO_IP || protocol == IPPROTO_TCP ||
+		protocol == IPPROTO_MPTCP);
+}
+
+static inline int default_protocol_dgram(int protocol)
+{
+	return (protocol == IPPROTO_IP || protocol == IPPROTO_UDP);
+}
+
+static inline u16 socket_type_to_security_class(int family, int type, int protocol)
+{
+	bool extsockclass = selinux_policycap_extsockclass();
+
+	switch (family) {
+	case PF_UNIX:
+		switch (type) {
+		case SOCK_STREAM:
+		case SOCK_SEQPACKET:
+			return SECCLASS_UNIX_STREAM_SOCKET;
+		case SOCK_DGRAM:
+		case SOCK_RAW:
+			return SECCLASS_UNIX_DGRAM_SOCKET;
+		}
+		break;
+	case PF_INET:
+	case PF_INET6:
+		switch (type) {
+		case SOCK_STREAM:
+		case SOCK_SEQPACKET:
+			if (default_protocol_stream(protocol))
+				return SECCLASS_TCP_SOCKET;
+			else if (extsockclass && protocol == IPPROTO_SCTP)
+				return SECCLASS_SCTP_SOCKET;
+			else
+				return SECCLASS_RAWIP_SOCKET;
+		case SOCK_DGRAM:
+			if (default_protocol_dgram(protocol))
+				return SECCLASS_UDP_SOCKET;
+			else if (extsockclass && (protocol == IPPROTO_ICMP ||
+						  protocol == IPPROTO_ICMPV6))
+				return SECCLASS_ICMP_SOCKET;
+			else
+				return SECCLASS_RAWIP_SOCKET;
+		default:
+			return SECCLASS_RAWIP_SOCKET;
+		}
+		break;
+	case PF_NETLINK:
+		switch (protocol) {
+		case NETLINK_ROUTE:
+			return SECCLASS_NETLINK_ROUTE_SOCKET;
+		case NETLINK_SOCK_DIAG:
+			return SECCLASS_NETLINK_TCPDIAG_SOCKET;
+		case NETLINK_NFLOG:
+			return SECCLASS_NETLINK_NFLOG_SOCKET;
+		case NETLINK_XFRM:
+			return SECCLASS_NETLINK_XFRM_SOCKET;
+		case NETLINK_SELINUX:
+			return SECCLASS_NETLINK_SELINUX_SOCKET;
+		case NETLINK_ISCSI:
+			return SECCLASS_NETLINK_ISCSI_SOCKET;
+		case NETLINK_AUDIT:
+			return SECCLASS_NETLINK_AUDIT_SOCKET;
+		case NETLINK_FIB_LOOKUP:
+			return SECCLASS_NETLINK_FIB_LOOKUP_SOCKET;
+		case NETLINK_CONNECTOR:
+			return SECCLASS_NETLINK_CONNECTOR_SOCKET;
+		case NETLINK_NETFILTER:
+			return SECCLASS_NETLINK_NETFILTER_SOCKET;
+		case NETLINK_DNRTMSG:
+			return SECCLASS_NETLINK_DNRT_SOCKET;
+		case NETLINK_KOBJECT_UEVENT:
+			return SECCLASS_NETLINK_KOBJECT_UEVENT_SOCKET;
+		case NETLINK_GENERIC:
+			return SECCLASS_NETLINK_GENERIC_SOCKET;
+		case NETLINK_SCSITRANSPORT:
+			return SECCLASS_NETLINK_SCSITRANSPORT_SOCKET;
+		case NETLINK_RDMA:
+			return SECCLASS_NETLINK_RDMA_SOCKET;
+		case NETLINK_CRYPTO:
+			return SECCLASS_NETLINK_CRYPTO_SOCKET;
+		default:
+			return SECCLASS_NETLINK_SOCKET;
+		}
+	case PF_PACKET:
+		return SECCLASS_PACKET_SOCKET;
+	case PF_KEY:
+		return SECCLASS_KEY_SOCKET;
+	case PF_APPLETALK:
+		return SECCLASS_APPLETALK_SOCKET;
+	}
+
+	if (extsockclass) {
+		switch (family) {
+		case PF_AX25:
+			return SECCLASS_AX25_SOCKET;
+		case PF_IPX:
+			return SECCLASS_IPX_SOCKET;
+		case PF_NETROM:
+			return SECCLASS_NETROM_SOCKET;
+		case PF_ATMPVC:
+			return SECCLASS_ATMPVC_SOCKET;
+		case PF_X25:
+			return SECCLASS_X25_SOCKET;
+		case PF_ROSE:
+			return SECCLASS_ROSE_SOCKET;
+		case PF_DECnet:
+			return SECCLASS_DECNET_SOCKET;
+		case PF_ATMSVC:
+			return SECCLASS_ATMSVC_SOCKET;
+		case PF_RDS:
+			return SECCLASS_RDS_SOCKET;
+		case PF_IRDA:
+			return SECCLASS_IRDA_SOCKET;
+		case PF_PPPOX:
+			return SECCLASS_PPPOX_SOCKET;
+		case PF_LLC:
+			return SECCLASS_LLC_SOCKET;
+		case PF_CAN:
+			return SECCLASS_CAN_SOCKET;
+		case PF_TIPC:
+			return SECCLASS_TIPC_SOCKET;
+		case PF_BLUETOOTH:
+			return SECCLASS_BLUETOOTH_SOCKET;
+		case PF_IUCV:
+			return SECCLASS_IUCV_SOCKET;
+		case PF_RXRPC:
+			return SECCLASS_RXRPC_SOCKET;
+		case PF_ISDN:
+			return SECCLASS_ISDN_SOCKET;
+		case PF_PHONET:
+			return SECCLASS_PHONET_SOCKET;
+		case PF_IEEE802154:
+			return SECCLASS_IEEE802154_SOCKET;
+		case PF_CAIF:
+			return SECCLASS_CAIF_SOCKET;
+		case PF_ALG:
+			return SECCLASS_ALG_SOCKET;
+		case PF_NFC:
+			return SECCLASS_NFC_SOCKET;
+		case PF_VSOCK:
+			return SECCLASS_VSOCK_SOCKET;
+		case PF_KCM:
+			return SECCLASS_KCM_SOCKET;
+		case PF_QIPCRTR:
+			return SECCLASS_QIPCRTR_SOCKET;
+		case PF_SMC:
+			return SECCLASS_SMC_SOCKET;
+		case PF_XDP:
+			return SECCLASS_XDP_SOCKET;
+		case PF_MCTP:
+			return SECCLASS_MCTP_SOCKET;
+#if PF_MAX > 46
+#error New address family defined, please update this function.
+#endif
+		}
+	}
+
+	return SECCLASS_SOCKET;
+}
+
+static int selinux_genfs_get_sid(struct dentry *dentry,
+				 u16 tclass,
+				 u16 flags,
+				 u32 *sid)
+{
+	int rc;
+	struct super_block *sb = dentry->d_sb;
+	char *buffer, *path;
+
+	buffer = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	path = dentry_path_raw(dentry, buffer, PATH_MAX);
+	if (IS_ERR(path))
+		rc = PTR_ERR(path);
+	else {
+		if (flags & SE_SBPROC) {
+			/* each process gets a /proc/PID/ entry. Strip off the
+			 * PID part to get a valid selinux labeling.
+			 * e.g. /proc/1/net/rpc/nfs -> /net/rpc/nfs */
+			while (path[1] >= '0' && path[1] <= '9') {
+				path[1] = '/';
+				path++;
+			}
+		}
+		rc = security_genfs_sid(sb->s_type->name,
+					path, tclass, sid);
+		if (rc == -ENOENT) {
+			/* No match in policy, mark as unlabeled. */
+			*sid = SECINITSID_UNLABELED;
+			rc = 0;
+		}
+	}
+	kfree(buffer);
+	return rc;
+}
+
+static int inode_doinit_use_xattr(struct inode *inode, struct dentry *dentry,
+				  u32 def_sid, u32 *sid)
+{
+#define INITCONTEXTLEN 255
+	char *context;
+	unsigned int len;
+	int rc;
+
+	len = INITCONTEXTLEN;
+	context = kmalloc(len + 1, GFP_NOFS);
+	if (!context)
+		return -ENOMEM;
+
+	context[len] = '\0';
+	rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, context, len);
+	if (rc == -ERANGE) {
+		kfree(context);
+
+		/* Need a larger buffer.  Query for the right size. */
+		rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX, NULL, 0);
+		if (rc < 0)
+			return rc;
+
+		len = rc;
+		context = kmalloc(len + 1, GFP_NOFS);
+		if (!context)
+			return -ENOMEM;
+
+		context[len] = '\0';
+		rc = __vfs_getxattr(dentry, inode, XATTR_NAME_SELINUX,
+				    context, len);
+	}
+	if (rc < 0) {
+		kfree(context);
+		if (rc != -ENODATA) {
+			pr_warn("SELinux: %s:  getxattr returned %d for dev=%s ino=%llu\n",
+				__func__, -rc, inode->i_sb->s_id, inode->i_ino);
+			return rc;
+		}
+		*sid = def_sid;
+		return 0;
+	}
+
+	rc = security_context_to_sid_default(context, rc, sid,
+					     def_sid, GFP_NOFS);
+	if (rc) {
+		char *dev = inode->i_sb->s_id;
+		u64 ino = inode->i_ino;
+
+		if (rc == -EINVAL) {
+			pr_notice_ratelimited("SELinux: inode=%llu on dev=%s was found to have an invalid context=%s.  This indicates you may need to relabel the inode or the filesystem in question.\n",
+					      ino, dev, context);
+		} else {
+			pr_warn("SELinux: %s:  context_to_sid(%s) returned %d for dev=%s ino=%llu\n",
+				__func__, context, -rc, dev, ino);
+		}
+	}
+	kfree(context);
+	return 0;
+}
+
+/* The inode's security attributes must be initialized before first use. */
+static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry)
+{
+	struct superblock_security_struct *sbsec = NULL;
+	struct inode_security_struct *isec = selinux_inode(inode);
+	u32 task_sid, sid = 0;
+	u16 sclass;
+	struct dentry *dentry;
+	int rc = 0;
+
+	/* check below is racy, but we will recheck with lock held */
+	if (data_race(isec->initialized == LABEL_INITIALIZED))
+		return 0;
+
+	spin_lock(&isec->lock);
+	if (isec->initialized == LABEL_INITIALIZED)
+		goto out_unlock;
+
+	if (isec->sclass == SECCLASS_FILE)
+		isec->sclass = inode_mode_to_security_class(inode->i_mode);
+
+	sbsec = selinux_superblock(inode->i_sb);
+	if (!(sbsec->flags & SE_SBINITIALIZED)) {
+		/* Defer initialization until selinux_complete_init,
+		   after the initial policy is loaded and the security
+		   server is ready to handle calls. */
+		spin_lock(&sbsec->isec_lock);
+		if (list_empty(&isec->list))
+			list_add(&isec->list, &sbsec->isec_head);
+		spin_unlock(&sbsec->isec_lock);
+		goto out_unlock;
+	}
+
+	sclass = isec->sclass;
+	task_sid = isec->task_sid;
+	sid = isec->sid;
+	isec->initialized = LABEL_PENDING;
+	spin_unlock(&isec->lock);
+
+	switch (sbsec->behavior) {
+	/*
+	 * In case of SECURITY_FS_USE_NATIVE we need to re-fetch the labels
+	 * via xattr when called from delayed_superblock_init().
+	 */
+	case SECURITY_FS_USE_NATIVE:
+	case SECURITY_FS_USE_XATTR:
+		if (!(inode->i_opflags & IOP_XATTR)) {
+			sid = sbsec->def_sid;
+			break;
+		}
+		/* Need a dentry, since the xattr API requires one.
+		   Life would be simpler if we could just pass the inode. */
+		if (opt_dentry) {
+			/* Called from d_instantiate or d_splice_alias. */
+			dentry = dget(opt_dentry);
+		} else {
+			/*
+			 * Called from selinux_complete_init, try to find a dentry.
+			 * Some filesystems really want a connected one, so try
+			 * that first.  We could split SECURITY_FS_USE_XATTR in
+			 * two, depending upon that...
+			 */
+			dentry = d_find_alias(inode);
+			if (!dentry)
+				dentry = d_find_any_alias(inode);
+		}
+		if (!dentry) {
+			/*
+			 * this is can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as these
+			 * will get fixed up the next time we go through
+			 * inode_doinit with a dentry, before these inodes could
+			 * be used again by userspace.
+			 */
+			goto out_invalid;
+		}
+
+		rc = inode_doinit_use_xattr(inode, dentry, sbsec->def_sid,
+					    &sid);
+		dput(dentry);
+		if (rc)
+			goto out;
+		break;
+	case SECURITY_FS_USE_TASK:
+		sid = task_sid;
+		break;
+	case SECURITY_FS_USE_TRANS:
+		/* Default to the fs SID. */
+		sid = sbsec->sid;
+
+		/* Try to obtain a transition SID. */
+		rc = security_transition_sid(task_sid, sid,
+					     sclass, NULL, &sid);
+		if (rc)
+			goto out;
+		break;
+	case SECURITY_FS_USE_MNTPOINT:
+		sid = sbsec->mntpoint_sid;
+		break;
+	default:
+		/* Default to the fs superblock SID. */
+		sid = sbsec->sid;
+
+		if ((sbsec->flags & SE_SBGENFS) &&
+		     (!S_ISLNK(inode->i_mode) ||
+		      selinux_policycap_genfs_seclabel_symlinks())) {
+			/* We must have a dentry to determine the label on
+			 * procfs inodes */
+			if (opt_dentry) {
+				/* Called from d_instantiate or
+				 * d_splice_alias. */
+				dentry = dget(opt_dentry);
+			} else {
+				/* Called from selinux_complete_init, try to
+				 * find a dentry.  Some filesystems really want
+				 * a connected one, so try that first.
+				 */
+				dentry = d_find_alias(inode);
+				if (!dentry)
+					dentry = d_find_any_alias(inode);
+			}
+			/*
+			 * This can be hit on boot when a file is accessed
+			 * before the policy is loaded.  When we load policy we
+			 * may find inodes that have no dentry on the
+			 * sbsec->isec_head list.  No reason to complain as
+			 * these will get fixed up the next time we go through
+			 * inode_doinit() with a dentry, before these inodes
+			 * could be used again by userspace.
+			 */
+			if (!dentry)
+				goto out_invalid;
+			rc = selinux_genfs_get_sid(dentry, sclass,
+						   sbsec->flags, &sid);
+			if (rc) {
+				dput(dentry);
+				goto out;
+			}
+
+			if ((sbsec->flags & SE_SBGENFS_XATTR) &&
+			    (inode->i_opflags & IOP_XATTR)) {
+				rc = inode_doinit_use_xattr(inode, dentry,
+							    sid, &sid);
+				if (rc) {
+					dput(dentry);
+					goto out;
+				}
+			}
+			dput(dentry);
+		}
+		break;
+	}
+
+out:
+	spin_lock(&isec->lock);
+	if (isec->initialized == LABEL_PENDING) {
+		if (rc) {
+			isec->initialized = LABEL_INVALID;
+			goto out_unlock;
+		}
+		isec->initialized = LABEL_INITIALIZED;
+		isec->sid = sid;
+	}
+
+out_unlock:
+	spin_unlock(&isec->lock);
+	return rc;
+
+out_invalid:
+	spin_lock(&isec->lock);
+	if (isec->initialized == LABEL_PENDING) {
+		isec->initialized = LABEL_INVALID;
+		isec->sid = sid;
+	}
+	spin_unlock(&isec->lock);
+	return 0;
+}
+
+/* Convert a Linux signal to an access vector. */
+static inline u32 signal_to_av(int sig)
+{
+	u32 perm = 0;
+
+	switch (sig) {
+	case SIGCHLD:
+		/* Commonly granted from child to parent. */
+		perm = PROCESS__SIGCHLD;
+		break;
+	case SIGKILL:
+		/* Cannot be caught or ignored */
+		perm = PROCESS__SIGKILL;
+		break;
+	case SIGSTOP:
+		/* Cannot be caught or ignored */
+		perm = PROCESS__SIGSTOP;
+		break;
+	default:
+		/* All other signals. */
+		perm = PROCESS__SIGNAL;
+		break;
+	}
+
+	return perm;
+}
+
+#if CAP_LAST_CAP > 63
+#error Fix SELinux to handle capabilities > 63.
+#endif
+
+/* Check whether a task is allowed to use a capability. */
+static int cred_has_capability(const struct cred *cred,
+			       int cap, unsigned int opts, bool initns)
+{
+	struct common_audit_data ad;
+	struct av_decision avd;
+	u16 sclass;
+	u32 sid = cred_sid(cred);
+	u32 av = CAP_TO_MASK(cap);
+	int rc;
+
+	ad.type = LSM_AUDIT_DATA_CAP;
+	ad.u.cap = cap;
+
+	switch (CAP_TO_INDEX(cap)) {
+	case 0:
+		sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS;
+		break;
+	case 1:
+		sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS;
+		break;
+	default:
+		pr_err("SELinux:  out of range capability %d\n", cap);
+		return -EINVAL;
+	}
+
+	rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd);
+	if (!(opts & CAP_OPT_NOAUDIT)) {
+		int rc2 = avc_audit(sid, sid, sclass, av, &avd, rc, &ad);
+		if (rc2)
+			return rc2;
+	}
+	return rc;
+}
+
+/* Check whether a task has a particular permission to an inode.
+   The 'adp' parameter is optional and allows other audit
+   data to be passed (e.g. the dentry). */
+static int inode_has_perm(const struct cred *cred,
+			  struct inode *inode,
+			  u32 perms,
+			  struct common_audit_data *adp)
+{
+	struct inode_security_struct *isec;
+	u32 sid;
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	sid = cred_sid(cred);
+	isec = selinux_inode(inode);
+
+	return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp);
+}
+
+/* Same as inode_has_perm, but pass explicit audit data containing
+   the dentry to help the auditing code to more easily generate the
+   pathname if needed. */
+static inline int dentry_has_perm(const struct cred *cred,
+				  struct dentry *dentry,
+				  u32 av)
+{
+	struct common_audit_data ad;
+	struct inode *inode = d_backing_inode(dentry);
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+	/* check below is racy, but revalidate will recheck with lock held */
+	if (data_race(unlikely(isec->initialized != LABEL_INITIALIZED)))
+		__inode_security_revalidate(inode, dentry, true);
+	return inode_has_perm(cred, inode, av, &ad);
+}
+
+/* Same as inode_has_perm, but pass explicit audit data containing
+   the path to help the auditing code to more easily generate the
+   pathname if needed. */
+static inline int path_has_perm(const struct cred *cred,
+				const struct path *path,
+				u32 av)
+{
+	struct common_audit_data ad;
+	struct inode *inode = d_backing_inode(path->dentry);
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	ad.type = LSM_AUDIT_DATA_PATH;
+	ad.u.path = *path;
+	/* check below is racy, but revalidate will recheck with lock held */
+	if (data_race(unlikely(isec->initialized != LABEL_INITIALIZED)))
+		__inode_security_revalidate(inode, path->dentry, true);
+	return inode_has_perm(cred, inode, av, &ad);
+}
+
+/* Same as path_has_perm, but uses the inode from the file struct. */
+static inline int file_path_has_perm(const struct cred *cred,
+				     struct file *file,
+				     u32 av)
+{
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_FILE;
+	ad.u.file = file;
+	return inode_has_perm(cred, file_inode(file), av, &ad);
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static int bpf_fd_pass(const struct file *file, u32 sid);
+#endif
+
+static int __file_has_perm(const struct cred *cred, const struct file *file,
+			   u32 av, bool bf_user_file)
+
+{
+	struct common_audit_data ad;
+	struct inode *inode;
+	u32 ssid = cred_sid(cred);
+	u32 tsid_fd;
+	int rc;
+
+	if (bf_user_file) {
+		struct backing_file_security_struct *bfsec;
+		const struct path *path;
+
+		if (WARN_ON(!(file->f_mode & FMODE_BACKING)))
+			return -EIO;
+
+		bfsec = selinux_backing_file(file);
+		path = backing_file_user_path(file);
+		tsid_fd = bfsec->uf_sid;
+		inode = d_inode(path->dentry);
+
+		ad.type = LSM_AUDIT_DATA_PATH;
+		ad.u.path = *path;
+	} else {
+		struct file_security_struct *fsec = selinux_file(file);
+
+		tsid_fd = fsec->sid;
+		inode = file_inode(file);
+
+		ad.type = LSM_AUDIT_DATA_FILE;
+		ad.u.file = file;
+	}
+
+	if (ssid != tsid_fd) {
+		rc = avc_has_perm(ssid, tsid_fd, SECCLASS_FD, FD__USE, &ad);
+		if (rc)
+			return rc;
+	}
+
+#ifdef CONFIG_BPF_SYSCALL
+	/* regardless of backing vs user file, use the underlying file here */
+	rc = bpf_fd_pass(file, ssid);
+	if (rc)
+		return rc;
+#endif
+
+	/* av is zero if only checking access to the descriptor. */
+	if (av)
+		return inode_has_perm(cred, inode, av, &ad);
+
+	return 0;
+}
+
+/* Check whether a task can use an open file descriptor to
+   access an inode in a given way.  Check access to the
+   descriptor itself, and then use dentry_has_perm to
+   check a particular permission to the file.
+   Access to the descriptor is implicitly granted if it
+   has the same SID as the process.  If av is zero, then
+   access to the file is not checked, e.g. for cases
+   where only the descriptor is affected like seek. */
+static inline int file_has_perm(const struct cred *cred,
+				const struct file *file, u32 av)
+{
+	return __file_has_perm(cred, file, av, false);
+}
+
+/*
+ * Determine the label for an inode that might be unioned.
+ */
+static int
+selinux_determine_inode_label(const struct cred_security_struct *crsec,
+				 struct inode *dir,
+				 const struct qstr *name, u16 tclass,
+				 u32 *_new_isid)
+{
+	const struct superblock_security_struct *sbsec =
+						selinux_superblock(dir->i_sb);
+
+	if ((sbsec->flags & SE_SBINITIALIZED) &&
+	    (sbsec->behavior == SECURITY_FS_USE_MNTPOINT)) {
+		*_new_isid = sbsec->mntpoint_sid;
+	} else if ((sbsec->flags & SBLABEL_MNT) &&
+		   crsec->create_sid) {
+		*_new_isid = crsec->create_sid;
+	} else {
+		const struct inode_security_struct *dsec = inode_security(dir);
+		return security_transition_sid(crsec->sid,
+					       dsec->sid, tclass,
+					       name, _new_isid);
+	}
+
+	return 0;
+}
+
+/* Check whether a task can create a file. */
+static int may_create(struct inode *dir,
+		      struct dentry *dentry,
+		      u16 tclass)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	struct inode_security_struct *dsec;
+	struct superblock_security_struct *sbsec;
+	u32 sid, newsid;
+	struct common_audit_data ad;
+	int rc;
+
+	dsec = inode_security(dir);
+	sbsec = selinux_superblock(dir->i_sb);
+
+	sid = crsec->sid;
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+
+	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR,
+			  DIR__ADD_NAME | DIR__SEARCH,
+			  &ad);
+	if (rc)
+		return rc;
+
+	rc = selinux_determine_inode_label(crsec, dir, &dentry->d_name, tclass,
+					   &newsid);
+	if (rc)
+		return rc;
+
+	rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad);
+	if (rc)
+		return rc;
+
+	return avc_has_perm(newsid, sbsec->sid,
+			    SECCLASS_FILESYSTEM,
+			    FILESYSTEM__ASSOCIATE, &ad);
+}
+
+#define MAY_LINK	0
+#define MAY_UNLINK	1
+#define MAY_RMDIR	2
+
+/* Check whether a task can link, unlink, or rmdir a file/directory. */
+static int may_link(struct inode *dir,
+		    struct dentry *dentry,
+		    int kind)
+
+{
+	struct inode_security_struct *dsec, *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+	u32 av;
+	int rc;
+
+	dsec = inode_security(dir);
+	isec = backing_inode_security(dentry);
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+
+	av = DIR__SEARCH;
+	av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME);
+	rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad);
+	if (rc)
+		return rc;
+
+	switch (kind) {
+	case MAY_LINK:
+		av = FILE__LINK;
+		break;
+	case MAY_UNLINK:
+		av = FILE__UNLINK;
+		break;
+	case MAY_RMDIR:
+		av = DIR__RMDIR;
+		break;
+	default:
+		pr_warn("SELinux: %s:  unrecognized kind %d\n",
+			__func__, kind);
+		return 0;
+	}
+
+	rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad);
+	return rc;
+}
+
+static inline int may_rename(struct inode *old_dir,
+			     struct dentry *old_dentry,
+			     struct inode *new_dir,
+			     struct dentry *new_dentry)
+{
+	struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+	u32 av;
+	int old_is_dir, new_is_dir;
+	int rc;
+
+	old_dsec = inode_security(old_dir);
+	old_isec = backing_inode_security(old_dentry);
+	old_is_dir = d_is_dir(old_dentry);
+	new_dsec = inode_security(new_dir);
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+
+	ad.u.dentry = old_dentry;
+	rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR,
+			  DIR__REMOVE_NAME | DIR__SEARCH, &ad);
+	if (rc)
+		return rc;
+	rc = avc_has_perm(sid, old_isec->sid,
+			  old_isec->sclass, FILE__RENAME, &ad);
+	if (rc)
+		return rc;
+	if (old_is_dir && new_dir != old_dir) {
+		rc = avc_has_perm(sid, old_isec->sid,
+				  old_isec->sclass, DIR__REPARENT, &ad);
+		if (rc)
+			return rc;
+	}
+
+	ad.u.dentry = new_dentry;
+	av = DIR__ADD_NAME | DIR__SEARCH;
+	if (d_is_positive(new_dentry))
+		av |= DIR__REMOVE_NAME;
+	rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad);
+	if (rc)
+		return rc;
+	if (d_is_positive(new_dentry)) {
+		new_isec = backing_inode_security(new_dentry);
+		new_is_dir = d_is_dir(new_dentry);
+		rc = avc_has_perm(sid, new_isec->sid,
+				  new_isec->sclass,
+				  (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+/* Check whether a task can perform a filesystem operation. */
+static int superblock_has_perm(const struct cred *cred,
+			       const struct super_block *sb,
+			       u32 perms,
+			       struct common_audit_data *ad)
+{
+	struct superblock_security_struct *sbsec;
+	u32 sid = cred_sid(cred);
+
+	sbsec = selinux_superblock(sb);
+	return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad);
+}
+
+/* Convert a Linux mode and permission mask to an access vector. */
+static inline u32 file_mask_to_av(int mode, int mask)
+{
+	u32 av = 0;
+
+	if (!S_ISDIR(mode)) {
+		if (mask & MAY_EXEC)
+			av |= FILE__EXECUTE;
+		if (mask & MAY_READ)
+			av |= FILE__READ;
+
+		if (mask & MAY_APPEND)
+			av |= FILE__APPEND;
+		else if (mask & MAY_WRITE)
+			av |= FILE__WRITE;
+
+	} else {
+		if (mask & MAY_EXEC)
+			av |= DIR__SEARCH;
+		if (mask & MAY_WRITE)
+			av |= DIR__WRITE;
+		if (mask & MAY_READ)
+			av |= DIR__READ;
+	}
+
+	return av;
+}
+
+/* Convert a Linux file to an access vector. */
+static inline u32 file_to_av(const struct file *file)
+{
+	u32 av = 0;
+
+	if (file->f_mode & FMODE_READ)
+		av |= FILE__READ;
+	if (file->f_mode & FMODE_WRITE) {
+		if (file->f_flags & O_APPEND)
+			av |= FILE__APPEND;
+		else
+			av |= FILE__WRITE;
+	}
+	if (!av) {
+		/*
+		 * Special file opened with flags 3 for ioctl-only use.
+		 */
+		av = FILE__IOCTL;
+	}
+
+	return av;
+}
+
+/*
+ * Convert a file to an access vector and include the correct
+ * open permission.
+ */
+static inline u32 open_file_to_av(struct file *file)
+{
+	u32 av = file_to_av(file);
+	struct inode *inode = file_inode(file);
+
+	if (selinux_policycap_openperm() &&
+	    inode->i_sb->s_magic != SOCKFS_MAGIC)
+		av |= FILE__OPEN;
+
+	return av;
+}
+
+/* Hook functions begin here. */
+
+static int selinux_binder_set_context_mgr(const struct cred *mgr)
+{
+	return avc_has_perm(current_sid(), cred_sid(mgr), SECCLASS_BINDER,
+			    BINDER__SET_CONTEXT_MGR, NULL);
+}
+
+static int selinux_binder_transaction(const struct cred *from,
+				      const struct cred *to)
+{
+	u32 mysid = current_sid();
+	u32 fromsid = cred_sid(from);
+	u32 tosid = cred_sid(to);
+	int rc;
+
+	if (mysid != fromsid) {
+		rc = avc_has_perm(mysid, fromsid, SECCLASS_BINDER,
+				  BINDER__IMPERSONATE, NULL);
+		if (rc)
+			return rc;
+	}
+
+	return avc_has_perm(fromsid, tosid,
+			    SECCLASS_BINDER, BINDER__CALL, NULL);
+}
+
+static int selinux_binder_transfer_binder(const struct cred *from,
+					  const struct cred *to)
+{
+	return avc_has_perm(cred_sid(from), cred_sid(to),
+			    SECCLASS_BINDER, BINDER__TRANSFER,
+			    NULL);
+}
+
+static int selinux_binder_transfer_file(const struct cred *from,
+					const struct cred *to,
+					const struct file *file)
+{
+	u32 sid = cred_sid(to);
+	struct file_security_struct *fsec = selinux_file(file);
+	struct dentry *dentry = file->f_path.dentry;
+	struct inode_security_struct *isec;
+	struct common_audit_data ad;
+	int rc;
+
+	ad.type = LSM_AUDIT_DATA_PATH;
+	ad.u.path = file->f_path;
+
+	if (sid != fsec->sid) {
+		rc = avc_has_perm(sid, fsec->sid,
+				  SECCLASS_FD,
+				  FD__USE,
+				  &ad);
+		if (rc)
+			return rc;
+	}
+
+#ifdef CONFIG_BPF_SYSCALL
+	rc = bpf_fd_pass(file, sid);
+	if (rc)
+		return rc;
+#endif
+
+	if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+		return 0;
+
+	isec = backing_inode_security(dentry);
+	return avc_has_perm(sid, isec->sid, isec->sclass, file_to_av(file),
+			    &ad);
+}
+
+static int selinux_ptrace_access_check(struct task_struct *child,
+				       unsigned int mode)
+{
+	u32 sid = current_sid();
+	u32 csid = task_sid_obj(child);
+
+	if (mode & PTRACE_MODE_READ)
+		return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ,
+				NULL);
+
+	return avc_has_perm(sid, csid, SECCLASS_PROCESS, PROCESS__PTRACE,
+			NULL);
+}
+
+static int selinux_ptrace_traceme(struct task_struct *parent)
+{
+	return avc_has_perm(task_sid_obj(parent), task_sid_obj(current),
+			    SECCLASS_PROCESS, PROCESS__PTRACE, NULL);
+}
+
+static int selinux_capget(const struct task_struct *target, kernel_cap_t *effective,
+			  kernel_cap_t *inheritable, kernel_cap_t *permitted)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(target),
+			SECCLASS_PROCESS, PROCESS__GETCAP, NULL);
+}
+
+static int selinux_capset(struct cred *new, const struct cred *old,
+			  const kernel_cap_t *effective,
+			  const kernel_cap_t *inheritable,
+			  const kernel_cap_t *permitted)
+{
+	return avc_has_perm(cred_sid(old), cred_sid(new), SECCLASS_PROCESS,
+			    PROCESS__SETCAP, NULL);
+}
+
+/*
+ * (This comment used to live with the selinux_task_setuid hook,
+ * which was removed).
+ *
+ * Since setuid only affects the current process, and since the SELinux
+ * controls are not based on the Linux identity attributes, SELinux does not
+ * need to control this operation.  However, SELinux does control the use of
+ * the CAP_SETUID and CAP_SETGID capabilities using the capable hook.
+ */
+
+static int selinux_capable(const struct cred *cred, struct user_namespace *ns,
+			   int cap, unsigned int opts)
+{
+	return cred_has_capability(cred, cap, opts, ns == &init_user_ns);
+}
+
+static int selinux_quotactl(int cmds, int type, int id, const struct super_block *sb)
+{
+	const struct cred *cred = current_cred();
+	int rc = 0;
+
+	if (!sb)
+		return 0;
+
+	switch (cmds) {
+	case Q_SYNC:
+	case Q_QUOTAON:
+	case Q_QUOTAOFF:
+	case Q_SETINFO:
+	case Q_SETQUOTA:
+	case Q_XQUOTAOFF:
+	case Q_XQUOTAON:
+	case Q_XSETQLIM:
+		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL);
+		break;
+	case Q_GETFMT:
+	case Q_GETINFO:
+	case Q_GETQUOTA:
+	case Q_XGETQUOTA:
+	case Q_XGETQSTAT:
+	case Q_XGETQSTATV:
+	case Q_XGETNEXTQUOTA:
+		rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL);
+		break;
+	default:
+		rc = 0;  /* let the kernel handle invalid cmds */
+		break;
+	}
+	return rc;
+}
+
+static int selinux_quota_on(struct dentry *dentry)
+{
+	const struct cred *cred = current_cred();
+
+	return dentry_has_perm(cred, dentry, FILE__QUOTAON);
+}
+
+static int selinux_syslog(int type)
+{
+	switch (type) {
+	case SYSLOG_ACTION_READ_ALL:	/* Read last kernel messages */
+	case SYSLOG_ACTION_SIZE_BUFFER:	/* Return size of the log buffer */
+		return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+				    SECCLASS_SYSTEM, SYSTEM__SYSLOG_READ, NULL);
+	case SYSLOG_ACTION_CONSOLE_OFF:	/* Disable logging to console */
+	case SYSLOG_ACTION_CONSOLE_ON:	/* Enable logging to console */
+	/* Set level of messages printed to console */
+	case SYSLOG_ACTION_CONSOLE_LEVEL:
+		return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+				    SECCLASS_SYSTEM, SYSTEM__SYSLOG_CONSOLE,
+				    NULL);
+	}
+	/* All other syslog types */
+	return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+			    SECCLASS_SYSTEM, SYSTEM__SYSLOG_MOD, NULL);
+}
+
+/*
+ * Check permission for allocating a new virtual mapping. Returns
+ * 0 if permission is granted, negative error code if not.
+ *
+ * Do not audit the selinux permission check, as this is applied to all
+ * processes that allocate mappings.
+ */
+static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
+{
+	return cred_has_capability(current_cred(), CAP_SYS_ADMIN,
+				   CAP_OPT_NOAUDIT, true);
+}
+
+/* binprm security operations */
+
+static u32 ptrace_parent_sid(void)
+{
+	u32 sid = 0;
+	struct task_struct *tracer;
+
+	rcu_read_lock();
+	tracer = ptrace_parent(current);
+	if (tracer)
+		sid = task_sid_obj(tracer);
+	rcu_read_unlock();
+
+	return sid;
+}
+
+static int check_nnp_nosuid(const struct linux_binprm *bprm,
+			    const struct cred_security_struct *old_crsec,
+			    const struct cred_security_struct *new_crsec)
+{
+	int nnp = (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS);
+	int nosuid = !mnt_may_suid(bprm->file->f_path.mnt);
+	int rc;
+	u32 av;
+
+	if (!nnp && !nosuid)
+		return 0; /* neither NNP nor nosuid */
+
+	if (new_crsec->sid == old_crsec->sid)
+		return 0; /* No change in credentials */
+
+	/*
+	 * If the policy enables the nnp_nosuid_transition policy capability,
+	 * then we permit transitions under NNP or nosuid if the
+	 * policy allows the corresponding permission between
+	 * the old and new contexts.
+	 */
+	if (selinux_policycap_nnp_nosuid_transition()) {
+		av = 0;
+		if (nnp)
+			av |= PROCESS2__NNP_TRANSITION;
+		if (nosuid)
+			av |= PROCESS2__NOSUID_TRANSITION;
+		rc = avc_has_perm(old_crsec->sid, new_crsec->sid,
+				  SECCLASS_PROCESS2, av, NULL);
+		if (!rc)
+			return 0;
+	}
+
+	/*
+	 * We also permit NNP or nosuid transitions to bounded SIDs,
+	 * i.e. SIDs that are guaranteed to only be allowed a subset
+	 * of the permissions of the current SID.
+	 */
+	rc = security_bounded_transition(old_crsec->sid,
+					 new_crsec->sid);
+	if (!rc)
+		return 0;
+
+	/*
+	 * On failure, preserve the errno values for NNP vs nosuid.
+	 * NNP:  Operation not permitted for caller.
+	 * nosuid:  Permission denied to file.
+	 */
+	if (nnp)
+		return -EPERM;
+	return -EACCES;
+}
+
+static int selinux_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	const struct cred_security_struct *old_crsec;
+	struct cred_security_struct *new_crsec;
+	struct inode_security_struct *isec;
+	struct common_audit_data ad;
+	struct inode *inode = file_inode(bprm->file);
+	int rc;
+
+	/* SELinux context only depends on initial program or script and not
+	 * the script interpreter */
+
+	old_crsec = selinux_cred(current_cred());
+	new_crsec = selinux_cred(bprm->cred);
+	isec = inode_security(inode);
+
+	if (WARN_ON(isec->sclass != SECCLASS_FILE &&
+		    isec->sclass != SECCLASS_MEMFD_FILE))
+		return -EACCES;
+
+	/* Default to the current task SID. */
+	new_crsec->sid = old_crsec->sid;
+	new_crsec->osid = old_crsec->sid;
+
+	/* Reset fs, key, and sock SIDs on execve. */
+	new_crsec->create_sid = 0;
+	new_crsec->keycreate_sid = 0;
+	new_crsec->sockcreate_sid = 0;
+
+	/*
+	 * Before policy is loaded, label any task outside kernel space
+	 * as SECINITSID_INIT, so that any userspace tasks surviving from
+	 * early boot end up with a label different from SECINITSID_KERNEL
+	 * (if the policy chooses to set SECINITSID_INIT != SECINITSID_KERNEL).
+	 */
+	if (!selinux_initialized()) {
+		new_crsec->sid = SECINITSID_INIT;
+		/* also clear the exec_sid just in case */
+		new_crsec->exec_sid = 0;
+		return 0;
+	}
+
+	if (old_crsec->exec_sid) {
+		new_crsec->sid = old_crsec->exec_sid;
+		/* Reset exec SID on execve. */
+		new_crsec->exec_sid = 0;
+
+		/* Fail on NNP or nosuid if not an allowed transition. */
+		rc = check_nnp_nosuid(bprm, old_crsec, new_crsec);
+		if (rc)
+			return rc;
+	} else {
+		/* Check for a default transition on this program. */
+		rc = security_transition_sid(old_crsec->sid,
+					     isec->sid, SECCLASS_PROCESS, NULL,
+					     &new_crsec->sid);
+		if (rc)
+			return rc;
+
+		/*
+		 * Fallback to old SID on NNP or nosuid if not an allowed
+		 * transition.
+		 */
+		rc = check_nnp_nosuid(bprm, old_crsec, new_crsec);
+		if (rc)
+			new_crsec->sid = old_crsec->sid;
+	}
+
+	ad.type = LSM_AUDIT_DATA_FILE;
+	ad.u.file = bprm->file;
+
+	if (new_crsec->sid == old_crsec->sid) {
+		rc = avc_has_perm(old_crsec->sid, isec->sid, isec->sclass,
+				  FILE__EXECUTE_NO_TRANS, &ad);
+		if (rc)
+			return rc;
+	} else {
+		/* Check permissions for the transition. */
+		rc = avc_has_perm(old_crsec->sid, new_crsec->sid,
+				  SECCLASS_PROCESS, PROCESS__TRANSITION, &ad);
+		if (rc)
+			return rc;
+
+		rc = avc_has_perm(new_crsec->sid, isec->sid, isec->sclass,
+				  FILE__ENTRYPOINT, &ad);
+		if (rc)
+			return rc;
+
+		/* Check for shared state */
+		if (bprm->unsafe & LSM_UNSAFE_SHARE) {
+			rc = avc_has_perm(old_crsec->sid, new_crsec->sid,
+					  SECCLASS_PROCESS, PROCESS__SHARE,
+					  NULL);
+			if (rc)
+				return -EPERM;
+		}
+
+		/* Make sure that anyone attempting to ptrace over a task that
+		 * changes its SID has the appropriate permit */
+		if (bprm->unsafe & LSM_UNSAFE_PTRACE) {
+			u32 ptsid = ptrace_parent_sid();
+			if (ptsid != 0) {
+				rc = avc_has_perm(ptsid, new_crsec->sid,
+						  SECCLASS_PROCESS,
+						  PROCESS__PTRACE, NULL);
+				if (rc)
+					return -EPERM;
+			}
+		}
+
+		/* Clear any possibly unsafe personality bits on exec: */
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+		/* Enable secure mode for SIDs transitions unless
+		   the noatsecure permission is granted between
+		   the two SIDs, i.e. ahp returns 0. */
+		rc = avc_has_perm(old_crsec->sid, new_crsec->sid,
+				  SECCLASS_PROCESS, PROCESS__NOATSECURE,
+				  NULL);
+		bprm->secureexec |= !!rc;
+	}
+
+	return 0;
+}
+
+static int match_file(const void *p, struct file *file, unsigned fd)
+{
+	return file_has_perm(p, file, file_to_av(file)) ? fd + 1 : 0;
+}
+
+/* Derived from fs/exec.c:flush_old_files. */
+static inline void flush_unauthorized_files(const struct cred *cred,
+					    struct files_struct *files)
+{
+	struct file *file, *devnull = NULL;
+	struct tty_struct *tty;
+	int drop_tty = 0;
+	unsigned n;
+
+	tty = get_current_tty();
+	if (tty) {
+		spin_lock(&tty->files_lock);
+		if (!list_empty(&tty->tty_files)) {
+			struct tty_file_private *file_priv;
+
+			/* Revalidate access to controlling tty.
+			   Use file_path_has_perm on the tty path directly
+			   rather than using file_has_perm, as this particular
+			   open file may belong to another process and we are
+			   only interested in the inode-based check here. */
+			file_priv = list_first_entry(&tty->tty_files,
+						struct tty_file_private, list);
+			file = file_priv->file;
+			if (file_path_has_perm(cred, file, FILE__READ | FILE__WRITE))
+				drop_tty = 1;
+		}
+		spin_unlock(&tty->files_lock);
+		tty_kref_put(tty);
+	}
+	/* Reset controlling tty. */
+	if (drop_tty)
+		no_tty();
+
+	/* Revalidate access to inherited open files. */
+	n = iterate_fd(files, 0, match_file, cred);
+	if (!n) /* none found? */
+		return;
+
+	devnull = dentry_open(&selinux_null, O_RDWR, cred);
+	if (IS_ERR(devnull))
+		devnull = NULL;
+	/* replace all the matching ones with this */
+	do {
+		replace_fd(n - 1, devnull, 0);
+	} while ((n = iterate_fd(files, n, match_file, cred)) != 0);
+	if (devnull)
+		fput(devnull);
+}
+
+/*
+ * Prepare a process for imminent new credential changes due to exec
+ */
+static void selinux_bprm_committing_creds(const struct linux_binprm *bprm)
+{
+	struct cred_security_struct *new_crsec;
+	struct rlimit *rlim, *initrlim;
+	int rc, i;
+
+	new_crsec = selinux_cred(bprm->cred);
+	if (new_crsec->sid == new_crsec->osid)
+		return;
+
+	/* Close files for which the new task SID is not authorized. */
+	flush_unauthorized_files(bprm->cred, current->files);
+
+	/* Always clear parent death signal on SID transitions. */
+	current->pdeath_signal = 0;
+
+	/* Check whether the new SID can inherit resource limits from the old
+	 * SID.  If not, reset all soft limits to the lower of the current
+	 * task's hard limit and the init task's soft limit.
+	 *
+	 * Note that the setting of hard limits (even to lower them) can be
+	 * controlled by the setrlimit check.  The inclusion of the init task's
+	 * soft limit into the computation is to avoid resetting soft limits
+	 * higher than the default soft limit for cases where the default is
+	 * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK.
+	 */
+	rc = avc_has_perm(new_crsec->osid, new_crsec->sid, SECCLASS_PROCESS,
+			  PROCESS__RLIMITINH, NULL);
+	if (rc) {
+		/* protect against do_prlimit() */
+		task_lock(current);
+		for (i = 0; i < RLIM_NLIMITS; i++) {
+			rlim = current->signal->rlim + i;
+			initrlim = init_task.signal->rlim + i;
+			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
+		}
+		task_unlock(current);
+		if (IS_ENABLED(CONFIG_POSIX_TIMERS))
+			update_rlimit_cpu(current, rlimit(RLIMIT_CPU));
+	}
+}
+
+/*
+ * Clean up the process immediately after the installation of new credentials
+ * due to exec
+ */
+static void selinux_bprm_committed_creds(const struct linux_binprm *bprm)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	u32 osid, sid;
+	int rc;
+
+	osid = crsec->osid;
+	sid = crsec->sid;
+
+	if (sid == osid)
+		return;
+
+	/* Check whether the new SID can inherit signal state from the old SID.
+	 * If not, clear itimers to avoid subsequent signal generation and
+	 * flush and unblock signals.
+	 *
+	 * This must occur _after_ the task SID has been updated so that any
+	 * kill done after the flush will be checked against the new SID.
+	 */
+	rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL);
+	if (rc) {
+		clear_itimer();
+
+		spin_lock_irq(&unrcu_pointer(current->sighand)->siglock);
+		if (!fatal_signal_pending(current)) {
+			flush_sigqueue(&current->pending);
+			flush_sigqueue(&current->signal->shared_pending);
+			flush_signal_handlers(current, 1);
+			sigemptyset(&current->blocked);
+			recalc_sigpending();
+		}
+		spin_unlock_irq(&unrcu_pointer(current->sighand)->siglock);
+	}
+
+	/* Wake up the parent if it is waiting so that it can recheck
+	 * wait permission to the new task SID. */
+	read_lock(&tasklist_lock);
+	__wake_up_parent(current, unrcu_pointer(current->real_parent));
+	read_unlock(&tasklist_lock);
+}
+
+/* superblock security operations */
+
+static int selinux_sb_alloc_security(struct super_block *sb)
+{
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+
+	mutex_init(&sbsec->lock);
+	INIT_LIST_HEAD(&sbsec->isec_head);
+	spin_lock_init(&sbsec->isec_lock);
+	sbsec->sid = SECINITSID_UNLABELED;
+	sbsec->def_sid = SECINITSID_FILE;
+	sbsec->mntpoint_sid = SECINITSID_UNLABELED;
+	sbsec->creator_sid = SECINITSID_UNLABELED;
+
+	return 0;
+}
+
+static inline int opt_len(const char *s)
+{
+	bool open_quote = false;
+	int len;
+	char c;
+
+	for (len = 0; (c = s[len]) != '\0'; len++) {
+		if (c == '"')
+			open_quote = !open_quote;
+		if (c == ',' && !open_quote)
+			break;
+	}
+	return len;
+}
+
+static int selinux_sb_eat_lsm_opts(char *options, void **mnt_opts)
+{
+	char *from = options;
+	char *to = options;
+	bool first = true;
+	int rc;
+
+	while (1) {
+		int len = opt_len(from);
+		int token;
+		char *arg = NULL;
+
+		token = match_opt_prefix(from, len, &arg);
+
+		if (token != Opt_error) {
+			char *p, *q;
+
+			/* strip quotes */
+			if (arg) {
+				for (p = q = arg; p < from + len; p++) {
+					char c = *p;
+					if (c != '"')
+						*q++ = c;
+				}
+				arg = kmemdup_nul(arg, q - arg, GFP_KERNEL);
+				if (!arg) {
+					rc = -ENOMEM;
+					goto free_opt;
+				}
+			}
+			rc = selinux_add_opt(token, arg, mnt_opts);
+			kfree(arg);
+			arg = NULL;
+			if (unlikely(rc)) {
+				goto free_opt;
+			}
+		} else {
+			if (!first) {	// copy with preceding comma
+				from--;
+				len++;
+			}
+			if (to != from)
+				memmove(to, from, len);
+			to += len;
+			first = false;
+		}
+		if (!from[len])
+			break;
+		from += len + 1;
+	}
+	*to = '\0';
+	return 0;
+
+free_opt:
+	if (*mnt_opts) {
+		selinux_free_mnt_opts(*mnt_opts);
+		*mnt_opts = NULL;
+	}
+	return rc;
+}
+
+static int selinux_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts)
+{
+	struct selinux_mnt_opts *opts = mnt_opts;
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+
+	/*
+	 * Superblock not initialized (i.e. no options) - reject if any
+	 * options specified, otherwise accept.
+	 */
+	if (!(sbsec->flags & SE_SBINITIALIZED))
+		return opts ? 1 : 0;
+
+	/*
+	 * Superblock initialized and no options specified - reject if
+	 * superblock has any options set, otherwise accept.
+	 */
+	if (!opts)
+		return (sbsec->flags & SE_MNTMASK) ? 1 : 0;
+
+	if (opts->fscontext_sid) {
+		if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
+			       opts->fscontext_sid))
+			return 1;
+	}
+	if (opts->context_sid) {
+		if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
+			       opts->context_sid))
+			return 1;
+	}
+	if (opts->rootcontext_sid) {
+		struct inode_security_struct *root_isec;
+
+		root_isec = backing_inode_security(sb->s_root);
+		if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
+			       opts->rootcontext_sid))
+			return 1;
+	}
+	if (opts->defcontext_sid) {
+		if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
+			       opts->defcontext_sid))
+			return 1;
+	}
+	return 0;
+}
+
+static int selinux_sb_remount(struct super_block *sb, void *mnt_opts)
+{
+	struct selinux_mnt_opts *opts = mnt_opts;
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+
+	if (!(sbsec->flags & SE_SBINITIALIZED))
+		return 0;
+
+	if (!opts)
+		return 0;
+
+	if (opts->fscontext_sid) {
+		if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
+			       opts->fscontext_sid))
+			goto out_bad_option;
+	}
+	if (opts->context_sid) {
+		if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
+			       opts->context_sid))
+			goto out_bad_option;
+	}
+	if (opts->rootcontext_sid) {
+		struct inode_security_struct *root_isec;
+		root_isec = backing_inode_security(sb->s_root);
+		if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
+			       opts->rootcontext_sid))
+			goto out_bad_option;
+	}
+	if (opts->defcontext_sid) {
+		if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
+			       opts->defcontext_sid))
+			goto out_bad_option;
+	}
+	return 0;
+
+out_bad_option:
+	pr_warn("SELinux: unable to change security options "
+	       "during remount (dev %s, type=%s)\n", sb->s_id,
+	       sb->s_type->name);
+	return -EINVAL;
+}
+
+static int selinux_sb_kern_mount(const struct super_block *sb)
+{
+	const struct cred *cred = current_cred();
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = sb->s_root;
+	return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad);
+}
+
+static int selinux_sb_statfs(struct dentry *dentry)
+{
+	const struct cred *cred = current_cred();
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry->d_sb->s_root;
+	return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad);
+}
+
+static int selinux_mount(const char *dev_name,
+			 const struct path *path,
+			 const char *type,
+			 unsigned long flags,
+			 void *data)
+{
+	const struct cred *cred = current_cred();
+
+	if (flags & MS_REMOUNT)
+		return superblock_has_perm(cred, path->dentry->d_sb,
+					   FILESYSTEM__REMOUNT, NULL);
+	else
+		return path_has_perm(cred, path, FILE__MOUNTON);
+}
+
+static int selinux_move_mount(const struct path *from_path,
+			      const struct path *to_path)
+{
+	const struct cred *cred = current_cred();
+
+	return path_has_perm(cred, to_path, FILE__MOUNTON);
+}
+
+static int selinux_umount(struct vfsmount *mnt, int flags)
+{
+	const struct cred *cred = current_cred();
+
+	return superblock_has_perm(cred, mnt->mnt_sb,
+				   FILESYSTEM__UNMOUNT, NULL);
+}
+
+static int selinux_fs_context_submount(struct fs_context *fc,
+				   struct super_block *reference)
+{
+	const struct superblock_security_struct *sbsec = selinux_superblock(reference);
+	struct selinux_mnt_opts *opts;
+
+	/*
+	 * Ensure that fc->security remains NULL when no options are set
+	 * as expected by selinux_set_mnt_opts().
+	 */
+	if (!(sbsec->flags & (FSCONTEXT_MNT|CONTEXT_MNT|DEFCONTEXT_MNT)))
+		return 0;
+
+	opts = kzalloc_obj(*opts);
+	if (!opts)
+		return -ENOMEM;
+
+	if (sbsec->flags & FSCONTEXT_MNT)
+		opts->fscontext_sid = sbsec->sid;
+	if (sbsec->flags & CONTEXT_MNT)
+		opts->context_sid = sbsec->mntpoint_sid;
+	if (sbsec->flags & DEFCONTEXT_MNT)
+		opts->defcontext_sid = sbsec->def_sid;
+	fc->security = opts;
+	return 0;
+}
+
+static int selinux_fs_context_dup(struct fs_context *fc,
+				  struct fs_context *src_fc)
+{
+	const struct selinux_mnt_opts *src = src_fc->security;
+
+	if (!src)
+		return 0;
+
+	fc->security = kmemdup(src, sizeof(*src), GFP_KERNEL);
+	return fc->security ? 0 : -ENOMEM;
+}
+
+static const struct fs_parameter_spec selinux_fs_parameters[] = {
+	fsparam_string(CONTEXT_STR,	Opt_context),
+	fsparam_string(DEFCONTEXT_STR,	Opt_defcontext),
+	fsparam_string(FSCONTEXT_STR,	Opt_fscontext),
+	fsparam_string(ROOTCONTEXT_STR,	Opt_rootcontext),
+	fsparam_flag  (SECLABEL_STR,	Opt_seclabel),
+	{}
+};
+
+static int selinux_fs_context_parse_param(struct fs_context *fc,
+					  struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	int opt;
+
+	opt = fs_parse(fc, selinux_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	return selinux_add_opt(opt, param->string, &fc->security);
+}
+
+/* inode security operations */
+
+static int selinux_inode_alloc_security(struct inode *inode)
+{
+	struct inode_security_struct *isec = selinux_inode(inode);
+	u32 sid = current_sid();
+
+	spin_lock_init(&isec->lock);
+	INIT_LIST_HEAD(&isec->list);
+	isec->inode = inode;
+	isec->sid = SECINITSID_UNLABELED;
+	isec->sclass = SECCLASS_FILE;
+	isec->task_sid = sid;
+	isec->initialized = LABEL_INVALID;
+
+	return 0;
+}
+
+static void selinux_inode_free_security(struct inode *inode)
+{
+	inode_free_security(inode);
+}
+
+static int selinux_dentry_init_security(struct dentry *dentry, int mode,
+					const struct qstr *name,
+					const char **xattr_name,
+					struct lsm_context *cp)
+{
+	u32 newsid;
+	int rc;
+
+	rc = selinux_determine_inode_label(selinux_cred(current_cred()),
+					   d_inode(dentry->d_parent), name,
+					   inode_mode_to_security_class(mode),
+					   &newsid);
+	if (rc)
+		return rc;
+
+	if (xattr_name)
+		*xattr_name = XATTR_NAME_SELINUX;
+
+	cp->id = LSM_ID_SELINUX;
+	return security_sid_to_context(newsid, &cp->context, &cp->len);
+}
+
+static int selinux_dentry_create_files_as(struct dentry *dentry, int mode,
+					  const struct qstr *name,
+					  const struct cred *old,
+					  struct cred *new)
+{
+	u32 newsid;
+	int rc;
+	struct cred_security_struct *crsec;
+
+	rc = selinux_determine_inode_label(selinux_cred(old),
+					   d_inode(dentry->d_parent), name,
+					   inode_mode_to_security_class(mode),
+					   &newsid);
+	if (rc)
+		return rc;
+
+	crsec = selinux_cred(new);
+	crsec->create_sid = newsid;
+	return 0;
+}
+
+static int selinux_inode_init_security(struct inode *inode, struct inode *dir,
+				       const struct qstr *qstr,
+				       struct xattr *xattrs, int *xattr_count)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	struct superblock_security_struct *sbsec;
+	struct xattr *xattr;
+	u32 newsid, clen;
+	u16 newsclass;
+	int rc;
+	char *context;
+
+	sbsec = selinux_superblock(dir->i_sb);
+
+	if (!selinux_initialized() ||
+	    !(sbsec->flags & SBLABEL_MNT))
+		return -EOPNOTSUPP;
+
+	newsid = crsec->create_sid;
+	newsclass = inode_mode_to_security_class(inode->i_mode);
+	rc = selinux_determine_inode_label(crsec, dir, qstr, newsclass, &newsid);
+	if (rc)
+		return rc;
+
+	/* Possibly defer initialization to selinux_complete_init. */
+	if (sbsec->flags & SE_SBINITIALIZED) {
+		struct inode_security_struct *isec = selinux_inode(inode);
+		isec->sclass = newsclass;
+		isec->sid = newsid;
+		isec->initialized = LABEL_INITIALIZED;
+	}
+
+	xattr = lsm_get_xattr_slot(xattrs, xattr_count);
+	if (xattr) {
+		rc = security_sid_to_context_force(newsid,
+						   &context, &clen);
+		if (rc)
+			return rc;
+		xattr->value = context;
+		xattr->value_len = clen;
+		xattr->name = XATTR_SELINUX_SUFFIX;
+	}
+
+	return 0;
+}
+
+static int selinux_inode_init_security_anon(struct inode *inode,
+					    const struct qstr *name,
+					    const struct inode *context_inode)
+{
+	u32 sid = current_sid();
+	struct common_audit_data ad;
+	struct inode_security_struct *isec;
+	int rc;
+	bool is_memfd = false;
+
+	if (unlikely(!selinux_initialized()))
+		return 0;
+
+	if (name != NULL && name->name != NULL &&
+	    !strcmp(name->name, MEMFD_ANON_NAME)) {
+		if (!selinux_policycap_memfd_class())
+			return 0;
+		is_memfd = true;
+	}
+
+	isec = selinux_inode(inode);
+
+	/*
+	 * We only get here once per ephemeral inode.  The inode has
+	 * been initialized via inode_alloc_security but is otherwise
+	 * untouched.
+	 */
+
+	if (context_inode) {
+		struct inode_security_struct *context_isec =
+			selinux_inode(context_inode);
+		if (context_isec->initialized != LABEL_INITIALIZED) {
+			pr_err("SELinux:  context_inode is not initialized\n");
+			return -EACCES;
+		}
+
+		isec->sclass = context_isec->sclass;
+		isec->sid = context_isec->sid;
+	} else {
+		if (is_memfd)
+			isec->sclass = SECCLASS_MEMFD_FILE;
+		else
+			isec->sclass = SECCLASS_ANON_INODE;
+		rc = security_transition_sid(
+			sid, sid,
+			isec->sclass, name, &isec->sid);
+		if (rc)
+			return rc;
+	}
+
+	isec->initialized = LABEL_INITIALIZED;
+	/*
+	 * Now that we've initialized security, check whether we're
+	 * allowed to actually create this type of anonymous inode.
+	 */
+
+	ad.type = LSM_AUDIT_DATA_ANONINODE;
+	ad.u.anonclass = name ? (const char *)name->name : "?";
+
+	return avc_has_perm(sid,
+			    isec->sid,
+			    isec->sclass,
+			    FILE__CREATE,
+			    &ad);
+}
+
+static int selinux_inode_create(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+	return may_create(dir, dentry, SECCLASS_FILE);
+}
+
+static int selinux_inode_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
+{
+	return may_link(dir, old_dentry, MAY_LINK);
+}
+
+static int selinux_inode_unlink(struct inode *dir, struct dentry *dentry)
+{
+	return may_link(dir, dentry, MAY_UNLINK);
+}
+
+static int selinux_inode_symlink(struct inode *dir, struct dentry *dentry, const char *name)
+{
+	return may_create(dir, dentry, SECCLASS_LNK_FILE);
+}
+
+static int selinux_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mask)
+{
+	return may_create(dir, dentry, SECCLASS_DIR);
+}
+
+static int selinux_inode_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	return may_link(dir, dentry, MAY_RMDIR);
+}
+
+static int selinux_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
+{
+	return may_create(dir, dentry, inode_mode_to_security_class(mode));
+}
+
+static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dentry,
+				struct inode *new_inode, struct dentry *new_dentry)
+{
+	return may_rename(old_inode, old_dentry, new_inode, new_dentry);
+}
+
+static int selinux_inode_readlink(struct dentry *dentry)
+{
+	const struct cred *cred = current_cred();
+
+	return dentry_has_perm(cred, dentry, FILE__READ);
+}
+
+static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode,
+				     bool rcu)
+{
+	struct common_audit_data ad;
+	struct inode_security_struct *isec;
+	u32 sid = current_sid();
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+	isec = inode_security_rcu(inode, rcu);
+	if (IS_ERR(isec))
+		return PTR_ERR(isec);
+
+	return avc_has_perm(sid, isec->sid, isec->sclass, FILE__READ, &ad);
+}
+
+static noinline int audit_inode_permission(struct inode *inode,
+					   u32 perms, u32 audited, u32 denied,
+					   int result)
+{
+	struct common_audit_data ad;
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	ad.type = LSM_AUDIT_DATA_INODE;
+	ad.u.inode = inode;
+
+	return slow_avc_audit(current_sid(), isec->sid, isec->sclass, perms,
+			    audited, denied, result, &ad);
+}
+
+/**
+ * task_avdcache_reset - Reset the task's AVD cache
+ * @tsec: the task's security state
+ *
+ * Clear the task's AVD cache in @tsec and reset it to the current policy's
+ * and task's info.
+ */
+static inline void task_avdcache_reset(struct task_security_struct *tsec)
+{
+	memset(&tsec->avdcache.dir, 0, sizeof(tsec->avdcache.dir));
+	tsec->avdcache.sid = current_sid();
+	tsec->avdcache.seqno = avc_policy_seqno();
+	tsec->avdcache.dir_spot = TSEC_AVDC_DIR_SIZE - 1;
+}
+
+/**
+ * task_avdcache_search - Search the task's AVD cache
+ * @tsec: the task's security state
+ * @isec: the inode to search for in the cache
+ * @avdc: matching avd cache entry returned to the caller
+ *
+ * Search @tsec for a AVD cache entry that matches @isec and return it to the
+ * caller via @avdc.  Returns 0 if a match is found, negative values otherwise.
+ */
+static inline int task_avdcache_search(struct task_security_struct *tsec,
+				       struct inode_security_struct *isec,
+				       struct avdc_entry **avdc)
+{
+	int orig, iter;
+
+	/* focused on path walk optimization, only cache directories */
+	if (isec->sclass != SECCLASS_DIR)
+		return -ENOENT;
+
+	if (unlikely(current_sid() != tsec->avdcache.sid ||
+		     tsec->avdcache.seqno != avc_policy_seqno())) {
+		task_avdcache_reset(tsec);
+		return -ENOENT;
+	}
+
+	orig = iter = tsec->avdcache.dir_spot;
+	do {
+		if (tsec->avdcache.dir[iter].isid == isec->sid) {
+			/* cache hit */
+			tsec->avdcache.dir_spot = iter;
+			*avdc = &tsec->avdcache.dir[iter];
+			return 0;
+		}
+		iter = (iter - 1) & (TSEC_AVDC_DIR_SIZE - 1);
+	} while (iter != orig);
+
+	return -ENOENT;
+}
+
+/**
+ * task_avdcache_update - Update the task's AVD cache
+ * @tsec: the task's security state
+ * @isec: the inode associated with the cache entry
+ * @avd: the AVD to cache
+ *
+ * Update the AVD cache in @tsec with the @avd info associated
+ * with @isec.
+ */
+static inline void task_avdcache_update(struct task_security_struct *tsec,
+					struct inode_security_struct *isec,
+					struct av_decision *avd)
+{
+	int spot;
+
+	/* focused on path walk optimization, only cache directories */
+	if (isec->sclass != SECCLASS_DIR)
+		return;
+
+	/* update cache */
+	spot = (tsec->avdcache.dir_spot + 1) & (TSEC_AVDC_DIR_SIZE - 1);
+	tsec->avdcache.dir_spot = spot;
+	tsec->avdcache.dir[spot].isid = isec->sid;
+	tsec->avdcache.dir[spot].avd = *avd;
+	tsec->avdcache.permissive_neveraudit =
+		(avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT));
+}
+
+/**
+ * selinux_inode_permission - Check if the current task can access an inode
+ * @inode: the inode that is being accessed
+ * @requested: the accesses being requested
+ *
+ * Check if the current task is allowed to access @inode according to
+ * @requested.  Returns 0 if allowed, negative values otherwise.
+ */
+static int selinux_inode_permission(struct inode *inode, int requested)
+{
+	int mask;
+	u32 perms;
+	u32 sid = current_sid();
+	struct task_security_struct *tsec;
+	struct inode_security_struct *isec;
+	struct avdc_entry *avdc;
+	struct av_decision avd, *avdp = &avd;
+	int rc, rc2;
+	u32 audited, denied;
+
+	mask = requested & (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND);
+
+	/* No permission to check.  Existence test. */
+	if (!mask)
+		return 0;
+
+	tsec = selinux_task(current);
+	if (task_avdcache_permnoaudit(tsec, sid))
+		return 0;
+
+	isec = inode_security_rcu(inode, requested & MAY_NOT_BLOCK);
+	if (IS_ERR(isec))
+		return PTR_ERR(isec);
+	perms = file_mask_to_av(inode->i_mode, mask);
+
+	rc = task_avdcache_search(tsec, isec, &avdc);
+	if (likely(!rc)) {
+		/* Cache hit. */
+		avdp = &avdc->avd;
+		denied = perms & ~avdp->allowed;
+		if (unlikely(denied) && enforcing_enabled() &&
+			!(avdp->flags & AVD_FLAGS_PERMISSIVE))
+			rc = -EACCES;
+	} else {
+		/* Cache miss. */
+		rc = avc_has_perm_noaudit(sid, isec->sid, isec->sclass,
+					  perms, 0, avdp);
+		task_avdcache_update(tsec, isec, avdp);
+	}
+
+	audited = avc_audit_required(perms, avdp, rc,
+				     (requested & MAY_ACCESS) ?
+				     FILE__AUDIT_ACCESS : 0, &denied);
+	if (likely(!audited))
+		return rc;
+
+	rc2 = audit_inode_permission(inode, perms, audited, denied, rc);
+	if (rc2)
+		return rc2;
+
+	return rc;
+}
+
+static int selinux_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+				 struct iattr *iattr)
+{
+	const struct cred *cred = current_cred();
+	struct inode *inode = d_backing_inode(dentry);
+	unsigned int ia_valid = iattr->ia_valid;
+	u32 av = FILE__WRITE;
+
+	/* ATTR_FORCE is just used for ATTR_KILL_S[UG]ID. */
+	if (ia_valid & ATTR_FORCE) {
+		ia_valid &= ~(ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_MODE |
+			      ATTR_FORCE);
+		if (!ia_valid)
+			return 0;
+	}
+
+	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID |
+			ATTR_ATIME_SET | ATTR_MTIME_SET | ATTR_TIMES_SET))
+		return dentry_has_perm(cred, dentry, FILE__SETATTR);
+
+	if (selinux_policycap_openperm() &&
+	    inode->i_sb->s_magic != SOCKFS_MAGIC &&
+	    (ia_valid & ATTR_SIZE) &&
+	    !(ia_valid & ATTR_FILE))
+		av |= FILE__OPEN;
+
+	return dentry_has_perm(cred, dentry, av);
+}
+
+static int selinux_inode_getattr(const struct path *path)
+{
+	struct task_security_struct *tsec;
+
+	tsec = selinux_task(current);
+
+	if (task_avdcache_permnoaudit(tsec, current_sid()))
+		return 0;
+
+	return path_has_perm(current_cred(), path, FILE__GETATTR);
+}
+
+static bool has_cap_mac_admin(bool audit)
+{
+	const struct cred *cred = current_cred();
+	unsigned int opts = audit ? CAP_OPT_NONE : CAP_OPT_NOAUDIT;
+
+	if (cap_capable(cred, &init_user_ns, CAP_MAC_ADMIN, opts))
+		return false;
+	if (cred_has_capability(cred, CAP_MAC_ADMIN, opts, true))
+		return false;
+	return true;
+}
+
+/**
+ * selinux_inode_xattr_skipcap - Skip the xattr capability checks?
+ * @name: name of the xattr
+ *
+ * Returns 1 to indicate that SELinux "owns" the access control rights to xattrs
+ * named @name; the LSM layer should avoid enforcing any traditional
+ * capability based access controls on this xattr.  Returns 0 to indicate that
+ * SELinux does not "own" the access control rights to xattrs named @name and is
+ * deferring to the LSM layer for further access controls, including capability
+ * based controls.
+ */
+static int selinux_inode_xattr_skipcap(const char *name)
+{
+	/* require capability check if not a selinux xattr */
+	return !strcmp(name, XATTR_NAME_SELINUX);
+}
+
+static int selinux_inode_setxattr(struct mnt_idmap *idmap,
+				  struct dentry *dentry, const char *name,
+				  const void *value, size_t size, int flags)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct inode_security_struct *isec;
+	struct superblock_security_struct *sbsec;
+	struct common_audit_data ad;
+	u32 newsid, sid = current_sid();
+	int rc = 0;
+
+	/* if not a selinux xattr, only check the ordinary setattr perm */
+	if (strcmp(name, XATTR_NAME_SELINUX))
+		return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+
+	if (!selinux_initialized())
+		return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM);
+
+	sbsec = selinux_superblock(inode->i_sb);
+	if (!(sbsec->flags & SBLABEL_MNT))
+		return -EOPNOTSUPP;
+
+	if (!inode_owner_or_capable(idmap, inode))
+		return -EPERM;
+
+	ad.type = LSM_AUDIT_DATA_DENTRY;
+	ad.u.dentry = dentry;
+
+	isec = backing_inode_security(dentry);
+	rc = avc_has_perm(sid, isec->sid, isec->sclass,
+			  FILE__RELABELFROM, &ad);
+	if (rc)
+		return rc;
+
+	rc = security_context_to_sid(value, size, &newsid,
+				     GFP_KERNEL);
+	if (rc == -EINVAL) {
+		if (!has_cap_mac_admin(true)) {
+			struct audit_buffer *ab;
+			size_t audit_size;
+
+			/* We strip a nul only if it is at the end, otherwise the
+			 * context contains a nul and we should audit that */
+			if (value) {
+				const char *str = value;
+
+				if (str[size - 1] == '\0')
+					audit_size = size - 1;
+				else
+					audit_size = size;
+			} else {
+				audit_size = 0;
+			}
+			ab = audit_log_start(audit_context(),
+					     GFP_ATOMIC, AUDIT_SELINUX_ERR);
+			if (!ab)
+				return rc;
+			audit_log_format(ab, "op=setxattr invalid_context=");
+			audit_log_n_untrustedstring(ab, value, audit_size);
+			audit_log_end(ab);
+
+			return rc;
+		}
+		rc = security_context_to_sid_force(value,
+						   size, &newsid);
+	}
+	if (rc)
+		return rc;
+
+	rc = avc_has_perm(sid, newsid, isec->sclass,
+			  FILE__RELABELTO, &ad);
+	if (rc)
+		return rc;
+
+	rc = security_validate_transition(isec->sid, newsid,
+					  sid, isec->sclass);
+	if (rc)
+		return rc;
+
+	return avc_has_perm(newsid,
+			    sbsec->sid,
+			    SECCLASS_FILESYSTEM,
+			    FILESYSTEM__ASSOCIATE,
+			    &ad);
+}
+
+static int selinux_inode_set_acl(struct mnt_idmap *idmap,
+				 struct dentry *dentry, const char *acl_name,
+				 struct posix_acl *kacl)
+{
+	return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+}
+
+static int selinux_inode_get_acl(struct mnt_idmap *idmap,
+				 struct dentry *dentry, const char *acl_name)
+{
+	return dentry_has_perm(current_cred(), dentry, FILE__GETATTR);
+}
+
+static int selinux_inode_remove_acl(struct mnt_idmap *idmap,
+				    struct dentry *dentry, const char *acl_name)
+{
+	return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+}
+
+static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
+					const void *value, size_t size,
+					int flags)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct inode_security_struct *isec;
+	u32 newsid;
+	int rc;
+
+	if (strcmp(name, XATTR_NAME_SELINUX)) {
+		/* Not an attribute we recognize, so nothing to do. */
+		return;
+	}
+
+	if (!selinux_initialized()) {
+		/* If we haven't even been initialized, then we can't validate
+		 * against a policy, so leave the label as invalid. It may
+		 * resolve to a valid label on the next revalidation try if
+		 * we've since initialized.
+		 */
+		return;
+	}
+
+	rc = security_context_to_sid_force(value, size,
+					   &newsid);
+	if (rc) {
+		pr_err("SELinux:  unable to map context to SID"
+		       "for (%s, %llu), rc=%d\n",
+		       inode->i_sb->s_id, inode->i_ino, -rc);
+		return;
+	}
+
+	isec = backing_inode_security(dentry);
+	spin_lock(&isec->lock);
+	isec->sclass = inode_mode_to_security_class(inode->i_mode);
+	isec->sid = newsid;
+	isec->initialized = LABEL_INITIALIZED;
+	spin_unlock(&isec->lock);
+}
+
+static int selinux_inode_getxattr(struct dentry *dentry, const char *name)
+{
+	const struct cred *cred = current_cred();
+
+	return dentry_has_perm(cred, dentry, FILE__GETATTR);
+}
+
+static int selinux_inode_listxattr(struct dentry *dentry)
+{
+	const struct cred *cred = current_cred();
+
+	return dentry_has_perm(cred, dentry, FILE__GETATTR);
+}
+
+static int selinux_inode_removexattr(struct mnt_idmap *idmap,
+				     struct dentry *dentry, const char *name)
+{
+	/* if not a selinux xattr, only check the ordinary setattr perm */
+	if (strcmp(name, XATTR_NAME_SELINUX))
+		return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+
+	if (!selinux_initialized())
+		return 0;
+
+	/* No one is allowed to remove a SELinux security label.
+	   You can change the label, but all data must be labeled. */
+	return -EACCES;
+}
+
+static int selinux_inode_file_setattr(struct dentry *dentry,
+				      struct file_kattr *fa)
+{
+	return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+}
+
+static int selinux_inode_file_getattr(struct dentry *dentry,
+				      struct file_kattr *fa)
+{
+	return dentry_has_perm(current_cred(), dentry, FILE__GETATTR);
+}
+
+static int selinux_path_notify(const struct path *path, u64 mask,
+						unsigned int obj_type)
+{
+	int ret;
+	u32 perm;
+
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_PATH;
+	ad.u.path = *path;
+
+	/*
+	 * Set permission needed based on the type of mark being set.
+	 * Performs an additional check for sb watches.
+	 */
+	switch (obj_type) {
+	case FSNOTIFY_OBJ_TYPE_VFSMOUNT:
+		perm = FILE__WATCH_MOUNT;
+		break;
+	case FSNOTIFY_OBJ_TYPE_SB:
+		perm = FILE__WATCH_SB;
+		ret = superblock_has_perm(current_cred(), path->dentry->d_sb,
+						FILESYSTEM__WATCH, &ad);
+		if (ret)
+			return ret;
+		break;
+	case FSNOTIFY_OBJ_TYPE_INODE:
+		perm = FILE__WATCH;
+		break;
+	case FSNOTIFY_OBJ_TYPE_MNTNS:
+		perm = FILE__WATCH_MOUNTNS;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* blocking watches require the file:watch_with_perm permission */
+	if (mask & (ALL_FSNOTIFY_PERM_EVENTS))
+		perm |= FILE__WATCH_WITH_PERM;
+
+	/* watches on read-like events need the file:watch_reads permission */
+	if (mask & (FS_ACCESS | FS_ACCESS_PERM | FS_PRE_ACCESS |
+		    FS_CLOSE_NOWRITE))
+		perm |= FILE__WATCH_READS;
+
+	return path_has_perm(current_cred(), path, perm);
+}
+
+/*
+ * Copy the inode security context value to the user.
+ *
+ * Permission check is handled by selinux_inode_getxattr hook.
+ */
+static int selinux_inode_getsecurity(struct mnt_idmap *idmap,
+				     struct inode *inode, const char *name,
+				     void **buffer, bool alloc)
+{
+	u32 size;
+	int error;
+	char *context = NULL;
+	struct inode_security_struct *isec;
+
+	/*
+	 * If we're not initialized yet, then we can't validate contexts, so
+	 * just let vfs_getxattr fall back to using the on-disk xattr.
+	 */
+	if (!selinux_initialized() ||
+	    strcmp(name, XATTR_SELINUX_SUFFIX))
+		return -EOPNOTSUPP;
+
+	/*
+	 * If the caller has CAP_MAC_ADMIN, then get the raw context
+	 * value even if it is not defined by current policy; otherwise,
+	 * use the in-core value under current policy.
+	 * Use the non-auditing forms of the permission checks since
+	 * getxattr may be called by unprivileged processes commonly
+	 * and lack of permission just means that we fall back to the
+	 * in-core context value, not a denial.
+	 */
+	isec = inode_security(inode);
+	if (has_cap_mac_admin(false))
+		error = security_sid_to_context_force(isec->sid, &context,
+						      &size);
+	else
+		error = security_sid_to_context(isec->sid,
+						&context, &size);
+	if (error)
+		return error;
+	error = size;
+	if (alloc) {
+		*buffer = context;
+		goto out_nofree;
+	}
+	kfree(context);
+out_nofree:
+	return error;
+}
+
+static int selinux_inode_setsecurity(struct inode *inode, const char *name,
+				     const void *value, size_t size, int flags)
+{
+	struct inode_security_struct *isec = inode_security_novalidate(inode);
+	struct superblock_security_struct *sbsec;
+	u32 newsid;
+	int rc;
+
+	if (strcmp(name, XATTR_SELINUX_SUFFIX))
+		return -EOPNOTSUPP;
+
+	sbsec = selinux_superblock(inode->i_sb);
+	if (!(sbsec->flags & SBLABEL_MNT))
+		return -EOPNOTSUPP;
+
+	if (!value || !size)
+		return -EACCES;
+
+	rc = security_context_to_sid(value, size, &newsid,
+				     GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	spin_lock(&isec->lock);
+	isec->sclass = inode_mode_to_security_class(inode->i_mode);
+	isec->sid = newsid;
+	isec->initialized = LABEL_INITIALIZED;
+	spin_unlock(&isec->lock);
+	return 0;
+}
+
+static int selinux_inode_listsecurity(struct inode *inode, char **buffer,
+				ssize_t *remaining_size)
+{
+	if (!selinux_initialized())
+		return 0;
+	return xattr_list_one(buffer, remaining_size, XATTR_NAME_SELINUX);
+}
+
+static void selinux_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop)
+{
+	struct inode_security_struct *isec = inode_security_novalidate(inode);
+
+	prop->selinux.secid = isec->sid;
+}
+
+static int selinux_inode_copy_up(struct dentry *src, struct cred **new)
+{
+	struct lsm_prop prop;
+	struct cred_security_struct *crsec;
+	struct cred *new_creds = *new;
+
+	if (new_creds == NULL) {
+		new_creds = prepare_creds();
+		if (!new_creds)
+			return -ENOMEM;
+	}
+
+	crsec = selinux_cred(new_creds);
+	/* Get label from overlay inode and set it in create_sid */
+	selinux_inode_getlsmprop(d_inode(src), &prop);
+	crsec->create_sid = prop.selinux.secid;
+	*new = new_creds;
+	return 0;
+}
+
+static int selinux_inode_copy_up_xattr(struct dentry *dentry, const char *name)
+{
+	/* The copy_up hook above sets the initial context on an inode, but we
+	 * don't then want to overwrite it by blindly copying all the lower
+	 * xattrs up.  Instead, filter out SELinux-related xattrs following
+	 * policy load.
+	 */
+	if (selinux_initialized() && !strcmp(name, XATTR_NAME_SELINUX))
+		return -ECANCELED; /* Discard */
+	/*
+	 * Any other attribute apart from SELINUX is not claimed, supported
+	 * by selinux.
+	 */
+	return -EOPNOTSUPP;
+}
+
+/* kernfs node operations */
+
+static int selinux_kernfs_init_security(struct kernfs_node *kn_dir,
+					struct kernfs_node *kn)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	u32 parent_sid, newsid, clen;
+	int rc;
+	char *context;
+
+	rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, NULL, 0);
+	if (rc == -ENODATA)
+		return 0;
+	else if (rc < 0)
+		return rc;
+
+	clen = (u32)rc;
+	context = kmalloc(clen, GFP_KERNEL);
+	if (!context)
+		return -ENOMEM;
+
+	rc = kernfs_xattr_get(kn_dir, XATTR_NAME_SELINUX, context, clen);
+	if (rc < 0) {
+		kfree(context);
+		return rc;
+	}
+
+	rc = security_context_to_sid(context, clen, &parent_sid,
+				     GFP_KERNEL);
+	kfree(context);
+	if (rc)
+		return rc;
+
+	if (crsec->create_sid) {
+		newsid = crsec->create_sid;
+	} else {
+		u16 secclass = inode_mode_to_security_class(kn->mode);
+		const char *kn_name;
+		struct qstr q;
+
+		/* kn is fresh, can't be renamed, name goes not away */
+		kn_name = rcu_dereference_check(kn->name, true);
+		q.name = kn_name;
+		q.hash_len = hashlen_string(kn_dir, kn_name);
+
+		rc = security_transition_sid(crsec->sid,
+					     parent_sid, secclass, &q,
+					     &newsid);
+		if (rc)
+			return rc;
+	}
+
+	rc = security_sid_to_context_force(newsid,
+					   &context, &clen);
+	if (rc)
+		return rc;
+
+	rc = kernfs_xattr_set(kn, XATTR_NAME_SELINUX, context, clen,
+			      XATTR_CREATE);
+	kfree(context);
+	return rc;
+}
+
+
+/* file security operations */
+
+static int selinux_revalidate_file_permission(struct file *file, int mask)
+{
+	const struct cred *cred = current_cred();
+	struct inode *inode = file_inode(file);
+
+	/* file_mask_to_av won't add FILE__WRITE if MAY_APPEND is set */
+	if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE))
+		mask |= MAY_APPEND;
+
+	return file_has_perm(cred, file,
+			     file_mask_to_av(inode->i_mode, mask));
+}
+
+static int selinux_file_permission(struct file *file, int mask)
+{
+	struct inode *inode = file_inode(file);
+	struct file_security_struct *fsec = selinux_file(file);
+	struct inode_security_struct *isec;
+	u32 sid = current_sid();
+
+	if (!mask)
+		/* No permission to check.  Existence test. */
+		return 0;
+
+	isec = inode_security(inode);
+	if (sid == fsec->sid && fsec->isid == isec->sid &&
+	    fsec->pseqno == avc_policy_seqno())
+		/* No change since file_open check. */
+		return 0;
+
+	return selinux_revalidate_file_permission(file, mask);
+}
+
+static int selinux_file_alloc_security(struct file *file)
+{
+	struct file_security_struct *fsec = selinux_file(file);
+	u32 sid = current_sid();
+
+	fsec->sid = sid;
+	fsec->fown_sid = sid;
+
+	return 0;
+}
+
+static int selinux_backing_file_alloc(struct file *backing_file,
+				      const struct file *user_file)
+{
+	struct backing_file_security_struct *bfsec;
+
+	bfsec = selinux_backing_file(backing_file);
+	bfsec->uf_sid = selinux_file(user_file)->sid;
+
+	return 0;
+}
+
+/*
+ * Check whether a task has the ioctl permission and cmd
+ * operation to an inode.
+ */
+static int ioctl_has_perm(const struct cred *cred, struct file *file,
+		u32 requested, u16 cmd)
+{
+	struct common_audit_data ad;
+	struct file_security_struct *fsec = selinux_file(file);
+	struct inode *inode = file_inode(file);
+	struct inode_security_struct *isec;
+	struct lsm_ioctlop_audit ioctl;
+	u32 ssid = cred_sid(cred);
+	int rc;
+	u8 driver = cmd >> 8;
+	u8 xperm = cmd & 0xff;
+
+	ad.type = LSM_AUDIT_DATA_IOCTL_OP;
+	ad.u.op = &ioctl;
+	ad.u.op->cmd = cmd;
+	ad.u.op->path = file->f_path;
+
+	if (ssid != fsec->sid) {
+		rc = avc_has_perm(ssid, fsec->sid,
+				SECCLASS_FD,
+				FD__USE,
+				&ad);
+		if (rc)
+			goto out;
+	}
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	isec = inode_security(inode);
+	rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested,
+				    driver, AVC_EXT_IOCTL, xperm, &ad);
+out:
+	return rc;
+}
+
+static int selinux_file_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	const struct cred *cred = current_cred();
+	int error = 0;
+
+	switch (cmd) {
+	case FIONREAD:
+	case FIBMAP:
+	case FIGETBSZ:
+	case FS_IOC_GETFLAGS:
+	case FS_IOC_GETVERSION:
+		error = file_has_perm(cred, file, FILE__GETATTR);
+		break;
+
+	case FS_IOC_SETFLAGS:
+	case FS_IOC_SETVERSION:
+		error = file_has_perm(cred, file, FILE__SETATTR);
+		break;
+
+	/* sys_ioctl() checks */
+	case FIONBIO:
+	case FIOASYNC:
+		error = file_has_perm(cred, file, 0);
+		break;
+
+	case KDSKBENT:
+	case KDSKBSENT:
+		error = cred_has_capability(cred, CAP_SYS_TTY_CONFIG,
+					    CAP_OPT_NONE, true);
+		break;
+
+	case FIOCLEX:
+	case FIONCLEX:
+		if (!selinux_policycap_ioctl_skip_cloexec())
+			error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd);
+		break;
+
+	/* default case assumes that the command will go
+	 * to the file's ioctl() function.
+	 */
+	default:
+		error = ioctl_has_perm(cred, file, FILE__IOCTL, (u16) cmd);
+	}
+	return error;
+}
+
+static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	/*
+	 * If we are in a 64-bit kernel running 32-bit userspace, we need to
+	 * make sure we don't compare 32-bit flags to 64-bit flags.
+	 */
+	switch (cmd) {
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	case FS_IOC32_GETVERSION:
+		cmd = FS_IOC_GETVERSION;
+		break;
+	case FS_IOC32_SETVERSION:
+		cmd = FS_IOC_SETVERSION;
+		break;
+	default:
+		break;
+	}
+
+	return selinux_file_ioctl(file, cmd, arg);
+}
+
+static int default_noexec __ro_after_init;
+
+static int __file_map_prot_check(const struct file *file, unsigned long prot,
+				 bool shared, bool mounter_check,
+				 bool bf_user_file)
+{
+	struct inode *inode = NULL;
+	bool prot_exec = prot & PROT_EXEC;
+	bool prot_write = prot & PROT_WRITE;
+
+	if (file) {
+		if (bf_user_file)
+			inode = d_inode(backing_file_user_path(file)->dentry);
+		else
+			inode = file_inode(file);
+	}
+
+	if (!mounter_check && default_noexec && prot_exec &&
+	    (!file || IS_PRIVATE(inode) || (!shared && prot_write))) {
+		int rc;
+		u32 sid = current_sid();
+
+		/*
+		 * We are making executable an anonymous mapping or a private
+		 * file mapping that will also be writable.
+		 */
+		rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM,
+				  NULL);
+		if (rc)
+			return rc;
+	}
+
+	if (file) {
+		const struct cred *cred = mounter_check ?
+				file->f_cred : current_cred();
+		/* "read" always possible, "write" only if shared */
+		u32 av = FILE__READ;
+		if (shared && prot_write)
+			av |= FILE__WRITE;
+		if (prot_exec)
+			av |= FILE__EXECUTE;
+
+		return __file_has_perm(cred, file, av, bf_user_file);
+	}
+
+	return 0;
+}
+
+static inline int file_map_prot_check(const struct file *file,
+				      unsigned long prot, bool shared,
+				      bool mounter_check)
+{
+	return __file_map_prot_check(file, prot, shared, mounter_check, false);
+}
+
+static int selinux_mmap_addr(unsigned long addr)
+{
+	int rc = 0;
+
+	if (addr < CONFIG_LSM_MMAP_MIN_ADDR) {
+		u32 sid = current_sid();
+		rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT,
+				  MEMPROTECT__MMAP_ZERO, NULL);
+	}
+
+	return rc;
+}
+
+static int selinux_mmap_file_common(struct file *file, unsigned long prot,
+				    bool shared, bool mounter_check)
+{
+	if (file) {
+		int rc;
+		struct common_audit_data ad;
+		const struct cred *cred = mounter_check ?
+				file->f_cred : current_cred();
+
+		ad.type = LSM_AUDIT_DATA_FILE;
+		ad.u.file = file;
+		rc = inode_has_perm(cred, file_inode(file), FILE__MAP, &ad);
+		if (rc)
+			return rc;
+	}
+
+	return file_map_prot_check(file, prot, shared, mounter_check);
+}
+
+static int selinux_mmap_file(struct file *file,
+			     unsigned long reqprot __always_unused,
+			     unsigned long prot, unsigned long flags)
+{
+	return selinux_mmap_file_common(file, prot,
+					(flags & MAP_TYPE) == MAP_SHARED,
+					false);
+}
+
+/**
+ * selinux_mmap_backing_file - Check mmap permissions on a backing file
+ * @vma: memory region
+ * @backing_file: stacked filesystem backing file
+ * @user_file: user visible file
+ *
+ * This is called after selinux_mmap_file() on stacked filesystems, and it
+ * is this function's responsibility to verify access to @backing_file and
+ * setup the SELinux state for possible later use in the mprotect() code path.
+ *
+ * By the time this function is called, mmap() access to @user_file has already
+ * been authorized and @vma->vm_file has been set to point to @backing_file.
+ *
+ * Return zero on success, negative values otherwise.
+ */
+static int selinux_mmap_backing_file(struct vm_area_struct *vma,
+				     struct file *backing_file,
+				     struct file *user_file __always_unused)
+{
+	unsigned long prot = 0;
+
+	/* translate vma->vm_flags perms into PROT perms */
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	return selinux_mmap_file_common(backing_file, prot,
+					vma->vm_flags & VM_SHARED,
+					true);
+}
+
+static int selinux_file_mprotect(struct vm_area_struct *vma,
+				 unsigned long reqprot __always_unused,
+				 unsigned long prot)
+{
+	int rc;
+	const struct cred *cred = current_cred();
+	u32 sid = cred_sid(cred);
+	const struct file *file = vma->vm_file;
+	bool backing_file;
+	bool shared = vma->vm_flags & VM_SHARED;
+
+	/* check if we need to trigger the "backing files are awful" mode */
+	backing_file = file && (file->f_mode & FMODE_BACKING);
+
+	if (default_noexec &&
+	    (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
+		/*
+		 * We don't use the vma_is_initial_heap() helper as it has
+		 * a history of problems and is currently broken on systems
+		 * where there is no heap, e.g. brk == start_brk.  Before
+		 * replacing the conditional below with vma_is_initial_heap(),
+		 * or something similar, please ensure that the logic is the
+		 * same as what we have below or you have tested every possible
+		 * corner case you can think to test.
+		 */
+		if (vma->vm_start >= vma->vm_mm->start_brk &&
+		    vma->vm_end <= vma->vm_mm->brk) {
+			rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
+					  PROCESS__EXECHEAP, NULL);
+			if (rc)
+				return rc;
+		} else if (!file && (vma_is_initial_stack(vma) ||
+			    vma_is_stack_for_current(vma))) {
+			rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
+					  PROCESS__EXECSTACK, NULL);
+			if (rc)
+				return rc;
+		} else if (file && vma->anon_vma) {
+			/*
+			 * We are making executable a file mapping that has
+			 * had some COW done. Since pages might have been
+			 * written, check ability to execute the possibly
+			 * modified content.  This typically should only
+			 * occur for text relocations.
+			 */
+			rc = __file_has_perm(cred, file, FILE__EXECMOD,
+					     backing_file);
+			if (rc)
+				return rc;
+			if (backing_file) {
+				rc = file_has_perm(file->f_cred, file,
+						   FILE__EXECMOD);
+				if (rc)
+					return rc;
+			}
+		}
+	}
+
+	rc = __file_map_prot_check(file, prot, shared, false, backing_file);
+	if (rc)
+		return rc;
+	if (backing_file) {
+		rc = file_map_prot_check(file, prot, shared, true);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int selinux_file_lock(struct file *file, unsigned int cmd)
+{
+	const struct cred *cred = current_cred();
+
+	return file_has_perm(cred, file, FILE__LOCK);
+}
+
+static int selinux_file_fcntl(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	const struct cred *cred = current_cred();
+	int err = 0;
+
+	switch (cmd) {
+	case F_SETFL:
+		if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) {
+			err = file_has_perm(cred, file, FILE__WRITE);
+			break;
+		}
+		fallthrough;
+	case F_SETOWN:
+	case F_SETSIG:
+	case F_GETFL:
+	case F_GETOWN:
+	case F_GETSIG:
+	case F_GETOWNER_UIDS:
+		/* Just check FD__USE permission */
+		err = file_has_perm(cred, file, 0);
+		break;
+	case F_GETLK:
+	case F_SETLK:
+	case F_SETLKW:
+	case F_OFD_GETLK:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+#if BITS_PER_LONG == 32
+	case F_GETLK64:
+	case F_SETLK64:
+	case F_SETLKW64:
+#endif
+		err = file_has_perm(cred, file, FILE__LOCK);
+		break;
+	}
+
+	return err;
+}
+
+static void selinux_file_set_fowner(struct file *file)
+{
+	struct file_security_struct *fsec;
+
+	fsec = selinux_file(file);
+	fsec->fown_sid = current_sid();
+}
+
+static int selinux_file_send_sigiotask(struct task_struct *tsk,
+				       struct fown_struct *fown, int signum)
+{
+	struct file *file;
+	u32 sid = task_sid_obj(tsk);
+	u32 perm;
+	struct file_security_struct *fsec;
+
+	/* struct fown_struct is never outside the context of a struct file */
+	file = fown->file;
+
+	fsec = selinux_file(file);
+
+	if (!signum)
+		perm = signal_to_av(SIGIO); /* as per send_sigio_to_task */
+	else
+		perm = signal_to_av(signum);
+
+	return avc_has_perm(fsec->fown_sid, sid,
+			    SECCLASS_PROCESS, perm, NULL);
+}
+
+static int selinux_file_receive(struct file *file)
+{
+	const struct cred *cred = current_cred();
+
+	return file_has_perm(cred, file, file_to_av(file));
+}
+
+static int selinux_file_open(struct file *file)
+{
+	struct file_security_struct *fsec;
+	struct inode_security_struct *isec;
+
+	fsec = selinux_file(file);
+	isec = inode_security(file_inode(file));
+	/*
+	 * Save inode label and policy sequence number
+	 * at open-time so that selinux_file_permission
+	 * can determine whether revalidation is necessary.
+	 * Task label is already saved in the file security
+	 * struct as its SID.
+	 */
+	fsec->isid = isec->sid;
+	fsec->pseqno = avc_policy_seqno();
+	/*
+	 * Since the inode label or policy seqno may have changed
+	 * between the selinux_inode_permission check and the saving
+	 * of state above, recheck that access is still permitted.
+	 * Otherwise, access might never be revalidated against the
+	 * new inode label or new policy.
+	 * This check is not redundant - do not remove.
+	 */
+	return file_path_has_perm(file->f_cred, file, open_file_to_av(file));
+}
+
+/* task security operations */
+
+static int selinux_task_alloc(struct task_struct *task,
+			      u64 clone_flags)
+{
+	u32 sid = current_sid();
+	struct task_security_struct *old_tsec = selinux_task(current);
+	struct task_security_struct *new_tsec = selinux_task(task);
+
+	*new_tsec = *old_tsec;
+	return avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__FORK, NULL);
+}
+
+/*
+ * prepare a new set of credentials for modification
+ */
+static int selinux_cred_prepare(struct cred *new, const struct cred *old,
+				gfp_t gfp)
+{
+	const struct cred_security_struct *old_crsec = selinux_cred(old);
+	struct cred_security_struct *crsec = selinux_cred(new);
+
+	*crsec = *old_crsec;
+	return 0;
+}
+
+/*
+ * transfer the SELinux data to a blank set of creds
+ */
+static void selinux_cred_transfer(struct cred *new, const struct cred *old)
+{
+	const struct cred_security_struct *old_crsec = selinux_cred(old);
+	struct cred_security_struct *crsec = selinux_cred(new);
+
+	*crsec = *old_crsec;
+}
+
+static void selinux_cred_getsecid(const struct cred *c, u32 *secid)
+{
+	*secid = cred_sid(c);
+}
+
+static void selinux_cred_getlsmprop(const struct cred *c, struct lsm_prop *prop)
+{
+	prop->selinux.secid = cred_sid(c);
+}
+
+/*
+ * set the security data for a kernel service
+ * - all the creation contexts are set to unlabelled
+ */
+static int selinux_kernel_act_as(struct cred *new, u32 secid)
+{
+	struct cred_security_struct *crsec = selinux_cred(new);
+	u32 sid = current_sid();
+	int ret;
+
+	ret = avc_has_perm(sid, secid,
+			   SECCLASS_KERNEL_SERVICE,
+			   KERNEL_SERVICE__USE_AS_OVERRIDE,
+			   NULL);
+	if (ret == 0) {
+		crsec->sid = secid;
+		crsec->create_sid = 0;
+		crsec->keycreate_sid = 0;
+		crsec->sockcreate_sid = 0;
+	}
+	return ret;
+}
+
+/*
+ * set the file creation context in a security record to the same as the
+ * objective context of the specified inode
+ */
+static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode)
+{
+	struct inode_security_struct *isec = inode_security(inode);
+	struct cred_security_struct *crsec = selinux_cred(new);
+	u32 sid = current_sid();
+	int ret;
+
+	ret = avc_has_perm(sid, isec->sid,
+			   SECCLASS_KERNEL_SERVICE,
+			   KERNEL_SERVICE__CREATE_FILES_AS,
+			   NULL);
+
+	if (ret == 0)
+		crsec->create_sid = isec->sid;
+	return ret;
+}
+
+static int selinux_kernel_module_request(char *kmod_name)
+{
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_KMOD;
+	ad.u.kmod_name = kmod_name;
+
+	return avc_has_perm(current_sid(), SECINITSID_KERNEL, SECCLASS_SYSTEM,
+			    SYSTEM__MODULE_REQUEST, &ad);
+}
+
+static int selinux_kernel_load_from_file(struct file *file, u32 requested)
+{
+	struct common_audit_data ad;
+	struct inode_security_struct *isec;
+	struct file_security_struct *fsec;
+	u32 sid = current_sid();
+	int rc;
+
+	if (file == NULL)
+		return avc_has_perm(sid, sid, SECCLASS_SYSTEM, requested, NULL);
+
+	ad.type = LSM_AUDIT_DATA_FILE;
+	ad.u.file = file;
+
+	fsec = selinux_file(file);
+	if (sid != fsec->sid) {
+		rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad);
+		if (rc)
+			return rc;
+	}
+
+	isec = inode_security(file_inode(file));
+	return avc_has_perm(sid, isec->sid, SECCLASS_SYSTEM, requested, &ad);
+}
+
+static int selinux_kernel_read_file(struct file *file,
+				    enum kernel_read_file_id id,
+				    bool contents)
+{
+	int rc = 0;
+
+	BUILD_BUG_ON_MSG(READING_MAX_ID > 8,
+			 "New kernel_read_file_id introduced; update SELinux!");
+
+	switch (id) {
+	case READING_FIRMWARE:
+		rc = selinux_kernel_load_from_file(file, SYSTEM__FIRMWARE_LOAD);
+		break;
+	case READING_MODULE:
+	case READING_MODULE_COMPRESSED:
+		rc = selinux_kernel_load_from_file(file, SYSTEM__MODULE_LOAD);
+		break;
+	case READING_KEXEC_IMAGE:
+		rc = selinux_kernel_load_from_file(file,
+						   SYSTEM__KEXEC_IMAGE_LOAD);
+		break;
+	case READING_KEXEC_INITRAMFS:
+		rc = selinux_kernel_load_from_file(file,
+						SYSTEM__KEXEC_INITRAMFS_LOAD);
+		break;
+	case READING_POLICY:
+		rc = selinux_kernel_load_from_file(file, SYSTEM__POLICY_LOAD);
+		break;
+	case READING_X509_CERTIFICATE:
+		rc = selinux_kernel_load_from_file(file,
+						SYSTEM__X509_CERTIFICATE_LOAD);
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
+static int selinux_kernel_load_data(enum kernel_load_data_id id, bool contents)
+{
+	int rc = 0;
+
+	BUILD_BUG_ON_MSG(LOADING_MAX_ID > 8,
+			 "New kernel_load_data_id introduced; update SELinux!");
+
+	switch (id) {
+	case LOADING_FIRMWARE:
+		rc = selinux_kernel_load_from_file(NULL, SYSTEM__FIRMWARE_LOAD);
+		break;
+	case LOADING_MODULE:
+		rc = selinux_kernel_load_from_file(NULL, SYSTEM__MODULE_LOAD);
+		break;
+	case LOADING_KEXEC_IMAGE:
+		rc = selinux_kernel_load_from_file(NULL,
+						   SYSTEM__KEXEC_IMAGE_LOAD);
+		break;
+	case LOADING_KEXEC_INITRAMFS:
+		rc = selinux_kernel_load_from_file(NULL,
+						SYSTEM__KEXEC_INITRAMFS_LOAD);
+		break;
+	case LOADING_POLICY:
+		rc = selinux_kernel_load_from_file(NULL,
+						   SYSTEM__POLICY_LOAD);
+		break;
+	case LOADING_X509_CERTIFICATE:
+		rc = selinux_kernel_load_from_file(NULL,
+						SYSTEM__X509_CERTIFICATE_LOAD);
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
+static int selinux_task_setpgid(struct task_struct *p, pid_t pgid)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__SETPGID, NULL);
+}
+
+static int selinux_task_getpgid(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__GETPGID, NULL);
+}
+
+static int selinux_task_getsid(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__GETSESSION, NULL);
+}
+
+static void selinux_current_getlsmprop_subj(struct lsm_prop *prop)
+{
+	prop->selinux.secid = current_sid();
+}
+
+static void selinux_task_getlsmprop_obj(struct task_struct *p,
+					struct lsm_prop *prop)
+{
+	prop->selinux.secid = task_sid_obj(p);
+}
+
+static int selinux_task_setnice(struct task_struct *p, int nice)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__SETSCHED, NULL);
+}
+
+static int selinux_task_setioprio(struct task_struct *p, int ioprio)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__SETSCHED, NULL);
+}
+
+static int selinux_task_getioprio(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__GETSCHED, NULL);
+}
+
+static int selinux_task_prlimit(const struct cred *cred, const struct cred *tcred,
+				unsigned int flags)
+{
+	u32 av = 0;
+
+	if (!flags)
+		return 0;
+	if (flags & LSM_PRLIMIT_WRITE)
+		av |= PROCESS__SETRLIMIT;
+	if (flags & LSM_PRLIMIT_READ)
+		av |= PROCESS__GETRLIMIT;
+	return avc_has_perm(cred_sid(cred), cred_sid(tcred),
+			    SECCLASS_PROCESS, av, NULL);
+}
+
+static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource,
+		struct rlimit *new_rlim)
+{
+	struct rlimit *old_rlim = p->signal->rlim + resource;
+
+	/* Control the ability to change the hard limit (whether
+	   lowering or raising it), so that the hard limit can
+	   later be used as a safe reset point for the soft limit
+	   upon context transitions.  See selinux_bprm_committing_creds. */
+	if (old_rlim->rlim_max != new_rlim->rlim_max)
+		return avc_has_perm(current_sid(), task_sid_obj(p),
+				    SECCLASS_PROCESS, PROCESS__SETRLIMIT, NULL);
+
+	return 0;
+}
+
+static int selinux_task_setscheduler(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__SETSCHED, NULL);
+}
+
+static int selinux_task_getscheduler(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__GETSCHED, NULL);
+}
+
+static int selinux_task_movememory(struct task_struct *p)
+{
+	return avc_has_perm(current_sid(), task_sid_obj(p), SECCLASS_PROCESS,
+			    PROCESS__SETSCHED, NULL);
+}
+
+static int selinux_task_kill(struct task_struct *p, struct kernel_siginfo *info,
+				int sig, const struct cred *cred)
+{
+	u32 secid;
+	u32 perm;
+
+	if (!sig)
+		perm = PROCESS__SIGNULL; /* null signal; existence test */
+	else
+		perm = signal_to_av(sig);
+	if (!cred)
+		secid = current_sid();
+	else
+		secid = cred_sid(cred);
+	return avc_has_perm(secid, task_sid_obj(p), SECCLASS_PROCESS, perm, NULL);
+}
+
+static void selinux_task_to_inode(struct task_struct *p,
+				  struct inode *inode)
+{
+	struct inode_security_struct *isec = selinux_inode(inode);
+	u32 sid = task_sid_obj(p);
+
+	spin_lock(&isec->lock);
+	isec->sclass = inode_mode_to_security_class(inode->i_mode);
+	isec->sid = sid;
+	isec->initialized = LABEL_INITIALIZED;
+	spin_unlock(&isec->lock);
+}
+
+static int selinux_userns_create(const struct cred *cred)
+{
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, sid, SECCLASS_USER_NAMESPACE,
+			USER_NAMESPACE__CREATE, NULL);
+}
+
+/* Returns error only if unable to parse addresses */
+static int selinux_parse_skb_ipv4(struct sk_buff *skb,
+			struct common_audit_data *ad, u8 *proto)
+{
+	int offset, ihlen, ret = -EINVAL;
+	struct iphdr _iph, *ih;
+
+	offset = skb_network_offset(skb);
+	ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
+	if (ih == NULL)
+		goto out;
+
+	ihlen = ih->ihl * 4;
+	if (ihlen < sizeof(_iph))
+		goto out;
+
+	ad->u.net->v4info.saddr = ih->saddr;
+	ad->u.net->v4info.daddr = ih->daddr;
+	ret = 0;
+
+	if (proto)
+		*proto = ih->protocol;
+
+	switch (ih->protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		if (ntohs(ih->frag_off) & IP_OFFSET)
+			break;
+
+		offset += ihlen;
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			break;
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		if (ntohs(ih->frag_off) & IP_OFFSET)
+			break;
+
+		offset += ihlen;
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			break;
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+
+#if IS_ENABLED(CONFIG_IP_SCTP)
+	case IPPROTO_SCTP: {
+		struct sctphdr _sctph, *sh;
+
+		if (ntohs(ih->frag_off) & IP_OFFSET)
+			break;
+
+		offset += ihlen;
+		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+		if (sh == NULL)
+			break;
+
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+#endif
+	default:
+		break;
+	}
+out:
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+/* Returns error only if unable to parse addresses */
+static int selinux_parse_skb_ipv6(struct sk_buff *skb,
+			struct common_audit_data *ad, u8 *proto)
+{
+	u8 nexthdr;
+	int ret = -EINVAL, offset;
+	struct ipv6hdr _ipv6h, *ip6;
+	__be16 frag_off;
+
+	offset = skb_network_offset(skb);
+	ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
+	if (ip6 == NULL)
+		goto out;
+
+	ad->u.net->v6info.saddr = ip6->saddr;
+	ad->u.net->v6info.daddr = ip6->daddr;
+	ret = 0;
+
+	nexthdr = ip6->nexthdr;
+	offset += sizeof(_ipv6h);
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+	if (offset < 0)
+		goto out;
+
+	if (proto)
+		*proto = nexthdr;
+
+	switch (nexthdr) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			break;
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			break;
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+
+#if IS_ENABLED(CONFIG_IP_SCTP)
+	case IPPROTO_SCTP: {
+		struct sctphdr _sctph, *sh;
+
+		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+		if (sh == NULL)
+			break;
+
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+#endif
+	/* includes fragments */
+	default:
+		break;
+	}
+out:
+	return ret;
+}
+
+#endif /* IPV6 */
+
+static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad,
+			     char **_addrp, int src, u8 *proto)
+{
+	char *addrp;
+	int ret;
+
+	switch (ad->u.net->family) {
+	case PF_INET:
+		ret = selinux_parse_skb_ipv4(skb, ad, proto);
+		if (ret)
+			goto parse_error;
+		addrp = (char *)(src ? &ad->u.net->v4info.saddr :
+				       &ad->u.net->v4info.daddr);
+		goto okay;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	case PF_INET6:
+		ret = selinux_parse_skb_ipv6(skb, ad, proto);
+		if (ret)
+			goto parse_error;
+		addrp = (char *)(src ? &ad->u.net->v6info.saddr :
+				       &ad->u.net->v6info.daddr);
+		goto okay;
+#endif	/* IPV6 */
+	default:
+		addrp = NULL;
+		goto okay;
+	}
+
+parse_error:
+	pr_warn(
+	       "SELinux: failure in selinux_parse_skb(),"
+	       " unable to parse packet\n");
+	return ret;
+
+okay:
+	if (_addrp)
+		*_addrp = addrp;
+	return 0;
+}
+
+/**
+ * selinux_skb_peerlbl_sid - Determine the peer label of a packet
+ * @skb: the packet
+ * @family: protocol family
+ * @sid: the packet's peer label SID
+ *
+ * Description:
+ * Check the various different forms of network peer labeling and determine
+ * the peer label/SID for the packet; most of the magic actually occurs in
+ * the security server function security_net_peersid_cmp().  The function
+ * returns zero if the value in @sid is valid (although it may be SECSID_NULL)
+ * or -EACCES if @sid is invalid due to inconsistencies with the different
+ * peer labels.
+ *
+ */
+static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
+{
+	int err;
+	u32 xfrm_sid;
+	u32 nlbl_sid;
+	u32 nlbl_type;
+
+	err = selinux_xfrm_skb_sid(skb, &xfrm_sid);
+	if (unlikely(err))
+		return -EACCES;
+	err = selinux_netlbl_skbuff_getsid(skb, family, &nlbl_type, &nlbl_sid);
+	if (unlikely(err))
+		return -EACCES;
+
+	err = security_net_peersid_resolve(nlbl_sid,
+					   nlbl_type, xfrm_sid, sid);
+	if (unlikely(err)) {
+		pr_warn(
+		       "SELinux: failure in selinux_skb_peerlbl_sid(),"
+		       " unable to determine packet's peer label\n");
+		return -EACCES;
+	}
+
+	return 0;
+}
+
+/**
+ * selinux_conn_sid - Determine the child socket label for a connection
+ * @sk_sid: the parent socket's SID
+ * @skb_sid: the packet's SID
+ * @conn_sid: the resulting connection SID
+ *
+ * If @skb_sid is valid then the user:role:type information from @sk_sid is
+ * combined with the MLS information from @skb_sid in order to create
+ * @conn_sid.  If @skb_sid is not valid then @conn_sid is simply a copy
+ * of @sk_sid.  Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_conn_sid(u32 sk_sid, u32 skb_sid, u32 *conn_sid)
+{
+	int err = 0;
+
+	if (skb_sid != SECSID_NULL)
+		err = security_sid_mls_copy(sk_sid, skb_sid,
+					    conn_sid);
+	else
+		*conn_sid = sk_sid;
+
+	return err;
+}
+
+/* socket security operations */
+
+static int socket_sockcreate_sid(const struct cred_security_struct *crsec,
+				 u16 secclass, u32 *socksid)
+{
+	if (crsec->sockcreate_sid > SECSID_NULL) {
+		*socksid = crsec->sockcreate_sid;
+		return 0;
+	}
+
+	return security_transition_sid(crsec->sid, crsec->sid,
+				       secclass, NULL, socksid);
+}
+
+static bool sock_skip_has_perm(u32 sid)
+{
+	if (sid == SECINITSID_KERNEL)
+		return true;
+
+	/*
+	 * Before POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT, sockets that
+	 * inherited the kernel context from early boot used to be skipped
+	 * here, so preserve that behavior unless the capability is set.
+	 *
+	 * By setting the capability the policy signals that it is ready
+	 * for this quirk to be fixed. Note that sockets created by a kernel
+	 * thread or a usermode helper executed without a transition will
+	 * still be skipped in this check regardless of the policycap
+	 * setting.
+	 */
+	if (!selinux_policycap_userspace_initial_context() &&
+	    sid == SECINITSID_INIT)
+		return true;
+	return false;
+}
+
+
+static int sock_has_perm(struct sock *sk, u32 perms)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+
+	if (sock_skip_has_perm(sksec->sid))
+		return 0;
+
+	ad_net_init_from_sk(&ad, &net, sk);
+
+	return avc_has_perm(current_sid(), sksec->sid, sksec->sclass, perms,
+			    &ad);
+}
+
+static int selinux_socket_create(int family, int type,
+				 int protocol, int kern)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	u32 newsid;
+	u16 secclass;
+	int rc;
+
+	if (kern)
+		return 0;
+
+	secclass = socket_type_to_security_class(family, type, protocol);
+	rc = socket_sockcreate_sid(crsec, secclass, &newsid);
+	if (rc)
+		return rc;
+
+	return avc_has_perm(crsec->sid, newsid, secclass, SOCKET__CREATE, NULL);
+}
+
+static int selinux_socket_post_create(struct socket *sock, int family,
+				      int type, int protocol, int kern)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+	struct inode_security_struct *isec = inode_security_novalidate(SOCK_INODE(sock));
+	struct sk_security_struct *sksec;
+	u16 sclass = socket_type_to_security_class(family, type, protocol);
+	u32 sid = SECINITSID_KERNEL;
+	int err = 0;
+
+	if (!kern) {
+		err = socket_sockcreate_sid(crsec, sclass, &sid);
+		if (err)
+			return err;
+	}
+
+	isec->sclass = sclass;
+	isec->sid = sid;
+	isec->initialized = LABEL_INITIALIZED;
+
+	if (sock->sk) {
+		sksec = selinux_sock(sock->sk);
+		sksec->sclass = sclass;
+		sksec->sid = sid;
+		/* Allows detection of the first association on this socket */
+		if (sksec->sclass == SECCLASS_SCTP_SOCKET)
+			sksec->sctp_assoc_state = SCTP_ASSOC_UNSET;
+
+		err = selinux_netlbl_socket_post_create(sock->sk, family);
+	}
+
+	return err;
+}
+
+static int selinux_socket_socketpair(struct socket *socka,
+				     struct socket *sockb)
+{
+	struct sk_security_struct *sksec_a = selinux_sock(socka->sk);
+	struct sk_security_struct *sksec_b = selinux_sock(sockb->sk);
+
+	sksec_a->peer_sid = sksec_b->sid;
+	sksec_b->peer_sid = sksec_a->sid;
+
+	return 0;
+}
+
+/* Range of port numbers used to automatically bind.
+   Need to determine whether we should perform a name_bind
+   permission check between the socket and the port number. */
+
+static int __selinux_socket_bind(struct sock *sk, struct sockaddr *address, int addrlen)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	u16 family;
+	int err;
+
+	err = sock_has_perm(sk, SOCKET__BIND);
+	if (err)
+		goto out;
+
+	/* If PF_INET or PF_INET6, check name_bind permission for the port. */
+	family = sk->sk_family;
+	if (family == PF_INET || family == PF_INET6) {
+		char *addrp;
+		struct common_audit_data ad;
+		struct lsm_network_audit net = {0,};
+		struct sockaddr_in *addr4 = NULL;
+		struct sockaddr_in6 *addr6 = NULL;
+		u16 family_sa;
+		unsigned short snum;
+		u32 sid, node_perm;
+
+		/*
+		 * sctp_bindx(3) calls via selinux_sctp_bind_connect()
+		 * that validates multiple binding addresses. Because of this
+		 * need to check address->sa_family as it is possible to have
+		 * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET.
+		 */
+		if (addrlen < offsetofend(struct sockaddr, sa_family))
+			return -EINVAL;
+		family_sa = address->sa_family;
+		switch (family_sa) {
+		case AF_UNSPEC:
+		case AF_INET:
+			if (addrlen < sizeof(struct sockaddr_in))
+				return -EINVAL;
+			addr4 = (struct sockaddr_in *)address;
+			if (family_sa == AF_UNSPEC) {
+				if (family == PF_INET6) {
+					/* Length check from inet6_bind_sk() */
+					if (addrlen < SIN6_LEN_RFC2133)
+						return -EINVAL;
+					/* Family check from __inet6_bind() */
+					goto err_af;
+				}
+				/* see __inet_bind(), we only want to allow
+				 * AF_UNSPEC if the address is INADDR_ANY
+				 */
+				if (addr4->sin_addr.s_addr != htonl(INADDR_ANY))
+					goto err_af;
+				family_sa = AF_INET;
+			}
+			snum = ntohs(addr4->sin_port);
+			addrp = (char *)&addr4->sin_addr.s_addr;
+			break;
+		case AF_INET6:
+			if (addrlen < SIN6_LEN_RFC2133)
+				return -EINVAL;
+			addr6 = (struct sockaddr_in6 *)address;
+			snum = ntohs(addr6->sin6_port);
+			addrp = (char *)&addr6->sin6_addr.s6_addr;
+			break;
+		default:
+			goto err_af;
+		}
+
+		ad.type = LSM_AUDIT_DATA_NET;
+		ad.u.net = &net;
+		ad.u.net->sport = htons(snum);
+		ad.u.net->family = family_sa;
+
+		if (snum) {
+			int low, high;
+
+			inet_get_local_port_range(sock_net(sk), &low, &high);
+
+			if (inet_port_requires_bind_service(sock_net(sk), snum) ||
+			    snum < low || snum > high) {
+				err = sel_netport_sid(sk->sk_protocol,
+						      snum, &sid);
+				if (err)
+					goto out;
+				err = avc_has_perm(sksec->sid, sid,
+						   sksec->sclass,
+						   SOCKET__NAME_BIND, &ad);
+				if (err)
+					goto out;
+			}
+		}
+
+		switch (sksec->sclass) {
+		case SECCLASS_TCP_SOCKET:
+			node_perm = TCP_SOCKET__NODE_BIND;
+			break;
+
+		case SECCLASS_UDP_SOCKET:
+			node_perm = UDP_SOCKET__NODE_BIND;
+			break;
+
+		case SECCLASS_SCTP_SOCKET:
+			node_perm = SCTP_SOCKET__NODE_BIND;
+			break;
+
+		default:
+			node_perm = RAWIP_SOCKET__NODE_BIND;
+			break;
+		}
+
+		err = sel_netnode_sid(addrp, family_sa, &sid);
+		if (err)
+			goto out;
+
+		if (family_sa == AF_INET)
+			ad.u.net->v4info.saddr = addr4->sin_addr.s_addr;
+		else
+			ad.u.net->v6info.saddr = addr6->sin6_addr;
+
+		err = avc_has_perm(sksec->sid, sid,
+				   sksec->sclass, node_perm, &ad);
+		if (err)
+			goto out;
+	}
+out:
+	return err;
+err_af:
+	/* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */
+	if (sk->sk_protocol == IPPROTO_SCTP)
+		return -EINVAL;
+	return -EAFNOSUPPORT;
+}
+
+static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
+{
+	return __selinux_socket_bind(sock->sk, address, addrlen);
+}
+
+/* This supports connect(2) and SCTP connect services such as sctp_connectx(3)
+ * and sctp_sendmsg(3) as described in Documentation/security/SCTP.rst
+ */
+static int selinux_socket_connect_helper(struct sock *sk,
+					 struct sockaddr *address, int addrlen)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	int err;
+
+	err = sock_has_perm(sk, SOCKET__CONNECT);
+	if (err)
+		return err;
+	if (addrlen < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
+
+	/* connect(AF_UNSPEC) has special handling, as it is a documented
+	 * way to disconnect the socket
+	 */
+	if (address->sa_family == AF_UNSPEC)
+		return 0;
+
+	/*
+	 * If a TCP or SCTP socket, check name_connect permission
+	 * for the port.
+	 */
+	if (sksec->sclass == SECCLASS_TCP_SOCKET ||
+	    sksec->sclass == SECCLASS_SCTP_SOCKET) {
+		struct common_audit_data ad;
+		struct lsm_network_audit net = {0,};
+		struct sockaddr_in *addr4 = NULL;
+		struct sockaddr_in6 *addr6 = NULL;
+		unsigned short snum;
+		u32 sid, perm;
+
+		/* sctp_connectx(3) calls via selinux_sctp_bind_connect()
+		 * that validates multiple connect addresses. Because of this
+		 * need to check address->sa_family as it is possible to have
+		 * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET.
+		 */
+		switch (address->sa_family) {
+		case AF_INET:
+			addr4 = (struct sockaddr_in *)address;
+			if (addrlen < sizeof(struct sockaddr_in))
+				return -EINVAL;
+			snum = ntohs(addr4->sin_port);
+			break;
+		case AF_INET6:
+			addr6 = (struct sockaddr_in6 *)address;
+			if (addrlen < SIN6_LEN_RFC2133)
+				return -EINVAL;
+			snum = ntohs(addr6->sin6_port);
+			break;
+		default:
+			/* Note that SCTP services expect -EINVAL, whereas
+			 * others expect -EAFNOSUPPORT.
+			 */
+			if (sksec->sclass == SECCLASS_SCTP_SOCKET)
+				return -EINVAL;
+			else
+				return -EAFNOSUPPORT;
+		}
+
+		err = sel_netport_sid(sk->sk_protocol, snum, &sid);
+		if (err)
+			return err;
+
+		switch (sksec->sclass) {
+		case SECCLASS_TCP_SOCKET:
+			perm = TCP_SOCKET__NAME_CONNECT;
+			break;
+		case SECCLASS_SCTP_SOCKET:
+			perm = SCTP_SOCKET__NAME_CONNECT;
+			break;
+		}
+
+		ad.type = LSM_AUDIT_DATA_NET;
+		ad.u.net = &net;
+		ad.u.net->dport = htons(snum);
+		ad.u.net->family = address->sa_family;
+		err = avc_has_perm(sksec->sid, sid, sksec->sclass, perm, &ad);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/* Supports connect(2), see comments in selinux_socket_connect_helper() */
+static int selinux_socket_connect(struct socket *sock,
+				  struct sockaddr *address, int addrlen)
+{
+	int err;
+	struct sock *sk = sock->sk;
+
+	err = selinux_socket_connect_helper(sk, address, addrlen);
+	if (err)
+		return err;
+
+	return selinux_netlbl_socket_connect(sk, address);
+}
+
+static int selinux_socket_listen(struct socket *sock, int backlog)
+{
+	return sock_has_perm(sock->sk, SOCKET__LISTEN);
+}
+
+static int selinux_socket_accept(struct socket *sock, struct socket *newsock)
+{
+	int err;
+	struct inode_security_struct *isec;
+	struct inode_security_struct *newisec;
+	u16 sclass;
+	u32 sid;
+
+	err = sock_has_perm(sock->sk, SOCKET__ACCEPT);
+	if (err)
+		return err;
+
+	isec = inode_security_novalidate(SOCK_INODE(sock));
+	spin_lock(&isec->lock);
+	sclass = isec->sclass;
+	sid = isec->sid;
+	spin_unlock(&isec->lock);
+
+	newisec = inode_security_novalidate(SOCK_INODE(newsock));
+	newisec->sclass = sclass;
+	newisec->sid = sid;
+	newisec->initialized = LABEL_INITIALIZED;
+
+	return 0;
+}
+
+static int selinux_socket_sendmsg(struct socket *sock, struct msghdr *msg,
+				  int size)
+{
+	int rc;
+	struct sockaddr *const addr = msg->msg_name;
+	const int addrlen = msg->msg_namelen;
+
+	rc = sock_has_perm(sock->sk, SOCKET__WRITE);
+	if (rc)
+		return rc;
+
+	if (addr && (msg->msg_flags & MSG_FASTOPEN) &&
+	    (sk_is_tcp(sock->sk) ||
+	     (sk_is_inet(sock->sk) && sock->sk->sk_type == SOCK_STREAM &&
+	      sock->sk->sk_protocol == IPPROTO_MPTCP))) {
+		rc = selinux_socket_connect(sock, addr, addrlen);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int selinux_socket_recvmsg(struct socket *sock, struct msghdr *msg,
+				  int size, int flags)
+{
+	return sock_has_perm(sock->sk, SOCKET__READ);
+}
+
+static int selinux_socket_getsockname(struct socket *sock)
+{
+	return sock_has_perm(sock->sk, SOCKET__GETATTR);
+}
+
+static int selinux_socket_getpeername(struct socket *sock)
+{
+	return sock_has_perm(sock->sk, SOCKET__GETATTR);
+}
+
+static int selinux_socket_setsockopt(struct socket *sock, int level, int optname)
+{
+	int err;
+
+	err = sock_has_perm(sock->sk, SOCKET__SETOPT);
+	if (err)
+		return err;
+
+	return selinux_netlbl_socket_setsockopt(sock, level, optname);
+}
+
+static int selinux_socket_getsockopt(struct socket *sock, int level,
+				     int optname)
+{
+	return sock_has_perm(sock->sk, SOCKET__GETOPT);
+}
+
+static int selinux_socket_shutdown(struct socket *sock, int how)
+{
+	return sock_has_perm(sock->sk, SOCKET__SHUTDOWN);
+}
+
+static int selinux_socket_unix_stream_connect(struct sock *sock,
+					      struct sock *other,
+					      struct sock *newsk)
+{
+	struct sk_security_struct *sksec_sock = selinux_sock(sock);
+	struct sk_security_struct *sksec_other = selinux_sock(other);
+	struct sk_security_struct *sksec_new = selinux_sock(newsk);
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	int err;
+
+	ad_net_init_from_sk(&ad, &net, other);
+
+	err = avc_has_perm(sksec_sock->sid, sksec_other->sid,
+			   sksec_other->sclass,
+			   UNIX_STREAM_SOCKET__CONNECTTO, &ad);
+	if (err)
+		return err;
+
+	/* server child socket */
+	sksec_new->peer_sid = sksec_sock->sid;
+	err = security_sid_mls_copy(sksec_other->sid,
+				    sksec_sock->sid, &sksec_new->sid);
+	if (err)
+		return err;
+
+	/* connecting socket */
+	sksec_sock->peer_sid = sksec_new->sid;
+
+	return 0;
+}
+
+static int selinux_socket_unix_may_send(struct socket *sock,
+					struct socket *other)
+{
+	struct sk_security_struct *ssec = selinux_sock(sock->sk);
+	struct sk_security_struct *osec = selinux_sock(other->sk);
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+
+	ad_net_init_from_sk(&ad, &net, other->sk);
+
+	return avc_has_perm(ssec->sid, osec->sid, osec->sclass, SOCKET__SENDTO,
+			    &ad);
+}
+
+static int selinux_inet_sys_rcv_skb(struct net *ns, int ifindex,
+				    char *addrp, u16 family, u32 peer_sid,
+				    struct common_audit_data *ad)
+{
+	int err;
+	u32 if_sid;
+	u32 node_sid;
+
+	err = sel_netif_sid(ns, ifindex, &if_sid);
+	if (err)
+		return err;
+	err = avc_has_perm(peer_sid, if_sid,
+			   SECCLASS_NETIF, NETIF__INGRESS, ad);
+	if (err)
+		return err;
+
+	err = sel_netnode_sid(addrp, family, &node_sid);
+	if (err)
+		return err;
+	return avc_has_perm(peer_sid, node_sid,
+			    SECCLASS_NODE, NODE__RECVFROM, ad);
+}
+
+static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb,
+				       u16 family)
+{
+	int err = 0;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	u32 sk_sid = sksec->sid;
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	char *addrp;
+
+	ad_net_init_from_iif(&ad, &net, skb->skb_iif, family);
+	err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL);
+	if (err)
+		return err;
+
+	if (selinux_secmark_enabled()) {
+		err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET,
+				   PACKET__RECV, &ad);
+		if (err)
+			return err;
+	}
+
+	err = selinux_netlbl_sock_rcv_skb(sksec, skb, family, &ad);
+	if (err)
+		return err;
+	err = selinux_xfrm_sock_rcv_skb(sksec->sid, skb, &ad);
+
+	return err;
+}
+
+static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	int err, peerlbl_active, secmark_active;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	u16 family = sk->sk_family;
+	u32 sk_sid = sksec->sid;
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	char *addrp;
+
+	if (family != PF_INET && family != PF_INET6)
+		return 0;
+
+	/* Handle mapped IPv4 packets arriving via IPv6 sockets */
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
+
+	/* If any sort of compatibility mode is enabled then handoff processing
+	 * to the selinux_sock_rcv_skb_compat() function to deal with the
+	 * special handling.  We do this in an attempt to keep this function
+	 * as fast and as clean as possible. */
+	if (!selinux_policycap_netpeer())
+		return selinux_sock_rcv_skb_compat(sk, skb, family);
+
+	secmark_active = selinux_secmark_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
+	if (!secmark_active && !peerlbl_active)
+		return 0;
+
+	ad_net_init_from_iif(&ad, &net, skb->skb_iif, family);
+	err = selinux_parse_skb(skb, &ad, &addrp, 1, NULL);
+	if (err)
+		return err;
+
+	if (peerlbl_active) {
+		u32 peer_sid;
+
+		err = selinux_skb_peerlbl_sid(skb, family, &peer_sid);
+		if (err)
+			return err;
+		err = selinux_inet_sys_rcv_skb(sock_net(sk), skb->skb_iif,
+					       addrp, family, peer_sid, &ad);
+		if (err) {
+			selinux_netlbl_err(skb, family, err, 0);
+			return err;
+		}
+		err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER,
+				   PEER__RECV, &ad);
+		if (err) {
+			selinux_netlbl_err(skb, family, err, 0);
+			return err;
+		}
+	}
+
+	if (secmark_active) {
+		err = avc_has_perm(sk_sid, skb->secmark, SECCLASS_PACKET,
+				   PACKET__RECV, &ad);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static int selinux_socket_getpeersec_stream(struct socket *sock,
+					    sockptr_t optval, sockptr_t optlen,
+					    unsigned int len)
+{
+	int err = 0;
+	char *scontext = NULL;
+	u32 scontext_len;
+	struct sk_security_struct *sksec = selinux_sock(sock->sk);
+	u32 peer_sid = SECSID_NULL;
+
+	if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET ||
+	    sksec->sclass == SECCLASS_TCP_SOCKET ||
+	    sksec->sclass == SECCLASS_SCTP_SOCKET)
+		peer_sid = sksec->peer_sid;
+	if (peer_sid == SECSID_NULL)
+		return -ENOPROTOOPT;
+
+	err = security_sid_to_context(peer_sid, &scontext,
+				      &scontext_len);
+	if (err)
+		return err;
+	if (scontext_len > len) {
+		err = -ERANGE;
+		goto out_len;
+	}
+
+	if (copy_to_sockptr(optval, scontext, scontext_len))
+		err = -EFAULT;
+out_len:
+	if (copy_to_sockptr(optlen, &scontext_len, sizeof(scontext_len)))
+		err = -EFAULT;
+	kfree(scontext);
+	return err;
+}
+
+static int selinux_socket_getpeersec_dgram(struct socket *sock,
+					   struct sk_buff *skb, u32 *secid)
+{
+	u32 peer_secid = SECSID_NULL;
+	u16 family;
+
+	if (skb && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
+	else if (skb && skb->protocol == htons(ETH_P_IPV6))
+		family = PF_INET6;
+	else if (sock)
+		family = sock->sk->sk_family;
+	else {
+		*secid = SECSID_NULL;
+		return -EINVAL;
+	}
+
+	if (sock && family == PF_UNIX) {
+		struct inode_security_struct *isec;
+		isec = inode_security_novalidate(SOCK_INODE(sock));
+		peer_secid = isec->sid;
+	} else if (skb)
+		selinux_skb_peerlbl_sid(skb, family, &peer_secid);
+
+	*secid = peer_secid;
+	if (peer_secid == SECSID_NULL)
+		return -ENOPROTOOPT;
+	return 0;
+}
+
+static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	sksec->peer_sid = SECINITSID_UNLABELED;
+	sksec->sid = SECINITSID_UNLABELED;
+	sksec->sclass = SECCLASS_SOCKET;
+	selinux_netlbl_sk_security_reset(sksec);
+
+	return 0;
+}
+
+static void selinux_sk_free_security(struct sock *sk)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	selinux_netlbl_sk_security_free(sksec);
+}
+
+static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+	newsksec->sid = sksec->sid;
+	newsksec->peer_sid = sksec->peer_sid;
+	newsksec->sclass = sksec->sclass;
+
+	selinux_netlbl_sk_security_reset(newsksec);
+}
+
+static void selinux_sk_getsecid(const struct sock *sk, u32 *secid)
+{
+	if (!sk)
+		*secid = SECINITSID_ANY_SOCKET;
+	else {
+		const struct sk_security_struct *sksec = selinux_sock(sk);
+
+		*secid = sksec->sid;
+	}
+}
+
+static void selinux_sock_graft(struct sock *sk, struct socket *parent)
+{
+	struct inode_security_struct *isec =
+		inode_security_novalidate(SOCK_INODE(parent));
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 ||
+	    sk->sk_family == PF_UNIX)
+		isec->sid = sksec->sid;
+	sksec->sclass = isec->sclass;
+}
+
+/*
+ * Determines peer_secid for the asoc and updates socket's peer label
+ * if it's the first association on the socket.
+ */
+static int selinux_sctp_process_new_assoc(struct sctp_association *asoc,
+					  struct sk_buff *skb)
+{
+	struct sock *sk = asoc->base.sk;
+	u16 family = sk->sk_family;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	int err;
+
+	/* handle mapped IPv4 packets arriving via IPv6 sockets */
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
+
+	if (selinux_peerlbl_enabled()) {
+		asoc->peer_secid = SECSID_NULL;
+
+		/* This will return peer_sid = SECSID_NULL if there are
+		 * no peer labels, see security_net_peersid_resolve().
+		 */
+		err = selinux_skb_peerlbl_sid(skb, family, &asoc->peer_secid);
+		if (err)
+			return err;
+
+		if (asoc->peer_secid == SECSID_NULL)
+			asoc->peer_secid = SECINITSID_UNLABELED;
+	} else {
+		asoc->peer_secid = SECINITSID_UNLABELED;
+	}
+
+	if (sksec->sctp_assoc_state == SCTP_ASSOC_UNSET) {
+		sksec->sctp_assoc_state = SCTP_ASSOC_SET;
+
+		/* Here as first association on socket. As the peer SID
+		 * was allowed by peer recv (and the netif/node checks),
+		 * then it is approved by policy and used as the primary
+		 * peer SID for getpeercon(3).
+		 */
+		sksec->peer_sid = asoc->peer_secid;
+	} else if (sksec->peer_sid != asoc->peer_secid) {
+		/* Other association peer SIDs are checked to enforce
+		 * consistency among the peer SIDs.
+		 */
+		ad_net_init_from_sk(&ad, &net, asoc->base.sk);
+		err = avc_has_perm(sksec->peer_sid, asoc->peer_secid,
+				   sksec->sclass, SCTP_SOCKET__ASSOCIATION,
+				   &ad);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+/* Called whenever SCTP receives an INIT or COOKIE ECHO chunk. This
+ * happens on an incoming connect(2), sctp_connectx(3) or
+ * sctp_sendmsg(3) (with no association already present).
+ */
+static int selinux_sctp_assoc_request(struct sctp_association *asoc,
+				      struct sk_buff *skb)
+{
+	struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+	u32 conn_sid;
+	int err;
+
+	if (!selinux_policycap_extsockclass())
+		return 0;
+
+	err = selinux_sctp_process_new_assoc(asoc, skb);
+	if (err)
+		return err;
+
+	/* Compute the MLS component for the connection and store
+	 * the information in asoc. This will be used by SCTP TCP type
+	 * sockets and peeled off connections as they cause a new
+	 * socket to be generated. selinux_sctp_sk_clone() will then
+	 * plug this into the new socket.
+	 */
+	err = selinux_conn_sid(sksec->sid, asoc->peer_secid, &conn_sid);
+	if (err)
+		return err;
+
+	asoc->secid = conn_sid;
+
+	/* Set any NetLabel labels including CIPSO/CALIPSO options. */
+	return selinux_netlbl_sctp_assoc_request(asoc, skb);
+}
+
+/* Called when SCTP receives a COOKIE ACK chunk as the final
+ * response to an association request (initited by us).
+ */
+static int selinux_sctp_assoc_established(struct sctp_association *asoc,
+					  struct sk_buff *skb)
+{
+	struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+
+	if (!selinux_policycap_extsockclass())
+		return 0;
+
+	/* Inherit secid from the parent socket - this will be picked up
+	 * by selinux_sctp_sk_clone() if the association gets peeled off
+	 * into a new socket.
+	 */
+	asoc->secid = sksec->sid;
+
+	return selinux_sctp_process_new_assoc(asoc, skb);
+}
+
+/* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting
+ * based on their @optname.
+ */
+static int selinux_sctp_bind_connect(struct sock *sk, int optname,
+				     struct sockaddr *address,
+				     int addrlen)
+{
+	int len, err = 0, walk_size = 0;
+	void *addr_buf;
+	struct sockaddr *addr;
+
+	if (!selinux_policycap_extsockclass())
+		return 0;
+
+	/* Process one or more addresses that may be IPv4 or IPv6 */
+	addr_buf = address;
+
+	while (walk_size < addrlen) {
+		if (walk_size + sizeof(sa_family_t) > addrlen)
+			return -EINVAL;
+
+		addr = addr_buf;
+		switch (addr->sa_family) {
+		case AF_UNSPEC:
+		case AF_INET:
+			len = sizeof(struct sockaddr_in);
+			break;
+		case AF_INET6:
+			len = sizeof(struct sockaddr_in6);
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (walk_size + len > addrlen)
+			return -EINVAL;
+
+		err = -EINVAL;
+		switch (optname) {
+		/* Bind checks */
+		case SCTP_PRIMARY_ADDR:
+		case SCTP_SET_PEER_PRIMARY_ADDR:
+		case SCTP_SOCKOPT_BINDX_ADD:
+			err = __selinux_socket_bind(sk, addr, len);
+			break;
+		/* Connect checks */
+		case SCTP_SOCKOPT_CONNECTX:
+		case SCTP_PARAM_SET_PRIMARY:
+		case SCTP_PARAM_ADD_IP:
+		case SCTP_SENDMSG_CONNECT:
+			err = selinux_socket_connect_helper(sk, addr, len);
+			if (err)
+				return err;
+
+			/* As selinux_sctp_bind_connect() is called by the
+			 * SCTP protocol layer, the socket is already locked,
+			 * therefore selinux_netlbl_socket_connect_locked()
+			 * is called here. The situations handled are:
+			 * sctp_connectx(3), sctp_sendmsg(3), sendmsg(2),
+			 * whenever a new IP address is added or when a new
+			 * primary address is selected.
+			 * Note that an SCTP connect(2) call happens before
+			 * the SCTP protocol layer and is handled via
+			 * selinux_socket_connect().
+			 */
+			err = selinux_netlbl_socket_connect_locked(sk, addr);
+			break;
+		}
+
+		if (err)
+			return err;
+
+		addr_buf += len;
+		walk_size += len;
+	}
+
+	return 0;
+}
+
+/* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */
+static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
+				  struct sock *newsk)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+	/* If policy does not support SECCLASS_SCTP_SOCKET then call
+	 * the non-sctp clone version.
+	 */
+	if (!selinux_policycap_extsockclass())
+		return selinux_sk_clone_security(sk, newsk);
+
+	newsksec->sid = asoc->secid;
+	newsksec->peer_sid = asoc->peer_secid;
+	newsksec->sclass = sksec->sclass;
+	selinux_netlbl_sctp_sk_clone(sk, newsk);
+}
+
+static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+{
+	struct sk_security_struct *ssksec = selinux_sock(ssk);
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	ssksec->sclass = sksec->sclass;
+	ssksec->sid = sksec->sid;
+
+	/* replace the existing subflow label deleting the existing one
+	 * and re-recreating a new label using the updated context
+	 */
+	selinux_netlbl_sk_security_free(ssksec);
+	return selinux_netlbl_socket_post_create(ssk, ssk->sk_family);
+}
+
+static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+				     struct request_sock *req)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	int err;
+	u16 family = req->rsk_ops->family;
+	u32 connsid;
+	u32 peersid;
+
+	err = selinux_skb_peerlbl_sid(skb, family, &peersid);
+	if (err)
+		return err;
+	err = selinux_conn_sid(sksec->sid, peersid, &connsid);
+	if (err)
+		return err;
+	req->secid = connsid;
+	req->peer_secid = peersid;
+
+	return selinux_netlbl_inet_conn_request(req, family);
+}
+
+static void selinux_inet_csk_clone(struct sock *newsk,
+				   const struct request_sock *req)
+{
+	struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+	newsksec->sid = req->secid;
+	newsksec->peer_sid = req->peer_secid;
+	/* NOTE: Ideally, we should also get the isec->sid for the
+	   new socket in sync, but we don't have the isec available yet.
+	   So we will wait until sock_graft to do it, by which
+	   time it will have been created and available. */
+
+	/* We don't need to take any sort of lock here as we are the only
+	 * thread with access to newsksec */
+	selinux_netlbl_inet_csk_clone(newsk, req->rsk_ops->family);
+}
+
+static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb)
+{
+	u16 family = sk->sk_family;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	/* handle mapped IPv4 packets arriving via IPv6 sockets */
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
+
+	selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid);
+}
+
+static int selinux_secmark_relabel_packet(u32 sid)
+{
+	return avc_has_perm(current_sid(), sid, SECCLASS_PACKET, PACKET__RELABELTO,
+			    NULL);
+}
+
+static void selinux_secmark_refcount_inc(void)
+{
+	atomic_inc(&selinux_secmark_refcount);
+}
+
+static void selinux_secmark_refcount_dec(void)
+{
+	atomic_dec(&selinux_secmark_refcount);
+}
+
+static void selinux_req_classify_flow(const struct request_sock *req,
+				      struct flowi_common *flic)
+{
+	flic->flowic_secid = req->secid;
+}
+
+static int selinux_tun_dev_alloc_security(void *security)
+{
+	struct tun_security_struct *tunsec = selinux_tun_dev(security);
+
+	tunsec->sid = current_sid();
+	return 0;
+}
+
+static int selinux_tun_dev_create(void)
+{
+	u32 sid = current_sid();
+
+	/* we aren't taking into account the "sockcreate" SID since the socket
+	 * that is being created here is not a socket in the traditional sense,
+	 * instead it is a private sock, accessible only to the kernel, and
+	 * representing a wide range of network traffic spanning multiple
+	 * connections unlike traditional sockets - check the TUN driver to
+	 * get a better understanding of why this socket is special */
+
+	return avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET, TUN_SOCKET__CREATE,
+			    NULL);
+}
+
+static int selinux_tun_dev_attach_queue(void *security)
+{
+	struct tun_security_struct *tunsec = selinux_tun_dev(security);
+
+	return avc_has_perm(current_sid(), tunsec->sid, SECCLASS_TUN_SOCKET,
+			    TUN_SOCKET__ATTACH_QUEUE, NULL);
+}
+
+static int selinux_tun_dev_attach(struct sock *sk, void *security)
+{
+	struct tun_security_struct *tunsec = selinux_tun_dev(security);
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	/* we don't currently perform any NetLabel based labeling here and it
+	 * isn't clear that we would want to do so anyway; while we could apply
+	 * labeling without the support of the TUN user the resulting labeled
+	 * traffic from the other end of the connection would almost certainly
+	 * cause confusion to the TUN user that had no idea network labeling
+	 * protocols were being used */
+
+	sksec->sid = tunsec->sid;
+	sksec->sclass = SECCLASS_TUN_SOCKET;
+
+	return 0;
+}
+
+static int selinux_tun_dev_open(void *security)
+{
+	struct tun_security_struct *tunsec = selinux_tun_dev(security);
+	u32 sid = current_sid();
+	int err;
+
+	err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET,
+			   TUN_SOCKET__RELABELFROM, NULL);
+	if (err)
+		return err;
+	err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET,
+			   TUN_SOCKET__RELABELTO, NULL);
+	if (err)
+		return err;
+	tunsec->sid = sid;
+
+	return 0;
+}
+
+#ifdef CONFIG_NETFILTER
+
+static unsigned int selinux_ip_forward(void *priv, struct sk_buff *skb,
+				       const struct nf_hook_state *state)
+{
+	int ifindex;
+	u16 family;
+	char *addrp;
+	u32 peer_sid;
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	int secmark_active, peerlbl_active;
+
+	if (!selinux_policycap_netpeer())
+		return NF_ACCEPT;
+
+	secmark_active = selinux_secmark_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
+	if (!secmark_active && !peerlbl_active)
+		return NF_ACCEPT;
+
+	family = state->pf;
+	if (selinux_skb_peerlbl_sid(skb, family, &peer_sid) != 0)
+		return NF_DROP;
+
+	ifindex = state->in->ifindex;
+	ad_net_init_from_iif(&ad, &net, ifindex, family);
+	if (selinux_parse_skb(skb, &ad, &addrp, 1, NULL) != 0)
+		return NF_DROP;
+
+	if (peerlbl_active) {
+		int err;
+
+		err = selinux_inet_sys_rcv_skb(state->net, ifindex,
+					       addrp, family, peer_sid, &ad);
+		if (err) {
+			selinux_netlbl_err(skb, family, err, 1);
+			return NF_DROP;
+		}
+	}
+
+	if (secmark_active)
+		if (avc_has_perm(peer_sid, skb->secmark,
+				 SECCLASS_PACKET, PACKET__FORWARD_IN, &ad))
+			return NF_DROP;
+
+	if (netlbl_enabled())
+		/* we do this in the FORWARD path and not the POST_ROUTING
+		 * path because we want to make sure we apply the necessary
+		 * labeling before IPsec is applied so we can leverage AH
+		 * protection */
+		if (selinux_netlbl_skbuff_setsid(skb, family, peer_sid) != 0)
+			return NF_DROP;
+
+	return NF_ACCEPT;
+}
+
+static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	struct sock *sk;
+	u32 sid;
+
+	if (!netlbl_enabled())
+		return NF_ACCEPT;
+
+	/* we do this in the LOCAL_OUT path and not the POST_ROUTING path
+	 * because we want to make sure we apply the necessary labeling
+	 * before IPsec is applied so we can leverage AH protection */
+	sk = skb_to_full_sk(skb);
+	if (sk) {
+		struct sk_security_struct *sksec;
+
+		if (sk_listener(sk))
+			/* if the socket is the listening state then this
+			 * packet is a SYN-ACK packet which means it needs to
+			 * be labeled based on the connection/request_sock and
+			 * not the parent socket.  unfortunately, we can't
+			 * lookup the request_sock yet as it isn't queued on
+			 * the parent socket until after the SYN-ACK is sent.
+			 * the "solution" is to simply pass the packet as-is
+			 * as any IP option based labeling should be copied
+			 * from the initial connection request (in the IP
+			 * layer).  it is far from ideal, but until we get a
+			 * security label in the packet itself this is the
+			 * best we can do. */
+			return NF_ACCEPT;
+
+		/* standard practice, label using the parent socket */
+		sksec = selinux_sock(sk);
+		sid = sksec->sid;
+	} else
+		sid = SECINITSID_KERNEL;
+	if (selinux_netlbl_skbuff_setsid(skb, state->pf, sid) != 0)
+		return NF_DROP;
+
+	return NF_ACCEPT;
+}
+
+
+static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
+					const struct nf_hook_state *state)
+{
+	struct sock *sk;
+	struct sk_security_struct *sksec;
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	u8 proto = 0;
+
+	sk = skb_to_full_sk(skb);
+	if (sk == NULL)
+		return NF_ACCEPT;
+	sksec = selinux_sock(sk);
+
+	ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf);
+	if (selinux_parse_skb(skb, &ad, NULL, 0, &proto))
+		return NF_DROP;
+
+	if (selinux_secmark_enabled())
+		if (avc_has_perm(sksec->sid, skb->secmark,
+				 SECCLASS_PACKET, PACKET__SEND, &ad))
+			return NF_DROP_ERR(-ECONNREFUSED);
+
+	if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto))
+		return NF_DROP_ERR(-ECONNREFUSED);
+
+	return NF_ACCEPT;
+}
+
+static unsigned int selinux_ip_postroute(void *priv,
+					 struct sk_buff *skb,
+					 const struct nf_hook_state *state)
+{
+	u16 family;
+	u32 secmark_perm;
+	u32 peer_sid;
+	int ifindex;
+	struct sock *sk;
+	struct common_audit_data ad;
+	struct lsm_network_audit net;
+	char *addrp;
+	int secmark_active, peerlbl_active;
+
+	/* If any sort of compatibility mode is enabled then handoff processing
+	 * to the selinux_ip_postroute_compat() function to deal with the
+	 * special handling.  We do this in an attempt to keep this function
+	 * as fast and as clean as possible. */
+	if (!selinux_policycap_netpeer())
+		return selinux_ip_postroute_compat(skb, state);
+
+	secmark_active = selinux_secmark_enabled();
+	peerlbl_active = selinux_peerlbl_enabled();
+	if (!secmark_active && !peerlbl_active)
+		return NF_ACCEPT;
+
+	sk = skb_to_full_sk(skb);
+
+#ifdef CONFIG_XFRM
+	/* If skb->dst->xfrm is non-NULL then the packet is undergoing an IPsec
+	 * packet transformation so allow the packet to pass without any checks
+	 * since we'll have another chance to perform access control checks
+	 * when the packet is on it's final way out.
+	 * NOTE: there appear to be some IPv6 multicast cases where skb->dst
+	 *       is NULL, in this case go ahead and apply access control.
+	 * NOTE: if this is a local socket (skb->sk != NULL) that is in the
+	 *       TCP listening state we cannot wait until the XFRM processing
+	 *       is done as we will miss out on the SA label if we do;
+	 *       unfortunately, this means more work, but it is only once per
+	 *       connection. */
+	if (skb_dst(skb) != NULL && skb_dst(skb)->xfrm != NULL &&
+	    !(sk && sk_listener(sk)))
+		return NF_ACCEPT;
+#endif
+
+	family = state->pf;
+	if (sk == NULL) {
+		/* Without an associated socket the packet is either coming
+		 * from the kernel or it is being forwarded; check the packet
+		 * to determine which and if the packet is being forwarded
+		 * query the packet directly to determine the security label. */
+		if (skb->skb_iif) {
+			secmark_perm = PACKET__FORWARD_OUT;
+			if (selinux_skb_peerlbl_sid(skb, family, &peer_sid))
+				return NF_DROP;
+		} else {
+			secmark_perm = PACKET__SEND;
+			peer_sid = SECINITSID_KERNEL;
+		}
+	} else if (sk_listener(sk)) {
+		/* Locally generated packet but the associated socket is in the
+		 * listening state which means this is a SYN-ACK packet.  In
+		 * this particular case the correct security label is assigned
+		 * to the connection/request_sock but unfortunately we can't
+		 * query the request_sock as it isn't queued on the parent
+		 * socket until after the SYN-ACK packet is sent; the only
+		 * viable choice is to regenerate the label like we do in
+		 * selinux_inet_conn_request().  See also selinux_ip_output()
+		 * for similar problems. */
+		u32 skb_sid;
+		struct sk_security_struct *sksec;
+
+		sksec = selinux_sock(sk);
+		if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+			return NF_DROP;
+		/* At this point, if the returned skb peerlbl is SECSID_NULL
+		 * and the packet has been through at least one XFRM
+		 * transformation then we must be dealing with the "final"
+		 * form of labeled IPsec packet; since we've already applied
+		 * all of our access controls on this packet we can safely
+		 * pass the packet. */
+		if (skb_sid == SECSID_NULL) {
+			switch (family) {
+			case PF_INET:
+				if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+				break;
+			case PF_INET6:
+				if (IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
+					return NF_ACCEPT;
+				break;
+			default:
+				return NF_DROP_ERR(-ECONNREFUSED);
+			}
+		}
+		if (selinux_conn_sid(sksec->sid, skb_sid, &peer_sid))
+			return NF_DROP;
+		secmark_perm = PACKET__SEND;
+	} else {
+		/* Locally generated packet, fetch the security label from the
+		 * associated socket. */
+		struct sk_security_struct *sksec = selinux_sock(sk);
+		peer_sid = sksec->sid;
+		secmark_perm = PACKET__SEND;
+	}
+
+	ifindex = state->out->ifindex;
+	ad_net_init_from_iif(&ad, &net, ifindex, family);
+	if (selinux_parse_skb(skb, &ad, &addrp, 0, NULL))
+		return NF_DROP;
+
+	if (secmark_active)
+		if (avc_has_perm(peer_sid, skb->secmark,
+				 SECCLASS_PACKET, secmark_perm, &ad))
+			return NF_DROP_ERR(-ECONNREFUSED);
+
+	if (peerlbl_active) {
+		u32 if_sid;
+		u32 node_sid;
+
+		if (sel_netif_sid(state->net, ifindex, &if_sid))
+			return NF_DROP;
+		if (avc_has_perm(peer_sid, if_sid,
+				 SECCLASS_NETIF, NETIF__EGRESS, &ad))
+			return NF_DROP_ERR(-ECONNREFUSED);
+
+		if (sel_netnode_sid(addrp, family, &node_sid))
+			return NF_DROP;
+		if (avc_has_perm(peer_sid, node_sid,
+				 SECCLASS_NODE, NODE__SENDTO, &ad))
+			return NF_DROP_ERR(-ECONNREFUSED);
+	}
+
+	return NF_ACCEPT;
+}
+#endif	/* CONFIG_NETFILTER */
+
+static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_type)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct common_audit_data ad;
+	u8 driver;
+	u8 xperm;
+
+	if (sock_skip_has_perm(sksec->sid))
+		return 0;
+
+	ad.type = LSM_AUDIT_DATA_NLMSGTYPE;
+	ad.u.nlmsg_type = nlmsg_type;
+
+	driver = nlmsg_type >> 8;
+	xperm = nlmsg_type & 0xff;
+
+	return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass,
+				      perms, driver, AVC_EXT_NLMSG, xperm, &ad);
+}
+
+static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb)
+{
+	int rc = 0;
+	unsigned int msg_len;
+	unsigned int data_len = skb->len;
+	unsigned char *data = skb->data;
+	struct nlmsghdr *nlh;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	u16 sclass = sksec->sclass;
+	u32 perm;
+
+	while (data_len >= nlmsg_total_size(0)) {
+		nlh = (struct nlmsghdr *)data;
+
+		/* NOTE: the nlmsg_len field isn't reliably set by some netlink
+		 *       users which means we can't reject skb's with bogus
+		 *       length fields; our solution is to follow what
+		 *       netlink_rcv_skb() does and simply skip processing at
+		 *       messages with length fields that are clearly junk
+		 */
+		if (nlh->nlmsg_len < NLMSG_HDRLEN || nlh->nlmsg_len > data_len)
+			return 0;
+
+		rc = selinux_nlmsg_lookup(sclass, nlh->nlmsg_type, &perm);
+		if (rc == 0) {
+			if (selinux_policycap_netlink_xperm()) {
+				rc = nlmsg_sock_has_extended_perms(
+					sk, perm, nlh->nlmsg_type);
+			} else {
+				rc = sock_has_perm(sk, perm);
+			}
+			if (rc)
+				return rc;
+		} else if (rc == -EINVAL) {
+			/* -EINVAL is a missing msg/perm mapping */
+			if (sclass == SECCLASS_NETLINK_TCPDIAG_SOCKET &&
+			    nlh->nlmsg_type == DCCPDIAG_GETSOCK)
+				pr_warn_once("SELinux: DCCP has been removed, pid=%d comm=%s\n",
+					     task_pid_nr(current), current->comm);
+			else
+				pr_warn_ratelimited("SELinux: unrecognized netlink"
+					" message: protocol=%hu nlmsg_type=%hu sclass=%s"
+					" pid=%d comm=%s\n",
+					sk->sk_protocol, nlh->nlmsg_type,
+					secclass_map[sclass - 1].name,
+					task_pid_nr(current), current->comm);
+			if (enforcing_enabled() &&
+			    !security_get_allow_unknown())
+				return rc;
+			rc = 0;
+		} else if (rc == -ENOENT) {
+			/* -ENOENT is a missing socket/class mapping, ignore */
+			rc = 0;
+		} else {
+			return rc;
+		}
+
+		/* move to the next message after applying netlink padding */
+		msg_len = NLMSG_ALIGN(nlh->nlmsg_len);
+		if (msg_len >= data_len)
+			return 0;
+		data_len -= msg_len;
+		data += msg_len;
+	}
+
+	return rc;
+}
+
+static void ipc_init_security(struct ipc_security_struct *isec, u16 sclass)
+{
+	isec->sclass = sclass;
+	isec->sid = current_sid();
+}
+
+static int ipc_has_perm(struct kern_ipc_perm *ipc_perms,
+			u32 perms)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(ipc_perms);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = ipc_perms->key;
+
+	return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad);
+}
+
+static int selinux_msg_msg_alloc_security(struct msg_msg *msg)
+{
+	struct msg_security_struct *msec;
+
+	msec = selinux_msg_msg(msg);
+	msec->sid = SECINITSID_UNLABELED;
+
+	return 0;
+}
+
+/* message queue security operations */
+static int selinux_msg_queue_alloc_security(struct kern_ipc_perm *msq)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(msq);
+	ipc_init_security(isec, SECCLASS_MSGQ);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = msq->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ,
+			    MSGQ__CREATE, &ad);
+}
+
+static int selinux_msg_queue_associate(struct kern_ipc_perm *msq, int msqflg)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(msq);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = msq->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ,
+			    MSGQ__ASSOCIATE, &ad);
+}
+
+static int selinux_msg_queue_msgctl(struct kern_ipc_perm *msq, int cmd)
+{
+	u32 perms;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case MSG_INFO:
+		/* No specific object, just general system-wide information. */
+		return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+				    SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL);
+	case IPC_STAT:
+	case MSG_STAT:
+	case MSG_STAT_ANY:
+		perms = MSGQ__GETATTR | MSGQ__ASSOCIATE;
+		break;
+	case IPC_SET:
+		perms = MSGQ__SETATTR;
+		break;
+	case IPC_RMID:
+		perms = MSGQ__DESTROY;
+		break;
+	default:
+		return 0;
+	}
+
+	return ipc_has_perm(msq, perms);
+}
+
+static int selinux_msg_queue_msgsnd(struct kern_ipc_perm *msq, struct msg_msg *msg, int msqflg)
+{
+	struct ipc_security_struct *isec;
+	struct msg_security_struct *msec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+	int rc;
+
+	isec = selinux_ipc(msq);
+	msec = selinux_msg_msg(msg);
+
+	/*
+	 * First time through, need to assign label to the message
+	 */
+	if (msec->sid == SECINITSID_UNLABELED) {
+		/*
+		 * Compute new sid based on current process and
+		 * message queue this message will be stored in
+		 */
+		rc = security_transition_sid(sid, isec->sid,
+					     SECCLASS_MSG, NULL, &msec->sid);
+		if (rc)
+			return rc;
+	}
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = msq->key;
+
+	/* Can this process write to the queue? */
+	rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ,
+			  MSGQ__WRITE, &ad);
+	if (!rc)
+		/* Can this process send the message */
+		rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG,
+				  MSG__SEND, &ad);
+	if (!rc)
+		/* Can the message be put in the queue? */
+		rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ,
+				  MSGQ__ENQUEUE, &ad);
+
+	return rc;
+}
+
+static int selinux_msg_queue_msgrcv(struct kern_ipc_perm *msq, struct msg_msg *msg,
+				    struct task_struct *target,
+				    long type, int mode)
+{
+	struct ipc_security_struct *isec;
+	struct msg_security_struct *msec;
+	struct common_audit_data ad;
+	u32 sid = task_sid_obj(target);
+	int rc;
+
+	isec = selinux_ipc(msq);
+	msec = selinux_msg_msg(msg);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = msq->key;
+
+	rc = avc_has_perm(sid, isec->sid,
+			  SECCLASS_MSGQ, MSGQ__READ, &ad);
+	if (!rc)
+		rc = avc_has_perm(sid, msec->sid,
+				  SECCLASS_MSG, MSG__RECEIVE, &ad);
+	return rc;
+}
+
+/* Shared Memory security operations */
+static int selinux_shm_alloc_security(struct kern_ipc_perm *shp)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(shp);
+	ipc_init_security(isec, SECCLASS_SHM);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = shp->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_SHM,
+			    SHM__CREATE, &ad);
+}
+
+static int selinux_shm_associate(struct kern_ipc_perm *shp, int shmflg)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(shp);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = shp->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_SHM,
+			    SHM__ASSOCIATE, &ad);
+}
+
+/* Note, at this point, shp is locked down */
+static int selinux_shm_shmctl(struct kern_ipc_perm *shp, int cmd)
+{
+	u32 perms;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SHM_INFO:
+		/* No specific object, just general system-wide information. */
+		return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+				    SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL);
+	case IPC_STAT:
+	case SHM_STAT:
+	case SHM_STAT_ANY:
+		perms = SHM__GETATTR | SHM__ASSOCIATE;
+		break;
+	case IPC_SET:
+		perms = SHM__SETATTR;
+		break;
+	case SHM_LOCK:
+	case SHM_UNLOCK:
+		perms = SHM__LOCK;
+		break;
+	case IPC_RMID:
+		perms = SHM__DESTROY;
+		break;
+	default:
+		return 0;
+	}
+
+	return ipc_has_perm(shp, perms);
+}
+
+static int selinux_shm_shmat(struct kern_ipc_perm *shp,
+			     char __user *shmaddr, int shmflg)
+{
+	u32 perms;
+
+	if (shmflg & SHM_RDONLY)
+		perms = SHM__READ;
+	else
+		perms = SHM__READ | SHM__WRITE;
+
+	return ipc_has_perm(shp, perms);
+}
+
+/* Semaphore security operations */
+static int selinux_sem_alloc_security(struct kern_ipc_perm *sma)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(sma);
+	ipc_init_security(isec, SECCLASS_SEM);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = sma->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_SEM,
+			    SEM__CREATE, &ad);
+}
+
+static int selinux_sem_associate(struct kern_ipc_perm *sma, int semflg)
+{
+	struct ipc_security_struct *isec;
+	struct common_audit_data ad;
+	u32 sid = current_sid();
+
+	isec = selinux_ipc(sma);
+
+	ad.type = LSM_AUDIT_DATA_IPC;
+	ad.u.ipc_id = sma->key;
+
+	return avc_has_perm(sid, isec->sid, SECCLASS_SEM,
+			    SEM__ASSOCIATE, &ad);
+}
+
+/* Note, at this point, sma is locked down */
+static int selinux_sem_semctl(struct kern_ipc_perm *sma, int cmd)
+{
+	int err;
+	u32 perms;
+
+	switch (cmd) {
+	case IPC_INFO:
+	case SEM_INFO:
+		/* No specific object, just general system-wide information. */
+		return avc_has_perm(current_sid(), SECINITSID_KERNEL,
+				    SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL);
+	case GETPID:
+	case GETNCNT:
+	case GETZCNT:
+		perms = SEM__GETATTR;
+		break;
+	case GETVAL:
+	case GETALL:
+		perms = SEM__READ;
+		break;
+	case SETVAL:
+	case SETALL:
+		perms = SEM__WRITE;
+		break;
+	case IPC_RMID:
+		perms = SEM__DESTROY;
+		break;
+	case IPC_SET:
+		perms = SEM__SETATTR;
+		break;
+	case IPC_STAT:
+	case SEM_STAT:
+	case SEM_STAT_ANY:
+		perms = SEM__GETATTR | SEM__ASSOCIATE;
+		break;
+	default:
+		return 0;
+	}
+
+	err = ipc_has_perm(sma, perms);
+	return err;
+}
+
+static int selinux_sem_semop(struct kern_ipc_perm *sma,
+			     struct sembuf *sops, unsigned nsops, int alter)
+{
+	u32 perms;
+
+	if (alter)
+		perms = SEM__READ | SEM__WRITE;
+	else
+		perms = SEM__READ;
+
+	return ipc_has_perm(sma, perms);
+}
+
+static int selinux_ipc_permission(struct kern_ipc_perm *ipcp, short flag)
+{
+	u32 av = 0;
+
+	av = 0;
+	if (flag & S_IRUGO)
+		av |= IPC__UNIX_READ;
+	if (flag & S_IWUGO)
+		av |= IPC__UNIX_WRITE;
+
+	if (av == 0)
+		return 0;
+
+	return ipc_has_perm(ipcp, av);
+}
+
+static void selinux_ipc_getlsmprop(struct kern_ipc_perm *ipcp,
+				   struct lsm_prop *prop)
+{
+	struct ipc_security_struct *isec = selinux_ipc(ipcp);
+	prop->selinux.secid = isec->sid;
+}
+
+static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode)
+{
+	if (inode)
+		inode_doinit_with_dentry(inode, dentry);
+}
+
+static int selinux_lsm_getattr(unsigned int attr, struct task_struct *p,
+			       char **value)
+{
+	const struct cred_security_struct *crsec;
+	int error;
+	u32 sid;
+	u32 len;
+
+	rcu_read_lock();
+	crsec = selinux_cred(__task_cred(p));
+	if (p != current) {
+		error = avc_has_perm(current_sid(), crsec->sid,
+				     SECCLASS_PROCESS, PROCESS__GETATTR, NULL);
+		if (error)
+			goto err_unlock;
+	}
+	switch (attr) {
+	case LSM_ATTR_CURRENT:
+		sid = crsec->sid;
+		break;
+	case LSM_ATTR_PREV:
+		sid = crsec->osid;
+		break;
+	case LSM_ATTR_EXEC:
+		sid = crsec->exec_sid;
+		break;
+	case LSM_ATTR_FSCREATE:
+		sid = crsec->create_sid;
+		break;
+	case LSM_ATTR_KEYCREATE:
+		sid = crsec->keycreate_sid;
+		break;
+	case LSM_ATTR_SOCKCREATE:
+		sid = crsec->sockcreate_sid;
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		goto err_unlock;
+	}
+	rcu_read_unlock();
+
+	if (sid == SECSID_NULL) {
+		*value = NULL;
+		return 0;
+	}
+
+	error = security_sid_to_context(sid, value, &len);
+	if (error)
+		return error;
+	return len;
+
+err_unlock:
+	rcu_read_unlock();
+	return error;
+}
+
+static int selinux_lsm_setattr(u64 attr, void *value, size_t size)
+{
+	struct cred_security_struct *crsec;
+	struct cred *new;
+	u32 mysid = current_sid(), sid = 0, ptsid;
+	int error;
+	char *str = value;
+
+	/*
+	 * Basic control over ability to set these attributes at all.
+	 */
+	switch (attr) {
+	case LSM_ATTR_EXEC:
+		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
+				     PROCESS__SETEXEC, NULL);
+		break;
+	case LSM_ATTR_FSCREATE:
+		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
+				     PROCESS__SETFSCREATE, NULL);
+		break;
+	case LSM_ATTR_KEYCREATE:
+		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
+				     PROCESS__SETKEYCREATE, NULL);
+		break;
+	case LSM_ATTR_SOCKCREATE:
+		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
+				     PROCESS__SETSOCKCREATE, NULL);
+		break;
+	case LSM_ATTR_CURRENT:
+		error = avc_has_perm(mysid, mysid, SECCLASS_PROCESS,
+				     PROCESS__SETCURRENT, NULL);
+		break;
+	default:
+		error = -EOPNOTSUPP;
+		break;
+	}
+	if (error)
+		return error;
+
+	/* Obtain a SID for the context, if one was specified. */
+	if (size && str[0] && str[0] != '\n') {
+		if (str[size-1] == '\n') {
+			str[size-1] = 0;
+			size--;
+		}
+		error = security_context_to_sid(value, size,
+						&sid, GFP_KERNEL);
+		if (error == -EINVAL && attr == LSM_ATTR_FSCREATE) {
+			if (!has_cap_mac_admin(true)) {
+				struct audit_buffer *ab;
+				size_t audit_size;
+
+				/* We strip a nul only if it is at the end,
+				 * otherwise the context contains a nul and
+				 * we should audit that */
+				if (str[size - 1] == '\0')
+					audit_size = size - 1;
+				else
+					audit_size = size;
+				ab = audit_log_start(audit_context(),
+						     GFP_ATOMIC,
+						     AUDIT_SELINUX_ERR);
+				if (!ab)
+					return error;
+				audit_log_format(ab, "op=fscreate invalid_context=");
+				audit_log_n_untrustedstring(ab, value,
+							    audit_size);
+				audit_log_end(ab);
+
+				return error;
+			}
+			error = security_context_to_sid_force(value, size,
+							&sid);
+		}
+		if (error)
+			return error;
+	}
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	/* Permission checking based on the specified context is
+	   performed during the actual operation (execve,
+	   open/mkdir/...), when we know the full context of the
+	   operation.  See selinux_bprm_creds_for_exec for the execve
+	   checks and may_create for the file creation checks. The
+	   operation will then fail if the context is not permitted. */
+	crsec = selinux_cred(new);
+	if (attr == LSM_ATTR_EXEC) {
+		crsec->exec_sid = sid;
+	} else if (attr == LSM_ATTR_FSCREATE) {
+		crsec->create_sid = sid;
+	} else if (attr == LSM_ATTR_KEYCREATE) {
+		if (sid) {
+			error = avc_has_perm(mysid, sid,
+					     SECCLASS_KEY, KEY__CREATE, NULL);
+			if (error)
+				goto abort_change;
+		}
+		crsec->keycreate_sid = sid;
+	} else if (attr == LSM_ATTR_SOCKCREATE) {
+		crsec->sockcreate_sid = sid;
+	} else if (attr == LSM_ATTR_CURRENT) {
+		error = -EINVAL;
+		if (sid == 0)
+			goto abort_change;
+
+		if (!current_is_single_threaded()) {
+			error = security_bounded_transition(crsec->sid, sid);
+			if (error)
+				goto abort_change;
+		}
+
+		/* Check permissions for the transition. */
+		error = avc_has_perm(crsec->sid, sid, SECCLASS_PROCESS,
+				     PROCESS__DYNTRANSITION, NULL);
+		if (error)
+			goto abort_change;
+
+		/* Check for ptracing, and update the task SID if ok.
+		   Otherwise, leave SID unchanged and fail. */
+		ptsid = ptrace_parent_sid();
+		if (ptsid != 0) {
+			error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS,
+					     PROCESS__PTRACE, NULL);
+			if (error)
+				goto abort_change;
+		}
+
+		crsec->sid = sid;
+	} else {
+		error = -EINVAL;
+		goto abort_change;
+	}
+
+	commit_creds(new);
+	return size;
+
+abort_change:
+	abort_creds(new);
+	return error;
+}
+
+/**
+ * selinux_getselfattr - Get SELinux current task attributes
+ * @attr: the requested attribute
+ * @ctx: buffer to receive the result
+ * @size: buffer size (input), buffer size used (output)
+ * @flags: unused
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns the number of attributes on success, an error code otherwise.
+ * There will only ever be one attribute.
+ */
+static int selinux_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			       u32 *size, u32 flags)
+{
+	int rc;
+	char *val = NULL;
+	int val_len;
+
+	val_len = selinux_lsm_getattr(attr, current, &val);
+	if (val_len < 0)
+		return val_len;
+	rc = lsm_fill_user_ctx(ctx, size, val, val_len, LSM_ID_SELINUX, 0);
+	kfree(val);
+	return (!rc ? 1 : rc);
+}
+
+static int selinux_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+			       u32 size, u32 flags)
+{
+	int rc;
+
+	rc = selinux_lsm_setattr(attr, ctx->ctx, ctx->ctx_len);
+	if (rc > 0)
+		return 0;
+	return rc;
+}
+
+static int selinux_getprocattr(struct task_struct *p,
+			       const char *name, char **value)
+{
+	unsigned int attr = lsm_name_to_attr(name);
+	int rc;
+
+	if (attr) {
+		rc = selinux_lsm_getattr(attr, p, value);
+		if (rc != -EOPNOTSUPP)
+			return rc;
+	}
+
+	return -EINVAL;
+}
+
+static int selinux_setprocattr(const char *name, void *value, size_t size)
+{
+	int attr = lsm_name_to_attr(name);
+
+	if (attr)
+		return selinux_lsm_setattr(attr, value, size);
+	return -EINVAL;
+}
+
+static int selinux_ismaclabel(const char *name)
+{
+	return (strcmp(name, XATTR_SELINUX_SUFFIX) == 0);
+}
+
+static int selinux_secid_to_secctx(u32 secid, struct lsm_context *cp)
+{
+	u32 seclen;
+	int ret;
+
+	if (cp) {
+		cp->id = LSM_ID_SELINUX;
+		ret = security_sid_to_context(secid, &cp->context, &cp->len);
+		if (ret < 0)
+			return ret;
+		return cp->len;
+	}
+	ret = security_sid_to_context(secid, NULL, &seclen);
+	if (ret < 0)
+		return ret;
+	return seclen;
+}
+
+static int selinux_lsmprop_to_secctx(struct lsm_prop *prop,
+				     struct lsm_context *cp)
+{
+	return selinux_secid_to_secctx(prop->selinux.secid, cp);
+}
+
+static int selinux_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
+{
+	return security_context_to_sid(secdata, seclen,
+				       secid, GFP_KERNEL);
+}
+
+static void selinux_release_secctx(struct lsm_context *cp)
+{
+	if (cp->id == LSM_ID_SELINUX) {
+		kfree(cp->context);
+		cp->context = NULL;
+		cp->id = LSM_ID_UNDEF;
+	}
+}
+
+static void selinux_inode_invalidate_secctx(struct inode *inode)
+{
+	struct inode_security_struct *isec = selinux_inode(inode);
+
+	spin_lock(&isec->lock);
+	isec->initialized = LABEL_INVALID;
+	spin_unlock(&isec->lock);
+}
+
+/*
+ *	called with inode->i_mutex locked
+ */
+static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
+{
+	int rc = selinux_inode_setsecurity(inode, XATTR_SELINUX_SUFFIX,
+					   ctx, ctxlen, 0);
+	/* Do not return error when suppressing label (SBLABEL_MNT not set). */
+	return rc == -EOPNOTSUPP ? 0 : rc;
+}
+
+/*
+ *	called with inode->i_mutex locked
+ */
+static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
+{
+	return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX,
+				     ctx, ctxlen, 0, NULL);
+}
+
+static int selinux_inode_getsecctx(struct inode *inode, struct lsm_context *cp)
+{
+	int len;
+	len = selinux_inode_getsecurity(&nop_mnt_idmap, inode,
+					XATTR_SELINUX_SUFFIX,
+					(void **)&cp->context, true);
+	if (len < 0)
+		return len;
+	cp->len = len;
+	cp->id = LSM_ID_SELINUX;
+	return 0;
+}
+#ifdef CONFIG_KEYS
+
+static int selinux_key_alloc(struct key *k, const struct cred *cred,
+			     unsigned long flags)
+{
+	const struct cred_security_struct *crsec;
+	struct key_security_struct *ksec = selinux_key(k);
+
+	crsec = selinux_cred(cred);
+	if (crsec->keycreate_sid)
+		ksec->sid = crsec->keycreate_sid;
+	else
+		ksec->sid = crsec->sid;
+
+	return 0;
+}
+
+static int selinux_key_permission(key_ref_t key_ref,
+				  const struct cred *cred,
+				  enum key_need_perm need_perm)
+{
+	struct key *key;
+	struct key_security_struct *ksec;
+	u32 perm, sid;
+
+	switch (need_perm) {
+	case KEY_NEED_VIEW:
+		perm = KEY__VIEW;
+		break;
+	case KEY_NEED_READ:
+		perm = KEY__READ;
+		break;
+	case KEY_NEED_WRITE:
+		perm = KEY__WRITE;
+		break;
+	case KEY_NEED_SEARCH:
+		perm = KEY__SEARCH;
+		break;
+	case KEY_NEED_LINK:
+		perm = KEY__LINK;
+		break;
+	case KEY_NEED_SETATTR:
+		perm = KEY__SETATTR;
+		break;
+	case KEY_NEED_UNLINK:
+	case KEY_SYSADMIN_OVERRIDE:
+	case KEY_AUTHTOKEN_OVERRIDE:
+	case KEY_DEFER_PERM_CHECK:
+		return 0;
+	default:
+		WARN_ON(1);
+		return -EPERM;
+
+	}
+
+	sid = cred_sid(cred);
+	key = key_ref_to_ptr(key_ref);
+	ksec = selinux_key(key);
+
+	return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL);
+}
+
+static int selinux_key_getsecurity(struct key *key, char **_buffer)
+{
+	struct key_security_struct *ksec = selinux_key(key);
+	char *context = NULL;
+	unsigned len;
+	int rc;
+
+	rc = security_sid_to_context(ksec->sid,
+				     &context, &len);
+	if (!rc)
+		rc = len;
+	*_buffer = context;
+	return rc;
+}
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+static int selinux_watch_key(struct key *key)
+{
+	struct key_security_struct *ksec = selinux_key(key);
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, KEY__VIEW, NULL);
+}
+#endif
+#endif
+
+#ifdef CONFIG_SECURITY_INFINIBAND
+static int selinux_ib_pkey_access(void *ib_sec, u64 subnet_prefix, u16 pkey_val)
+{
+	struct common_audit_data ad;
+	int err;
+	u32 sid = 0;
+	struct ib_security_struct *sec = ib_sec;
+	struct lsm_ibpkey_audit ibpkey;
+
+	err = sel_ib_pkey_sid(subnet_prefix, pkey_val, &sid);
+	if (err)
+		return err;
+
+	ad.type = LSM_AUDIT_DATA_IBPKEY;
+	ibpkey.subnet_prefix = subnet_prefix;
+	ibpkey.pkey = pkey_val;
+	ad.u.ibpkey = &ibpkey;
+	return avc_has_perm(sec->sid, sid,
+			    SECCLASS_INFINIBAND_PKEY,
+			    INFINIBAND_PKEY__ACCESS, &ad);
+}
+
+static int selinux_ib_endport_manage_subnet(void *ib_sec, const char *dev_name,
+					    u8 port_num)
+{
+	struct common_audit_data ad;
+	int err;
+	u32 sid = 0;
+	struct ib_security_struct *sec = ib_sec;
+	struct lsm_ibendport_audit ibendport;
+
+	err = security_ib_endport_sid(dev_name, port_num,
+				      &sid);
+
+	if (err)
+		return err;
+
+	ad.type = LSM_AUDIT_DATA_IBENDPORT;
+	ibendport.dev_name = dev_name;
+	ibendport.port = port_num;
+	ad.u.ibendport = &ibendport;
+	return avc_has_perm(sec->sid, sid,
+			    SECCLASS_INFINIBAND_ENDPORT,
+			    INFINIBAND_ENDPORT__MANAGE_SUBNET, &ad);
+}
+
+static int selinux_ib_alloc_security(void *ib_sec)
+{
+	struct ib_security_struct *sec = selinux_ib(ib_sec);
+
+	sec->sid = current_sid();
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_BPF_SYSCALL
+static int selinux_bpf(int cmd, union bpf_attr *attr,
+		       unsigned int size, bool kernel)
+{
+	u32 sid = current_sid();
+	int ret;
+
+	if (selinux_policycap_bpf_token_perms())
+		return 0;
+
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__MAP_CREATE,
+				   NULL);
+		break;
+	case BPF_PROG_LOAD:
+		ret = avc_has_perm(sid, sid, SECCLASS_BPF, BPF__PROG_LOAD,
+				   NULL);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+static u32 bpf_map_fmode_to_av(fmode_t fmode)
+{
+	u32 av = 0;
+
+	if (fmode & FMODE_READ)
+		av |= BPF__MAP_READ;
+	if (fmode & FMODE_WRITE)
+		av |= BPF__MAP_WRITE;
+	return av;
+}
+
+/* This function will check the file pass through unix socket or binder to see
+ * if it is a bpf related object. And apply corresponding checks on the bpf
+ * object based on the type. The bpf maps and programs, not like other files and
+ * socket, are using a shared anonymous inode inside the kernel as their inode.
+ * So checking that inode cannot identify if the process have privilege to
+ * access the bpf object and that's why we have to add this additional check in
+ * selinux_file_receive and selinux_binder_transfer_files.
+ */
+static int bpf_fd_pass(const struct file *file, u32 sid)
+{
+	struct bpf_security_struct *bpfsec;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	int ret;
+
+	if (file->f_op == &bpf_map_fops) {
+		map = file->private_data;
+		bpfsec = selinux_bpf_map_security(map);
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   bpf_map_fmode_to_av(file->f_mode), NULL);
+		if (ret)
+			return ret;
+	} else if (file->f_op == &bpf_prog_fops) {
+		prog = file->private_data;
+		bpfsec = selinux_bpf_prog_security(prog);
+		ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+				   BPF__PROG_RUN, NULL);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = selinux_bpf_map_security(map);
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    bpf_map_fmode_to_av(fmode), NULL);
+}
+
+static int selinux_bpf_prog(struct bpf_prog *prog)
+{
+	u32 sid = current_sid();
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = selinux_bpf_prog_security(prog);
+	return avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF,
+			    BPF__PROG_RUN, NULL);
+}
+
+static u32 selinux_bpffs_creator_sid(u32 fd)
+{
+	struct path path;
+	struct super_block *sb;
+	struct superblock_security_struct *sbsec;
+
+	CLASS(fd, f)(fd);
+
+	if (fd_empty(f))
+		return SECSID_NULL;
+
+	path = fd_file(f)->f_path;
+	sb = path.dentry->d_sb;
+	sbsec = selinux_superblock(sb);
+
+	return sbsec->creator_sid;
+}
+
+static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr,
+				  struct bpf_token *token, bool kernel)
+{
+	struct bpf_security_struct *bpfsec;
+	u32 ssid;
+
+	bpfsec = selinux_bpf_map_security(map);
+	bpfsec->sid = current_sid();
+
+	if (!token)
+		ssid = bpfsec->sid;
+	else
+		ssid = selinux_bpffs_creator_sid(attr->map_token_fd);
+
+	return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__MAP_CREATE,
+			    NULL);
+}
+
+static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr,
+				 struct bpf_token *token, bool kernel)
+{
+	struct bpf_security_struct *bpfsec;
+	u32 ssid;
+
+	bpfsec = selinux_bpf_prog_security(prog);
+	bpfsec->sid = current_sid();
+
+	if (!token)
+		ssid = bpfsec->sid;
+	else
+		ssid = selinux_bpffs_creator_sid(attr->prog_token_fd);
+
+	return avc_has_perm(ssid, bpfsec->sid, SECCLASS_BPF, BPF__PROG_LOAD,
+			    NULL);
+}
+
+#define bpf_token_cmd(T, C) \
+	((T)->allowed_cmds & (1ULL << (C)))
+
+static int selinux_bpf_token_create(struct bpf_token *token,
+				    union bpf_attr *attr,
+				    const struct path *path)
+{
+	struct bpf_security_struct *bpfsec;
+	u32 sid = selinux_bpffs_creator_sid(attr->token_create.bpffs_fd);
+	int err;
+
+	bpfsec = selinux_bpf_token_security(token);
+	bpfsec->sid = current_sid();
+	bpfsec->grantor_sid = sid;
+
+	bpfsec->perms = 0;
+	/**
+	 * 'token->allowed_cmds' is a bit mask of allowed commands
+	 * Convert the BPF command enum to a bitmask representing its position
+	 * in the allowed_cmds bitmap.
+	 */
+	if (bpf_token_cmd(token, BPF_MAP_CREATE)) {
+		err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF,
+				   BPF__MAP_CREATE_AS, NULL);
+		if (err)
+			return err;
+		bpfsec->perms |= BPF__MAP_CREATE;
+	}
+	if (bpf_token_cmd(token, BPF_PROG_LOAD)) {
+		err = avc_has_perm(bpfsec->sid, sid, SECCLASS_BPF,
+				   BPF__PROG_LOAD_AS, NULL);
+		if (err)
+			return err;
+		bpfsec->perms |= BPF__PROG_LOAD;
+	}
+
+	return 0;
+}
+
+static int selinux_bpf_token_cmd(const struct bpf_token *token,
+				 enum bpf_cmd cmd)
+{
+	struct bpf_security_struct *bpfsec;
+
+	bpfsec = token->security;
+	switch (cmd) {
+	case BPF_MAP_CREATE:
+		if (!(bpfsec->perms & BPF__MAP_CREATE))
+			return -EACCES;
+		break;
+	case BPF_PROG_LOAD:
+		if (!(bpfsec->perms & BPF__PROG_LOAD))
+			return -EACCES;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int selinux_bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	u16 sclass;
+	struct bpf_security_struct *bpfsec = token->security;
+	bool initns = (token->userns == &init_user_ns);
+	u32 av = CAP_TO_MASK(cap);
+
+	switch (CAP_TO_INDEX(cap)) {
+	case 0:
+		sclass = initns ? SECCLASS_CAPABILITY : SECCLASS_CAP_USERNS;
+		break;
+	case 1:
+		sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS;
+		break;
+	default:
+		pr_err("SELinux:  out of range capability %d\n", cap);
+		return -EINVAL;
+	}
+
+	return avc_has_perm(current_sid(), bpfsec->grantor_sid, sclass, av,
+			    NULL);
+}
+#endif
+
+#ifdef CONFIG_PERF_EVENTS
+static int selinux_perf_event_open(int type)
+{
+	u32 requested, sid = current_sid();
+
+	if (type == PERF_SECURITY_OPEN)
+		requested = PERF_EVENT__OPEN;
+	else if (type == PERF_SECURITY_CPU)
+		requested = PERF_EVENT__CPU;
+	else if (type == PERF_SECURITY_KERNEL)
+		requested = PERF_EVENT__KERNEL;
+	else if (type == PERF_SECURITY_TRACEPOINT)
+		requested = PERF_EVENT__TRACEPOINT;
+	else
+		return -EINVAL;
+
+	return avc_has_perm(sid, sid, SECCLASS_PERF_EVENT,
+			    requested, NULL);
+}
+
+static int selinux_perf_event_alloc(struct perf_event *event)
+{
+	struct perf_event_security_struct *perfsec;
+
+	perfsec = selinux_perf_event(event->security);
+	perfsec->sid = current_sid();
+
+	return 0;
+}
+
+static int selinux_perf_event_read(struct perf_event *event)
+{
+	struct perf_event_security_struct *perfsec = event->security;
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, perfsec->sid,
+			    SECCLASS_PERF_EVENT, PERF_EVENT__READ, NULL);
+}
+
+static int selinux_perf_event_write(struct perf_event *event)
+{
+	struct perf_event_security_struct *perfsec = event->security;
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, perfsec->sid,
+			    SECCLASS_PERF_EVENT, PERF_EVENT__WRITE, NULL);
+}
+#endif
+
+#ifdef CONFIG_IO_URING
+/**
+ * selinux_uring_override_creds - check the requested cred override
+ * @new: the target creds
+ *
+ * Check to see if the current task is allowed to override it's credentials
+ * to service an io_uring operation.
+ */
+static int selinux_uring_override_creds(const struct cred *new)
+{
+	return avc_has_perm(current_sid(), cred_sid(new),
+			    SECCLASS_IO_URING, IO_URING__OVERRIDE_CREDS, NULL);
+}
+
+/**
+ * selinux_uring_sqpoll - check if a io_uring polling thread can be created
+ *
+ * Check to see if the current task is allowed to create a new io_uring
+ * kernel polling thread.
+ */
+static int selinux_uring_sqpoll(void)
+{
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, sid,
+			    SECCLASS_IO_URING, IO_URING__SQPOLL, NULL);
+}
+
+/**
+ * selinux_uring_cmd - check if IORING_OP_URING_CMD is allowed
+ * @ioucmd: the io_uring command structure
+ *
+ * Check to see if the current domain is allowed to execute an
+ * IORING_OP_URING_CMD against the device/file specified in @ioucmd.
+ *
+ */
+static int selinux_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	struct file *file = ioucmd->file;
+	struct inode *inode = file_inode(file);
+	struct inode_security_struct *isec = selinux_inode(inode);
+	struct common_audit_data ad;
+
+	ad.type = LSM_AUDIT_DATA_FILE;
+	ad.u.file = file;
+
+	return avc_has_perm(current_sid(), isec->sid,
+			    SECCLASS_IO_URING, IO_URING__CMD, &ad);
+}
+
+/**
+ * selinux_uring_allowed - check if io_uring_setup() can be called
+ *
+ * Check to see if the current task is allowed to call io_uring_setup().
+ */
+static int selinux_uring_allowed(void)
+{
+	u32 sid = current_sid();
+
+	return avc_has_perm(sid, sid, SECCLASS_IO_URING, IO_URING__ALLOWED,
+			    NULL);
+}
+#endif /* CONFIG_IO_URING */
+
+static const struct lsm_id selinux_lsmid = {
+	.name = "selinux",
+	.id = LSM_ID_SELINUX,
+};
+
+struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = {
+	.lbs_cred = sizeof(struct cred_security_struct),
+	.lbs_task = sizeof(struct task_security_struct),
+	.lbs_file = sizeof(struct file_security_struct),
+	.lbs_backing_file = sizeof(struct backing_file_security_struct),
+	.lbs_inode = sizeof(struct inode_security_struct),
+	.lbs_ipc = sizeof(struct ipc_security_struct),
+	.lbs_key = sizeof(struct key_security_struct),
+	.lbs_msg_msg = sizeof(struct msg_security_struct),
+#ifdef CONFIG_PERF_EVENTS
+	.lbs_perf_event = sizeof(struct perf_event_security_struct),
+#endif
+	.lbs_sock = sizeof(struct sk_security_struct),
+	.lbs_superblock = sizeof(struct superblock_security_struct),
+	.lbs_xattr_count = SELINUX_INODE_INIT_XATTRS,
+	.lbs_tun_dev = sizeof(struct tun_security_struct),
+	.lbs_ib = sizeof(struct ib_security_struct),
+	.lbs_bpf_map = sizeof(struct bpf_security_struct),
+	.lbs_bpf_prog = sizeof(struct bpf_security_struct),
+	.lbs_bpf_token = sizeof(struct bpf_security_struct),
+};
+
+/*
+ * IMPORTANT NOTE: When adding new hooks, please be careful to keep this order:
+ * 1. any hooks that don't belong to (2.) or (3.) below,
+ * 2. hooks that both access structures allocated by other hooks, and allocate
+ *    structures that can be later accessed by other hooks (mostly "cloning"
+ *    hooks),
+ * 3. hooks that only allocate structures that can be later accessed by other
+ *    hooks ("allocating" hooks).
+ *
+ * Please follow block comment delimiters in the list to keep this order.
+ */
+static struct security_hook_list selinux_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(binder_set_context_mgr, selinux_binder_set_context_mgr),
+	LSM_HOOK_INIT(binder_transaction, selinux_binder_transaction),
+	LSM_HOOK_INIT(binder_transfer_binder, selinux_binder_transfer_binder),
+	LSM_HOOK_INIT(binder_transfer_file, selinux_binder_transfer_file),
+
+	LSM_HOOK_INIT(ptrace_access_check, selinux_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, selinux_ptrace_traceme),
+	LSM_HOOK_INIT(capget, selinux_capget),
+	LSM_HOOK_INIT(capset, selinux_capset),
+	LSM_HOOK_INIT(capable, selinux_capable),
+	LSM_HOOK_INIT(quotactl, selinux_quotactl),
+	LSM_HOOK_INIT(quota_on, selinux_quota_on),
+	LSM_HOOK_INIT(syslog, selinux_syslog),
+	LSM_HOOK_INIT(vm_enough_memory, selinux_vm_enough_memory),
+
+	LSM_HOOK_INIT(netlink_send, selinux_netlink_send),
+
+	LSM_HOOK_INIT(bprm_creds_for_exec, selinux_bprm_creds_for_exec),
+	LSM_HOOK_INIT(bprm_committing_creds, selinux_bprm_committing_creds),
+	LSM_HOOK_INIT(bprm_committed_creds, selinux_bprm_committed_creds),
+
+	LSM_HOOK_INIT(sb_free_mnt_opts, selinux_free_mnt_opts),
+	LSM_HOOK_INIT(sb_mnt_opts_compat, selinux_sb_mnt_opts_compat),
+	LSM_HOOK_INIT(sb_remount, selinux_sb_remount),
+	LSM_HOOK_INIT(sb_kern_mount, selinux_sb_kern_mount),
+	LSM_HOOK_INIT(sb_show_options, selinux_sb_show_options),
+	LSM_HOOK_INIT(sb_statfs, selinux_sb_statfs),
+	LSM_HOOK_INIT(sb_mount, selinux_mount),
+	LSM_HOOK_INIT(sb_umount, selinux_umount),
+	LSM_HOOK_INIT(sb_set_mnt_opts, selinux_set_mnt_opts),
+	LSM_HOOK_INIT(sb_clone_mnt_opts, selinux_sb_clone_mnt_opts),
+
+	LSM_HOOK_INIT(move_mount, selinux_move_mount),
+
+	LSM_HOOK_INIT(dentry_init_security, selinux_dentry_init_security),
+	LSM_HOOK_INIT(dentry_create_files_as, selinux_dentry_create_files_as),
+
+	LSM_HOOK_INIT(inode_free_security, selinux_inode_free_security),
+	LSM_HOOK_INIT(inode_init_security, selinux_inode_init_security),
+	LSM_HOOK_INIT(inode_init_security_anon, selinux_inode_init_security_anon),
+	LSM_HOOK_INIT(inode_create, selinux_inode_create),
+	LSM_HOOK_INIT(inode_link, selinux_inode_link),
+	LSM_HOOK_INIT(inode_unlink, selinux_inode_unlink),
+	LSM_HOOK_INIT(inode_symlink, selinux_inode_symlink),
+	LSM_HOOK_INIT(inode_mkdir, selinux_inode_mkdir),
+	LSM_HOOK_INIT(inode_rmdir, selinux_inode_rmdir),
+	LSM_HOOK_INIT(inode_mknod, selinux_inode_mknod),
+	LSM_HOOK_INIT(inode_rename, selinux_inode_rename),
+	LSM_HOOK_INIT(inode_readlink, selinux_inode_readlink),
+	LSM_HOOK_INIT(inode_follow_link, selinux_inode_follow_link),
+	LSM_HOOK_INIT(inode_permission, selinux_inode_permission),
+	LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr),
+	LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr),
+	LSM_HOOK_INIT(inode_xattr_skipcap, selinux_inode_xattr_skipcap),
+	LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr),
+	LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr),
+	LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr),
+	LSM_HOOK_INIT(inode_listxattr, selinux_inode_listxattr),
+	LSM_HOOK_INIT(inode_removexattr, selinux_inode_removexattr),
+	LSM_HOOK_INIT(inode_file_getattr, selinux_inode_file_getattr),
+	LSM_HOOK_INIT(inode_file_setattr, selinux_inode_file_setattr),
+	LSM_HOOK_INIT(inode_set_acl, selinux_inode_set_acl),
+	LSM_HOOK_INIT(inode_get_acl, selinux_inode_get_acl),
+	LSM_HOOK_INIT(inode_remove_acl, selinux_inode_remove_acl),
+	LSM_HOOK_INIT(inode_getsecurity, selinux_inode_getsecurity),
+	LSM_HOOK_INIT(inode_setsecurity, selinux_inode_setsecurity),
+	LSM_HOOK_INIT(inode_listsecurity, selinux_inode_listsecurity),
+	LSM_HOOK_INIT(inode_getlsmprop, selinux_inode_getlsmprop),
+	LSM_HOOK_INIT(inode_copy_up, selinux_inode_copy_up),
+	LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr),
+	LSM_HOOK_INIT(path_notify, selinux_path_notify),
+
+	LSM_HOOK_INIT(kernfs_init_security, selinux_kernfs_init_security),
+
+	LSM_HOOK_INIT(file_permission, selinux_file_permission),
+	LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
+	LSM_HOOK_INIT(backing_file_alloc, selinux_backing_file_alloc),
+	LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
+	LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
+	LSM_HOOK_INIT(mmap_backing_file, selinux_mmap_backing_file),
+	LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
+	LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
+	LSM_HOOK_INIT(file_lock, selinux_file_lock),
+	LSM_HOOK_INIT(file_fcntl, selinux_file_fcntl),
+	LSM_HOOK_INIT(file_set_fowner, selinux_file_set_fowner),
+	LSM_HOOK_INIT(file_send_sigiotask, selinux_file_send_sigiotask),
+	LSM_HOOK_INIT(file_receive, selinux_file_receive),
+
+	LSM_HOOK_INIT(file_open, selinux_file_open),
+
+	LSM_HOOK_INIT(task_alloc, selinux_task_alloc),
+	LSM_HOOK_INIT(cred_prepare, selinux_cred_prepare),
+	LSM_HOOK_INIT(cred_transfer, selinux_cred_transfer),
+	LSM_HOOK_INIT(cred_getsecid, selinux_cred_getsecid),
+	LSM_HOOK_INIT(cred_getlsmprop, selinux_cred_getlsmprop),
+	LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as),
+	LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as),
+	LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request),
+	LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data),
+	LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file),
+	LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid),
+	LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid),
+	LSM_HOOK_INIT(task_getsid, selinux_task_getsid),
+	LSM_HOOK_INIT(current_getlsmprop_subj, selinux_current_getlsmprop_subj),
+	LSM_HOOK_INIT(task_getlsmprop_obj, selinux_task_getlsmprop_obj),
+	LSM_HOOK_INIT(task_setnice, selinux_task_setnice),
+	LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio),
+	LSM_HOOK_INIT(task_getioprio, selinux_task_getioprio),
+	LSM_HOOK_INIT(task_prlimit, selinux_task_prlimit),
+	LSM_HOOK_INIT(task_setrlimit, selinux_task_setrlimit),
+	LSM_HOOK_INIT(task_setscheduler, selinux_task_setscheduler),
+	LSM_HOOK_INIT(task_getscheduler, selinux_task_getscheduler),
+	LSM_HOOK_INIT(task_movememory, selinux_task_movememory),
+	LSM_HOOK_INIT(task_kill, selinux_task_kill),
+	LSM_HOOK_INIT(task_to_inode, selinux_task_to_inode),
+	LSM_HOOK_INIT(userns_create, selinux_userns_create),
+
+	LSM_HOOK_INIT(ipc_permission, selinux_ipc_permission),
+	LSM_HOOK_INIT(ipc_getlsmprop, selinux_ipc_getlsmprop),
+
+	LSM_HOOK_INIT(msg_queue_associate, selinux_msg_queue_associate),
+	LSM_HOOK_INIT(msg_queue_msgctl, selinux_msg_queue_msgctl),
+	LSM_HOOK_INIT(msg_queue_msgsnd, selinux_msg_queue_msgsnd),
+	LSM_HOOK_INIT(msg_queue_msgrcv, selinux_msg_queue_msgrcv),
+
+	LSM_HOOK_INIT(shm_associate, selinux_shm_associate),
+	LSM_HOOK_INIT(shm_shmctl, selinux_shm_shmctl),
+	LSM_HOOK_INIT(shm_shmat, selinux_shm_shmat),
+
+	LSM_HOOK_INIT(sem_associate, selinux_sem_associate),
+	LSM_HOOK_INIT(sem_semctl, selinux_sem_semctl),
+	LSM_HOOK_INIT(sem_semop, selinux_sem_semop),
+
+	LSM_HOOK_INIT(d_instantiate, selinux_d_instantiate),
+
+	LSM_HOOK_INIT(getselfattr, selinux_getselfattr),
+	LSM_HOOK_INIT(setselfattr, selinux_setselfattr),
+	LSM_HOOK_INIT(getprocattr, selinux_getprocattr),
+	LSM_HOOK_INIT(setprocattr, selinux_setprocattr),
+
+	LSM_HOOK_INIT(ismaclabel, selinux_ismaclabel),
+	LSM_HOOK_INIT(secctx_to_secid, selinux_secctx_to_secid),
+	LSM_HOOK_INIT(release_secctx, selinux_release_secctx),
+	LSM_HOOK_INIT(inode_invalidate_secctx, selinux_inode_invalidate_secctx),
+	LSM_HOOK_INIT(inode_notifysecctx, selinux_inode_notifysecctx),
+	LSM_HOOK_INIT(inode_setsecctx, selinux_inode_setsecctx),
+
+	LSM_HOOK_INIT(unix_stream_connect, selinux_socket_unix_stream_connect),
+	LSM_HOOK_INIT(unix_may_send, selinux_socket_unix_may_send),
+
+	LSM_HOOK_INIT(socket_create, selinux_socket_create),
+	LSM_HOOK_INIT(socket_post_create, selinux_socket_post_create),
+	LSM_HOOK_INIT(socket_socketpair, selinux_socket_socketpair),
+	LSM_HOOK_INIT(socket_bind, selinux_socket_bind),
+	LSM_HOOK_INIT(socket_connect, selinux_socket_connect),
+	LSM_HOOK_INIT(socket_listen, selinux_socket_listen),
+	LSM_HOOK_INIT(socket_accept, selinux_socket_accept),
+	LSM_HOOK_INIT(socket_sendmsg, selinux_socket_sendmsg),
+	LSM_HOOK_INIT(socket_recvmsg, selinux_socket_recvmsg),
+	LSM_HOOK_INIT(socket_getsockname, selinux_socket_getsockname),
+	LSM_HOOK_INIT(socket_getpeername, selinux_socket_getpeername),
+	LSM_HOOK_INIT(socket_getsockopt, selinux_socket_getsockopt),
+	LSM_HOOK_INIT(socket_setsockopt, selinux_socket_setsockopt),
+	LSM_HOOK_INIT(socket_shutdown, selinux_socket_shutdown),
+	LSM_HOOK_INIT(socket_sock_rcv_skb, selinux_socket_sock_rcv_skb),
+	LSM_HOOK_INIT(socket_getpeersec_stream,
+			selinux_socket_getpeersec_stream),
+	LSM_HOOK_INIT(socket_getpeersec_dgram, selinux_socket_getpeersec_dgram),
+	LSM_HOOK_INIT(sk_free_security, selinux_sk_free_security),
+	LSM_HOOK_INIT(sk_clone_security, selinux_sk_clone_security),
+	LSM_HOOK_INIT(sk_getsecid, selinux_sk_getsecid),
+	LSM_HOOK_INIT(sock_graft, selinux_sock_graft),
+	LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request),
+	LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone),
+	LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect),
+	LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established),
+	LSM_HOOK_INIT(mptcp_add_subflow, selinux_mptcp_add_subflow),
+	LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request),
+	LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone),
+	LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established),
+	LSM_HOOK_INIT(secmark_relabel_packet, selinux_secmark_relabel_packet),
+	LSM_HOOK_INIT(secmark_refcount_inc, selinux_secmark_refcount_inc),
+	LSM_HOOK_INIT(secmark_refcount_dec, selinux_secmark_refcount_dec),
+	LSM_HOOK_INIT(req_classify_flow, selinux_req_classify_flow),
+	LSM_HOOK_INIT(tun_dev_create, selinux_tun_dev_create),
+	LSM_HOOK_INIT(tun_dev_attach_queue, selinux_tun_dev_attach_queue),
+	LSM_HOOK_INIT(tun_dev_attach, selinux_tun_dev_attach),
+	LSM_HOOK_INIT(tun_dev_open, selinux_tun_dev_open),
+#ifdef CONFIG_SECURITY_INFINIBAND
+	LSM_HOOK_INIT(ib_pkey_access, selinux_ib_pkey_access),
+	LSM_HOOK_INIT(ib_endport_manage_subnet,
+		      selinux_ib_endport_manage_subnet),
+#endif
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+	LSM_HOOK_INIT(xfrm_policy_free_security, selinux_xfrm_policy_free),
+	LSM_HOOK_INIT(xfrm_policy_delete_security, selinux_xfrm_policy_delete),
+	LSM_HOOK_INIT(xfrm_state_free_security, selinux_xfrm_state_free),
+	LSM_HOOK_INIT(xfrm_state_delete_security, selinux_xfrm_state_delete),
+	LSM_HOOK_INIT(xfrm_policy_lookup, selinux_xfrm_policy_lookup),
+	LSM_HOOK_INIT(xfrm_state_pol_flow_match,
+			selinux_xfrm_state_pol_flow_match),
+	LSM_HOOK_INIT(xfrm_decode_session, selinux_xfrm_decode_session),
+#endif
+
+#ifdef CONFIG_KEYS
+	LSM_HOOK_INIT(key_permission, selinux_key_permission),
+	LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity),
+#ifdef CONFIG_KEY_NOTIFICATIONS
+	LSM_HOOK_INIT(watch_key, selinux_watch_key),
+#endif
+#endif
+
+#ifdef CONFIG_AUDIT
+	LSM_HOOK_INIT(audit_rule_known, selinux_audit_rule_known),
+	LSM_HOOK_INIT(audit_rule_match, selinux_audit_rule_match),
+	LSM_HOOK_INIT(audit_rule_free, selinux_audit_rule_free),
+#endif
+
+#ifdef CONFIG_BPF_SYSCALL
+	LSM_HOOK_INIT(bpf, selinux_bpf),
+	LSM_HOOK_INIT(bpf_map, selinux_bpf_map),
+	LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog),
+#endif
+
+#ifdef CONFIG_PERF_EVENTS
+	LSM_HOOK_INIT(perf_event_open, selinux_perf_event_open),
+	LSM_HOOK_INIT(perf_event_read, selinux_perf_event_read),
+	LSM_HOOK_INIT(perf_event_write, selinux_perf_event_write),
+#endif
+
+#ifdef CONFIG_IO_URING
+	LSM_HOOK_INIT(uring_override_creds, selinux_uring_override_creds),
+	LSM_HOOK_INIT(uring_sqpoll, selinux_uring_sqpoll),
+	LSM_HOOK_INIT(uring_cmd, selinux_uring_cmd),
+	LSM_HOOK_INIT(uring_allowed, selinux_uring_allowed),
+#endif
+
+	/*
+	 * PUT "CLONING" (ACCESSING + ALLOCATING) HOOKS HERE
+	 */
+	LSM_HOOK_INIT(fs_context_submount, selinux_fs_context_submount),
+	LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup),
+	LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param),
+	LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts),
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+	LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone),
+#endif
+
+	/*
+	 * PUT "ALLOCATING" HOOKS HERE
+	 */
+	LSM_HOOK_INIT(msg_msg_alloc_security, selinux_msg_msg_alloc_security),
+	LSM_HOOK_INIT(msg_queue_alloc_security,
+		      selinux_msg_queue_alloc_security),
+	LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security),
+	LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security),
+	LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security),
+	LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security),
+	LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx),
+	LSM_HOOK_INIT(lsmprop_to_secctx, selinux_lsmprop_to_secctx),
+	LSM_HOOK_INIT(inode_getsecctx, selinux_inode_getsecctx),
+	LSM_HOOK_INIT(sk_alloc_security, selinux_sk_alloc_security),
+	LSM_HOOK_INIT(tun_dev_alloc_security, selinux_tun_dev_alloc_security),
+#ifdef CONFIG_SECURITY_INFINIBAND
+	LSM_HOOK_INIT(ib_alloc_security, selinux_ib_alloc_security),
+#endif
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+	LSM_HOOK_INIT(xfrm_policy_alloc_security, selinux_xfrm_policy_alloc),
+	LSM_HOOK_INIT(xfrm_state_alloc, selinux_xfrm_state_alloc),
+	LSM_HOOK_INIT(xfrm_state_alloc_acquire,
+		      selinux_xfrm_state_alloc_acquire),
+#endif
+#ifdef CONFIG_KEYS
+	LSM_HOOK_INIT(key_alloc, selinux_key_alloc),
+#endif
+#ifdef CONFIG_AUDIT
+	LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init),
+#endif
+#ifdef CONFIG_BPF_SYSCALL
+	LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create),
+	LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load),
+	LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create),
+	LSM_HOOK_INIT(bpf_token_cmd, selinux_bpf_token_cmd),
+	LSM_HOOK_INIT(bpf_token_capable, selinux_bpf_token_capable),
+#endif
+#ifdef CONFIG_PERF_EVENTS
+	LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc),
+#endif
+};
+
+static __init int selinux_init(void)
+{
+	vma_flags_t data_default_flags = VMA_DATA_DEFAULT_FLAGS;
+
+	pr_info("SELinux:  Initializing.\n");
+
+	memset(&selinux_state, 0, sizeof(selinux_state));
+	enforcing_set(selinux_enforcing_boot);
+	selinux_avc_init();
+	mutex_init(&selinux_state.status_lock);
+	mutex_init(&selinux_state.policy_mutex);
+
+	/* Set the security state for the initial task. */
+	cred_init_security();
+
+	/* Inform the audit system that secctx is used */
+	audit_cfg_lsm(&selinux_lsmid,
+		      AUDIT_CFG_LSM_SECCTX_SUBJECT |
+		      AUDIT_CFG_LSM_SECCTX_OBJECT);
+
+	default_noexec = !vma_flags_test(&data_default_flags, VMA_EXEC_BIT);
+	if (!default_noexec)
+		pr_notice("SELinux:  virtual memory is executable by default\n");
+
+	avc_init();
+
+	avtab_cache_init();
+
+	ebitmap_cache_init();
+
+	hashtab_cache_init();
+
+	selinux_ima_config_len_init();
+
+	security_add_hooks(selinux_hooks, ARRAY_SIZE(selinux_hooks),
+			   &selinux_lsmid);
+
+	if (avc_add_callback(selinux_netcache_avc_callback, AVC_CALLBACK_RESET))
+		panic("SELinux: Unable to register AVC netcache callback\n");
+
+	if (avc_add_callback(selinux_lsm_notifier_avc_callback, AVC_CALLBACK_RESET))
+		panic("SELinux: Unable to register AVC LSM notifier callback\n");
+
+	if (avc_add_callback(selinux_audit_rule_avc_callback,
+			     AVC_CALLBACK_RESET))
+		panic("SELinux: Unable to register AVC audit callback\n");
+
+	if (selinux_enforcing_boot)
+		pr_debug("SELinux:  Starting in enforcing mode\n");
+	else
+		pr_debug("SELinux:  Starting in permissive mode\n");
+
+	fs_validate_description("selinux", selinux_fs_parameters);
+
+	return 0;
+}
+
+static void delayed_superblock_init(struct super_block *sb, void *unused)
+{
+	selinux_set_mnt_opts(sb, NULL, 0, NULL);
+}
+
+void selinux_complete_init(void)
+{
+	pr_debug("SELinux:  Completing initialization.\n");
+
+	/* Set up any superblocks initialized prior to the policy load. */
+	pr_debug("SELinux:  Setting up existing superblocks.\n");
+	iterate_supers(delayed_superblock_init, NULL);
+}
+
+/* SELinux requires early initialization in order to label
+   all processes and objects when they are created. */
+DEFINE_LSM(selinux) = {
+	.id = &selinux_lsmid,
+	.flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE,
+	.enabled = &selinux_enabled_boot,
+	.blobs = &selinux_blob_sizes,
+	.init = selinux_init,
+	.initcall_device = selinux_initcall,
+};
+
+#if defined(CONFIG_NETFILTER)
+static const struct nf_hook_ops selinux_nf_ops[] = {
+	{
+		.hook =		selinux_ip_postroute,
+		.pf =		NFPROTO_IPV4,
+		.hooknum =	NF_INET_POST_ROUTING,
+		.priority =	NF_IP_PRI_SELINUX_LAST,
+	},
+	{
+		.hook =		selinux_ip_forward,
+		.pf =		NFPROTO_IPV4,
+		.hooknum =	NF_INET_FORWARD,
+		.priority =	NF_IP_PRI_SELINUX_FIRST,
+	},
+	{
+		.hook =		selinux_ip_output,
+		.pf =		NFPROTO_IPV4,
+		.hooknum =	NF_INET_LOCAL_OUT,
+		.priority =	NF_IP_PRI_SELINUX_FIRST,
+	},
+#if IS_ENABLED(CONFIG_IPV6)
+	{
+		.hook =		selinux_ip_postroute,
+		.pf =		NFPROTO_IPV6,
+		.hooknum =	NF_INET_POST_ROUTING,
+		.priority =	NF_IP6_PRI_SELINUX_LAST,
+	},
+	{
+		.hook =		selinux_ip_forward,
+		.pf =		NFPROTO_IPV6,
+		.hooknum =	NF_INET_FORWARD,
+		.priority =	NF_IP6_PRI_SELINUX_FIRST,
+	},
+	{
+		.hook =		selinux_ip_output,
+		.pf =		NFPROTO_IPV6,
+		.hooknum =	NF_INET_LOCAL_OUT,
+		.priority =	NF_IP6_PRI_SELINUX_FIRST,
+	},
+#endif	/* IPV6 */
+};
+
+static int __net_init selinux_nf_register(struct net *net)
+{
+	return nf_register_net_hooks(net, selinux_nf_ops,
+				     ARRAY_SIZE(selinux_nf_ops));
+}
+
+static void __net_exit selinux_nf_unregister(struct net *net)
+{
+	nf_unregister_net_hooks(net, selinux_nf_ops,
+				ARRAY_SIZE(selinux_nf_ops));
+}
+
+static struct pernet_operations selinux_net_ops = {
+	.init = selinux_nf_register,
+	.exit = selinux_nf_unregister,
+};
+
+int __init selinux_nf_ip_init(void)
+{
+	int err;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	pr_debug("SELinux:  Registering netfilter hooks\n");
+
+	err = register_pernet_subsys(&selinux_net_ops);
+	if (err)
+		panic("SELinux: register_pernet_subsys: error %d\n", err);
+
+	return 0;
+}
+#endif /* CONFIG_NETFILTER */
diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c
new file mode 100644
index 000000000..ae09d59aa
--- /dev/null
+++ b/security/selinux/ibpkey.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Pkey table
+ *
+ * SELinux must keep a mapping of Infiniband PKEYs to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead.
+ *
+ * This code is heavily based on the "netif" and "netport" concept originally
+ * developed by
+ * James Morris <jmorris@redhat.com> and
+ * Paul Moore <paul@paul-moore.com>
+ *   (see security/selinux/netif.c and security/selinux/netport.c for more
+ *   information)
+ */
+
+/*
+ * (c) Mellanox Technologies, 2016
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#include "initcalls.h"
+#include "ibpkey.h"
+#include "objsec.h"
+
+#define SEL_PKEY_HASH_SIZE       256
+#define SEL_PKEY_HASH_BKT_LIMIT   16
+
+struct sel_ib_pkey_bkt {
+	int size;
+	struct list_head list;
+};
+
+struct sel_ib_pkey {
+	struct pkey_security_struct psec;
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+static DEFINE_SPINLOCK(sel_ib_pkey_lock);
+static struct sel_ib_pkey_bkt sel_ib_pkey_hash[SEL_PKEY_HASH_SIZE];
+
+/**
+ * sel_ib_pkey_hashfn - Hashing function for the pkey table
+ * @pkey: pkey number
+ *
+ * Description:
+ * This is the hashing function for the pkey table, it returns the bucket
+ * number for the given pkey.
+ *
+ */
+static unsigned int sel_ib_pkey_hashfn(u16 pkey)
+{
+	return (pkey & (SEL_PKEY_HASH_SIZE - 1));
+}
+
+/**
+ * sel_ib_pkey_find - Search for a pkey record
+ * @subnet_prefix: subnet_prefix
+ * @pkey_num: pkey_num
+ *
+ * Description:
+ * Search the pkey table and return the matching record.  If an entry
+ * can not be found in the table return NULL.
+ *
+ */
+static struct sel_ib_pkey *sel_ib_pkey_find(u64 subnet_prefix, u16 pkey_num)
+{
+	unsigned int idx;
+	struct sel_ib_pkey *pkey;
+
+	idx = sel_ib_pkey_hashfn(pkey_num);
+	list_for_each_entry_rcu(pkey, &sel_ib_pkey_hash[idx].list, list) {
+		if (pkey->psec.pkey == pkey_num &&
+		    pkey->psec.subnet_prefix == subnet_prefix)
+			return pkey;
+	}
+
+	return NULL;
+}
+
+/**
+ * sel_ib_pkey_insert - Insert a new pkey into the table
+ * @pkey: the new pkey record
+ *
+ * Description:
+ * Add a new pkey record to the hash table.
+ *
+ */
+static void sel_ib_pkey_insert(struct sel_ib_pkey *pkey)
+{
+	unsigned int idx;
+
+	/* we need to impose a limit on the growth of the hash table so check
+	 * this bucket to make sure it is within the specified bounds
+	 */
+	idx = sel_ib_pkey_hashfn(pkey->psec.pkey);
+	list_add_rcu(&pkey->list, &sel_ib_pkey_hash[idx].list);
+	if (sel_ib_pkey_hash[idx].size == SEL_PKEY_HASH_BKT_LIMIT) {
+		struct sel_ib_pkey *tail;
+
+		tail = list_entry(
+			rcu_dereference_protected(
+				list_tail_rcu(&sel_ib_pkey_hash[idx].list),
+				lockdep_is_held(&sel_ib_pkey_lock)),
+			struct sel_ib_pkey, list);
+		list_del_rcu(&tail->list);
+		kfree_rcu(tail, rcu);
+	} else {
+		sel_ib_pkey_hash[idx].size++;
+	}
+}
+
+/**
+ * sel_ib_pkey_sid_slow - Lookup the SID of a pkey using the policy
+ * @subnet_prefix: subnet prefix
+ * @pkey_num: pkey number
+ * @sid: pkey SID
+ *
+ * Description:
+ * This function determines the SID of a pkey by querying the security
+ * policy.  The result is added to the pkey table to speedup future
+ * queries.  Returns zero on success, negative values on failure.
+ *
+ */
+static int sel_ib_pkey_sid_slow(u64 subnet_prefix, u16 pkey_num, u32 *sid)
+{
+	int ret;
+	struct sel_ib_pkey *pkey;
+	struct sel_ib_pkey *new;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sel_ib_pkey_lock, flags);
+	pkey = sel_ib_pkey_find(subnet_prefix, pkey_num);
+	if (pkey) {
+		*sid = pkey->psec.sid;
+		spin_unlock_irqrestore(&sel_ib_pkey_lock, flags);
+		return 0;
+	}
+
+	ret = security_ib_pkey_sid(subnet_prefix, pkey_num,
+				   sid);
+	if (ret)
+		goto out;
+
+	new = kmalloc_obj(*new, GFP_ATOMIC);
+	if (!new) {
+		/* If this memory allocation fails still return 0. The SID
+		 * is valid, it just won't be added to the cache.
+		 */
+		goto out;
+	}
+
+	new->psec.subnet_prefix = subnet_prefix;
+	new->psec.pkey = pkey_num;
+	new->psec.sid = *sid;
+	sel_ib_pkey_insert(new);
+
+out:
+	spin_unlock_irqrestore(&sel_ib_pkey_lock, flags);
+	return ret;
+}
+
+/**
+ * sel_ib_pkey_sid - Lookup the SID of a PKEY
+ * @subnet_prefix: subnet_prefix
+ * @pkey_num: pkey number
+ * @sid: pkey SID
+ *
+ * Description:
+ * This function determines the SID of a PKEY using the fastest method
+ * possible.  First the pkey table is queried, but if an entry can't be found
+ * then the policy is queried and the result is added to the table to speedup
+ * future queries.  Returns zero on success, negative values on failure.
+ *
+ */
+int sel_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *sid)
+{
+	struct sel_ib_pkey *pkey;
+
+	rcu_read_lock();
+	pkey = sel_ib_pkey_find(subnet_prefix, pkey_num);
+	if (likely(pkey)) {
+		*sid = pkey->psec.sid;
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+
+	return sel_ib_pkey_sid_slow(subnet_prefix, pkey_num, sid);
+}
+
+/**
+ * sel_ib_pkey_flush - Flush the entire pkey table
+ *
+ * Description:
+ * Remove all entries from the pkey table
+ *
+ */
+void sel_ib_pkey_flush(void)
+{
+	unsigned int idx;
+	struct sel_ib_pkey *pkey, *pkey_tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sel_ib_pkey_lock, flags);
+	for (idx = 0; idx < SEL_PKEY_HASH_SIZE; idx++) {
+		list_for_each_entry_safe(pkey, pkey_tmp,
+					 &sel_ib_pkey_hash[idx].list, list) {
+			list_del_rcu(&pkey->list);
+			kfree_rcu(pkey, rcu);
+		}
+		sel_ib_pkey_hash[idx].size = 0;
+	}
+	spin_unlock_irqrestore(&sel_ib_pkey_lock, flags);
+}
+
+int __init sel_ib_pkey_init(void)
+{
+	int iter;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	for (iter = 0; iter < SEL_PKEY_HASH_SIZE; iter++) {
+		INIT_LIST_HEAD(&sel_ib_pkey_hash[iter].list);
+		sel_ib_pkey_hash[iter].size = 0;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/ima.c b/security/selinux/ima.c
new file mode 100644
index 000000000..cda68122e
--- /dev/null
+++ b/security/selinux/ima.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2021 Microsoft Corporation
+ *
+ * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
+ *
+ * Measure critical data structures maintained by SELinux
+ * using IMA subsystem.
+ */
+#include <linux/vmalloc.h>
+#include <linux/ima.h>
+#include <linux/seq_buf.h>
+#include "security.h"
+#include "ima.h"
+
+static int selinux_ima_config_len __ro_after_init;
+
+/*
+ * selinux_ima_config_len_init - Compute the configuration settings string length
+ *
+ * The string is fixed text plus one digit per setting, so its length
+ * is known at boot.
+ */
+void __init selinux_ima_config_len_init(void)
+{
+	int buf_len, suffix_len, i;
+
+	buf_len = strlen("initialized=0;enforcing=0;checkreqprot=0;") + 1;
+	suffix_len = strlen("=0;");
+
+	for (i = 0; i < __POLICYDB_CAP_MAX; i++)
+		buf_len += strlen(selinux_policycap_names[i]) + suffix_len;
+
+	selinux_ima_config_len = buf_len;
+}
+
+/*
+ * selinux_ima_collect_state - Read selinux configuration settings
+ *
+ * On success returns the configuration settings string.
+ * On error, returns NULL.
+ */
+static char *selinux_ima_collect_state(void)
+{
+	struct seq_buf s;
+	char *buf;
+	int i;
+
+	buf = kzalloc(selinux_ima_config_len, GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	seq_buf_init(&s, buf, selinux_ima_config_len);
+
+	seq_buf_printf(&s, "initialized=%d;enforcing=%d;checkreqprot=%d;",
+		       selinux_initialized(), enforcing_enabled(),
+		       checkreqprot_get());
+
+	for (i = 0; i < __POLICYDB_CAP_MAX; i++)
+		seq_buf_printf(&s, "%s=%d;", selinux_policycap_names[i],
+			       selinux_state.policycap[i]);
+
+	WARN_ON(seq_buf_has_overflowed(&s));
+
+	return buf;
+}
+
+/*
+ * selinux_ima_measure_state_locked - Measure SELinux state and hash of policy
+ */
+void selinux_ima_measure_state_locked(void)
+{
+	char *state_str = NULL;
+	void *policy = NULL;
+	size_t policy_len;
+	int rc = 0;
+
+	lockdep_assert_held(&selinux_state.policy_mutex);
+
+	state_str = selinux_ima_collect_state();
+	if (!state_str) {
+		pr_err("SELinux: %s: failed to read state.\n", __func__);
+		return;
+	}
+
+	ima_measure_critical_data("selinux", "selinux-state",
+				  state_str, strlen(state_str), false,
+				  NULL, 0);
+
+	kfree(state_str);
+
+	/*
+	 * Measure SELinux policy only after initialization is completed.
+	 */
+	if (!selinux_initialized())
+		return;
+
+	rc = security_read_state_kernel(&policy, &policy_len);
+	if (rc) {
+		pr_err("SELinux: %s: failed to read policy %d.\n", __func__, rc);
+		return;
+	}
+
+	ima_measure_critical_data("selinux", "selinux-policy-hash",
+				  policy, policy_len, true,
+				  NULL, 0);
+
+	vfree(policy);
+}
+
+/*
+ * selinux_ima_measure_state - Measure SELinux state and hash of policy
+ */
+void selinux_ima_measure_state(void)
+{
+	lockdep_assert_not_held(&selinux_state.policy_mutex);
+
+	mutex_lock(&selinux_state.policy_mutex);
+	selinux_ima_measure_state_locked();
+	mutex_unlock(&selinux_state.policy_mutex);
+}
diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h
new file mode 100644
index 000000000..85a531ac7
--- /dev/null
+++ b/security/selinux/include/audit.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * SELinux support for the Audit LSM hooks
+ *
+ * Author: James Morris <jmorris@redhat.com>
+ *
+ * Copyright (C) 2005 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ * Copyright (C) 2006 Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ * Copyright (C) 2006 IBM Corporation, Timothy R. Chavez <tinytim@us.ibm.com>
+ */
+
+#ifndef _SELINUX_AUDIT_H
+#define _SELINUX_AUDIT_H
+
+#include <linux/audit.h>
+#include <linux/types.h>
+
+/**
+ * selinux_audit_rule_avc_callback - update the audit LSM rules on AVC events.
+ * @event: the AVC event
+ *
+ * Update any audit LSM rules based on the AVC event specified in @event.
+ * Returns 0 on success, negative values otherwise.
+ */
+int selinux_audit_rule_avc_callback(u32 event);
+
+/**
+ * selinux_audit_rule_init - alloc/init an selinux audit rule structure.
+ * @field: the field this rule refers to
+ * @op: the operator the rule uses
+ * @rulestr: the text "target" of the rule
+ * @rule: pointer to the new rule structure returned via this
+ * @gfp: GFP flag used for kmalloc
+ *
+ * Returns 0 if successful, -errno if not.  On success, the rule structure
+ * will be allocated internally.  The caller must free this structure with
+ * selinux_audit_rule_free() after use.
+ */
+int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule,
+			    gfp_t gfp);
+
+/**
+ * selinux_audit_rule_free - free an selinux audit rule structure.
+ * @rule: pointer to the audit rule to be freed
+ *
+ * This will free all memory associated with the given rule.
+ * If @rule is NULL, no operation is performed.
+ */
+void selinux_audit_rule_free(void *rule);
+
+/**
+ * selinux_audit_rule_match - determine if a context ID matches a rule.
+ * @prop: includes the context ID to check
+ * @field: the field this rule refers to
+ * @op: the operator the rule uses
+ * @rule: pointer to the audit rule to check against
+ *
+ * Returns 1 if the context id matches the rule, 0 if it does not, and
+ * -errno on failure.
+ */
+int selinux_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op,
+			     void *rule);
+
+/**
+ * selinux_audit_rule_known - check to see if rule contains selinux fields.
+ * @rule: rule to be checked
+ * Returns 1 if there are selinux fields specified in the rule, 0 otherwise.
+ */
+int selinux_audit_rule_known(struct audit_krule *rule);
+
+#endif /* _SELINUX_AUDIT_H */
diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h
new file mode 100644
index 000000000..01b5167fe
--- /dev/null
+++ b/security/selinux/include/avc.h
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Access vector cache interface for object managers.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SELINUX_AVC_H_
+#define _SELINUX_AVC_H_
+
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kdev_t.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/audit.h>
+#include <linux/lsm_audit.h>
+#include <linux/in6.h>
+#include "flask.h"
+#include "av_permissions.h"
+#include "security.h"
+
+/*
+ * An entry in the AVC.
+ */
+struct avc_entry;
+
+struct task_struct;
+struct inode;
+struct sock;
+struct sk_buff;
+
+/*
+ * AVC statistics
+ */
+struct avc_cache_stats {
+	unsigned int lookups;
+	unsigned int misses;
+	unsigned int allocations;
+	unsigned int reclaims;
+	unsigned int frees;
+};
+
+/*
+ * We only need this data after we have decided to send an audit message.
+ */
+struct selinux_audit_data {
+	u32 ssid;
+	u32 tsid;
+	u16 tclass;
+	u32 requested;
+	u32 audited;
+	u32 denied;
+	int result;
+} __randomize_layout;
+
+/*
+ * AVC operations
+ */
+
+void __init avc_init(void);
+
+static inline u32 avc_audit_required(u32 requested, struct av_decision *avd,
+				     int result, u32 auditdeny, u32 *deniedp)
+{
+	u32 denied, audited;
+
+	if (avd->flags & AVD_FLAGS_NEVERAUDIT)
+		return 0;
+
+	denied = requested & ~avd->allowed;
+	if (unlikely(denied)) {
+		audited = denied & avd->auditdeny;
+		/*
+		 * auditdeny is TRICKY!  Setting a bit in
+		 * this field means that ANY denials should NOT be audited if
+		 * the policy contains an explicit dontaudit rule for that
+		 * permission.  Take notice that this is unrelated to the
+		 * actual permissions that were denied.  As an example lets
+		 * assume:
+		 *
+		 * denied == READ
+		 * avd.auditdeny & ACCESS == 0 (not set means explicit rule)
+		 * auditdeny & ACCESS == 1
+		 *
+		 * We will NOT audit the denial even though the denied
+		 * permission was READ and the auditdeny checks were for
+		 * ACCESS
+		 */
+		if (auditdeny && !(auditdeny & avd->auditdeny))
+			audited = 0;
+	} else if (result)
+		audited = denied = requested;
+	else
+		audited = requested & avd->auditallow;
+	*deniedp = denied;
+	return audited;
+}
+
+int slow_avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited,
+		   u32 denied, int result, struct common_audit_data *a);
+
+/**
+ * avc_audit - Audit the granting or denial of permissions.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @requested: requested permissions
+ * @avd: access vector decisions
+ * @result: result from avc_has_perm_noaudit
+ * @a:  auxiliary audit data
+ *
+ * Audit the granting or denial of permissions in accordance
+ * with the policy.  This function is typically called by
+ * avc_has_perm() after a permission check, but can also be
+ * called directly by callers who use avc_has_perm_noaudit()
+ * in order to separate the permission check from the auditing.
+ * For example, this separation is useful when the permission check must
+ * be performed under a lock, to allow the lock to be released
+ * before calling the auditing code.
+ */
+static inline int avc_audit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			    struct av_decision *avd, int result,
+			    struct common_audit_data *a)
+{
+	u32 audited, denied;
+	audited = avc_audit_required(requested, avd, result, 0, &denied);
+	if (likely(!audited))
+		return 0;
+	return slow_avc_audit(ssid, tsid, tclass, requested, audited, denied,
+			      result, a);
+}
+
+#define AVC_STRICT	   1 /* Ignore permissive mode. */
+#define AVC_EXTENDED_PERMS 2 /* update extended permissions */
+int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			 unsigned int flags, struct av_decision *avd);
+
+int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+		 struct common_audit_data *auditdata);
+
+#define AVC_EXT_IOCTL	(1 << 0) /* Cache entry for an ioctl extended permission */
+#define AVC_EXT_NLMSG	(1 << 1) /* Cache entry for an nlmsg extended permission */
+int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested,
+			   u8 driver, u8 base_perm, u8 perm,
+			   struct common_audit_data *ad);
+
+u32 avc_policy_seqno(void);
+
+#define AVC_CALLBACK_GRANT		1
+#define AVC_CALLBACK_TRY_REVOKE		2
+#define AVC_CALLBACK_REVOKE		4
+#define AVC_CALLBACK_RESET		8
+#define AVC_CALLBACK_AUDITALLOW_ENABLE	16
+#define AVC_CALLBACK_AUDITALLOW_DISABLE 32
+#define AVC_CALLBACK_AUDITDENY_ENABLE	64
+#define AVC_CALLBACK_AUDITDENY_DISABLE	128
+#define AVC_CALLBACK_ADD_XPERMS		256
+
+int avc_add_callback(int (*callback)(u32 event), u32 events);
+
+/* Exported to selinuxfs */
+int avc_get_hash_stats(char *page);
+unsigned int avc_get_cache_threshold(void);
+void avc_set_cache_threshold(unsigned int cache_threshold);
+
+#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
+DECLARE_PER_CPU(struct avc_cache_stats, avc_cache_stats);
+#endif
+
+#endif /* _SELINUX_AVC_H_ */
diff --git a/security/selinux/include/avc_ss.h b/security/selinux/include/avc_ss.h
new file mode 100644
index 000000000..48ad64d54
--- /dev/null
+++ b/security/selinux/include/avc_ss.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Access vector cache interface for the security server.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SELINUX_AVC_SS_H_
+#define _SELINUX_AVC_SS_H_
+
+#include <linux/types.h>
+
+int avc_ss_reset(u32 seqno);
+
+/* Class/perm mapping support */
+struct security_class_mapping {
+	const char *name;
+	const char *perms[sizeof(u32) * 8 + 1];
+};
+
+extern const struct security_class_mapping secclass_map[];
+
+#endif /* _SELINUX_AVC_SS_H_ */
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
new file mode 100644
index 000000000..90cb61b16
--- /dev/null
+++ b/security/selinux/include/classmap.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define COMMON_FILE_SOCK_PERMS                                            \
+	"ioctl", "read", "write", "create", "getattr", "setattr", "lock", \
+		"relabelfrom", "relabelto", "append", "map"
+
+#define COMMON_FILE_PERMS                                                \
+	COMMON_FILE_SOCK_PERMS, "unlink", "link", "rename", "execute",   \
+		"quotaon", "mounton", "audit_access", "open", "execmod", \
+		"watch", "watch_mount", "watch_sb", "watch_with_perm",   \
+		"watch_reads", "watch_mountns"
+
+#define COMMON_SOCK_PERMS                                              \
+	COMMON_FILE_SOCK_PERMS, "bind", "connect", "listen", "accept", \
+		"getopt", "setopt", "shutdown", "recvfrom", "sendto",  \
+		"name_bind"
+
+#define COMMON_IPC_PERMS                                            \
+	"create", "destroy", "getattr", "setattr", "read", "write", \
+		"associate", "unix_read", "unix_write"
+
+#define COMMON_CAP_PERMS                                                     \
+	"chown", "dac_override", "dac_read_search", "fowner", "fsetid",      \
+		"kill", "setgid", "setuid", "setpcap", "linux_immutable",    \
+		"net_bind_service", "net_broadcast", "net_admin", "net_raw", \
+		"ipc_lock", "ipc_owner", "sys_module", "sys_rawio",          \
+		"sys_chroot", "sys_ptrace", "sys_pacct", "sys_admin",        \
+		"sys_boot", "sys_nice", "sys_resource", "sys_time",          \
+		"sys_tty_config", "mknod", "lease", "audit_write",           \
+		"audit_control", "setfcap"
+
+#define COMMON_CAP2_PERMS                                                     \
+	"mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend", \
+		"audit_read", "perfmon", "bpf", "checkpoint_restore"
+
+#ifdef __KERNEL__ /* avoid this check when building host programs */
+#include <linux/capability.h>
+
+#if CAP_LAST_CAP > CAP_CHECKPOINT_RESTORE
+#error New capability defined, please update COMMON_CAP2_PERMS.
+#endif
+#endif
+
+/*
+ * Note: The name for any socket class should be suffixed by "socket",
+ *	 and doesn't contain more than one substr of "socket".
+ */
+const struct security_class_mapping secclass_map[] = {
+	{ "security",
+	  { "compute_av", "compute_create", "compute_member", "check_context",
+	    "load_policy", "compute_relabel", "compute_user", "setenforce",
+	    "setbool", "setsecparam", "setcheckreqprot", "read_policy",
+	    "validate_trans", NULL } },
+	{ "process",
+	  { "fork",	    "transition",    "sigchld",	    "sigkill",
+	    "sigstop",	    "signull",	     "signal",	    "ptrace",
+	    "getsched",	    "setsched",	     "getsession",  "getpgid",
+	    "setpgid",	    "getcap",	     "setcap",	    "share",
+	    "getattr",	    "setexec",	     "setfscreate", "noatsecure",
+	    "siginh",	    "setrlimit",     "rlimitinh",   "dyntransition",
+	    "setcurrent",   "execmem",	     "execstack",   "execheap",
+	    "setkeycreate", "setsockcreate", "getrlimit",   NULL } },
+	{ "process2", { "nnp_transition", "nosuid_transition", NULL } },
+	{ "system",
+	  { "ipc_info", "syslog_read", "syslog_mod", "syslog_console",
+	    "module_request", "module_load", "firmware_load",
+	    "kexec_image_load", "kexec_initramfs_load", "policy_load",
+	    "x509_certificate_load", NULL } },
+	{ "capability", { COMMON_CAP_PERMS, NULL } },
+	{ "filesystem",
+	  { "mount", "remount", "unmount", "getattr", "relabelfrom",
+	    "relabelto", "associate", "quotamod", "quotaget", "watch", NULL } },
+	{ "file",
+	  { COMMON_FILE_PERMS, "execute_no_trans", "entrypoint", NULL } },
+	{ "dir",
+	  { COMMON_FILE_PERMS, "add_name", "remove_name", "reparent", "search",
+	    "rmdir", NULL } },
+	{ "fd", { "use", NULL } },
+	{ "lnk_file", { COMMON_FILE_PERMS, NULL } },
+	{ "chr_file", { COMMON_FILE_PERMS, NULL } },
+	{ "blk_file", { COMMON_FILE_PERMS, NULL } },
+	{ "sock_file", { COMMON_FILE_PERMS, NULL } },
+	{ "fifo_file", { COMMON_FILE_PERMS, NULL } },
+	{ "socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "tcp_socket",
+	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", NULL } },
+	{ "udp_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "rawip_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "node", { "recvfrom", "sendto", NULL } },
+	{ "netif", { "ingress", "egress", NULL } },
+	{ "netlink_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "packet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "key_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "unix_stream_socket", { COMMON_SOCK_PERMS, "connectto", NULL } },
+	{ "unix_dgram_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "sem", { COMMON_IPC_PERMS, NULL } },
+	{ "msg", { "send", "receive", NULL } },
+	{ "msgq", { COMMON_IPC_PERMS, "enqueue", NULL } },
+	{ "shm", { COMMON_IPC_PERMS, "lock", NULL } },
+	{ "ipc", { COMMON_IPC_PERMS, NULL } },
+	{ "netlink_route_socket",
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", "nlmsg", NULL } },
+	{ "netlink_tcpdiag_socket",
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", "nlmsg", NULL } },
+	{ "netlink_nflog_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_xfrm_socket",
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", "nlmsg", NULL } },
+	{ "netlink_selinux_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_iscsi_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_audit_socket",
+	  { COMMON_SOCK_PERMS, "nlmsg_read", "nlmsg_write", "nlmsg_relay",
+	    "nlmsg_readpriv", "nlmsg_tty_audit", "nlmsg", NULL } },
+	{ "netlink_fib_lookup_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_connector_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_netfilter_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_dnrt_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "association",
+	  { "sendto", "recvfrom", "setcontext", "polmatch", NULL } },
+	{ "netlink_kobject_uevent_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_generic_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_scsitransport_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_rdma_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netlink_crypto_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "appletalk_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "packet",
+	  { "send", "recv", "relabelto", "forward_in", "forward_out", NULL } },
+	{ "key",
+	  { "view", "read", "write", "search", "link", "setattr", "create",
+	    NULL } },
+	{ "memprotect", { "mmap_zero", NULL } },
+	{ "peer", { "recv", NULL } },
+	{ "capability2", { COMMON_CAP2_PERMS, NULL } },
+	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
+	{ "tun_socket", { COMMON_SOCK_PERMS, "attach_queue", NULL } },
+	{ "binder",
+	  { "impersonate", "call", "set_context_mgr", "transfer", NULL } },
+	{ "cap_userns", { COMMON_CAP_PERMS, NULL } },
+	{ "cap2_userns", { COMMON_CAP2_PERMS, NULL } },
+	{ "sctp_socket",
+	  { COMMON_SOCK_PERMS, "node_bind", "name_connect", "association",
+	    NULL } },
+	{ "icmp_socket", { COMMON_SOCK_PERMS, "node_bind", NULL } },
+	{ "ax25_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "ipx_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "netrom_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "atmpvc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "x25_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rose_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "decnet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "atmsvc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rds_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "irda_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "pppox_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "llc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "can_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "tipc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "bluetooth_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "iucv_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "rxrpc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "isdn_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "phonet_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "ieee802154_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "caif_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "alg_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "nfc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "vsock_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "kcm_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "qipcrtr_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "smc_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "infiniband_pkey", { "access", NULL } },
+	{ "infiniband_endport", { "manage_subnet", NULL } },
+	{ "bpf",
+	  { "map_create", "map_read", "map_write", "prog_load", "prog_run",
+	    "map_create_as", "prog_load_as", NULL } },
+	{ "xdp_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "mctp_socket", { COMMON_SOCK_PERMS, NULL } },
+	{ "perf_event",
+	  { "open", "cpu", "kernel", "tracepoint", "read", "write", NULL } },
+	{ "anon_inode", { COMMON_FILE_PERMS, NULL } },
+	{ "io_uring", { "override_creds", "sqpoll", "cmd", "allowed", NULL } },
+	{ "user_namespace", { "create", NULL } },
+	{ "memfd_file",
+	  { COMMON_FILE_PERMS, "execute_no_trans", "entrypoint", NULL } },
+	/* last one */ { NULL, {} }
+};
+
+#ifdef __KERNEL__ /* avoid this check when building host programs */
+#include <linux/socket.h>
+
+#if PF_MAX > 46
+#error New address family defined, please update secclass_map.
+#endif
+#endif
diff --git a/security/selinux/include/conditional.h b/security/selinux/include/conditional.h
new file mode 100644
index 000000000..060833e2d
--- /dev/null
+++ b/security/selinux/include/conditional.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Interface to booleans in the security server. This is exported
+ * for the selinuxfs.
+ *
+ * Author: Karl MacMillan <kmacmillan@tresys.com>
+ *
+ * Copyright (C) 2003 - 2004 Tresys Technology, LLC
+ */
+
+#ifndef _SELINUX_CONDITIONAL_H_
+#define _SELINUX_CONDITIONAL_H_
+
+#include "security.h"
+
+int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names,
+		       int **values);
+
+int security_set_bools(u32 len, const int *values);
+
+int security_get_bool_value(u32 index);
+
+#endif
diff --git a/security/selinux/include/hash.h b/security/selinux/include/hash.h
new file mode 100644
index 000000000..18956dbef
--- /dev/null
+++ b/security/selinux/include/hash.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _SELINUX_HASH_H_
+#define _SELINUX_HASH_H_
+
+/*
+ * Based on MurmurHash3, written by Austin Appleby and placed in the
+ * public domain.
+ */
+static inline u32 av_hash(u32 key1, u32 key2, u32 key3, u32 mask)
+{
+	static const u32 c1 = 0xcc9e2d51;
+	static const u32 c2 = 0x1b873593;
+	static const u32 r1 = 15;
+	static const u32 r2 = 13;
+	static const u32 m = 5;
+	static const u32 n = 0xe6546b64;
+
+	u32 hash = 0;
+
+#define mix(input)                                         \
+	do {                                               \
+		u32 v = input;                             \
+		v *= c1;                                   \
+		v = (v << r1) | (v >> (32 - r1));          \
+		v *= c2;                                   \
+		hash ^= v;                                 \
+		hash = (hash << r2) | (hash >> (32 - r2)); \
+		hash = hash * m + n;                       \
+	} while (0)
+
+	mix(key1);
+	mix(key2);
+	mix(key3);
+
+#undef mix
+
+	hash ^= hash >> 16;
+	hash *= 0x85ebca6b;
+	hash ^= hash >> 13;
+	hash *= 0xc2b2ae35;
+	hash ^= hash >> 16;
+
+	return hash & mask;
+}
+
+#endif /* _SELINUX_HASH_H_ */
diff --git a/security/selinux/include/ibpkey.h b/security/selinux/include/ibpkey.h
new file mode 100644
index 000000000..875b05584
--- /dev/null
+++ b/security/selinux/include/ibpkey.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * pkey table
+ *
+ * SELinux must keep a mapping of pkeys to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead.
+ */
+
+/*
+ * (c) Mellanox Technologies, 2016
+ */
+
+#ifndef _SELINUX_IB_PKEY_H
+#define _SELINUX_IB_PKEY_H
+
+#include <linux/types.h>
+#include "flask.h"
+
+#ifdef CONFIG_SECURITY_INFINIBAND
+void sel_ib_pkey_flush(void);
+int sel_ib_pkey_sid(u64 subnet_prefix, u16 pkey, u32 *sid);
+#else
+static inline void sel_ib_pkey_flush(void)
+{
+	return;
+}
+static inline int sel_ib_pkey_sid(u64 subnet_prefix, u16 pkey, u32 *sid)
+{
+	*sid = SECINITSID_UNLABELED;
+	return 0;
+}
+#endif
+
+#endif
diff --git a/security/selinux/include/ima.h b/security/selinux/include/ima.h
new file mode 100644
index 000000000..d7d18f030
--- /dev/null
+++ b/security/selinux/include/ima.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (C) 2021 Microsoft Corporation
+ *
+ * Author: Lakshmi Ramasubramanian (nramas@linux.microsoft.com)
+ *
+ * Measure critical data structures maintained by SELinux
+ * using IMA subsystem.
+ */
+
+#ifndef _SELINUX_IMA_H_
+#define _SELINUX_IMA_H_
+
+#include "security.h"
+
+#ifdef CONFIG_IMA
+void __init selinux_ima_config_len_init(void);
+extern void selinux_ima_measure_state(void);
+extern void selinux_ima_measure_state_locked(void);
+#else
+static inline void selinux_ima_config_len_init(void)
+{
+}
+static inline void selinux_ima_measure_state(void)
+{
+}
+static inline void selinux_ima_measure_state_locked(void)
+{
+}
+#endif
+
+#endif /* _SELINUX_IMA_H_ */
diff --git a/security/selinux/include/initcalls.h b/security/selinux/include/initcalls.h
new file mode 100644
index 000000000..6674cf489
--- /dev/null
+++ b/security/selinux/include/initcalls.h
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SELinux initcalls
+ */
+
+#ifndef _SELINUX_INITCALLS_H
+#define _SELINUX_INITCALLS_H
+
+int init_sel_fs(void);
+int sel_netport_init(void);
+int sel_netnode_init(void);
+int sel_netif_init(void);
+int sel_netlink_init(void);
+int sel_ib_pkey_init(void);
+int selinux_nf_ip_init(void);
+
+int selinux_initcall(void);
+
+#endif
diff --git a/security/selinux/include/initial_sid_to_string.h b/security/selinux/include/initial_sid_to_string.h
new file mode 100644
index 000000000..d7ba60b62
--- /dev/null
+++ b/security/selinux/include/initial_sid_to_string.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef __KERNEL__
+#include <linux/stddef.h>
+#else
+#include <stddef.h>
+#endif
+
+static const char *const initial_sid_to_string[] = {
+	NULL, /* zero placeholder, not used */
+	"kernel", /* kernel / SECINITSID_KERNEL */
+	"security", /* security / SECINITSID_SECURITY */
+	"unlabeled", /* unlabeled / SECINITSID_UNLABELED */
+	NULL, /* fs */
+	"file", /* file / SECINITSID_FILE */
+	NULL, /* file_labels */
+	"init", /* init / SECINITSID_INIT */
+	"any_socket", /* any_socket / SECINITSID_ANY_SOCKET */
+	"port", /* port / SECINITSID_PORT */
+	"netif", /* netif / SECINITSID_NETIF */
+	"netmsg", /* netmsg / SECINITSID_NETMSG */
+	"node", /* node / SECINITSID_NODE */
+	NULL, /* igmp_packet */
+	NULL, /* icmp_socket */
+	NULL, /* tcp_socket */
+	NULL, /* sysctl_modprobe */
+	NULL, /* sysctl */
+	NULL, /* sysctl_fs */
+	NULL, /* sysctl_kernel */
+	NULL, /* sysctl_net */
+	NULL, /* sysctl_net_unix */
+	NULL, /* sysctl_vm */
+	NULL, /* sysctl_dev */
+	NULL, /* kmod */
+	NULL, /* policy */
+	NULL, /* scmp_packet */
+	"devnull", /* devnull / SECINITSID_DEVNULL */
+};
diff --git a/security/selinux/include/netif.h b/security/selinux/include/netif.h
new file mode 100644
index 000000000..2838bdc17
--- /dev/null
+++ b/security/selinux/include/netif.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Network interface table.
+ *
+ * Network interfaces (devices) do not have a security field, so we
+ * maintain a table associating each interface with a SID.
+ *
+ * Author: James Morris <jmorris@redhat.com>
+ *
+ * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ * Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
+ *                    Paul Moore <paul@paul-moore.com>
+ */
+
+#ifndef _SELINUX_NETIF_H_
+#define _SELINUX_NETIF_H_
+
+#include <net/net_namespace.h>
+
+void sel_netif_flush(void);
+
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid);
+
+#endif /* _SELINUX_NETIF_H_ */
diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h
new file mode 100644
index 000000000..5731c0dcd
--- /dev/null
+++ b/security/selinux/include/netlabel.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * SELinux interface to the NetLabel subsystem
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2006
+ */
+
+#ifndef _SELINUX_NETLABEL_H_
+#define _SELINUX_NETLABEL_H_
+
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/request_sock.h>
+#include <net/sctp/structs.h>
+
+#include "avc.h"
+#include "objsec.h"
+
+#ifdef CONFIG_NETLABEL
+void selinux_netlbl_cache_invalidate(void);
+
+void selinux_netlbl_err(struct sk_buff *skb, u16 family, int error,
+			int gateway);
+
+void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec);
+void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec);
+
+int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, u16 family, u32 *type,
+				 u32 *sid);
+int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid);
+int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
+				      struct sk_buff *skb);
+int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family);
+void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family);
+void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk);
+int selinux_netlbl_socket_post_create(struct sock *sk, u16 family);
+int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
+				struct sk_buff *skb, u16 family,
+				struct common_audit_data *ad);
+int selinux_netlbl_socket_setsockopt(struct socket *sock, int level,
+				     int optname);
+int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr);
+int selinux_netlbl_socket_connect_locked(struct sock *sk,
+					 struct sockaddr *addr);
+
+#else
+static inline void selinux_netlbl_cache_invalidate(void)
+{
+	return;
+}
+
+static inline void selinux_netlbl_err(struct sk_buff *skb, u16 family,
+				      int error, int gateway)
+{
+	return;
+}
+
+static inline void
+selinux_netlbl_sk_security_free(struct sk_security_struct *sksec)
+{
+	return;
+}
+
+static inline void
+selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec)
+{
+	return;
+}
+
+static inline int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, u16 family,
+					       u32 *type, u32 *sid)
+{
+	*type = NETLBL_NLTYPE_NONE;
+	*sid = SECSID_NULL;
+	return 0;
+}
+static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family,
+					       u32 sid)
+{
+	return 0;
+}
+
+static inline int
+selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
+				  struct sk_buff *skb)
+{
+	return 0;
+}
+static inline int selinux_netlbl_inet_conn_request(struct request_sock *req,
+						   u16 family)
+{
+	return 0;
+}
+static inline void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family)
+{
+	return;
+}
+static inline void selinux_netlbl_sctp_sk_clone(struct sock *sk,
+						struct sock *newsk)
+{
+	return;
+}
+static inline int selinux_netlbl_socket_post_create(struct sock *sk, u16 family)
+{
+	return 0;
+}
+static inline int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
+					      struct sk_buff *skb, u16 family,
+					      struct common_audit_data *ad)
+{
+	return 0;
+}
+static inline int selinux_netlbl_socket_setsockopt(struct socket *sock,
+						   int level, int optname)
+{
+	return 0;
+}
+static inline int selinux_netlbl_socket_connect(struct sock *sk,
+						struct sockaddr *addr)
+{
+	return 0;
+}
+static inline int selinux_netlbl_socket_connect_locked(struct sock *sk,
+						       struct sockaddr *addr)
+{
+	return 0;
+}
+#endif /* CONFIG_NETLABEL */
+
+#endif
diff --git a/security/selinux/include/netnode.h b/security/selinux/include/netnode.h
new file mode 100644
index 000000000..e4dc904c3
--- /dev/null
+++ b/security/selinux/include/netnode.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Network node table
+ *
+ * SELinux must keep a mapping of network nodes to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead since most of these queries happen on
+ * a per-packet basis.
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2007
+ */
+
+#ifndef _SELINUX_NETNODE_H
+#define _SELINUX_NETNODE_H
+
+#include <linux/types.h>
+
+void sel_netnode_flush(void);
+
+int sel_netnode_sid(const void *addr, u16 family, u32 *sid);
+
+#endif
diff --git a/security/selinux/include/netport.h b/security/selinux/include/netport.h
new file mode 100644
index 000000000..9096a8289
--- /dev/null
+++ b/security/selinux/include/netport.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Network port table
+ *
+ * SELinux must keep a mapping of network ports to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead.
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2008
+ */
+
+#ifndef _SELINUX_NETPORT_H
+#define _SELINUX_NETPORT_H
+
+#include <linux/types.h>
+
+void sel_netport_flush(void);
+
+int sel_netport_sid(u8 protocol, u16 pnum, u32 *sid);
+
+#endif
diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
new file mode 100644
index 000000000..3c0a16ec9
--- /dev/null
+++ b/security/selinux/include/objsec.h
@@ -0,0 +1,290 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Security-Enhanced Linux (SELinux) security module
+ *
+ *  This file contains the SELinux security data structures for kernel objects.
+ *
+ *  Author(s):  Stephen Smalley, <stephen.smalley.work@gmail.com>
+ *		Chris Vance, <cvance@nai.com>
+ *		Wayne Salamon, <wsalamon@nai.com>
+ *		James Morris <jmorris@redhat.com>
+ *
+ *  Copyright (C) 2001,2002 Networks Associates Technology, Inc.
+ *  Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ *  Copyright (C) 2016 Mellanox Technologies
+ */
+
+#ifndef _SELINUX_OBJSEC_H_
+#define _SELINUX_OBJSEC_H_
+
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/binfmts.h>
+#include <linux/in.h>
+#include <linux/spinlock.h>
+#include <linux/lsm_hooks.h>
+#include <linux/msg.h>
+#include <net/net_namespace.h>
+#include <linux/bpf.h>
+#include "flask.h"
+#include "avc.h"
+
+struct avdc_entry {
+	u32 isid; /* inode SID */
+	struct av_decision avd; /* av decision */
+};
+
+struct cred_security_struct {
+	u32 osid; /* SID prior to last execve */
+	u32 sid; /* current SID */
+	u32 exec_sid; /* exec SID */
+	u32 create_sid; /* fscreate SID */
+	u32 keycreate_sid; /* keycreate SID */
+	u32 sockcreate_sid; /* fscreate SID */
+} __randomize_layout;
+
+struct task_security_struct {
+#define TSEC_AVDC_DIR_SIZE (1 << 2)
+	struct {
+		u32 sid; /* current SID for cached entries */
+		u32 seqno; /* AVC sequence number */
+		unsigned int dir_spot; /* dir cache index to check first */
+		struct avdc_entry dir[TSEC_AVDC_DIR_SIZE]; /* dir entries */
+		bool permissive_neveraudit; /* permissive and neveraudit */
+	} avdcache;
+} __randomize_layout;
+
+static inline bool task_avdcache_permnoaudit(struct task_security_struct *tsec,
+					     u32 sid)
+{
+	return (tsec->avdcache.permissive_neveraudit &&
+		sid == tsec->avdcache.sid &&
+		tsec->avdcache.seqno == avc_policy_seqno());
+}
+
+enum label_initialized {
+	LABEL_INVALID, /* invalid or not initialized */
+	LABEL_INITIALIZED, /* initialized */
+	LABEL_PENDING
+};
+
+struct inode_security_struct {
+	struct inode *inode; /* back pointer to inode object */
+	struct list_head list; /* list of inode_security_struct */
+	u32 task_sid; /* SID of creating task */
+	u32 sid; /* SID of this object */
+	u16 sclass; /* security class of this object */
+	unsigned char initialized; /* initialization flag */
+	spinlock_t lock;
+};
+
+struct file_security_struct {
+	u32 sid; /* SID of open file description */
+	u32 fown_sid; /* SID of file owner (for SIGIO) */
+	u32 isid; /* SID of inode at the time of file open */
+	u32 pseqno; /* Policy seqno at the time of file open */
+};
+
+struct backing_file_security_struct {
+	u32 uf_sid; /* associated user file fsec->sid */
+};
+
+struct superblock_security_struct {
+	u32 sid; /* SID of file system superblock */
+	u32 def_sid; /* default SID for labeling */
+	u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */
+	u32 creator_sid; /* SID of privileged process */
+	unsigned short behavior; /* labeling behavior */
+	unsigned short flags; /* which mount options were specified */
+	struct mutex lock;
+	struct list_head isec_head;
+	spinlock_t isec_lock;
+};
+
+struct msg_security_struct {
+	u32 sid; /* SID of message */
+};
+
+struct ipc_security_struct {
+	u16 sclass; /* security class of this object */
+	u32 sid; /* SID of IPC resource */
+};
+
+struct netif_security_struct {
+	const struct net *ns; /* network namespace */
+	int ifindex; /* device index */
+	u32 sid; /* SID for this interface */
+};
+
+struct netnode_security_struct {
+	union {
+		__be32 ipv4; /* IPv4 node address */
+		struct in6_addr ipv6; /* IPv6 node address */
+	} addr;
+	u32 sid; /* SID for this node */
+	u16 family; /* address family */
+};
+
+struct netport_security_struct {
+	u32 sid; /* SID for this node */
+	u16 port; /* port number */
+	u8 protocol; /* transport protocol */
+};
+
+struct sk_security_struct {
+#ifdef CONFIG_NETLABEL
+	enum { /* NetLabel state */
+	       NLBL_UNSET = 0,
+	       NLBL_REQUIRE,
+	       NLBL_LABELED,
+	       NLBL_REQSKB,
+	       NLBL_CONNLABELED,
+	} nlbl_state;
+	struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */
+#endif
+	u32 sid; /* SID of this object */
+	u32 peer_sid; /* SID of peer */
+	u16 sclass; /* sock security class */
+	enum { /* SCTP association state */
+	       SCTP_ASSOC_UNSET = 0,
+	       SCTP_ASSOC_SET,
+	} sctp_assoc_state;
+};
+
+struct tun_security_struct {
+	u32 sid; /* SID for the tun device sockets */
+};
+
+struct key_security_struct {
+	u32 sid; /* SID of key */
+};
+
+struct ib_security_struct {
+	u32 sid; /* SID of the queue pair or MAD agent */
+};
+
+struct pkey_security_struct {
+	u64 subnet_prefix; /* Port subnet prefix */
+	u16 pkey; /* PKey number */
+	u32 sid; /* SID of pkey */
+};
+
+struct bpf_security_struct {
+	u32 sid; /* SID of bpf obj creator */
+	u32 perms; /* permissions for allowed bpf token commands */
+	u32 grantor_sid; /* SID of token grantor */
+};
+
+struct perf_event_security_struct {
+	u32 sid; /* SID of perf_event obj creator */
+};
+
+extern struct lsm_blob_sizes selinux_blob_sizes;
+static inline struct cred_security_struct *selinux_cred(const struct cred *cred)
+{
+	return cred->security + selinux_blob_sizes.lbs_cred;
+}
+
+static inline struct task_security_struct *
+selinux_task(const struct task_struct *task)
+{
+	return task->security + selinux_blob_sizes.lbs_task;
+}
+
+static inline struct file_security_struct *selinux_file(const struct file *file)
+{
+	return file->f_security + selinux_blob_sizes.lbs_file;
+}
+
+static inline struct backing_file_security_struct *
+selinux_backing_file(const struct file *backing_file)
+{
+	void *blob = backing_file_security(backing_file);
+	return blob + selinux_blob_sizes.lbs_backing_file;
+}
+
+static inline struct inode_security_struct *
+selinux_inode(const struct inode *inode)
+{
+	if (unlikely(!inode->i_security))
+		return NULL;
+	return inode->i_security + selinux_blob_sizes.lbs_inode;
+}
+
+static inline struct msg_security_struct *
+selinux_msg_msg(const struct msg_msg *msg_msg)
+{
+	return msg_msg->security + selinux_blob_sizes.lbs_msg_msg;
+}
+
+static inline struct ipc_security_struct *
+selinux_ipc(const struct kern_ipc_perm *ipc)
+{
+	return ipc->security + selinux_blob_sizes.lbs_ipc;
+}
+
+/*
+ * get the subjective security ID of the current task
+ */
+static inline u32 current_sid(void)
+{
+	const struct cred_security_struct *crsec = selinux_cred(current_cred());
+
+	return crsec->sid;
+}
+
+static inline struct superblock_security_struct *
+selinux_superblock(const struct super_block *superblock)
+{
+	return superblock->s_security + selinux_blob_sizes.lbs_superblock;
+}
+
+#ifdef CONFIG_KEYS
+static inline struct key_security_struct *selinux_key(const struct key *key)
+{
+	return key->security + selinux_blob_sizes.lbs_key;
+}
+#endif /* CONFIG_KEYS */
+
+static inline struct sk_security_struct *selinux_sock(const struct sock *sock)
+{
+	return sock->sk_security + selinux_blob_sizes.lbs_sock;
+}
+
+static inline struct tun_security_struct *selinux_tun_dev(void *security)
+{
+	return security + selinux_blob_sizes.lbs_tun_dev;
+}
+
+static inline struct ib_security_struct *selinux_ib(void *ib_sec)
+{
+	return ib_sec + selinux_blob_sizes.lbs_ib;
+}
+
+static inline struct perf_event_security_struct *
+selinux_perf_event(void *perf_event)
+{
+	return perf_event + selinux_blob_sizes.lbs_perf_event;
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static inline struct bpf_security_struct *
+selinux_bpf_map_security(struct bpf_map *map)
+{
+	return map->security + selinux_blob_sizes.lbs_bpf_map;
+}
+
+static inline struct bpf_security_struct *
+selinux_bpf_prog_security(struct bpf_prog *prog)
+{
+	return prog->aux->security + selinux_blob_sizes.lbs_bpf_prog;
+}
+
+static inline struct bpf_security_struct *
+selinux_bpf_token_security(struct bpf_token *token)
+{
+	return token->security + selinux_blob_sizes.lbs_bpf_token;
+}
+#endif /* CONFIG_BPF_SYSCALL */
+#endif /* _SELINUX_OBJSEC_H_ */
diff --git a/security/selinux/include/policycap.h b/security/selinux/include/policycap.h
new file mode 100644
index 000000000..dbf39358a
--- /dev/null
+++ b/security/selinux/include/policycap.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _SELINUX_POLICYCAP_H_
+#define _SELINUX_POLICYCAP_H_
+
+/* Policy capabilities */
+enum {
+	POLICYDB_CAP_NETPEER,
+	POLICYDB_CAP_OPENPERM,
+	POLICYDB_CAP_EXTSOCKCLASS,
+	POLICYDB_CAP_ALWAYSNETWORK,
+	POLICYDB_CAP_CGROUPSECLABEL,
+	POLICYDB_CAP_NNP_NOSUID_TRANSITION,
+	POLICYDB_CAP_GENFS_SECLABEL_SYMLINKS,
+	POLICYDB_CAP_IOCTL_SKIP_CLOEXEC,
+	POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT,
+	POLICYDB_CAP_NETLINK_XPERM,
+	POLICYDB_CAP_NETIF_WILDCARD,
+	POLICYDB_CAP_GENFS_SECLABEL_WILDCARD,
+	POLICYDB_CAP_FUNCTIONFS_SECLABEL,
+	POLICYDB_CAP_MEMFD_CLASS,
+	POLICYDB_CAP_BPF_TOKEN_PERMS,
+	__POLICYDB_CAP_MAX
+};
+#define POLICYDB_CAP_MAX (__POLICYDB_CAP_MAX - 1)
+
+extern const char *const selinux_policycap_names[__POLICYDB_CAP_MAX];
+
+#endif /* _SELINUX_POLICYCAP_H_ */
diff --git a/security/selinux/include/policycap_names.h b/security/selinux/include/policycap_names.h
new file mode 100644
index 000000000..6e2b808e1
--- /dev/null
+++ b/security/selinux/include/policycap_names.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _SELINUX_POLICYCAP_NAMES_H_
+#define _SELINUX_POLICYCAP_NAMES_H_
+
+#include "policycap.h"
+
+/* clang-format off */
+/* Policy capability names */
+const char *const selinux_policycap_names[__POLICYDB_CAP_MAX] = {
+	"network_peer_controls",
+	"open_perms",
+	"extended_socket_class",
+	"always_check_network",
+	"cgroup_seclabel",
+	"nnp_nosuid_transition",
+	"genfs_seclabel_symlinks",
+	"ioctl_skip_cloexec",
+	"userspace_initial_context",
+	"netlink_xperm",
+	"netif_wildcard",
+	"genfs_seclabel_wildcard",
+	"functionfs_seclabel",
+	"memfd_class",
+	"bpf_token_perms",
+};
+/* clang-format on */
+
+#endif /* _SELINUX_POLICYCAP_NAMES_H_ */
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
new file mode 100644
index 000000000..a74415e3a
--- /dev/null
+++ b/security/selinux/include/security.h
@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Security server interface.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ *
+ */
+
+#ifndef _SELINUX_SECURITY_H_
+#define _SELINUX_SECURITY_H_
+
+#include <linux/compiler.h>
+#include <linux/dcache.h>
+#include <linux/magic.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/workqueue.h>
+#include <linux/delay.h>
+#include <linux/printk.h>
+#include "flask.h"
+#include "policycap.h"
+
+#define SECSID_NULL   0x00000000 /* unspecified SID */
+#define SECSID_WILD   0xffffffff /* wildcard SID */
+#define SECCLASS_NULL 0x0000 /* no class */
+
+/* Identify specific policy version changes */
+#define POLICYDB_VERSION_BASE		     15
+#define POLICYDB_VERSION_BOOL		     16
+#define POLICYDB_VERSION_IPV6		     17
+#define POLICYDB_VERSION_NLCLASS	     18
+#define POLICYDB_VERSION_VALIDATETRANS	     19
+#define POLICYDB_VERSION_MLS		     19
+#define POLICYDB_VERSION_AVTAB		     20
+#define POLICYDB_VERSION_RANGETRANS	     21
+#define POLICYDB_VERSION_POLCAP		     22
+#define POLICYDB_VERSION_PERMISSIVE	     23
+#define POLICYDB_VERSION_BOUNDARY	     24
+#define POLICYDB_VERSION_FILENAME_TRANS	     25
+#define POLICYDB_VERSION_ROLETRANS	     26
+#define POLICYDB_VERSION_NEW_OBJECT_DEFAULTS 27
+#define POLICYDB_VERSION_DEFAULT_TYPE	     28
+#define POLICYDB_VERSION_CONSTRAINT_NAMES    29
+#define POLICYDB_VERSION_XPERMS_IOCTL	     30
+#define POLICYDB_VERSION_INFINIBAND	     31
+#define POLICYDB_VERSION_GLBLUB		     32
+#define POLICYDB_VERSION_COMP_FTRANS	     33 /* compressed filename transitions */
+#define POLICYDB_VERSION_COND_XPERMS	     34 /* extended permissions in conditional policies */
+#define POLICYDB_VERSION_NEVERAUDIT	     35 /* neveraudit types */
+
+/* Range of policy versions we understand*/
+#define POLICYDB_VERSION_MIN POLICYDB_VERSION_BASE
+#define POLICYDB_VERSION_MAX POLICYDB_VERSION_NEVERAUDIT
+
+/* Mask for just the mount related flags */
+#define SE_MNTMASK 0x0f
+/* Super block security struct flags for mount options */
+/* BE CAREFUL, these need to be the low order bits for selinux_get_mnt_opts */
+#define CONTEXT_MNT	0x01
+#define FSCONTEXT_MNT	0x02
+#define ROOTCONTEXT_MNT 0x04
+#define DEFCONTEXT_MNT	0x08
+#define SBLABEL_MNT	0x10
+/* Non-mount related flags */
+#define SE_SBINITIALIZED 0x0100
+#define SE_SBPROC	 0x0200
+#define SE_SBGENFS	 0x0400
+#define SE_SBGENFS_XATTR 0x0800
+#define SE_SBNATIVE	 0x1000
+
+#define CONTEXT_STR	"context"
+#define FSCONTEXT_STR	"fscontext"
+#define ROOTCONTEXT_STR "rootcontext"
+#define DEFCONTEXT_STR	"defcontext"
+#define SECLABEL_STR	"seclabel"
+
+struct netlbl_lsm_secattr;
+
+extern int selinux_enabled_boot;
+
+/*
+ * type_datum properties
+ * available at the kernel policy version >= POLICYDB_VERSION_BOUNDARY
+ */
+#define TYPEDATUM_PROPERTY_PRIMARY   0x0001
+#define TYPEDATUM_PROPERTY_ATTRIBUTE 0x0002
+
+/* limitation of boundary depth  */
+#define POLICYDB_BOUNDS_MAXDEPTH 4
+
+struct selinux_policy;
+
+struct selinux_state {
+#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
+	bool enforcing;
+#endif
+	bool initialized;
+	bool policycap[__POLICYDB_CAP_MAX];
+
+	struct page *status_page;
+	struct mutex status_lock;
+
+	struct selinux_policy __rcu *policy;
+	struct mutex policy_mutex;
+} __randomize_layout;
+
+void selinux_avc_init(void);
+
+extern struct selinux_state selinux_state;
+
+static inline bool selinux_initialized(void)
+{
+	/* do a synchronized load to avoid race conditions */
+	return smp_load_acquire(&selinux_state.initialized);
+}
+
+static inline void selinux_mark_initialized(void)
+{
+	/* do a synchronized write to avoid race conditions */
+	smp_store_release(&selinux_state.initialized, true);
+}
+
+#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
+static inline bool enforcing_enabled(void)
+{
+	return READ_ONCE(selinux_state.enforcing);
+}
+
+static inline void enforcing_set(bool value)
+{
+	WRITE_ONCE(selinux_state.enforcing, value);
+}
+#else
+static inline bool enforcing_enabled(void)
+{
+	return true;
+}
+
+static inline void enforcing_set(bool value)
+{
+}
+#endif
+
+static inline bool checkreqprot_get(void)
+{
+	/* non-zero/true checkreqprot values are no longer supported */
+	return 0;
+}
+
+static inline bool selinux_policycap_netpeer(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_NETPEER]);
+}
+
+static inline bool selinux_policycap_openperm(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_OPENPERM]);
+}
+
+static inline bool selinux_policycap_extsockclass(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_EXTSOCKCLASS]);
+}
+
+static inline bool selinux_policycap_alwaysnetwork(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_ALWAYSNETWORK]);
+}
+
+static inline bool selinux_policycap_cgroupseclabel(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_CGROUPSECLABEL]);
+}
+
+static inline bool selinux_policycap_nnp_nosuid_transition(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_NNP_NOSUID_TRANSITION]);
+}
+
+static inline bool selinux_policycap_genfs_seclabel_symlinks(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_GENFS_SECLABEL_SYMLINKS]);
+}
+
+static inline bool selinux_policycap_ioctl_skip_cloexec(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_IOCTL_SKIP_CLOEXEC]);
+}
+
+static inline bool selinux_policycap_userspace_initial_context(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT]);
+}
+
+static inline bool selinux_policycap_netlink_xperm(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_NETLINK_XPERM]);
+}
+
+static inline bool selinux_policycap_functionfs_seclabel(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_FUNCTIONFS_SECLABEL]);
+}
+
+static inline bool selinux_policycap_memfd_class(void)
+{
+	return READ_ONCE(selinux_state.policycap[POLICYDB_CAP_MEMFD_CLASS]);
+}
+
+static inline bool selinux_policycap_bpf_token_perms(void)
+{
+	return READ_ONCE(
+		selinux_state.policycap[POLICYDB_CAP_BPF_TOKEN_PERMS]);
+}
+
+struct selinux_policy_convert_data;
+
+struct selinux_load_state {
+	struct selinux_policy *policy;
+	struct selinux_policy_convert_data *convert_data;
+};
+
+int security_mls_enabled(void);
+int security_load_policy(void *data, size_t len,
+			 struct selinux_load_state *load_state);
+void selinux_policy_commit(struct selinux_load_state *load_state);
+void selinux_policy_cancel(struct selinux_load_state *load_state);
+int security_read_policy(void **data, size_t *len);
+int security_read_state_kernel(void **data, size_t *len);
+int security_policycap_supported(unsigned int req_cap);
+
+/* Maximum supported number of permissions per class */
+#define SEL_VEC_MAX 32
+struct av_decision {
+	u32 allowed;
+	u32 auditallow;
+	u32 auditdeny;
+	u32 seqno;
+	u32 flags;
+};
+
+#define XPERMS_ALLOWED	  1
+#define XPERMS_AUDITALLOW 2
+#define XPERMS_DONTAUDIT  4
+
+#define security_xperm_set(perms, x)  ((perms)[(x) >> 5] |= 1 << ((x)&0x1f))
+#define security_xperm_test(perms, x) (1 & ((perms)[(x) >> 5] >> ((x)&0x1f)))
+struct extended_perms_data {
+	u32 p[8];
+};
+
+struct extended_perms_decision {
+	u8 used;
+	u8 driver;
+	u8 base_perm;
+	struct extended_perms_data *allowed;
+	struct extended_perms_data *auditallow;
+	struct extended_perms_data *dontaudit;
+};
+
+struct extended_perms {
+	u16 len; /* length associated decision chain */
+	u8 base_perms; /* which base permissions are covered */
+	struct extended_perms_data drivers; /* flag drivers that are used */
+};
+
+/* definitions of av_decision.flags */
+#define AVD_FLAGS_PERMISSIVE 0x0001
+#define AVD_FLAGS_NEVERAUDIT  0x0002
+
+void security_compute_av(u32 ssid, u32 tsid, u16 tclass,
+			 struct av_decision *avd,
+			 struct extended_perms *xperms);
+
+void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass, u8 driver,
+				      u8 base_perm,
+				      struct extended_perms_decision *xpermd);
+
+void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass,
+			      struct av_decision *avd);
+
+int security_transition_sid(u32 ssid, u32 tsid, u16 tclass,
+			    const struct qstr *qstr, u32 *out_sid);
+
+int security_transition_sid_user(u32 ssid, u32 tsid, u16 tclass,
+				 const char *objname, u32 *out_sid);
+
+int security_member_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid);
+
+int security_change_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid);
+
+int security_sid_to_context(u32 sid, char **scontext, u32 *scontext_len);
+
+int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len);
+
+int security_sid_to_context_inval(u32 sid, char **scontext, u32 *scontext_len);
+
+int security_context_to_sid(const char *scontext, u32 scontext_len,
+			    u32 *out_sid, gfp_t gfp);
+
+int security_context_str_to_sid(const char *scontext, u32 *out_sid, gfp_t gfp);
+
+int security_context_to_sid_default(const char *scontext, u32 scontext_len,
+				    u32 *out_sid, u32 def_sid, gfp_t gfp_flags);
+
+int security_context_to_sid_force(const char *scontext, u32 scontext_len,
+				  u32 *sid);
+
+int security_port_sid(u8 protocol, u16 port, u32 *out_sid);
+
+int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid);
+
+int security_ib_endport_sid(const char *dev_name, u8 port_num, u32 *out_sid);
+
+int security_netif_sid(const char *name, u32 *if_sid);
+
+int security_node_sid(u16 domain, const void *addr, u32 addrlen, u32 *out_sid);
+
+int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid,
+				 u16 tclass);
+
+int security_validate_transition_user(u32 oldsid, u32 newsid, u32 tasksid,
+				      u16 tclass);
+
+int security_bounded_transition(u32 old_sid, u32 new_sid);
+
+int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid);
+
+int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid,
+				 u32 *peer_sid);
+
+int security_get_classes(struct selinux_policy *policy, char ***classes,
+			 u32 *nclasses);
+int security_get_permissions(struct selinux_policy *policy, const char *class,
+			     char ***perms, u32 *nperms);
+int security_get_reject_unknown(void);
+int security_get_allow_unknown(void);
+
+#define SECURITY_FS_USE_XATTR	 1 /* use xattr */
+#define SECURITY_FS_USE_TRANS	 2 /* use transition SIDs, e.g. devpts/tmpfs */
+#define SECURITY_FS_USE_TASK	 3 /* use task SIDs, e.g. pipefs/sockfs */
+#define SECURITY_FS_USE_GENFS	 4 /* use the genfs support */
+#define SECURITY_FS_USE_NONE	 5 /* no labeling support */
+#define SECURITY_FS_USE_MNTPOINT 6 /* use mountpoint labeling */
+#define SECURITY_FS_USE_NATIVE	 7 /* use native label support */
+#define SECURITY_FS_USE_MAX	 7 /* Highest SECURITY_FS_USE_XXX */
+
+int security_fs_use(struct super_block *sb);
+
+int security_genfs_sid(const char *fstype, const char *path, u16 sclass,
+		       u32 *sid);
+
+int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype,
+			     const char *path, u16 sclass, u32 *sid);
+
+#ifdef CONFIG_NETLABEL
+int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr,
+				   u32 *sid);
+
+int security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr);
+#else
+static inline int
+security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr, u32 *sid)
+{
+	return -EIDRM;
+}
+
+static inline int
+security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOENT;
+}
+#endif /* CONFIG_NETLABEL */
+
+const char *security_get_initial_sid_context(u32 sid);
+
+/*
+ * status notifier using mmap interface
+ */
+extern struct page *selinux_kernel_status_page(void);
+
+#define SELINUX_KERNEL_STATUS_VERSION 1
+struct selinux_kernel_status {
+	u32 version; /* version number of the structure */
+	u32 sequence; /* sequence number of seqlock logic */
+	u32 enforcing; /* current setting of enforcing mode */
+	u32 policyload; /* times of policy reloaded */
+	u32 deny_unknown; /* current setting of deny_unknown */
+	/*
+	 * The version > 0 supports above members.
+	 */
+} __packed;
+
+extern void selinux_status_update_setenforce(bool enforcing);
+extern void selinux_status_update_policyload(u32 seqno);
+extern void selinux_complete_init(void);
+extern struct path selinux_null;
+extern void selnl_notify_setenforce(int val);
+extern void selnl_notify_policyload(u32 seqno);
+extern int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm);
+
+extern void avtab_cache_init(void);
+extern void ebitmap_cache_init(void);
+extern void hashtab_cache_init(void);
+extern int security_sidtab_hash_stats(char *page);
+
+#endif /* _SELINUX_SECURITY_H_ */
diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h
new file mode 100644
index 000000000..de485556a
--- /dev/null
+++ b/security/selinux/include/xfrm.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * SELinux support for the XFRM LSM hooks
+ *
+ * Author : Trent Jaeger, <jaegert@us.ibm.com>
+ * Updated : Venkat Yekkirala, <vyekkirala@TrustedCS.com>
+ */
+
+#ifndef _SELINUX_XFRM_H_
+#define _SELINUX_XFRM_H_
+
+#include <linux/lsm_audit.h>
+#include <net/flow.h>
+#include <net/xfrm.h>
+
+int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+			      struct xfrm_user_sec_ctx *uctx, gfp_t gfp);
+int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
+			      struct xfrm_sec_ctx **new_ctxp);
+void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx);
+int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx);
+int selinux_xfrm_state_alloc(struct xfrm_state *x,
+			     struct xfrm_user_sec_ctx *uctx);
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+				     struct xfrm_sec_ctx *polsec, u32 secid);
+void selinux_xfrm_state_free(struct xfrm_state *x);
+int selinux_xfrm_state_delete(struct xfrm_state *x);
+int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid);
+int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
+				      struct xfrm_policy *xp,
+				      const struct flowi_common *flic);
+
+#ifdef CONFIG_SECURITY_NETWORK_XFRM
+extern atomic_t selinux_xfrm_refcount;
+
+static inline int selinux_xfrm_enabled(void)
+{
+	return (atomic_read(&selinux_xfrm_refcount) > 0);
+}
+
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+			      struct common_audit_data *ad);
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+				struct common_audit_data *ad, u8 proto);
+int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid);
+
+static inline void selinux_xfrm_notify_policyload(void)
+{
+	struct net *net;
+
+	down_read(&net_rwsem);
+	for_each_net(net)
+		rt_genid_bump_all(net);
+	up_read(&net_rwsem);
+}
+#else
+static inline int selinux_xfrm_enabled(void)
+{
+	return 0;
+}
+
+static inline int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+					    struct common_audit_data *ad)
+{
+	return 0;
+}
+
+static inline int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+					      struct common_audit_data *ad,
+					      u8 proto)
+{
+	return 0;
+}
+
+static inline int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid,
+					      int ckall)
+{
+	*sid = SECSID_NULL;
+	return 0;
+}
+
+static inline void selinux_xfrm_notify_policyload(void)
+{
+}
+
+static inline int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
+{
+	*sid = SECSID_NULL;
+	return 0;
+}
+#endif
+
+#endif /* _SELINUX_XFRM_H_ */
diff --git a/security/selinux/initcalls.c b/security/selinux/initcalls.c
new file mode 100644
index 000000000..f6716a1d3
--- /dev/null
+++ b/security/selinux/initcalls.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * SELinux initcalls
+ */
+
+#include <linux/init.h>
+
+#include "initcalls.h"
+
+/**
+ * selinux_initcall - Perform the SELinux initcalls
+ *
+ * Used as a device initcall in the SELinux LSM definition.
+ */
+int __init selinux_initcall(void)
+{
+	int rc = 0, rc_tmp = 0;
+
+	rc_tmp = init_sel_fs();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+
+	rc_tmp = sel_netport_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+
+	rc_tmp = sel_netnode_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+
+	rc_tmp = sel_netif_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+
+	rc_tmp = sel_netlink_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+
+#if defined(CONFIG_SECURITY_INFINIBAND)
+	rc_tmp = sel_ib_pkey_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+#endif
+
+#if defined(CONFIG_NETFILTER)
+	rc_tmp = selinux_nf_ip_init();
+	if (!rc && rc_tmp)
+		rc = rc_tmp;
+#endif
+
+	return rc;
+}
diff --git a/security/selinux/netif.c b/security/selinux/netif.c
new file mode 100644
index 000000000..fa6d24a37
--- /dev/null
+++ b/security/selinux/netif.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Network interface table.
+ *
+ * Network interfaces (devices) do not have a security field, so we
+ * maintain a table associating each interface with a SID.
+ *
+ * Author: James Morris <jmorris@redhat.com>
+ *
+ * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ * Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
+ *		      Paul Moore <paul@paul-moore.com>
+ */
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/rcupdate.h>
+#include <net/net_namespace.h>
+
+#include "initcalls.h"
+#include "security.h"
+#include "objsec.h"
+#include "netif.h"
+
+#define SEL_NETIF_HASH_SIZE	64
+#define SEL_NETIF_HASH_MAX	1024
+
+struct sel_netif {
+	struct list_head list;
+	struct netif_security_struct nsec;
+	struct rcu_head rcu_head;
+};
+
+static u32 sel_netif_total;
+static DEFINE_SPINLOCK(sel_netif_lock);
+static struct list_head sel_netif_hash[SEL_NETIF_HASH_SIZE];
+
+/**
+ * sel_netif_hashfn - Hashing function for the interface table
+ * @ns: the network namespace
+ * @ifindex: the network interface
+ *
+ * Description:
+ * This is the hashing function for the network interface table, it returns the
+ * bucket number for the given interface.
+ *
+ */
+static inline u32 sel_netif_hashfn(const struct net *ns, int ifindex)
+{
+	return (((uintptr_t)ns + ifindex) & (SEL_NETIF_HASH_SIZE - 1));
+}
+
+/**
+ * sel_netif_find - Search for an interface record
+ * @ns: the network namespace
+ * @ifindex: the network interface
+ *
+ * Description:
+ * Search the network interface table and return the record matching @ifindex.
+ * If an entry can not be found in the table return NULL.
+ *
+ */
+static inline struct sel_netif *sel_netif_find(const struct net *ns,
+					       int ifindex)
+{
+	u32 idx = sel_netif_hashfn(ns, ifindex);
+	struct sel_netif *netif;
+
+	list_for_each_entry_rcu(netif, &sel_netif_hash[idx], list)
+		if (net_eq(netif->nsec.ns, ns) &&
+		    netif->nsec.ifindex == ifindex)
+			return netif;
+
+	return NULL;
+}
+
+/**
+ * sel_netif_insert - Insert a new interface into the table
+ * @netif: the new interface record
+ *
+ * Description:
+ * Add a new interface record to the network interface hash table.  Returns
+ * zero on success, negative values on failure.
+ *
+ */
+static int sel_netif_insert(struct sel_netif *netif)
+{
+	u32 idx;
+
+	if (sel_netif_total >= SEL_NETIF_HASH_MAX)
+		return -ENOSPC;
+
+	idx = sel_netif_hashfn(netif->nsec.ns, netif->nsec.ifindex);
+	list_add_rcu(&netif->list, &sel_netif_hash[idx]);
+	sel_netif_total++;
+
+	return 0;
+}
+
+/**
+ * sel_netif_destroy - Remove an interface record from the table
+ * @netif: the existing interface record
+ *
+ * Description:
+ * Remove an existing interface record from the network interface table.
+ *
+ */
+static void sel_netif_destroy(struct sel_netif *netif)
+{
+	list_del_rcu(&netif->list);
+	sel_netif_total--;
+	kfree_rcu(netif, rcu_head);
+}
+
+/**
+ * sel_netif_sid_slow - Lookup the SID of a network interface using the policy
+ * @ns: the network namespace
+ * @ifindex: the network interface
+ * @sid: interface SID
+ *
+ * Description:
+ * This function determines the SID of a network interface by querying the
+ * security policy.  The result is added to the network interface table to
+ * speedup future queries.  Returns zero on success, negative values on
+ * failure.
+ *
+ */
+static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid)
+{
+	int ret = 0;
+	struct sel_netif *netif;
+	struct sel_netif *new;
+	struct net_device *dev;
+
+	/* NOTE: we always use init's network namespace since we don't
+	 * currently support containers */
+
+	dev = dev_get_by_index(ns, ifindex);
+	if (unlikely(dev == NULL)) {
+		pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n",
+			__func__, ifindex);
+		return -ENOENT;
+	}
+
+	spin_lock_bh(&sel_netif_lock);
+	netif = sel_netif_find(ns, ifindex);
+	if (netif != NULL) {
+		*sid = netif->nsec.sid;
+		goto out;
+	}
+
+	ret = security_netif_sid(dev->name, sid);
+	if (ret != 0)
+		goto out;
+
+	/* If this memory allocation fails still return 0. The SID
+	 * is valid, it just won't be added to the cache.
+	 */
+	new = kmalloc_obj(*new, GFP_ATOMIC);
+	if (new) {
+		new->nsec.ns = ns;
+		new->nsec.ifindex = ifindex;
+		new->nsec.sid = *sid;
+		if (sel_netif_insert(new))
+			kfree(new);
+	}
+
+out:
+	spin_unlock_bh(&sel_netif_lock);
+	dev_put(dev);
+	if (unlikely(ret))
+		pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n",
+			__func__, ifindex);
+	return ret;
+}
+
+/**
+ * sel_netif_sid - Lookup the SID of a network interface
+ * @ns: the network namespace
+ * @ifindex: the network interface
+ * @sid: interface SID
+ *
+ * Description:
+ * This function determines the SID of a network interface using the fastest
+ * method possible.  First the interface table is queried, but if an entry
+ * can't be found then the policy is queried and the result is added to the
+ * table to speedup future queries.  Returns zero on success, negative values
+ * on failure.
+ *
+ */
+int sel_netif_sid(struct net *ns, int ifindex, u32 *sid)
+{
+	struct sel_netif *netif;
+
+	rcu_read_lock();
+	netif = sel_netif_find(ns, ifindex);
+	if (likely(netif != NULL)) {
+		*sid = netif->nsec.sid;
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+
+	return sel_netif_sid_slow(ns, ifindex, sid);
+}
+
+/**
+ * sel_netif_kill - Remove an entry from the network interface table
+ * @ns: the network namespace
+ * @ifindex: the network interface
+ *
+ * Description:
+ * This function removes the entry matching @ifindex from the network interface
+ * table if it exists.
+ *
+ */
+static void sel_netif_kill(const struct net *ns, int ifindex)
+{
+	struct sel_netif *netif;
+
+	rcu_read_lock();
+	spin_lock_bh(&sel_netif_lock);
+	netif = sel_netif_find(ns, ifindex);
+	if (netif)
+		sel_netif_destroy(netif);
+	spin_unlock_bh(&sel_netif_lock);
+	rcu_read_unlock();
+}
+
+/**
+ * sel_netif_flush - Flush the entire network interface table
+ *
+ * Description:
+ * Remove all entries from the network interface table.
+ *
+ */
+void sel_netif_flush(void)
+{
+	int idx;
+	struct sel_netif *netif;
+
+	spin_lock_bh(&sel_netif_lock);
+	for (idx = 0; idx < SEL_NETIF_HASH_SIZE; idx++)
+		list_for_each_entry(netif, &sel_netif_hash[idx], list)
+			sel_netif_destroy(netif);
+	spin_unlock_bh(&sel_netif_lock);
+}
+
+static int sel_netif_netdev_notifier_handler(struct notifier_block *this,
+					     unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (event == NETDEV_DOWN)
+		sel_netif_kill(dev_net(dev), dev->ifindex);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block sel_netif_netdev_notifier = {
+	.notifier_call = sel_netif_netdev_notifier_handler,
+};
+
+int __init sel_netif_init(void)
+{
+	int i;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	for (i = 0; i < SEL_NETIF_HASH_SIZE; i++)
+		INIT_LIST_HEAD(&sel_netif_hash[i]);
+
+	register_netdevice_notifier(&sel_netif_netdev_notifier);
+
+	return 0;
+}
+
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
new file mode 100644
index 000000000..d51dfe892
--- /dev/null
+++ b/security/selinux/netlabel.c
@@ -0,0 +1,619 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SELinux NetLabel Support
+ *
+ * This file provides the necessary glue to tie NetLabel into the SELinux
+ * subsystem.
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2007, 2008
+ */
+
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+#include <linux/gfp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/lsm_hooks.h>
+#include <net/sock.h>
+#include <net/netlabel.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+#include "objsec.h"
+#include "security.h"
+#include "netlabel.h"
+
+/**
+ * selinux_netlbl_sidlookup_cached - Cache a SID lookup
+ * @skb: the packet
+ * @family: the packet's address family
+ * @secattr: the NetLabel security attributes
+ * @sid: the SID
+ *
+ * Description:
+ * Query the SELinux security server to lookup the correct SID for the given
+ * security attributes.  If the query is successful, cache the result to speed
+ * up future lookups.  Returns zero on success, negative values on failure.
+ *
+ */
+static int selinux_netlbl_sidlookup_cached(struct sk_buff *skb,
+					   u16 family,
+					   struct netlbl_lsm_secattr *secattr,
+					   u32 *sid)
+{
+	int rc;
+
+	rc = security_netlbl_secattr_to_sid(secattr, sid);
+	if (rc == 0 &&
+	    (secattr->flags & NETLBL_SECATTR_CACHEABLE) &&
+	    (secattr->flags & NETLBL_SECATTR_CACHE))
+		netlbl_cache_add(skb, family, secattr);
+
+	return rc;
+}
+
+/**
+ * selinux_netlbl_sock_genattr - Generate the NetLabel socket secattr
+ * @sk: the socket
+ *
+ * Description:
+ * Generate the NetLabel security attributes for a socket, making full use of
+ * the socket's attribute cache.  Returns a pointer to the security attributes
+ * on success, or an ERR_PTR on failure.
+ *
+ */
+static struct netlbl_lsm_secattr *selinux_netlbl_sock_genattr(struct sock *sk)
+{
+	int rc;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct netlbl_lsm_secattr *secattr;
+
+	if (sksec->nlbl_secattr != NULL)
+		return sksec->nlbl_secattr;
+
+	secattr = netlbl_secattr_alloc(GFP_ATOMIC);
+	if (secattr == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	rc = security_netlbl_sid_to_secattr(sksec->sid, secattr);
+	if (rc != 0) {
+		netlbl_secattr_free(secattr);
+		return ERR_PTR(rc);
+	}
+	sksec->nlbl_secattr = secattr;
+
+	return secattr;
+}
+
+/**
+ * selinux_netlbl_sock_getattr - Get the cached NetLabel secattr
+ * @sk: the socket
+ * @sid: the SID
+ *
+ * Query the socket's cached secattr and if the SID matches the cached value
+ * return the cache, otherwise return NULL.
+ *
+ */
+static struct netlbl_lsm_secattr *selinux_netlbl_sock_getattr(
+							const struct sock *sk,
+							u32 sid)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct netlbl_lsm_secattr *secattr = sksec->nlbl_secattr;
+
+	if (secattr == NULL)
+		return NULL;
+
+	if ((secattr->flags & NETLBL_SECATTR_SECID) &&
+	    (secattr->attr.secid == sid))
+		return secattr;
+
+	return NULL;
+}
+
+/**
+ * selinux_netlbl_cache_invalidate - Invalidate the NetLabel cache
+ *
+ * Description:
+ * Invalidate the NetLabel security attribute mapping cache.
+ *
+ */
+void selinux_netlbl_cache_invalidate(void)
+{
+	netlbl_cache_invalidate();
+}
+
+/**
+ * selinux_netlbl_err - Handle a NetLabel packet error
+ * @skb: the packet
+ * @family: the packet's address family
+ * @error: the error code
+ * @gateway: true if host is acting as a gateway, false otherwise
+ *
+ * Description:
+ * When a packet is dropped due to a call to avc_has_perm() pass the error
+ * code to the NetLabel subsystem so any protocol specific processing can be
+ * done.  This is safe to call even if you are unsure if NetLabel labeling is
+ * present on the packet, NetLabel is smart enough to only act when it should.
+ *
+ */
+void selinux_netlbl_err(struct sk_buff *skb, u16 family, int error, int gateway)
+{
+	netlbl_skbuff_err(skb, family, error, gateway);
+}
+
+/**
+ * selinux_netlbl_sk_security_free - Free the NetLabel fields
+ * @sksec: the sk_security_struct
+ *
+ * Description:
+ * Free all of the memory in the NetLabel fields of a sk_security_struct.
+ *
+ */
+void selinux_netlbl_sk_security_free(struct sk_security_struct *sksec)
+{
+	if (!sksec->nlbl_secattr)
+		return;
+
+	netlbl_secattr_free(sksec->nlbl_secattr);
+	sksec->nlbl_secattr = NULL;
+	sksec->nlbl_state = NLBL_UNSET;
+}
+
+/**
+ * selinux_netlbl_sk_security_reset - Reset the NetLabel fields
+ * @sksec: the sk_security_struct
+ *
+ * Description:
+ * Called when the NetLabel state of a sk_security_struct needs to be reset.
+ * The caller is responsible for all the NetLabel sk_security_struct locking.
+ *
+ */
+void selinux_netlbl_sk_security_reset(struct sk_security_struct *sksec)
+{
+	sksec->nlbl_state = NLBL_UNSET;
+}
+
+/**
+ * selinux_netlbl_skbuff_getsid - Get the sid of a packet using NetLabel
+ * @skb: the packet
+ * @family: protocol family
+ * @type: NetLabel labeling protocol type
+ * @sid: the SID
+ *
+ * Description:
+ * Call the NetLabel mechanism to get the security attributes of the given
+ * packet and use those attributes to determine the correct context/SID to
+ * assign to the packet.  Returns zero on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_skbuff_getsid(struct sk_buff *skb,
+				 u16 family,
+				 u32 *type,
+				 u32 *sid)
+{
+	int rc;
+	struct netlbl_lsm_secattr secattr;
+
+	if (!netlbl_enabled()) {
+		*type = NETLBL_NLTYPE_NONE;
+		*sid = SECSID_NULL;
+		return 0;
+	}
+
+	netlbl_secattr_init(&secattr);
+	rc = netlbl_skbuff_getattr(skb, family, &secattr);
+	if (rc == 0 && secattr.flags != NETLBL_SECATTR_NONE)
+		rc = selinux_netlbl_sidlookup_cached(skb, family,
+						     &secattr, sid);
+	else
+		*sid = SECSID_NULL;
+	*type = secattr.type;
+	netlbl_secattr_destroy(&secattr);
+
+	return rc;
+}
+
+/**
+ * selinux_netlbl_skbuff_setsid - Set the NetLabel on a packet given a sid
+ * @skb: the packet
+ * @family: protocol family
+ * @sid: the SID
+ *
+ * Description
+ * Call the NetLabel mechanism to set the label of a packet using @sid.
+ * Returns zero on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_skbuff_setsid(struct sk_buff *skb,
+				 u16 family,
+				 u32 sid)
+{
+	int rc;
+	struct netlbl_lsm_secattr secattr_storage;
+	struct netlbl_lsm_secattr *secattr = NULL;
+	struct sock *sk;
+
+	/* if this is a locally generated packet check to see if it is already
+	 * being labeled by it's parent socket, if it is just exit */
+	sk = skb_to_full_sk(skb);
+	if (sk != NULL) {
+		struct sk_security_struct *sksec = selinux_sock(sk);
+
+		if (sksec->nlbl_state != NLBL_REQSKB)
+			return 0;
+		secattr = selinux_netlbl_sock_getattr(sk, sid);
+	}
+	if (secattr == NULL) {
+		secattr = &secattr_storage;
+		netlbl_secattr_init(secattr);
+		rc = security_netlbl_sid_to_secattr(sid, secattr);
+		if (rc != 0)
+			goto skbuff_setsid_return;
+	}
+
+	rc = netlbl_skbuff_setattr(skb, family, secattr);
+
+skbuff_setsid_return:
+	if (secattr == &secattr_storage)
+		netlbl_secattr_destroy(secattr);
+	return rc;
+}
+
+/**
+ * selinux_netlbl_sctp_assoc_request - Label an incoming sctp association.
+ * @asoc: incoming association.
+ * @skb: the packet.
+ *
+ * Description:
+ * A new incoming connection is represented by @asoc, ......
+ * Returns zero on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
+				     struct sk_buff *skb)
+{
+	int rc;
+	struct netlbl_lsm_secattr secattr;
+	struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+	struct sockaddr_in addr4;
+	struct sockaddr_in6 addr6;
+
+	if (asoc->base.sk->sk_family != PF_INET &&
+	    asoc->base.sk->sk_family != PF_INET6)
+		return 0;
+
+	netlbl_secattr_init(&secattr);
+	rc = security_netlbl_sid_to_secattr(asoc->secid, &secattr);
+	if (rc != 0)
+		goto assoc_request_return;
+
+	/* Move skb hdr address info to a struct sockaddr and then call
+	 * netlbl_conn_setattr().
+	 */
+	if (ip_hdr(skb)->version == 4) {
+		addr4.sin_family = AF_INET;
+		addr4.sin_addr.s_addr = ip_hdr(skb)->saddr;
+		rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr4, &secattr);
+	} else if (IS_ENABLED(CONFIG_IPV6) && ip_hdr(skb)->version == 6) {
+		addr6.sin6_family = AF_INET6;
+		addr6.sin6_addr = ipv6_hdr(skb)->saddr;
+		rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr6, &secattr);
+	} else {
+		rc = -EAFNOSUPPORT;
+	}
+
+	if (rc == 0)
+		sksec->nlbl_state = NLBL_LABELED;
+
+assoc_request_return:
+	netlbl_secattr_destroy(&secattr);
+	return rc;
+}
+
+/**
+ * selinux_netlbl_inet_conn_request - Label an incoming stream connection
+ * @req: incoming connection request socket
+ * @family: the request socket's address family
+ *
+ * Description:
+ * A new incoming connection request is represented by @req, we need to label
+ * the new request_sock here and the stack will ensure the on-the-wire label
+ * will get preserved when a full sock is created once the connection handshake
+ * is complete.  Returns zero on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family)
+{
+	int rc;
+	struct netlbl_lsm_secattr secattr;
+
+	if (family != PF_INET && family != PF_INET6)
+		return 0;
+
+	netlbl_secattr_init(&secattr);
+	rc = security_netlbl_sid_to_secattr(req->secid, &secattr);
+	if (rc != 0)
+		goto inet_conn_request_return;
+	rc = netlbl_req_setattr(req, &secattr);
+inet_conn_request_return:
+	netlbl_secattr_destroy(&secattr);
+	return rc;
+}
+
+/**
+ * selinux_netlbl_inet_csk_clone - Initialize the newly created sock
+ * @sk: the new sock
+ * @family: the sock's address family
+ *
+ * Description:
+ * A new connection has been established using @sk, we've already labeled the
+ * socket via the request_sock struct in selinux_netlbl_inet_conn_request() but
+ * we need to set the NetLabel state here since we now have a sock structure.
+ *
+ */
+void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	if (family == PF_INET || family == PF_INET6)
+		sksec->nlbl_state = NLBL_LABELED;
+	else
+		sksec->nlbl_state = NLBL_UNSET;
+}
+
+/**
+ * selinux_netlbl_sctp_sk_clone - Copy state to the newly created sock
+ * @sk: current sock
+ * @newsk: the new sock
+ *
+ * Description:
+ * Called whenever a new socket is created by accept(2) or sctp_peeloff(3).
+ */
+void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+	newsksec->nlbl_state = sksec->nlbl_state;
+}
+
+/**
+ * selinux_netlbl_socket_post_create - Label a socket using NetLabel
+ * @sk: the sock to label
+ * @family: protocol family
+ *
+ * Description:
+ * Attempt to label a socket using the NetLabel mechanism using the given
+ * SID.  Returns zero values on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_socket_post_create(struct sock *sk, u16 family)
+{
+	int rc;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct netlbl_lsm_secattr *secattr;
+
+	if (family != PF_INET && family != PF_INET6)
+		return 0;
+
+	secattr = selinux_netlbl_sock_genattr(sk);
+	if (IS_ERR(secattr))
+		return PTR_ERR(secattr);
+	/* On socket creation, replacement of IP options is safe even if
+	 * the caller does not hold the socket lock.
+	 */
+	rc = netlbl_sock_setattr(sk, family, secattr, true);
+	switch (rc) {
+	case 0:
+		sksec->nlbl_state = NLBL_LABELED;
+		break;
+	case -EDESTADDRREQ:
+		sksec->nlbl_state = NLBL_REQSKB;
+		rc = 0;
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * selinux_netlbl_sock_rcv_skb - Do an inbound access check using NetLabel
+ * @sksec: the sock's sk_security_struct
+ * @skb: the packet
+ * @family: protocol family
+ * @ad: the audit data
+ *
+ * Description:
+ * Fetch the NetLabel security attributes from @skb and perform an access check
+ * against the receiving socket.  Returns zero on success, negative values on
+ * error.
+ *
+ */
+int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec,
+				struct sk_buff *skb,
+				u16 family,
+				struct common_audit_data *ad)
+{
+	int rc;
+	u32 nlbl_sid;
+	u32 perm;
+	struct netlbl_lsm_secattr secattr;
+
+	if (!netlbl_enabled())
+		return 0;
+
+	netlbl_secattr_init(&secattr);
+	rc = netlbl_skbuff_getattr(skb, family, &secattr);
+	if (rc == 0 && secattr.flags != NETLBL_SECATTR_NONE)
+		rc = selinux_netlbl_sidlookup_cached(skb, family,
+						     &secattr, &nlbl_sid);
+	else
+		nlbl_sid = SECINITSID_UNLABELED;
+	netlbl_secattr_destroy(&secattr);
+	if (rc != 0)
+		return rc;
+
+	switch (sksec->sclass) {
+	case SECCLASS_UDP_SOCKET:
+		perm = UDP_SOCKET__RECVFROM;
+		break;
+	case SECCLASS_TCP_SOCKET:
+		perm = TCP_SOCKET__RECVFROM;
+		break;
+	default:
+		perm = RAWIP_SOCKET__RECVFROM;
+	}
+
+	rc = avc_has_perm(sksec->sid, nlbl_sid, sksec->sclass, perm, ad);
+	if (rc == 0)
+		return 0;
+
+	if (nlbl_sid != SECINITSID_UNLABELED)
+		netlbl_skbuff_err(skb, family, rc, 0);
+	return rc;
+}
+
+/**
+ * selinux_netlbl_option - Is this a NetLabel option
+ * @level: the socket level or protocol
+ * @optname: the socket option name
+ *
+ * Description:
+ * Returns true if @level and @optname refer to a NetLabel option.
+ * Helper for selinux_netlbl_socket_setsockopt().
+ */
+static inline int selinux_netlbl_option(int level, int optname)
+{
+	return (level == IPPROTO_IP && optname == IP_OPTIONS) ||
+		(level == IPPROTO_IPV6 && optname == IPV6_HOPOPTS);
+}
+
+/**
+ * selinux_netlbl_socket_setsockopt - Do not allow users to remove a NetLabel
+ * @sock: the socket
+ * @level: the socket level or protocol
+ * @optname: the socket option name
+ *
+ * Description:
+ * Check the setsockopt() call and if the user is trying to replace the IP
+ * options on a socket and a NetLabel is in place for the socket deny the
+ * access; otherwise allow the access.  Returns zero when the access is
+ * allowed, -EACCES when denied, and other negative values on error.
+ *
+ */
+int selinux_netlbl_socket_setsockopt(struct socket *sock,
+				     int level,
+				     int optname)
+{
+	int rc = 0;
+	struct sock *sk = sock->sk;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct netlbl_lsm_secattr secattr;
+
+	if (selinux_netlbl_option(level, optname) &&
+	    (sksec->nlbl_state == NLBL_LABELED ||
+	     sksec->nlbl_state == NLBL_CONNLABELED)) {
+		netlbl_secattr_init(&secattr);
+		lock_sock(sk);
+		/* call the netlabel function directly as we want to see the
+		 * on-the-wire label that is assigned via the socket's options
+		 * and not the cached netlabel/lsm attributes */
+		rc = netlbl_sock_getattr(sk, &secattr);
+		release_sock(sk);
+		if (rc == 0)
+			rc = -EACCES;
+		else if (rc == -ENOMSG)
+			rc = 0;
+		netlbl_secattr_destroy(&secattr);
+	}
+
+	return rc;
+}
+
+/**
+ * selinux_netlbl_socket_connect_helper - Help label a client-side socket on
+ * connect
+ * @sk: the socket to label
+ * @addr: the destination address
+ *
+ * Description:
+ * Attempt to label a connected socket with NetLabel using the given address.
+ * Returns zero values on success, negative values on failure.
+ *
+ */
+static int selinux_netlbl_socket_connect_helper(struct sock *sk,
+						struct sockaddr *addr)
+{
+	int rc;
+	struct sk_security_struct *sksec = selinux_sock(sk);
+	struct netlbl_lsm_secattr *secattr;
+
+	/* connected sockets are allowed to disconnect when the address family
+	 * is set to AF_UNSPEC, if that is what is happening we want to reset
+	 * the socket */
+	if (addr->sa_family == AF_UNSPEC) {
+		netlbl_sock_delattr(sk);
+		sksec->nlbl_state = NLBL_REQSKB;
+		rc = 0;
+		return rc;
+	}
+	secattr = selinux_netlbl_sock_genattr(sk);
+	if (IS_ERR(secattr))
+		return PTR_ERR(secattr);
+
+	rc = netlbl_conn_setattr(sk, addr, secattr);
+	if (rc == 0)
+		sksec->nlbl_state = NLBL_CONNLABELED;
+
+	return rc;
+}
+
+/**
+ * selinux_netlbl_socket_connect_locked - Label a client-side socket on
+ * connect
+ * @sk: the socket to label
+ * @addr: the destination address
+ *
+ * Description:
+ * Attempt to label a connected socket that already has the socket locked
+ * with NetLabel using the given address.
+ * Returns zero values on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_socket_connect_locked(struct sock *sk,
+					 struct sockaddr *addr)
+{
+	struct sk_security_struct *sksec = selinux_sock(sk);
+
+	if (sksec->nlbl_state != NLBL_REQSKB &&
+	    sksec->nlbl_state != NLBL_CONNLABELED)
+		return 0;
+
+	return selinux_netlbl_socket_connect_helper(sk, addr);
+}
+
+/**
+ * selinux_netlbl_socket_connect - Label a client-side socket on connect
+ * @sk: the socket to label
+ * @addr: the destination address
+ *
+ * Description:
+ * Attempt to label a connected socket with NetLabel using the given address.
+ * Returns zero values on success, negative values on failure.
+ *
+ */
+int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr)
+{
+	int rc;
+
+	lock_sock(sk);
+	rc = selinux_netlbl_socket_connect_locked(sk, addr);
+	release_sock(sk);
+
+	return rc;
+}
diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c
new file mode 100644
index 000000000..eb40e4603
--- /dev/null
+++ b/security/selinux/netlink.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Netlink event notifications for SELinux.
+ *
+ * Author: James Morris <jmorris@redhat.com>
+ *
+ * Copyright (C) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ */
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/skbuff.h>
+#include <linux/selinux_netlink.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+
+#include "initcalls.h"
+#include "security.h"
+
+static struct sock *selnl __ro_after_init;
+
+static int selnl_msglen(int msgtype)
+{
+	int ret = 0;
+
+	switch (msgtype) {
+	case SELNL_MSG_SETENFORCE:
+		ret = sizeof(struct selnl_msg_setenforce);
+		break;
+
+	case SELNL_MSG_POLICYLOAD:
+		ret = sizeof(struct selnl_msg_policyload);
+		break;
+
+	default:
+		BUG();
+	}
+	return ret;
+}
+
+static void selnl_add_payload(struct nlmsghdr *nlh, int len, int msgtype, void *data)
+{
+	switch (msgtype) {
+	case SELNL_MSG_SETENFORCE: {
+		struct selnl_msg_setenforce *msg = nlmsg_data(nlh);
+
+		memset(msg, 0, len);
+		msg->val = *((int *)data);
+		break;
+	}
+
+	case SELNL_MSG_POLICYLOAD: {
+		struct selnl_msg_policyload *msg = nlmsg_data(nlh);
+
+		memset(msg, 0, len);
+		msg->seqno = *((u32 *)data);
+		break;
+	}
+
+	default:
+		BUG();
+	}
+}
+
+static void selnl_notify(int msgtype, void *data)
+{
+	int len;
+	sk_buff_data_t tmp;
+	struct sk_buff *skb;
+	struct nlmsghdr *nlh;
+
+	len = selnl_msglen(msgtype);
+
+	skb = nlmsg_new(len, GFP_USER);
+	if (!skb)
+		goto oom;
+
+	tmp = skb->tail;
+	nlh = nlmsg_put(skb, 0, 0, msgtype, len, 0);
+	if (!nlh)
+		goto out_kfree_skb;
+	selnl_add_payload(nlh, len, msgtype, data);
+	nlh->nlmsg_len = skb->tail - tmp;
+	NETLINK_CB(skb).dst_group = SELNLGRP_AVC;
+	netlink_broadcast(selnl, skb, 0, SELNLGRP_AVC, GFP_USER);
+out:
+	return;
+
+out_kfree_skb:
+	kfree_skb(skb);
+oom:
+	pr_err("SELinux:  OOM in %s\n", __func__);
+	goto out;
+}
+
+void selnl_notify_setenforce(int val)
+{
+	selnl_notify(SELNL_MSG_SETENFORCE, &val);
+}
+
+void selnl_notify_policyload(u32 seqno)
+{
+	selnl_notify(SELNL_MSG_POLICYLOAD, &seqno);
+}
+
+int __init sel_netlink_init(void)
+{
+	struct netlink_kernel_cfg cfg = {
+		.groups	= SELNLGRP_MAX,
+		.flags	= NL_CFG_F_NONROOT_RECV,
+	};
+
+	selnl = netlink_kernel_create(&init_net, NETLINK_SELINUX, &cfg);
+	if (selnl == NULL)
+		panic("SELinux:  Cannot create netlink socket.");
+	return 0;
+}
diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
new file mode 100644
index 000000000..adb93003b
--- /dev/null
+++ b/security/selinux/netnode.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Network node table
+ *
+ * SELinux must keep a mapping of network nodes to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead since most of these queries happen on
+ * a per-packet basis.
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ *
+ * This code is heavily based on the "netif" concept originally developed by
+ * James Morris <jmorris@redhat.com>
+ *   (see security/selinux/netif.c for more information)
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2007
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+#include "initcalls.h"
+#include "netnode.h"
+#include "objsec.h"
+
+#define SEL_NETNODE_HASH_SIZE       256
+#define SEL_NETNODE_HASH_BKT_LIMIT   16
+
+struct sel_netnode_bkt {
+	unsigned int size;
+	struct list_head list;
+};
+
+struct sel_netnode {
+	struct netnode_security_struct nsec;
+
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+/* NOTE: we are using a combined hash table for both IPv4 and IPv6, the reason
+ * for this is that I suspect most users will not make heavy use of both
+ * address families at the same time so one table will usually end up wasted,
+ * if this becomes a problem we can always add a hash table for each address
+ * family later */
+
+static DEFINE_SPINLOCK(sel_netnode_lock);
+static struct sel_netnode_bkt sel_netnode_hash[SEL_NETNODE_HASH_SIZE];
+
+/**
+ * sel_netnode_hashfn_ipv4 - IPv4 hashing function for the node table
+ * @addr: IPv4 address
+ *
+ * Description:
+ * This is the IPv4 hashing function for the node interface table, it returns
+ * the bucket number for the given IP address.
+ *
+ */
+static unsigned int sel_netnode_hashfn_ipv4(__be32 addr)
+{
+	/* at some point we should determine if the mismatch in byte order
+	 * affects the hash function dramatically */
+	return (addr & (SEL_NETNODE_HASH_SIZE - 1));
+}
+
+/**
+ * sel_netnode_hashfn_ipv6 - IPv6 hashing function for the node table
+ * @addr: IPv6 address
+ *
+ * Description:
+ * This is the IPv6 hashing function for the node interface table, it returns
+ * the bucket number for the given IP address.
+ *
+ */
+static unsigned int sel_netnode_hashfn_ipv6(const struct in6_addr *addr)
+{
+	/* just hash the least significant 32 bits to keep things fast (they
+	 * are the most likely to be different anyway), we can revisit this
+	 * later if needed */
+	return (addr->s6_addr32[3] & (SEL_NETNODE_HASH_SIZE - 1));
+}
+
+/**
+ * sel_netnode_find - Search for a node record
+ * @addr: IP address
+ * @family: address family
+ *
+ * Description:
+ * Search the network node table and return the record matching @addr.  If an
+ * entry can not be found in the table return NULL.
+ *
+ */
+static struct sel_netnode *sel_netnode_find(const void *addr, u16 family)
+{
+	unsigned int idx;
+	struct sel_netnode *node;
+
+	switch (family) {
+	case PF_INET:
+		idx = sel_netnode_hashfn_ipv4(*(const __be32 *)addr);
+		break;
+	case PF_INET6:
+		idx = sel_netnode_hashfn_ipv6(addr);
+		break;
+	default:
+		BUG();
+		return NULL;
+	}
+
+	list_for_each_entry_rcu(node, &sel_netnode_hash[idx].list, list)
+		if (node->nsec.family == family)
+			switch (family) {
+			case PF_INET:
+				if (node->nsec.addr.ipv4 == *(const __be32 *)addr)
+					return node;
+				break;
+			case PF_INET6:
+				if (ipv6_addr_equal(&node->nsec.addr.ipv6,
+						    addr))
+					return node;
+				break;
+			}
+
+	return NULL;
+}
+
+/**
+ * sel_netnode_insert - Insert a new node into the table
+ * @node: the new node record
+ *
+ * Description:
+ * Add a new node record to the network address hash table.
+ *
+ */
+static void sel_netnode_insert(struct sel_netnode *node)
+{
+	unsigned int idx;
+
+	switch (node->nsec.family) {
+	case PF_INET:
+		idx = sel_netnode_hashfn_ipv4(node->nsec.addr.ipv4);
+		break;
+	case PF_INET6:
+		idx = sel_netnode_hashfn_ipv6(&node->nsec.addr.ipv6);
+		break;
+	default:
+		BUG();
+		return;
+	}
+
+	/* we need to impose a limit on the growth of the hash table so check
+	 * this bucket to make sure it is within the specified bounds */
+	list_add_rcu(&node->list, &sel_netnode_hash[idx].list);
+	if (sel_netnode_hash[idx].size == SEL_NETNODE_HASH_BKT_LIMIT) {
+		struct sel_netnode *tail;
+		tail = list_entry(
+			rcu_dereference_protected(
+				list_tail_rcu(&sel_netnode_hash[idx].list),
+				lockdep_is_held(&sel_netnode_lock)),
+			struct sel_netnode, list);
+		list_del_rcu(&tail->list);
+		kfree_rcu(tail, rcu);
+	} else
+		sel_netnode_hash[idx].size++;
+}
+
+/**
+ * sel_netnode_sid_slow - Lookup the SID of a network address using the policy
+ * @addr: the IP address
+ * @family: the address family
+ * @sid: node SID
+ *
+ * Description:
+ * This function determines the SID of a network address by querying the
+ * security policy.  The result is added to the network address table to
+ * speedup future queries.  Returns zero on success, negative values on
+ * failure.
+ *
+ */
+static int sel_netnode_sid_slow(const void *addr, u16 family, u32 *sid)
+{
+	int ret;
+	struct sel_netnode *node;
+	struct sel_netnode *new;
+
+	spin_lock_bh(&sel_netnode_lock);
+	node = sel_netnode_find(addr, family);
+	if (node != NULL) {
+		*sid = node->nsec.sid;
+		spin_unlock_bh(&sel_netnode_lock);
+		return 0;
+	}
+
+	/* If this memory allocation fails still return 0. The SID
+	 * is valid, it just won't be added to the cache.
+	 */
+	new = kmalloc_obj(*new, GFP_ATOMIC);
+	switch (family) {
+	case PF_INET:
+		ret = security_node_sid(PF_INET,
+					addr, sizeof(struct in_addr), sid);
+		if (new)
+			new->nsec.addr.ipv4 = *(const __be32 *)addr;
+		break;
+	case PF_INET6:
+		ret = security_node_sid(PF_INET6,
+					addr, sizeof(struct in6_addr), sid);
+		if (new)
+			new->nsec.addr.ipv6 = *(const struct in6_addr *)addr;
+		break;
+	default:
+		BUG();
+		ret = -EINVAL;
+	}
+	if (ret == 0 && new) {
+		new->nsec.family = family;
+		new->nsec.sid = *sid;
+		sel_netnode_insert(new);
+	} else
+		kfree(new);
+
+	spin_unlock_bh(&sel_netnode_lock);
+	if (unlikely(ret))
+		pr_warn("SELinux: failure in %s(), unable to determine network node label\n",
+			__func__);
+	return ret;
+}
+
+/**
+ * sel_netnode_sid - Lookup the SID of a network address
+ * @addr: the IP address
+ * @family: the address family
+ * @sid: node SID
+ *
+ * Description:
+ * This function determines the SID of a network address using the fastest
+ * method possible.  First the address table is queried, but if an entry
+ * can't be found then the policy is queried and the result is added to the
+ * table to speedup future queries.  Returns zero on success, negative values
+ * on failure.
+ *
+ */
+int sel_netnode_sid(const void *addr, u16 family, u32 *sid)
+{
+	struct sel_netnode *node;
+
+	rcu_read_lock();
+	node = sel_netnode_find(addr, family);
+	if (likely(node != NULL)) {
+		*sid = node->nsec.sid;
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+
+	return sel_netnode_sid_slow(addr, family, sid);
+}
+
+/**
+ * sel_netnode_flush - Flush the entire network address table
+ *
+ * Description:
+ * Remove all entries from the network address table.
+ *
+ */
+void sel_netnode_flush(void)
+{
+	unsigned int idx;
+	struct sel_netnode *node, *node_tmp;
+
+	spin_lock_bh(&sel_netnode_lock);
+	for (idx = 0; idx < SEL_NETNODE_HASH_SIZE; idx++) {
+		list_for_each_entry_safe(node, node_tmp,
+					 &sel_netnode_hash[idx].list, list) {
+				list_del_rcu(&node->list);
+				kfree_rcu(node, rcu);
+		}
+		sel_netnode_hash[idx].size = 0;
+	}
+	spin_unlock_bh(&sel_netnode_lock);
+}
+
+int __init sel_netnode_init(void)
+{
+	int iter;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	for (iter = 0; iter < SEL_NETNODE_HASH_SIZE; iter++) {
+		INIT_LIST_HEAD(&sel_netnode_hash[iter].list);
+		sel_netnode_hash[iter].size = 0;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/netport.c b/security/selinux/netport.c
new file mode 100644
index 000000000..006a6ec71
--- /dev/null
+++ b/security/selinux/netport.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Network port table
+ *
+ * SELinux must keep a mapping of network ports to labels/SIDs.  This
+ * mapping is maintained as part of the normal policy but a fast cache is
+ * needed to reduce the lookup overhead.
+ *
+ * Author: Paul Moore <paul@paul-moore.com>
+ *
+ * This code is heavily based on the "netif" concept originally developed by
+ * James Morris <jmorris@redhat.com>
+ *   (see security/selinux/netif.c for more information)
+ */
+
+/*
+ * (c) Copyright Hewlett-Packard Development Company, L.P., 2008
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+
+#include "initcalls.h"
+#include "netport.h"
+#include "objsec.h"
+
+#define SEL_NETPORT_HASH_SIZE       256
+#define SEL_NETPORT_HASH_BKT_LIMIT   16
+
+struct sel_netport_bkt {
+	int size;
+	struct list_head list;
+};
+
+struct sel_netport {
+	struct netport_security_struct psec;
+
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+static DEFINE_SPINLOCK(sel_netport_lock);
+static struct sel_netport_bkt sel_netport_hash[SEL_NETPORT_HASH_SIZE];
+
+/**
+ * sel_netport_hashfn - Hashing function for the port table
+ * @pnum: port number
+ *
+ * Description:
+ * This is the hashing function for the port table, it returns the bucket
+ * number for the given port.
+ *
+ */
+static unsigned int sel_netport_hashfn(u16 pnum)
+{
+	return (pnum & (SEL_NETPORT_HASH_SIZE - 1));
+}
+
+/**
+ * sel_netport_find - Search for a port record
+ * @protocol: protocol
+ * @pnum: port
+ *
+ * Description:
+ * Search the network port table and return the matching record.  If an entry
+ * can not be found in the table return NULL.
+ *
+ */
+static struct sel_netport *sel_netport_find(u8 protocol, u16 pnum)
+{
+	unsigned int idx;
+	struct sel_netport *port;
+
+	idx = sel_netport_hashfn(pnum);
+	list_for_each_entry_rcu(port, &sel_netport_hash[idx].list, list)
+		if (port->psec.port == pnum && port->psec.protocol == protocol)
+			return port;
+
+	return NULL;
+}
+
+/**
+ * sel_netport_insert - Insert a new port into the table
+ * @port: the new port record
+ *
+ * Description:
+ * Add a new port record to the network address hash table.
+ *
+ */
+static void sel_netport_insert(struct sel_netport *port)
+{
+	unsigned int idx;
+
+	/* we need to impose a limit on the growth of the hash table so check
+	 * this bucket to make sure it is within the specified bounds */
+	idx = sel_netport_hashfn(port->psec.port);
+	list_add_rcu(&port->list, &sel_netport_hash[idx].list);
+	if (sel_netport_hash[idx].size == SEL_NETPORT_HASH_BKT_LIMIT) {
+		struct sel_netport *tail;
+		tail = list_entry(
+			rcu_dereference_protected(
+				list_tail_rcu(&sel_netport_hash[idx].list),
+				lockdep_is_held(&sel_netport_lock)),
+			struct sel_netport, list);
+		list_del_rcu(&tail->list);
+		kfree_rcu(tail, rcu);
+	} else
+		sel_netport_hash[idx].size++;
+}
+
+/**
+ * sel_netport_sid_slow - Lookup the SID of a network address using the policy
+ * @protocol: protocol
+ * @pnum: port
+ * @sid: port SID
+ *
+ * Description:
+ * This function determines the SID of a network port by querying the security
+ * policy.  The result is added to the network port table to speedup future
+ * queries.  Returns zero on success, negative values on failure.
+ *
+ */
+static int sel_netport_sid_slow(u8 protocol, u16 pnum, u32 *sid)
+{
+	int ret;
+	struct sel_netport *port;
+	struct sel_netport *new;
+
+	spin_lock_bh(&sel_netport_lock);
+	port = sel_netport_find(protocol, pnum);
+	if (port != NULL) {
+		*sid = port->psec.sid;
+		spin_unlock_bh(&sel_netport_lock);
+		return 0;
+	}
+
+	ret = security_port_sid(protocol, pnum, sid);
+	if (ret != 0)
+		goto out;
+
+	/* If this memory allocation fails still return 0. The SID
+	 * is valid, it just won't be added to the cache.
+	 */
+	new = kmalloc_obj(*new, GFP_ATOMIC);
+	if (new) {
+		new->psec.port = pnum;
+		new->psec.protocol = protocol;
+		new->psec.sid = *sid;
+		sel_netport_insert(new);
+	}
+
+out:
+	spin_unlock_bh(&sel_netport_lock);
+	if (unlikely(ret))
+		pr_warn("SELinux: failure in %s(), unable to determine network port label\n",
+			__func__);
+	return ret;
+}
+
+/**
+ * sel_netport_sid - Lookup the SID of a network port
+ * @protocol: protocol
+ * @pnum: port
+ * @sid: port SID
+ *
+ * Description:
+ * This function determines the SID of a network port using the fastest method
+ * possible.  First the port table is queried, but if an entry can't be found
+ * then the policy is queried and the result is added to the table to speedup
+ * future queries.  Returns zero on success, negative values on failure.
+ *
+ */
+int sel_netport_sid(u8 protocol, u16 pnum, u32 *sid)
+{
+	struct sel_netport *port;
+
+	rcu_read_lock();
+	port = sel_netport_find(protocol, pnum);
+	if (likely(port != NULL)) {
+		*sid = port->psec.sid;
+		rcu_read_unlock();
+		return 0;
+	}
+	rcu_read_unlock();
+
+	return sel_netport_sid_slow(protocol, pnum, sid);
+}
+
+/**
+ * sel_netport_flush - Flush the entire network port table
+ *
+ * Description:
+ * Remove all entries from the network address table.
+ *
+ */
+void sel_netport_flush(void)
+{
+	unsigned int idx;
+	struct sel_netport *port, *port_tmp;
+
+	spin_lock_bh(&sel_netport_lock);
+	for (idx = 0; idx < SEL_NETPORT_HASH_SIZE; idx++) {
+		list_for_each_entry_safe(port, port_tmp,
+					 &sel_netport_hash[idx].list, list) {
+			list_del_rcu(&port->list);
+			kfree_rcu(port, rcu);
+		}
+		sel_netport_hash[idx].size = 0;
+	}
+	spin_unlock_bh(&sel_netport_lock);
+}
+
+int __init sel_netport_init(void)
+{
+	int iter;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	for (iter = 0; iter < SEL_NETPORT_HASH_SIZE; iter++) {
+		INIT_LIST_HEAD(&sel_netport_hash[iter].list);
+		sel_netport_hash[iter].size = 0;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
new file mode 100644
index 000000000..655d2616c
--- /dev/null
+++ b/security/selinux/nlmsgtab.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Netlink message type permission tables, for user generated messages.
+ *
+ * Author: James Morris <jmorris@redhat.com>
+ *
+ * Copyright (C) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ */
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/if.h>
+#include <linux/inet_diag.h>
+#include <linux/xfrm.h>
+#include <linux/audit.h>
+#include <linux/sock_diag.h>
+
+#include "flask.h"
+#include "av_permissions.h"
+#include "security.h"
+
+struct nlmsg_perm {
+	u16 nlmsg_type;
+	u32 perm;
+};
+
+static const struct nlmsg_perm nlmsg_route_perms[] = {
+	{ RTM_NEWLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETLINK, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_SETLINK, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_NEWADDR, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELADDR, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETADDR, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWROUTE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELROUTE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETROUTE, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETNEIGH, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWRULE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELRULE, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETRULE, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWQDISC, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELQDISC, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETQDISC, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETTCLASS, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETTFILTER, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWACTION, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELACTION, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETACTION, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWPREFIX, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETMULTICAST, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_GETANYCAST, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_GETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_SETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_NEWADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_GETDCB, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_NEWNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETNETCONF, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELMDB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETMDB, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWNSID, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNSID, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_GETNSID, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_GETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_SETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_NEWCACHEREPORT, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETNEXTHOP, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELLINKPROP, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_NEWVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELVLAN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETVLAN, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETNEXTHOPBUCKET, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+	{ RTM_NEWTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_DELTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
+	{ RTM_GETTUNNEL, NETLINK_ROUTE_SOCKET__NLMSG_READ },
+};
+
+static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = {
+	{ TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DIAG_BY_FAMILY, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
+	{ SOCK_DESTROY, NETLINK_TCPDIAG_SOCKET__NLMSG_WRITE },
+};
+
+static const struct nlmsg_perm nlmsg_xfrm_perms[] = {
+	{ XFRM_MSG_NEWSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_DELSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETSA, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_NEWPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_DELPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETPOLICY, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_ALLOCSPI, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_ACQUIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_EXPIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_UPDPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_UPDSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_POLEXPIRE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_FLUSHSA, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_FLUSHPOLICY, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_NEWAE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETAE, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_REPORT, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_MIGRATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_NEWSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_GETSADINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_NEWSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_SETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+	{ XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ },
+	{ XFRM_MSG_MIGRATE_STATE, NETLINK_XFRM_SOCKET__NLMSG_WRITE },
+};
+
+static const struct nlmsg_perm nlmsg_audit_perms[] = {
+	{ AUDIT_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+	{ AUDIT_SET, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_LIST, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV },
+	{ AUDIT_ADD, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_DEL, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_LIST_RULES, NETLINK_AUDIT_SOCKET__NLMSG_READPRIV },
+	{ AUDIT_ADD_RULE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_DEL_RULE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_USER, NETLINK_AUDIT_SOCKET__NLMSG_RELAY },
+	{ AUDIT_SIGNAL_INFO, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+	{ AUDIT_TRIM, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_MAKE_EQUIV, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+	{ AUDIT_TTY_GET, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+	{ AUDIT_TTY_SET, NETLINK_AUDIT_SOCKET__NLMSG_TTY_AUDIT },
+	{ AUDIT_GET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_READ },
+	{ AUDIT_SET_FEATURE, NETLINK_AUDIT_SOCKET__NLMSG_WRITE },
+};
+
+static int nlmsg_perm(u16 nlmsg_type, u32 *perm, const struct nlmsg_perm *tab,
+		      size_t tabsize)
+{
+	unsigned int i;
+	int err = -EINVAL;
+
+	for (i = 0; i < tabsize / sizeof(struct nlmsg_perm); i++)
+		if (nlmsg_type == tab[i].nlmsg_type) {
+			*perm = tab[i].perm;
+			err = 0;
+			break;
+		}
+
+	return err;
+}
+
+int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
+{
+	/* While it is possible to add a similar permission to other netlink
+	 * classes, note that the extended permission value is matched against
+	 * the nlmsg_type field. Notably, SECCLASS_NETLINK_GENERIC_SOCKET uses
+	 * dynamic values for this field, which means that it cannot be added
+	 * as-is.
+	 */
+
+	switch (sclass) {
+	case SECCLASS_NETLINK_ROUTE_SOCKET:
+		/* RTM_MAX always points to RTM_SETxxxx, ie RTM_NEWxxx + 3.
+		 * If the BUILD_BUG_ON() below fails you must update the
+		 * structures at the top of this file with the new mappings
+		 * before updating the BUILD_BUG_ON() macro!
+		 */
+		BUILD_BUG_ON(RTM_MAX != (RTM_NEWTUNNEL + 3));
+
+		if (selinux_policycap_netlink_xperm()) {
+			*perm = NETLINK_ROUTE_SOCKET__NLMSG;
+			return 0;
+		}
+		return nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms,
+				  sizeof(nlmsg_route_perms));
+		break;
+	case SECCLASS_NETLINK_TCPDIAG_SOCKET:
+		if (selinux_policycap_netlink_xperm()) {
+			*perm = NETLINK_TCPDIAG_SOCKET__NLMSG;
+			return 0;
+		}
+		return nlmsg_perm(nlmsg_type, perm, nlmsg_tcpdiag_perms,
+				  sizeof(nlmsg_tcpdiag_perms));
+		break;
+	case SECCLASS_NETLINK_XFRM_SOCKET:
+		/* If the BUILD_BUG_ON() below fails you must update the
+		 * structures at the top of this file with the new mappings
+		 * before updating the BUILD_BUG_ON() macro!
+		 */
+		BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MIGRATE_STATE);
+
+		if (selinux_policycap_netlink_xperm()) {
+			*perm = NETLINK_XFRM_SOCKET__NLMSG;
+			return 0;
+		}
+		return nlmsg_perm(nlmsg_type, perm, nlmsg_xfrm_perms,
+				  sizeof(nlmsg_xfrm_perms));
+		break;
+	case SECCLASS_NETLINK_AUDIT_SOCKET:
+		if (selinux_policycap_netlink_xperm()) {
+			*perm = NETLINK_AUDIT_SOCKET__NLMSG;
+			return 0;
+		} else if ((nlmsg_type >= AUDIT_FIRST_USER_MSG &&
+			    nlmsg_type <= AUDIT_LAST_USER_MSG) ||
+			   (nlmsg_type >= AUDIT_FIRST_USER_MSG2 &&
+			    nlmsg_type <= AUDIT_LAST_USER_MSG2)) {
+			*perm = NETLINK_AUDIT_SOCKET__NLMSG_RELAY;
+			return 0;
+		}
+		return nlmsg_perm(nlmsg_type, perm, nlmsg_audit_perms,
+				  sizeof(nlmsg_audit_perms));
+		break;
+	}
+
+	/* No messaging from userspace, or class unknown/unhandled */
+	return -ENOENT;
+}
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
new file mode 100644
index 000000000..c7d914769
--- /dev/null
+++ b/security/selinux/selinuxfs.c
@@ -0,0 +1,2023 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Updated: Karl MacMillan <kmacmillan@tresys.com>
+ *
+ *	Added conditional policy language extensions
+ *
+ *  Updated: Hewlett-Packard <paul@paul-moore.com>
+ *
+ *	Added support for the policy capability bitmap
+ *
+ * Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
+ * Copyright (C) 2003 - 2004 Tresys Technology, LLC
+ * Copyright (C) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/hex.h>
+#include <linux/mount.h>
+#include <linux/mutex.h>
+#include <linux/namei.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/security.h>
+#include <linux/major.h>
+#include <linux/seq_file.h>
+#include <linux/percpu.h>
+#include <linux/audit.h>
+#include <linux/uaccess.h>
+#include <linux/kobject.h>
+#include <linux/ctype.h>
+
+/* selinuxfs pseudo filesystem for exporting the security policy API.
+   Based on the proc code and the fs/nfsd/nfsctl.c code. */
+
+#include "initcalls.h"
+#include "flask.h"
+#include "avc.h"
+#include "avc_ss.h"
+#include "security.h"
+#include "objsec.h"
+#include "conditional.h"
+#include "ima.h"
+
+enum sel_inos {
+	SEL_ROOT_INO = 2,
+	SEL_LOAD,	/* load policy */
+	SEL_ENFORCE,	/* get or set enforcing status */
+	SEL_CONTEXT,	/* validate context */
+	SEL_ACCESS,	/* compute access decision */
+	SEL_CREATE,	/* compute create labeling decision */
+	SEL_RELABEL,	/* compute relabeling decision */
+	SEL_USER,	/* compute reachable user contexts */
+	SEL_POLICYVERS,	/* return policy version for this kernel */
+	SEL_COMMIT_BOOLS, /* commit new boolean values */
+	SEL_MLS,	/* return if MLS policy is enabled */
+	SEL_DISABLE,	/* disable SELinux until next reboot */
+	SEL_MEMBER,	/* compute polyinstantiation membership decision */
+	SEL_CHECKREQPROT, /* check requested protection, not kernel-applied one */
+	SEL_COMPAT_NET,	/* whether to use old compat network packet controls */
+	SEL_REJECT_UNKNOWN, /* export unknown reject handling to userspace */
+	SEL_DENY_UNKNOWN, /* export unknown deny handling to userspace */
+	SEL_STATUS,	/* export current status using mmap() */
+	SEL_POLICY,	/* allow userspace to read the in kernel policy */
+	SEL_VALIDATE_TRANS, /* compute validatetrans decision */
+	SEL_INO_NEXT,	/* The next inode number to use */
+};
+
+struct selinux_fs_info {
+	struct dentry *bool_dir;
+	unsigned int bool_num;
+	char **bool_pending_names;
+	int *bool_pending_values;
+	struct dentry *class_dir;
+	unsigned long last_class_ino;
+	unsigned long last_ino;
+	struct super_block *sb;
+};
+
+static int selinux_fs_info_create(struct super_block *sb)
+{
+	struct selinux_fs_info *fsi;
+
+	fsi = kzalloc_obj(*fsi);
+	if (!fsi)
+		return -ENOMEM;
+
+	fsi->last_ino = SEL_INO_NEXT - 1;
+	fsi->sb = sb;
+	sb->s_fs_info = fsi;
+	return 0;
+}
+
+static void selinux_fs_info_free(struct selinux_fs_info *fsi)
+{
+	unsigned int i;
+
+	if (fsi) {
+		for (i = 0; i < fsi->bool_num; i++)
+			kfree(fsi->bool_pending_names[i]);
+		kfree(fsi->bool_pending_names);
+		kfree(fsi->bool_pending_values);
+	}
+	kfree(fsi);
+}
+
+#define SEL_INITCON_INO_OFFSET		0x01000000
+#define SEL_BOOL_INO_OFFSET		0x02000000
+#define SEL_CLASS_INO_OFFSET		0x04000000
+#define SEL_POLICYCAP_INO_OFFSET	0x08000000
+#define SEL_INO_MASK			0x00ffffff
+
+#define BOOL_DIR_NAME "booleans"
+#define CLASS_DIR_NAME "class"
+
+#define TMPBUFLEN	12
+static ssize_t sel_read_enforce(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%d",
+			   enforcing_enabled());
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+#ifdef CONFIG_SECURITY_SELINUX_DEVELOP
+static ssize_t sel_write_enforce(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+
+{
+	char *page = NULL;
+	ssize_t length;
+	int scan_value;
+	bool old_value, new_value;
+
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	length = -EINVAL;
+	if (sscanf(page, "%d", &scan_value) != 1)
+		goto out;
+
+	new_value = !!scan_value;
+
+	old_value = enforcing_enabled();
+	if (new_value != old_value) {
+		length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+				      SECCLASS_SECURITY, SECURITY__SETENFORCE,
+				      NULL);
+		if (length)
+			goto out;
+		audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS,
+			"enforcing=%d old_enforcing=%d auid=%u ses=%u"
+			" enabled=1 old-enabled=1 lsm=selinux res=1",
+			new_value, old_value,
+			from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			audit_get_sessionid(current));
+		enforcing_set(new_value);
+		if (new_value)
+			avc_ss_reset(0);
+		selnl_notify_setenforce(new_value);
+		selinux_status_update_setenforce(new_value);
+		if (!new_value)
+			call_blocking_lsm_notifier(LSM_POLICY_CHANGE, NULL);
+
+		selinux_ima_measure_state();
+	}
+	length = count;
+out:
+	kfree(page);
+	return length;
+}
+#else
+#define sel_write_enforce NULL
+#endif
+
+static const struct file_operations sel_enforce_ops = {
+	.read		= sel_read_enforce,
+	.write		= sel_write_enforce,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_read_handle_unknown(struct file *filp, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+	ino_t ino = file_inode(filp)->i_ino;
+	int handle_unknown = (ino == SEL_REJECT_UNKNOWN) ?
+		security_get_reject_unknown() :
+		!security_get_allow_unknown();
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%d", handle_unknown);
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations sel_handle_unknown_ops = {
+	.read		= sel_read_handle_unknown,
+	.llseek		= generic_file_llseek,
+};
+
+static int sel_open_handle_status(struct inode *inode, struct file *filp)
+{
+	struct page    *status = selinux_kernel_status_page();
+
+	if (!status)
+		return -ENOMEM;
+
+	filp->private_data = status;
+
+	return 0;
+}
+
+static ssize_t sel_read_handle_status(struct file *filp, char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct page    *status = filp->private_data;
+
+	BUG_ON(!status);
+
+	return simple_read_from_buffer(buf, count, ppos,
+				       page_address(status),
+				       sizeof(struct selinux_kernel_status));
+}
+
+static int sel_mmap_handle_status(struct file *filp,
+				  struct vm_area_struct *vma)
+{
+	struct page    *status = filp->private_data;
+	unsigned long	size = vma->vm_end - vma->vm_start;
+
+	BUG_ON(!status);
+
+	/* only allows one page from the head */
+	if (vma->vm_pgoff > 0 || size != PAGE_SIZE)
+		return -EIO;
+	/* disallow writable mapping */
+	if (vma->vm_flags & VM_WRITE)
+		return -EPERM;
+	/* disallow mprotect() turns it into writable */
+	vm_flags_clear(vma, VM_MAYWRITE);
+
+	return remap_pfn_range(vma, vma->vm_start,
+			       page_to_pfn(status),
+			       size, vma->vm_page_prot);
+}
+
+static const struct file_operations sel_handle_status_ops = {
+	.open		= sel_open_handle_status,
+	.read		= sel_read_handle_status,
+	.mmap		= sel_mmap_handle_status,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_write_disable(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+
+{
+	/*
+	 * Setting disable is no longer supported, see
+	 * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-runtime-disable
+	 */
+	pr_err_once("SELinux: %s (%d) wrote to disable. This is no longer supported.\n",
+		    current->comm, current->pid);
+	return count;
+}
+
+static const struct file_operations sel_disable_ops = {
+	.write		= sel_write_disable,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_read_policyvers(struct file *filp, char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%u", POLICYDB_VERSION_MAX);
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations sel_policyvers_ops = {
+	.read		= sel_read_policyvers,
+	.llseek		= generic_file_llseek,
+};
+
+/* declaration for sel_write_load */
+static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir,
+			  unsigned int *bool_num, char ***bool_pending_names,
+			  int **bool_pending_values);
+static int sel_make_classes(struct selinux_policy *newpolicy,
+			    struct dentry *class_dir,
+			    unsigned long *last_class_ino);
+
+/* declaration for sel_make_class_dirs */
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
+			unsigned long *ino);
+
+/* declaration for sel_make_policy_nodes */
+static struct dentry *sel_make_swapover_dir(struct super_block *sb,
+						unsigned long *ino);
+
+static ssize_t sel_read_mls(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%d",
+			   security_mls_enabled());
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations sel_mls_ops = {
+	.read		= sel_read_mls,
+	.llseek		= generic_file_llseek,
+};
+
+struct policy_load_memory {
+	size_t len;
+	void *data;
+};
+
+static int sel_open_policy(struct inode *inode, struct file *filp)
+{
+	struct policy_load_memory *plm = NULL;
+	int rc;
+
+	rc = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			  SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL);
+	if (rc)
+		return rc;
+
+	plm = kzalloc_obj(*plm);
+	if (!plm)
+		return -ENOMEM;
+
+	mutex_lock(&selinux_state.policy_mutex);
+	rc = security_read_policy(&plm->data, &plm->len);
+	if (rc)
+		goto err;
+	if ((size_t)i_size_read(inode) != plm->len) {
+		inode_lock(inode);
+		i_size_write(inode, plm->len);
+		inode_unlock(inode);
+	}
+	mutex_unlock(&selinux_state.policy_mutex);
+
+	filp->private_data = plm;
+
+	return 0;
+err:
+	mutex_unlock(&selinux_state.policy_mutex);
+
+	if (plm)
+		vfree(plm->data);
+	kfree(plm);
+	return rc;
+}
+
+static int sel_release_policy(struct inode *inode, struct file *filp)
+{
+	struct policy_load_memory *plm = filp->private_data;
+
+	vfree(plm->data);
+	kfree(plm);
+
+	return 0;
+}
+
+static ssize_t sel_read_policy(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	struct policy_load_memory *plm = filp->private_data;
+	int ret;
+
+	ret = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			  SECCLASS_SECURITY, SECURITY__READ_POLICY, NULL);
+	if (ret)
+		return ret;
+
+	return simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
+}
+
+static vm_fault_t sel_mmap_policy_fault(struct vm_fault *vmf)
+{
+	struct policy_load_memory *plm = vmf->vma->vm_file->private_data;
+	unsigned long offset;
+	struct page *page;
+
+	if (vmf->flags & (FAULT_FLAG_MKWRITE | FAULT_FLAG_WRITE))
+		return VM_FAULT_SIGBUS;
+
+	offset = vmf->pgoff << PAGE_SHIFT;
+	if (offset >= roundup(plm->len, PAGE_SIZE))
+		return VM_FAULT_SIGBUS;
+
+	page = vmalloc_to_page(plm->data + offset);
+	get_page(page);
+
+	vmf->page = page;
+
+	return 0;
+}
+
+static const struct vm_operations_struct sel_mmap_policy_ops = {
+	.fault = sel_mmap_policy_fault,
+	.page_mkwrite = sel_mmap_policy_fault,
+};
+
+static int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_SHARED) {
+		/* do not allow mprotect to make mapping writable */
+		vm_flags_clear(vma, VM_MAYWRITE);
+
+		if (vma->vm_flags & VM_WRITE)
+			return -EACCES;
+	}
+
+	vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
+	vma->vm_ops = &sel_mmap_policy_ops;
+
+	return 0;
+}
+
+static const struct file_operations sel_policy_ops = {
+	.open		= sel_open_policy,
+	.read		= sel_read_policy,
+	.mmap		= sel_mmap_policy,
+	.release	= sel_release_policy,
+	.llseek		= generic_file_llseek,
+};
+
+static void sel_remove_old_bool_data(unsigned int bool_num, char **bool_names,
+				     int *bool_values)
+{
+	u32 i;
+
+	/* bool_dir cleanup */
+	for (i = 0; i < bool_num; i++)
+		kfree(bool_names[i]);
+	kfree(bool_names);
+	kfree(bool_values);
+}
+
+static int sel_make_policy_nodes(struct selinux_fs_info *fsi,
+				struct selinux_policy *newpolicy)
+{
+	int ret = 0;
+	struct dentry *tmp_parent, *tmp_bool_dir, *tmp_class_dir;
+	struct renamedata rd = {};
+	unsigned int bool_num = 0;
+	char **bool_names = NULL;
+	int *bool_values = NULL;
+	unsigned long tmp_ino = fsi->last_ino; /* Don't increment last_ino in this function */
+
+	tmp_parent = sel_make_swapover_dir(fsi->sb, &tmp_ino);
+	if (IS_ERR(tmp_parent))
+		return PTR_ERR(tmp_parent);
+
+	tmp_ino = fsi->bool_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */
+	tmp_bool_dir = sel_make_dir(tmp_parent, BOOL_DIR_NAME, &tmp_ino);
+	if (IS_ERR(tmp_bool_dir)) {
+		ret = PTR_ERR(tmp_bool_dir);
+		goto out;
+	}
+
+	tmp_ino = fsi->class_dir->d_inode->i_ino - 1; /* sel_make_dir will increment and set */
+	tmp_class_dir = sel_make_dir(tmp_parent, CLASS_DIR_NAME, &tmp_ino);
+	if (IS_ERR(tmp_class_dir)) {
+		ret = PTR_ERR(tmp_class_dir);
+		goto out;
+	}
+
+	ret = sel_make_bools(newpolicy, tmp_bool_dir, &bool_num,
+			     &bool_names, &bool_values);
+	if (ret)
+		goto out;
+
+	ret = sel_make_classes(newpolicy, tmp_class_dir,
+			       &fsi->last_class_ino);
+	if (ret)
+		goto out;
+
+	rd.old_parent = tmp_parent;
+	rd.new_parent = fsi->sb->s_root;
+
+	/* booleans */
+	ret = start_renaming_two_dentries(&rd, tmp_bool_dir, fsi->bool_dir);
+	if (ret)
+		goto out;
+
+	d_exchange(tmp_bool_dir, fsi->bool_dir);
+
+	swap(fsi->bool_num, bool_num);
+	swap(fsi->bool_pending_names, bool_names);
+	swap(fsi->bool_pending_values, bool_values);
+
+	fsi->bool_dir = tmp_bool_dir;
+	end_renaming(&rd);
+
+	/* classes */
+	ret = start_renaming_two_dentries(&rd, tmp_class_dir, fsi->class_dir);
+	if (ret)
+		goto out;
+
+	d_exchange(tmp_class_dir, fsi->class_dir);
+	fsi->class_dir = tmp_class_dir;
+
+	end_renaming(&rd);
+
+out:
+	sel_remove_old_bool_data(bool_num, bool_names, bool_values);
+	/* Since the other temporary dirs are children of tmp_parent
+	 * this will handle all the cleanup in the case of a failure before
+	 * the swapover
+	 */
+	simple_recursive_removal(tmp_parent, NULL);
+
+	return ret;
+}
+
+static ssize_t sel_write_load(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+
+{
+	struct selinux_fs_info *fsi;
+	struct selinux_load_state load_state;
+	ssize_t length;
+	void *data = NULL;
+
+	/* no partial writes */
+	if (*ppos)
+		return -EINVAL;
+	/* no empty policies */
+	if (!count)
+		return -EINVAL;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__LOAD_POLICY, NULL);
+	if (length)
+		return length;
+
+	data = vmalloc(count);
+	if (!data)
+		return -ENOMEM;
+	if (copy_from_user(data, buf, count) != 0) {
+		length = -EFAULT;
+		goto out;
+	}
+
+	mutex_lock(&selinux_state.policy_mutex);
+	length = security_load_policy(data, count, &load_state);
+	if (length) {
+		pr_warn_ratelimited("SELinux: failed to load policy\n");
+		goto out_unlock;
+	}
+	fsi = file_inode(file)->i_sb->s_fs_info;
+	length = sel_make_policy_nodes(fsi, load_state.policy);
+	if (length) {
+		pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n");
+		selinux_policy_cancel(&load_state);
+		goto out_unlock;
+	}
+
+	selinux_policy_commit(&load_state);
+	length = count;
+	audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD,
+		"auid=%u ses=%u lsm=selinux res=1",
+		from_kuid(&init_user_ns, audit_get_loginuid(current)),
+		audit_get_sessionid(current));
+
+out_unlock:
+	mutex_unlock(&selinux_state.policy_mutex);
+out:
+	vfree(data);
+	return length;
+}
+
+static const struct file_operations sel_load_ops = {
+	.write		= sel_write_load,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_write_context(struct file *file, char *buf, size_t size)
+{
+	char *canon = NULL;
+	u32 sid, len;
+	ssize_t length;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__CHECK_CONTEXT, NULL);
+	if (length)
+		goto out;
+
+	length = security_context_to_sid(buf, size, &sid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_sid_to_context(sid, &canon, &len);
+	if (length)
+		goto out;
+
+	length = -ERANGE;
+	if (len > SIMPLE_TRANSACTION_LIMIT) {
+		pr_err("SELinux: %s:  context size (%u) exceeds "
+			"payload max\n", __func__, len);
+		goto out;
+	}
+
+	memcpy(buf, canon, len);
+	length = len;
+out:
+	kfree(canon);
+	return length;
+}
+
+static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
+			   checkreqprot_get());
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	/*
+	 * Setting checkreqprot is no longer supported, see
+	 * https://github.com/SELinuxProject/selinux-kernel/wiki/DEPRECATE-checkreqprot
+	 */
+	pr_err_once("SELinux: %s (%d) wrote to checkreqprot. This is no longer supported.\n",
+		    current->comm, current->pid);
+	return count;
+}
+static const struct file_operations sel_checkreqprot_ops = {
+	.read		= sel_read_checkreqprot,
+	.write		= sel_write_checkreqprot,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_write_validatetrans(struct file *file,
+					const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	char *oldcon = NULL, *newcon = NULL, *taskcon = NULL;
+	char *req = NULL;
+	u32 osid, nsid, tsid;
+	u16 tclass;
+	int rc;
+
+	rc = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			  SECCLASS_SECURITY, SECURITY__VALIDATE_TRANS, NULL);
+	if (rc)
+		goto out;
+
+	rc = -ENOMEM;
+	if (count >= PAGE_SIZE)
+		goto out;
+
+	/* No partial writes. */
+	rc = -EINVAL;
+	if (*ppos != 0)
+		goto out;
+
+	req = memdup_user_nul(buf, count);
+	if (IS_ERR(req)) {
+		rc = PTR_ERR(req);
+		req = NULL;
+		goto out;
+	}
+
+	rc = -ENOMEM;
+	oldcon = kzalloc(count + 1, GFP_KERNEL);
+	if (!oldcon)
+		goto out;
+
+	newcon = kzalloc(count + 1, GFP_KERNEL);
+	if (!newcon)
+		goto out;
+
+	taskcon = kzalloc(count + 1, GFP_KERNEL);
+	if (!taskcon)
+		goto out;
+
+	rc = -EINVAL;
+	if (sscanf(req, "%s %s %hu %s", oldcon, newcon, &tclass, taskcon) != 4)
+		goto out;
+
+	rc = security_context_str_to_sid(oldcon, &osid, GFP_KERNEL);
+	if (rc)
+		goto out;
+
+	rc = security_context_str_to_sid(newcon, &nsid, GFP_KERNEL);
+	if (rc)
+		goto out;
+
+	rc = security_context_str_to_sid(taskcon, &tsid, GFP_KERNEL);
+	if (rc)
+		goto out;
+
+	rc = security_validate_transition_user(osid, nsid, tsid, tclass);
+	if (!rc)
+		rc = count;
+out:
+	kfree(req);
+	kfree(oldcon);
+	kfree(newcon);
+	kfree(taskcon);
+	return rc;
+}
+
+static const struct file_operations sel_transition_ops = {
+	.write		= sel_write_validatetrans,
+	.llseek		= generic_file_llseek,
+};
+
+/*
+ * Remaining nodes use transaction based IO methods like nfsd/nfsctl.c
+ */
+static ssize_t sel_write_access(struct file *file, char *buf, size_t size);
+static ssize_t sel_write_create(struct file *file, char *buf, size_t size);
+static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size);
+static ssize_t sel_write_user(struct file *file, char *buf, size_t size);
+static ssize_t sel_write_member(struct file *file, char *buf, size_t size);
+
+static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
+	[SEL_ACCESS] = sel_write_access,
+	[SEL_CREATE] = sel_write_create,
+	[SEL_RELABEL] = sel_write_relabel,
+	[SEL_USER] = sel_write_user,
+	[SEL_MEMBER] = sel_write_member,
+	[SEL_CONTEXT] = sel_write_context,
+};
+
+static ssize_t selinux_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos)
+{
+	ino_t ino = file_inode(file)->i_ino;
+	char *data;
+	ssize_t rv;
+
+	if (ino >= ARRAY_SIZE(write_op) || !write_op[ino])
+		return -EINVAL;
+
+	data = simple_transaction_get(file, buf, size);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	rv = write_op[ino](file, data, size);
+	if (rv > 0) {
+		simple_transaction_set(file, rv);
+		rv = size;
+	}
+	return rv;
+}
+
+static const struct file_operations transaction_ops = {
+	.write		= selinux_transaction_write,
+	.read		= simple_transaction_read,
+	.release	= simple_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+/*
+ * payload - write methods
+ * If the method has a response, the response should be put in buf,
+ * and the length returned.  Otherwise return 0 or -error.
+ */
+
+static ssize_t sel_write_access(struct file *file, char *buf, size_t size)
+{
+	char *scon = NULL, *tcon = NULL;
+	u32 ssid, tsid;
+	u16 tclass;
+	struct av_decision avd;
+	ssize_t length;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__COMPUTE_AV, NULL);
+	if (length)
+		goto out;
+
+	length = -ENOMEM;
+	scon = kzalloc(size + 1, GFP_KERNEL);
+	if (!scon)
+		goto out;
+
+	length = -ENOMEM;
+	tcon = kzalloc(size + 1, GFP_KERNEL);
+	if (!tcon)
+		goto out;
+
+	length = -EINVAL;
+	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
+		goto out;
+
+	length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	security_compute_av_user(ssid, tsid, tclass, &avd);
+
+	length = scnprintf(buf, SIMPLE_TRANSACTION_LIMIT,
+			  "%x %x %x %x %u %x",
+			  avd.allowed, 0xffffffff,
+			  avd.auditallow, avd.auditdeny,
+			  avd.seqno, avd.flags);
+out:
+	kfree(tcon);
+	kfree(scon);
+	return length;
+}
+
+static ssize_t sel_write_create(struct file *file, char *buf, size_t size)
+{
+	char *scon = NULL, *tcon = NULL;
+	char *namebuf = NULL, *objname = NULL;
+	u32 ssid, tsid, newsid;
+	u16 tclass;
+	ssize_t length;
+	char *newcon = NULL;
+	u32 len;
+	int nargs;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__COMPUTE_CREATE,
+			      NULL);
+	if (length)
+		goto out;
+
+	length = -ENOMEM;
+	scon = kzalloc(size + 1, GFP_KERNEL);
+	if (!scon)
+		goto out;
+
+	length = -ENOMEM;
+	tcon = kzalloc(size + 1, GFP_KERNEL);
+	if (!tcon)
+		goto out;
+
+	length = -ENOMEM;
+	namebuf = kzalloc(size + 1, GFP_KERNEL);
+	if (!namebuf)
+		goto out;
+
+	length = -EINVAL;
+	nargs = sscanf(buf, "%s %s %hu %s", scon, tcon, &tclass, namebuf);
+	if (nargs < 3 || nargs > 4)
+		goto out;
+	if (nargs == 4) {
+		/*
+		 * If and when the name of new object to be queried contains
+		 * either whitespace or multibyte characters, they shall be
+		 * encoded based on the percentage-encoding rule.
+		 * If not encoded, the sscanf logic picks up only left-half
+		 * of the supplied name; split by a whitespace unexpectedly.
+		 */
+		char   *r, *w;
+		int     c1, c2;
+
+		r = w = namebuf;
+		do {
+			c1 = *r++;
+			if (c1 == '+')
+				c1 = ' ';
+			else if (c1 == '%') {
+				c1 = hex_to_bin(*r++);
+				if (c1 < 0)
+					goto out;
+				c2 = hex_to_bin(*r++);
+				if (c2 < 0)
+					goto out;
+				c1 = (c1 << 4) | c2;
+			}
+			*w++ = c1;
+		} while (c1 != '\0');
+
+		objname = namebuf;
+	}
+
+	length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_transition_sid_user(ssid, tsid, tclass,
+					      objname, &newsid);
+	if (length)
+		goto out;
+
+	length = security_sid_to_context(newsid, &newcon, &len);
+	if (length)
+		goto out;
+
+	length = -ERANGE;
+	if (len > SIMPLE_TRANSACTION_LIMIT) {
+		pr_err("SELinux: %s:  context size (%u) exceeds "
+			"payload max\n", __func__, len);
+		goto out;
+	}
+
+	memcpy(buf, newcon, len);
+	length = len;
+out:
+	kfree(newcon);
+	kfree(namebuf);
+	kfree(tcon);
+	kfree(scon);
+	return length;
+}
+
+static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size)
+{
+	char *scon = NULL, *tcon = NULL;
+	u32 ssid, tsid, newsid;
+	u16 tclass;
+	ssize_t length;
+	char *newcon = NULL;
+	u32 len;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__COMPUTE_RELABEL,
+			      NULL);
+	if (length)
+		goto out;
+
+	length = -ENOMEM;
+	scon = kzalloc(size + 1, GFP_KERNEL);
+	if (!scon)
+		goto out;
+
+	length = -ENOMEM;
+	tcon = kzalloc(size + 1, GFP_KERNEL);
+	if (!tcon)
+		goto out;
+
+	length = -EINVAL;
+	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
+		goto out;
+
+	length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_change_sid(ssid, tsid, tclass, &newsid);
+	if (length)
+		goto out;
+
+	length = security_sid_to_context(newsid, &newcon, &len);
+	if (length)
+		goto out;
+
+	length = -ERANGE;
+	if (len > SIMPLE_TRANSACTION_LIMIT)
+		goto out;
+
+	memcpy(buf, newcon, len);
+	length = len;
+out:
+	kfree(newcon);
+	kfree(tcon);
+	kfree(scon);
+	return length;
+}
+
+static ssize_t sel_write_user(struct file *file, char *buf, size_t size)
+{
+	pr_err_once("SELinux: %s (%d) wrote to user. This is no longer supported.\n",
+		    current->comm, current->pid);
+	buf[0] = '0';
+	buf[1] = 0;
+	return 2;
+}
+
+static ssize_t sel_write_member(struct file *file, char *buf, size_t size)
+{
+	char *scon = NULL, *tcon = NULL;
+	u32 ssid, tsid, newsid;
+	u16 tclass;
+	ssize_t length;
+	char *newcon = NULL;
+	u32 len;
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__COMPUTE_MEMBER,
+			      NULL);
+	if (length)
+		goto out;
+
+	length = -ENOMEM;
+	scon = kzalloc(size + 1, GFP_KERNEL);
+	if (!scon)
+		goto out;
+
+	length = -ENOMEM;
+	tcon = kzalloc(size + 1, GFP_KERNEL);
+	if (!tcon)
+		goto out;
+
+	length = -EINVAL;
+	if (sscanf(buf, "%s %s %hu", scon, tcon, &tclass) != 3)
+		goto out;
+
+	length = security_context_str_to_sid(scon, &ssid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_context_str_to_sid(tcon, &tsid, GFP_KERNEL);
+	if (length)
+		goto out;
+
+	length = security_member_sid(ssid, tsid, tclass, &newsid);
+	if (length)
+		goto out;
+
+	length = security_sid_to_context(newsid, &newcon, &len);
+	if (length)
+		goto out;
+
+	length = -ERANGE;
+	if (len > SIMPLE_TRANSACTION_LIMIT) {
+		pr_err("SELinux: %s:  context size (%u) exceeds "
+			"payload max\n", __func__, len);
+		goto out;
+	}
+
+	memcpy(buf, newcon, len);
+	length = len;
+out:
+	kfree(newcon);
+	kfree(tcon);
+	kfree(scon);
+	return length;
+}
+
+static struct inode *sel_make_inode(struct super_block *sb, umode_t mode)
+{
+	struct inode *ret = new_inode(sb);
+
+	if (ret) {
+		ret->i_mode = mode;
+		simple_inode_init_ts(ret);
+	}
+	return ret;
+}
+
+static struct dentry *sel_attach(struct dentry *parent, const char *name,
+				 struct inode *inode)
+{
+	struct dentry *dentry = d_alloc_name(parent, name);
+	if (unlikely(!dentry)) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
+	d_make_persistent(dentry, inode);
+	dput(dentry);
+	return dentry;
+}
+
+static int sel_attach_file(struct dentry *parent, const char *name,
+			   struct inode *inode)
+{
+	struct dentry *dentry = sel_attach(parent, name, inode);
+	return PTR_ERR_OR_ZERO(dentry);
+}
+
+static ssize_t sel_read_bool(struct file *filep, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info;
+	char buffer[4];
+	ssize_t length;
+	ssize_t ret;
+	int cur_enforcing;
+	unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK;
+	const char *name = filep->f_path.dentry->d_name.name;
+
+	mutex_lock(&selinux_state.policy_mutex);
+
+	ret = -EINVAL;
+	if (index >= fsi->bool_num || strcmp(name,
+					     fsi->bool_pending_names[index]))
+		goto out_unlock;
+
+	cur_enforcing = security_get_bool_value(index);
+	if (cur_enforcing < 0) {
+		ret = cur_enforcing;
+		goto out_unlock;
+	}
+	length = scnprintf(buffer, sizeof(buffer), "%d %d", !!cur_enforcing,
+			  !!fsi->bool_pending_values[index]);
+	mutex_unlock(&selinux_state.policy_mutex);
+	return simple_read_from_buffer(buf, count, ppos, buffer, length);
+
+out_unlock:
+	mutex_unlock(&selinux_state.policy_mutex);
+	return ret;
+}
+
+static ssize_t sel_write_bool(struct file *filep, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info;
+	char *page = NULL;
+	ssize_t length;
+	int new_value;
+	unsigned index = file_inode(filep)->i_ino & SEL_INO_MASK;
+	const char *name = filep->f_path.dentry->d_name.name;
+
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	mutex_lock(&selinux_state.policy_mutex);
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__SETBOOL,
+			      NULL);
+	if (length)
+		goto out;
+
+	length = -EINVAL;
+	if (index >= fsi->bool_num || strcmp(name,
+					     fsi->bool_pending_names[index]))
+		goto out;
+
+	length = -EINVAL;
+	if (sscanf(page, "%d", &new_value) != 1)
+		goto out;
+
+	if (new_value)
+		new_value = 1;
+
+	fsi->bool_pending_values[index] = new_value;
+	length = count;
+
+out:
+	mutex_unlock(&selinux_state.policy_mutex);
+	kfree(page);
+	return length;
+}
+
+static const struct file_operations sel_bool_ops = {
+	.read		= sel_read_bool,
+	.write		= sel_write_bool,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_commit_bools_write(struct file *filep,
+				      const char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct selinux_fs_info *fsi = file_inode(filep)->i_sb->s_fs_info;
+	char *page = NULL;
+	ssize_t length;
+	int new_value;
+
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	mutex_lock(&selinux_state.policy_mutex);
+
+	length = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			      SECCLASS_SECURITY, SECURITY__SETBOOL,
+			      NULL);
+	if (length)
+		goto out;
+
+	length = -EINVAL;
+	if (sscanf(page, "%d", &new_value) != 1)
+		goto out;
+
+	length = 0;
+	if (new_value && fsi->bool_pending_values)
+		length = security_set_bools(fsi->bool_num,
+					    fsi->bool_pending_values);
+
+	if (!length)
+		length = count;
+
+out:
+	mutex_unlock(&selinux_state.policy_mutex);
+	kfree(page);
+	return length;
+}
+
+static const struct file_operations sel_commit_bools_ops = {
+	.write		= sel_commit_bools_write,
+	.llseek		= generic_file_llseek,
+};
+
+static int sel_make_bools(struct selinux_policy *newpolicy, struct dentry *bool_dir,
+			  unsigned int *bool_num, char ***bool_pending_names,
+			  int **bool_pending_values)
+{
+	int ret;
+	char **names, *page;
+	u32 i, num;
+
+	page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	ret = security_get_bools(newpolicy, &num, &names, bool_pending_values);
+	if (ret)
+		goto out;
+
+	*bool_num = num;
+	*bool_pending_names = names;
+
+	for (i = 0; !ret && i < num; i++) {
+		struct inode *inode;
+		struct inode_security_struct *isec;
+		ssize_t len;
+		u32 sid;
+
+		len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]);
+		if (len >= PAGE_SIZE) {
+			ret = -ENAMETOOLONG;
+			break;
+		}
+
+		inode = sel_make_inode(bool_dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR);
+		if (!inode) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		isec = selinux_inode(inode);
+		ret = selinux_policy_genfs_sid(newpolicy, "selinuxfs", page,
+					 SECCLASS_FILE, &sid);
+		if (ret) {
+			pr_warn_ratelimited("SELinux: no sid found, defaulting to security isid for %s\n",
+					   page);
+			sid = SECINITSID_SECURITY;
+		}
+
+		isec->sid = sid;
+		isec->initialized = LABEL_INITIALIZED;
+		inode->i_fop = &sel_bool_ops;
+		inode->i_ino = i|SEL_BOOL_INO_OFFSET;
+
+		ret = sel_attach_file(bool_dir, names[i], inode);
+	}
+out:
+	kfree(page);
+	return ret;
+}
+
+static ssize_t sel_read_avc_cache_threshold(struct file *filp, char __user *buf,
+					    size_t count, loff_t *ppos)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%u",
+			   avc_get_cache_threshold());
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static ssize_t sel_write_avc_cache_threshold(struct file *file,
+					     const char __user *buf,
+					     size_t count, loff_t *ppos)
+
+{
+	char *page;
+	ssize_t ret;
+	unsigned int new_value;
+
+	ret = avc_has_perm(current_sid(), SECINITSID_SECURITY,
+			   SECCLASS_SECURITY, SECURITY__SETSECPARAM,
+			   NULL);
+	if (ret)
+		return ret;
+
+	if (count >= PAGE_SIZE)
+		return -ENOMEM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	page = memdup_user_nul(buf, count);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+
+	ret = -EINVAL;
+	if (sscanf(page, "%u", &new_value) != 1)
+		goto out;
+
+	avc_set_cache_threshold(new_value);
+
+	ret = count;
+out:
+	kfree(page);
+	return ret;
+}
+
+static ssize_t sel_read_avc_hash_stats(struct file *filp, char __user *buf,
+				       size_t count, loff_t *ppos)
+{
+	char *page;
+	ssize_t length;
+
+	page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	length = avc_get_hash_stats(page);
+	if (length >= 0)
+		length = simple_read_from_buffer(buf, count, ppos, page, length);
+	kfree(page);
+
+	return length;
+}
+
+static ssize_t sel_read_sidtab_hash_stats(struct file *filp, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	char *page;
+	ssize_t length;
+
+	page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+
+	length = security_sidtab_hash_stats(page);
+	if (length >= 0)
+		length = simple_read_from_buffer(buf, count, ppos, page,
+						length);
+	kfree(page);
+
+	return length;
+}
+
+static const struct file_operations sel_sidtab_hash_stats_ops = {
+	.read		= sel_read_sidtab_hash_stats,
+	.llseek		= generic_file_llseek,
+};
+
+static const struct file_operations sel_avc_cache_threshold_ops = {
+	.read		= sel_read_avc_cache_threshold,
+	.write		= sel_write_avc_cache_threshold,
+	.llseek		= generic_file_llseek,
+};
+
+static const struct file_operations sel_avc_hash_stats_ops = {
+	.read		= sel_read_avc_hash_stats,
+	.llseek		= generic_file_llseek,
+};
+
+#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
+static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx)
+{
+	loff_t cpu;
+
+	for (cpu = *idx; cpu < nr_cpu_ids; ++cpu) {
+		if (!cpu_possible(cpu))
+			continue;
+		*idx = cpu + 1;
+		return &per_cpu(avc_cache_stats, cpu);
+	}
+	(*idx)++;
+	return NULL;
+}
+
+static void *sel_avc_stats_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	loff_t n = *pos - 1;
+
+	if (*pos == 0)
+		return SEQ_START_TOKEN;
+
+	return sel_avc_get_stat_idx(&n);
+}
+
+static void *sel_avc_stats_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return sel_avc_get_stat_idx(pos);
+}
+
+static int sel_avc_stats_seq_show(struct seq_file *seq, void *v)
+{
+	struct avc_cache_stats *st = v;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq,
+			 "lookups hits misses allocations reclaims frees\n");
+	} else {
+		unsigned int lookups = st->lookups;
+		unsigned int misses = st->misses;
+		unsigned int hits = lookups - misses;
+		seq_printf(seq, "%u %u %u %u %u %u\n", lookups,
+			   hits, misses, st->allocations,
+			   st->reclaims, st->frees);
+	}
+	return 0;
+}
+
+static void sel_avc_stats_seq_stop(struct seq_file *seq, void *v)
+{ }
+
+static const struct seq_operations sel_avc_cache_stats_seq_ops = {
+	.start		= sel_avc_stats_seq_start,
+	.next		= sel_avc_stats_seq_next,
+	.show		= sel_avc_stats_seq_show,
+	.stop		= sel_avc_stats_seq_stop,
+};
+
+static int sel_open_avc_cache_stats(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &sel_avc_cache_stats_seq_ops);
+}
+
+static const struct file_operations sel_avc_cache_stats_ops = {
+	.open		= sel_open_avc_cache_stats,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+static int sel_make_avc_files(struct dentry *dir)
+{
+	struct super_block *sb = dir->d_sb;
+	struct selinux_fs_info *fsi = sb->s_fs_info;
+	unsigned int i;
+	int err = 0;
+	static const struct tree_descr files[] = {
+		{ "cache_threshold",
+		  &sel_avc_cache_threshold_ops, S_IRUGO|S_IWUSR },
+		{ "hash_stats", &sel_avc_hash_stats_ops, S_IRUGO },
+#ifdef CONFIG_SECURITY_SELINUX_AVC_STATS
+		{ "cache_stats", &sel_avc_cache_stats_ops, S_IRUGO },
+#endif
+	};
+
+	for (i = 0; !err && i < ARRAY_SIZE(files); i++) {
+		struct inode *inode;
+
+		inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode);
+		if (!inode)
+			return -ENOMEM;
+
+		inode->i_fop = files[i].ops;
+		inode->i_ino = ++fsi->last_ino;
+
+		err = sel_attach_file(dir, files[i].name, inode);
+	}
+
+	return err;
+}
+
+static int sel_make_ss_files(struct dentry *dir)
+{
+	struct super_block *sb = dir->d_sb;
+	struct selinux_fs_info *fsi = sb->s_fs_info;
+	unsigned int i;
+	int err = 0;
+	static const struct tree_descr files[] = {
+		{ "sidtab_hash_stats", &sel_sidtab_hash_stats_ops, S_IRUGO },
+	};
+
+	for (i = 0; !err && i < ARRAY_SIZE(files); i++) {
+		struct inode *inode;
+
+		inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode);
+		if (!inode)
+			return -ENOMEM;
+
+		inode->i_fop = files[i].ops;
+		inode->i_ino = ++fsi->last_ino;
+
+		err = sel_attach_file(dir, files[i].name, inode);
+	}
+
+	return err;
+}
+
+static ssize_t sel_read_initcon(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char *con;
+	u32 sid, len;
+	ssize_t ret;
+
+	sid = file_inode(file)->i_ino&SEL_INO_MASK;
+	ret = security_sid_to_context(sid, &con, &len);
+	if (ret)
+		return ret;
+
+	ret = simple_read_from_buffer(buf, count, ppos, con, len);
+	kfree(con);
+	return ret;
+}
+
+static const struct file_operations sel_initcon_ops = {
+	.read		= sel_read_initcon,
+	.llseek		= generic_file_llseek,
+};
+
+static int sel_make_initcon_files(struct dentry *dir)
+{
+	unsigned int i;
+	int err = 0;
+
+	for (i = 1; !err && i <= SECINITSID_NUM; i++) {
+		const char *s = security_get_initial_sid_context(i);
+		struct inode *inode;
+
+		if (!s)
+			continue;
+
+		inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
+		if (!inode)
+			return -ENOMEM;
+
+		inode->i_fop = &sel_initcon_ops;
+		inode->i_ino = i|SEL_INITCON_INO_OFFSET;
+		err = sel_attach_file(dir, s, inode);
+	}
+
+	return err;
+}
+
+static inline unsigned long sel_class_to_ino(u16 class)
+{
+	return (class * (SEL_VEC_MAX + 1)) | SEL_CLASS_INO_OFFSET;
+}
+
+static inline u16 sel_ino_to_class(unsigned long ino)
+{
+	return (ino & SEL_INO_MASK) / (SEL_VEC_MAX + 1);
+}
+
+static inline unsigned long sel_perm_to_ino(u16 class, u32 perm)
+{
+	return (class * (SEL_VEC_MAX + 1) + perm) | SEL_CLASS_INO_OFFSET;
+}
+
+static inline u32 sel_ino_to_perm(unsigned long ino)
+{
+	return (ino & SEL_INO_MASK) % (SEL_VEC_MAX + 1);
+}
+
+static ssize_t sel_read_class(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	unsigned long ino = file_inode(file)->i_ino;
+	char res[TMPBUFLEN];
+	ssize_t len = scnprintf(res, sizeof(res), "%d", sel_ino_to_class(ino));
+	return simple_read_from_buffer(buf, count, ppos, res, len);
+}
+
+static const struct file_operations sel_class_ops = {
+	.read		= sel_read_class,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_read_perm(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	unsigned long ino = file_inode(file)->i_ino;
+	char res[TMPBUFLEN];
+	ssize_t len = scnprintf(res, sizeof(res), "%d", sel_ino_to_perm(ino));
+	return simple_read_from_buffer(buf, count, ppos, res, len);
+}
+
+static const struct file_operations sel_perm_ops = {
+	.read		= sel_read_perm,
+	.llseek		= generic_file_llseek,
+};
+
+static ssize_t sel_read_policycap(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	int value;
+	char tmpbuf[TMPBUFLEN];
+	ssize_t length;
+	unsigned long i_ino = file_inode(file)->i_ino;
+
+	value = security_policycap_supported(i_ino & SEL_INO_MASK);
+	length = scnprintf(tmpbuf, TMPBUFLEN, "%d", value);
+
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static const struct file_operations sel_policycap_ops = {
+	.read		= sel_read_policycap,
+	.llseek		= generic_file_llseek,
+};
+
+static int sel_make_perm_files(struct selinux_policy *newpolicy,
+			char *objclass, int classvalue,
+			struct dentry *dir)
+{
+	u32 i, nperms;
+	int rc;
+	char **perms;
+
+	rc = security_get_permissions(newpolicy, objclass, &perms, &nperms);
+	if (rc)
+		return rc;
+
+	for (i = 0; !rc && i < nperms; i++) {
+		struct inode *inode;
+
+		inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
+		if (!inode) {
+			rc = -ENOMEM;
+			break;
+		}
+
+		inode->i_fop = &sel_perm_ops;
+		/* i+1 since perm values are 1-indexed */
+		inode->i_ino = sel_perm_to_ino(classvalue, i + 1);
+
+		rc = sel_attach_file(dir, perms[i], inode);
+	}
+	for (i = 0; i < nperms; i++)
+		kfree(perms[i]);
+	kfree(perms);
+	return rc;
+}
+
+static int sel_make_class_dir_entries(struct selinux_policy *newpolicy,
+				char *classname, int index,
+				struct dentry *dir)
+{
+	struct super_block *sb = dir->d_sb;
+	struct selinux_fs_info *fsi = sb->s_fs_info;
+	struct dentry *dentry = NULL;
+	struct inode *inode = NULL;
+	int err;
+
+	inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
+	if (!inode)
+		return -ENOMEM;
+
+	inode->i_fop = &sel_class_ops;
+	inode->i_ino = sel_class_to_ino(index);
+
+	err = sel_attach_file(dir, "index", inode);
+	if (err)
+		return err;
+
+	dentry = sel_make_dir(dir, "perms", &fsi->last_class_ino);
+	if (IS_ERR(dentry))
+		return PTR_ERR(dentry);
+
+	return sel_make_perm_files(newpolicy, classname, index, dentry);
+}
+
+static int sel_make_classes(struct selinux_policy *newpolicy,
+			    struct dentry *class_dir,
+			    unsigned long *last_class_ino)
+{
+	u32 i, nclasses;
+	int rc;
+	char **classes;
+
+	rc = security_get_classes(newpolicy, &classes, &nclasses);
+	if (rc)
+		return rc;
+
+	/* +2 since classes are 1-indexed */
+	*last_class_ino = sel_class_to_ino(nclasses + 2);
+
+	for (i = 0; i < nclasses; i++) {
+		struct dentry *class_name_dir;
+
+		class_name_dir = sel_make_dir(class_dir, classes[i],
+					      last_class_ino);
+		if (IS_ERR(class_name_dir)) {
+			rc = PTR_ERR(class_name_dir);
+			goto out;
+		}
+
+		/* i+1 since class values are 1-indexed */
+		rc = sel_make_class_dir_entries(newpolicy, classes[i], i + 1,
+				class_name_dir);
+		if (rc)
+			goto out;
+	}
+	rc = 0;
+out:
+	for (i = 0; i < nclasses; i++)
+		kfree(classes[i]);
+	kfree(classes);
+	return rc;
+}
+
+static int sel_make_policycap(struct dentry *dir)
+{
+	struct super_block *sb = dir->d_sb;
+	unsigned int iter;
+	struct inode *inode = NULL;
+	int err = 0;
+
+	for (iter = 0; !err && iter <= POLICYDB_CAP_MAX; iter++) {
+		const char *name;
+
+		if (iter < ARRAY_SIZE(selinux_policycap_names))
+			name = selinux_policycap_names[iter];
+		else
+			name = "unknown";
+
+		inode = sel_make_inode(sb, S_IFREG | 0444);
+		if (!inode)
+			return -ENOMEM;
+
+		inode->i_fop = &sel_policycap_ops;
+		inode->i_ino = iter | SEL_POLICYCAP_INO_OFFSET;
+		err = sel_attach_file(dir, name, inode);
+	}
+
+	return err;
+}
+
+static struct dentry *sel_make_dir(struct dentry *dir, const char *name,
+			unsigned long *ino)
+{
+	struct inode *inode;
+
+	inode = sel_make_inode(dir->d_sb, S_IFDIR | S_IRUGO | S_IXUGO);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	inode->i_op = &simple_dir_inode_operations;
+	inode->i_fop = &simple_dir_operations;
+	inode->i_ino = ++(*ino);
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(inode);
+	/* bump link count on parent directory, too */
+	inc_nlink(d_inode(dir));
+
+	return sel_attach(dir, name, inode);
+}
+
+static int reject_all(struct mnt_idmap *idmap, struct inode *inode, int mask)
+{
+	return -EPERM;	// no access for anyone, root or no root.
+}
+
+static const struct inode_operations swapover_dir_inode_operations = {
+	.lookup		= simple_lookup,
+	.permission	= reject_all,
+};
+
+static struct dentry *sel_make_swapover_dir(struct super_block *sb,
+						unsigned long *ino)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	inode = sel_make_inode(sb, S_IFDIR);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	dentry = simple_start_creating(sb->s_root, ".swapover");
+	if (IS_ERR(dentry)) {
+		iput(inode);
+		return dentry;
+	}
+
+	inode->i_op = &swapover_dir_inode_operations;
+	inode->i_ino = ++(*ino);
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(inode);
+	d_make_persistent(dentry, inode);
+	inc_nlink(sb->s_root->d_inode);
+	simple_done_creating(dentry);
+	return dentry;	// borrowed
+}
+
+#define NULL_FILE_NAME "null"
+
+static int sel_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct selinux_fs_info *fsi;
+	int ret;
+	struct dentry *dentry;
+	struct inode *inode;
+	struct inode_security_struct *isec;
+
+	static const struct tree_descr selinux_files[] = {
+		[SEL_LOAD] = {"load", &sel_load_ops, S_IRUSR|S_IWUSR},
+		[SEL_ENFORCE] = {"enforce", &sel_enforce_ops, S_IRUGO|S_IWUSR},
+		[SEL_CONTEXT] = {"context", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_ACCESS] = {"access", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_CREATE] = {"create", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_RELABEL] = {"relabel", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_USER] = {"user", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_POLICYVERS] = {"policyvers", &sel_policyvers_ops, S_IRUGO},
+		[SEL_COMMIT_BOOLS] = {"commit_pending_bools", &sel_commit_bools_ops, S_IWUSR},
+		[SEL_MLS] = {"mls", &sel_mls_ops, S_IRUGO},
+		[SEL_DISABLE] = {"disable", &sel_disable_ops, S_IWUSR},
+		[SEL_MEMBER] = {"member", &transaction_ops, S_IRUGO|S_IWUGO},
+		[SEL_CHECKREQPROT] = {"checkreqprot", &sel_checkreqprot_ops, S_IRUGO|S_IWUSR},
+		[SEL_REJECT_UNKNOWN] = {"reject_unknown", &sel_handle_unknown_ops, S_IRUGO},
+		[SEL_DENY_UNKNOWN] = {"deny_unknown", &sel_handle_unknown_ops, S_IRUGO},
+		[SEL_STATUS] = {"status", &sel_handle_status_ops, S_IRUGO},
+		[SEL_POLICY] = {"policy", &sel_policy_ops, S_IRUGO},
+		[SEL_VALIDATE_TRANS] = {"validatetrans", &sel_transition_ops,
+					S_IWUGO},
+		/* last one */ {"", NULL, 0}
+	};
+
+	ret = selinux_fs_info_create(sb);
+	if (ret)
+		goto err;
+
+	ret = simple_fill_super(sb, SELINUX_MAGIC, selinux_files);
+	if (ret)
+		goto err;
+
+	fsi = sb->s_fs_info;
+	fsi->bool_dir = sel_make_dir(sb->s_root, BOOL_DIR_NAME, &fsi->last_ino);
+	if (IS_ERR(fsi->bool_dir)) {
+		ret = PTR_ERR(fsi->bool_dir);
+		fsi->bool_dir = NULL;
+		goto err;
+	}
+
+	ret = -ENOMEM;
+	inode = sel_make_inode(sb, S_IFCHR | S_IRUGO | S_IWUGO);
+	if (!inode)
+		goto err;
+
+	inode->i_ino = ++fsi->last_ino;
+	isec = selinux_inode(inode);
+	isec->sid = SECINITSID_DEVNULL;
+	isec->sclass = SECCLASS_CHR_FILE;
+	isec->initialized = LABEL_INITIALIZED;
+
+	init_special_inode(inode, S_IFCHR | S_IRUGO | S_IWUGO, MKDEV(MEM_MAJOR, 3));
+	ret = sel_attach_file(sb->s_root, NULL_FILE_NAME, inode);
+	if (ret)
+		goto err;
+
+	dentry = sel_make_dir(sb->s_root, "avc", &fsi->last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	ret = sel_make_avc_files(dentry);
+	if (ret)
+		goto err;
+
+	dentry = sel_make_dir(sb->s_root, "ss", &fsi->last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	ret = sel_make_ss_files(dentry);
+	if (ret)
+		goto err;
+
+	dentry = sel_make_dir(sb->s_root, "initial_contexts", &fsi->last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	ret = sel_make_initcon_files(dentry);
+	if (ret)
+		goto err;
+
+	fsi->class_dir = sel_make_dir(sb->s_root, CLASS_DIR_NAME, &fsi->last_ino);
+	if (IS_ERR(fsi->class_dir)) {
+		ret = PTR_ERR(fsi->class_dir);
+		fsi->class_dir = NULL;
+		goto err;
+	}
+
+	dentry = sel_make_dir(sb->s_root, "policy_capabilities", &fsi->last_ino);
+	if (IS_ERR(dentry)) {
+		ret = PTR_ERR(dentry);
+		goto err;
+	}
+
+	ret = sel_make_policycap(dentry);
+	if (ret) {
+		pr_err("SELinux: failed to load policy capabilities\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	pr_err("SELinux: %s:  failed while creating inodes\n",
+		__func__);
+
+	return ret;
+}
+
+static int sel_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, sel_fill_super);
+}
+
+static const struct fs_context_operations sel_context_ops = {
+	.get_tree	= sel_get_tree,
+};
+
+static int sel_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &sel_context_ops;
+	return 0;
+}
+
+static void sel_kill_sb(struct super_block *sb)
+{
+	struct selinux_fs_info *fsi = sb->s_fs_info;
+
+	kill_anon_super(sb);
+	selinux_fs_info_free(fsi);
+}
+
+static struct file_system_type sel_fs_type = {
+	.name		= "selinuxfs",
+	.init_fs_context = sel_init_fs_context,
+	.kill_sb	= sel_kill_sb,
+};
+
+struct path selinux_null __ro_after_init;
+
+int __init init_sel_fs(void)
+{
+	struct qstr null_name = QSTR(NULL_FILE_NAME);
+	int err;
+
+	if (!selinux_enabled_boot)
+		return 0;
+
+	err = sysfs_create_mount_point(fs_kobj, "selinux");
+	if (err)
+		return err;
+
+	err = register_filesystem(&sel_fs_type);
+	if (err)
+		goto err_remove_mount_point;
+
+	selinux_null.mnt = kern_mount(&sel_fs_type);
+	if (IS_ERR(selinux_null.mnt)) {
+		pr_err("selinuxfs:  could not mount!\n");
+		err = PTR_ERR(selinux_null.mnt);
+		selinux_null.mnt = NULL;
+		goto err_unregister_fs;
+	}
+
+	selinux_null.dentry = try_lookup_noperm(&null_name,
+						  selinux_null.mnt->mnt_root);
+	if (IS_ERR(selinux_null.dentry)) {
+		pr_err("selinuxfs:  could not lookup null!\n");
+		err = PTR_ERR(selinux_null.dentry);
+		selinux_null.dentry = NULL;
+		goto err_unmount;
+	}
+
+	/*
+	 * Try to pre-allocate the status page, so the sequence number of the
+	 * initial policy load can be stored.
+	 */
+	(void) selinux_kernel_status_page();
+
+	return 0;
+
+err_unmount:
+	kern_unmount(selinux_null.mnt);
+	selinux_null.mnt = NULL;
+err_unregister_fs:
+	unregister_filesystem(&sel_fs_type);
+err_remove_mount_point:
+	sysfs_remove_mount_point(fs_kobj, "selinux");
+	return err;
+}
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
new file mode 100644
index 000000000..0f94edd01
--- /dev/null
+++ b/security/selinux/ss/avtab.c
@@ -0,0 +1,618 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Implementation of the access vector table type.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/* Updated: Frank Mayer <mayerf@tresys.com> and
+ *          Karl MacMillan <kmacmillan@tresys.com>
+ *          Added conditional policy language extensions
+ *          Copyright (C) 2003 Tresys Technology, LLC
+ *
+ * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp>
+ *          Tuned number of hash slots for avtab to reduce memory usage
+ */
+
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include "avtab.h"
+#include "policydb.h"
+#include "hash.h"
+
+static struct kmem_cache *avtab_node_cachep __ro_after_init;
+static struct kmem_cache *avtab_xperms_cachep __ro_after_init;
+
+static inline u32 avtab_hash(const struct avtab_key *keyp, u32 mask)
+{
+	return av_hash((u32)keyp->target_class, (u32)keyp->target_type,
+		       (u32)keyp->source_type, mask);
+}
+
+static struct avtab_node *avtab_insert_node(struct avtab *h,
+					    struct avtab_node **dst,
+					    const struct avtab_key *key,
+					    const struct avtab_datum *datum)
+{
+	struct avtab_node *newnode;
+	struct avtab_extended_perms *xperms;
+	newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
+	if (newnode == NULL)
+		return NULL;
+	newnode->key = *key;
+
+	if (key->specified & AVTAB_XPERMS) {
+		xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL);
+		if (xperms == NULL) {
+			kmem_cache_free(avtab_node_cachep, newnode);
+			return NULL;
+		}
+		*xperms = *(datum->u.xperms);
+		newnode->datum.u.xperms = xperms;
+	} else {
+		newnode->datum.u.data = datum->u.data;
+	}
+
+	newnode->next = *dst;
+	*dst = newnode;
+
+	h->nel++;
+	return newnode;
+}
+
+static int avtab_node_cmp(const struct avtab_key *key1,
+			  const struct avtab_key *key2)
+{
+	u16 specified = key1->specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD);
+
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type == key2->target_type &&
+	    key1->target_class == key2->target_class &&
+	    (specified & key2->specified))
+		return 0;
+	if (key1->source_type < key2->source_type)
+		return -1;
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type < key2->target_type)
+		return -1;
+	if (key1->source_type == key2->source_type &&
+	    key1->target_type == key2->target_type &&
+	    key1->target_class < key2->target_class)
+		return -1;
+	return 1;
+}
+
+static int avtab_insert(struct avtab *h, const struct avtab_key *key,
+			const struct avtab_datum *datum)
+{
+	u32 hvalue;
+	struct avtab_node *prev, *cur, *newnode;
+	int cmp;
+
+	if (!h || !h->nslot || h->nel == U32_MAX)
+		return -EINVAL;
+
+	hvalue = avtab_hash(key, h->mask);
+	for (prev = NULL, cur = h->htable[hvalue]; cur;
+	     prev = cur, cur = cur->next) {
+		cmp = avtab_node_cmp(key, &cur->key);
+		/* extended perms may not be unique */
+		if (cmp == 0 && !(key->specified & AVTAB_XPERMS))
+			return -EEXIST;
+		if (cmp <= 0)
+			break;
+	}
+
+	newnode = avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue],
+				    key, datum);
+	if (!newnode)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/* Unlike avtab_insert(), this function allow multiple insertions of the same
+ * key/specified mask into the table, as needed by the conditional avtab.
+ * It also returns a pointer to the node inserted.
+ */
+struct avtab_node *avtab_insert_nonunique(struct avtab *h,
+					  const struct avtab_key *key,
+					  const struct avtab_datum *datum)
+{
+	u32 hvalue;
+	struct avtab_node *prev, *cur;
+	int cmp;
+
+	if (!h || !h->nslot || h->nel == U32_MAX)
+		return NULL;
+	hvalue = avtab_hash(key, h->mask);
+	for (prev = NULL, cur = h->htable[hvalue]; cur;
+	     prev = cur, cur = cur->next) {
+		cmp = avtab_node_cmp(key, &cur->key);
+		if (cmp <= 0)
+			break;
+	}
+	return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue],
+				 key, datum);
+}
+
+/* This search function returns a node pointer, and can be used in
+ * conjunction with avtab_search_next_node()
+ */
+struct avtab_node *avtab_search_node(struct avtab *h,
+				     const struct avtab_key *key)
+{
+	u32 hvalue;
+	struct avtab_node *cur;
+	int cmp;
+
+	if (!h || !h->nslot)
+		return NULL;
+
+	hvalue = avtab_hash(key, h->mask);
+	for (cur = h->htable[hvalue]; cur; cur = cur->next) {
+		cmp = avtab_node_cmp(key, &cur->key);
+		if (cmp == 0)
+			return cur;
+		if (cmp < 0)
+			break;
+	}
+	return NULL;
+}
+
+struct avtab_node *avtab_search_node_next(struct avtab_node *node,
+					  u16 specified)
+{
+	struct avtab_key tmp_key;
+	struct avtab_node *cur;
+	int cmp;
+
+	if (!node)
+		return NULL;
+	tmp_key = node->key;
+	tmp_key.specified = specified;
+	for (cur = node->next; cur; cur = cur->next) {
+		cmp = avtab_node_cmp(&tmp_key, &cur->key);
+		if (cmp == 0)
+			return cur;
+		if (cmp < 0)
+			break;
+	}
+	return NULL;
+}
+
+void avtab_destroy(struct avtab *h)
+{
+	u32 i;
+	struct avtab_node *cur, *temp;
+
+	if (!h)
+		return;
+
+	for (i = 0; i < h->nslot; i++) {
+		cur = h->htable[i];
+		while (cur) {
+			temp = cur;
+			cur = cur->next;
+			if (temp->key.specified & AVTAB_XPERMS)
+				kmem_cache_free(avtab_xperms_cachep,
+						temp->datum.u.xperms);
+			kmem_cache_free(avtab_node_cachep, temp);
+		}
+	}
+	kvfree(h->htable);
+	h->htable = NULL;
+	h->nel = 0;
+	h->nslot = 0;
+	h->mask = 0;
+}
+
+void avtab_init(struct avtab *h)
+{
+	h->htable = NULL;
+	h->nel = 0;
+	h->nslot = 0;
+	h->mask = 0;
+}
+
+static int avtab_alloc_common(struct avtab *h, u32 nslot)
+{
+	if (!nslot)
+		return 0;
+
+	h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL);
+	if (!h->htable)
+		return -ENOMEM;
+
+	h->nslot = nslot;
+	h->mask = nslot - 1;
+	return 0;
+}
+
+int avtab_alloc(struct avtab *h, u32 nrules)
+{
+	int rc;
+	u32 nslot = 0;
+
+	if (nrules != 0) {
+		nslot = nrules > 3 ? rounddown_pow_of_two(nrules / 2) : 2;
+		if (nslot > MAX_AVTAB_HASH_BUCKETS)
+			nslot = MAX_AVTAB_HASH_BUCKETS;
+
+		rc = avtab_alloc_common(h, nslot);
+		if (rc)
+			return rc;
+	}
+
+	pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules);
+	return 0;
+}
+
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig)
+{
+	return avtab_alloc_common(new, orig->nslot);
+}
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+void avtab_hash_eval(struct avtab *h, const char *tag)
+{
+	u32 i, chain_len, slots_used, max_chain_len;
+	unsigned long long chain2_len_sum;
+	struct avtab_node *cur;
+
+	slots_used = 0;
+	max_chain_len = 0;
+	chain2_len_sum = 0;
+	for (i = 0; i < h->nslot; i++) {
+		cur = h->htable[i];
+		if (cur) {
+			slots_used++;
+			chain_len = 0;
+			while (cur) {
+				chain_len++;
+				cur = cur->next;
+			}
+
+			if (chain_len > max_chain_len)
+				max_chain_len = chain_len;
+			chain2_len_sum +=
+				(unsigned long long)chain_len * chain_len;
+		}
+	}
+
+	pr_debug("SELinux: %s:  %d entries and %d/%d buckets used, "
+		 "longest chain length %d, sum of chain length^2 %llu\n",
+		 tag, h->nel, slots_used, h->nslot, max_chain_len,
+		 chain2_len_sum);
+}
+#endif /* CONFIG_SECURITY_SELINUX_DEBUG */
+
+/* clang-format off */
+static const uint16_t spec_order[] = {
+	AVTAB_ALLOWED,
+	AVTAB_AUDITDENY,
+	AVTAB_AUDITALLOW,
+	AVTAB_TRANSITION,
+	AVTAB_CHANGE,
+	AVTAB_MEMBER,
+	AVTAB_XPERMS_ALLOWED,
+	AVTAB_XPERMS_AUDITALLOW,
+	AVTAB_XPERMS_DONTAUDIT
+};
+/* clang-format on */
+
+int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol,
+		    int (*insertf)(struct avtab *a, const struct avtab_key *k,
+				   const struct avtab_datum *d, void *p),
+		    void *p, bool conditional)
+{
+	__le16 buf16[4];
+	u16 enabled;
+	u32 items, items2, val, i;
+	struct avtab_key key;
+	struct avtab_datum datum;
+	struct avtab_extended_perms xperms;
+	__le32 buf32[ARRAY_SIZE(xperms.perms.p)];
+	int rc;
+	unsigned int vers = pol->policyvers;
+
+	memset(&key, 0, sizeof(struct avtab_key));
+	memset(&datum, 0, sizeof(struct avtab_datum));
+
+	if (vers < POLICYDB_VERSION_AVTAB) {
+		rc = next_entry(buf32, fp, sizeof(u32));
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		/* Read five or more items: source type, target type,
+		 * target class, AV type, and at least one datum.
+		 */
+		items2 = le32_to_cpu(buf32[0]);
+		if (items2 < 5 || items2 > ARRAY_SIZE(buf32)) {
+			pr_err("SELinux: avtab: invalid item count\n");
+			return -EINVAL;
+		}
+		rc = next_entry(buf32, fp, sizeof(u32) * items2);
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		items = 0;
+
+		val = le32_to_cpu(buf32[items++]);
+		key.source_type = (u16)val;
+		if (key.source_type != val) {
+			pr_err("SELinux: avtab: truncated source type\n");
+			return -EINVAL;
+		}
+		val = le32_to_cpu(buf32[items++]);
+		key.target_type = (u16)val;
+		if (key.target_type != val) {
+			pr_err("SELinux: avtab: truncated target type\n");
+			return -EINVAL;
+		}
+		val = le32_to_cpu(buf32[items++]);
+		key.target_class = (u16)val;
+		if (key.target_class != val) {
+			pr_err("SELinux: avtab: truncated target class\n");
+			return -EINVAL;
+		}
+
+		if (!policydb_type_isvalid(pol, key.source_type) ||
+		    !policydb_type_isvalid(pol, key.target_type) ||
+		    !policydb_class_isvalid(pol, key.target_class)) {
+			pr_err("SELinux: avtab: invalid type or class\n");
+			return -EINVAL;
+		}
+
+		val = le32_to_cpu(buf32[items++]);
+		enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0;
+
+		if (!(val & (AVTAB_AV | AVTAB_TYPE))) {
+			pr_err("SELinux: avtab: null entry\n");
+			return -EINVAL;
+		}
+		if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) {
+			pr_err("SELinux: avtab: entry has both access vectors and types\n");
+			return -EINVAL;
+		}
+		if (val & AVTAB_XPERMS) {
+			pr_err("SELinux: avtab: entry has extended permissions\n");
+			return -EINVAL;
+		}
+
+		for (i = 0; i < ARRAY_SIZE(spec_order); i++) {
+			if (val & spec_order[i]) {
+				if (items >= items2) {
+					pr_err("SELinux: avtab: entry has too many items (%d/%d)\n",
+					       items + 1, items2);
+					return -EINVAL;
+				}
+				key.specified = spec_order[i] | enabled;
+				datum.u.data = le32_to_cpu(buf32[items++]);
+
+				if ((key.specified & AVTAB_TYPE) &&
+				    !policydb_simpletype_isvalid(pol, datum.u.data)) {
+					pr_err("SELinux: avtab: invalid type\n");
+					return -EINVAL;
+				}
+
+				rc = insertf(a, &key, &datum, p);
+				if (rc)
+					return rc;
+			}
+		}
+
+		if (items != items2) {
+			pr_err("SELinux: avtab: entry only had %d items, expected %d\n",
+			       items2, items);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	rc = next_entry(buf16, fp, sizeof(u16) * 4);
+	if (rc) {
+		pr_err("SELinux: avtab: truncated entry\n");
+		return rc;
+	}
+
+	items = 0;
+	key.source_type = le16_to_cpu(buf16[items++]);
+	key.target_type = le16_to_cpu(buf16[items++]);
+	key.target_class = le16_to_cpu(buf16[items++]);
+	key.specified = le16_to_cpu(buf16[items++]);
+
+	if (!policydb_type_isvalid(pol, key.source_type) ||
+	    !policydb_type_isvalid(pol, key.target_type) ||
+	    !policydb_class_isvalid(pol, key.target_class)) {
+		pr_err("SELinux: avtab: invalid type or class\n");
+		return -EINVAL;
+	}
+
+	if (hweight16(key.specified & ~AVTAB_ENABLED) != 1) {
+		pr_err("SELinux:  avtab:  not exactly one specifier\n");
+		return -EINVAL;
+	}
+
+	if (key.specified & ~AVTAB_SPECIFIER_MASK) {
+		pr_err("SELinux:  avtab:  invalid specifier\n");
+		return -EINVAL;
+	}
+
+	if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) &&
+	    (key.specified & AVTAB_XPERMS)) {
+		pr_err("SELinux:  avtab:  policy version %u does not "
+		       "support extended permissions rules and one "
+		       "was specified\n",
+		       vers);
+		return -EINVAL;
+	} else if ((vers < POLICYDB_VERSION_COND_XPERMS) &&
+		   (key.specified & AVTAB_XPERMS) && conditional) {
+		pr_err("SELinux:  avtab:  policy version %u does not "
+		       "support extended permissions rules in conditional "
+		       "policies and one was specified\n",
+		       vers);
+		return -EINVAL;
+	} else if (key.specified & AVTAB_XPERMS) {
+		memset(&xperms, 0, sizeof(struct avtab_extended_perms));
+		rc = next_entry(&xperms.specified, fp, sizeof(u8));
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		if (!avtab_is_valid_xperm_specified(xperms.specified))
+			pr_warn_once_policyload(pol,
+						"SELinux: avtab: unsupported xperm specifier %#x\n",
+						xperms.specified);
+		rc = next_entry(&xperms.driver, fp, sizeof(u8));
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		rc = next_entry(buf32, fp,
+				sizeof(u32) * ARRAY_SIZE(xperms.perms.p));
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++)
+			xperms.perms.p[i] = le32_to_cpu(buf32[i]);
+		datum.u.xperms = &xperms;
+	} else {
+		rc = next_entry(buf32, fp, sizeof(u32));
+		if (rc) {
+			pr_err("SELinux: avtab: truncated entry\n");
+			return rc;
+		}
+		datum.u.data = le32_to_cpu(*buf32);
+	}
+	if ((key.specified & AVTAB_TYPE) &&
+	    !policydb_simpletype_isvalid(pol, datum.u.data)) {
+		pr_err("SELinux: avtab: invalid type\n");
+		return -EINVAL;
+	}
+	return insertf(a, &key, &datum, p);
+}
+
+static int avtab_insertf(struct avtab *a, const struct avtab_key *k,
+			 const struct avtab_datum *d, void *p)
+{
+	return avtab_insert(a, k, d);
+}
+
+int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol)
+{
+	int rc;
+	__le32 buf[1];
+	u32 nel, i;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc < 0) {
+		pr_err("SELinux: avtab: truncated table\n");
+		goto bad;
+	}
+	nel = le32_to_cpu(buf[0]);
+	if (!nel) {
+		pr_err("SELinux: avtab: table is empty\n");
+		rc = -EINVAL;
+		goto bad;
+	}
+
+	/* avtab_read_item() reads at least 96 bytes for any valid entry */
+	rc = size_check(3 * sizeof(u32), nel, fp);
+	if (rc)
+		goto bad;
+
+	rc = avtab_alloc(a, nel);
+	if (rc)
+		goto bad;
+
+	for (i = 0; i < nel; i++) {
+		rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL, false);
+		if (rc) {
+			if (rc == -ENOMEM)
+				pr_err("SELinux: avtab: out of memory\n");
+			else if (rc == -EEXIST)
+				pr_err("SELinux: avtab: duplicate entry\n");
+
+			goto bad;
+		}
+	}
+
+	rc = 0;
+out:
+	return rc;
+
+bad:
+	avtab_destroy(a);
+	goto out;
+}
+
+int avtab_write_item(struct policydb *p, const struct avtab_node *cur, struct policy_file *fp)
+{
+	__le16 buf16[4];
+	__le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)];
+	int rc;
+	unsigned int i;
+
+	buf16[0] = cpu_to_le16(cur->key.source_type);
+	buf16[1] = cpu_to_le16(cur->key.target_type);
+	buf16[2] = cpu_to_le16(cur->key.target_class);
+	buf16[3] = cpu_to_le16(cur->key.specified);
+	rc = put_entry(buf16, sizeof(u16), 4, fp);
+	if (rc)
+		return rc;
+
+	if (cur->key.specified & AVTAB_XPERMS) {
+		rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1,
+			       fp);
+		if (rc)
+			return rc;
+		rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp);
+		if (rc)
+			return rc;
+		for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++)
+			buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]);
+		rc = put_entry(buf32, sizeof(u32),
+			       ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp);
+	} else {
+		buf32[0] = cpu_to_le32(cur->datum.u.data);
+		rc = put_entry(buf32, sizeof(u32), 1, fp);
+	}
+	if (rc)
+		return rc;
+	return 0;
+}
+
+int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp)
+{
+	u32 i;
+	int rc = 0;
+	struct avtab_node *cur;
+	__le32 buf[1];
+
+	buf[0] = cpu_to_le32(a->nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < a->nslot; i++) {
+		for (cur = a->htable[i]; cur; cur = cur->next) {
+			rc = avtab_write_item(p, cur, fp);
+			if (rc)
+				return rc;
+		}
+	}
+
+	return rc;
+}
+
+void __init avtab_cache_init(void)
+{
+	avtab_node_cachep = KMEM_CACHE(avtab_node, SLAB_PANIC);
+	avtab_xperms_cachep = KMEM_CACHE(avtab_extended_perms, SLAB_PANIC);
+}
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
new file mode 100644
index 000000000..1de4cce28
--- /dev/null
+++ b/security/selinux/ss/avtab.h
@@ -0,0 +1,141 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * An access vector table (avtab) is a hash table
+ * of access vectors and transition types indexed
+ * by a type pair and a class.  An access vector
+ * table is used to represent the type enforcement
+ * tables.
+ *
+ *  Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/* Updated: Frank Mayer <mayerf@tresys.com> and
+ *          Karl MacMillan <kmacmillan@tresys.com>
+ *          Added conditional policy language extensions
+ *          Copyright (C) 2003 Tresys Technology, LLC
+ *
+ * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp>
+ *          Tuned number of hash slots for avtab to reduce memory usage
+ */
+
+#ifndef _SS_AVTAB_H_
+#define _SS_AVTAB_H_
+
+#include "security.h"
+
+struct avtab_key {
+	u16 source_type; /* source type */
+	u16 target_type; /* target type */
+	u16 target_class; /* target object class */
+#define AVTAB_ALLOWED	 0x0001
+#define AVTAB_AUDITALLOW 0x0002
+#define AVTAB_AUDITDENY	 0x0004
+#define AVTAB_AV	 (AVTAB_ALLOWED | AVTAB_AUDITALLOW | AVTAB_AUDITDENY)
+#define AVTAB_TRANSITION 0x0010
+#define AVTAB_MEMBER	 0x0020
+#define AVTAB_CHANGE	 0x0040
+#define AVTAB_TYPE	 (AVTAB_TRANSITION | AVTAB_MEMBER | AVTAB_CHANGE)
+/* extended permissions */
+#define AVTAB_XPERMS_ALLOWED	0x0100
+#define AVTAB_XPERMS_AUDITALLOW 0x0200
+#define AVTAB_XPERMS_DONTAUDIT	0x0400
+#define AVTAB_XPERMS                                      \
+	(AVTAB_XPERMS_ALLOWED | AVTAB_XPERMS_AUDITALLOW | \
+	 AVTAB_XPERMS_DONTAUDIT)
+#define AVTAB_ENABLED_OLD 0x80000000 /* reserved for used in cond_avtab */
+#define AVTAB_ENABLED	  0x8000 /* reserved for used in cond_avtab */
+#define AVTAB_SPECIFIER_MASK (AVTAB_AV | AVTAB_TYPE | AVTAB_XPERMS | AVTAB_ENABLED)
+	u16 specified; /* what field is specified */
+};
+
+/*
+ * For operations that require more than the 32 permissions provided by the avc
+ * extended permissions may be used to provide 256 bits of permissions.
+ */
+struct avtab_extended_perms {
+/* These are not flags. All 256 values may be used */
+#define AVTAB_XPERMS_IOCTLFUNCTION	0x01
+#define AVTAB_XPERMS_IOCTLDRIVER	0x02
+#define AVTAB_XPERMS_NLMSG		0x03
+	/* extension of the avtab_key specified */
+	u8 specified; /* ioctl, netfilter, ... */
+	/*
+	 * if 256 bits is not adequate as is often the case with ioctls, then
+	 * multiple extended perms may be used and the driver field
+	 * specifies which permissions are included.
+	 */
+	u8 driver;
+	/* 256 bits of permissions */
+	struct extended_perms_data perms;
+};
+
+static inline bool avtab_is_valid_xperm_specified(u8 specified)
+{
+	switch (specified) {
+	case AVTAB_XPERMS_IOCTLFUNCTION:
+	case AVTAB_XPERMS_IOCTLDRIVER:
+	case AVTAB_XPERMS_NLMSG:
+		return true;
+	default:
+		return false;
+	}
+}
+
+struct avtab_datum {
+	union {
+		u32 data; /* access vector or type value */
+		struct avtab_extended_perms *xperms;
+	} u;
+};
+
+struct avtab_node {
+	struct avtab_key key;
+	struct avtab_datum datum;
+	struct avtab_node *next;
+};
+
+struct avtab {
+	struct avtab_node **htable;
+	u32 nel; /* number of elements */
+	u32 nslot; /* number of hash slots */
+	u32 mask; /* mask to compute hash func */
+};
+
+void avtab_init(struct avtab *h);
+int avtab_alloc(struct avtab *h, u32 nrules);
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig);
+void avtab_destroy(struct avtab *h);
+
+#define MAX_AVTAB_HASH_BITS    16
+#define MAX_AVTAB_HASH_BUCKETS (1 << MAX_AVTAB_HASH_BITS)
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+void avtab_hash_eval(struct avtab *h, const char *tag);
+#else
+static inline void avtab_hash_eval(struct avtab *h, const char *tag)
+{
+}
+#endif
+
+struct policydb;
+struct policy_file;
+int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol,
+		    int (*insert)(struct avtab *a, const struct avtab_key *k,
+				  const struct avtab_datum *d, void *p),
+		    void *p, bool conditional);
+
+int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol);
+int avtab_write_item(struct policydb *p, const struct avtab_node *cur,
+		     struct policy_file *fp);
+int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp);
+
+struct avtab_node *avtab_insert_nonunique(struct avtab *h,
+					  const struct avtab_key *key,
+					  const struct avtab_datum *datum);
+
+struct avtab_node *avtab_search_node(struct avtab *h,
+				     const struct avtab_key *key);
+struct avtab_node *avtab_search_node_next(struct avtab_node *node,
+					  u16 specified);
+
+#endif /* _SS_AVTAB_H_ */
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
new file mode 100644
index 000000000..2956dd7ed
--- /dev/null
+++ b/security/selinux/ss/conditional.c
@@ -0,0 +1,765 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Authors: Karl MacMillan <kmacmillan@tresys.com>
+ *	    Frank Mayer <mayerf@tresys.com>
+ *          Copyright (C) 2003 - 2004 Tresys Technology, LLC
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+
+#include "security.h"
+#include "conditional.h"
+#include "policydb.h"
+#include "services.h"
+
+/*
+ * cond_evaluate_expr evaluates a conditional expr
+ * in reverse polish notation. It returns true (1), false (0),
+ * or undefined (-1). Undefined occurs when the expression
+ * exceeds the stack depth of COND_EXPR_MAXDEPTH.
+ */
+static int cond_evaluate_expr(struct policydb *p, struct cond_expr *expr)
+{
+	u32 i;
+	int s[COND_EXPR_MAXDEPTH];
+	int sp = -1;
+
+	if (expr->len == 0)
+		return -1;
+
+	for (i = 0; i < expr->len; i++) {
+		struct cond_expr_node *node = &expr->nodes[i];
+
+		switch (node->expr_type) {
+		case COND_BOOL:
+			if (sp == (COND_EXPR_MAXDEPTH - 1))
+				return -1;
+			sp++;
+			s[sp] = p->bool_val_to_struct[node->boolean - 1]->state;
+			break;
+		case COND_NOT:
+			if (sp < 0)
+				return -1;
+			s[sp] = !s[sp];
+			break;
+		case COND_OR:
+			if (sp < 1)
+				return -1;
+			sp--;
+			s[sp] |= s[sp + 1];
+			break;
+		case COND_AND:
+			if (sp < 1)
+				return -1;
+			sp--;
+			s[sp] &= s[sp + 1];
+			break;
+		case COND_XOR:
+			if (sp < 1)
+				return -1;
+			sp--;
+			s[sp] ^= s[sp + 1];
+			break;
+		case COND_EQ:
+			if (sp < 1)
+				return -1;
+			sp--;
+			s[sp] = (s[sp] == s[sp + 1]);
+			break;
+		case COND_NEQ:
+			if (sp < 1)
+				return -1;
+			sp--;
+			s[sp] = (s[sp] != s[sp + 1]);
+			break;
+		default:
+			return -1;
+		}
+	}
+	return s[0];
+}
+
+/*
+ * evaluate_cond_node evaluates the conditional stored in
+ * a struct cond_node and if the result is different than the
+ * current state of the node it sets the rules in the true/false
+ * list appropriately. If the result of the expression is undefined
+ * all of the rules are disabled for safety.
+ */
+static void evaluate_cond_node(struct policydb *p, struct cond_node *node)
+{
+	struct avtab_node *avnode;
+	int new_state;
+	u32 i;
+
+	new_state = cond_evaluate_expr(p, &node->expr);
+	if (new_state != node->cur_state) {
+		node->cur_state = new_state;
+		if (new_state == -1)
+			pr_err("SELinux: expression result was undefined - disabling all rules.\n");
+		/* turn the rules on or off */
+		for (i = 0; i < node->true_list.len; i++) {
+			avnode = node->true_list.nodes[i];
+			if (new_state <= 0)
+				avnode->key.specified &= ~AVTAB_ENABLED;
+			else
+				avnode->key.specified |= AVTAB_ENABLED;
+		}
+
+		for (i = 0; i < node->false_list.len; i++) {
+			avnode = node->false_list.nodes[i];
+			/* -1 or 1 */
+			if (new_state)
+				avnode->key.specified &= ~AVTAB_ENABLED;
+			else
+				avnode->key.specified |= AVTAB_ENABLED;
+		}
+	}
+}
+
+void evaluate_cond_nodes(struct policydb *p)
+{
+	u32 i;
+
+	for (i = 0; i < p->cond_list_len; i++)
+		evaluate_cond_node(p, &p->cond_list[i]);
+}
+
+void cond_policydb_init(struct policydb *p)
+{
+	p->bool_val_to_struct = NULL;
+	p->cond_list = NULL;
+	p->cond_list_len = 0;
+
+	avtab_init(&p->te_cond_avtab);
+}
+
+static void cond_node_destroy(struct cond_node *node)
+{
+	kfree(node->expr.nodes);
+	/* the avtab_ptr_t nodes are destroyed by the avtab */
+	kfree(node->true_list.nodes);
+	kfree(node->false_list.nodes);
+}
+
+static void cond_list_destroy(struct policydb *p)
+{
+	u32 i;
+
+	for (i = 0; i < p->cond_list_len; i++)
+		cond_node_destroy(&p->cond_list[i]);
+	kfree(p->cond_list);
+	p->cond_list = NULL;
+	p->cond_list_len = 0;
+}
+
+void cond_policydb_destroy(struct policydb *p)
+{
+	kfree(p->bool_val_to_struct);
+	avtab_destroy(&p->te_cond_avtab);
+	cond_list_destroy(p);
+}
+
+int cond_init_bool_indexes(struct policydb *p)
+{
+	kfree(p->bool_val_to_struct);
+	p->bool_val_to_struct = kzalloc_objs(*p->bool_val_to_struct,
+					     p->p_bools.nprim);
+	if (!p->bool_val_to_struct)
+		return -ENOMEM;
+
+	avtab_hash_eval(&p->te_cond_avtab, "conditional_rules");
+
+	return 0;
+}
+
+int cond_destroy_bool(void *key, void *datum, void *p)
+{
+	kfree(key);
+	kfree(datum);
+	return 0;
+}
+
+int cond_index_bool(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct cond_bool_datum *booldatum;
+
+	booldatum = datum;
+	p = datap;
+
+	if (!booldatum->value || booldatum->value > p->p_bools.nprim)
+		return -EINVAL;
+
+	p->sym_val_to_name[SYM_BOOLS][booldatum->value - 1] = key;
+	p->bool_val_to_struct[booldatum->value - 1] = booldatum;
+
+	return 0;
+}
+
+int cond_read_bool(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct cond_bool_datum *booldatum;
+	__le32 buf[3];
+	u32 len, val;
+	int rc;
+
+	booldatum = kzalloc_obj(*booldatum);
+	if (!booldatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof(buf));
+	if (rc)
+		goto err;
+
+	booldatum->value = le32_to_cpu(buf[0]);
+	val = le32_to_cpu(buf[1]);
+
+	rc = -EINVAL;
+	if (!val_is_boolean(val))
+		goto err;
+	booldatum->state = (int)val;
+
+	len = le32_to_cpu(buf[2]);
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto err;
+
+	rc = symtab_insert(s, key, booldatum);
+	if (rc)
+		goto err;
+
+	return 0;
+err:
+	pr_err("SELinux: conditional: failed to read boolean\n");
+	cond_destroy_bool(key, booldatum, NULL);
+	return rc;
+}
+
+struct cond_insertf_data {
+	struct policydb *p;
+	struct avtab_node **dst;
+	struct cond_av_list *other;
+};
+
+static int cond_insertf(struct avtab *a, const struct avtab_key *k,
+			const struct avtab_datum *d, void *ptr)
+{
+	struct cond_insertf_data *data = ptr;
+	struct policydb *p = data->p;
+	struct cond_av_list *other = data->other;
+	struct avtab_node *node_ptr;
+	u32 i;
+	bool found;
+
+	/*
+	 * For type rules we have to make certain there aren't any
+	 * conflicting rules by searching the te_avtab and the
+	 * cond_te_avtab.
+	 */
+	if (k->specified & AVTAB_TYPE) {
+		if (avtab_search_node(&p->te_avtab, k)) {
+			pr_err("SELinux: type rule already exists outside of a conditional.\n");
+			return -EINVAL;
+		}
+		/*
+		 * If we are reading the false list other will be a pointer to
+		 * the true list. We can have duplicate entries if there is only
+		 * 1 other entry and it is in our true list.
+		 *
+		 * If we are reading the true list (other == NULL) there shouldn't
+		 * be any other entries.
+		 */
+		if (other) {
+			node_ptr = avtab_search_node(&p->te_cond_avtab, k);
+			if (node_ptr) {
+				if (avtab_search_node_next(node_ptr,
+							   k->specified)) {
+					pr_err("SELinux: too many conflicting type rules.\n");
+					return -EINVAL;
+				}
+				found = false;
+				for (i = 0; i < other->len; i++) {
+					if (other->nodes[i] == node_ptr) {
+						found = true;
+						break;
+					}
+				}
+				if (!found) {
+					pr_err("SELinux: conflicting type rules.\n");
+					return -EINVAL;
+				}
+			}
+		} else {
+			if (avtab_search_node(&p->te_cond_avtab, k)) {
+				pr_err("SELinux: conflicting type rules when adding type rule for true.\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	node_ptr = avtab_insert_nonunique(&p->te_cond_avtab, k, d);
+	if (!node_ptr) {
+		pr_err("SELinux: could not insert rule.\n");
+		return -ENOMEM;
+	}
+
+	*data->dst = node_ptr;
+	return 0;
+}
+
+static int cond_read_av_list(struct policydb *p, struct policy_file *fp,
+			     struct cond_av_list *list,
+			     struct cond_av_list *other)
+{
+	int rc;
+	__le32 buf[1];
+	u32 i, len;
+	struct cond_insertf_data data;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+
+	len = le32_to_cpu(buf[0]);
+	if (len == 0)
+		return 0;
+
+	/* avtab_read_item() reads at least 96 bytes for any valid entry */
+	rc = size_check(3 * sizeof(u32), len, fp);
+	if (rc)
+		return rc;
+
+	list->nodes = kzalloc_objs(*list->nodes, len);
+	if (!list->nodes)
+		return -ENOMEM;
+
+	data.p = p;
+	data.other = other;
+	for (i = 0; i < len; i++) {
+		data.dst = &list->nodes[i];
+		rc = avtab_read_item(&p->te_cond_avtab, fp, p, cond_insertf,
+				     &data, true);
+		if (rc) {
+			kfree(list->nodes);
+			list->nodes = NULL;
+			return rc;
+		}
+	}
+
+	list->len = len;
+	return 0;
+}
+
+static int expr_node_isvalid(struct policydb *p, struct cond_expr_node *expr)
+{
+	if (expr->expr_type <= 0 || expr->expr_type > COND_LAST) {
+		pr_err("SELinux: conditional expressions uses unknown operator.\n");
+		return 0;
+	}
+
+	if (expr->expr_type == COND_BOOL &&
+	    (expr->boolean == 0 || expr->boolean > p->p_bools.nprim)) {
+		pr_err("SELinux: conditional expressions uses unknown bool.\n");
+		return 0;
+	}
+	return 1;
+}
+
+static int cond_read_node(struct policydb *p, struct cond_node *node, struct policy_file *fp)
+{
+	__le32 buf[2];
+	u32 i, len;
+	int rc;
+
+	rc = next_entry(buf, fp, sizeof(u32) * 2);
+	if (rc)
+		return rc;
+
+	node->cur_state = le32_to_cpu(buf[0]);
+
+	/* expr */
+	len = le32_to_cpu(buf[1]);
+
+	/* we will read 64 bytes per node */
+	rc = size_check(2 * sizeof(u32), len, fp);
+	if (rc)
+		return rc;
+
+	node->expr.nodes = kzalloc_objs(*node->expr.nodes, len);
+	if (!node->expr.nodes)
+		return -ENOMEM;
+
+	node->expr.len = len;
+
+	for (i = 0; i < len; i++) {
+		struct cond_expr_node *expr = &node->expr.nodes[i];
+
+		rc = next_entry(buf, fp, sizeof(u32) * 2);
+		if (rc)
+			return rc;
+
+		expr->expr_type = le32_to_cpu(buf[0]);
+		expr->boolean = le32_to_cpu(buf[1]);
+
+		if (!expr_node_isvalid(p, expr))
+			return -EINVAL;
+	}
+
+	rc = cond_read_av_list(p, fp, &node->true_list, NULL);
+	if (rc)
+		return rc;
+	return cond_read_av_list(p, fp, &node->false_list, &node->true_list);
+}
+
+int cond_read_list(struct policydb *p, struct policy_file *fp)
+{
+	__le32 buf[1];
+	u32 i, len;
+	int rc;
+
+	rc = next_entry(buf, fp, sizeof(buf));
+	if (rc)
+		return rc;
+
+	len = le32_to_cpu(buf[0]);
+
+	/* cond_read_node() reads at least 128 bytes for any valid node */
+	rc = size_check(4 * sizeof(u32), len, fp);
+	if (rc)
+		return rc;
+
+	p->cond_list = kzalloc_objs(*p->cond_list, len);
+	if (!p->cond_list)
+		return -ENOMEM;
+
+	rc = avtab_alloc(&(p->te_cond_avtab), p->te_avtab.nel);
+	if (rc)
+		goto err;
+
+	p->cond_list_len = len;
+
+	for (i = 0; i < len; i++) {
+		rc = cond_read_node(p, &p->cond_list[i], fp);
+		if (rc)
+			goto err;
+	}
+	return 0;
+err:
+	cond_list_destroy(p);
+	return rc;
+}
+
+int cond_write_bool(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct cond_bool_datum *booldatum = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[3];
+	u32 len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(booldatum->value);
+	buf[1] = cpu_to_le32(booldatum->state);
+	buf[2] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+	return 0;
+}
+
+/*
+ * cond_write_cond_av_list doesn't write out the av_list nodes.
+ * Instead it writes out the key/value pairs from the avtab. This
+ * is necessary because there is no way to uniquely identifying rules
+ * in the avtab so it is not possible to associate individual rules
+ * in the avtab with a conditional without saving them as part of
+ * the conditional. This means that the avtab with the conditional
+ * rules will not be saved but will be rebuilt on policy load.
+ */
+static int cond_write_av_list(struct policydb *p, struct cond_av_list *list,
+			      struct policy_file *fp)
+{
+	__le32 buf[1];
+	u32 i;
+	int rc;
+
+	buf[0] = cpu_to_le32(list->len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < list->len; i++) {
+		rc = avtab_write_item(p, list->nodes[i], fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int cond_write_node(struct policydb *p, struct cond_node *node,
+			   struct policy_file *fp)
+{
+	__le32 buf[2];
+	int rc;
+	u32 i;
+
+	buf[0] = cpu_to_le32(node->cur_state);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	buf[0] = cpu_to_le32(node->expr.len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < node->expr.len; i++) {
+		buf[0] = cpu_to_le32(node->expr.nodes[i].expr_type);
+		buf[1] = cpu_to_le32(node->expr.nodes[i].boolean);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+	}
+
+	rc = cond_write_av_list(p, &node->true_list, fp);
+	if (rc)
+		return rc;
+	rc = cond_write_av_list(p, &node->false_list, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+int cond_write_list(struct policydb *p, struct policy_file *fp)
+{
+	u32 i;
+	__le32 buf[1];
+	int rc;
+
+	buf[0] = cpu_to_le32(p->cond_list_len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < p->cond_list_len; i++) {
+		rc = cond_write_node(p, &p->cond_list[i], fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key,
+			 struct extended_perms_decision *xpermd)
+{
+	struct avtab_node *node;
+
+	if (!ctab || !key || !xpermd)
+		return;
+
+	for (node = avtab_search_node(ctab, key); node;
+	     node = avtab_search_node_next(node, key->specified)) {
+		if (node->key.specified & AVTAB_ENABLED)
+			services_compute_xperms_decision(xpermd, node);
+	}
+}
+/* Determine whether additional permissions are granted by the conditional
+ * av table, and if so, add them to the result
+ */
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		     struct av_decision *avd, struct extended_perms *xperms)
+{
+	struct avtab_node *node;
+
+	if (!ctab || !key || !avd)
+		return;
+
+	for (node = avtab_search_node(ctab, key); node;
+	     node = avtab_search_node_next(node, key->specified)) {
+		if ((u16)(AVTAB_ALLOWED | AVTAB_ENABLED) ==
+		    (node->key.specified & (AVTAB_ALLOWED | AVTAB_ENABLED)))
+			avd->allowed |= node->datum.u.data;
+		if ((u16)(AVTAB_AUDITDENY | AVTAB_ENABLED) ==
+		    (node->key.specified & (AVTAB_AUDITDENY | AVTAB_ENABLED)))
+			/* Since a '0' in an auditdeny mask represents a
+			 * permission we do NOT want to audit (dontaudit), we use
+			 * the '&' operand to ensure that all '0's in the mask
+			 * are retained (much unlike the allow and auditallow cases).
+			 */
+			avd->auditdeny &= node->datum.u.data;
+		if ((u16)(AVTAB_AUDITALLOW | AVTAB_ENABLED) ==
+		    (node->key.specified & (AVTAB_AUDITALLOW | AVTAB_ENABLED)))
+			avd->auditallow |= node->datum.u.data;
+		if (xperms && (node->key.specified & AVTAB_ENABLED) &&
+		    (node->key.specified & AVTAB_XPERMS))
+			services_compute_xperms_drivers(xperms, node);
+	}
+}
+
+static int cond_dup_av_list(struct cond_av_list *new,
+			    const struct cond_av_list *orig,
+			    struct avtab *avtab)
+{
+	u32 i;
+
+	memset(new, 0, sizeof(*new));
+
+	new->nodes = kzalloc_objs(*new->nodes, orig->len);
+	if (!new->nodes)
+		return -ENOMEM;
+
+	for (i = 0; i < orig->len; i++) {
+		new->nodes[i] = avtab_insert_nonunique(
+			avtab, &orig->nodes[i]->key, &orig->nodes[i]->datum);
+		if (!new->nodes[i])
+			return -ENOMEM;
+		new->len++;
+	}
+
+	return 0;
+}
+
+static int duplicate_policydb_cond_list(struct policydb *newp,
+					const struct policydb *origp)
+{
+	int rc;
+	u32 i;
+
+	rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab);
+	if (rc)
+		return rc;
+
+	newp->cond_list_len = 0;
+	newp->cond_list = kzalloc_objs(*newp->cond_list, origp->cond_list_len);
+	if (!newp->cond_list)
+		goto error;
+
+	for (i = 0; i < origp->cond_list_len; i++) {
+		struct cond_node *newn = &newp->cond_list[i];
+		const struct cond_node *orign = &origp->cond_list[i];
+
+		newp->cond_list_len++;
+
+		newn->cur_state = orign->cur_state;
+		newn->expr.nodes =
+			kmemdup(orign->expr.nodes,
+				orign->expr.len * sizeof(*orign->expr.nodes),
+				GFP_KERNEL);
+		if (!newn->expr.nodes)
+			goto error;
+
+		newn->expr.len = orign->expr.len;
+
+		rc = cond_dup_av_list(&newn->true_list, &orign->true_list,
+				      &newp->te_cond_avtab);
+		if (rc)
+			goto error;
+
+		rc = cond_dup_av_list(&newn->false_list, &orign->false_list,
+				      &newp->te_cond_avtab);
+		if (rc)
+			goto error;
+	}
+
+	return 0;
+
+error:
+	avtab_destroy(&newp->te_cond_avtab);
+	cond_list_destroy(newp);
+	return -ENOMEM;
+}
+
+static int cond_bools_destroy(void *key, void *datum, void *args)
+{
+	/* key was not copied so no need to free here */
+	kfree(datum);
+	return 0;
+}
+
+static int cond_bools_copy(struct hashtab_node *new,
+			   const struct hashtab_node *orig, void *args)
+{
+	struct cond_bool_datum *datum;
+
+	datum = kmemdup(orig->datum, sizeof(struct cond_bool_datum),
+			GFP_KERNEL);
+	if (!datum)
+		return -ENOMEM;
+
+	new->key = orig->key; /* No need to copy, never modified */
+	new->datum = datum;
+	return 0;
+}
+
+static int cond_bools_index(void *key, void *datum, void *args)
+{
+	struct cond_bool_datum *booldatum, **cond_bool_array;
+
+	booldatum = datum;
+	cond_bool_array = args;
+	cond_bool_array[booldatum->value - 1] = booldatum;
+
+	return 0;
+}
+
+static int duplicate_policydb_bools(struct policydb *newdb,
+				    const struct policydb *orig)
+{
+	struct cond_bool_datum **cond_bool_array;
+	int rc;
+
+	cond_bool_array = kzalloc_objs(*orig->bool_val_to_struct,
+				       orig->p_bools.nprim);
+	if (!cond_bool_array)
+		return -ENOMEM;
+
+	rc = hashtab_duplicate(&newdb->p_bools.table, &orig->p_bools.table,
+			       cond_bools_copy, cond_bools_destroy, NULL);
+	if (rc) {
+		kfree(cond_bool_array);
+		return -ENOMEM;
+	}
+
+	hashtab_map(&newdb->p_bools.table, cond_bools_index, cond_bool_array);
+	newdb->bool_val_to_struct = cond_bool_array;
+
+	newdb->p_bools.nprim = orig->p_bools.nprim;
+
+	return 0;
+}
+
+void cond_policydb_destroy_dup(struct policydb *p)
+{
+	hashtab_map(&p->p_bools.table, cond_bools_destroy, NULL);
+	hashtab_destroy(&p->p_bools.table);
+	cond_policydb_destroy(p);
+}
+
+int cond_policydb_dup(struct policydb *new, const struct policydb *orig)
+{
+	cond_policydb_init(new);
+
+	if (duplicate_policydb_bools(new, orig))
+		return -ENOMEM;
+
+	if (duplicate_policydb_cond_list(new, orig)) {
+		cond_policydb_destroy_dup(new);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
new file mode 100644
index 000000000..468e98ad3
--- /dev/null
+++ b/security/selinux/ss/conditional.h
@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Authors: Karl MacMillan <kmacmillan@tresys.com>
+ *          Frank Mayer <mayerf@tresys.com>
+ *          Copyright (C) 2003 - 2004 Tresys Technology, LLC
+ */
+
+#ifndef _CONDITIONAL_H_
+#define _CONDITIONAL_H_
+
+#include "avtab.h"
+#include "symtab.h"
+#include "policydb.h"
+#include "../include/conditional.h"
+
+#define COND_EXPR_MAXDEPTH 10
+
+/*
+ * A conditional expression is a list of operators and operands
+ * in reverse polish notation.
+ */
+struct cond_expr_node {
+#define COND_BOOL 1 /* plain bool */
+#define COND_NOT  2 /* !bool */
+#define COND_OR	  3 /* bool || bool */
+#define COND_AND  4 /* bool && bool */
+#define COND_XOR  5 /* bool ^ bool */
+#define COND_EQ	  6 /* bool == bool */
+#define COND_NEQ  7 /* bool != bool */
+#define COND_LAST COND_NEQ
+	u32 expr_type;
+	u32 boolean;
+};
+
+struct cond_expr {
+	struct cond_expr_node *nodes;
+	u32 len;
+};
+
+/*
+ * Each cond_node contains a list of rules to be enabled/disabled
+ * depending on the current value of the conditional expression. This
+ * struct is for that list.
+ */
+struct cond_av_list {
+	struct avtab_node **nodes;
+	u32 len;
+};
+
+/*
+ * A cond node represents a conditional block in a policy. It
+ * contains a conditional expression, the current state of the expression,
+ * two lists of rules to enable/disable depending on the value of the
+ * expression (the true list corresponds to if and the false list corresponds
+ * to else)..
+ */
+struct cond_node {
+	int cur_state;
+	struct cond_expr expr;
+	struct cond_av_list true_list;
+	struct cond_av_list false_list;
+};
+
+void cond_policydb_init(struct policydb *p);
+void cond_policydb_destroy(struct policydb *p);
+
+int cond_init_bool_indexes(struct policydb *p);
+int cond_destroy_bool(void *key, void *datum, void *p);
+
+int cond_index_bool(void *key, void *datum, void *datap);
+
+int cond_read_bool(struct policydb *p, struct symtab *s, struct policy_file *fp);
+int cond_read_list(struct policydb *p, struct policy_file *fp);
+int cond_write_bool(void *key, void *datum, void *ptr);
+int cond_write_list(struct policydb *p, struct policy_file *fp);
+
+void cond_compute_av(struct avtab *ctab, struct avtab_key *key,
+		     struct av_decision *avd, struct extended_perms *xperms);
+void cond_compute_xperms(struct avtab *ctab, struct avtab_key *key,
+			 struct extended_perms_decision *xpermd);
+void evaluate_cond_nodes(struct policydb *p);
+void cond_policydb_destroy_dup(struct policydb *p);
+int cond_policydb_dup(struct policydb *new, const struct policydb *orig);
+
+#endif /* _CONDITIONAL_H_ */
diff --git a/security/selinux/ss/constraint.h b/security/selinux/ss/constraint.h
new file mode 100644
index 000000000..1d75a8a04
--- /dev/null
+++ b/security/selinux/ss/constraint.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A constraint is a condition that must be satisfied in
+ * order for one or more permissions to be granted.
+ * Constraints are used to impose additional restrictions
+ * beyond the type-based rules in `te' or the role-based
+ * transition rules in `rbac'.  Constraints are typically
+ * used to prevent a process from transitioning to a new user
+ * identity or role unless it is in a privileged type.
+ * Constraints are likewise typically used to prevent a
+ * process from labeling an object with a different user
+ * identity.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_CONSTRAINT_H_
+#define _SS_CONSTRAINT_H_
+
+#include "ebitmap.h"
+
+#define CEXPR_MAXDEPTH 5
+
+struct constraint_expr {
+#define CEXPR_NOT   1 /* not expr */
+#define CEXPR_AND   2 /* expr and expr */
+#define CEXPR_OR    3 /* expr or expr */
+#define CEXPR_ATTR  4 /* attr op attr */
+#define CEXPR_NAMES 5 /* attr op names */
+	u32 expr_type; /* expression type */
+
+#define CEXPR_USER    1 /* user */
+#define CEXPR_ROLE    2 /* role */
+#define CEXPR_TYPE    4 /* type */
+#define CEXPR_TARGET  8 /* target if set, source otherwise */
+#define CEXPR_XTARGET 16 /* special 3rd target for validatetrans rule */
+#define CEXPR_L1L2    32 /* low level 1 vs. low level 2 */
+#define CEXPR_L1H2    64 /* low level 1 vs. high level 2 */
+#define CEXPR_H1L2    128 /* high level 1 vs. low level 2 */
+#define CEXPR_H1H2    256 /* high level 1 vs. high level 2 */
+#define CEXPR_L1H1    512 /* low level 1 vs. high level 1 */
+#define CEXPR_L2H2    1024 /* low level 2 vs. high level 2 */
+	u32 attr; /* attribute */
+
+#define CEXPR_EQ     1 /* == or eq */
+#define CEXPR_NEQ    2 /* != */
+#define CEXPR_DOM    3 /* dom */
+#define CEXPR_DOMBY  4 /* domby  */
+#define CEXPR_INCOMP 5 /* incomp */
+	u32 op; /* operator */
+
+	struct ebitmap names; /* names */
+	/* internally unused, only forwarded via policydb_write() */
+	struct type_set *type_names;
+
+	struct constraint_expr *next; /* next expression */
+};
+
+struct constraint_node {
+	u32 permissions; /* constrained permissions */
+	struct constraint_expr *expr; /* constraint on permissions */
+	struct constraint_node *next; /* next constraint */
+};
+
+#endif /* _SS_CONSTRAINT_H_ */
diff --git a/security/selinux/ss/context.c b/security/selinux/ss/context.c
new file mode 100644
index 000000000..a528b7f76
--- /dev/null
+++ b/security/selinux/ss/context.c
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Implementations of the security context functions.
+ *
+ * Author: Ondrej Mosnacek <omosnacek@gmail.com>
+ * Copyright (C) 2020 Red Hat, Inc.
+ */
+
+#include <linux/jhash.h>
+
+#include "context.h"
+#include "mls.h"
+
+u32 context_compute_hash(const struct context *c)
+{
+	u32 hash = 0;
+
+	/*
+	 * If a context is invalid, it will always be represented by a
+	 * context struct with only the len & str set (and vice versa)
+	 * under a given policy. Since context structs from different
+	 * policies should never meet, it is safe to hash valid and
+	 * invalid contexts differently. The context_equal() function
+	 * already operates under the same assumption.
+	 */
+	if (c->len)
+		return full_name_hash(NULL, c->str, c->len);
+
+	hash = jhash_3words(c->user, c->role, c->type, hash);
+	hash = mls_range_hash(&c->range, hash);
+	return hash;
+}
diff --git a/security/selinux/ss/context.h b/security/selinux/ss/context.h
new file mode 100644
index 000000000..dd3b9b5b5
--- /dev/null
+++ b/security/selinux/ss/context.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A security context is a set of security attributes
+ * associated with each subject and object controlled
+ * by the security policy.  Security contexts are
+  * externally represented as variable-length strings
+ * that can be interpreted by a user or application
+ * with an understanding of the security policy.
+ * Internally, the security server uses a simple
+ * structure.  This structure is private to the
+ * security server and can be changed without affecting
+ * clients of the security server.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_CONTEXT_H_
+#define _SS_CONTEXT_H_
+
+#include "ebitmap.h"
+#include "mls_types.h"
+#include "security.h"
+
+/*
+ * A security context consists of an authenticated user
+ * identity, a role, a type and a MLS range.
+ */
+struct context {
+	u32 user;
+	u32 role;
+	u32 type;
+	u32 len; /* length of string in bytes */
+	struct mls_range range;
+	char *str; /* string representation if context cannot be mapped. */
+};
+
+static inline void mls_context_init(struct context *c)
+{
+	memset(&c->range, 0, sizeof(c->range));
+}
+
+static inline int mls_context_cpy(struct context *dst,
+				  const struct context *src)
+{
+	int rc;
+
+	dst->range.level[0].sens = src->range.level[0].sens;
+	rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat);
+	if (rc)
+		goto out;
+
+	dst->range.level[1].sens = src->range.level[1].sens;
+	rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat);
+	if (rc)
+		ebitmap_destroy(&dst->range.level[0].cat);
+out:
+	return rc;
+}
+
+/*
+ * Sets both levels in the MLS range of 'dst' to the low level of 'src'.
+ */
+static inline int mls_context_cpy_low(struct context *dst,
+				      const struct context *src)
+{
+	int rc;
+
+	dst->range.level[0].sens = src->range.level[0].sens;
+	rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[0].cat);
+	if (rc)
+		goto out;
+
+	dst->range.level[1].sens = src->range.level[0].sens;
+	rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[0].cat);
+	if (rc)
+		ebitmap_destroy(&dst->range.level[0].cat);
+out:
+	return rc;
+}
+
+/*
+ * Sets both levels in the MLS range of 'dst' to the high level of 'src'.
+ */
+static inline int mls_context_cpy_high(struct context *dst,
+				       const struct context *src)
+{
+	int rc;
+
+	dst->range.level[0].sens = src->range.level[1].sens;
+	rc = ebitmap_cpy(&dst->range.level[0].cat, &src->range.level[1].cat);
+	if (rc)
+		goto out;
+
+	dst->range.level[1].sens = src->range.level[1].sens;
+	rc = ebitmap_cpy(&dst->range.level[1].cat, &src->range.level[1].cat);
+	if (rc)
+		ebitmap_destroy(&dst->range.level[0].cat);
+out:
+	return rc;
+}
+
+static inline int mls_context_glblub(struct context *dst,
+				     const struct context *c1,
+				     const struct context *c2)
+{
+	struct mls_range *dr = &dst->range;
+	const struct mls_range *r1 = &c1->range, *r2 = &c2->range;
+	int rc = 0;
+
+	if (r1->level[1].sens < r2->level[0].sens ||
+	    r2->level[1].sens < r1->level[0].sens)
+		/* These ranges have no common sensitivities */
+		return -EINVAL;
+
+	/* Take the greatest of the low */
+	dr->level[0].sens = max(r1->level[0].sens, r2->level[0].sens);
+
+	/* Take the least of the high */
+	dr->level[1].sens = min(r1->level[1].sens, r2->level[1].sens);
+
+	rc = ebitmap_and(&dr->level[0].cat, &r1->level[0].cat,
+			 &r2->level[0].cat);
+	if (rc)
+		goto out;
+
+	rc = ebitmap_and(&dr->level[1].cat, &r1->level[1].cat,
+			 &r2->level[1].cat);
+	if (rc)
+		goto out;
+
+out:
+	return rc;
+}
+
+static inline bool mls_context_equal(const struct context *c1,
+				     const struct context *c2)
+{
+	return ((c1->range.level[0].sens == c2->range.level[0].sens) &&
+		ebitmap_equal(&c1->range.level[0].cat, &c2->range.level[0].cat) &&
+		(c1->range.level[1].sens == c2->range.level[1].sens) &&
+		ebitmap_equal(&c1->range.level[1].cat, &c2->range.level[1].cat));
+}
+
+static inline void mls_context_destroy(struct context *c)
+{
+	ebitmap_destroy(&c->range.level[0].cat);
+	ebitmap_destroy(&c->range.level[1].cat);
+	mls_context_init(c);
+}
+
+static inline void context_init(struct context *c)
+{
+	memset(c, 0, sizeof(*c));
+}
+
+static inline int context_cpy(struct context *dst, const struct context *src)
+{
+	int rc;
+
+	dst->user = src->user;
+	dst->role = src->role;
+	dst->type = src->type;
+	if (src->str) {
+		dst->str = kstrdup(src->str, GFP_ATOMIC);
+		if (!dst->str)
+			return -ENOMEM;
+		dst->len = src->len;
+	} else {
+		dst->str = NULL;
+		dst->len = 0;
+	}
+	rc = mls_context_cpy(dst, src);
+	if (rc) {
+		kfree(dst->str);
+		dst->str = NULL;
+		dst->len = 0;
+		return rc;
+	}
+	return 0;
+}
+
+static inline void context_destroy(struct context *c)
+{
+	c->user = c->role = c->type = 0;
+	kfree(c->str);
+	c->str = NULL;
+	c->len = 0;
+	mls_context_destroy(c);
+}
+
+static inline bool context_equal(const struct context *c1,
+				 const struct context *c2)
+{
+	if (c1->len && c2->len)
+		return (c1->len == c2->len && !strcmp(c1->str, c2->str));
+	if (c1->len || c2->len)
+		return 0;
+	return ((c1->user == c2->user) && (c1->role == c2->role) &&
+		(c1->type == c2->type) && mls_context_equal(c1, c2));
+}
+
+u32 context_compute_hash(const struct context *c);
+
+#endif /* _SS_CONTEXT_H_ */
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
new file mode 100644
index 000000000..ea894361f
--- /dev/null
+++ b/security/selinux/ss/ebitmap.c
@@ -0,0 +1,603 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Implementation of the extensible bitmap type.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+/*
+ * Updated: Hewlett-Packard <paul@paul-moore.com>
+ *          Added support to import/export the NetLabel category bitmap
+ *          (c) Copyright Hewlett-Packard Development Company, L.P., 2006
+ *
+ * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com>
+ *          Applied standard bit operations to improve bitmap scanning.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/jhash.h>
+#include <net/netlabel.h>
+#include "ebitmap.h"
+#include "policydb.h"
+
+#define BITS_PER_U64 ((u32)(sizeof(u64) * 8))
+
+static struct kmem_cache *ebitmap_node_cachep __ro_after_init;
+
+bool ebitmap_equal(const struct ebitmap *e1, const struct ebitmap *e2)
+{
+	const struct ebitmap_node *n1, *n2;
+
+	if (e1->highbit != e2->highbit)
+		return false;
+
+	n1 = e1->node;
+	n2 = e2->node;
+	while (n1 && n2 && (n1->startbit == n2->startbit) &&
+	       !memcmp(n1->maps, n2->maps, EBITMAP_SIZE / 8)) {
+		n1 = n1->next;
+		n2 = n2->next;
+	}
+
+	if (n1 || n2)
+		return false;
+
+	return true;
+}
+
+int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src)
+{
+	struct ebitmap_node *new, *prev;
+	const struct ebitmap_node *n;
+
+	ebitmap_init(dst);
+	n = src->node;
+	prev = NULL;
+	while (n) {
+		new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC);
+		if (!new) {
+			ebitmap_destroy(dst);
+			return -ENOMEM;
+		}
+		new->startbit = n->startbit;
+		memcpy(new->maps, n->maps, EBITMAP_SIZE / 8);
+		new->next = NULL;
+		if (prev)
+			prev->next = new;
+		else
+			dst->node = new;
+		prev = new;
+		n = n->next;
+	}
+
+	dst->highbit = src->highbit;
+	return 0;
+}
+
+int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1,
+		const struct ebitmap *e2)
+{
+	struct ebitmap_node *n;
+	u32 bit;
+	int rc;
+
+	ebitmap_init(dst);
+
+	ebitmap_for_each_positive_bit(e1, n, bit)
+	{
+		if (ebitmap_get_bit(e2, bit)) {
+			rc = ebitmap_set_bit(dst, bit, 1);
+			if (rc < 0)
+				return rc;
+		}
+	}
+	return 0;
+}
+
+#ifdef CONFIG_NETLABEL
+/**
+ * ebitmap_netlbl_export - Export an ebitmap into a NetLabel category bitmap
+ * @ebmap: the ebitmap to export
+ * @catmap: the NetLabel category bitmap
+ *
+ * Description:
+ * Export a SELinux extensibile bitmap into a NetLabel category bitmap.
+ * Returns zero on success, negative values on error.
+ *
+ */
+int ebitmap_netlbl_export(struct ebitmap *ebmap,
+			  struct netlbl_lsm_catmap **catmap)
+{
+	struct ebitmap_node *e_iter = ebmap->node;
+	unsigned long e_map;
+	u32 offset;
+	unsigned int iter;
+	int rc;
+
+	if (e_iter == NULL) {
+		*catmap = NULL;
+		return 0;
+	}
+
+	if (*catmap != NULL)
+		netlbl_catmap_free(*catmap);
+	*catmap = NULL;
+
+	while (e_iter) {
+		offset = e_iter->startbit;
+		for (iter = 0; iter < EBITMAP_UNIT_NUMS; iter++) {
+			e_map = e_iter->maps[iter];
+			if (e_map != 0) {
+				rc = netlbl_catmap_setlong(catmap, offset,
+							   e_map, GFP_ATOMIC);
+				if (rc != 0)
+					goto netlbl_export_failure;
+			}
+			offset += EBITMAP_UNIT_SIZE;
+		}
+		e_iter = e_iter->next;
+	}
+
+	return 0;
+
+netlbl_export_failure:
+	netlbl_catmap_free(*catmap);
+	return -ENOMEM;
+}
+
+/**
+ * ebitmap_netlbl_import - Import a NetLabel category bitmap into an ebitmap
+ * @ebmap: the ebitmap to import
+ * @catmap: the NetLabel category bitmap
+ *
+ * Description:
+ * Import a NetLabel category bitmap into a SELinux extensibile bitmap.
+ * Returns zero on success, negative values on error.
+ *
+ */
+int ebitmap_netlbl_import(struct ebitmap *ebmap,
+			  struct netlbl_lsm_catmap *catmap)
+{
+	int rc;
+	struct ebitmap_node *e_iter = NULL;
+	struct ebitmap_node *e_prev = NULL;
+	u32 offset = 0, idx;
+	unsigned long bitmap;
+
+	for (;;) {
+		rc = netlbl_catmap_getlong(catmap, &offset, &bitmap);
+		if (rc < 0)
+			goto netlbl_import_failure;
+		if (offset == (u32)-1)
+			return 0;
+
+		/* don't waste ebitmap space if the netlabel bitmap is empty */
+		if (bitmap == 0) {
+			offset += EBITMAP_UNIT_SIZE;
+			continue;
+		}
+
+		if (e_iter == NULL ||
+		    offset >= e_iter->startbit + EBITMAP_SIZE) {
+			e_prev = e_iter;
+			e_iter = kmem_cache_zalloc(ebitmap_node_cachep,
+						   GFP_ATOMIC);
+			if (e_iter == NULL)
+				goto netlbl_import_failure;
+			e_iter->startbit = offset - (offset % EBITMAP_SIZE);
+			if (e_prev == NULL)
+				ebmap->node = e_iter;
+			else
+				e_prev->next = e_iter;
+			ebmap->highbit = e_iter->startbit + EBITMAP_SIZE;
+		}
+
+		/* offset will always be aligned to an unsigned long */
+		idx = EBITMAP_NODE_INDEX(e_iter, offset);
+		e_iter->maps[idx] = bitmap;
+
+		/* next */
+		offset += EBITMAP_UNIT_SIZE;
+	}
+
+	/* NOTE: we should never reach this return */
+	return 0;
+
+netlbl_import_failure:
+	ebitmap_destroy(ebmap);
+	return -ENOMEM;
+}
+#endif /* CONFIG_NETLABEL */
+
+/*
+ * Check to see if all the bits set in e2 are also set in e1. Optionally,
+ * if last_e2bit is non-zero, the highest set bit in e2 cannot exceed
+ * last_e2bit.
+ */
+int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2,
+		     u32 last_e2bit)
+{
+	const struct ebitmap_node *n1, *n2;
+	int i;
+
+	if (e1->highbit < e2->highbit)
+		return 0;
+
+	n1 = e1->node;
+	n2 = e2->node;
+
+	while (n1 && n2 && (n1->startbit <= n2->startbit)) {
+		if (n1->startbit < n2->startbit) {
+			n1 = n1->next;
+			continue;
+		}
+		for (i = EBITMAP_UNIT_NUMS - 1; (i >= 0) && !n2->maps[i];)
+			i--; /* Skip trailing NULL map entries */
+		if (last_e2bit && (i >= 0)) {
+			u32 lastsetbit = n2->startbit + i * EBITMAP_UNIT_SIZE +
+					 __fls(n2->maps[i]);
+			if (lastsetbit > last_e2bit)
+				return 0;
+		}
+
+		while (i >= 0) {
+			if ((n1->maps[i] & n2->maps[i]) != n2->maps[i])
+				return 0;
+			i--;
+		}
+
+		n1 = n1->next;
+		n2 = n2->next;
+	}
+
+	if (n2)
+		return 0;
+
+	return 1;
+}
+
+u32 ebitmap_get_highest_set_bit(const struct ebitmap *e)
+{
+	const struct ebitmap_node *n;
+	unsigned long unit;
+	u32 pos = 0;
+
+	n = e->node;
+	if (!n)
+		return 0;
+
+	while (n->next)
+		n = n->next;
+
+	for (unsigned int i = EBITMAP_UNIT_NUMS; i > 0; i--) {
+		unit = n->maps[i - 1];
+		if (unit == 0)
+			continue;
+
+		pos = (i - 1) * EBITMAP_UNIT_SIZE;
+		while (unit >>= 1)
+			pos++;
+		break;
+	}
+
+	return n->startbit + pos;
+}
+
+int ebitmap_get_bit(const struct ebitmap *e, u32 bit)
+{
+	const struct ebitmap_node *n;
+
+	if (e->highbit < bit)
+		return 0;
+
+	n = e->node;
+	while (n && (n->startbit <= bit)) {
+		if ((n->startbit + EBITMAP_SIZE) > bit)
+			return ebitmap_node_get_bit(n, bit);
+		n = n->next;
+	}
+
+	return 0;
+}
+
+int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value)
+{
+	struct ebitmap_node *n, *prev, *new;
+
+	prev = NULL;
+	n = e->node;
+	while (n && n->startbit <= bit) {
+		if ((n->startbit + EBITMAP_SIZE) > bit) {
+			if (value) {
+				ebitmap_node_set_bit(n, bit);
+			} else {
+				u32 s;
+
+				ebitmap_node_clr_bit(n, bit);
+
+				s = find_first_bit(n->maps, EBITMAP_SIZE);
+				if (s < EBITMAP_SIZE)
+					return 0;
+
+				/* drop this node from the bitmap */
+				if (!n->next) {
+					/*
+					 * this was the highest map
+					 * within the bitmap
+					 */
+					if (prev)
+						e->highbit = prev->startbit +
+							     EBITMAP_SIZE;
+					else
+						e->highbit = 0;
+				}
+				if (prev)
+					prev->next = n->next;
+				else
+					e->node = n->next;
+				kmem_cache_free(ebitmap_node_cachep, n);
+			}
+			return 0;
+		}
+		prev = n;
+		n = n->next;
+	}
+
+	if (!value)
+		return 0;
+
+	new = kmem_cache_zalloc(ebitmap_node_cachep, GFP_ATOMIC);
+	if (!new)
+		return -ENOMEM;
+
+	new->startbit = bit - (bit % EBITMAP_SIZE);
+	ebitmap_node_set_bit(new, bit);
+
+	if (!n)
+		/* this node will be the highest map within the bitmap */
+		e->highbit = new->startbit + EBITMAP_SIZE;
+
+	if (prev) {
+		new->next = prev->next;
+		prev->next = new;
+	} else {
+		new->next = e->node;
+		e->node = new;
+	}
+
+	return 0;
+}
+
+void ebitmap_destroy(struct ebitmap *e)
+{
+	struct ebitmap_node *n, *temp;
+
+	if (!e)
+		return;
+
+	n = e->node;
+	while (n) {
+		temp = n;
+		n = n->next;
+		kmem_cache_free(ebitmap_node_cachep, temp);
+	}
+
+	e->highbit = 0;
+	e->node = NULL;
+}
+
+int ebitmap_read(struct ebitmap *e, struct policy_file *fp)
+{
+	struct ebitmap_node *n = NULL;
+	u32 mapunit, count, startbit, index, i;
+	__le32 ebitmap_start;
+	u64 map;
+	__le64 mapbits;
+	__le32 buf[3];
+	int rc;
+
+	ebitmap_init(e);
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc < 0)
+		goto out;
+
+	mapunit = le32_to_cpu(buf[0]);
+	e->highbit = le32_to_cpu(buf[1]);
+	count = le32_to_cpu(buf[2]);
+
+	if (mapunit != BITS_PER_U64) {
+		pr_err("SELinux: ebitmap: map size %u does not "
+		       "match my size %u (high bit was %u)\n",
+		       mapunit, BITS_PER_U64, e->highbit);
+		goto bad;
+	}
+
+	/* round up e->highbit */
+	e->highbit += EBITMAP_SIZE - 1;
+	e->highbit -= (e->highbit % EBITMAP_SIZE);
+
+	if (!e->highbit) {
+		e->node = NULL;
+		goto ok;
+	}
+
+	if (e->highbit && !count)
+		goto bad;
+
+	for (i = 0; i < count; i++) {
+		rc = next_entry(&ebitmap_start, fp, sizeof(u32));
+		if (rc < 0) {
+			pr_err("SELinux: ebitmap: truncated map\n");
+			goto bad;
+		}
+		startbit = le32_to_cpu(ebitmap_start);
+
+		if (startbit & (mapunit - 1)) {
+			pr_err("SELinux: ebitmap start bit (%u) is "
+			       "not a multiple of the map unit size (%u)\n",
+			       startbit, mapunit);
+			goto bad;
+		}
+		if (startbit > e->highbit - mapunit) {
+			pr_err("SELinux: ebitmap start bit (%u) is "
+			       "beyond the end of the bitmap (%u)\n",
+			       startbit, (e->highbit - mapunit));
+			goto bad;
+		}
+
+		if (!n || startbit >= n->startbit + EBITMAP_SIZE) {
+			struct ebitmap_node *tmp;
+			tmp = kmem_cache_zalloc(ebitmap_node_cachep,
+						GFP_KERNEL);
+			if (!tmp) {
+				pr_err("SELinux: ebitmap: out of memory\n");
+				rc = -ENOMEM;
+				goto bad;
+			}
+			/* round down */
+			tmp->startbit = startbit - (startbit % EBITMAP_SIZE);
+			if (n)
+				n->next = tmp;
+			else
+				e->node = tmp;
+			n = tmp;
+		} else if (startbit <= n->startbit) {
+			pr_err("SELinux: ebitmap: start bit %u"
+			       " comes after start bit %u\n",
+			       startbit, n->startbit);
+			goto bad;
+		}
+
+		rc = next_entry(&mapbits, fp, sizeof(u64));
+		if (rc < 0) {
+			pr_err("SELinux: ebitmap: truncated map\n");
+			goto bad;
+		}
+		map = le64_to_cpu(mapbits);
+		if (!map) {
+			pr_err("SELinux: ebitmap: empty map\n");
+			goto bad;
+		}
+
+		index = (startbit - n->startbit) / EBITMAP_UNIT_SIZE;
+		while (map) {
+			n->maps[index++] = map & (-1UL);
+			map = EBITMAP_SHIFT_UNIT_SIZE(map);
+		}
+	}
+
+	if (n && n->startbit + EBITMAP_SIZE != e->highbit) {
+		pr_err("SELinux: ebitmap: high bit %u is not equal to the expected value %zu\n",
+		       e->highbit, n->startbit + EBITMAP_SIZE);
+		goto bad;
+	}
+
+ok:
+	rc = 0;
+out:
+	return rc;
+bad:
+	if (!rc)
+		rc = -EINVAL;
+	ebitmap_destroy(e);
+	goto out;
+}
+
+int ebitmap_write(const struct ebitmap *e, struct policy_file *fp)
+{
+	struct ebitmap_node *n;
+	u32 bit, count, last_bit, last_startbit;
+	__le32 buf[3];
+	u64 map;
+	int rc;
+
+	buf[0] = cpu_to_le32(BITS_PER_U64);
+
+	count = 0;
+	last_bit = 0;
+	last_startbit = U32_MAX;
+	ebitmap_for_each_positive_bit(e, n, bit)
+	{
+		if (last_startbit == U32_MAX ||
+		    rounddown(bit, BITS_PER_U64) > last_startbit) {
+			count++;
+			last_startbit = rounddown(bit, BITS_PER_U64);
+		}
+		last_bit = roundup(bit + 1, BITS_PER_U64);
+	}
+	buf[1] = cpu_to_le32(last_bit);
+	buf[2] = cpu_to_le32(count);
+
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	map = 0;
+	last_startbit = U32_MAX;
+	ebitmap_for_each_positive_bit(e, n, bit)
+	{
+		if (last_startbit == U32_MAX ||
+		    rounddown(bit, BITS_PER_U64) > last_startbit) {
+			__le64 buf64[1];
+
+			/* this is the very first bit */
+			if (!map) {
+				last_startbit = rounddown(bit, BITS_PER_U64);
+				map = (u64)1 << (bit - last_startbit);
+				continue;
+			}
+
+			/* write the last node */
+			buf[0] = cpu_to_le32(last_startbit);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+
+			buf64[0] = cpu_to_le64(map);
+			rc = put_entry(buf64, sizeof(u64), 1, fp);
+			if (rc)
+				return rc;
+
+			/* set up for the next node */
+			map = 0;
+			last_startbit = rounddown(bit, BITS_PER_U64);
+		}
+		map |= (u64)1 << (bit - last_startbit);
+	}
+	/* write the last node */
+	if (map) {
+		__le64 buf64[1];
+
+		/* write the last node */
+		buf[0] = cpu_to_le32(last_startbit);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+
+		buf64[0] = cpu_to_le64(map);
+		rc = put_entry(buf64, sizeof(u64), 1, fp);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+u32 ebitmap_hash(const struct ebitmap *e, u32 hash)
+{
+	struct ebitmap_node *node;
+
+	/* need to change hash even if ebitmap is empty */
+	hash = jhash_1word(e->highbit, hash);
+	for (node = e->node; node; node = node->next) {
+		hash = jhash_1word(node->startbit, hash);
+		hash = jhash(node->maps, sizeof(node->maps), hash);
+	}
+	return hash;
+}
+
+void __init ebitmap_cache_init(void)
+{
+	ebitmap_node_cachep = KMEM_CACHE(ebitmap_node, SLAB_PANIC);
+}
diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
new file mode 100644
index 000000000..ae05cc8e4
--- /dev/null
+++ b/security/selinux/ss/ebitmap.h
@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * An extensible bitmap is a bitmap that supports an
+ * arbitrary number of bits.  Extensible bitmaps are
+ * used to represent sets of values, such as types,
+ * roles, categories, and classes.
+ *
+ * Each extensible bitmap is implemented as a linked
+ * list of bitmap nodes, where each bitmap node has
+ * an explicitly specified starting bit position within
+ * the total bitmap.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_EBITMAP_H_
+#define _SS_EBITMAP_H_
+
+#include <net/netlabel.h>
+
+#ifdef CONFIG_64BIT
+#define EBITMAP_NODE_SIZE 64
+#else
+#define EBITMAP_NODE_SIZE 32
+#endif
+
+#define EBITMAP_UNIT_NUMS                                     \
+	((EBITMAP_NODE_SIZE - sizeof(void *) - sizeof(u32)) / \
+	 sizeof(unsigned long))
+#define EBITMAP_UNIT_SIZE BITS_PER_LONG
+#define EBITMAP_SIZE	  (EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE)
+#define EBITMAP_BIT	  1UL
+#define EBITMAP_SHIFT_UNIT_SIZE(x) \
+	(((x) >> EBITMAP_UNIT_SIZE / 2) >> EBITMAP_UNIT_SIZE / 2)
+
+struct ebitmap_node {
+	struct ebitmap_node *next;
+	unsigned long maps[EBITMAP_UNIT_NUMS];
+	u32 startbit;
+};
+
+struct ebitmap {
+	struct ebitmap_node *node; /* first node in the bitmap */
+	u32 highbit; /* highest position in the total bitmap */
+};
+
+#define ebitmap_length(e) ((e)->highbit)
+
+static inline u32 ebitmap_start_positive(const struct ebitmap *e,
+					 struct ebitmap_node **n)
+{
+	u32 ofs;
+
+	for (*n = e->node; *n; *n = (*n)->next) {
+		ofs = find_first_bit((*n)->maps, EBITMAP_SIZE);
+		if (ofs < EBITMAP_SIZE)
+			return (*n)->startbit + ofs;
+	}
+	return ebitmap_length(e);
+}
+
+static inline void ebitmap_init(struct ebitmap *e)
+{
+	memset(e, 0, sizeof(*e));
+}
+
+static inline u32 ebitmap_next_positive(const struct ebitmap *e,
+					struct ebitmap_node **n, u32 bit)
+{
+	u32 ofs;
+
+	ofs = find_next_bit((*n)->maps, EBITMAP_SIZE, bit - (*n)->startbit + 1);
+	if (ofs < EBITMAP_SIZE)
+		return ofs + (*n)->startbit;
+
+	for (*n = (*n)->next; *n; *n = (*n)->next) {
+		ofs = find_first_bit((*n)->maps, EBITMAP_SIZE);
+		if (ofs < EBITMAP_SIZE)
+			return ofs + (*n)->startbit;
+	}
+	return ebitmap_length(e);
+}
+
+#define EBITMAP_NODE_INDEX(node, bit) \
+	(((bit) - (node)->startbit) / EBITMAP_UNIT_SIZE)
+#define EBITMAP_NODE_OFFSET(node, bit) \
+	(((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE)
+
+static inline int ebitmap_node_get_bit(const struct ebitmap_node *n, u32 bit)
+{
+	u32 index = EBITMAP_NODE_INDEX(n, bit);
+	u32 ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	if ((n->maps[index] & (EBITMAP_BIT << ofs)))
+		return 1;
+	return 0;
+}
+
+static inline void ebitmap_node_set_bit(struct ebitmap_node *n, u32 bit)
+{
+	u32 index = EBITMAP_NODE_INDEX(n, bit);
+	u32 ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	n->maps[index] |= (EBITMAP_BIT << ofs);
+}
+
+static inline void ebitmap_node_clr_bit(struct ebitmap_node *n, u32 bit)
+{
+	u32 index = EBITMAP_NODE_INDEX(n, bit);
+	u32 ofs = EBITMAP_NODE_OFFSET(n, bit);
+
+	BUG_ON(index >= EBITMAP_UNIT_NUMS);
+	n->maps[index] &= ~(EBITMAP_BIT << ofs);
+}
+
+#define ebitmap_for_each_positive_bit(e, n, bit)      \
+	for ((bit) = ebitmap_start_positive(e, &(n)); \
+	     (bit) < ebitmap_length(e);               \
+	     (bit) = ebitmap_next_positive(e, &(n), bit))
+
+bool ebitmap_equal(const struct ebitmap *e1, const struct ebitmap *e2);
+int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src);
+int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1,
+		const struct ebitmap *e2);
+int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2,
+		     u32 last_e2bit);
+u32 ebitmap_get_highest_set_bit(const struct ebitmap *e);
+int ebitmap_get_bit(const struct ebitmap *e, u32 bit);
+int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value);
+void ebitmap_destroy(struct ebitmap *e);
+struct policy_file;
+int ebitmap_read(struct ebitmap *e, struct policy_file *fp);
+int ebitmap_write(const struct ebitmap *e, struct policy_file *fp);
+u32 ebitmap_hash(const struct ebitmap *e, u32 hash);
+
+#ifdef CONFIG_NETLABEL
+int ebitmap_netlbl_export(struct ebitmap *ebmap,
+			  struct netlbl_lsm_catmap **catmap);
+int ebitmap_netlbl_import(struct ebitmap *ebmap,
+			  struct netlbl_lsm_catmap *catmap);
+#else
+static inline int ebitmap_netlbl_export(struct ebitmap *ebmap,
+					struct netlbl_lsm_catmap **catmap)
+{
+	return -ENOMEM;
+}
+static inline int ebitmap_netlbl_import(struct ebitmap *ebmap,
+					struct netlbl_lsm_catmap *catmap)
+{
+	return -ENOMEM;
+}
+#endif
+
+#endif /* _SS_EBITMAP_H_ */
diff --git a/security/selinux/ss/hashtab.c b/security/selinux/ss/hashtab.c
new file mode 100644
index 000000000..9ffc8a371
--- /dev/null
+++ b/security/selinux/ss/hashtab.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the hash table type.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include "hashtab.h"
+#include "security.h"
+
+static struct kmem_cache *hashtab_node_cachep __ro_after_init;
+
+/*
+ * Here we simply round the number of elements up to the nearest power of two.
+ * I tried also other options like rounding down or rounding to the closest
+ * power of two (up or down based on which is closer), but I was unable to
+ * find any significant difference in lookup/insert performance that would
+ * justify switching to a different (less intuitive) formula. It could be that
+ * a different formula is actually more optimal, but any future changes here
+ * should be supported with performance/memory usage data.
+ *
+ * The total memory used by the htable arrays (only) with Fedora policy loaded
+ * is approximately 163 KB at the time of writing.
+ */
+static u32 hashtab_compute_size(u32 nel)
+{
+	return nel == 0 ? 0 : roundup_pow_of_two(nel);
+}
+
+int hashtab_init(struct hashtab *h, u32 nel_hint)
+{
+	u32 size = hashtab_compute_size(nel_hint);
+
+	/* should already be zeroed, but better be safe */
+	h->nel = 0;
+	h->size = 0;
+	h->htable = NULL;
+
+	if (size) {
+		h->htable = kzalloc_objs(*h->htable, size,
+					 GFP_KERNEL | __GFP_NOWARN);
+		if (!h->htable)
+			return -ENOMEM;
+		h->size = size;
+	}
+	return 0;
+}
+
+int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key,
+		     void *datum)
+{
+	struct hashtab_node *newnode;
+
+	newnode = kmem_cache_zalloc(hashtab_node_cachep, GFP_KERNEL);
+	if (!newnode)
+		return -ENOMEM;
+	newnode->key = key;
+	newnode->datum = datum;
+	newnode->next = *dst;
+	*dst = newnode;
+
+	h->nel++;
+	return 0;
+}
+
+void hashtab_destroy(struct hashtab *h)
+{
+	u32 i;
+	struct hashtab_node *cur, *temp;
+
+	for (i = 0; i < h->size; i++) {
+		cur = h->htable[i];
+		while (cur) {
+			temp = cur;
+			cur = cur->next;
+			kmem_cache_free(hashtab_node_cachep, temp);
+		}
+		h->htable[i] = NULL;
+	}
+
+	kfree(h->htable);
+	h->htable = NULL;
+}
+
+int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args),
+		void *args)
+{
+	u32 i;
+	int ret;
+	struct hashtab_node *cur;
+
+	for (i = 0; i < h->size; i++) {
+		cur = h->htable[i];
+		while (cur) {
+			ret = apply(cur->key, cur->datum, args);
+			if (ret)
+				return ret;
+			cur = cur->next;
+		}
+	}
+	return 0;
+}
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+void hashtab_stat(struct hashtab *h, struct hashtab_info *info)
+{
+	u32 i, chain_len, slots_used, max_chain_len;
+	u64 chain2_len_sum;
+	struct hashtab_node *cur;
+
+	slots_used = 0;
+	max_chain_len = 0;
+	chain2_len_sum = 0;
+	for (i = 0; i < h->size; i++) {
+		cur = h->htable[i];
+		if (cur) {
+			slots_used++;
+			chain_len = 0;
+			while (cur) {
+				chain_len++;
+				cur = cur->next;
+			}
+
+			if (chain_len > max_chain_len)
+				max_chain_len = chain_len;
+
+			chain2_len_sum += (u64)chain_len * chain_len;
+		}
+	}
+
+	info->slots_used = slots_used;
+	info->max_chain_len = max_chain_len;
+	info->chain2_len_sum = chain2_len_sum;
+}
+#endif /* CONFIG_SECURITY_SELINUX_DEBUG */
+
+int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig,
+		      int (*copy)(struct hashtab_node *new,
+				  const struct hashtab_node *orig, void *args),
+		      int (*destroy)(void *k, void *d, void *args), void *args)
+{
+	const struct hashtab_node *orig_cur;
+	struct hashtab_node *cur, *tmp, *tail;
+	u32 i;
+	int rc;
+
+	memset(new, 0, sizeof(*new));
+
+	new->htable = kzalloc_objs(*new->htable, orig->size);
+	if (!new->htable)
+		return -ENOMEM;
+
+	new->size = orig->size;
+
+	for (i = 0; i < orig->size; i++) {
+		tail = NULL;
+		for (orig_cur = orig->htable[i]; orig_cur;
+		     orig_cur = orig_cur->next) {
+			tmp = kmem_cache_zalloc(hashtab_node_cachep,
+						GFP_KERNEL);
+			if (!tmp)
+				goto error;
+			rc = copy(tmp, orig_cur, args);
+			if (rc) {
+				kmem_cache_free(hashtab_node_cachep, tmp);
+				goto error;
+			}
+			tmp->next = NULL;
+			if (!tail)
+				new->htable[i] = tmp;
+			else
+				tail->next = tmp;
+			tail = tmp;
+			new->nel++;
+		}
+	}
+
+	return 0;
+
+error:
+	for (i = 0; i < new->size; i++) {
+		for (cur = new->htable[i]; cur; cur = tmp) {
+			tmp = cur->next;
+			destroy(cur->key, cur->datum, args);
+			kmem_cache_free(hashtab_node_cachep, cur);
+		}
+	}
+	kfree(new->htable);
+	memset(new, 0, sizeof(*new));
+	return -ENOMEM;
+}
+
+void __init hashtab_cache_init(void)
+{
+	hashtab_node_cachep = KMEM_CACHE(hashtab_node, SLAB_PANIC);
+}
diff --git a/security/selinux/ss/hashtab.h b/security/selinux/ss/hashtab.h
new file mode 100644
index 000000000..c641fb129
--- /dev/null
+++ b/security/selinux/ss/hashtab.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A hash table (hashtab) maintains associations between
+ * key values and datum values.  The type of the key values
+ * and the type of the datum values is arbitrary.  The
+ * functions for hash computation and key comparison are
+ * provided by the creator of the table.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_HASHTAB_H_
+#define _SS_HASHTAB_H_
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+
+#define HASHTAB_MAX_NODES U32_MAX
+
+struct hashtab_key_params {
+	u32 (*hash)(const void *key); /* hash func */
+	int (*cmp)(const void *key1, const void *key2); /* comparison func */
+};
+
+struct hashtab_node {
+	void *key;
+	void *datum;
+	struct hashtab_node *next;
+};
+
+struct hashtab {
+	struct hashtab_node **htable; /* hash table */
+	u32 size; /* number of slots in hash table */
+	u32 nel; /* number of elements in hash table */
+};
+
+struct hashtab_info {
+	u32 slots_used;
+	u32 max_chain_len;
+	u64 chain2_len_sum;
+};
+
+/*
+ * Initializes a new hash table with the specified characteristics.
+ *
+ * Returns -ENOMEM if insufficient space is available or 0 otherwise.
+ */
+int hashtab_init(struct hashtab *h, u32 nel_hint);
+
+int __hashtab_insert(struct hashtab *h, struct hashtab_node **dst, void *key,
+		     void *datum);
+
+/*
+ * Inserts the specified (key, datum) pair into the specified hash table.
+ *
+ * Returns -ENOMEM on memory allocation error,
+ * -EEXIST if there is already an entry with the same key,
+ * -EINVAL for general errors or
+  0 otherwise.
+ */
+static inline int hashtab_insert(struct hashtab *h, void *key, void *datum,
+				 struct hashtab_key_params key_params)
+{
+	u32 hvalue;
+	struct hashtab_node *prev, *cur;
+
+	cond_resched();
+
+	if (!h->size || h->nel == HASHTAB_MAX_NODES)
+		return -EINVAL;
+
+	hvalue = key_params.hash(key) & (h->size - 1);
+	prev = NULL;
+	cur = h->htable[hvalue];
+	while (cur) {
+		int cmp = key_params.cmp(key, cur->key);
+
+		if (cmp == 0)
+			return -EEXIST;
+		if (cmp < 0)
+			break;
+		prev = cur;
+		cur = cur->next;
+	}
+
+	return __hashtab_insert(h, prev ? &prev->next : &h->htable[hvalue], key,
+				datum);
+}
+
+/*
+ * Searches for the entry with the specified key in the hash table.
+ *
+ * Returns NULL if no entry has the specified key or
+ * the datum of the entry otherwise.
+ */
+static inline void *hashtab_search(const struct hashtab *h, const void *key,
+				   struct hashtab_key_params key_params)
+{
+	u32 hvalue;
+	const struct hashtab_node *cur;
+
+	if (!h->size)
+		return NULL;
+
+	hvalue = key_params.hash(key) & (h->size - 1);
+	cur = h->htable[hvalue];
+	while (cur) {
+		int cmp = key_params.cmp(key, cur->key);
+
+		if (cmp == 0)
+			return cur->datum;
+		if (cmp < 0)
+			break;
+		cur = cur->next;
+	}
+	return NULL;
+}
+
+/*
+ * Destroys the specified hash table.
+ */
+void hashtab_destroy(struct hashtab *h);
+
+/*
+ * Applies the specified apply function to (key,datum,args)
+ * for each entry in the specified hash table.
+ *
+ * The order in which the function is applied to the entries
+ * is dependent upon the internal structure of the hash table.
+ *
+ * If apply returns a non-zero status, then hashtab_map will cease
+ * iterating through the hash table and will propagate the error
+ * return to its caller.
+ */
+int hashtab_map(struct hashtab *h, int (*apply)(void *k, void *d, void *args),
+		void *args);
+
+int hashtab_duplicate(struct hashtab *new, const struct hashtab *orig,
+		      int (*copy)(struct hashtab_node *new,
+				  const struct hashtab_node *orig, void *args),
+		      int (*destroy)(void *k, void *d, void *args), void *args);
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+/* Fill info with some hash table statistics */
+void hashtab_stat(struct hashtab *h, struct hashtab_info *info);
+#else
+static inline void hashtab_stat(struct hashtab *h, struct hashtab_info *info)
+{
+	return;
+}
+#endif
+
+#endif /* _SS_HASHTAB_H */
diff --git a/security/selinux/ss/mls.c b/security/selinux/ss/mls.c
new file mode 100644
index 000000000..40c626006
--- /dev/null
+++ b/security/selinux/ss/mls.c
@@ -0,0 +1,653 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the multi-level security (MLS) policy.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/*
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *          Support for enhanced MLS infrastructure.
+ *          Copyright (C) 2004-2006 Trusted Computer Solutions, Inc.
+ *
+ * Updated: Hewlett-Packard <paul@paul-moore.com>
+ *          Added support to import/export the MLS label from NetLabel
+ *          Copyright (C) Hewlett-Packard Development Company, L.P., 2006
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <net/netlabel.h>
+#include "sidtab.h"
+#include "mls.h"
+#include "policydb.h"
+#include "services.h"
+
+/*
+ * Return the length in bytes for the MLS fields of the
+ * security context string representation of `context'.
+ */
+int mls_compute_context_len(struct policydb *p, struct context *context)
+{
+	int i, l, len, head, prev;
+	const char *nm;
+	struct ebitmap *e;
+	struct ebitmap_node *node;
+
+	if (!p->mls_enabled)
+		return 0;
+
+	len = 1; /* for the beginning ":" */
+	for (l = 0; l < 2; l++) {
+		u32 index_sens = context->range.level[l].sens;
+		len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1));
+
+		/* categories */
+		head = -2;
+		prev = -2;
+		e = &context->range.level[l].cat;
+		ebitmap_for_each_positive_bit(e, node, i)
+		{
+			if (i - prev > 1) {
+				/* one or more negative bits are skipped */
+				if (head != prev) {
+					nm = sym_name(p, SYM_CATS, prev);
+					len += strlen(nm) + 1;
+				}
+				nm = sym_name(p, SYM_CATS, i);
+				len += strlen(nm) + 1;
+				head = i;
+			}
+			prev = i;
+		}
+		if (prev != head) {
+			nm = sym_name(p, SYM_CATS, prev);
+			len += strlen(nm) + 1;
+		}
+		if (l == 0) {
+			if (mls_level_eq(&context->range.level[0],
+					 &context->range.level[1]))
+				break;
+			else
+				len++;
+		}
+	}
+
+	return len;
+}
+
+/*
+ * Write the security context string representation of
+ * the MLS fields of `context' into the string `*scontext'.
+ * Update `*scontext' to point to the end of the MLS fields.
+ */
+void mls_sid_to_context(struct policydb *p, struct context *context,
+			char **scontext)
+{
+	const char *nm;
+	char *scontextp;
+	int i, l, head, prev;
+	struct ebitmap *e;
+	struct ebitmap_node *node;
+
+	if (!p->mls_enabled)
+		return;
+
+	scontextp = *scontext;
+
+	*scontextp = ':';
+	scontextp++;
+
+	for (l = 0; l < 2; l++) {
+		strcpy(scontextp, sym_name(p, SYM_LEVELS,
+					   context->range.level[l].sens - 1));
+		scontextp += strlen(scontextp);
+
+		/* categories */
+		head = -2;
+		prev = -2;
+		e = &context->range.level[l].cat;
+		ebitmap_for_each_positive_bit(e, node, i)
+		{
+			if (i - prev > 1) {
+				/* one or more negative bits are skipped */
+				if (prev != head) {
+					if (prev - head > 1)
+						*scontextp++ = '.';
+					else
+						*scontextp++ = ',';
+					nm = sym_name(p, SYM_CATS, prev);
+					strcpy(scontextp, nm);
+					scontextp += strlen(nm);
+				}
+				if (prev < 0)
+					*scontextp++ = ':';
+				else
+					*scontextp++ = ',';
+				nm = sym_name(p, SYM_CATS, i);
+				strcpy(scontextp, nm);
+				scontextp += strlen(nm);
+				head = i;
+			}
+			prev = i;
+		}
+
+		if (prev != head) {
+			if (prev - head > 1)
+				*scontextp++ = '.';
+			else
+				*scontextp++ = ',';
+			nm = sym_name(p, SYM_CATS, prev);
+			strcpy(scontextp, nm);
+			scontextp += strlen(nm);
+		}
+
+		if (l == 0) {
+			if (mls_level_eq(&context->range.level[0],
+					 &context->range.level[1]))
+				break;
+			else
+				*scontextp++ = '-';
+		}
+	}
+
+	*scontext = scontextp;
+}
+
+bool mls_level_isvalid(const struct policydb *p, const struct mls_level *l)
+{
+	const char *name;
+	const struct level_datum *levdatum;
+
+	if (!l->sens || l->sens > p->p_levels.nprim)
+		return false;
+
+	name = sym_name(p, SYM_LEVELS, l->sens - 1);
+	if (!name)
+		return false;
+
+	levdatum = symtab_search(&p->p_levels, name);
+	if (!levdatum)
+		return false;
+
+	/*
+	 * l is valid iff every bit in l->cat is set in levdatum->level.cat
+	 * and no bit in l->cat is larger than p->p_cats.nprim.
+	 * policydb_index() has already verified that every bit set in
+	 * levdatum->level.cat names a defined category, so containment is
+	 * sufficient here.
+	 */
+	return ebitmap_contains(&levdatum->level.cat, &l->cat,
+				p->p_cats.nprim);
+}
+
+bool mls_range_isvalid(const struct policydb *p, const struct mls_range *r)
+{
+	return (mls_level_isvalid(p, &r->level[0]) &&
+		mls_level_isvalid(p, &r->level[1]) &&
+		mls_level_dom(&r->level[1], &r->level[0]));
+}
+
+/*
+ * Return true if the MLS fields in the security context
+ * structure `c' are valid.  Return 0 otherwise.
+ */
+bool mls_context_isvalid(const struct policydb *p, const struct context *c)
+{
+	const struct user_datum *usrdatum;
+
+	if (!p->mls_enabled)
+		return true;
+
+	if (!mls_range_isvalid(p, &c->range))
+		return false;
+
+	if (c->role == OBJECT_R_VAL)
+		return true;
+
+	/*
+	 * User must be authorized for the MLS range.
+	 */
+	if (!c->user || c->user > p->p_users.nprim)
+		return false;
+	usrdatum = p->user_val_to_struct[c->user - 1];
+	if (!usrdatum || !mls_range_contains(usrdatum->range, c->range))
+		return false; /* user may not be associated with range */
+
+	return true;
+}
+
+/*
+ * Set the MLS fields in the security context structure
+ * `context' based on the string representation in
+ * the string `scontext'.
+ *
+ * This function modifies the string in place, inserting
+ * NULL characters to terminate the MLS fields.
+ *
+ * If a def_sid is provided and no MLS field is present,
+ * copy the MLS field of the associated default context.
+ * Used for upgraded to MLS systems where objects may lack
+ * MLS fields.
+ *
+ * Policy read-lock must be held for sidtab lookup.
+ *
+ */
+int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext,
+		       struct context *context, struct sidtab *s, u32 def_sid)
+{
+	char *sensitivity, *cur_cat, *next_cat, *rngptr;
+	struct level_datum *levdatum;
+	struct cat_datum *catdatum, *rngdatum;
+	u32 i;
+	int l, rc;
+	char *rangep[2];
+
+	if (!pol->mls_enabled) {
+		/*
+		 * With no MLS, only return -EINVAL if there is a MLS field
+		 * and it did not come from an xattr.
+		 */
+		if (oldc && def_sid == SECSID_NULL)
+			return -EINVAL;
+		return 0;
+	}
+
+	/*
+	 * No MLS component to the security context, try and map to
+	 * default if provided.
+	 */
+	if (!oldc) {
+		struct context *defcon;
+
+		if (def_sid == SECSID_NULL)
+			return -EINVAL;
+
+		defcon = sidtab_search(s, def_sid);
+		if (!defcon)
+			return -EINVAL;
+
+		return mls_context_cpy(context, defcon);
+	}
+
+	/*
+	 * If we're dealing with a range, figure out where the two parts
+	 * of the range begin.
+	 */
+	rangep[0] = scontext;
+	rangep[1] = strchr(scontext, '-');
+	if (rangep[1]) {
+		rangep[1][0] = '\0';
+		rangep[1]++;
+	}
+
+	/* For each part of the range: */
+	for (l = 0; l < 2; l++) {
+		/* Split sensitivity and category set. */
+		sensitivity = rangep[l];
+		if (sensitivity == NULL)
+			break;
+		next_cat = strchr(sensitivity, ':');
+		if (next_cat)
+			*(next_cat++) = '\0';
+
+		/* Parse sensitivity. */
+		levdatum = symtab_search(&pol->p_levels, sensitivity);
+		if (!levdatum)
+			return -EINVAL;
+		context->range.level[l].sens = levdatum->level.sens;
+
+		/* Extract category set. */
+		while (next_cat != NULL) {
+			cur_cat = next_cat;
+			next_cat = strchr(next_cat, ',');
+			if (next_cat != NULL)
+				*(next_cat++) = '\0';
+
+			/* Separate into range if exists */
+			rngptr = strchr(cur_cat, '.');
+			if (rngptr != NULL) {
+				/* Remove '.' */
+				*rngptr++ = '\0';
+			}
+
+			catdatum = symtab_search(&pol->p_cats, cur_cat);
+			if (!catdatum)
+				return -EINVAL;
+
+			rc = ebitmap_set_bit(&context->range.level[l].cat,
+					     catdatum->value - 1, 1);
+			if (rc)
+				return rc;
+
+			/* If range, set all categories in range */
+			if (rngptr == NULL)
+				continue;
+
+			rngdatum = symtab_search(&pol->p_cats, rngptr);
+			if (!rngdatum)
+				return -EINVAL;
+
+			if (catdatum->value >= rngdatum->value)
+				return -EINVAL;
+
+			for (i = catdatum->value; i < rngdatum->value; i++) {
+				rc = ebitmap_set_bit(
+					&context->range.level[l].cat, i, 1);
+				if (rc)
+					return rc;
+			}
+		}
+	}
+
+	/* If we didn't see a '-', the range start is also the range end. */
+	if (rangep[1] == NULL) {
+		context->range.level[1].sens = context->range.level[0].sens;
+		rc = ebitmap_cpy(&context->range.level[1].cat,
+				 &context->range.level[0].cat);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+/*
+ * Set the MLS fields in the security context structure
+ * `context' based on the string representation in
+ * the string `str'.  This function will allocate temporary memory with the
+ * given constraints of gfp_mask.
+ */
+int mls_from_string(struct policydb *p, char *str, struct context *context,
+		    gfp_t gfp_mask)
+{
+	char *tmpstr;
+	int rc;
+
+	if (!p->mls_enabled)
+		return -EINVAL;
+
+	tmpstr = kstrdup(str, gfp_mask);
+	if (!tmpstr) {
+		rc = -ENOMEM;
+	} else {
+		rc = mls_context_to_sid(p, ':', tmpstr, context, NULL,
+					SECSID_NULL);
+		kfree(tmpstr);
+	}
+
+	return rc;
+}
+
+/*
+ * Copies the MLS range `range' into `context'.
+ */
+int mls_range_set(struct context *context, struct mls_range *range)
+{
+	int l, rc = 0;
+
+	/* Copy the MLS range into the  context */
+	for (l = 0; l < 2; l++) {
+		context->range.level[l].sens = range->level[l].sens;
+		rc = ebitmap_cpy(&context->range.level[l].cat,
+				 &range->level[l].cat);
+		if (rc)
+			break;
+	}
+
+	return rc;
+}
+
+int mls_setup_user_range(struct policydb *p, struct context *fromcon,
+			 struct user_datum *user, struct context *usercon)
+{
+	if (p->mls_enabled) {
+		struct mls_level *fromcon_sen = &(fromcon->range.level[0]);
+		struct mls_level *fromcon_clr = &(fromcon->range.level[1]);
+		struct mls_level *user_low = &(user->range.level[0]);
+		struct mls_level *user_clr = &(user->range.level[1]);
+		struct mls_level *user_def = &(user->dfltlevel);
+		struct mls_level *usercon_sen = &(usercon->range.level[0]);
+		struct mls_level *usercon_clr = &(usercon->range.level[1]);
+
+		/* Honor the user's default level if we can */
+		if (mls_level_between(user_def, fromcon_sen, fromcon_clr))
+			*usercon_sen = *user_def;
+		else if (mls_level_between(fromcon_sen, user_def, user_clr))
+			*usercon_sen = *fromcon_sen;
+		else if (mls_level_between(fromcon_clr, user_low, user_def))
+			*usercon_sen = *user_low;
+		else
+			return -EINVAL;
+
+		/* Lower the clearance of available contexts
+		   if the clearance of "fromcon" is lower than
+		   that of the user's default clearance (but
+		   only if the "fromcon" clearance dominates
+		   the user's computed sensitivity level) */
+		if (mls_level_dom(user_clr, fromcon_clr))
+			*usercon_clr = *fromcon_clr;
+		else if (mls_level_dom(fromcon_clr, user_clr))
+			*usercon_clr = *user_clr;
+		else
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Convert the MLS fields in the security context
+ * structure `oldc' from the values specified in the
+ * policy `oldp' to the values specified in the policy `newp',
+ * storing the resulting context in `newc'.
+ */
+int mls_convert_context(struct policydb *oldp, struct policydb *newp,
+			struct context *oldc, struct context *newc)
+{
+	struct level_datum *levdatum;
+	struct cat_datum *catdatum;
+	struct ebitmap_node *node;
+	u32 i;
+	int l;
+
+	if (!oldp->mls_enabled || !newp->mls_enabled)
+		return 0;
+
+	for (l = 0; l < 2; l++) {
+		const char *name = sym_name(oldp, SYM_LEVELS,
+					    oldc->range.level[l].sens - 1);
+
+		levdatum = symtab_search(&newp->p_levels, name);
+
+		if (!levdatum)
+			return -EINVAL;
+		newc->range.level[l].sens = levdatum->level.sens;
+
+		ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node,
+					      i)
+		{
+			int rc;
+
+			catdatum = symtab_search(&newp->p_cats,
+						 sym_name(oldp, SYM_CATS, i));
+			if (!catdatum)
+				return -EINVAL;
+			rc = ebitmap_set_bit(&newc->range.level[l].cat,
+					     catdatum->value - 1, 1);
+			if (rc)
+				return rc;
+		}
+	}
+
+	return 0;
+}
+
+int mls_compute_sid(struct policydb *p, struct context *scontext,
+		    struct context *tcontext, u16 tclass, u32 specified,
+		    struct context *newcontext, bool sock)
+{
+	struct range_trans rtr;
+	struct mls_range *r;
+	struct class_datum *cladatum;
+	char default_range = 0;
+
+	if (!p->mls_enabled)
+		return 0;
+
+	switch (specified) {
+	case AVTAB_TRANSITION:
+		/* Look for a range transition rule. */
+		rtr.source_type = scontext->type;
+		rtr.target_type = tcontext->type;
+		rtr.target_class = tclass;
+		r = policydb_rangetr_search(p, &rtr);
+		if (r)
+			return mls_range_set(newcontext, r);
+
+		if (tclass && tclass <= p->p_classes.nprim) {
+			cladatum = p->class_val_to_struct[tclass - 1];
+			if (cladatum)
+				default_range = cladatum->default_range;
+		}
+
+		switch (default_range) {
+		case DEFAULT_SOURCE_LOW:
+			return mls_context_cpy_low(newcontext, scontext);
+		case DEFAULT_SOURCE_HIGH:
+			return mls_context_cpy_high(newcontext, scontext);
+		case DEFAULT_SOURCE_LOW_HIGH:
+			return mls_context_cpy(newcontext, scontext);
+		case DEFAULT_TARGET_LOW:
+			return mls_context_cpy_low(newcontext, tcontext);
+		case DEFAULT_TARGET_HIGH:
+			return mls_context_cpy_high(newcontext, tcontext);
+		case DEFAULT_TARGET_LOW_HIGH:
+			return mls_context_cpy(newcontext, tcontext);
+		case DEFAULT_GLBLUB:
+			return mls_context_glblub(newcontext, scontext,
+						  tcontext);
+		}
+
+		fallthrough;
+	case AVTAB_CHANGE:
+		if ((tclass == p->process_class) || sock)
+			/* Use the process MLS attributes. */
+			return mls_context_cpy(newcontext, scontext);
+		else
+			/* Use the process effective MLS attributes. */
+			return mls_context_cpy_low(newcontext, scontext);
+	case AVTAB_MEMBER:
+		/* Use the process effective MLS attributes. */
+		return mls_context_cpy_low(newcontext, scontext);
+	}
+	return -EINVAL;
+}
+
+#ifdef CONFIG_NETLABEL
+/**
+ * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel
+ * @p: the policy
+ * @context: the security context
+ * @secattr: the NetLabel security attributes
+ *
+ * Description:
+ * Given the security context copy the low MLS sensitivity level into the
+ * NetLabel MLS sensitivity level field.
+ *
+ */
+void mls_export_netlbl_lvl(struct policydb *p, struct context *context,
+			   struct netlbl_lsm_secattr *secattr)
+{
+	if (!p->mls_enabled)
+		return;
+
+	secattr->attr.mls.lvl = context->range.level[0].sens - 1;
+	secattr->flags |= NETLBL_SECATTR_MLS_LVL;
+}
+
+/**
+ * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels
+ * @p: the policy
+ * @context: the security context
+ * @secattr: the NetLabel security attributes
+ *
+ * Description:
+ * Given the security context and the NetLabel security attributes, copy the
+ * NetLabel MLS sensitivity level into the context.
+ *
+ */
+void mls_import_netlbl_lvl(struct policydb *p, struct context *context,
+			   struct netlbl_lsm_secattr *secattr)
+{
+	if (!p->mls_enabled)
+		return;
+
+	context->range.level[0].sens = secattr->attr.mls.lvl + 1;
+	context->range.level[1].sens = context->range.level[0].sens;
+}
+
+/**
+ * mls_export_netlbl_cat - Export the MLS categories to NetLabel
+ * @p: the policy
+ * @context: the security context
+ * @secattr: the NetLabel security attributes
+ *
+ * Description:
+ * Given the security context copy the low MLS categories into the NetLabel
+ * MLS category field.  Returns zero on success, negative values on failure.
+ *
+ */
+int mls_export_netlbl_cat(struct policydb *p, struct context *context,
+			  struct netlbl_lsm_secattr *secattr)
+{
+	int rc;
+
+	if (!p->mls_enabled)
+		return 0;
+
+	rc = ebitmap_netlbl_export(&context->range.level[0].cat,
+				   &secattr->attr.mls.cat);
+	if (rc == 0 && secattr->attr.mls.cat != NULL)
+		secattr->flags |= NETLBL_SECATTR_MLS_CAT;
+
+	return rc;
+}
+
+/**
+ * mls_import_netlbl_cat - Import the MLS categories from NetLabel
+ * @p: the policy
+ * @context: the security context
+ * @secattr: the NetLabel security attributes
+ *
+ * Description:
+ * Copy the NetLabel security attributes into the SELinux context; since the
+ * NetLabel security attribute only contains a single MLS category use it for
+ * both the low and high categories of the context.  Returns zero on success,
+ * negative values on failure.
+ *
+ */
+int mls_import_netlbl_cat(struct policydb *p, struct context *context,
+			  struct netlbl_lsm_secattr *secattr)
+{
+	int rc;
+
+	if (!p->mls_enabled)
+		return 0;
+
+	rc = ebitmap_netlbl_import(&context->range.level[0].cat,
+				   secattr->attr.mls.cat);
+	if (rc)
+		goto import_netlbl_cat_failure;
+	memcpy(&context->range.level[1].cat, &context->range.level[0].cat,
+	       sizeof(context->range.level[0].cat));
+
+	return 0;
+
+import_netlbl_cat_failure:
+	ebitmap_destroy(&context->range.level[0].cat);
+	return rc;
+}
+#endif /* CONFIG_NETLABEL */
diff --git a/security/selinux/ss/mls.h b/security/selinux/ss/mls.h
new file mode 100644
index 000000000..93cde1b22
--- /dev/null
+++ b/security/selinux/ss/mls.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Multi-level security (MLS) policy operations.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/*
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *          Support for enhanced MLS infrastructure.
+ *          Copyright (C) 2004-2006 Trusted Computer Solutions, Inc.
+ *
+ * Updated: Hewlett-Packard <paul@paul-moore.com>
+ *          Added support to import/export the MLS label from NetLabel
+ *          Copyright (X) Hewlett-Packard Development Company, L.P., 2006
+ */
+
+#ifndef _SS_MLS_H_
+#define _SS_MLS_H_
+
+#include <linux/jhash.h>
+
+#include "context.h"
+#include "ebitmap.h"
+#include "policydb.h"
+
+int mls_compute_context_len(struct policydb *p, struct context *context);
+void mls_sid_to_context(struct policydb *p, struct context *context,
+			char **scontext);
+bool mls_context_isvalid(const struct policydb *p, const struct context *c);
+bool mls_range_isvalid(const struct policydb *p, const struct mls_range *r);
+bool mls_level_isvalid(const struct policydb *p, const struct mls_level *l);
+
+int mls_context_to_sid(struct policydb *p, char oldc, char *scontext,
+		       struct context *context, struct sidtab *s, u32 def_sid);
+
+int mls_from_string(struct policydb *p, char *str, struct context *context,
+		    gfp_t gfp_mask);
+
+int mls_range_set(struct context *context, struct mls_range *range);
+
+int mls_convert_context(struct policydb *oldp, struct policydb *newp,
+			struct context *oldc, struct context *newc);
+
+int mls_compute_sid(struct policydb *p, struct context *scontext,
+		    struct context *tcontext, u16 tclass, u32 specified,
+		    struct context *newcontext, bool sock);
+
+int mls_setup_user_range(struct policydb *p, struct context *fromcon,
+			 struct user_datum *user, struct context *usercon);
+
+#ifdef CONFIG_NETLABEL
+void mls_export_netlbl_lvl(struct policydb *p, struct context *context,
+			   struct netlbl_lsm_secattr *secattr);
+void mls_import_netlbl_lvl(struct policydb *p, struct context *context,
+			   struct netlbl_lsm_secattr *secattr);
+int mls_export_netlbl_cat(struct policydb *p, struct context *context,
+			  struct netlbl_lsm_secattr *secattr);
+int mls_import_netlbl_cat(struct policydb *p, struct context *context,
+			  struct netlbl_lsm_secattr *secattr);
+#else
+static inline void mls_export_netlbl_lvl(struct policydb *p,
+					 struct context *context,
+					 struct netlbl_lsm_secattr *secattr)
+{
+	return;
+}
+static inline void mls_import_netlbl_lvl(struct policydb *p,
+					 struct context *context,
+					 struct netlbl_lsm_secattr *secattr)
+{
+	return;
+}
+static inline int mls_export_netlbl_cat(struct policydb *p,
+					struct context *context,
+					struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOMEM;
+}
+static inline int mls_import_netlbl_cat(struct policydb *p,
+					struct context *context,
+					struct netlbl_lsm_secattr *secattr)
+{
+	return -ENOMEM;
+}
+#endif
+
+static inline u32 mls_range_hash(const struct mls_range *r, u32 hash)
+{
+	hash = jhash_2words(r->level[0].sens, r->level[1].sens, hash);
+	hash = ebitmap_hash(&r->level[0].cat, hash);
+	hash = ebitmap_hash(&r->level[1].cat, hash);
+	return hash;
+}
+
+#endif /* _SS_MLS_H */
diff --git a/security/selinux/ss/mls_types.h b/security/selinux/ss/mls_types.h
new file mode 100644
index 000000000..51df2ebd1
--- /dev/null
+++ b/security/selinux/ss/mls_types.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Type definitions for the multi-level security (MLS) policy.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/*
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *          Support for enhanced MLS infrastructure.
+ *          Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
+ */
+
+#ifndef _SS_MLS_TYPES_H_
+#define _SS_MLS_TYPES_H_
+
+#include "security.h"
+#include "ebitmap.h"
+
+struct mls_level {
+	u32 sens; /* sensitivity */
+	struct ebitmap cat; /* category set */
+};
+
+struct mls_range {
+	struct mls_level level[2]; /* low == level[0], high == level[1] */
+};
+
+static inline int mls_level_eq(const struct mls_level *l1,
+			       const struct mls_level *l2)
+{
+	return ((l1->sens == l2->sens) && ebitmap_equal(&l1->cat, &l2->cat));
+}
+
+static inline int mls_level_dom(const struct mls_level *l1,
+				const struct mls_level *l2)
+{
+	return ((l1->sens >= l2->sens) &&
+		ebitmap_contains(&l1->cat, &l2->cat, 0));
+}
+
+#define mls_level_incomp(l1, l2) \
+	(!mls_level_dom((l1), (l2)) && !mls_level_dom((l2), (l1)))
+
+#define mls_level_between(l1, l2, l3) \
+	(mls_level_dom((l1), (l2)) && mls_level_dom((l3), (l1)))
+
+#define mls_range_contains(r1, r2)                        \
+	(mls_level_dom(&(r2).level[0], &(r1).level[0]) && \
+	 mls_level_dom(&(r1).level[1], &(r2).level[1]))
+
+#endif /* _SS_MLS_TYPES_H_ */
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
new file mode 100644
index 000000000..b75c977c6
--- /dev/null
+++ b/security/selinux/ss/policydb.c
@@ -0,0 +1,4155 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implementation of the policy database.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/*
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *          Support for enhanced MLS infrastructure.
+ *          Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
+ *
+ * Updated: Frank Mayer <mayerf@tresys.com> and
+ *          Karl MacMillan <kmacmillan@tresys.com>
+ *          Added conditional policy language extensions
+ *          Copyright (C) 2003-2004 Tresys Technology, LLC
+ *
+ * Updated: Hewlett-Packard <paul@paul-moore.com>
+ *          Added support for the policy capability bitmap
+ *          Copyright (C) 2007 Hewlett-Packard Development Company, L.P.
+ *
+ * Update: Mellanox Techonologies
+ *         Added Infiniband support
+ *         Copyright (C) 2016 Mellanox Techonologies
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/audit.h>
+#include <linux/sort.h>
+#include "security.h"
+
+#include "policydb.h"
+#include "conditional.h"
+#include "mls.h"
+#include "services.h"
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+/* clang-format off */
+static const char *const symtab_name[SYM_NUM] = {
+	"common prefixes",
+	"classes",
+	"roles",
+	"types",
+	"users",
+	"bools",
+	"levels",
+	"categories",
+};
+/* clang-format off */
+#endif
+
+struct policydb_compat_info {
+	unsigned int version;
+	unsigned int sym_num;
+	unsigned int ocon_num;
+};
+
+/* These need to be updated if SYM_NUM or OCON_NUM changes */
+static const struct policydb_compat_info policydb_compat[] = {
+	{
+		.version = POLICYDB_VERSION_BASE,
+		.sym_num = SYM_NUM - 3,
+		.ocon_num = OCON_NUM - 3,
+	},
+	{
+		.version = POLICYDB_VERSION_BOOL,
+		.sym_num = SYM_NUM - 2,
+		.ocon_num = OCON_NUM - 3,
+	},
+	{
+		.version = POLICYDB_VERSION_IPV6,
+		.sym_num = SYM_NUM - 2,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_NLCLASS,
+		.sym_num = SYM_NUM - 2,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_MLS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_AVTAB,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_RANGETRANS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_POLCAP,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_PERMISSIVE,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_BOUNDARY,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_FILENAME_TRANS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_ROLETRANS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_NEW_OBJECT_DEFAULTS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_DEFAULT_TYPE,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_CONSTRAINT_NAMES,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_XPERMS_IOCTL,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM - 2,
+	},
+	{
+		.version = POLICYDB_VERSION_INFINIBAND,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM,
+	},
+	{
+		.version = POLICYDB_VERSION_GLBLUB,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM,
+	},
+	{
+		.version = POLICYDB_VERSION_COMP_FTRANS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM,
+	},
+	{
+		.version = POLICYDB_VERSION_COND_XPERMS,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM,
+	},
+	{
+		.version = POLICYDB_VERSION_NEVERAUDIT,
+		.sym_num = SYM_NUM,
+		.ocon_num = OCON_NUM,
+	},
+};
+
+static const struct policydb_compat_info *
+policydb_lookup_compat(unsigned int version)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(policydb_compat); i++) {
+		if (policydb_compat[i].version == version)
+			return &policydb_compat[i];
+	}
+
+	return NULL;
+}
+
+/*
+ * The following *_destroy functions are used to
+ * free any memory allocated for each kind of
+ * symbol data in the policy database.
+ */
+
+static int perm_destroy(void *key, void *datum, void *p)
+{
+	kfree(key);
+	kfree(datum);
+	return 0;
+}
+
+static int common_destroy(void *key, void *datum, void *p)
+{
+	struct common_datum *comdatum;
+
+	kfree(key);
+	if (datum) {
+		comdatum = datum;
+		hashtab_map(&comdatum->permissions.table, perm_destroy, NULL);
+		hashtab_destroy(&comdatum->permissions.table);
+	}
+	kfree(datum);
+	return 0;
+}
+
+static void constraint_expr_destroy(struct constraint_expr *expr)
+{
+	if (expr) {
+		ebitmap_destroy(&expr->names);
+		if (expr->type_names) {
+			ebitmap_destroy(&expr->type_names->types);
+			ebitmap_destroy(&expr->type_names->negset);
+			kfree(expr->type_names);
+		}
+		kfree(expr);
+	}
+}
+
+static int cls_destroy(void *key, void *datum, void *p)
+{
+	struct class_datum *cladatum;
+	struct constraint_node *constraint, *ctemp;
+	struct constraint_expr *e, *etmp;
+
+	kfree(key);
+	if (datum) {
+		cladatum = datum;
+		hashtab_map(&cladatum->permissions.table, perm_destroy, NULL);
+		hashtab_destroy(&cladatum->permissions.table);
+		constraint = cladatum->constraints;
+		while (constraint) {
+			e = constraint->expr;
+			while (e) {
+				etmp = e;
+				e = e->next;
+				constraint_expr_destroy(etmp);
+			}
+			ctemp = constraint;
+			constraint = constraint->next;
+			kfree(ctemp);
+		}
+
+		constraint = cladatum->validatetrans;
+		while (constraint) {
+			e = constraint->expr;
+			while (e) {
+				etmp = e;
+				e = e->next;
+				constraint_expr_destroy(etmp);
+			}
+			ctemp = constraint;
+			constraint = constraint->next;
+			kfree(ctemp);
+		}
+		kfree(cladatum->comkey);
+	}
+	kfree(datum);
+	return 0;
+}
+
+static int role_destroy(void *key, void *datum, void *p)
+{
+	struct role_datum *role;
+
+	kfree(key);
+	if (datum) {
+		role = datum;
+		ebitmap_destroy(&role->dominates);
+		ebitmap_destroy(&role->types);
+	}
+	kfree(datum);
+	return 0;
+}
+
+static int type_destroy(void *key, void *datum, void *p)
+{
+	kfree(key);
+	kfree(datum);
+	return 0;
+}
+
+static int user_destroy(void *key, void *datum, void *p)
+{
+	struct user_datum *usrdatum;
+
+	kfree(key);
+	if (datum) {
+		usrdatum = datum;
+		ebitmap_destroy(&usrdatum->roles);
+		ebitmap_destroy(&usrdatum->range.level[0].cat);
+		ebitmap_destroy(&usrdatum->range.level[1].cat);
+		ebitmap_destroy(&usrdatum->dfltlevel.cat);
+	}
+	kfree(datum);
+	return 0;
+}
+
+static int sens_destroy(void *key, void *datum, void *p)
+{
+	struct level_datum *levdatum;
+
+	kfree(key);
+	if (datum) {
+		levdatum = datum;
+		ebitmap_destroy(&levdatum->level.cat);
+	}
+	kfree(datum);
+	return 0;
+}
+
+static int cat_destroy(void *key, void *datum, void *p)
+{
+	kfree(key);
+	kfree(datum);
+	return 0;
+}
+
+/* clang-format off */
+static int (*const destroy_f[SYM_NUM])(void *key, void *datum, void *datap) = {
+	common_destroy,
+	cls_destroy,
+	role_destroy,
+	type_destroy,
+	user_destroy,
+	cond_destroy_bool,
+	sens_destroy,
+	cat_destroy,
+};
+/* clang-format on */
+
+static int filenametr_destroy(void *key, void *datum, void *p)
+{
+	struct filename_trans_key *ft = key;
+	struct filename_trans_datum *next, *d = datum;
+
+	kfree(ft->name);
+	kfree(key);
+	do {
+		ebitmap_destroy(&d->stypes);
+		next = d->next;
+		kfree(d);
+		d = next;
+	} while (unlikely(d));
+	cond_resched();
+	return 0;
+}
+
+static int range_tr_destroy(void *key, void *datum, void *p)
+{
+	struct mls_range *rt = datum;
+
+	kfree(key);
+	ebitmap_destroy(&rt->level[0].cat);
+	ebitmap_destroy(&rt->level[1].cat);
+	kfree(datum);
+	cond_resched();
+	return 0;
+}
+
+static int role_tr_destroy(void *key, void *datum, void *p)
+{
+	kfree(key);
+	kfree(datum);
+	return 0;
+}
+
+static void ocontext_destroy(struct ocontext *c, unsigned int i)
+{
+	if (!c)
+		return;
+
+	context_destroy(&c->context[0]);
+	context_destroy(&c->context[1]);
+	if (i == OCON_ISID || i == OCON_FS || i == OCON_NETIF ||
+	    i == OCON_FSUSE)
+		kfree(c->u.name);
+	kfree(c);
+}
+
+/*
+ * Initialize the role table.
+ */
+static int roles_init(struct policydb *p)
+{
+	char *key = NULL;
+	int rc;
+	struct role_datum *role;
+
+	role = kzalloc_obj(*role);
+	if (!role)
+		return -ENOMEM;
+
+	rc = -EINVAL;
+	role->value = ++p->p_roles.nprim;
+	if (role->value != OBJECT_R_VAL)
+		goto out;
+
+	rc = -ENOMEM;
+	key = kstrdup(OBJECT_R, GFP_KERNEL);
+	if (!key)
+		goto out;
+
+	rc = symtab_insert(&p->p_roles, key, role);
+	if (rc)
+		goto out;
+
+	return 0;
+out:
+	kfree(key);
+	kfree(role);
+	return rc;
+}
+
+static u32 filenametr_hash(const void *k)
+{
+	const struct filename_trans_key *ft = k;
+	unsigned long salt = ft->ttype ^ ft->tclass;
+
+	return full_name_hash((void *)salt, ft->name, strlen(ft->name));
+}
+
+static int filenametr_cmp(const void *k1, const void *k2)
+{
+	const struct filename_trans_key *ft1 = k1;
+	const struct filename_trans_key *ft2 = k2;
+	int v;
+
+	v = cmp_int(ft1->ttype, ft2->ttype);
+	if (v)
+		return v;
+
+	v = cmp_int(ft1->tclass, ft2->tclass);
+	if (v)
+		return v;
+
+	return strcmp(ft1->name, ft2->name);
+}
+
+static const struct hashtab_key_params filenametr_key_params = {
+	.hash = filenametr_hash,
+	.cmp = filenametr_cmp,
+};
+
+struct filename_trans_datum *
+policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key)
+{
+	return hashtab_search(&p->filename_trans, key, filenametr_key_params);
+}
+
+static u32 rangetr_hash(const void *k)
+{
+	const struct range_trans *key = k;
+
+	return key->source_type + (key->target_type << 3) +
+	       (key->target_class << 5);
+}
+
+static int rangetr_cmp(const void *k1, const void *k2)
+{
+	const struct range_trans *key1 = k1, *key2 = k2;
+	int v;
+
+	v = cmp_int(key1->source_type, key2->source_type);
+	if (v)
+		return v;
+
+	v = cmp_int(key1->target_type, key2->target_type);
+	if (v)
+		return v;
+
+	v = cmp_int(key1->target_class, key2->target_class);
+
+	return v;
+}
+
+static const struct hashtab_key_params rangetr_key_params = {
+	.hash = rangetr_hash,
+	.cmp = rangetr_cmp,
+};
+
+struct mls_range *policydb_rangetr_search(struct policydb *p,
+					  struct range_trans *key)
+{
+	return hashtab_search(&p->range_tr, key, rangetr_key_params);
+}
+
+static u32 role_trans_hash(const void *k)
+{
+	const struct role_trans_key *key = k;
+
+	return jhash_3words(key->role, key->type,
+			    (u32)key->tclass << 16 | key->tclass, 0);
+}
+
+static int role_trans_cmp(const void *k1, const void *k2)
+{
+	const struct role_trans_key *key1 = k1, *key2 = k2;
+	int v;
+
+	v = cmp_int(key1->role, key2->role);
+	if (v)
+		return v;
+
+	v = cmp_int(key1->type, key2->type);
+	if (v)
+		return v;
+
+	return cmp_int(key1->tclass, key2->tclass);
+}
+
+static const struct hashtab_key_params roletr_key_params = {
+	.hash = role_trans_hash,
+	.cmp = role_trans_cmp,
+};
+
+struct role_trans_datum *policydb_roletr_search(struct policydb *p,
+						struct role_trans_key *key)
+{
+	return hashtab_search(&p->role_tr, key, roletr_key_params);
+}
+
+/*
+ * Initialize a policy database structure.
+ */
+static void policydb_init(struct policydb *p)
+{
+	memset(p, 0, sizeof(*p));
+
+	avtab_init(&p->te_avtab);
+	cond_policydb_init(p);
+
+	ebitmap_init(&p->filename_trans_ttypes);
+	ebitmap_init(&p->policycaps);
+	ebitmap_init(&p->permissive_map);
+	ebitmap_init(&p->neveraudit_map);
+}
+
+/*
+ * The following *_index functions are used to
+ * define the val_to_name and val_to_struct arrays
+ * in a policy database structure.  The val_to_name
+ * arrays are used when converting security context
+ * structures into string representations.  The
+ * val_to_struct arrays are used when the attributes
+ * of a class, role, or user are needed.
+ */
+
+static int common_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct common_datum *comdatum;
+
+	comdatum = datum;
+	p = datap;
+	if (!comdatum->value || comdatum->value > p->p_commons.nprim)
+		return -EINVAL;
+
+	p->sym_val_to_name[SYM_COMMONS][comdatum->value - 1] = key;
+
+	return 0;
+}
+
+static int class_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct class_datum *cladatum;
+
+	cladatum = datum;
+	p = datap;
+	if (!cladatum->value || cladatum->value > p->p_classes.nprim)
+		return -EINVAL;
+
+	p->sym_val_to_name[SYM_CLASSES][cladatum->value - 1] = key;
+	p->class_val_to_struct[cladatum->value - 1] = cladatum;
+	return 0;
+}
+
+static int role_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct role_datum *role;
+
+	role = datum;
+	p = datap;
+	if (!role->value || role->value > p->p_roles.nprim ||
+	    role->bounds > p->p_roles.nprim)
+		return -EINVAL;
+
+	p->sym_val_to_name[SYM_ROLES][role->value - 1] = key;
+	p->role_val_to_struct[role->value - 1] = role;
+	return 0;
+}
+
+static int type_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct type_datum *typdatum;
+
+	typdatum = datum;
+	p = datap;
+
+	if (!typdatum->value || typdatum->value > p->p_types.nprim ||
+		typdatum->bounds > p->p_types.nprim) {
+		pr_err("SELinux: type %s had value %u bounds %u nprim %u\n",
+			(char *)key, typdatum->value, typdatum->bounds,
+			p->p_types.nprim);
+		return -EINVAL;
+	}
+
+	if (typdatum->primary) {
+		p->sym_val_to_name[SYM_TYPES][typdatum->value - 1] = key;
+		p->type_val_to_struct[typdatum->value - 1] = typdatum;
+	}
+
+	return 0;
+}
+
+static int user_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct user_datum *usrdatum;
+
+	usrdatum = datum;
+	p = datap;
+	if (!usrdatum->value || usrdatum->value > p->p_users.nprim ||
+	    usrdatum->bounds > p->p_users.nprim)
+		return -EINVAL;
+
+	p->sym_val_to_name[SYM_USERS][usrdatum->value - 1] = key;
+	p->user_val_to_struct[usrdatum->value - 1] = usrdatum;
+	return 0;
+}
+
+static int sens_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct level_datum *levdatum;
+
+	levdatum = datum;
+	p = datap;
+
+	if (!levdatum->level.sens || levdatum->level.sens > p->p_levels.nprim)
+		return -EINVAL;
+
+	if (!levdatum->isalias)
+		p->sym_val_to_name[SYM_LEVELS][levdatum->level.sens - 1] = key;
+
+	return 0;
+}
+
+static int cat_index(void *key, void *datum, void *datap)
+{
+	struct policydb *p;
+	struct cat_datum *catdatum;
+
+	catdatum = datum;
+	p = datap;
+
+	if (!catdatum->value || catdatum->value > p->p_cats.nprim)
+		return -EINVAL;
+
+	if (!catdatum->isalias)
+		p->sym_val_to_name[SYM_CATS][catdatum->value - 1] = key;
+
+	return 0;
+}
+
+static int sens_cat_index_check(void *key, void *datum, void *datap)
+{
+	struct policydb *p = datap;
+	struct level_datum *levdatum = datum;
+	struct ebitmap_node *node;
+	u32 bit;
+
+	ebitmap_for_each_positive_bit(&levdatum->level.cat, node, bit) {
+		if (bit >= p->p_cats.nprim || !sym_name(p, SYM_CATS, bit)) {
+			pr_err("SELinux: sensitivity %s allows undefined category %u\n",
+				(const char *)key, bit + 1);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+/* clang-format off */
+static int (*const index_f[SYM_NUM])(void *key, void *datum, void *datap) = {
+	common_index,
+	class_index,
+	role_index,
+	type_index,
+	user_index,
+	cond_index_bool,
+	sens_index,
+	cat_index,
+};
+/* clang-format on */
+
+#ifdef CONFIG_SECURITY_SELINUX_DEBUG
+static void hash_eval(struct hashtab *h, const char *hash_name,
+		      const char *hash_details)
+{
+	struct hashtab_info info;
+
+	hashtab_stat(h, &info);
+	pr_debug(
+		"SELinux: %s%s%s:  %d entries and %d/%d buckets used, longest chain length %d, sum of chain length^2 %llu\n",
+		hash_name, hash_details ? "@" : "", hash_details ?: "", h->nel,
+		info.slots_used, h->size, info.max_chain_len,
+		info.chain2_len_sum);
+}
+
+static void symtab_hash_eval(struct symtab *s)
+{
+	int i;
+
+	for (i = 0; i < SYM_NUM; i++)
+		hash_eval(&s[i].table, symtab_name[i], NULL);
+}
+
+#else
+static inline void hash_eval(struct hashtab *h, const char *hash_name,
+			     const char *hash_details)
+{
+}
+static inline void symtab_hash_eval(struct symtab *s)
+{
+}
+#endif /* CONFIG_SECURITY_SELINUX_DEBUG */
+
+/*
+ * Define the other val_to_name and val_to_struct arrays
+ * in a policy database structure.
+ *
+ * Caller must clean up on failure.
+ */
+static int policydb_index(struct policydb *p)
+{
+	int i, rc;
+	u32 v;
+
+	if (p->mls_enabled)
+		pr_debug(
+			"SELinux:  %d users, %d roles, %d types, %d bools, %d sens, %d cats\n",
+			p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim,
+			p->p_bools.nprim, p->p_levels.nprim, p->p_cats.nprim);
+	else
+		pr_debug("SELinux:  %d users, %d roles, %d types, %d bools\n",
+			 p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim,
+			 p->p_bools.nprim);
+
+	pr_debug("SELinux:  %d classes, %d rules\n", p->p_classes.nprim,
+		 p->te_avtab.nel);
+
+	symtab_hash_eval(p->symtab);
+
+	p->class_val_to_struct = kzalloc_objs(*p->class_val_to_struct,
+					      p->p_classes.nprim);
+	if (!p->class_val_to_struct)
+		return -ENOMEM;
+
+	p->role_val_to_struct = kzalloc_objs(*p->role_val_to_struct,
+					     p->p_roles.nprim);
+	if (!p->role_val_to_struct)
+		return -ENOMEM;
+
+	p->user_val_to_struct = kzalloc_objs(*p->user_val_to_struct,
+					     p->p_users.nprim);
+	if (!p->user_val_to_struct)
+		return -ENOMEM;
+
+	p->type_val_to_struct = kvzalloc_objs(*p->type_val_to_struct,
+					      p->p_types.nprim);
+	if (!p->type_val_to_struct)
+		return -ENOMEM;
+
+	rc = cond_init_bool_indexes(p);
+	if (rc)
+		goto out;
+
+	for (i = 0; i < SYM_NUM; i++) {
+		p->sym_val_to_name[i] = kvcalloc(p->symtab[i].nprim,
+						 sizeof(char *), GFP_KERNEL);
+		if (!p->sym_val_to_name[i])
+			return -ENOMEM;
+
+		rc = hashtab_map(&p->symtab[i].table, index_f[i], p);
+		if (rc)
+			goto out;
+	}
+
+	/*
+	 * A sparse class value is absorbed by policydb_class_isvalid() and
+	 * its siblings, but no such predicate exists for booleans: every
+	 * user of bool_val_to_struct[] walks it by index and dereferences
+	 * each entry -- cond_evaluate_expr(), the two getters and
+	 * security_set_bools() -- so an unclaimed one has no consumer that
+	 * can tolerate it.
+	 */
+	for (v = 0; v < p->p_bools.nprim; v++) {
+		if (!p->bool_val_to_struct[v]) {
+			pr_err("SELinux:  boolean %u is declared but not defined\n",
+			       v + 1);
+			rc = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (p->mls_enabled) {
+		rc = hashtab_map(&p->p_levels.table, sens_cat_index_check, p);
+		if (rc)
+			goto out;
+	}
+
+	rc = 0;
+out:
+	return rc;
+}
+
+/*
+ * Free any memory allocated by a policy database structure.
+ */
+void policydb_destroy(struct policydb *p)
+{
+	struct ocontext *c, *ctmp;
+	struct genfs *g, *gtmp;
+	u32 i;
+	struct role_allow *ra, *lra = NULL;
+
+	for (i = 0; i < SYM_NUM; i++) {
+		cond_resched();
+		hashtab_map(&p->symtab[i].table, destroy_f[i], NULL);
+		hashtab_destroy(&p->symtab[i].table);
+	}
+
+	for (i = 0; i < SYM_NUM; i++)
+		kvfree(p->sym_val_to_name[i]);
+
+	kfree(p->class_val_to_struct);
+	kfree(p->role_val_to_struct);
+	kfree(p->user_val_to_struct);
+	kvfree(p->type_val_to_struct);
+
+	avtab_destroy(&p->te_avtab);
+
+	for (i = 0; i < OCON_NUM; i++) {
+		cond_resched();
+		c = p->ocontexts[i];
+		while (c) {
+			ctmp = c;
+			c = c->next;
+			ocontext_destroy(ctmp, i);
+		}
+		p->ocontexts[i] = NULL;
+	}
+
+	g = p->genfs;
+	while (g) {
+		cond_resched();
+		kfree(g->fstype);
+		c = g->head;
+		while (c) {
+			ctmp = c;
+			c = c->next;
+			ocontext_destroy(ctmp, OCON_FSUSE);
+		}
+		gtmp = g;
+		g = g->next;
+		kfree(gtmp);
+	}
+	p->genfs = NULL;
+
+	cond_policydb_destroy(p);
+
+	hashtab_map(&p->role_tr, role_tr_destroy, NULL);
+	hashtab_destroy(&p->role_tr);
+
+	for (ra = p->role_allow; ra; ra = ra->next) {
+		cond_resched();
+		kfree(lra);
+		lra = ra;
+	}
+	kfree(lra);
+
+	hashtab_map(&p->filename_trans, filenametr_destroy, NULL);
+	hashtab_destroy(&p->filename_trans);
+
+	hashtab_map(&p->range_tr, range_tr_destroy, NULL);
+	hashtab_destroy(&p->range_tr);
+
+	if (p->type_attr_map_array) {
+		for (i = 0; i < p->p_types.nprim; i++)
+			ebitmap_destroy(&p->type_attr_map_array[i]);
+		kvfree(p->type_attr_map_array);
+	}
+
+	ebitmap_destroy(&p->filename_trans_ttypes);
+	ebitmap_destroy(&p->policycaps);
+	ebitmap_destroy(&p->permissive_map);
+	ebitmap_destroy(&p->neveraudit_map);
+}
+
+/*
+ * Load the initial SIDs specified in a policy database
+ * structure into a SID table.
+ */
+int policydb_load_isids(struct policydb *p, struct sidtab *s)
+{
+	struct ocontext *head, *c;
+	bool isid_init;
+	int rc;
+
+	rc = sidtab_init(s);
+	if (rc) {
+		pr_err("SELinux:  out of memory on SID table init\n");
+		return rc;
+	}
+
+	isid_init = ebitmap_get_bit(&p->policycaps,
+				    POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT);
+
+	head = p->ocontexts[OCON_ISID];
+	for (c = head; c; c = c->next) {
+		u32 sid = c->sid[0];
+		const char *name = security_get_initial_sid_context(sid);
+
+		if (sid == SECSID_NULL) {
+			pr_err("SELinux:  SID 0 was assigned a context.\n");
+			sidtab_destroy(s);
+			return -EINVAL;
+		}
+
+		/* Ignore initial SIDs unused by this kernel. */
+		if (!name)
+			continue;
+
+		/*
+		 * Also ignore SECINITSID_INIT if the policy doesn't declare
+		 * support for it
+		 */
+		if (sid == SECINITSID_INIT && !isid_init)
+			continue;
+
+		rc = sidtab_set_initial(s, sid, &c->context[0]);
+		if (rc) {
+			pr_err("SELinux:  unable to load initial SID %s.\n",
+			       name);
+			sidtab_destroy(s);
+			return rc;
+		}
+
+		/*
+		 * If the policy doesn't support the "userspace_initial_context"
+		 * capability, set SECINITSID_INIT to the same context as
+		 * SECINITSID_KERNEL. This ensures the same behavior as before
+		 * the reintroduction of SECINITSID_INIT, where all tasks
+		 * started before policy load would initially get the context
+		 * corresponding to SECINITSID_KERNEL.
+		 */
+		if (sid == SECINITSID_KERNEL && !isid_init) {
+			rc = sidtab_set_initial(s, SECINITSID_INIT,
+						&c->context[0]);
+			if (rc) {
+				pr_err("SELinux:  unable to load initial SID %s.\n",
+				       name);
+				sidtab_destroy(s);
+				return rc;
+			}
+		}
+	}
+	return 0;
+}
+
+bool policydb_class_isvalid(const struct policydb *p, u16 class)
+{
+	if (!class || class > p->p_classes.nprim)
+		return false;
+	if (!p->sym_val_to_name[SYM_CLASSES][class - 1])
+		return false;
+	return true;
+}
+
+bool policydb_user_isvalid(const struct policydb *p, u32 user)
+{
+	if (!user || user > p->p_users.nprim)
+		return false;
+	if (!p->sym_val_to_name[SYM_USERS][user - 1])
+		return false;
+	return true;
+}
+
+bool policydb_role_isvalid(const struct policydb *p, u32 role)
+{
+	if (!role || role > p->p_roles.nprim)
+		return false;
+	if (!p->sym_val_to_name[SYM_ROLES][role - 1])
+		return false;
+	return true;
+}
+
+bool policydb_type_isvalid(const struct policydb *p, u32 type)
+{
+	if (!type || type > p->p_types.nprim)
+		return false;
+	if (!p->sym_val_to_name[SYM_TYPES][type - 1])
+		return false;
+	return true;
+}
+
+bool policydb_simpletype_isvalid(const struct policydb *p, u32 type)
+{
+	const struct type_datum *datum;
+
+	if (!type || type > p->p_types.nprim)
+		return false;
+
+	datum = p->type_val_to_struct[type - 1];
+	if (!datum)
+		return false;
+
+	if (datum->attribute)
+		return false;
+
+	return true;
+}
+
+/*
+ * Return true if the fields in the security context
+ * structure `c' are valid.  Return 0 otherwise.
+ */
+bool policydb_context_isvalid(const struct policydb *p, const struct context *c)
+{
+	const struct role_datum *role;
+	const struct user_datum *usrdatum;
+
+	if (!c->role || c->role > p->p_roles.nprim)
+		return false;
+
+	if (!c->user || c->user > p->p_users.nprim)
+		return false;
+
+	if (!c->type || c->type > p->p_types.nprim)
+		return false;
+
+	if (c->role != OBJECT_R_VAL) {
+		/*
+		 * Role must be authorized for the type.
+		 */
+		role = p->role_val_to_struct[c->role - 1];
+		if (!role || !ebitmap_get_bit(&role->types, c->type - 1))
+			/* role may not be associated with type */
+			return false;
+
+		/*
+		 * User must be authorized for the role.
+		 */
+		usrdatum = p->user_val_to_struct[c->user - 1];
+		if (!usrdatum)
+			return false;
+
+		if (!ebitmap_get_bit(&usrdatum->roles, c->role - 1))
+			/* user may not be associated with role */
+			return false;
+	}
+
+	if (!mls_context_isvalid(p, c))
+		return false;
+
+	return true;
+}
+
+/*
+ * Read a MLS range structure from a policydb binary
+ * representation file.
+ */
+static int mls_read_range_helper(struct mls_range *r, struct policy_file *fp)
+{
+	__le32 buf[2];
+	u32 items;
+	int rc;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		goto out;
+
+	rc = -EINVAL;
+	items = le32_to_cpu(buf[0]);
+	if (items > ARRAY_SIZE(buf)) {
+		pr_err("SELinux: mls:  range overflow\n");
+		goto out;
+	}
+
+	rc = next_entry(buf, fp, sizeof(u32) * items);
+	if (rc) {
+		pr_err("SELinux: mls:  truncated range\n");
+		goto out;
+	}
+
+	r->level[0].sens = le32_to_cpu(buf[0]);
+	if (items > 1)
+		r->level[1].sens = le32_to_cpu(buf[1]);
+	else
+		r->level[1].sens = r->level[0].sens;
+
+	rc = ebitmap_read(&r->level[0].cat, fp);
+	if (rc) {
+		pr_err("SELinux: mls:  error reading low categories\n");
+		goto out;
+	}
+	if (items > 1) {
+		rc = ebitmap_read(&r->level[1].cat, fp);
+		if (rc) {
+			pr_err("SELinux: mls:  error reading high categories\n");
+			goto bad_high;
+		}
+	} else {
+		rc = ebitmap_cpy(&r->level[1].cat, &r->level[0].cat);
+		if (rc) {
+			pr_err("SELinux: mls:  out of memory\n");
+			goto bad_high;
+		}
+	}
+
+	return 0;
+bad_high:
+	ebitmap_destroy(&r->level[0].cat);
+out:
+	return rc;
+}
+
+/*
+ * Read and validate a security context structure
+ * from a policydb binary representation file.
+ */
+static int context_read_and_validate(struct context *c, struct policydb *p,
+				     struct policy_file *fp)
+{
+	__le32 buf[3];
+	int rc;
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc) {
+		pr_err("SELinux: context truncated\n");
+		goto out;
+	}
+	c->user = le32_to_cpu(buf[0]);
+	c->role = le32_to_cpu(buf[1]);
+	c->type = le32_to_cpu(buf[2]);
+	if (p->policyvers >= POLICYDB_VERSION_MLS) {
+		rc = mls_read_range_helper(&c->range, fp);
+		if (rc) {
+			pr_err("SELinux: error reading MLS range of context\n");
+			goto out;
+		}
+	}
+
+	rc = -EINVAL;
+	if (!policydb_context_isvalid(p, c)) {
+		pr_err("SELinux:  invalid security context\n");
+		context_destroy(c);
+		goto out;
+	}
+	rc = 0;
+out:
+	return rc;
+}
+
+/*
+ * The following *_read functions are used to
+ * read the symbol data from a policy database
+ * binary representation file.
+ */
+
+int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len)
+{
+	int rc;
+	char *str;
+
+	if ((len == 0) || (len == (u32)-1))
+		return -EINVAL;
+
+	if (size_check(sizeof(char), len, fp))
+		return -EINVAL;
+
+	str = kmalloc(len + 1, flags | __GFP_NOWARN);
+	if (!str)
+		return -ENOMEM;
+
+	rc = next_entry(str, fp, len);
+	if (rc) {
+		kfree(str);
+		return rc;
+	}
+
+	str[len] = '\0';
+	*strp = str;
+	return 0;
+}
+
+/*
+ * Bitmap of the permission values a symtab has claimed.  Values are 1-based
+ * and bounded by SEL_VEC_MAX, the width of an access vector, so the whole set
+ * fits in a u32 and the callers reject an nprim past that width.
+ */
+static u32 perm_claimed_mask(u32 nprim)
+{
+	return nprim ? U32_MAX >> (SEL_VEC_MAX - nprim) : 0;
+}
+
+static int perm_read(struct policydb *p, struct symtab *s,
+		     struct policy_file *fp, u32 *claimed)
+{
+	char *key = NULL;
+	struct perm_datum *perdatum;
+	int rc;
+	__le32 buf[2];
+	u32 len;
+
+	perdatum = kzalloc_obj(*perdatum);
+	if (!perdatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	perdatum->value = le32_to_cpu(buf[1]);
+	rc = -EINVAL;
+	if (perdatum->value < 1 || perdatum->value > SEL_VEC_MAX)
+		goto bad;
+	/* indexes an nprim-sized array in security_get_permissions() */
+	if (perdatum->value > s->nprim)
+		goto bad;
+	/* two permissions cannot share one slot of that array */
+	if (*claimed & (1U << (perdatum->value - 1)))
+		goto bad;
+	*claimed |= 1U << (perdatum->value - 1);
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = symtab_insert(s, key, perdatum);
+	if (rc)
+		goto bad;
+
+	return 0;
+bad:
+	perm_destroy(key, perdatum, NULL);
+	return rc;
+}
+
+static int common_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct common_datum *comdatum;
+	__le32 buf[4];
+	u32 i, len, nel, claimed = 0;
+	int rc;
+
+	comdatum = kzalloc_obj(*comdatum);
+	if (!comdatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	comdatum->value = le32_to_cpu(buf[1]);
+	nel = le32_to_cpu(buf[3]);
+	rc = -EINVAL;
+	if (nel > SEL_VEC_MAX)
+		goto bad;
+
+	/* perm_read() reads at least 64 bytes for any valid permission */
+	rc = size_check(2 * sizeof(u32), nel, fp);
+	if (rc)
+		goto bad;
+
+	rc = symtab_init(&comdatum->permissions, nel);
+	if (rc)
+		goto bad;
+	comdatum->permissions.nprim = le32_to_cpu(buf[2]);
+	/* no permission value can reach a slot past SEL_VEC_MAX */
+	rc = -EINVAL;
+	if (comdatum->permissions.nprim > SEL_VEC_MAX)
+		goto bad;
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	for (i = 0; i < nel; i++) {
+		rc = perm_read(p, &comdatum->permissions, fp, &claimed);
+		if (rc)
+			goto bad;
+	}
+
+	rc = -EINVAL;
+	if (claimed != perm_claimed_mask(comdatum->permissions.nprim)) {
+		pr_err("SELinux:  common %s does not define every permission it declares\n",
+		       key);
+		goto bad;
+	}
+
+	hash_eval(&comdatum->permissions.table, "common_permissions", key);
+
+	rc = symtab_insert(s, key, comdatum);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	common_destroy(key, comdatum, NULL);
+	return rc;
+}
+
+static void type_set_init(struct type_set *t)
+{
+	ebitmap_init(&t->types);
+	ebitmap_init(&t->negset);
+}
+
+static int type_set_read(struct type_set *t, struct policy_file *fp)
+{
+	__le32 buf[1];
+	int rc;
+
+	if (ebitmap_read(&t->types, fp))
+		return -EINVAL;
+	if (ebitmap_read(&t->negset, fp))
+		return -EINVAL;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc < 0)
+		return -EINVAL;
+	t->flags = le32_to_cpu(buf[0]);
+
+	return 0;
+}
+
+static int read_cons_helper(struct policydb *p, struct constraint_node **nodep,
+			    u32 ncons, int allowxtarget, struct policy_file *fp)
+{
+	struct constraint_node *c, *lc;
+	struct constraint_expr *e, *le;
+	__le32 buf[3];
+	u32 i, j, nexpr;
+	int rc, depth;
+
+	lc = NULL;
+	for (i = 0; i < ncons; i++) {
+		c = kzalloc_obj(*c);
+		if (!c)
+			return -ENOMEM;
+
+		if (lc)
+			lc->next = c;
+		else
+			*nodep = c;
+
+		rc = next_entry(buf, fp, (sizeof(u32) * 2));
+		if (rc)
+			return rc;
+		c->permissions = le32_to_cpu(buf[0]);
+		nexpr = le32_to_cpu(buf[1]);
+		le = NULL;
+		depth = -1;
+		for (j = 0; j < nexpr; j++) {
+			e = kzalloc_obj(*e);
+			if (!e)
+				return -ENOMEM;
+
+			if (le)
+				le->next = e;
+			else
+				c->expr = e;
+
+			rc = next_entry(buf, fp, (sizeof(u32) * 3));
+			if (rc)
+				return rc;
+			e->expr_type = le32_to_cpu(buf[0]);
+			e->attr = le32_to_cpu(buf[1]);
+			e->op = le32_to_cpu(buf[2]);
+
+			switch (e->expr_type) {
+			case CEXPR_NOT:
+				if (depth < 0)
+					return -EINVAL;
+				break;
+			case CEXPR_AND:
+			case CEXPR_OR:
+				if (depth < 1)
+					return -EINVAL;
+				depth--;
+				break;
+			case CEXPR_ATTR:
+				if (depth == (CEXPR_MAXDEPTH - 1))
+					return -EINVAL;
+				depth++;
+				switch (e->attr) {
+				case CEXPR_USER:
+				case CEXPR_TYPE:
+					if (e->op != CEXPR_EQ &&
+					    e->op != CEXPR_NEQ)
+						return -EINVAL;
+					break;
+				case CEXPR_ROLE:
+				case CEXPR_L1L2:
+				case CEXPR_L1H2:
+				case CEXPR_H1L2:
+				case CEXPR_H1H2:
+				case CEXPR_L1H1:
+				case CEXPR_L2H2:
+					if (e->op < CEXPR_EQ ||
+					    e->op > CEXPR_INCOMP)
+						return -EINVAL;
+					break;
+				default:
+					return -EINVAL;
+				}
+				break;
+			case CEXPR_NAMES:
+				if (!allowxtarget && (e->attr & CEXPR_XTARGET))
+					return -EINVAL;
+				if (depth == (CEXPR_MAXDEPTH - 1))
+					return -EINVAL;
+				depth++;
+				switch (e->attr &
+					~(CEXPR_TARGET|CEXPR_XTARGET)) {
+				case CEXPR_USER:
+				case CEXPR_ROLE:
+				case CEXPR_TYPE:
+					break;
+				default:
+					return -EINVAL;
+				}
+				if ((e->attr & (CEXPR_TARGET|CEXPR_XTARGET)) ==
+					(CEXPR_TARGET|CEXPR_XTARGET))
+					return -EINVAL;
+				if (e->op != CEXPR_EQ && e->op != CEXPR_NEQ)
+					return -EINVAL;
+				rc = ebitmap_read(&e->names, fp);
+				if (rc)
+					return rc;
+				if (p->policyvers >=
+				    POLICYDB_VERSION_CONSTRAINT_NAMES) {
+					e->type_names = kzalloc_obj(*e->type_names);
+					if (!e->type_names)
+						return -ENOMEM;
+					type_set_init(e->type_names);
+					rc = type_set_read(e->type_names, fp);
+					if (rc)
+						return rc;
+				}
+				break;
+			default:
+				return -EINVAL;
+			}
+			le = e;
+		}
+		if (depth != 0)
+			return -EINVAL;
+		lc = c;
+	}
+
+	return 0;
+}
+
+static int class_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct class_datum *cladatum;
+	__le32 buf[6];
+	u32 i, len, len2, ncons, nel, val, claimed = 0, inherited = 0;
+	int rc;
+
+	cladatum = kzalloc_obj(*cladatum);
+	if (!cladatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof(u32) * 6);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	len2 = le32_to_cpu(buf[1]);
+	nel = le32_to_cpu(buf[4]);
+	rc = -EINVAL;
+	if (nel > SEL_VEC_MAX)
+		goto bad;
+
+	val = le32_to_cpu(buf[2]);
+	rc = -EINVAL;
+	if (val > U16_MAX)
+		goto bad;
+	cladatum->value = val;
+
+	/* perm_read() reads at least 64 bytes for any valid permission */
+	rc = size_check(2 * sizeof(u32), nel, fp);
+	if (rc)
+		goto bad;
+
+	rc = symtab_init(&cladatum->permissions, nel);
+	if (rc)
+		goto bad;
+	cladatum->permissions.nprim = le32_to_cpu(buf[3]);
+	/* no permission value can reach a slot past SEL_VEC_MAX */
+	rc = -EINVAL;
+	if (cladatum->permissions.nprim > SEL_VEC_MAX)
+		goto bad;
+
+	ncons = le32_to_cpu(buf[5]);
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	if (len2) {
+		rc = str_read(&cladatum->comkey, GFP_KERNEL, fp, len2);
+		if (rc)
+			goto bad;
+
+		rc = -EINVAL;
+		cladatum->comdatum =
+			symtab_search(&p->p_commons, cladatum->comkey);
+		if (!cladatum->comdatum) {
+			pr_err("SELinux:  unknown common %s\n",
+			       cladatum->comkey);
+			goto bad;
+		}
+
+		/*
+		 * security_get_permissions() maps the common's permissions
+		 * into an array sized by this class's nprim, so a class must
+		 * declare at least as many as the common it inherits.
+		 */
+		if (cladatum->permissions.nprim <
+		    cladatum->comdatum->permissions.nprim) {
+			pr_err("SELinux:  class %s has fewer permissions than common %s\n",
+			       key, cladatum->comkey);
+			goto bad;
+		}
+	}
+	for (i = 0; i < nel; i++) {
+		rc = perm_read(p, &cladatum->permissions, fp, &claimed);
+		if (rc)
+			goto bad;
+	}
+
+	/* the class's own permissions must claim the slots the common leaves */
+	if (cladatum->comdatum)
+		inherited = cladatum->comdatum->permissions.nprim;
+	rc = -EINVAL;
+	if (claimed != (perm_claimed_mask(cladatum->permissions.nprim) &
+			~perm_claimed_mask(inherited))) {
+		pr_err("SELinux:  class %s does not define every permission it declares\n",
+		       key);
+		goto bad;
+	}
+
+	hash_eval(&cladatum->permissions.table, "class_permissions", key);
+
+	rc = read_cons_helper(p, &cladatum->constraints, ncons, 0, fp);
+	if (rc)
+		goto bad;
+
+	if (p->policyvers >= POLICYDB_VERSION_VALIDATETRANS) {
+		/* grab the validatetrans rules */
+		rc = next_entry(buf, fp, sizeof(u32));
+		if (rc)
+			goto bad;
+		ncons = le32_to_cpu(buf[0]);
+		rc = read_cons_helper(p, &cladatum->validatetrans, ncons, 1,
+				      fp);
+		if (rc)
+			goto bad;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) {
+		rc = next_entry(buf, fp, sizeof(u32) * 3);
+		if (rc)
+			goto bad;
+
+		rc = -EINVAL;
+		val = le32_to_cpu(buf[0]);
+		switch (val) {
+		case 0:
+		case DEFAULT_SOURCE:
+		case DEFAULT_TARGET:
+			cladatum->default_user = val;
+			break;
+		default:
+			goto bad;
+		}
+		val = le32_to_cpu(buf[1]);
+		switch (val) {
+		case 0:
+		case DEFAULT_SOURCE:
+		case DEFAULT_TARGET:
+			cladatum->default_role = val;
+			break;
+		default:
+			goto bad;
+		}
+		val = le32_to_cpu(buf[2]);
+		switch (val) {
+		case 0:
+		case DEFAULT_SOURCE_LOW:
+		case DEFAULT_SOURCE_HIGH:
+		case DEFAULT_SOURCE_LOW_HIGH:
+		case DEFAULT_TARGET_LOW:
+		case DEFAULT_TARGET_HIGH:
+		case DEFAULT_TARGET_LOW_HIGH:
+		case DEFAULT_GLBLUB:
+			cladatum->default_range = val;
+			break;
+		default:
+			goto bad;
+		}
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) {
+		rc = next_entry(buf, fp, sizeof(u32) * 1);
+		if (rc)
+			goto bad;
+		rc = -EINVAL;
+		val = le32_to_cpu(buf[0]);
+		switch (val) {
+		case 0:
+		case DEFAULT_TARGET:
+		case DEFAULT_SOURCE:
+			cladatum->default_type = val;
+			break;
+		default:
+			goto bad;
+		}
+	}
+
+	rc = symtab_insert(s, key, cladatum);
+	if (rc)
+		goto bad;
+
+	return 0;
+bad:
+	cls_destroy(key, cladatum, NULL);
+	if (rc)
+		pr_err("SELinux:  invalid class\n");
+	return rc;
+}
+
+static int role_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct role_datum *role;
+	int rc;
+	unsigned int to_read = 2;
+	__le32 buf[3];
+	u32 len;
+
+	role = kzalloc_obj(*role);
+	if (!role)
+		return -ENOMEM;
+
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		to_read = 3;
+
+	rc = next_entry(buf, fp, sizeof(buf[0]) * to_read);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	role->value = le32_to_cpu(buf[1]);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		role->bounds = le32_to_cpu(buf[2]);
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = ebitmap_read(&role->dominates, fp);
+	if (rc)
+		goto bad;
+
+	rc = ebitmap_read(&role->types, fp);
+	if (rc)
+		goto bad;
+
+	if (strcmp(key, OBJECT_R) == 0) {
+		rc = -EINVAL;
+		if (role->value != OBJECT_R_VAL) {
+			pr_err("SELinux: Role %s has wrong value %d\n",
+			       OBJECT_R, role->value);
+			goto bad;
+		}
+		rc = 0;
+		goto bad;
+	}
+
+	rc = symtab_insert(s, key, role);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	role_destroy(key, role, NULL);
+	return rc;
+}
+
+static int type_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct type_datum *typdatum;
+	int rc;
+	unsigned int to_read = 3;
+	__le32 buf[4];
+	u32 len;
+
+	typdatum = kzalloc_obj(*typdatum);
+	if (!typdatum)
+		return -ENOMEM;
+
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		to_read = 4;
+
+	rc = next_entry(buf, fp, sizeof(buf[0]) * to_read);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	typdatum->value = le32_to_cpu(buf[1]);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) {
+		u32 prop = le32_to_cpu(buf[2]);
+
+		if (prop & TYPEDATUM_PROPERTY_PRIMARY)
+			typdatum->primary = 1;
+		if (prop & TYPEDATUM_PROPERTY_ATTRIBUTE)
+			typdatum->attribute = 1;
+
+		typdatum->bounds = le32_to_cpu(buf[3]);
+	} else {
+		typdatum->primary = le32_to_cpu(buf[2]);
+	}
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = symtab_insert(s, key, typdatum);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	type_destroy(key, typdatum, NULL);
+	return rc;
+}
+
+/*
+ * Read a MLS level structure from a policydb binary
+ * representation file.
+ */
+static int mls_read_level(struct mls_level *lp, struct policy_file *fp)
+{
+	__le32 buf[1];
+	int rc;
+
+	memset(lp, 0, sizeof(*lp));
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc) {
+		pr_err("SELinux: mls: truncated level\n");
+		return rc;
+	}
+	lp->sens = le32_to_cpu(buf[0]);
+
+	rc = ebitmap_read(&lp->cat, fp);
+	if (rc) {
+		pr_err("SELinux: mls:  error reading level categories\n");
+		return rc;
+	}
+	return 0;
+}
+
+static int user_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct user_datum *usrdatum;
+	int rc;
+	unsigned int to_read = 2;
+	__le32 buf[3];
+	u32 len;
+
+	usrdatum = kzalloc_obj(*usrdatum);
+	if (!usrdatum)
+		return -ENOMEM;
+
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		to_read = 3;
+
+	rc = next_entry(buf, fp, sizeof(buf[0]) * to_read);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	usrdatum->value = le32_to_cpu(buf[1]);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		usrdatum->bounds = le32_to_cpu(buf[2]);
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = ebitmap_read(&usrdatum->roles, fp);
+	if (rc)
+		goto bad;
+
+	if (p->policyvers >= POLICYDB_VERSION_MLS) {
+		rc = mls_read_range_helper(&usrdatum->range, fp);
+		if (rc)
+			goto bad;
+		rc = mls_read_level(&usrdatum->dfltlevel, fp);
+		if (rc)
+			goto bad;
+	}
+
+	rc = symtab_insert(s, key, usrdatum);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	user_destroy(key, usrdatum, NULL);
+	return rc;
+}
+
+static int sens_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct level_datum *levdatum;
+	int rc;
+	__le32 buf[2];
+	u32 len, val;
+
+	levdatum = kzalloc_obj(*levdatum);
+	if (!levdatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	val = le32_to_cpu(buf[1]);
+	rc = -EINVAL;
+	if (!val_is_boolean(val))
+		goto bad;
+	levdatum->isalias = val;
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = mls_read_level(&levdatum->level, fp);
+	if (rc)
+		goto bad;
+
+	rc = symtab_insert(s, key, levdatum);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	sens_destroy(key, levdatum, NULL);
+	if (rc)
+		pr_err("SELinux:  invalid sensitivity\n");
+	return rc;
+}
+
+static int cat_read(struct policydb *p, struct symtab *s, struct policy_file *fp)
+{
+	char *key = NULL;
+	struct cat_datum *catdatum;
+	int rc;
+	__le32 buf[3];
+	u32 len, val;
+
+	catdatum = kzalloc_obj(*catdatum);
+	if (!catdatum)
+		return -ENOMEM;
+
+	rc = next_entry(buf, fp, sizeof buf);
+	if (rc)
+		goto bad;
+
+	len = le32_to_cpu(buf[0]);
+	catdatum->value = le32_to_cpu(buf[1]);
+	val = le32_to_cpu(buf[2]);
+	rc = -EINVAL;
+	if (!val_is_boolean(val))
+		goto bad;
+	catdatum->isalias = val;
+
+	rc = str_read(&key, GFP_KERNEL, fp, len);
+	if (rc)
+		goto bad;
+
+	rc = symtab_insert(s, key, catdatum);
+	if (rc)
+		goto bad;
+	return 0;
+bad:
+	cat_destroy(key, catdatum, NULL);
+	if (rc)
+		pr_err("SELinux:  invalid category\n");
+	return rc;
+}
+
+/* clang-format off */
+static int (*const read_f[SYM_NUM])(struct policydb *p, struct symtab *s,
+				    struct policy_file *fp) = {
+	common_read,
+	class_read,
+	role_read,
+	type_read,
+	user_read,
+	cond_read_bool,
+	sens_read,
+	cat_read,
+};
+/* clang-format on */
+
+static int user_bounds_sanity_check(void *key, void *datum, void *datap)
+{
+	struct user_datum *upper, *user;
+	struct policydb *p = datap;
+	int depth = 0;
+
+	upper = user = datum;
+	while (upper->bounds) {
+		struct ebitmap_node *node;
+		u32 bit;
+
+		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
+			pr_err("SELinux: user %s: "
+			       "too deep or looped boundary\n",
+			       (char *)key);
+			return -EINVAL;
+		}
+
+		if (!policydb_user_isvalid(p, upper->bounds)) {
+			pr_err("SELinux: user %s: invalid boundary id %d\n",
+			       (char *) key, upper->bounds);
+			return -EINVAL;
+		}
+
+		upper = p->user_val_to_struct[upper->bounds - 1];
+		ebitmap_for_each_positive_bit(&user->roles, node, bit)
+		{
+			if (ebitmap_get_bit(&upper->roles, bit))
+				continue;
+
+			pr_err("SELinux: boundary violated policy: "
+			       "user=%s role=%s bounds=%s\n",
+			       sym_name(p, SYM_USERS, user->value - 1),
+			       sym_name(p, SYM_ROLES, bit),
+			       sym_name(p, SYM_USERS, upper->value - 1));
+
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int role_bounds_sanity_check(void *key, void *datum, void *datap)
+{
+	struct role_datum *upper, *role;
+	struct policydb *p = datap;
+	int depth = 0;
+
+	upper = role = datum;
+	while (upper->bounds) {
+		struct ebitmap_node *node;
+		u32 bit;
+
+		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
+			pr_err("SELinux: role %s: "
+			       "too deep or looped bounds\n",
+			       (char *)key);
+			return -EINVAL;
+		}
+
+		if (!policydb_role_isvalid(p, upper->bounds)) {
+			pr_err("SELinux: role %s: invalid boundary id %d\n",
+			       (char *) key, upper->bounds);
+			return -EINVAL;
+		}
+
+		upper = p->role_val_to_struct[upper->bounds - 1];
+		ebitmap_for_each_positive_bit(&role->types, node, bit)
+		{
+			if (ebitmap_get_bit(&upper->types, bit))
+				continue;
+
+			pr_err("SELinux: boundary violated policy: "
+			       "role=%s type=%s bounds=%s\n",
+			       sym_name(p, SYM_ROLES, role->value - 1),
+			       sym_name(p, SYM_TYPES, bit),
+			       sym_name(p, SYM_ROLES, upper->value - 1));
+
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int type_bounds_sanity_check(void *key, void *datum, void *datap)
+{
+	struct type_datum *upper;
+	struct policydb *p = datap;
+	int depth = 0;
+
+	upper = datum;
+	while (upper->bounds) {
+		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
+			pr_err("SELinux: type %s: "
+			       "too deep or looped boundary\n",
+			       (char *)key);
+			return -EINVAL;
+		}
+
+		if (!policydb_type_isvalid(p, upper->bounds)) {
+			pr_err("SELinux: type %s: invalid boundary id %d\n",
+			       (char *) key, upper->bounds);
+			return -EINVAL;
+		}
+
+		upper = p->type_val_to_struct[upper->bounds - 1];
+		if (upper->attribute) {
+			pr_err("SELinux: type %s: "
+			       "bounded by attribute %s\n",
+			       (char *)key,
+			       sym_name(p, SYM_TYPES, upper->value - 1));
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int policydb_bounds_sanity_check(struct policydb *p)
+{
+	int rc;
+
+	if (p->policyvers < POLICYDB_VERSION_BOUNDARY)
+		return 0;
+
+	rc = hashtab_map(&p->p_users.table, user_bounds_sanity_check, p);
+	if (rc)
+		return rc;
+
+	rc = hashtab_map(&p->p_roles.table, role_bounds_sanity_check, p);
+	if (rc)
+		return rc;
+
+	rc = hashtab_map(&p->p_types.table, type_bounds_sanity_check, p);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+u16 string_to_security_class(struct policydb *p, const char *name)
+{
+	struct class_datum *cladatum;
+
+	cladatum = symtab_search(&p->p_classes, name);
+	if (!cladatum)
+		return 0;
+
+	return cladatum->value;
+}
+
+u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name)
+{
+	struct class_datum *cladatum;
+	struct perm_datum *perdatum = NULL;
+	struct common_datum *comdatum;
+
+	if (!tclass || tclass > p->p_classes.nprim)
+		return 0;
+
+	cladatum = p->class_val_to_struct[tclass - 1];
+	comdatum = cladatum->comdatum;
+	if (comdatum)
+		perdatum = symtab_search(&comdatum->permissions, name);
+	if (!perdatum)
+		perdatum = symtab_search(&cladatum->permissions, name);
+	if (!perdatum)
+		return 0;
+
+	return 1U << (perdatum->value - 1);
+}
+
+static int range_read(struct policydb *p, struct policy_file *fp)
+{
+	struct range_trans *rt = NULL;
+	struct mls_range *r = NULL;
+	int rc;
+	__le32 buf[2];
+	u32 i, nel, val;
+
+	if (p->policyvers < POLICYDB_VERSION_MLS)
+		return 0;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+
+	nel = le32_to_cpu(buf[0]);
+
+	/* we read at least 64 bytes and mls_read_range_helper() 32 bytes
+	 * for any valid range-transition
+	 */
+	rc = size_check(3 * sizeof(u32), nel, fp);
+	if (rc)
+		return rc;
+
+	rc = hashtab_init(&p->range_tr, nel);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < nel; i++) {
+		rc = -ENOMEM;
+		rt = kzalloc_obj(*rt);
+		if (!rt)
+			goto out;
+
+		rc = next_entry(buf, fp, (sizeof(u32) * 2));
+		if (rc)
+			goto out;
+
+		rt->source_type = le32_to_cpu(buf[0]);
+		rt->target_type = le32_to_cpu(buf[1]);
+		if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) {
+			rc = next_entry(buf, fp, sizeof(u32));
+			if (rc)
+				goto out;
+			rc = -EINVAL;
+			val = le32_to_cpu(buf[0]);
+			if (val > U16_MAX)
+				goto out;
+			rt->target_class = val;
+		} else
+			rt->target_class = p->process_class;
+
+		rc = -EINVAL;
+		if (!policydb_type_isvalid(p, rt->source_type) ||
+		    !policydb_type_isvalid(p, rt->target_type) ||
+		    !policydb_class_isvalid(p, rt->target_class))
+			goto out;
+
+		rc = -ENOMEM;
+		r = kzalloc_obj(*r);
+		if (!r)
+			goto out;
+
+		rc = mls_read_range_helper(r, fp);
+		if (rc)
+			goto out;
+
+		rc = -EINVAL;
+		if (!mls_range_isvalid(p, r)) {
+			pr_warn("SELinux:  rangetrans:  invalid range\n");
+			goto out;
+		}
+
+		rc = hashtab_insert(&p->range_tr, rt, r, rangetr_key_params);
+		if (rc)
+			goto out;
+
+		rt = NULL;
+		r = NULL;
+	}
+	hash_eval(&p->range_tr, "rangetr", NULL);
+	rc = 0;
+out:
+	kfree(rt);
+	kfree(r);
+	if (rc)
+		pr_err("SELinux:  invalid range\n");
+	return rc;
+}
+
+static int filename_trans_read_helper_compat(struct policydb *p, struct policy_file *fp)
+{
+	struct filename_trans_key key, *ft = NULL;
+	struct filename_trans_datum *last, *datum = NULL;
+	char *name = NULL;
+	u32 len, stype, otype, val;
+	__le32 buf[4];
+	int rc;
+
+	/* length of the path component string */
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+	len = le32_to_cpu(buf[0]);
+
+	/* path component string */
+	rc = str_read(&name, GFP_KERNEL, fp, len);
+	if (rc)
+		return rc;
+
+	rc = next_entry(buf, fp, sizeof(u32) * 4);
+	if (rc)
+		goto out;
+
+	rc = -EINVAL;
+	stype = le32_to_cpu(buf[0]);
+	if (!policydb_type_isvalid(p, stype))
+		goto out;
+	key.ttype = le32_to_cpu(buf[1]);
+	if (!policydb_type_isvalid(p, key.ttype))
+		goto out;
+	val = le32_to_cpu(buf[2]);
+	if (val > U16_MAX || !policydb_class_isvalid(p, val))
+		goto out;
+	key.tclass = val;
+	key.name = name;
+
+	otype = le32_to_cpu(buf[3]);
+	if (!policydb_simpletype_isvalid(p, otype))
+		goto out;
+
+	last = NULL;
+	datum = policydb_filenametr_search(p, &key);
+	while (datum) {
+		if (unlikely(ebitmap_get_bit(&datum->stypes, stype - 1))) {
+			/* conflicting/duplicate rules are ignored */
+			datum = NULL;
+			rc = 0;
+			goto out;
+		}
+		if (likely(datum->otype == otype))
+			break;
+		last = datum;
+		datum = datum->next;
+	}
+	if (!datum) {
+		rc = -ENOMEM;
+		datum = kmalloc_obj(*datum);
+		if (!datum)
+			goto out;
+
+		ebitmap_init(&datum->stypes);
+		datum->otype = otype;
+		datum->next = NULL;
+
+		if (unlikely(last)) {
+			last->next = datum;
+		} else {
+			rc = -ENOMEM;
+			ft = kmemdup(&key, sizeof(key), GFP_KERNEL);
+			if (!ft)
+				goto out;
+
+			rc = hashtab_insert(&p->filename_trans, ft, datum,
+					    filenametr_key_params);
+			if (rc)
+				goto out;
+			name = NULL;
+
+			rc = ebitmap_set_bit(&p->filename_trans_ttypes,
+					     key.ttype, 1);
+			if (rc)
+				return rc;
+		}
+	}
+	kfree(name);
+	return ebitmap_set_bit(&datum->stypes, stype - 1, 1);
+
+out:
+	kfree(ft);
+	kfree(name);
+	kfree(datum);
+
+	if (rc)
+		pr_err("SELinux:  invalid compat filename transition\n");
+	return rc;
+}
+
+static int filename_trans_read_helper(struct policydb *p, struct policy_file *fp)
+{
+	struct filename_trans_key *ft = NULL;
+	struct filename_trans_datum **dst, *datum, *first = NULL;
+	char *name = NULL;
+	u32 len, ttype, ndatum, i, val;
+	u16 tclass;
+	__le32 buf[3];
+	int rc;
+
+	/* length of the path component string */
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+	len = le32_to_cpu(buf[0]);
+
+	/* path component string */
+	rc = str_read(&name, GFP_KERNEL, fp, len);
+	if (rc)
+		return rc;
+
+	rc = next_entry(buf, fp, sizeof(u32) * 3);
+	if (rc)
+		goto out;
+
+	rc = -EINVAL;
+	ttype = le32_to_cpu(buf[0]);
+	if (!policydb_type_isvalid(p, ttype))
+		goto out;
+	val = le32_to_cpu(buf[1]);
+	rc = -EINVAL;
+	if (val > U16_MAX || !policydb_class_isvalid(p, val))
+		goto out;
+	tclass = val;
+
+	ndatum = le32_to_cpu(buf[2]);
+	if (ndatum == 0) {
+		pr_err("SELinux:  Filename transition key with no datum\n");
+		rc = -ENOENT;
+		goto out;
+	}
+
+	dst = &first;
+	for (i = 0; i < ndatum; i++) {
+		rc = -ENOMEM;
+		datum = kmalloc_obj(*datum);
+		if (!datum)
+			goto out;
+
+		datum->next = NULL;
+		*dst = datum;
+
+		/* ebitmap_read() will at least init the bitmap */
+		rc = ebitmap_read(&datum->stypes, fp);
+		if (rc)
+			goto out;
+
+		rc = next_entry(buf, fp, sizeof(u32));
+		if (rc)
+			goto out;
+
+		datum->otype = le32_to_cpu(buf[0]);
+
+		rc = -EINVAL;
+		if (!policydb_simpletype_isvalid(p, datum->otype))
+			goto out;
+
+		dst = &datum->next;
+	}
+
+	rc = -ENOMEM;
+	ft = kmalloc_obj(*ft);
+	if (!ft)
+		goto out;
+
+	ft->ttype = ttype;
+	ft->tclass = tclass;
+	ft->name = name;
+
+	rc = hashtab_insert(&p->filename_trans, ft, first,
+			    filenametr_key_params);
+	if (rc == -EEXIST)
+		pr_err("SELinux:  Duplicate filename transition key\n");
+	if (rc)
+		goto out;
+
+	return ebitmap_set_bit(&p->filename_trans_ttypes, ttype, 1);
+
+out:
+	kfree(ft);
+	kfree(name);
+	while (first) {
+		datum = first;
+		first = first->next;
+
+		ebitmap_destroy(&datum->stypes);
+		kfree(datum);
+	}
+
+	if (rc)
+		pr_err("SELinux:  invalid filename transition\n");
+	return rc;
+}
+
+static int filename_trans_read(struct policydb *p, struct policy_file *fp)
+{
+	u32 nel, i;
+	__le32 buf[1];
+	int rc;
+
+	if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS)
+		return 0;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+	nel = le32_to_cpu(buf[0]);
+
+	if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) {
+		p->compat_filename_trans_count = nel;
+
+		rc = hashtab_init(&p->filename_trans, (1 << 11));
+		if (rc)
+			return rc;
+
+		for (i = 0; i < nel; i++) {
+			rc = filename_trans_read_helper_compat(p, fp);
+			if (rc)
+				return rc;
+		}
+	} else {
+		rc = hashtab_init(&p->filename_trans, nel);
+		if (rc)
+			return rc;
+
+		for (i = 0; i < nel; i++) {
+			rc = filename_trans_read_helper(p, fp);
+			if (rc)
+				return rc;
+		}
+	}
+	hash_eval(&p->filename_trans, "filenametr", NULL);
+	return 0;
+}
+
+static int genfs_read(struct policydb *p, struct policy_file *fp)
+{
+	int rc;
+	u32 i, j, nel, nel2, len, len2, val;
+	__le32 buf[1];
+	struct ocontext *l, *c;
+	struct ocontext *newc = NULL;
+	struct genfs *genfs_p, *genfs;
+	struct genfs *newgenfs = NULL;
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		return rc;
+	nel = le32_to_cpu(buf[0]);
+
+	for (i = 0; i < nel; i++) {
+		rc = next_entry(buf, fp, sizeof(u32));
+		if (rc)
+			goto out;
+		len = le32_to_cpu(buf[0]);
+
+		rc = -ENOMEM;
+		newgenfs = kzalloc_obj(*newgenfs);
+		if (!newgenfs)
+			goto out;
+
+		rc = str_read(&newgenfs->fstype, GFP_KERNEL, fp, len);
+		if (rc)
+			goto out;
+
+		for (genfs_p = NULL, genfs = p->genfs; genfs;
+		     genfs_p = genfs, genfs = genfs->next) {
+			rc = -EINVAL;
+			if (strcmp(newgenfs->fstype, genfs->fstype) == 0) {
+				pr_err("SELinux:  dup genfs fstype %s\n",
+				       newgenfs->fstype);
+				goto out;
+			}
+			if (strcmp(newgenfs->fstype, genfs->fstype) < 0)
+				break;
+		}
+		newgenfs->next = genfs;
+		if (genfs_p)
+			genfs_p->next = newgenfs;
+		else
+			p->genfs = newgenfs;
+		genfs = newgenfs;
+		newgenfs = NULL;
+
+		rc = next_entry(buf, fp, sizeof(u32));
+		if (rc)
+			goto out;
+
+		nel2 = le32_to_cpu(buf[0]);
+		for (j = 0; j < nel2; j++) {
+			rc = next_entry(buf, fp, sizeof(u32));
+			if (rc)
+				goto out;
+			len = le32_to_cpu(buf[0]);
+
+			rc = -ENOMEM;
+			newc = kzalloc_obj(*newc);
+			if (!newc)
+				goto out;
+
+			rc = str_read(&newc->u.name, GFP_KERNEL, fp, len);
+			if (rc)
+				goto out;
+
+			rc = next_entry(buf, fp, sizeof(u32));
+			if (rc)
+				goto out;
+
+			rc = -EINVAL;
+			val = le32_to_cpu(buf[0]);
+			if (val > U16_MAX || (val != 0 && !policydb_class_isvalid(p, val)))
+				goto out;
+			newc->v.sclass = val;
+			rc = context_read_and_validate(&newc->context[0], p,
+						       fp);
+			if (rc)
+				goto out;
+
+			for (l = NULL, c = genfs->head; c; l = c, c = c->next) {
+				rc = -EINVAL;
+				if (!strcmp(newc->u.name, c->u.name) &&
+				    (!c->v.sclass || !newc->v.sclass ||
+				     newc->v.sclass == c->v.sclass)) {
+					pr_err("SELinux:  dup genfs entry (%s,%s)\n",
+					       genfs->fstype, c->u.name);
+					goto out;
+				}
+				len = strlen(newc->u.name);
+				len2 = strlen(c->u.name);
+				if (len > len2)
+					break;
+			}
+
+			newc->next = c;
+			if (l)
+				l->next = newc;
+			else
+				genfs->head = newc;
+			newc = NULL;
+		}
+	}
+	rc = 0;
+out:
+	if (newgenfs) {
+		kfree(newgenfs->fstype);
+		kfree(newgenfs);
+	}
+	ocontext_destroy(newc, OCON_FSUSE);
+
+	if (rc)
+		pr_err("SELinux:  invalid genfs\n");
+
+	return rc;
+}
+
+static int ocontext_read(struct policydb *p,
+			 const struct policydb_compat_info *info, struct policy_file *fp)
+{
+	int rc;
+	unsigned int i;
+	u32 j, nel, len, val;
+	__be64 prefixbuf[1];
+	__le32 buf[3];
+	struct ocontext *l, *c;
+	u32 nodebuf[8];
+
+	for (i = 0; i < info->ocon_num; i++) {
+		rc = next_entry(buf, fp, sizeof(u32));
+		if (rc)
+			goto out;
+		nel = le32_to_cpu(buf[0]);
+
+		l = NULL;
+		for (j = 0; j < nel; j++) {
+			rc = -ENOMEM;
+			c = kzalloc_obj(*c);
+			if (!c)
+				goto out;
+			if (l)
+				l->next = c;
+			else
+				p->ocontexts[i] = c;
+			l = c;
+
+			switch (i) {
+			case OCON_ISID:
+				rc = next_entry(buf, fp, sizeof(u32));
+				if (rc)
+					goto out;
+
+				c->sid[0] = le32_to_cpu(buf[0]);
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			case OCON_FS:
+			case OCON_NETIF:
+				rc = next_entry(buf, fp, sizeof(u32));
+				if (rc)
+					goto out;
+				len = le32_to_cpu(buf[0]);
+
+				rc = str_read(&c->u.name, GFP_KERNEL, fp, len);
+				if (rc)
+					goto out;
+
+				if (i == OCON_FS)
+					pr_warn("SELinux:  void and deprecated fs ocon %s\n",
+						c->u.name);
+
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				rc = context_read_and_validate(&c->context[1],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			case OCON_PORT:
+				rc = next_entry(buf, fp, sizeof(u32) * 3);
+				if (rc)
+					goto out;
+
+				rc = -EINVAL;
+				val = le32_to_cpu(buf[0]);
+				if (val > U8_MAX)
+					goto out;
+				c->u.port.protocol = val;
+				val = le32_to_cpu(buf[1]);
+				if (val > U16_MAX)
+					goto out;
+				c->u.port.low_port = val;
+				val = le32_to_cpu(buf[2]);
+				if (val > U16_MAX)
+					goto out;
+				c->u.port.high_port = val;
+				if (c->u.port.low_port == 0 ||
+				    c->u.port.low_port > c->u.port.high_port)
+					goto out;
+
+				rc = context_read_and_validate(&c->context[0], p, fp);
+				if (rc)
+					goto out;
+				break;
+			case OCON_NODE:
+				rc = next_entry(nodebuf, fp, sizeof(u32) * 2);
+				if (rc)
+					goto out;
+				c->u.node.addr = nodebuf[0]; /* network order */
+				c->u.node.mask = nodebuf[1]; /* network order */
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			case OCON_FSUSE:
+				rc = next_entry(buf, fp, sizeof(u32) * 2);
+				if (rc)
+					goto out;
+
+				rc = -EINVAL;
+				c->v.behavior = le32_to_cpu(buf[0]);
+				/* Determined at runtime, not in policy DB. */
+				if (c->v.behavior == SECURITY_FS_USE_MNTPOINT)
+					goto out;
+				if (c->v.behavior > SECURITY_FS_USE_MAX)
+					goto out;
+
+				len = le32_to_cpu(buf[1]);
+				rc = str_read(&c->u.name, GFP_KERNEL, fp, len);
+				if (rc)
+					goto out;
+
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			case OCON_NODE6: {
+				int k;
+
+				rc = next_entry(nodebuf, fp, sizeof(u32) * 8);
+				if (rc)
+					goto out;
+				for (k = 0; k < 4; k++)
+					c->u.node6.addr[k] = nodebuf[k];
+				for (k = 0; k < 4; k++)
+					c->u.node6.mask[k] = nodebuf[k + 4];
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			}
+			case OCON_IBPKEY: {
+				u32 pkey_lo, pkey_hi;
+
+				rc = next_entry(prefixbuf, fp, sizeof(u64));
+				if (rc)
+					goto out;
+
+				/* we need to have subnet_prefix in CPU order */
+				c->u.ibpkey.subnet_prefix =
+					be64_to_cpu(prefixbuf[0]);
+
+				rc = next_entry(buf, fp, sizeof(u32) * 2);
+				if (rc)
+					goto out;
+
+				pkey_lo = le32_to_cpu(buf[0]);
+				pkey_hi = le32_to_cpu(buf[1]);
+
+				if (pkey_lo > U16_MAX || pkey_hi > U16_MAX) {
+					rc = -EINVAL;
+					goto out;
+				}
+
+				c->u.ibpkey.low_pkey = pkey_lo;
+				c->u.ibpkey.high_pkey = pkey_hi;
+
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			}
+			case OCON_IBENDPORT: {
+				u32 port;
+
+				rc = next_entry(buf, fp, sizeof(u32) * 2);
+				if (rc)
+					goto out;
+				len = le32_to_cpu(buf[0]);
+
+				rc = str_read(&c->u.ibendport.dev_name,
+					      GFP_KERNEL, fp, len);
+				if (rc)
+					goto out;
+
+				port = le32_to_cpu(buf[1]);
+				if (port > U8_MAX || port == 0) {
+					rc = -EINVAL;
+					goto out;
+				}
+
+				c->u.ibendport.port = port;
+
+				rc = context_read_and_validate(&c->context[0],
+							       p, fp);
+				if (rc)
+					goto out;
+				break;
+			} /* end case */
+			} /* end switch */
+		}
+	}
+	rc = 0;
+out:
+	if (rc)
+		pr_err("SELinux:  invalid ocon\n");
+	return rc;
+}
+
+/*
+ * Read the configuration data from a policy database binary
+ * representation file into a policy database structure.
+ */
+int policydb_read(struct policydb *p, struct policy_file *fp)
+{
+	struct role_allow *ra, *lra;
+	struct role_trans_key *rtk = NULL;
+	struct role_trans_datum *rtd = NULL;
+	int rc;
+	__le32 buf[4];
+	u32 i, j, len, nprim, nel, perm, val;
+
+	char *policydb_str;
+	const struct policydb_compat_info *info;
+
+	policydb_init(p);
+
+	/* Read the magic number and string length. */
+	rc = next_entry(buf, fp, sizeof(u32) * 2);
+	if (rc)
+		goto bad;
+
+	rc = -EINVAL;
+	if (le32_to_cpu(buf[0]) != POLICYDB_MAGIC) {
+		pr_err("SELinux:  policydb magic number 0x%x does "
+		       "not match expected magic number 0x%x\n",
+		       le32_to_cpu(buf[0]), POLICYDB_MAGIC);
+		goto bad;
+	}
+
+	rc = -EINVAL;
+	len = le32_to_cpu(buf[1]);
+	if (len != strlen(POLICYDB_STRING)) {
+		pr_err("SELinux:  policydb string length %d does not "
+		       "match expected length %zu\n",
+		       len, strlen(POLICYDB_STRING));
+		goto bad;
+	}
+
+	rc = str_read(&policydb_str, GFP_KERNEL, fp, len);
+	if (rc) {
+		if (rc == -ENOMEM) {
+			pr_err("SELinux:  unable to allocate memory for policydb string of length %d\n",
+			       len);
+		} else {
+			pr_err("SELinux:  truncated policydb string identifier\n");
+		}
+		goto bad;
+	}
+
+	rc = -EINVAL;
+	if (strcmp(policydb_str, POLICYDB_STRING)) {
+		pr_err("SELinux:  policydb string %s does not match "
+		       "my string %s\n",
+		       policydb_str, POLICYDB_STRING);
+		kfree(policydb_str);
+		goto bad;
+	}
+	/* Done with policydb_str. */
+	kfree(policydb_str);
+	policydb_str = NULL;
+
+	/* Read the version and table sizes. */
+	rc = next_entry(buf, fp, sizeof(u32) * 4);
+	if (rc)
+		goto bad;
+
+	rc = -EINVAL;
+	p->policyvers = le32_to_cpu(buf[0]);
+	if (p->policyvers < POLICYDB_VERSION_MIN ||
+	    p->policyvers > POLICYDB_VERSION_MAX) {
+		pr_err("SELinux:  policydb version %d does not match "
+		       "my version range %d-%d\n",
+		       le32_to_cpu(buf[0]), POLICYDB_VERSION_MIN,
+		       POLICYDB_VERSION_MAX);
+		goto bad;
+	}
+
+	if ((le32_to_cpu(buf[1]) & POLICYDB_CONFIG_MLS)) {
+		p->mls_enabled = 1;
+
+		rc = -EINVAL;
+		if (p->policyvers < POLICYDB_VERSION_MLS) {
+			pr_err("SELinux: security policydb version %d "
+			       "(MLS) not backwards compatible\n",
+			       p->policyvers);
+			goto bad;
+		}
+	}
+	p->reject_unknown = !!(le32_to_cpu(buf[1]) & REJECT_UNKNOWN);
+	p->allow_unknown = !!(le32_to_cpu(buf[1]) & ALLOW_UNKNOWN);
+
+	if (p->policyvers >= POLICYDB_VERSION_POLCAP) {
+		rc = ebitmap_read(&p->policycaps, fp);
+		if (rc)
+			goto bad;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) {
+		rc = ebitmap_read(&p->permissive_map, fp);
+		if (rc)
+			goto bad;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_NEVERAUDIT) {
+		rc = ebitmap_read(&p->neveraudit_map, fp);
+		if (rc)
+			goto bad;
+	}
+
+	rc = -EINVAL;
+	info = policydb_lookup_compat(p->policyvers);
+	if (!info) {
+		pr_err("SELinux:  unable to find policy compat info "
+		       "for version %d\n",
+		       p->policyvers);
+		goto bad;
+	}
+
+	rc = -EINVAL;
+	if (le32_to_cpu(buf[2]) != info->sym_num ||
+	    le32_to_cpu(buf[3]) != info->ocon_num) {
+		pr_err("SELinux:  policydb table sizes (%d,%d) do "
+		       "not match mine (%d,%d)\n",
+		       le32_to_cpu(buf[2]), le32_to_cpu(buf[3]), info->sym_num,
+		       info->ocon_num);
+		goto bad;
+	}
+
+	for (i = 0; i < info->sym_num; i++) {
+		rc = next_entry(buf, fp, sizeof(u32) * 2);
+		if (rc)
+			goto bad;
+		nprim = le32_to_cpu(buf[0]);
+		nel = le32_to_cpu(buf[1]);
+
+		/* every read_f() implementation reads at least 128 bytes
+		 * for any valid entry
+		 */
+		rc = size_check(4 * sizeof(u32), nel, fp);
+		if (rc)
+			goto out;
+
+		rc = symtab_init(&p->symtab[i], nel);
+		if (rc)
+			goto out;
+
+		if (i == SYM_ROLES) {
+			rc = roles_init(p);
+			if (rc)
+				goto out;
+		}
+
+		for (j = 0; j < nel; j++) {
+			rc = read_f[i](p, &p->symtab[i], fp);
+			if (rc)
+				goto bad;
+		}
+
+		p->symtab[i].nprim = nprim;
+	}
+
+	rc = policydb_index(p);
+	if (rc)
+		goto bad;
+
+	rc = -EINVAL;
+	p->process_class = string_to_security_class(p, "process");
+	if (!p->process_class) {
+		pr_err("SELinux: process class is required, not defined in policy\n");
+		goto bad;
+	}
+
+	rc = avtab_read(&p->te_avtab, fp, p);
+	if (rc)
+		goto bad;
+
+	avtab_hash_eval(&p->te_avtab, "rules");
+
+	if (p->policyvers >= POLICYDB_VERSION_BOOL) {
+		rc = cond_read_list(p, fp);
+		if (rc)
+			goto bad;
+	}
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		goto bad;
+	nel = le32_to_cpu(buf[0]);
+
+	/* we read at least 96 bytes for any valid role-transition */
+	rc = size_check(3 * sizeof(u32), nel, fp);
+	if (rc)
+		goto bad;
+
+	rc = hashtab_init(&p->role_tr, nel);
+	if (rc)
+		goto bad;
+	for (i = 0; i < nel; i++) {
+		rc = -ENOMEM;
+		rtk = kmalloc_obj(*rtk);
+		if (!rtk)
+			goto bad;
+
+		rc = -ENOMEM;
+		rtd = kmalloc_obj(*rtd);
+		if (!rtd)
+			goto bad;
+
+		rc = next_entry(buf, fp, sizeof(u32) * 3);
+		if (rc)
+			goto bad;
+
+		rtk->role = le32_to_cpu(buf[0]);
+		rtk->type = le32_to_cpu(buf[1]);
+		rtd->new_role = le32_to_cpu(buf[2]);
+		if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) {
+			rc = next_entry(buf, fp, sizeof(u32));
+			if (rc)
+				goto bad;
+			rc = -EINVAL;
+			val = le32_to_cpu(buf[0]);
+			if (val > U16_MAX)
+				goto bad;
+			rtk->tclass = val;
+		} else
+			rtk->tclass = p->process_class;
+
+		rc = -EINVAL;
+		if (!policydb_role_isvalid(p, rtk->role) ||
+		    !policydb_type_isvalid(p, rtk->type) ||
+		    !policydb_class_isvalid(p, rtk->tclass) ||
+		    !policydb_role_isvalid(p, rtd->new_role))
+			goto bad;
+
+		rc = hashtab_insert(&p->role_tr, rtk, rtd, roletr_key_params);
+		if (rc)
+			goto bad;
+
+		rtk = NULL;
+		rtd = NULL;
+	}
+
+	hash_eval(&p->role_tr, "roletr", NULL);
+
+	rc = next_entry(buf, fp, sizeof(u32));
+	if (rc)
+		goto bad;
+	nel = le32_to_cpu(buf[0]);
+	lra = NULL;
+	for (i = 0; i < nel; i++) {
+		rc = -ENOMEM;
+		ra = kzalloc_obj(*ra);
+		if (!ra)
+			goto bad;
+		if (lra)
+			lra->next = ra;
+		else
+			p->role_allow = ra;
+		rc = next_entry(buf, fp, sizeof(u32) * 2);
+		if (rc)
+			goto bad;
+
+		rc = -EINVAL;
+		ra->role = le32_to_cpu(buf[0]);
+		ra->new_role = le32_to_cpu(buf[1]);
+		if (!policydb_role_isvalid(p, ra->role) ||
+		    !policydb_role_isvalid(p, ra->new_role))
+			goto bad;
+		lra = ra;
+	}
+
+	rc = filename_trans_read(p, fp);
+	if (rc)
+		goto bad;
+
+	rc = -EINVAL;
+	perm = string_to_av_perm(p, p->process_class, "transition");
+	if (!perm) {
+		pr_err("SELinux: process transition permission is required, not defined in policy\n");
+		goto bad;
+	}
+	p->process_trans_perms = perm;
+	perm = string_to_av_perm(p, p->process_class, "dyntransition");
+	if (!perm) {
+		pr_err("SELinux: process dyntransition permission is required, not defined in policy\n");
+		goto bad;
+	}
+	p->process_trans_perms |= perm;
+
+	rc = ocontext_read(p, info, fp);
+	if (rc)
+		goto bad;
+
+	rc = genfs_read(p, fp);
+	if (rc)
+		goto bad;
+
+	rc = range_read(p, fp);
+	if (rc)
+		goto bad;
+
+	rc = -ENOMEM;
+	p->type_attr_map_array = kvzalloc_objs(*p->type_attr_map_array,
+					       p->p_types.nprim);
+	if (!p->type_attr_map_array)
+		goto bad;
+
+	/* just in case ebitmap_init() becomes more than just a memset(0): */
+	for (i = 0; i < p->p_types.nprim; i++)
+		ebitmap_init(&p->type_attr_map_array[i]);
+
+	for (i = 0; i < p->p_types.nprim; i++) {
+		struct ebitmap *e = &p->type_attr_map_array[i];
+
+		if (p->policyvers >= POLICYDB_VERSION_AVTAB) {
+			rc = ebitmap_read(e, fp);
+			if (rc)
+				goto bad;
+		}
+
+		rc = -EINVAL;
+		if (ebitmap_get_highest_set_bit(e) >= p->p_types.nprim)
+			goto bad;
+
+		/* add the type itself as the degenerate case */
+		rc = ebitmap_set_bit(e, i, 1);
+		if (rc)
+			goto bad;
+	}
+
+	rc = policydb_bounds_sanity_check(p);
+	if (rc)
+		goto bad;
+
+	rc = 0;
+out:
+	return rc;
+bad:
+	kfree(rtk);
+	kfree(rtd);
+	policydb_destroy(p);
+	goto out;
+}
+
+/*
+ * Write a MLS level structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_level(struct mls_level *l, struct policy_file *fp)
+{
+	__le32 buf[1];
+	int rc;
+
+	buf[0] = cpu_to_le32(l->sens);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&l->cat, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/*
+ * Write a MLS range structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_range_helper(struct mls_range *r, struct policy_file *fp)
+{
+	__le32 buf[3];
+	size_t items;
+	int rc, eq;
+
+	eq = mls_level_eq(&r->level[1], &r->level[0]);
+
+	if (eq)
+		items = 2;
+	else
+		items = 3;
+	buf[0] = cpu_to_le32(items - 1);
+	buf[1] = cpu_to_le32(r->level[0].sens);
+	if (!eq)
+		buf[2] = cpu_to_le32(r->level[1].sens);
+
+	BUG_ON(items > ARRAY_SIZE(buf));
+
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&r->level[0].cat, fp);
+	if (rc)
+		return rc;
+	if (!eq) {
+		rc = ebitmap_write(&r->level[1].cat, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int sens_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct level_datum *levdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[2];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(levdatum->isalias);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_level(&levdatum->level, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int cat_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct cat_datum *catdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[3];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(catdatum->value);
+	buf[2] = cpu_to_le32(catdatum->isalias);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int role_trans_write_one(void *key, void *datum, void *ptr)
+{
+	struct role_trans_key *rtk = key;
+	struct role_trans_datum *rtd = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	struct policydb *p = pd->p;
+	__le32 buf[3];
+	int rc;
+
+	buf[0] = cpu_to_le32(rtk->role);
+	buf[1] = cpu_to_le32(rtk->type);
+	buf[2] = cpu_to_le32(rtd->new_role);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+	if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) {
+		buf[0] = cpu_to_le32(rtk->tclass);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static int role_trans_write(struct policydb *p, struct policy_file *fp)
+{
+	struct policy_data pd = { .p = p, .fp = fp };
+	__le32 buf[1];
+	int rc;
+
+	buf[0] = cpu_to_le32(p->role_tr.nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	return hashtab_map(&p->role_tr, role_trans_write_one, &pd);
+}
+
+static int role_allow_write(struct role_allow *r, struct policy_file *fp)
+{
+	struct role_allow *ra;
+	__le32 buf[2];
+	size_t nel;
+	int rc;
+
+	nel = 0;
+	for (ra = r; ra; ra = ra->next)
+		nel++;
+	buf[0] = cpu_to_le32(nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	for (ra = r; ra; ra = ra->next) {
+		buf[0] = cpu_to_le32(ra->role);
+		buf[1] = cpu_to_le32(ra->new_role);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+/*
+ * Write a security context structure
+ * to a policydb binary representation file.
+ */
+static int context_write(struct policydb *p, struct context *c, struct policy_file *fp)
+{
+	int rc;
+	__le32 buf[3];
+
+	buf[0] = cpu_to_le32(c->user);
+	buf[1] = cpu_to_le32(c->role);
+	buf[2] = cpu_to_le32(c->type);
+
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_range_helper(&c->range, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/*
+ * The following *_write functions are used to
+ * write the symbol data to a policy database
+ * binary representation file.
+ */
+
+static int perm_write(void *vkey, void *datum, void *fp)
+{
+	char *key = vkey;
+	struct perm_datum *perdatum = datum;
+	__le32 buf[2];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(perdatum->value);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int common_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct common_datum *comdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[4];
+	size_t len;
+	int rc;
+
+	len = strlen(key);
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(comdatum->value);
+	buf[2] = cpu_to_le32(comdatum->permissions.nprim);
+	buf[3] = cpu_to_le32(comdatum->permissions.table.nel);
+	rc = put_entry(buf, sizeof(u32), 4, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = hashtab_map(&comdatum->permissions.table, perm_write, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int type_set_write(struct type_set *t, struct policy_file *fp)
+{
+	int rc;
+	__le32 buf[1];
+
+	if (ebitmap_write(&t->types, fp))
+		return -EINVAL;
+	if (ebitmap_write(&t->negset, fp))
+		return -EINVAL;
+
+	buf[0] = cpu_to_le32(t->flags);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int write_cons_helper(struct policydb *p, struct constraint_node *node,
+			     struct policy_file *fp)
+{
+	struct constraint_node *c;
+	struct constraint_expr *e;
+	__le32 buf[3];
+	u32 nel;
+	int rc;
+
+	for (c = node; c; c = c->next) {
+		nel = 0;
+		for (e = c->expr; e; e = e->next)
+			nel++;
+		buf[0] = cpu_to_le32(c->permissions);
+		buf[1] = cpu_to_le32(nel);
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+		for (e = c->expr; e; e = e->next) {
+			buf[0] = cpu_to_le32(e->expr_type);
+			buf[1] = cpu_to_le32(e->attr);
+			buf[2] = cpu_to_le32(e->op);
+			rc = put_entry(buf, sizeof(u32), 3, fp);
+			if (rc)
+				return rc;
+
+			switch (e->expr_type) {
+			case CEXPR_NAMES:
+				rc = ebitmap_write(&e->names, fp);
+				if (rc)
+					return rc;
+				if (p->policyvers >=
+				    POLICYDB_VERSION_CONSTRAINT_NAMES) {
+					rc = type_set_write(e->type_names, fp);
+					if (rc)
+						return rc;
+				}
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int class_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct class_datum *cladatum = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	struct policydb *p = pd->p;
+	struct constraint_node *c;
+	__le32 buf[6];
+	u32 ncons;
+	size_t len, len2;
+	int rc;
+
+	len = strlen(key);
+	if (cladatum->comkey)
+		len2 = strlen(cladatum->comkey);
+	else
+		len2 = 0;
+
+	ncons = 0;
+	for (c = cladatum->constraints; c; c = c->next)
+		ncons++;
+
+	buf[0] = cpu_to_le32(len);
+	buf[1] = cpu_to_le32(len2);
+	buf[2] = cpu_to_le32(cladatum->value);
+	buf[3] = cpu_to_le32(cladatum->permissions.nprim);
+	buf[4] = cpu_to_le32(cladatum->permissions.table.nel);
+	buf[5] = cpu_to_le32(ncons);
+	rc = put_entry(buf, sizeof(u32), 6, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	if (cladatum->comkey) {
+		rc = put_entry(cladatum->comkey, 1, len2, fp);
+		if (rc)
+			return rc;
+	}
+
+	rc = hashtab_map(&cladatum->permissions.table, perm_write, fp);
+	if (rc)
+		return rc;
+
+	rc = write_cons_helper(p, cladatum->constraints, fp);
+	if (rc)
+		return rc;
+
+	/* write out the validatetrans rule */
+	ncons = 0;
+	for (c = cladatum->validatetrans; c; c = c->next)
+		ncons++;
+
+	buf[0] = cpu_to_le32(ncons);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	rc = write_cons_helper(p, cladatum->validatetrans, fp);
+	if (rc)
+		return rc;
+
+	if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) {
+		buf[0] = cpu_to_le32(cladatum->default_user);
+		buf[1] = cpu_to_le32(cladatum->default_role);
+		buf[2] = cpu_to_le32(cladatum->default_range);
+
+		rc = put_entry(buf, sizeof(uint32_t), 3, fp);
+		if (rc)
+			return rc;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) {
+		buf[0] = cpu_to_le32(cladatum->default_type);
+		rc = put_entry(buf, sizeof(uint32_t), 1, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int role_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct role_datum *role = datum;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	struct policydb *p = pd->p;
+	__le32 buf[3];
+	size_t items, len;
+	int rc;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(role->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		buf[items++] = cpu_to_le32(role->bounds);
+
+	BUG_ON(items > ARRAY_SIZE(buf));
+
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&role->dominates, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&role->types, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int type_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct type_datum *typdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policydb *p = pd->p;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[4];
+	int rc;
+	size_t items, len;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(typdatum->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) {
+		u32 properties = 0;
+
+		if (typdatum->primary)
+			properties |= TYPEDATUM_PROPERTY_PRIMARY;
+
+		if (typdatum->attribute)
+			properties |= TYPEDATUM_PROPERTY_ATTRIBUTE;
+
+		buf[items++] = cpu_to_le32(properties);
+		buf[items++] = cpu_to_le32(typdatum->bounds);
+	} else {
+		buf[items++] = cpu_to_le32(typdatum->primary);
+	}
+	BUG_ON(items > ARRAY_SIZE(buf));
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int user_write(void *vkey, void *datum, void *ptr)
+{
+	char *key = vkey;
+	struct user_datum *usrdatum = datum;
+	struct policy_data *pd = ptr;
+	struct policydb *p = pd->p;
+	struct policy_file *fp = pd->fp;
+	__le32 buf[3];
+	size_t items, len;
+	int rc;
+
+	len = strlen(key);
+	items = 0;
+	buf[items++] = cpu_to_le32(len);
+	buf[items++] = cpu_to_le32(usrdatum->value);
+	if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+		buf[items++] = cpu_to_le32(usrdatum->bounds);
+	BUG_ON(items > ARRAY_SIZE(buf));
+	rc = put_entry(buf, sizeof(u32), items, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(key, 1, len, fp);
+	if (rc)
+		return rc;
+
+	rc = ebitmap_write(&usrdatum->roles, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_range_helper(&usrdatum->range, fp);
+	if (rc)
+		return rc;
+
+	rc = mls_write_level(&usrdatum->dfltlevel, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+/* clang-format off */
+static int (*const write_f[SYM_NUM])(void *key, void *datum, void *datap) = {
+	common_write,
+	class_write,
+	role_write,
+	type_write,
+	user_write,
+	cond_write_bool,
+	sens_write,
+	cat_write,
+};
+/* clang-format on */
+
+static int ocontext_write(struct policydb *p,
+			  const struct policydb_compat_info *info,
+			  struct policy_file *fp)
+{
+	unsigned int i, j;
+	int rc;
+	size_t nel, len;
+	__be64 prefixbuf[1];
+	__le32 buf[3];
+	u32 nodebuf[8];
+	struct ocontext *c;
+	for (i = 0; i < info->ocon_num; i++) {
+		nel = 0;
+		for (c = p->ocontexts[i]; c; c = c->next)
+			nel++;
+		buf[0] = cpu_to_le32(nel);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		for (c = p->ocontexts[i]; c; c = c->next) {
+			switch (i) {
+			case OCON_ISID:
+				buf[0] = cpu_to_le32(c->sid[0]);
+				rc = put_entry(buf, sizeof(u32), 1, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_FS:
+			case OCON_NETIF:
+				len = strlen(c->u.name);
+				buf[0] = cpu_to_le32(len);
+				rc = put_entry(buf, sizeof(u32), 1, fp);
+				if (rc)
+					return rc;
+				rc = put_entry(c->u.name, 1, len, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[1], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_PORT:
+				buf[0] = cpu_to_le32(c->u.port.protocol);
+				buf[1] = cpu_to_le32(c->u.port.low_port);
+				buf[2] = cpu_to_le32(c->u.port.high_port);
+				rc = put_entry(buf, sizeof(u32), 3, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_NODE:
+				nodebuf[0] = c->u.node.addr; /* network order */
+				nodebuf[1] = c->u.node.mask; /* network order */
+				rc = put_entry(nodebuf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_FSUSE:
+				buf[0] = cpu_to_le32(c->v.behavior);
+				len = strlen(c->u.name);
+				buf[1] = cpu_to_le32(len);
+				rc = put_entry(buf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = put_entry(c->u.name, 1, len, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_NODE6:
+				for (j = 0; j < 4; j++)
+					nodebuf[j] =
+						c->u.node6.addr
+							[j]; /* network order */
+				for (j = 0; j < 4; j++)
+					nodebuf[j + 4] =
+						c->u.node6.mask
+							[j]; /* network order */
+				rc = put_entry(nodebuf, sizeof(u32), 8, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_IBPKEY:
+				/* subnet_prefix is in CPU order */
+				prefixbuf[0] =
+					cpu_to_be64(c->u.ibpkey.subnet_prefix);
+
+				rc = put_entry(prefixbuf, sizeof(u64), 1, fp);
+				if (rc)
+					return rc;
+
+				buf[0] = cpu_to_le32(c->u.ibpkey.low_pkey);
+				buf[1] = cpu_to_le32(c->u.ibpkey.high_pkey);
+
+				rc = put_entry(buf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			case OCON_IBENDPORT:
+				len = strlen(c->u.ibendport.dev_name);
+				buf[0] = cpu_to_le32(len);
+				buf[1] = cpu_to_le32(c->u.ibendport.port);
+				rc = put_entry(buf, sizeof(u32), 2, fp);
+				if (rc)
+					return rc;
+				rc = put_entry(c->u.ibendport.dev_name, 1, len,
+					       fp);
+				if (rc)
+					return rc;
+				rc = context_write(p, &c->context[0], fp);
+				if (rc)
+					return rc;
+				break;
+			}
+		}
+	}
+	return 0;
+}
+
+static int genfs_write(struct policydb *p, struct policy_file *fp)
+{
+	struct genfs *genfs;
+	struct ocontext *c;
+	size_t len;
+	__le32 buf[1];
+	int rc;
+
+	len = 0;
+	for (genfs = p->genfs; genfs; genfs = genfs->next)
+		len++;
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+	for (genfs = p->genfs; genfs; genfs = genfs->next) {
+		len = strlen(genfs->fstype);
+		buf[0] = cpu_to_le32(len);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		rc = put_entry(genfs->fstype, 1, len, fp);
+		if (rc)
+			return rc;
+		len = 0;
+		for (c = genfs->head; c; c = c->next)
+			len++;
+		buf[0] = cpu_to_le32(len);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+		for (c = genfs->head; c; c = c->next) {
+			len = strlen(c->u.name);
+			buf[0] = cpu_to_le32(len);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+			rc = put_entry(c->u.name, 1, len, fp);
+			if (rc)
+				return rc;
+			buf[0] = cpu_to_le32(c->v.sclass);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+			rc = context_write(p, &c->context[0], fp);
+			if (rc)
+				return rc;
+		}
+	}
+	return 0;
+}
+
+static int range_write_helper(void *key, void *data, void *ptr)
+{
+	__le32 buf[2];
+	struct range_trans *rt = key;
+	struct mls_range *r = data;
+	struct policy_data *pd = ptr;
+	struct policy_file *fp = pd->fp;
+	struct policydb *p = pd->p;
+	int rc;
+
+	buf[0] = cpu_to_le32(rt->source_type);
+	buf[1] = cpu_to_le32(rt->target_type);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+	if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) {
+		buf[0] = cpu_to_le32(rt->target_class);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+	}
+	rc = mls_write_range_helper(r, fp);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int range_write(struct policydb *p, struct policy_file *fp)
+{
+	__le32 buf[1];
+	int rc;
+	struct policy_data pd;
+
+	pd.p = p;
+	pd.fp = fp;
+
+	buf[0] = cpu_to_le32(p->range_tr.nel);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	/* actually write all of the entries */
+	rc = hashtab_map(&p->range_tr, range_write_helper, &pd);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
+static int filename_write_helper_compat(void *key, void *data, void *ptr)
+{
+	struct filename_trans_key *ft = key;
+	struct filename_trans_datum *datum = data;
+	struct ebitmap_node *node;
+	struct policy_file *fp = ptr;
+	__le32 buf[4];
+	int rc;
+	u32 bit, len = strlen(ft->name);
+
+	do {
+		ebitmap_for_each_positive_bit(&datum->stypes, node, bit)
+		{
+			buf[0] = cpu_to_le32(len);
+			rc = put_entry(buf, sizeof(u32), 1, fp);
+			if (rc)
+				return rc;
+
+			rc = put_entry(ft->name, sizeof(char), len, fp);
+			if (rc)
+				return rc;
+
+			buf[0] = cpu_to_le32(bit + 1);
+			buf[1] = cpu_to_le32(ft->ttype);
+			buf[2] = cpu_to_le32(ft->tclass);
+			buf[3] = cpu_to_le32(datum->otype);
+
+			rc = put_entry(buf, sizeof(u32), 4, fp);
+			if (rc)
+				return rc;
+		}
+
+		datum = datum->next;
+	} while (unlikely(datum));
+
+	return 0;
+}
+
+static int filename_write_helper(void *key, void *data, void *ptr)
+{
+	struct filename_trans_key *ft = key;
+	struct filename_trans_datum *datum;
+	struct policy_file *fp = ptr;
+	__le32 buf[3];
+	int rc;
+	u32 ndatum, len = strlen(ft->name);
+
+	buf[0] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 1, fp);
+	if (rc)
+		return rc;
+
+	rc = put_entry(ft->name, sizeof(char), len, fp);
+	if (rc)
+		return rc;
+
+	ndatum = 0;
+	datum = data;
+	do {
+		ndatum++;
+		datum = datum->next;
+	} while (unlikely(datum));
+
+	buf[0] = cpu_to_le32(ft->ttype);
+	buf[1] = cpu_to_le32(ft->tclass);
+	buf[2] = cpu_to_le32(ndatum);
+	rc = put_entry(buf, sizeof(u32), 3, fp);
+	if (rc)
+		return rc;
+
+	datum = data;
+	do {
+		rc = ebitmap_write(&datum->stypes, fp);
+		if (rc)
+			return rc;
+
+		buf[0] = cpu_to_le32(datum->otype);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+
+		datum = datum->next;
+	} while (unlikely(datum));
+
+	return 0;
+}
+
+static int filename_trans_write(struct policydb *p, struct policy_file *fp)
+{
+	__le32 buf[1];
+	int rc;
+
+	if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS)
+		return 0;
+
+	if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) {
+		buf[0] = cpu_to_le32(p->compat_filename_trans_count);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+
+		rc = hashtab_map(&p->filename_trans,
+				 filename_write_helper_compat, fp);
+	} else {
+		buf[0] = cpu_to_le32(p->filename_trans.nel);
+		rc = put_entry(buf, sizeof(u32), 1, fp);
+		if (rc)
+			return rc;
+
+		rc = hashtab_map(&p->filename_trans, filename_write_helper, fp);
+	}
+	return rc;
+}
+
+/*
+ * Write the configuration data in a policy database
+ * structure to a policy database binary representation
+ * file.
+ */
+int policydb_write(struct policydb *p, struct policy_file *fp)
+{
+	unsigned int num_syms;
+	int rc;
+	__le32 buf[4];
+	u32 config, i;
+	size_t len;
+	const struct policydb_compat_info *info;
+
+	/*
+	 * refuse to write policy older than compressed avtab
+	 * to simplify the writer.  There are other tests dropped
+	 * since we assume this throughout the writer code.  Be
+	 * careful if you ever try to remove this restriction
+	 */
+	if (p->policyvers < POLICYDB_VERSION_AVTAB) {
+		pr_err("SELinux: refusing to write policy version %d."
+		       "  Because it is less than version %d\n",
+		       p->policyvers, POLICYDB_VERSION_AVTAB);
+		return -EINVAL;
+	}
+
+	config = 0;
+	if (p->mls_enabled)
+		config |= POLICYDB_CONFIG_MLS;
+
+	if (p->reject_unknown)
+		config |= REJECT_UNKNOWN;
+	if (p->allow_unknown)
+		config |= ALLOW_UNKNOWN;
+
+	/* Write the magic number and string identifiers. */
+	buf[0] = cpu_to_le32(POLICYDB_MAGIC);
+	len = strlen(POLICYDB_STRING);
+	buf[1] = cpu_to_le32(len);
+	rc = put_entry(buf, sizeof(u32), 2, fp);
+	if (rc)
+		return rc;
+	rc = put_entry(POLICYDB_STRING, 1, len, fp);
+	if (rc)
+		return rc;
+
+	/* Write the version, config, and table sizes. */
+	info = policydb_lookup_compat(p->policyvers);
+	if (!info) {
+		pr_err("SELinux: compatibility lookup failed for policy "
+		       "version %d\n",
+		       p->policyvers);
+		return -EINVAL;
+	}
+
+	buf[0] = cpu_to_le32(p->policyvers);
+	buf[1] = cpu_to_le32(config);
+	buf[2] = cpu_to_le32(info->sym_num);
+	buf[3] = cpu_to_le32(info->ocon_num);
+
+	rc = put_entry(buf, sizeof(u32), 4, fp);
+	if (rc)
+		return rc;
+
+	if (p->policyvers >= POLICYDB_VERSION_POLCAP) {
+		rc = ebitmap_write(&p->policycaps, fp);
+		if (rc)
+			return rc;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) {
+		rc = ebitmap_write(&p->permissive_map, fp);
+		if (rc)
+			return rc;
+	}
+
+	if (p->policyvers >= POLICYDB_VERSION_NEVERAUDIT) {
+		rc = ebitmap_write(&p->neveraudit_map, fp);
+		if (rc)
+			return rc;
+	}
+
+	num_syms = info->sym_num;
+	for (i = 0; i < num_syms; i++) {
+		struct policy_data pd;
+
+		pd.fp = fp;
+		pd.p = p;
+
+		buf[0] = cpu_to_le32(p->symtab[i].nprim);
+		buf[1] = cpu_to_le32(p->symtab[i].table.nel);
+
+		rc = put_entry(buf, sizeof(u32), 2, fp);
+		if (rc)
+			return rc;
+		rc = hashtab_map(&p->symtab[i].table, write_f[i], &pd);
+		if (rc)
+			return rc;
+	}
+
+	rc = avtab_write(p, &p->te_avtab, fp);
+	if (rc)
+		return rc;
+
+	rc = cond_write_list(p, fp);
+	if (rc)
+		return rc;
+
+	rc = role_trans_write(p, fp);
+	if (rc)
+		return rc;
+
+	rc = role_allow_write(p->role_allow, fp);
+	if (rc)
+		return rc;
+
+	rc = filename_trans_write(p, fp);
+	if (rc)
+		return rc;
+
+	rc = ocontext_write(p, info, fp);
+	if (rc)
+		return rc;
+
+	rc = genfs_write(p, fp);
+	if (rc)
+		return rc;
+
+	rc = range_write(p, fp);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < p->p_types.nprim; i++) {
+		struct ebitmap *e = &p->type_attr_map_array[i];
+
+		rc = ebitmap_write(e, fp);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
new file mode 100644
index 000000000..974180b2e
--- /dev/null
+++ b/security/selinux/ss/policydb.h
@@ -0,0 +1,428 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * A policy database (policydb) specifies the
+ * configuration data for the security policy.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+/*
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *          Support for enhanced MLS infrastructure.
+ *          Copyright (C) 2004-2005 Trusted Computer Solutions, Inc.
+ *
+ * Updated: Frank Mayer <mayerf@tresys.com> and
+ *          Karl MacMillan <kmacmillan@tresys.com>
+ *          Added conditional policy language extensions
+ *          Copyright (C) 2003-2004 Tresys Technology, LLC
+ */
+
+#ifndef _SS_POLICYDB_H_
+#define _SS_POLICYDB_H_
+
+#include "symtab.h"
+#include "avtab.h"
+#include "sidtab.h"
+#include "ebitmap.h"
+#include "mls_types.h"
+#include "context.h"
+#include "constraint.h"
+
+/*
+ * A datum type is defined for each kind of symbol
+ * in the configuration data:  individual permissions,
+ * common prefixes for access vectors, classes,
+ * users, roles, types, sensitivities, categories, etc.
+ */
+
+/* Permission attributes */
+struct perm_datum {
+	u32 value; /* permission bit + 1 */
+};
+
+/* Attributes of a common prefix for access vectors */
+struct common_datum {
+	u32 value; /* internal common value */
+	struct symtab permissions; /* common permissions */
+};
+
+/* Class attributes */
+struct class_datum {
+	u16 value; /* class value */
+	char *comkey; /* common name */
+	struct common_datum *comdatum; /* common datum */
+	struct symtab permissions; /* class-specific permission symbol table */
+	struct constraint_node *constraints; /* constraints on class perms */
+	struct constraint_node *validatetrans; /* special transition rules */
+/* Options how a new object user, role, and type should be decided */
+#define DEFAULT_SOURCE 1
+#define DEFAULT_TARGET 2
+	char default_user;
+	char default_role;
+	char default_type;
+/* Options how a new object range should be decided */
+#define DEFAULT_SOURCE_LOW	1
+#define DEFAULT_SOURCE_HIGH	2
+#define DEFAULT_SOURCE_LOW_HIGH 3
+#define DEFAULT_TARGET_LOW	4
+#define DEFAULT_TARGET_HIGH	5
+#define DEFAULT_TARGET_LOW_HIGH 6
+#define DEFAULT_GLBLUB		7
+	char default_range;
+};
+
+/* Role attributes */
+struct role_datum {
+	u32 value; /* internal role value */
+	u32 bounds; /* boundary of role, 0 for none */
+	struct ebitmap dominates; /* set of roles dominated by this role */
+	struct ebitmap types; /* set of authorized types for role */
+};
+
+struct role_trans_key {
+	u32 role; /* current role */
+	u32 type; /* program executable type, or new object type */
+	u16 tclass; /* process class, or new object class */
+};
+
+struct role_trans_datum {
+	u32 new_role; /* new role */
+};
+
+struct filename_trans_key {
+	u32 ttype; /* parent dir context */
+	u16 tclass; /* class of new object */
+	const char *name; /* last path component */
+};
+
+struct filename_trans_datum {
+	struct ebitmap stypes; /* bitmap of source types for this otype */
+	u32 otype; /* resulting type of new object */
+	struct filename_trans_datum *next; /* record for next otype*/
+};
+
+struct role_allow {
+	u32 role; /* current role */
+	u32 new_role; /* new role */
+	struct role_allow *next;
+};
+
+/* Type attributes */
+struct type_datum {
+	u32 value; /* internal type value */
+	u32 bounds; /* boundary of type, 0 for none */
+	/* internally unused, only forwarded via policydb_write() */
+	unsigned char primary; /* primary name? */
+	unsigned char attribute; /* attribute ?*/
+};
+
+/* User attributes */
+struct user_datum {
+	u32 value; /* internal user value */
+	u32 bounds; /* bounds of user, 0 for none */
+	struct ebitmap roles; /* set of authorized roles for user */
+	struct mls_range range; /* MLS range (min - max) for user */
+	struct mls_level dfltlevel; /* default login MLS level for user */
+};
+
+/* Sensitivity attributes */
+struct level_datum {
+	struct mls_level level; /* sensitivity and associated categories */
+	unsigned char isalias; /* is this sensitivity an alias for another? */
+};
+
+/* Category attributes */
+struct cat_datum {
+	u32 value; /* internal category bit + 1 */
+	unsigned char isalias; /* is this category an alias for another? */
+};
+
+struct range_trans {
+	u32 source_type;
+	u32 target_type;
+	u16 target_class;
+};
+
+/* Boolean data type */
+struct cond_bool_datum {
+	u32 value; /* internal type value */
+	int state;
+};
+
+struct cond_node;
+
+/*
+ * type set preserves data needed to determine constraint info from
+ * policy source. This is not used by the kernel policy but allows
+ * utilities such as audit2allow to determine constraint denials.
+ */
+struct type_set {
+	struct ebitmap types;
+	struct ebitmap negset;
+	u32 flags;
+};
+
+/*
+ * The configuration data includes security contexts for
+ * initial SIDs, unlabeled file systems, TCP and UDP port numbers,
+ * network interfaces, and nodes.  This structure stores the
+ * relevant data for one such entry.  Entries of the same kind
+ * (e.g. all initial SIDs) are linked together into a list.
+ */
+struct ocontext {
+	union {
+		char *name; /* name of initial SID, fs, netif, fstype, path */
+		struct {
+			u8 protocol;
+			u16 low_port;
+			u16 high_port;
+		} port; /* TCP or UDP port information */
+		struct {
+			u32 addr;
+			u32 mask;
+		} node; /* node information */
+		struct {
+			u32 addr[4];
+			u32 mask[4];
+		} node6; /* IPv6 node information */
+		struct {
+			u64 subnet_prefix;
+			u16 low_pkey;
+			u16 high_pkey;
+		} ibpkey;
+		struct {
+			char *dev_name;
+			u8 port;
+		} ibendport;
+	} u;
+	union {
+		u16 sclass; /* security class for genfs (can be 0 for wildcard) */
+		u32 behavior; /* labeling behavior for fs_use */
+	} v;
+	struct context context[2]; /* security context(s) */
+	u32 sid[2]; /* SID(s) */
+	struct ocontext *next;
+};
+
+struct genfs {
+	char *fstype;
+	struct ocontext *head;
+	struct genfs *next;
+};
+
+/* symbol table array indices */
+#define SYM_COMMONS 0
+#define SYM_CLASSES 1
+#define SYM_ROLES   2
+#define SYM_TYPES   3
+#define SYM_USERS   4
+#define SYM_BOOLS   5
+#define SYM_LEVELS  6
+#define SYM_CATS    7
+#define SYM_NUM	    8
+
+/* object context array indices */
+#define OCON_ISID      0 /* initial SIDs */
+#define OCON_FS	       1 /* unlabeled file systems (deprecated) */
+#define OCON_PORT      2 /* TCP and UDP port numbers */
+#define OCON_NETIF     3 /* network interfaces */
+#define OCON_NODE      4 /* nodes */
+#define OCON_FSUSE     5 /* fs_use */
+#define OCON_NODE6     6 /* IPv6 nodes */
+#define OCON_IBPKEY    7 /* Infiniband PKeys */
+#define OCON_IBENDPORT 8 /* Infiniband end ports */
+#define OCON_NUM       9
+
+/* The policy database */
+struct policydb {
+	int mls_enabled;
+
+	/* symbol tables */
+	struct symtab symtab[SYM_NUM];
+#define p_commons symtab[SYM_COMMONS]
+#define p_classes symtab[SYM_CLASSES]
+#define p_roles	  symtab[SYM_ROLES]
+#define p_types	  symtab[SYM_TYPES]
+#define p_users	  symtab[SYM_USERS]
+#define p_bools	  symtab[SYM_BOOLS]
+#define p_levels  symtab[SYM_LEVELS]
+#define p_cats	  symtab[SYM_CATS]
+
+	/* symbol names indexed by (value - 1) */
+	char **sym_val_to_name[SYM_NUM];
+
+	/* class, role, and user attributes indexed by (value - 1) */
+	struct class_datum **class_val_to_struct;
+	struct role_datum **role_val_to_struct;
+	struct user_datum **user_val_to_struct;
+	struct type_datum **type_val_to_struct;
+
+	/* type enforcement access vectors and transitions */
+	struct avtab te_avtab;
+
+	/* role transitions */
+	struct hashtab role_tr;
+
+	/* file transitions with the last path component */
+	/* quickly exclude lookups when parent ttype has no rules */
+	struct ebitmap filename_trans_ttypes;
+	/* actual set of filename_trans rules */
+	struct hashtab filename_trans;
+	/* only used if policyvers < POLICYDB_VERSION_COMP_FTRANS */
+	u32 compat_filename_trans_count;
+
+	/* bools indexed by (value - 1) */
+	struct cond_bool_datum **bool_val_to_struct;
+	/* type enforcement conditional access vectors and transitions */
+	struct avtab te_cond_avtab;
+	/* array indexing te_cond_avtab by conditional */
+	struct cond_node *cond_list;
+	u32 cond_list_len;
+
+	/* role allows */
+	struct role_allow *role_allow;
+
+	/* security contexts of initial SIDs, unlabeled file systems,
+	   TCP or UDP port numbers, network interfaces and nodes */
+	struct ocontext *ocontexts[OCON_NUM];
+
+	/* security contexts for files in filesystems that cannot support
+	   a persistent label mapping or use another
+	   fixed labeling behavior. */
+	struct genfs *genfs;
+
+	/* range transitions table (range_trans_key -> mls_range) */
+	struct hashtab range_tr;
+
+	/* type -> attribute reverse mapping */
+	struct ebitmap *type_attr_map_array;
+
+	struct ebitmap policycaps;
+
+	struct ebitmap permissive_map;
+
+	struct ebitmap neveraudit_map;
+
+	/* length of this policy when it was loaded */
+	size_t len;
+
+	unsigned int policyvers;
+
+	unsigned int reject_unknown : 1;
+	unsigned int allow_unknown : 1;
+
+	u16 process_class;
+	u32 process_trans_perms;
+} __randomize_layout;
+
+struct policy_file {
+	char *data;
+	size_t len;
+};
+
+extern void policydb_destroy(struct policydb *p);
+extern int policydb_load_isids(struct policydb *p, struct sidtab *s);
+extern bool policydb_context_isvalid(const struct policydb *p,
+				     const struct context *c);
+extern bool policydb_class_isvalid(const struct policydb *p, u16 class);
+extern bool policydb_type_isvalid(const struct policydb *p, u32 type);
+extern bool policydb_simpletype_isvalid(const struct policydb *p, u32 type);
+extern bool policydb_role_isvalid(const struct policydb *p, u32 role);
+extern bool policydb_user_isvalid(const struct policydb *p, u32 user);
+extern int policydb_read(struct policydb *p, struct policy_file *fp);
+extern int policydb_write(struct policydb *p, struct policy_file *fp);
+
+extern struct filename_trans_datum *
+policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key);
+
+extern struct mls_range *policydb_rangetr_search(struct policydb *p,
+						 struct range_trans *key);
+
+extern struct role_trans_datum *
+policydb_roletr_search(struct policydb *p, struct role_trans_key *key);
+
+#define POLICYDB_CONFIG_MLS 1
+
+/* the config flags related to unknown classes/perms are bits 2 and 3 */
+#define REJECT_UNKNOWN 0x00000002
+#define ALLOW_UNKNOWN  0x00000004
+
+#define OBJECT_R     "object_r"
+#define OBJECT_R_VAL 1
+
+#define POLICYDB_MAGIC	SELINUX_MAGIC
+#define POLICYDB_STRING "SE Linux"
+
+struct policy_data {
+	struct policydb *p;
+	struct policy_file *fp;
+};
+
+static inline int size_check(size_t bytes, size_t num,
+			     const struct policy_file *fp)
+{
+	size_t len;
+
+	if (unlikely(check_mul_overflow(bytes, num, &len)))
+		return -EINVAL;
+
+	if (unlikely(len > fp->len))
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes)
+{
+	if (bytes > fp->len)
+		return -EINVAL;
+
+	memcpy(buf, fp->data, bytes);
+	fp->data += bytes;
+	fp->len -= bytes;
+	return 0;
+}
+
+static inline int put_entry(const void *buf, size_t bytes, size_t num,
+			    struct policy_file *fp)
+{
+	size_t len;
+
+	if (unlikely(check_mul_overflow(bytes, num, &len)))
+		return -EINVAL;
+
+	if (len > fp->len)
+		return -EINVAL;
+	memcpy(fp->data, buf, len);
+	fp->data += len;
+	fp->len -= len;
+
+	return 0;
+}
+
+static inline const char *sym_name(const struct policydb *p, unsigned int sym_num,
+			     unsigned int element_nr)
+{
+	return p->sym_val_to_name[sym_num][element_nr];
+}
+
+static inline bool val_is_boolean(u32 value)
+{
+	return value == 0 || value == 1;
+}
+
+extern int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len);
+
+extern u16 string_to_security_class(struct policydb *p, const char *name);
+extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name);
+
+#define pr_warn_once_policyload(policy, fmt, ...)    \
+	do {                                         \
+		static const void *prev_policy__;    \
+		if (prev_policy__ != policy) {       \
+			pr_warn(fmt, ##__VA_ARGS__); \
+			prev_policy__ = policy;      \
+		}                                    \
+	} while (0)
+
+#endif /* _SS_POLICYDB_H_ */
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
new file mode 100644
index 000000000..da77ad769
--- /dev/null
+++ b/security/selinux/ss/services.c
@@ -0,0 +1,3962 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implementation of the security services.
+ *
+ * Authors : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ *	     James Morris <jmorris@redhat.com>
+ *
+ * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com>
+ *
+ *	Support for enhanced MLS infrastructure.
+ *	Support for context based audit filters.
+ *
+ * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com>
+ *
+ *	Added conditional policy language extensions
+ *
+ * Updated: Hewlett-Packard <paul@paul-moore.com>
+ *
+ *      Added support for NetLabel
+ *      Added support for the policy capability bitmap
+ *
+ * Updated: Chad Sellers <csellers@tresys.com>
+ *
+ *  Added validation of kernel classes and permissions
+ *
+ * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com>
+ *
+ *  Added support for bounds domain and audit messaged on masked permissions
+ *
+ * Updated: Guido Trentalancia <guido@trentalancia.com>
+ *
+ *  Added support for runtime switching of the policy type
+ *
+ * Copyright (C) 2008, 2009 NEC Corporation
+ * Copyright (C) 2006, 2007 Hewlett-Packard Development Company, L.P.
+ * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc.
+ * Copyright (C) 2003 - 2004, 2006 Tresys Technology, LLC
+ * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ */
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+#include <linux/errno.h>
+#include <linux/in.h>
+#include <linux/sched.h>
+#include <linux/audit.h>
+#include <linux/parser.h>
+#include <linux/vmalloc.h>
+#include <linux/lsm_hooks.h>
+#include <net/netlabel.h>
+
+#include "flask.h"
+#include "avc.h"
+#include "avc_ss.h"
+#include "security.h"
+#include "context.h"
+#include "policydb.h"
+#include "sidtab.h"
+#include "services.h"
+#include "conditional.h"
+#include "mls.h"
+#include "objsec.h"
+#include "netlabel.h"
+#include "xfrm.h"
+#include "ebitmap.h"
+#include "audit.h"
+#include "policycap_names.h"
+#include "ima.h"
+
+struct selinux_policy_convert_data {
+	struct convert_context_args args;
+	struct sidtab_convert_params sidtab_params;
+};
+
+/* Forward declaration. */
+static int context_struct_to_string(struct policydb *policydb,
+				    struct context *context,
+				    char **scontext,
+				    u32 *scontext_len);
+
+static int sidtab_entry_to_string(struct policydb *policydb,
+				  struct sidtab *sidtab,
+				  struct sidtab_entry *entry,
+				  char **scontext,
+				  u32 *scontext_len);
+
+static void context_struct_compute_av(struct policydb *policydb,
+				      struct context *scontext,
+				      struct context *tcontext,
+				      u16 tclass,
+				      struct av_decision *avd,
+				      struct extended_perms *xperms);
+
+static int selinux_set_mapping(struct policydb *pol,
+			       const struct security_class_mapping *map,
+			       struct selinux_map *out_map)
+{
+	u16 i, j;
+	bool print_unknown_handle = false;
+
+	/* Find number of classes in the input mapping */
+	if (!map)
+		return -EINVAL;
+	i = 0;
+	while (map[i].name)
+		i++;
+
+	/* Allocate space for the class records, plus one for class zero */
+	out_map->mapping = kzalloc_objs(*out_map->mapping, ++i, GFP_ATOMIC);
+	if (!out_map->mapping)
+		return -ENOMEM;
+
+	/* Store the raw class and permission values */
+	j = 0;
+	while (map[j].name) {
+		const struct security_class_mapping *p_in = map + (j++);
+		struct selinux_mapping *p_out = out_map->mapping + j;
+		u16 k;
+
+		/* An empty class string skips ahead */
+		if (!strcmp(p_in->name, "")) {
+			p_out->num_perms = 0;
+			continue;
+		}
+
+		p_out->value = string_to_security_class(pol, p_in->name);
+		if (!p_out->value) {
+			pr_info("SELinux:  Class %s not defined in policy.\n",
+			       p_in->name);
+			if (pol->reject_unknown)
+				goto err;
+			p_out->num_perms = 0;
+			print_unknown_handle = true;
+			continue;
+		}
+
+		k = 0;
+		while (p_in->perms[k]) {
+			/* An empty permission string skips ahead */
+			if (!*p_in->perms[k]) {
+				k++;
+				continue;
+			}
+			p_out->perms[k] = string_to_av_perm(pol, p_out->value,
+							    p_in->perms[k]);
+			if (!p_out->perms[k]) {
+				pr_info("SELinux:  Permission %s in class %s not defined in policy.\n",
+				       p_in->perms[k], p_in->name);
+				if (pol->reject_unknown)
+					goto err;
+				print_unknown_handle = true;
+			}
+
+			k++;
+		}
+		p_out->num_perms = k;
+	}
+
+	if (print_unknown_handle)
+		pr_info("SELinux: the above unknown classes and permissions will be %s\n",
+		       pol->allow_unknown ? "allowed" : "denied");
+
+	out_map->size = i;
+	return 0;
+err:
+	kfree(out_map->mapping);
+	out_map->mapping = NULL;
+	return -EINVAL;
+}
+
+/*
+ * Get real, policy values from mapped values
+ */
+
+static u16 unmap_class(struct selinux_map *map, u16 tclass)
+{
+	if (tclass < map->size)
+		return map->mapping[tclass].value;
+
+	return tclass;
+}
+
+/*
+ * Get kernel value for class from its policy value
+ */
+static u16 map_class(struct selinux_map *map, u16 pol_value)
+{
+	u16 i;
+
+	for (i = 1; i < map->size; i++) {
+		if (map->mapping[i].value == pol_value)
+			return i;
+	}
+
+	return SECCLASS_NULL;
+}
+
+static void map_decision(struct selinux_map *map,
+			 u16 tclass, struct av_decision *avd,
+			 int allow_unknown)
+{
+	if (tclass < map->size) {
+		struct selinux_mapping *mapping = &map->mapping[tclass];
+		unsigned int i, n = mapping->num_perms;
+		u32 result;
+
+		for (i = 0, result = 0; i < n; i++) {
+			if (avd->allowed & mapping->perms[i])
+				result |= (u32)1<<i;
+			if (allow_unknown && !mapping->perms[i])
+				result |= (u32)1<<i;
+		}
+		avd->allowed = result;
+
+		for (i = 0, result = 0; i < n; i++)
+			if (avd->auditallow & mapping->perms[i])
+				result |= (u32)1<<i;
+		avd->auditallow = result;
+
+		for (i = 0, result = 0; i < n; i++) {
+			if (avd->auditdeny & mapping->perms[i])
+				result |= (u32)1<<i;
+			if (!allow_unknown && !mapping->perms[i])
+				result |= (u32)1<<i;
+		}
+		/*
+		 * In case the kernel has a bug and requests a permission
+		 * between num_perms and the maximum permission number, we
+		 * should audit that denial
+		 */
+		for (; i < (sizeof(u32)*8); i++)
+			result |= (u32)1<<i;
+		avd->auditdeny = result;
+	}
+}
+
+int security_mls_enabled(void)
+{
+	int mls_enabled;
+	struct selinux_policy *policy;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	mls_enabled = policy->policydb.mls_enabled;
+	rcu_read_unlock();
+	return mls_enabled;
+}
+
+/*
+ * Return the boolean value of a constraint expression
+ * when it is applied to the specified source and target
+ * security contexts.
+ *
+ * xcontext is a special beast...  It is used by the validatetrans rules
+ * only.  For these rules, scontext is the context before the transition,
+ * tcontext is the context after the transition, and xcontext is the context
+ * of the process performing the transition.  All other callers of
+ * constraint_expr_eval should pass in NULL for xcontext.
+ */
+static int constraint_expr_eval(struct policydb *policydb,
+				struct context *scontext,
+				struct context *tcontext,
+				struct context *xcontext,
+				struct constraint_expr *cexpr)
+{
+	u32 val1, val2;
+	struct context *c;
+	struct role_datum *r1, *r2;
+	struct mls_level *l1, *l2;
+	struct constraint_expr *e;
+	int s[CEXPR_MAXDEPTH];
+	int sp = -1;
+
+	for (e = cexpr; e; e = e->next) {
+		switch (e->expr_type) {
+		case CEXPR_NOT:
+			BUG_ON(sp < 0);
+			s[sp] = !s[sp];
+			break;
+		case CEXPR_AND:
+			BUG_ON(sp < 1);
+			sp--;
+			s[sp] &= s[sp + 1];
+			break;
+		case CEXPR_OR:
+			BUG_ON(sp < 1);
+			sp--;
+			s[sp] |= s[sp + 1];
+			break;
+		case CEXPR_ATTR:
+			if (sp == (CEXPR_MAXDEPTH - 1))
+				return 0;
+			switch (e->attr) {
+			case CEXPR_USER:
+				val1 = scontext->user;
+				val2 = tcontext->user;
+				break;
+			case CEXPR_TYPE:
+				val1 = scontext->type;
+				val2 = tcontext->type;
+				break;
+			case CEXPR_ROLE:
+				val1 = scontext->role;
+				val2 = tcontext->role;
+				r1 = policydb->role_val_to_struct[val1 - 1];
+				r2 = policydb->role_val_to_struct[val2 - 1];
+				switch (e->op) {
+				case CEXPR_DOM:
+					s[++sp] = ebitmap_get_bit(&r1->dominates,
+								  val2 - 1);
+					continue;
+				case CEXPR_DOMBY:
+					s[++sp] = ebitmap_get_bit(&r2->dominates,
+								  val1 - 1);
+					continue;
+				case CEXPR_INCOMP:
+					s[++sp] = (!ebitmap_get_bit(&r1->dominates,
+								    val2 - 1) &&
+						   !ebitmap_get_bit(&r2->dominates,
+								    val1 - 1));
+					continue;
+				default:
+					break;
+				}
+				break;
+			case CEXPR_L1L2:
+				l1 = &(scontext->range.level[0]);
+				l2 = &(tcontext->range.level[0]);
+				goto mls_ops;
+			case CEXPR_L1H2:
+				l1 = &(scontext->range.level[0]);
+				l2 = &(tcontext->range.level[1]);
+				goto mls_ops;
+			case CEXPR_H1L2:
+				l1 = &(scontext->range.level[1]);
+				l2 = &(tcontext->range.level[0]);
+				goto mls_ops;
+			case CEXPR_H1H2:
+				l1 = &(scontext->range.level[1]);
+				l2 = &(tcontext->range.level[1]);
+				goto mls_ops;
+			case CEXPR_L1H1:
+				l1 = &(scontext->range.level[0]);
+				l2 = &(scontext->range.level[1]);
+				goto mls_ops;
+			case CEXPR_L2H2:
+				l1 = &(tcontext->range.level[0]);
+				l2 = &(tcontext->range.level[1]);
+				goto mls_ops;
+mls_ops:
+				switch (e->op) {
+				case CEXPR_EQ:
+					s[++sp] = mls_level_eq(l1, l2);
+					continue;
+				case CEXPR_NEQ:
+					s[++sp] = !mls_level_eq(l1, l2);
+					continue;
+				case CEXPR_DOM:
+					s[++sp] = mls_level_dom(l1, l2);
+					continue;
+				case CEXPR_DOMBY:
+					s[++sp] = mls_level_dom(l2, l1);
+					continue;
+				case CEXPR_INCOMP:
+					s[++sp] = mls_level_incomp(l2, l1);
+					continue;
+				default:
+					BUG();
+					return 0;
+				}
+				break;
+			default:
+				BUG();
+				return 0;
+			}
+
+			switch (e->op) {
+			case CEXPR_EQ:
+				s[++sp] = (val1 == val2);
+				break;
+			case CEXPR_NEQ:
+				s[++sp] = (val1 != val2);
+				break;
+			default:
+				BUG();
+				return 0;
+			}
+			break;
+		case CEXPR_NAMES:
+			if (sp == (CEXPR_MAXDEPTH-1))
+				return 0;
+			c = scontext;
+			if (e->attr & CEXPR_TARGET)
+				c = tcontext;
+			else if (e->attr & CEXPR_XTARGET) {
+				c = xcontext;
+				if (!c) {
+					BUG();
+					return 0;
+				}
+			}
+			if (e->attr & CEXPR_USER)
+				val1 = c->user;
+			else if (e->attr & CEXPR_ROLE)
+				val1 = c->role;
+			else if (e->attr & CEXPR_TYPE)
+				val1 = c->type;
+			else {
+				BUG();
+				return 0;
+			}
+
+			switch (e->op) {
+			case CEXPR_EQ:
+				s[++sp] = ebitmap_get_bit(&e->names, val1 - 1);
+				break;
+			case CEXPR_NEQ:
+				s[++sp] = !ebitmap_get_bit(&e->names, val1 - 1);
+				break;
+			default:
+				BUG();
+				return 0;
+			}
+			break;
+		default:
+			BUG();
+			return 0;
+		}
+	}
+
+	BUG_ON(sp != 0);
+	return s[0];
+}
+
+/*
+ * security_dump_masked_av - dumps masked permissions during
+ * security_compute_av due to RBAC, MLS/Constraint and Type bounds.
+ */
+static int dump_masked_av_helper(void *k, void *d, void *args)
+{
+	struct perm_datum *pdatum = d;
+	char **permission_names = args;
+
+	permission_names[pdatum->value - 1] = (char *)k;
+
+	return 0;
+}
+
+static void security_dump_masked_av(struct policydb *policydb,
+				    struct context *scontext,
+				    struct context *tcontext,
+				    u16 tclass,
+				    u32 permissions,
+				    const char *reason)
+{
+	struct common_datum *common_dat;
+	struct class_datum *tclass_dat;
+	struct audit_buffer *ab;
+	const char *tclass_name;
+	char *scontext_name = NULL;
+	char *tcontext_name = NULL;
+	char *permission_names[SEL_VEC_MAX];
+	int index;
+	u32 length;
+	bool need_comma = false;
+
+	if (!permissions)
+		return;
+
+	tclass_name = sym_name(policydb, SYM_CLASSES, tclass - 1);
+	tclass_dat = policydb->class_val_to_struct[tclass - 1];
+	common_dat = tclass_dat->comdatum;
+
+	/* init permission_names */
+	if (common_dat &&
+	    hashtab_map(&common_dat->permissions.table,
+			dump_masked_av_helper, permission_names) < 0)
+		goto out;
+
+	if (hashtab_map(&tclass_dat->permissions.table,
+			dump_masked_av_helper, permission_names) < 0)
+		goto out;
+
+	/* get scontext/tcontext in text form */
+	if (context_struct_to_string(policydb, scontext,
+				     &scontext_name, &length) < 0)
+		goto out;
+
+	if (context_struct_to_string(policydb, tcontext,
+				     &tcontext_name, &length) < 0)
+		goto out;
+
+	/* audit a message */
+	ab = audit_log_start(audit_context(),
+			     GFP_ATOMIC, AUDIT_SELINUX_ERR);
+	if (!ab)
+		goto out;
+
+	audit_log_format(ab, "op=security_compute_av reason=%s "
+			 "scontext=%s tcontext=%s tclass=%s perms=",
+			 reason, scontext_name, tcontext_name, tclass_name);
+
+	for (index = 0; index < SEL_VEC_MAX; index++) {
+		u32 mask = (1 << index);
+
+		if ((mask & permissions) == 0)
+			continue;
+
+		audit_log_format(ab, "%s%s",
+				 need_comma ? "," : "",
+				 permission_names[index]
+				 ? permission_names[index] : "????");
+		need_comma = true;
+	}
+	audit_log_end(ab);
+out:
+	/* release scontext/tcontext */
+	kfree(tcontext_name);
+	kfree(scontext_name);
+}
+
+/*
+ * security_boundary_permission - drops violated permissions
+ * on boundary constraint.
+ */
+static void type_attribute_bounds_av(struct policydb *policydb,
+				     struct context *scontext,
+				     struct context *tcontext,
+				     u16 tclass,
+				     struct av_decision *avd)
+{
+	struct context lo_scontext;
+	struct context lo_tcontext, *tcontextp = tcontext;
+	struct av_decision lo_avd;
+	struct type_datum *source;
+	struct type_datum *target;
+	u32 masked = 0;
+
+	source = policydb->type_val_to_struct[scontext->type - 1];
+	BUG_ON(!source);
+
+	if (!source->bounds)
+		return;
+
+	target = policydb->type_val_to_struct[tcontext->type - 1];
+	BUG_ON(!target);
+
+	memset(&lo_avd, 0, sizeof(lo_avd));
+
+	memcpy(&lo_scontext, scontext, sizeof(lo_scontext));
+	lo_scontext.type = source->bounds;
+
+	if (target->bounds) {
+		memcpy(&lo_tcontext, tcontext, sizeof(lo_tcontext));
+		lo_tcontext.type = target->bounds;
+		tcontextp = &lo_tcontext;
+	}
+
+	context_struct_compute_av(policydb, &lo_scontext,
+				  tcontextp,
+				  tclass,
+				  &lo_avd,
+				  NULL);
+
+	masked = ~lo_avd.allowed & avd->allowed;
+
+	if (likely(!masked))
+		return;		/* no masked permission */
+
+	/* mask violated permissions */
+	avd->allowed &= ~masked;
+
+	/* audit masked permissions */
+	security_dump_masked_av(policydb, scontext, tcontext,
+				tclass, masked, "bounds");
+}
+
+/*
+ * Flag which drivers have permissions and which base permissions are covered.
+ */
+void services_compute_xperms_drivers(
+		struct extended_perms *xperms,
+		struct avtab_node *node)
+{
+	unsigned int i;
+
+	switch (node->datum.u.xperms->specified) {
+	case AVTAB_XPERMS_IOCTLDRIVER:
+		xperms->base_perms |= AVC_EXT_IOCTL;
+		/* if one or more driver has all permissions allowed */
+		for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++)
+			xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i];
+		break;
+	case AVTAB_XPERMS_IOCTLFUNCTION:
+		xperms->base_perms |= AVC_EXT_IOCTL;
+		/* if allowing permissions within a driver */
+		security_xperm_set(xperms->drivers.p,
+					node->datum.u.xperms->driver);
+		break;
+	case AVTAB_XPERMS_NLMSG:
+		xperms->base_perms |= AVC_EXT_NLMSG;
+		/* if allowing permissions within a driver */
+		security_xperm_set(xperms->drivers.p,
+					node->datum.u.xperms->driver);
+		break;
+	}
+
+	xperms->len = 1;
+}
+
+/*
+ * Compute access vectors and extended permissions based on a context
+ * structure pair for the permissions in a particular class.
+ */
+static void context_struct_compute_av(struct policydb *policydb,
+				      struct context *scontext,
+				      struct context *tcontext,
+				      u16 tclass,
+				      struct av_decision *avd,
+				      struct extended_perms *xperms)
+{
+	struct constraint_node *constraint;
+	struct role_allow *ra;
+	struct avtab_key avkey;
+	struct avtab_node *node;
+	struct class_datum *tclass_datum;
+	struct ebitmap *sattr, *tattr;
+	struct ebitmap_node *snode, *tnode;
+	unsigned int i, j;
+
+	avd->allowed = 0;
+	avd->auditallow = 0;
+	avd->auditdeny = 0xffffffff;
+	if (xperms) {
+		memset(xperms, 0, sizeof(*xperms));
+	}
+
+	if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) {
+		pr_warn_ratelimited("SELinux:  Invalid class %u\n", tclass);
+		return;
+	}
+
+	tclass_datum = policydb->class_val_to_struct[tclass - 1];
+
+	/*
+	 * If a specific type enforcement rule was defined for
+	 * this permission check, then use it.
+	 */
+	avkey.target_class = tclass;
+	avkey.specified = AVTAB_AV | AVTAB_XPERMS;
+	sattr = &policydb->type_attr_map_array[scontext->type - 1];
+	tattr = &policydb->type_attr_map_array[tcontext->type - 1];
+	ebitmap_for_each_positive_bit(sattr, snode, i) {
+		ebitmap_for_each_positive_bit(tattr, tnode, j) {
+			avkey.source_type = i + 1;
+			avkey.target_type = j + 1;
+			for (node = avtab_search_node(&policydb->te_avtab,
+						      &avkey);
+			     node;
+			     node = avtab_search_node_next(node, avkey.specified)) {
+				if (node->key.specified == AVTAB_ALLOWED)
+					avd->allowed |= node->datum.u.data;
+				else if (node->key.specified == AVTAB_AUDITALLOW)
+					avd->auditallow |= node->datum.u.data;
+				else if (node->key.specified == AVTAB_AUDITDENY)
+					avd->auditdeny &= node->datum.u.data;
+				else if (xperms && (node->key.specified & AVTAB_XPERMS))
+					services_compute_xperms_drivers(xperms, node);
+			}
+
+			/* Check conditional av table for additional permissions */
+			cond_compute_av(&policydb->te_cond_avtab, &avkey,
+					avd, xperms);
+
+		}
+	}
+
+	/*
+	 * Remove any permissions prohibited by a constraint (this includes
+	 * the MLS policy).
+	 */
+	constraint = tclass_datum->constraints;
+	while (constraint) {
+		if ((constraint->permissions & (avd->allowed)) &&
+		    !constraint_expr_eval(policydb, scontext, tcontext, NULL,
+					  constraint->expr)) {
+			avd->allowed &= ~(constraint->permissions);
+		}
+		constraint = constraint->next;
+	}
+
+	/*
+	 * If checking process transition permission and the
+	 * role is changing, then check the (current_role, new_role)
+	 * pair.
+	 */
+	if (tclass == policydb->process_class &&
+	    (avd->allowed & policydb->process_trans_perms) &&
+	    scontext->role != tcontext->role) {
+		for (ra = policydb->role_allow; ra; ra = ra->next) {
+			if (scontext->role == ra->role &&
+			    tcontext->role == ra->new_role)
+				break;
+		}
+		if (!ra)
+			avd->allowed &= ~policydb->process_trans_perms;
+	}
+
+	/*
+	 * If the given source and target types have boundary
+	 * constraint, lazy checks have to mask any violated
+	 * permission and notice it to userspace via audit.
+	 *
+	 * Infinite recursion is avoided via a depth pre-check in
+	 * type_bounds_sanity_check().
+	 */
+	type_attribute_bounds_av(policydb, scontext, tcontext,
+				 tclass, avd);
+}
+
+static int security_validtrans_handle_fail(struct selinux_policy *policy,
+					struct sidtab_entry *oentry,
+					struct sidtab_entry *nentry,
+					struct sidtab_entry *tentry,
+					u16 tclass)
+{
+	struct policydb *p = &policy->policydb;
+	struct sidtab *sidtab = policy->sidtab;
+	char *o = NULL, *n = NULL, *t = NULL;
+	u32 olen, nlen, tlen;
+
+	if (sidtab_entry_to_string(p, sidtab, oentry, &o, &olen))
+		goto out;
+	if (sidtab_entry_to_string(p, sidtab, nentry, &n, &nlen))
+		goto out;
+	if (sidtab_entry_to_string(p, sidtab, tentry, &t, &tlen))
+		goto out;
+	audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR,
+		  "op=security_validate_transition seresult=denied"
+		  " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s",
+		  o, n, t, sym_name(p, SYM_CLASSES, tclass-1));
+out:
+	kfree(o);
+	kfree(n);
+	kfree(t);
+
+	if (!enforcing_enabled())
+		return 0;
+	return -EPERM;
+}
+
+static int security_compute_validatetrans(u32 oldsid, u32 newsid, u32 tasksid,
+					  u16 orig_tclass, bool user)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct sidtab_entry *oentry;
+	struct sidtab_entry *nentry;
+	struct sidtab_entry *tentry;
+	struct class_datum *tclass_datum;
+	struct constraint_node *constraint;
+	u16 tclass;
+	int rc = 0;
+
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	if (!user)
+		tclass = unmap_class(&policy->map, orig_tclass);
+	else
+		tclass = orig_tclass;
+
+	if (!tclass || tclass > policydb->p_classes.nprim) {
+		rc = -EINVAL;
+		goto out;
+	}
+	tclass_datum = policydb->class_val_to_struct[tclass - 1];
+
+	oentry = sidtab_search_entry(sidtab, oldsid);
+	if (!oentry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, oldsid);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	nentry = sidtab_search_entry(sidtab, newsid);
+	if (!nentry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, newsid);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	tentry = sidtab_search_entry(sidtab, tasksid);
+	if (!tentry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, tasksid);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	constraint = tclass_datum->validatetrans;
+	while (constraint) {
+		if (!constraint_expr_eval(policydb, &oentry->context,
+					  &nentry->context, &tentry->context,
+					  constraint->expr)) {
+			if (user)
+				rc = -EPERM;
+			else
+				rc = security_validtrans_handle_fail(policy,
+								oentry,
+								nentry,
+								tentry,
+								tclass);
+			goto out;
+		}
+		constraint = constraint->next;
+	}
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+int security_validate_transition_user(u32 oldsid, u32 newsid, u32 tasksid,
+				      u16 tclass)
+{
+	return security_compute_validatetrans(oldsid, newsid, tasksid,
+					      tclass, true);
+}
+
+int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid,
+				 u16 orig_tclass)
+{
+	return security_compute_validatetrans(oldsid, newsid, tasksid,
+					      orig_tclass, false);
+}
+
+/*
+ * security_bounded_transition - check whether the given
+ * transition is directed to bounded, or not.
+ * It returns 0, if @newsid is bounded by @oldsid.
+ * Otherwise, it returns error code.
+ *
+ * @oldsid : current security identifier
+ * @newsid : destinated security identifier
+ */
+int security_bounded_transition(u32 old_sid, u32 new_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct sidtab_entry *old_entry, *new_entry;
+	struct type_datum *type;
+	u32 index;
+	int rc;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	rc = -EINVAL;
+	old_entry = sidtab_search_entry(sidtab, old_sid);
+	if (!old_entry) {
+		pr_err("SELinux: %s: unrecognized SID %u\n",
+		       __func__, old_sid);
+		goto out;
+	}
+
+	rc = -EINVAL;
+	new_entry = sidtab_search_entry(sidtab, new_sid);
+	if (!new_entry) {
+		pr_err("SELinux: %s: unrecognized SID %u\n",
+		       __func__, new_sid);
+		goto out;
+	}
+
+	rc = 0;
+	/* type/domain unchanged */
+	if (old_entry->context.type == new_entry->context.type)
+		goto out;
+
+	index = new_entry->context.type;
+	while (true) {
+		type = policydb->type_val_to_struct[index - 1];
+		BUG_ON(!type);
+
+		/* not bounded anymore */
+		rc = -EPERM;
+		if (!type->bounds)
+			break;
+
+		/* @newsid is bounded by @oldsid */
+		rc = 0;
+		if (type->bounds == old_entry->context.type)
+			break;
+
+		index = type->bounds;
+	}
+
+	if (rc) {
+		char *old_name = NULL;
+		char *new_name = NULL;
+		u32 length;
+
+		if (!sidtab_entry_to_string(policydb, sidtab, old_entry,
+					    &old_name, &length) &&
+		    !sidtab_entry_to_string(policydb, sidtab, new_entry,
+					    &new_name, &length)) {
+			audit_log(audit_context(),
+				  GFP_ATOMIC, AUDIT_SELINUX_ERR,
+				  "op=security_bounded_transition "
+				  "seresult=denied "
+				  "oldcontext=%s newcontext=%s",
+				  old_name, new_name);
+		}
+		kfree(new_name);
+		kfree(old_name);
+	}
+out:
+	rcu_read_unlock();
+
+	return rc;
+}
+
+static void avd_init(struct selinux_policy *policy, struct av_decision *avd)
+{
+	avd->allowed = 0;
+	avd->auditallow = 0;
+	avd->auditdeny = 0xffffffff;
+	if (policy)
+		avd->seqno = policy->latest_granting;
+	else
+		avd->seqno = 0;
+	avd->flags = 0;
+}
+
+static void update_xperms_extended_data(u8 specified,
+					const struct extended_perms_data *from,
+					struct extended_perms_data *xp_data)
+{
+	unsigned int i;
+
+	switch (specified) {
+	case AVTAB_XPERMS_IOCTLDRIVER:
+		memset(xp_data->p, 0xff, sizeof(xp_data->p));
+		break;
+	case AVTAB_XPERMS_IOCTLFUNCTION:
+	case AVTAB_XPERMS_NLMSG:
+		for (i = 0; i < ARRAY_SIZE(xp_data->p); i++)
+			xp_data->p[i] |= from->p[i];
+		break;
+	}
+
+}
+
+void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
+					struct avtab_node *node)
+{
+	u16 specified;
+
+	switch (node->datum.u.xperms->specified) {
+	case AVTAB_XPERMS_IOCTLFUNCTION:
+		if (xpermd->base_perm != AVC_EXT_IOCTL ||
+		    xpermd->driver != node->datum.u.xperms->driver)
+			return;
+		break;
+	case AVTAB_XPERMS_IOCTLDRIVER:
+		if (xpermd->base_perm != AVC_EXT_IOCTL ||
+		    !security_xperm_test(node->datum.u.xperms->perms.p,
+					 xpermd->driver))
+			return;
+		break;
+	case AVTAB_XPERMS_NLMSG:
+		if (xpermd->base_perm != AVC_EXT_NLMSG ||
+		    xpermd->driver != node->datum.u.xperms->driver)
+			return;
+		break;
+	default:
+		pr_warn_once(
+			"SELinux: unknown extended permission (%u) will be ignored\n",
+			node->datum.u.xperms->specified);
+		return;
+	}
+
+	specified = node->key.specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD);
+
+	if (specified == AVTAB_XPERMS_ALLOWED) {
+		xpermd->used |= XPERMS_ALLOWED;
+		update_xperms_extended_data(node->datum.u.xperms->specified,
+					    &node->datum.u.xperms->perms,
+					    xpermd->allowed);
+	} else if (specified == AVTAB_XPERMS_AUDITALLOW) {
+		xpermd->used |= XPERMS_AUDITALLOW;
+		update_xperms_extended_data(node->datum.u.xperms->specified,
+					    &node->datum.u.xperms->perms,
+					    xpermd->auditallow);
+	} else if (specified == AVTAB_XPERMS_DONTAUDIT) {
+		xpermd->used |= XPERMS_DONTAUDIT;
+		update_xperms_extended_data(node->datum.u.xperms->specified,
+					    &node->datum.u.xperms->perms,
+					    xpermd->dontaudit);
+	} else {
+		pr_warn_once("SELinux: unknown specified key (%u)\n",
+			     node->key.specified);
+	}
+}
+
+void security_compute_xperms_decision(u32 ssid,
+				      u32 tsid,
+				      u16 orig_tclass,
+				      u8 driver,
+				      u8 base_perm,
+				      struct extended_perms_decision *xpermd)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	u16 tclass;
+	struct context *scontext, *tcontext;
+	struct avtab_key avkey;
+	struct avtab_node *node;
+	struct ebitmap *sattr, *tattr;
+	struct ebitmap_node *snode, *tnode;
+	unsigned int i, j;
+
+	xpermd->base_perm = base_perm;
+	xpermd->driver = driver;
+	xpermd->used = 0;
+	memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p));
+	memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p));
+	memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p));
+
+	rcu_read_lock();
+	if (!selinux_initialized())
+		goto allow;
+
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	scontext = sidtab_search(sidtab, ssid);
+	if (!scontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		goto out;
+	}
+
+	tcontext = sidtab_search(sidtab, tsid);
+	if (!tcontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		goto out;
+	}
+
+	tclass = unmap_class(&policy->map, orig_tclass);
+	if (unlikely(orig_tclass && !tclass)) {
+		if (policydb->allow_unknown)
+			goto allow;
+		goto out;
+	}
+
+
+	if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) {
+		pr_warn_ratelimited("SELinux:  Invalid class %hu\n", tclass);
+		goto out;
+	}
+
+	avkey.target_class = tclass;
+	avkey.specified = AVTAB_XPERMS;
+	sattr = &policydb->type_attr_map_array[scontext->type - 1];
+	tattr = &policydb->type_attr_map_array[tcontext->type - 1];
+	ebitmap_for_each_positive_bit(sattr, snode, i) {
+		ebitmap_for_each_positive_bit(tattr, tnode, j) {
+			avkey.source_type = i + 1;
+			avkey.target_type = j + 1;
+			for (node = avtab_search_node(&policydb->te_avtab,
+						      &avkey);
+			     node;
+			     node = avtab_search_node_next(node, avkey.specified))
+				services_compute_xperms_decision(xpermd, node);
+
+			cond_compute_xperms(&policydb->te_cond_avtab,
+						&avkey, xpermd);
+		}
+	}
+out:
+	rcu_read_unlock();
+	return;
+allow:
+	memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p));
+	goto out;
+}
+
+/**
+ * security_compute_av - Compute access vector decisions.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @orig_tclass: target security class
+ * @avd: access vector decisions
+ * @xperms: extended permissions
+ *
+ * Compute a set of access vector decisions based on the
+ * SID pair (@ssid, @tsid) for the permissions in @tclass.
+ */
+void security_compute_av(u32 ssid,
+			 u32 tsid,
+			 u16 orig_tclass,
+			 struct av_decision *avd,
+			 struct extended_perms *xperms)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	u16 tclass;
+	struct context *scontext = NULL, *tcontext = NULL;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	avd_init(policy, avd);
+	xperms->len = 0;
+	if (!selinux_initialized())
+		goto allow;
+
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	scontext = sidtab_search(sidtab, ssid);
+	if (!scontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		goto out;
+	}
+
+	/* permissive domain? */
+	if (ebitmap_get_bit(&policydb->permissive_map, scontext->type))
+		avd->flags |= AVD_FLAGS_PERMISSIVE;
+
+	/* neveraudit domain? */
+	if (ebitmap_get_bit(&policydb->neveraudit_map, scontext->type))
+		avd->flags |= AVD_FLAGS_NEVERAUDIT;
+
+	/* both permissive and neveraudit => allow */
+	if (avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT))
+		goto allow;
+
+	tcontext = sidtab_search(sidtab, tsid);
+	if (!tcontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		goto out;
+	}
+
+	tclass = unmap_class(&policy->map, orig_tclass);
+	if (unlikely(orig_tclass && !tclass)) {
+		if (policydb->allow_unknown)
+			goto allow;
+		goto out;
+	}
+	context_struct_compute_av(policydb, scontext, tcontext, tclass, avd,
+				  xperms);
+	map_decision(&policy->map, orig_tclass, avd,
+		     policydb->allow_unknown);
+out:
+	rcu_read_unlock();
+	if (avd->flags & AVD_FLAGS_NEVERAUDIT)
+		avd->auditallow = avd->auditdeny = 0;
+	return;
+allow:
+	avd->allowed = 0xffffffff;
+	goto out;
+}
+
+void security_compute_av_user(u32 ssid,
+			      u32 tsid,
+			      u16 tclass,
+			      struct av_decision *avd)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct context *scontext = NULL, *tcontext = NULL;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	avd_init(policy, avd);
+	if (!selinux_initialized())
+		goto allow;
+
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	scontext = sidtab_search(sidtab, ssid);
+	if (!scontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		goto out;
+	}
+
+	/* permissive domain? */
+	if (ebitmap_get_bit(&policydb->permissive_map, scontext->type))
+		avd->flags |= AVD_FLAGS_PERMISSIVE;
+
+	/* neveraudit domain? */
+	if (ebitmap_get_bit(&policydb->neveraudit_map, scontext->type))
+		avd->flags |= AVD_FLAGS_NEVERAUDIT;
+
+	/* both permissive and neveraudit => allow */
+	if (avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT))
+		goto allow;
+
+	tcontext = sidtab_search(sidtab, tsid);
+	if (!tcontext) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		goto out;
+	}
+
+	if (unlikely(!tclass)) {
+		if (policydb->allow_unknown)
+			goto allow;
+		goto out;
+	}
+
+	context_struct_compute_av(policydb, scontext, tcontext, tclass, avd,
+				  NULL);
+ out:
+	rcu_read_unlock();
+	if (avd->flags & AVD_FLAGS_NEVERAUDIT)
+		avd->auditallow = avd->auditdeny = 0;
+	return;
+allow:
+	avd->allowed = 0xffffffff;
+	goto out;
+}
+
+/*
+ * Write the security context string representation of
+ * the context structure `context' into a dynamically
+ * allocated string of the correct size.  Set `*scontext'
+ * to point to this string and set `*scontext_len' to
+ * the length of the string.
+ */
+static int context_struct_to_string(struct policydb *p,
+				    struct context *context,
+				    char **scontext, u32 *scontext_len)
+{
+	char *scontextp;
+
+	if (scontext)
+		*scontext = NULL;
+	*scontext_len = 0;
+
+	if (context->len) {
+		*scontext_len = context->len;
+		if (scontext) {
+			*scontext = kstrdup(context->str, GFP_ATOMIC);
+			if (!(*scontext))
+				return -ENOMEM;
+		}
+		return 0;
+	}
+
+	/* Compute the size of the context. */
+	*scontext_len += strlen(sym_name(p, SYM_USERS, context->user - 1)) + 1;
+	*scontext_len += strlen(sym_name(p, SYM_ROLES, context->role - 1)) + 1;
+	*scontext_len += strlen(sym_name(p, SYM_TYPES, context->type - 1)) + 1;
+	*scontext_len += mls_compute_context_len(p, context);
+
+	if (!scontext)
+		return 0;
+
+	/* Allocate space for the context; caller must free this space. */
+	scontextp = kmalloc(*scontext_len, GFP_ATOMIC);
+	if (!scontextp)
+		return -ENOMEM;
+	*scontext = scontextp;
+
+	/*
+	 * Copy the user name, role name and type name into the context.
+	 */
+	scontextp += sprintf(scontextp, "%s:%s:%s",
+		sym_name(p, SYM_USERS, context->user - 1),
+		sym_name(p, SYM_ROLES, context->role - 1),
+		sym_name(p, SYM_TYPES, context->type - 1));
+
+	mls_sid_to_context(p, context, &scontextp);
+
+	*scontextp = 0;
+
+	return 0;
+}
+
+static int sidtab_entry_to_string(struct policydb *p,
+				  struct sidtab *sidtab,
+				  struct sidtab_entry *entry,
+				  char **scontext, u32 *scontext_len)
+{
+	int rc = sidtab_sid2str_get(sidtab, entry, scontext, scontext_len);
+
+	if (rc != -ENOENT)
+		return rc;
+
+	rc = context_struct_to_string(p, &entry->context, scontext,
+				      scontext_len);
+	if (!rc && scontext)
+		sidtab_sid2str_put(sidtab, entry, *scontext, *scontext_len);
+	return rc;
+}
+
+#include "initial_sid_to_string.h"
+
+int security_sidtab_hash_stats(char *page)
+{
+	struct selinux_policy *policy;
+	int rc;
+
+	if (!selinux_initialized()) {
+		pr_err("SELinux: %s:  called before initial load_policy\n",
+		       __func__);
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	rc = sidtab_hash_stats(policy->sidtab, page);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+const char *security_get_initial_sid_context(u32 sid)
+{
+	if (unlikely(sid > SECINITSID_NUM))
+		return NULL;
+	return initial_sid_to_string[sid];
+}
+
+static int security_sid_to_context_core(u32 sid, char **scontext,
+					u32 *scontext_len, bool force,
+					bool only_invalid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct sidtab_entry *entry;
+	int rc = 0;
+
+	if (scontext)
+		*scontext = NULL;
+	*scontext_len  = 0;
+
+	if (!selinux_initialized()) {
+		if (sid <= SECINITSID_NUM) {
+			char *scontextp;
+			const char *s;
+
+			/*
+			 * Before the policy is loaded, translate
+			 * SECINITSID_INIT to "kernel", because systemd and
+			 * libselinux < 2.6 take a getcon_raw() result that is
+			 * both non-null and not "kernel" to mean that a policy
+			 * is already loaded.
+			 */
+			if (sid == SECINITSID_INIT)
+				sid = SECINITSID_KERNEL;
+
+			s = initial_sid_to_string[sid];
+			if (!s)
+				return -EINVAL;
+			*scontext_len = strlen(s) + 1;
+			if (!scontext)
+				return 0;
+			scontextp = kmemdup(s, *scontext_len, GFP_ATOMIC);
+			if (!scontextp)
+				return -ENOMEM;
+			*scontext = scontextp;
+			return 0;
+		}
+		pr_err("SELinux: %s:  called before initial "
+		       "load_policy on unknown SID %d\n", __func__, sid);
+		return -EINVAL;
+	}
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	if (force)
+		entry = sidtab_search_entry_force(sidtab, sid);
+	else
+		entry = sidtab_search_entry(sidtab, sid);
+	if (!entry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, sid);
+		rc = -EINVAL;
+		goto out_unlock;
+	}
+	if (only_invalid && !entry->context.len)
+		goto out_unlock;
+
+	rc = sidtab_entry_to_string(policydb, sidtab, entry, scontext,
+				    scontext_len);
+
+out_unlock:
+	rcu_read_unlock();
+	return rc;
+
+}
+
+/**
+ * security_sid_to_context - Obtain a context for a given SID.
+ * @sid: security identifier, SID
+ * @scontext: security context
+ * @scontext_len: length in bytes
+ *
+ * Write the string representation of the context associated with @sid
+ * into a dynamically allocated string of the correct size.  Set @scontext
+ * to point to this string and set @scontext_len to the length of the string.
+ */
+int security_sid_to_context(u32 sid, char **scontext, u32 *scontext_len)
+{
+	return security_sid_to_context_core(sid, scontext,
+					    scontext_len, false, false);
+}
+
+int security_sid_to_context_force(u32 sid,
+				  char **scontext, u32 *scontext_len)
+{
+	return security_sid_to_context_core(sid, scontext,
+					    scontext_len, true, false);
+}
+
+/**
+ * security_sid_to_context_inval - Obtain a context for a given SID if it
+ *                                 is invalid.
+ * @sid: security identifier, SID
+ * @scontext: security context
+ * @scontext_len: length in bytes
+ *
+ * Write the string representation of the context associated with @sid
+ * into a dynamically allocated string of the correct size, but only if the
+ * context is invalid in the current policy.  Set @scontext to point to
+ * this string (or NULL if the context is valid) and set @scontext_len to
+ * the length of the string (or 0 if the context is valid).
+ */
+int security_sid_to_context_inval(u32 sid,
+				  char **scontext, u32 *scontext_len)
+{
+	return security_sid_to_context_core(sid, scontext,
+					    scontext_len, true, true);
+}
+
+/*
+ * Caveat:  Mutates scontext.
+ */
+static int string_to_context_struct(struct policydb *pol,
+				    struct sidtab *sidtabp,
+				    char *scontext,
+				    struct context *ctx,
+				    u32 def_sid)
+{
+	struct role_datum *role;
+	struct type_datum *typdatum;
+	struct user_datum *usrdatum;
+	char *scontextp, *p, oldc;
+	int rc = 0;
+
+	context_init(ctx);
+
+	/* Parse the security context. */
+
+	rc = -EINVAL;
+	scontextp = scontext;
+
+	/* Extract the user. */
+	p = scontextp;
+	while (*p && *p != ':')
+		p++;
+
+	if (*p == 0)
+		goto out;
+
+	*p++ = 0;
+
+	usrdatum = symtab_search(&pol->p_users, scontextp);
+	if (!usrdatum)
+		goto out;
+
+	ctx->user = usrdatum->value;
+
+	/* Extract role. */
+	scontextp = p;
+	while (*p && *p != ':')
+		p++;
+
+	if (*p == 0)
+		goto out;
+
+	*p++ = 0;
+
+	role = symtab_search(&pol->p_roles, scontextp);
+	if (!role)
+		goto out;
+	ctx->role = role->value;
+
+	/* Extract type. */
+	scontextp = p;
+	while (*p && *p != ':')
+		p++;
+	oldc = *p;
+	*p++ = 0;
+
+	typdatum = symtab_search(&pol->p_types, scontextp);
+	if (!typdatum || typdatum->attribute)
+		goto out;
+
+	ctx->type = typdatum->value;
+
+	rc = mls_context_to_sid(pol, oldc, p, ctx, sidtabp, def_sid);
+	if (rc)
+		goto out;
+
+	/* Check the validity of the new context. */
+	rc = -EINVAL;
+	if (!policydb_context_isvalid(pol, ctx))
+		goto out;
+	rc = 0;
+out:
+	if (rc)
+		context_destroy(ctx);
+	return rc;
+}
+
+static int security_context_to_sid_core(const char *scontext, u32 scontext_len,
+					u32 *sid, u32 def_sid, gfp_t gfp_flags,
+					bool force)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	char *scontext2, *str = NULL;
+	struct context context;
+	int rc = 0;
+
+	/* An empty security context is never valid. */
+	if (!scontext_len)
+		return -EINVAL;
+
+	/* Copy the string to allow changes and ensure a NUL terminator */
+	scontext2 = kmemdup_nul(scontext, scontext_len, gfp_flags);
+	if (!scontext2)
+		return -ENOMEM;
+
+	if (!selinux_initialized()) {
+		u32 i;
+
+		for (i = 1; i < SECINITSID_NUM; i++) {
+			const char *s = initial_sid_to_string[i];
+
+			if (s && !strcmp(s, scontext2)) {
+				*sid = i;
+				goto out;
+			}
+		}
+		*sid = SECINITSID_KERNEL;
+		goto out;
+	}
+	*sid = SECSID_NULL;
+
+	if (force) {
+		/* Save another copy for storing in uninterpreted form */
+		rc = -ENOMEM;
+		str = kstrdup(scontext2, gfp_flags);
+		if (!str)
+			goto out;
+	}
+retry:
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+	rc = string_to_context_struct(policydb, sidtab, scontext2,
+				      &context, def_sid);
+	if (rc == -EINVAL && force) {
+		context.str = str;
+		context.len = strlen(str) + 1;
+		str = NULL;
+	} else if (rc)
+		goto out_unlock;
+	rc = sidtab_context_to_sid(sidtab, &context, sid);
+	if (rc == -ESTALE) {
+		rcu_read_unlock();
+		if (context.str) {
+			str = context.str;
+			context.str = NULL;
+		}
+		context_destroy(&context);
+		goto retry;
+	}
+	context_destroy(&context);
+out_unlock:
+	rcu_read_unlock();
+out:
+	kfree(scontext2);
+	kfree(str);
+	return rc;
+}
+
+/**
+ * security_context_to_sid - Obtain a SID for a given security context.
+ * @scontext: security context
+ * @scontext_len: length in bytes
+ * @sid: security identifier, SID
+ * @gfp: context for the allocation
+ *
+ * Obtains a SID associated with the security context that
+ * has the string representation specified by @scontext.
+ * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
+ * memory is available, or 0 on success.
+ */
+int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid,
+			    gfp_t gfp)
+{
+	return security_context_to_sid_core(scontext, scontext_len,
+					    sid, SECSID_NULL, gfp, false);
+}
+
+int security_context_str_to_sid(const char *scontext, u32 *sid, gfp_t gfp)
+{
+	return security_context_to_sid(scontext, strlen(scontext),
+				       sid, gfp);
+}
+
+/**
+ * security_context_to_sid_default - Obtain a SID for a given security context,
+ * falling back to specified default if needed.
+ *
+ * @scontext: security context
+ * @scontext_len: length in bytes
+ * @sid: security identifier, SID
+ * @def_sid: default SID to assign on error
+ * @gfp_flags: the allocator get-free-page (GFP) flags
+ *
+ * Obtains a SID associated with the security context that
+ * has the string representation specified by @scontext.
+ * The default SID is passed to the MLS layer to be used to allow
+ * kernel labeling of the MLS field if the MLS field is not present
+ * (for upgrading to MLS without full relabel).
+ * Implicitly forces adding of the context even if it cannot be mapped yet.
+ * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient
+ * memory is available, or 0 on success.
+ */
+int security_context_to_sid_default(const char *scontext, u32 scontext_len,
+				    u32 *sid, u32 def_sid, gfp_t gfp_flags)
+{
+	return security_context_to_sid_core(scontext, scontext_len,
+					    sid, def_sid, gfp_flags, true);
+}
+
+int security_context_to_sid_force(const char *scontext, u32 scontext_len,
+				  u32 *sid)
+{
+	return security_context_to_sid_core(scontext, scontext_len,
+					    sid, SECSID_NULL, GFP_KERNEL, true);
+}
+
+static int compute_sid_handle_invalid_context(
+	struct selinux_policy *policy,
+	struct sidtab_entry *sentry,
+	struct sidtab_entry *tentry,
+	u16 tclass,
+	struct context *newcontext)
+{
+	struct policydb *policydb = &policy->policydb;
+	struct sidtab *sidtab = policy->sidtab;
+	char *s = NULL, *t = NULL, *n = NULL;
+	u32 slen, tlen, nlen;
+	struct audit_buffer *ab;
+
+	if (sidtab_entry_to_string(policydb, sidtab, sentry, &s, &slen))
+		goto out;
+	if (sidtab_entry_to_string(policydb, sidtab, tentry, &t, &tlen))
+		goto out;
+	if (context_struct_to_string(policydb, newcontext, &n, &nlen))
+		goto out;
+	ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR);
+	if (!ab)
+		goto out;
+	audit_log_format(ab,
+			 "op=security_compute_sid invalid_context=");
+	/* no need to record the NUL with untrusted strings */
+	audit_log_n_untrustedstring(ab, n, nlen - 1);
+	audit_log_format(ab, " scontext=%s tcontext=%s tclass=%s",
+			 s, t, sym_name(policydb, SYM_CLASSES, tclass-1));
+	audit_log_end(ab);
+out:
+	kfree(s);
+	kfree(t);
+	kfree(n);
+	if (!enforcing_enabled())
+		return 0;
+	return -EACCES;
+}
+
+static void filename_compute_type(struct policydb *policydb,
+				  struct context *newcontext,
+				  u32 stype, u32 ttype, u16 tclass,
+				  const char *objname)
+{
+	struct filename_trans_key ft;
+	struct filename_trans_datum *datum;
+
+	/*
+	 * Most filename trans rules are going to live in specific directories
+	 * like /dev or /var/run.  This bitmap will quickly skip rule searches
+	 * if the ttype does not contain any rules.
+	 */
+	if (!ebitmap_get_bit(&policydb->filename_trans_ttypes, ttype))
+		return;
+
+	ft.ttype = ttype;
+	ft.tclass = tclass;
+	ft.name = objname;
+
+	datum = policydb_filenametr_search(policydb, &ft);
+	while (datum) {
+		if (ebitmap_get_bit(&datum->stypes, stype - 1)) {
+			newcontext->type = datum->otype;
+			return;
+		}
+		datum = datum->next;
+	}
+}
+
+static int security_compute_sid(u32 ssid,
+				u32 tsid,
+				u16 orig_tclass,
+				u16 specified,
+				const char *objname,
+				u32 *out_sid,
+				bool kern)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct class_datum *cladatum;
+	struct context *scontext, *tcontext, newcontext;
+	struct sidtab_entry *sentry, *tentry;
+	struct avtab_key avkey;
+	struct avtab_node *avnode, *node;
+	u16 tclass;
+	int rc = 0;
+	bool sock;
+
+	if (!selinux_initialized()) {
+		switch (orig_tclass) {
+		case SECCLASS_PROCESS: /* kernel value */
+			*out_sid = ssid;
+			break;
+		default:
+			*out_sid = tsid;
+			break;
+		}
+		goto out;
+	}
+
+retry:
+	cladatum = NULL;
+	context_init(&newcontext);
+
+	rcu_read_lock();
+
+	policy = rcu_dereference(selinux_state.policy);
+
+	if (kern) {
+		tclass = unmap_class(&policy->map, orig_tclass);
+		sock = security_is_socket_class(orig_tclass);
+	} else {
+		tclass = orig_tclass;
+		sock = security_is_socket_class(map_class(&policy->map,
+							  tclass));
+	}
+
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	sentry = sidtab_search_entry(sidtab, ssid);
+	if (!sentry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, ssid);
+		rc = -EINVAL;
+		goto out_unlock;
+	}
+	tentry = sidtab_search_entry(sidtab, tsid);
+	if (!tentry) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, tsid);
+		rc = -EINVAL;
+		goto out_unlock;
+	}
+
+	scontext = &sentry->context;
+	tcontext = &tentry->context;
+
+	if (tclass && tclass <= policydb->p_classes.nprim)
+		cladatum = policydb->class_val_to_struct[tclass - 1];
+
+	/* Set the user identity. */
+	switch (specified) {
+	case AVTAB_TRANSITION:
+	case AVTAB_CHANGE:
+		if (cladatum && cladatum->default_user == DEFAULT_TARGET) {
+			newcontext.user = tcontext->user;
+		} else {
+			/* notice this gets both DEFAULT_SOURCE and unset */
+			/* Use the process user identity. */
+			newcontext.user = scontext->user;
+		}
+		break;
+	case AVTAB_MEMBER:
+		/* Use the related object owner. */
+		newcontext.user = tcontext->user;
+		break;
+	}
+
+	/* Set the role to default values. */
+	if (cladatum && cladatum->default_role == DEFAULT_SOURCE) {
+		newcontext.role = scontext->role;
+	} else if (cladatum && cladatum->default_role == DEFAULT_TARGET) {
+		newcontext.role = tcontext->role;
+	} else {
+		if ((tclass == policydb->process_class) || sock)
+			newcontext.role = scontext->role;
+		else
+			newcontext.role = OBJECT_R_VAL;
+	}
+
+	/* Set the type.
+	 * Look for a type transition/member/change rule.
+	 */
+	avkey.source_type = scontext->type;
+	avkey.target_type = tcontext->type;
+	avkey.target_class = tclass;
+	avkey.specified = specified;
+	avnode = avtab_search_node(&policydb->te_avtab, &avkey);
+
+	/* If no permanent rule, also check for enabled conditional rules */
+	if (!avnode) {
+		node = avtab_search_node(&policydb->te_cond_avtab, &avkey);
+		for (; node; node = avtab_search_node_next(node, specified)) {
+			if (node->key.specified & AVTAB_ENABLED) {
+				avnode = node;
+				break;
+			}
+		}
+	}
+
+	/* If a permanent rule is found, use the type from
+	 * the type transition/member/change rule. Otherwise,
+	 * set the type to its default values.
+	 */
+	if (avnode) {
+		newcontext.type = avnode->datum.u.data;
+	} else if (cladatum && cladatum->default_type == DEFAULT_SOURCE) {
+		newcontext.type = scontext->type;
+	} else if (cladatum && cladatum->default_type == DEFAULT_TARGET) {
+		newcontext.type = tcontext->type;
+	} else {
+		if ((tclass == policydb->process_class) || sock) {
+			/* Use the type of process. */
+			newcontext.type = scontext->type;
+		} else {
+			/* Use the type of the related object. */
+			newcontext.type = tcontext->type;
+		}
+	}
+
+	/* if we have a objname this is a file trans check so check those rules */
+	if (objname)
+		filename_compute_type(policydb, &newcontext, scontext->type,
+				      tcontext->type, tclass, objname);
+
+	/* Check for class-specific changes. */
+	if (specified & AVTAB_TRANSITION) {
+		/* Look for a role transition rule. */
+		struct role_trans_datum *rtd;
+		struct role_trans_key rtk = {
+			.role = scontext->role,
+			.type = tcontext->type,
+			.tclass = tclass,
+		};
+
+		rtd = policydb_roletr_search(policydb, &rtk);
+		if (rtd)
+			newcontext.role = rtd->new_role;
+	}
+
+	/* Set the MLS attributes.
+	   This is done last because it may allocate memory. */
+	rc = mls_compute_sid(policydb, scontext, tcontext, tclass, specified,
+			     &newcontext, sock);
+	if (rc)
+		goto out_unlock;
+
+	/* Check the validity of the context. */
+	if (!policydb_context_isvalid(policydb, &newcontext)) {
+		rc = compute_sid_handle_invalid_context(policy, sentry,
+							tentry, tclass,
+							&newcontext);
+		if (rc)
+			goto out_unlock;
+	}
+	/* Obtain the sid for the context. */
+	if (context_equal(scontext, &newcontext))
+		*out_sid = ssid;
+	else if (context_equal(tcontext, &newcontext))
+		*out_sid = tsid;
+	else {
+		rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			context_destroy(&newcontext);
+			goto retry;
+		}
+	}
+out_unlock:
+	rcu_read_unlock();
+	context_destroy(&newcontext);
+out:
+	return rc;
+}
+
+/**
+ * security_transition_sid - Compute the SID for a new subject/object.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @qstr: object name
+ * @out_sid: security identifier for new subject/object
+ *
+ * Compute a SID to use for labeling a new subject or object in the
+ * class @tclass based on a SID pair (@ssid, @tsid).
+ * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM
+ * if insufficient memory is available, or %0 if the new SID was
+ * computed successfully.
+ */
+int security_transition_sid(u32 ssid, u32 tsid, u16 tclass,
+			    const struct qstr *qstr, u32 *out_sid)
+{
+	return security_compute_sid(ssid, tsid, tclass,
+				    AVTAB_TRANSITION,
+				    qstr ? qstr->name : NULL, out_sid, true);
+}
+
+int security_transition_sid_user(u32 ssid, u32 tsid, u16 tclass,
+				 const char *objname, u32 *out_sid)
+{
+	return security_compute_sid(ssid, tsid, tclass,
+				    AVTAB_TRANSITION,
+				    objname, out_sid, false);
+}
+
+/**
+ * security_member_sid - Compute the SID for member selection.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @out_sid: security identifier for selected member
+ *
+ * Compute a SID to use when selecting a member of a polyinstantiated
+ * object of class @tclass based on a SID pair (@ssid, @tsid).
+ * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM
+ * if insufficient memory is available, or %0 if the SID was
+ * computed successfully.
+ */
+int security_member_sid(u32 ssid,
+			u32 tsid,
+			u16 tclass,
+			u32 *out_sid)
+{
+	return security_compute_sid(ssid, tsid, tclass,
+				    AVTAB_MEMBER, NULL,
+				    out_sid, false);
+}
+
+/**
+ * security_change_sid - Compute the SID for object relabeling.
+ * @ssid: source security identifier
+ * @tsid: target security identifier
+ * @tclass: target security class
+ * @out_sid: security identifier for selected member
+ *
+ * Compute a SID to use for relabeling an object of class @tclass
+ * based on a SID pair (@ssid, @tsid).
+ * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM
+ * if insufficient memory is available, or %0 if the SID was
+ * computed successfully.
+ */
+int security_change_sid(u32 ssid,
+			u32 tsid,
+			u16 tclass,
+			u32 *out_sid)
+{
+	return security_compute_sid(ssid, tsid, tclass, AVTAB_CHANGE, NULL,
+				    out_sid, false);
+}
+
+static inline int convert_context_handle_invalid_context(
+	struct policydb *policydb,
+	struct context *context)
+{
+	char *s;
+	u32 len;
+
+	if (enforcing_enabled())
+		return -EINVAL;
+
+	if (!context_struct_to_string(policydb, context, &s, &len)) {
+		pr_warn("SELinux:  Context %s would be invalid if enforcing\n",
+			s);
+		kfree(s);
+	}
+	return 0;
+}
+
+/**
+ * services_convert_context - Convert a security context across policies.
+ * @args: populated convert_context_args struct
+ * @oldc: original context
+ * @newc: converted context
+ * @gfp_flags: allocation flags
+ *
+ * Convert the values in the security context structure @oldc from the values
+ * specified in the policy @args->oldp to the values specified in the policy
+ * @args->newp, storing the new context in @newc, and verifying that the
+ * context is valid under the new policy.
+ */
+int services_convert_context(struct convert_context_args *args,
+			     struct context *oldc, struct context *newc,
+			     gfp_t gfp_flags)
+{
+	struct ocontext *oc;
+	struct role_datum *role;
+	struct type_datum *typdatum;
+	struct user_datum *usrdatum;
+	char *s;
+	u32 len;
+	int rc;
+
+	if (oldc->str) {
+		s = kstrdup(oldc->str, gfp_flags);
+		if (!s)
+			return -ENOMEM;
+
+		rc = string_to_context_struct(args->newp, NULL, s, newc, SECSID_NULL);
+		if (rc == -EINVAL) {
+			/*
+			 * Retain string representation for later mapping.
+			 *
+			 * IMPORTANT: We need to copy the contents of oldc->str
+			 * back into s again because string_to_context_struct()
+			 * may have garbled it.
+			 */
+			memcpy(s, oldc->str, oldc->len);
+			context_init(newc);
+			newc->str = s;
+			newc->len = oldc->len;
+			return 0;
+		}
+		kfree(s);
+		if (rc) {
+			/* Other error condition, e.g. ENOMEM. */
+			pr_err("SELinux:   Unable to map context %s, rc = %d.\n",
+			       oldc->str, -rc);
+			return rc;
+		}
+		pr_info("SELinux:  Context %s became valid (mapped).\n",
+			oldc->str);
+		return 0;
+	}
+
+	context_init(newc);
+
+	/* Convert the user. */
+	usrdatum = symtab_search(&args->newp->p_users,
+				 sym_name(args->oldp, SYM_USERS, oldc->user - 1));
+	if (!usrdatum)
+		goto bad;
+	newc->user = usrdatum->value;
+
+	/* Convert the role. */
+	role = symtab_search(&args->newp->p_roles,
+			     sym_name(args->oldp, SYM_ROLES, oldc->role - 1));
+	if (!role)
+		goto bad;
+	newc->role = role->value;
+
+	/* Convert the type. */
+	typdatum = symtab_search(&args->newp->p_types,
+				 sym_name(args->oldp, SYM_TYPES, oldc->type - 1));
+	if (!typdatum)
+		goto bad;
+	newc->type = typdatum->value;
+
+	/* Convert the MLS fields if dealing with MLS policies */
+	if (args->oldp->mls_enabled && args->newp->mls_enabled) {
+		rc = mls_convert_context(args->oldp, args->newp, oldc, newc);
+		if (rc)
+			goto bad;
+	} else if (!args->oldp->mls_enabled && args->newp->mls_enabled) {
+		/*
+		 * Switching between non-MLS and MLS policy:
+		 * ensure that the MLS fields of the context for all
+		 * existing entries in the sidtab are filled in with a
+		 * suitable default value, likely taken from one of the
+		 * initial SIDs.
+		 */
+		oc = args->newp->ocontexts[OCON_ISID];
+		while (oc && oc->sid[0] != SECINITSID_UNLABELED)
+			oc = oc->next;
+		if (!oc) {
+			pr_err("SELinux:  unable to look up"
+				" the initial SIDs list\n");
+			goto bad;
+		}
+		rc = mls_range_set(newc, &oc->context[0].range);
+		if (rc)
+			goto bad;
+	}
+
+	/* Check the validity of the new context. */
+	if (!policydb_context_isvalid(args->newp, newc)) {
+		rc = convert_context_handle_invalid_context(args->oldp, oldc);
+		if (rc)
+			goto bad;
+	}
+
+	return 0;
+bad:
+	/* Map old representation to string and save it. */
+	rc = context_struct_to_string(args->oldp, oldc, &s, &len);
+	if (rc)
+		return rc;
+	context_destroy(newc);
+	newc->str = s;
+	newc->len = len;
+	pr_info("SELinux:  Context %s became invalid (unmapped).\n",
+		newc->str);
+	return 0;
+}
+
+static void security_load_policycaps(struct selinux_policy *policy)
+{
+	struct policydb *p;
+	unsigned int i;
+	struct ebitmap_node *node;
+
+	p = &policy->policydb;
+
+	for (i = 0; i < ARRAY_SIZE(selinux_state.policycap); i++)
+		WRITE_ONCE(selinux_state.policycap[i],
+			ebitmap_get_bit(&p->policycaps, i));
+
+	for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++)
+		pr_info("SELinux:  policy capability %s=%d\n",
+			selinux_policycap_names[i],
+			ebitmap_get_bit(&p->policycaps, i));
+
+	ebitmap_for_each_positive_bit(&p->policycaps, node, i) {
+		if (i >= ARRAY_SIZE(selinux_policycap_names))
+			pr_info("SELinux:  unknown policy capability %u\n",
+				i);
+	}
+}
+
+static int security_preserve_bools(struct selinux_policy *oldpolicy,
+				struct selinux_policy *newpolicy);
+
+static void selinux_policy_free(struct selinux_policy *policy)
+{
+	if (!policy)
+		return;
+
+	sidtab_destroy(policy->sidtab);
+	kfree(policy->map.mapping);
+	policydb_destroy(&policy->policydb);
+	kfree(policy->sidtab);
+	kfree(policy);
+}
+
+static void selinux_policy_cond_free(struct selinux_policy *policy)
+{
+	cond_policydb_destroy_dup(&policy->policydb);
+	kfree(policy);
+}
+
+void selinux_policy_cancel(struct selinux_load_state *load_state)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *oldpolicy;
+
+	oldpolicy = rcu_dereference_protected(state->policy,
+					lockdep_is_held(&state->policy_mutex));
+
+	/* a first load has no outgoing policy and converted nothing */
+	if (oldpolicy)
+		sidtab_cancel_convert(oldpolicy->sidtab);
+	selinux_policy_free(load_state->policy);
+	kfree(load_state->convert_data);
+}
+
+static void selinux_notify_policy_change(u32 seqno)
+{
+	/* Flush external caches and notify userspace of policy load */
+	avc_ss_reset(seqno);
+	selnl_notify_policyload(seqno);
+	selinux_status_update_policyload(seqno);
+	selinux_netlbl_cache_invalidate();
+	selinux_xfrm_notify_policyload();
+	selinux_ima_measure_state_locked();
+}
+
+void selinux_policy_commit(struct selinux_load_state *load_state)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *oldpolicy, *newpolicy = load_state->policy;
+	unsigned long flags;
+	u32 seqno;
+
+	oldpolicy = rcu_dereference_protected(state->policy,
+					lockdep_is_held(&state->policy_mutex));
+
+	/* If switching between different policy types, log MLS status */
+	if (oldpolicy) {
+		if (oldpolicy->policydb.mls_enabled && !newpolicy->policydb.mls_enabled)
+			pr_info("SELinux: Disabling MLS support...\n");
+		else if (!oldpolicy->policydb.mls_enabled && newpolicy->policydb.mls_enabled)
+			pr_info("SELinux: Enabling MLS support...\n");
+	}
+
+	/* Set latest granting seqno for new policy. */
+	if (oldpolicy)
+		newpolicy->latest_granting = oldpolicy->latest_granting + 1;
+	else
+		newpolicy->latest_granting = 1;
+	seqno = newpolicy->latest_granting;
+
+	/* Install the new policy. */
+	if (oldpolicy) {
+		sidtab_freeze_begin(oldpolicy->sidtab, &flags);
+		rcu_assign_pointer(state->policy, newpolicy);
+		sidtab_freeze_end(oldpolicy->sidtab, &flags);
+	} else {
+		rcu_assign_pointer(state->policy, newpolicy);
+	}
+
+	/* Load the policycaps from the new policy */
+	security_load_policycaps(newpolicy);
+
+	if (!selinux_initialized()) {
+		/*
+		 * After first policy load, the security server is
+		 * marked as initialized and ready to handle requests and
+		 * any objects created prior to policy load are then labeled.
+		 */
+		selinux_mark_initialized();
+		selinux_complete_init();
+	}
+
+	/* Free the old policy */
+	synchronize_rcu();
+	selinux_policy_free(oldpolicy);
+	kfree(load_state->convert_data);
+
+	/* Notify others of the policy change */
+	selinux_notify_policy_change(seqno);
+}
+
+/**
+ * security_load_policy - Load a security policy configuration.
+ * @data: binary policy data
+ * @len: length of data in bytes
+ * @load_state: policy load state
+ *
+ * Load a new set of security policy configuration data,
+ * validate it and convert the SID table as necessary.
+ * This function will flush the access vector cache after
+ * loading the new policy.
+ */
+int security_load_policy(void *data, size_t len,
+			 struct selinux_load_state *load_state)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *newpolicy, *oldpolicy;
+	struct selinux_policy_convert_data *convert_data;
+	int rc = 0;
+	struct policy_file file = { data, len }, *fp = &file;
+
+	newpolicy = kzalloc_obj(*newpolicy);
+	if (!newpolicy)
+		return -ENOMEM;
+
+	newpolicy->sidtab = kzalloc_obj(*newpolicy->sidtab);
+	if (!newpolicy->sidtab) {
+		rc = -ENOMEM;
+		goto err_policy;
+	}
+
+	rc = policydb_read(&newpolicy->policydb, fp);
+	if (rc)
+		goto err_sidtab;
+
+	newpolicy->policydb.len = len;
+	rc = selinux_set_mapping(&newpolicy->policydb, secclass_map,
+				&newpolicy->map);
+	if (rc)
+		goto err_policydb;
+
+	rc = policydb_load_isids(&newpolicy->policydb, newpolicy->sidtab);
+	if (rc) {
+		pr_err("SELinux:  unable to load the initial SIDs\n");
+		goto err_mapping;
+	}
+
+	if (!selinux_initialized()) {
+		/* First policy load, so no need to preserve state from old policy */
+		load_state->policy = newpolicy;
+		load_state->convert_data = NULL;
+		return 0;
+	}
+
+	oldpolicy = rcu_dereference_protected(state->policy,
+					lockdep_is_held(&state->policy_mutex));
+
+	/* Preserve active boolean values from the old policy */
+	rc = security_preserve_bools(oldpolicy, newpolicy);
+	if (rc) {
+		pr_err("SELinux:  unable to preserve booleans\n");
+		goto err_free_isids;
+	}
+
+	/*
+	 * Convert the internal representations of contexts
+	 * in the new SID table.
+	 */
+
+	convert_data = kmalloc_obj(*convert_data);
+	if (!convert_data) {
+		rc = -ENOMEM;
+		goto err_free_isids;
+	}
+
+	convert_data->args.oldp = &oldpolicy->policydb;
+	convert_data->args.newp = &newpolicy->policydb;
+
+	convert_data->sidtab_params.args = &convert_data->args;
+	convert_data->sidtab_params.target = newpolicy->sidtab;
+
+	rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params);
+	if (rc) {
+		pr_err("SELinux:  unable to convert the internal"
+			" representation of contexts in the new SID"
+			" table\n");
+		goto err_free_convert_data;
+	}
+
+	load_state->policy = newpolicy;
+	load_state->convert_data = convert_data;
+	return 0;
+
+err_free_convert_data:
+	kfree(convert_data);
+err_free_isids:
+	sidtab_destroy(newpolicy->sidtab);
+err_mapping:
+	kfree(newpolicy->map.mapping);
+err_policydb:
+	policydb_destroy(&newpolicy->policydb);
+err_sidtab:
+	kfree(newpolicy->sidtab);
+err_policy:
+	kfree(newpolicy);
+
+	return rc;
+}
+
+/**
+ * ocontext_to_sid - Helper to safely get sid for an ocontext
+ * @sidtab: SID table
+ * @c: ocontext structure
+ * @index: index of the context entry (0 or 1)
+ * @out_sid: pointer to the resulting SID value
+ *
+ * For all ocontexts except OCON_ISID the SID fields are populated
+ * on-demand when needed. Since updating the SID value is an SMP-sensitive
+ * operation, this helper must be used to do that safely.
+ *
+ * WARNING: This function may return -ESTALE, indicating that the caller
+ * must retry the operation after re-acquiring the policy pointer!
+ */
+static int ocontext_to_sid(struct sidtab *sidtab, struct ocontext *c,
+			   size_t index, u32 *out_sid)
+{
+	int rc;
+	u32 sid;
+
+	/* Ensure the associated sidtab entry is visible to this thread. */
+	sid = smp_load_acquire(&c->sid[index]);
+	if (!sid) {
+		rc = sidtab_context_to_sid(sidtab, &c->context[index], &sid);
+		if (rc)
+			return rc;
+
+		/*
+		 * Ensure the new sidtab entry is visible to other threads
+		 * when they see the SID.
+		 */
+		smp_store_release(&c->sid[index], sid);
+	}
+	*out_sid = sid;
+	return 0;
+}
+
+/**
+ * security_port_sid - Obtain the SID for a port.
+ * @protocol: protocol number
+ * @port: port number
+ * @out_sid: security identifier
+ */
+int security_port_sid(u8 protocol, u16 port, u32 *out_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct ocontext *c;
+	int rc;
+
+	if (!selinux_initialized()) {
+		*out_sid = SECINITSID_PORT;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	c = policydb->ocontexts[OCON_PORT];
+	while (c) {
+		if (c->u.port.protocol == protocol &&
+		    c->u.port.low_port <= port &&
+		    c->u.port.high_port >= port)
+			break;
+		c = c->next;
+	}
+
+	if (c) {
+		rc = ocontext_to_sid(sidtab, c, 0, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else {
+		*out_sid = SECINITSID_PORT;
+	}
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/**
+ * security_ib_pkey_sid - Obtain the SID for a pkey.
+ * @subnet_prefix: Subnet Prefix
+ * @pkey_num: pkey number
+ * @out_sid: security identifier
+ */
+int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct ocontext *c;
+	int rc;
+
+	if (!selinux_initialized()) {
+		*out_sid = SECINITSID_UNLABELED;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	c = policydb->ocontexts[OCON_IBPKEY];
+	while (c) {
+		if (c->u.ibpkey.low_pkey <= pkey_num &&
+		    c->u.ibpkey.high_pkey >= pkey_num &&
+		    c->u.ibpkey.subnet_prefix == subnet_prefix)
+			break;
+
+		c = c->next;
+	}
+
+	if (c) {
+		rc = ocontext_to_sid(sidtab, c, 0, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else
+		*out_sid = SECINITSID_UNLABELED;
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/**
+ * security_ib_endport_sid - Obtain the SID for a subnet management interface.
+ * @dev_name: device name
+ * @port_num: port number
+ * @out_sid: security identifier
+ */
+int security_ib_endport_sid(const char *dev_name, u8 port_num, u32 *out_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct ocontext *c;
+	int rc;
+
+	if (!selinux_initialized()) {
+		*out_sid = SECINITSID_UNLABELED;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	c = policydb->ocontexts[OCON_IBENDPORT];
+	while (c) {
+		if (c->u.ibendport.port == port_num &&
+		    !strncmp(c->u.ibendport.dev_name,
+			     dev_name,
+			     IB_DEVICE_NAME_MAX))
+			break;
+
+		c = c->next;
+	}
+
+	if (c) {
+		rc = ocontext_to_sid(sidtab, c, 0, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else
+		*out_sid = SECINITSID_UNLABELED;
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/**
+ * security_netif_sid - Obtain the SID for a network interface.
+ * @name: interface name
+ * @if_sid: interface SID
+ */
+int security_netif_sid(const char *name, u32 *if_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	int rc;
+	struct ocontext *c;
+	bool wildcard_support;
+
+	if (!selinux_initialized()) {
+		*if_sid = SECINITSID_NETIF;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+	wildcard_support = ebitmap_get_bit(&policydb->policycaps, POLICYDB_CAP_NETIF_WILDCARD);
+
+	c = policydb->ocontexts[OCON_NETIF];
+	while (c) {
+		if (wildcard_support) {
+			if (match_wildcard(c->u.name, name))
+				break;
+		} else {
+			if (strcmp(c->u.name, name) == 0)
+				break;
+		}
+
+		c = c->next;
+	}
+
+	if (c) {
+		rc = ocontext_to_sid(sidtab, c, 0, if_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else
+		*if_sid = SECINITSID_NETIF;
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+static bool match_ipv6_addrmask(const u32 input[4], const u32 addr[4], const u32 mask[4])
+{
+	int i;
+
+	for (i = 0; i < 4; i++)
+		if (addr[i] != (input[i] & mask[i]))
+			return false;
+
+	return true;
+}
+
+/**
+ * security_node_sid - Obtain the SID for a node (host).
+ * @domain: communication domain aka address family
+ * @addrp: address
+ * @addrlen: address length in bytes
+ * @out_sid: security identifier
+ */
+int security_node_sid(u16 domain,
+		      const void *addrp,
+		      u32 addrlen,
+		      u32 *out_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	int rc;
+	struct ocontext *c;
+
+	if (!selinux_initialized()) {
+		*out_sid = SECINITSID_NODE;
+		return 0;
+	}
+
+retry:
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	switch (domain) {
+	case AF_INET: {
+		u32 addr;
+
+		rc = -EINVAL;
+		if (addrlen != sizeof(u32))
+			goto out;
+
+		addr = *((const u32 *)addrp);
+
+		c = policydb->ocontexts[OCON_NODE];
+		while (c) {
+			if (c->u.node.addr == (addr & c->u.node.mask))
+				break;
+			c = c->next;
+		}
+		break;
+	}
+
+	case AF_INET6:
+		rc = -EINVAL;
+		if (addrlen != sizeof(u64) * 2)
+			goto out;
+		c = policydb->ocontexts[OCON_NODE6];
+		while (c) {
+			if (match_ipv6_addrmask(addrp, c->u.node6.addr,
+						c->u.node6.mask))
+				break;
+			c = c->next;
+		}
+		break;
+
+	default:
+		rc = 0;
+		*out_sid = SECINITSID_NODE;
+		goto out;
+	}
+
+	if (c) {
+		rc = ocontext_to_sid(sidtab, c, 0, out_sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else {
+		*out_sid = SECINITSID_NODE;
+	}
+
+	rc = 0;
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/**
+ * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem
+ * @policy: policy
+ * @fstype: filesystem type
+ * @path: path from root of mount
+ * @orig_sclass: file security class
+ * @sid: SID for path
+ *
+ * Obtain a SID to use for a file in a filesystem that
+ * cannot support xattr or use a fixed labeling behavior like
+ * transition SIDs or task SIDs.
+ *
+ * WARNING: This function may return -ESTALE, indicating that the caller
+ * must retry the operation after re-acquiring the policy pointer!
+ */
+static inline int __security_genfs_sid(struct selinux_policy *policy,
+				       const char *fstype,
+				       const char *path,
+				       u16 orig_sclass,
+				       u32 *sid)
+{
+	struct policydb *policydb = &policy->policydb;
+	struct sidtab *sidtab = policy->sidtab;
+	u16 sclass;
+	struct genfs *genfs;
+	struct ocontext *c;
+	int cmp = 0;
+	bool wildcard;
+
+	while (path[0] == '/' && path[1] == '/')
+		path++;
+
+	sclass = unmap_class(&policy->map, orig_sclass);
+	*sid = SECINITSID_UNLABELED;
+
+	for (genfs = policydb->genfs; genfs; genfs = genfs->next) {
+		cmp = strcmp(fstype, genfs->fstype);
+		if (cmp <= 0)
+			break;
+	}
+
+	if (!genfs || cmp)
+		return -ENOENT;
+
+	wildcard = ebitmap_get_bit(&policy->policydb.policycaps,
+				   POLICYDB_CAP_GENFS_SECLABEL_WILDCARD);
+	for (c = genfs->head; c; c = c->next) {
+		if (!c->v.sclass || sclass == c->v.sclass) {
+			if (wildcard) {
+				if (match_wildcard(c->u.name, path))
+					break;
+			} else {
+				size_t len = strlen(c->u.name);
+
+				if ((strncmp(c->u.name, path, len)) == 0)
+					break;
+			}
+		}
+	}
+
+	if (!c)
+		return -ENOENT;
+
+	return ocontext_to_sid(sidtab, c, 0, sid);
+}
+
+/**
+ * security_genfs_sid - Obtain a SID for a file in a filesystem
+ * @fstype: filesystem type
+ * @path: path from root of mount
+ * @orig_sclass: file security class
+ * @sid: SID for path
+ *
+ * Acquire policy_rwlock before calling __security_genfs_sid() and release
+ * it afterward.
+ */
+int security_genfs_sid(const char *fstype,
+		       const char *path,
+		       u16 orig_sclass,
+		       u32 *sid)
+{
+	struct selinux_policy *policy;
+	int retval;
+
+	if (!selinux_initialized()) {
+		*sid = SECINITSID_UNLABELED;
+		return 0;
+	}
+
+	do {
+		rcu_read_lock();
+		policy = rcu_dereference(selinux_state.policy);
+		retval = __security_genfs_sid(policy, fstype, path,
+					      orig_sclass, sid);
+		rcu_read_unlock();
+	} while (retval == -ESTALE);
+	return retval;
+}
+
+int selinux_policy_genfs_sid(struct selinux_policy *policy,
+			const char *fstype,
+			const char *path,
+			u16 orig_sclass,
+			u32 *sid)
+{
+	/* no lock required, policy is not yet accessible by other threads */
+	return __security_genfs_sid(policy, fstype, path, orig_sclass, sid);
+}
+
+/**
+ * security_fs_use - Determine how to handle labeling for a filesystem.
+ * @sb: superblock in question
+ */
+int security_fs_use(struct super_block *sb)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	int rc;
+	struct ocontext *c;
+	struct superblock_security_struct *sbsec = selinux_superblock(sb);
+	const char *fstype = sb->s_type->name;
+
+	if (!selinux_initialized()) {
+		sbsec->behavior = SECURITY_FS_USE_NONE;
+		sbsec->sid = SECINITSID_UNLABELED;
+		return 0;
+	}
+
+retry:
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	c = policydb->ocontexts[OCON_FSUSE];
+	while (c) {
+		if (strcmp(fstype, c->u.name) == 0)
+			break;
+		c = c->next;
+	}
+
+	if (c) {
+		sbsec->behavior = c->v.behavior;
+		rc = ocontext_to_sid(sidtab, c, 0, &sbsec->sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+	} else {
+		rc = __security_genfs_sid(policy, fstype, "/",
+					SECCLASS_DIR, &sbsec->sid);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc) {
+			sbsec->behavior = SECURITY_FS_USE_NONE;
+			rc = 0;
+		} else {
+			sbsec->behavior = SECURITY_FS_USE_GENFS;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+int security_get_bools(struct selinux_policy *policy,
+		       u32 *len, char ***names, int **values)
+{
+	struct policydb *policydb;
+	u32 i;
+	int rc;
+
+	policydb = &policy->policydb;
+
+	*names = NULL;
+	*values = NULL;
+
+	rc = 0;
+	*len = policydb->p_bools.nprim;
+	if (!*len)
+		goto out;
+
+	rc = -ENOMEM;
+	*names = kcalloc(*len, sizeof(char *), GFP_ATOMIC);
+	if (!*names)
+		goto err;
+
+	rc = -ENOMEM;
+	*values = kzalloc_objs(int, *len, GFP_ATOMIC);
+	if (!*values)
+		goto err;
+
+	for (i = 0; i < *len; i++) {
+		(*values)[i] = policydb->bool_val_to_struct[i]->state;
+
+		rc = -ENOMEM;
+		(*names)[i] = kstrdup(sym_name(policydb, SYM_BOOLS, i),
+				      GFP_ATOMIC);
+		if (!(*names)[i])
+			goto err;
+	}
+	rc = 0;
+out:
+	return rc;
+err:
+	if (*names) {
+		for (i = 0; i < *len; i++)
+			kfree((*names)[i]);
+		kfree(*names);
+	}
+	kfree(*values);
+	*len = 0;
+	*names = NULL;
+	*values = NULL;
+	goto out;
+}
+
+
+int security_set_bools(u32 len, const int *values)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *newpolicy, *oldpolicy;
+	int rc;
+	u32 i, seqno = 0;
+
+	if (!selinux_initialized())
+		return -EINVAL;
+
+	oldpolicy = rcu_dereference_protected(state->policy,
+					lockdep_is_held(&state->policy_mutex));
+
+	/* Consistency check on number of booleans, should never fail */
+	if (WARN_ON(len != oldpolicy->policydb.p_bools.nprim))
+		return -EINVAL;
+
+	newpolicy = kmemdup(oldpolicy, sizeof(*newpolicy), GFP_KERNEL);
+	if (!newpolicy)
+		return -ENOMEM;
+
+	/*
+	 * Deep copy only the parts of the policydb that might be
+	 * modified as a result of changing booleans.
+	 */
+	rc = cond_policydb_dup(&newpolicy->policydb, &oldpolicy->policydb);
+	if (rc) {
+		kfree(newpolicy);
+		return -ENOMEM;
+	}
+
+	/* Update the boolean states in the copy */
+	for (i = 0; i < len; i++) {
+		int new_state = !!values[i];
+		int old_state = newpolicy->policydb.bool_val_to_struct[i]->state;
+
+		if (new_state != old_state) {
+			audit_log(audit_context(), GFP_ATOMIC,
+				AUDIT_MAC_CONFIG_CHANGE,
+				"bool=%s val=%d old_val=%d auid=%u ses=%u",
+				sym_name(&newpolicy->policydb, SYM_BOOLS, i),
+				new_state,
+				old_state,
+				from_kuid(&init_user_ns, audit_get_loginuid(current)),
+				audit_get_sessionid(current));
+			newpolicy->policydb.bool_val_to_struct[i]->state = new_state;
+		}
+	}
+
+	/* Re-evaluate the conditional rules in the copy */
+	evaluate_cond_nodes(&newpolicy->policydb);
+
+	/* Set latest granting seqno for new policy */
+	newpolicy->latest_granting = oldpolicy->latest_granting + 1;
+	seqno = newpolicy->latest_granting;
+
+	/* Install the new policy */
+	rcu_assign_pointer(state->policy, newpolicy);
+
+	/*
+	 * Free the conditional portions of the old policydb
+	 * that were copied for the new policy, and the oldpolicy
+	 * structure itself but not what it references.
+	 */
+	synchronize_rcu();
+	selinux_policy_cond_free(oldpolicy);
+
+	/* Notify others of the policy change */
+	selinux_notify_policy_change(seqno);
+	return 0;
+}
+
+int security_get_bool_value(u32 index)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	int rc;
+	u32 len;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+
+	rc = -EFAULT;
+	len = policydb->p_bools.nprim;
+	if (index >= len)
+		goto out;
+
+	rc = policydb->bool_val_to_struct[index]->state;
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+static int security_preserve_bools(struct selinux_policy *oldpolicy,
+				struct selinux_policy *newpolicy)
+{
+	int rc, *bvalues = NULL;
+	char **bnames = NULL;
+	struct cond_bool_datum *booldatum;
+	u32 i, nbools = 0;
+
+	rc = security_get_bools(oldpolicy, &nbools, &bnames, &bvalues);
+	if (rc)
+		goto out;
+	for (i = 0; i < nbools; i++) {
+		booldatum = symtab_search(&newpolicy->policydb.p_bools,
+					bnames[i]);
+		if (booldatum)
+			booldatum->state = bvalues[i];
+	}
+	evaluate_cond_nodes(&newpolicy->policydb);
+
+out:
+	if (bnames) {
+		for (i = 0; i < nbools; i++)
+			kfree(bnames[i]);
+	}
+	kfree(bnames);
+	kfree(bvalues);
+	return rc;
+}
+
+/*
+ * security_sid_mls_copy() - computes a new sid based on the given
+ * sid and the mls portion of mls_sid.
+ */
+int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	struct context *context1;
+	struct context *context2;
+	struct context newcon;
+	char *s;
+	u32 len;
+	int rc;
+
+	if (!selinux_initialized()) {
+		*new_sid = sid;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	context_init(&newcon);
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	if (!policydb->mls_enabled) {
+		*new_sid = sid;
+		goto out_unlock;
+	}
+
+	rc = -EINVAL;
+	context1 = sidtab_search(sidtab, sid);
+	if (!context1) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, sid);
+		goto out_unlock;
+	}
+
+	rc = -EINVAL;
+	context2 = sidtab_search(sidtab, mls_sid);
+	if (!context2) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+			__func__, mls_sid);
+		goto out_unlock;
+	}
+
+	newcon.user = context1->user;
+	newcon.role = context1->role;
+	newcon.type = context1->type;
+	rc = mls_context_cpy(&newcon, context2);
+	if (rc)
+		goto out_unlock;
+
+	/* Check the validity of the new context. */
+	if (!policydb_context_isvalid(policydb, &newcon)) {
+		rc = convert_context_handle_invalid_context(policydb,
+							&newcon);
+		if (rc) {
+			if (!context_struct_to_string(policydb, &newcon, &s,
+						      &len)) {
+				struct audit_buffer *ab;
+
+				ab = audit_log_start(audit_context(),
+						     GFP_ATOMIC,
+						     AUDIT_SELINUX_ERR);
+				audit_log_format(ab,
+						 "op=security_sid_mls_copy invalid_context=");
+				/* don't record NUL with untrusted strings */
+				audit_log_n_untrustedstring(ab, s, len - 1);
+				audit_log_end(ab);
+				kfree(s);
+			}
+			goto out_unlock;
+		}
+	}
+	rc = sidtab_context_to_sid(sidtab, &newcon, new_sid);
+	if (rc == -ESTALE) {
+		rcu_read_unlock();
+		context_destroy(&newcon);
+		goto retry;
+	}
+out_unlock:
+	rcu_read_unlock();
+	context_destroy(&newcon);
+	return rc;
+}
+
+/**
+ * security_net_peersid_resolve - Compare and resolve two network peer SIDs
+ * @nlbl_sid: NetLabel SID
+ * @nlbl_type: NetLabel labeling protocol type
+ * @xfrm_sid: XFRM SID
+ * @peer_sid: network peer sid
+ *
+ * Description:
+ * Compare the @nlbl_sid and @xfrm_sid values and if the two SIDs can be
+ * resolved into a single SID it is returned via @peer_sid and the function
+ * returns zero.  Otherwise @peer_sid is set to SECSID_NULL and the function
+ * returns a negative value.  A table summarizing the behavior is below:
+ *
+ *                                 | function return |      @sid
+ *   ------------------------------+-----------------+-----------------
+ *   no peer labels                |        0        |    SECSID_NULL
+ *   single peer label             |        0        |    <peer_label>
+ *   multiple, consistent labels   |        0        |    <peer_label>
+ *   multiple, inconsistent labels |    -<errno>     |    SECSID_NULL
+ *
+ */
+int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type,
+				 u32 xfrm_sid,
+				 u32 *peer_sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	int rc;
+	struct context *nlbl_ctx;
+	struct context *xfrm_ctx;
+
+	*peer_sid = SECSID_NULL;
+
+	/* handle the common (which also happens to be the set of easy) cases
+	 * right away, these two if statements catch everything involving a
+	 * single or absent peer SID/label */
+	if (xfrm_sid == SECSID_NULL) {
+		*peer_sid = nlbl_sid;
+		return 0;
+	}
+	/* NOTE: an nlbl_type == NETLBL_NLTYPE_UNLABELED is a "fallback" label
+	 * and is treated as if nlbl_sid == SECSID_NULL when a XFRM SID/label
+	 * is present */
+	if (nlbl_sid == SECSID_NULL || nlbl_type == NETLBL_NLTYPE_UNLABELED) {
+		*peer_sid = xfrm_sid;
+		return 0;
+	}
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	/*
+	 * We don't need to check initialized here since the only way both
+	 * nlbl_sid and xfrm_sid are not equal to SECSID_NULL would be if the
+	 * security server was initialized and state->initialized was true.
+	 */
+	if (!policydb->mls_enabled) {
+		rc = 0;
+		goto out;
+	}
+
+	rc = -EINVAL;
+	nlbl_ctx = sidtab_search(sidtab, nlbl_sid);
+	if (!nlbl_ctx) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, nlbl_sid);
+		goto out;
+	}
+	rc = -EINVAL;
+	xfrm_ctx = sidtab_search(sidtab, xfrm_sid);
+	if (!xfrm_ctx) {
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
+		       __func__, xfrm_sid);
+		goto out;
+	}
+	rc = (mls_context_equal(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES);
+	if (rc)
+		goto out;
+
+	/* at present NetLabel SIDs/labels really only carry MLS
+	 * information so if the MLS portion of the NetLabel SID
+	 * matches the MLS portion of the labeled XFRM SID/label
+	 * then pass along the XFRM SID as it is the most
+	 * expressive */
+	*peer_sid = xfrm_sid;
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+static int get_classes_callback(void *k, void *d, void *args)
+{
+	struct class_datum *datum = d;
+	char *name = k, **classes = args;
+	u16 value = datum->value - 1;
+
+	classes[value] = kstrdup(name, GFP_ATOMIC);
+	if (!classes[value])
+		return -ENOMEM;
+
+	return 0;
+}
+
+int security_get_classes(struct selinux_policy *policy,
+			 char ***classes, u32 *nclasses)
+{
+	struct policydb *policydb;
+	u32 i;
+	int rc;
+
+	policydb = &policy->policydb;
+
+	rc = -ENOMEM;
+	*nclasses = policydb->p_classes.nprim;
+	*classes = kcalloc(*nclasses, sizeof(**classes), GFP_ATOMIC);
+	if (!*classes)
+		goto out;
+
+	rc = hashtab_map(&policydb->p_classes.table, get_classes_callback,
+			 *classes);
+	if (rc)
+		goto err;
+
+	/*
+	 * The class symtab may be sparse, which policydb_class_isvalid() exists
+	 * to absorb; the callback fills this array by value, so an unclaimed
+	 * one leaves a NULL that sel_make_classes() hands to sel_make_dir().
+	 */
+	for (i = 0; i < *nclasses; i++) {
+		if (!(*classes)[i]) {
+			rc = -EINVAL;
+			goto err;
+		}
+	}
+
+out:
+	return rc;
+
+err:
+	for (i = 0; i < *nclasses; i++)
+		kfree((*classes)[i]);
+	kfree(*classes);
+	return rc;
+}
+
+static int get_permissions_callback(void *k, void *d, void *args)
+{
+	struct perm_datum *datum = d;
+	char *name = k, **perms = args;
+	u32 value = datum->value - 1;
+
+	perms[value] = kstrdup(name, GFP_ATOMIC);
+	if (!perms[value])
+		return -ENOMEM;
+
+	return 0;
+}
+
+int security_get_permissions(struct selinux_policy *policy,
+			     const char *class, char ***perms, u32 *nperms)
+{
+	struct policydb *policydb;
+	u32 i;
+	int rc;
+	struct class_datum *match;
+
+	policydb = &policy->policydb;
+
+	rc = -EINVAL;
+	match = symtab_search(&policydb->p_classes, class);
+	if (!match) {
+		pr_err("SELinux: %s:  unrecognized class %s\n",
+			__func__, class);
+		goto out;
+	}
+
+	rc = -ENOMEM;
+	*nperms = match->permissions.nprim;
+	*perms = kcalloc(*nperms, sizeof(**perms), GFP_ATOMIC);
+	if (!*perms)
+		goto out;
+
+	if (match->comdatum) {
+		rc = hashtab_map(&match->comdatum->permissions.table,
+				 get_permissions_callback, *perms);
+		if (rc)
+			goto err;
+	}
+
+	rc = hashtab_map(&match->permissions.table, get_permissions_callback,
+			 *perms);
+	if (rc)
+		goto err;
+
+out:
+	return rc;
+
+err:
+	for (i = 0; i < *nperms; i++)
+		kfree((*perms)[i]);
+	kfree(*perms);
+	return rc;
+}
+
+int security_get_reject_unknown(void)
+{
+	struct selinux_policy *policy;
+	int value;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	value = policy->policydb.reject_unknown;
+	rcu_read_unlock();
+	return value;
+}
+
+int security_get_allow_unknown(void)
+{
+	struct selinux_policy *policy;
+	int value;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	value = policy->policydb.allow_unknown;
+	rcu_read_unlock();
+	return value;
+}
+
+/**
+ * security_policycap_supported - Check for a specific policy capability
+ * @req_cap: capability
+ *
+ * Description:
+ * This function queries the currently loaded policy to see if it supports the
+ * capability specified by @req_cap.  Returns true (1) if the capability is
+ * supported, false (0) if it isn't supported.
+ *
+ */
+int security_policycap_supported(unsigned int req_cap)
+{
+	struct selinux_policy *policy;
+	int rc;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	rc = ebitmap_get_bit(&policy->policydb.policycaps, req_cap);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+struct selinux_audit_rule {
+	u32 au_seqno;
+	struct context au_ctxt;
+};
+
+int selinux_audit_rule_avc_callback(u32 event)
+{
+	if (event == AVC_CALLBACK_RESET)
+		return audit_update_lsm_rules();
+	return 0;
+}
+
+void selinux_audit_rule_free(void *vrule)
+{
+	struct selinux_audit_rule *rule = vrule;
+
+	if (rule) {
+		context_destroy(&rule->au_ctxt);
+		kfree(rule);
+	}
+}
+
+int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule,
+			    gfp_t gfp)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct selinux_audit_rule *tmprule;
+	struct role_datum *roledatum;
+	struct type_datum *typedatum;
+	struct user_datum *userdatum;
+	struct selinux_audit_rule **rule = (struct selinux_audit_rule **)vrule;
+	int rc = 0;
+
+	*rule = NULL;
+
+	if (!selinux_initialized())
+		return -EOPNOTSUPP;
+
+	switch (field) {
+	case AUDIT_SUBJ_USER:
+	case AUDIT_SUBJ_ROLE:
+	case AUDIT_SUBJ_TYPE:
+	case AUDIT_OBJ_USER:
+	case AUDIT_OBJ_ROLE:
+	case AUDIT_OBJ_TYPE:
+		/* only 'equals' and 'not equals' fit user, role, and type */
+		if (op != Audit_equal && op != Audit_not_equal)
+			return -EINVAL;
+		break;
+	case AUDIT_SUBJ_SEN:
+	case AUDIT_SUBJ_CLR:
+	case AUDIT_OBJ_LEV_LOW:
+	case AUDIT_OBJ_LEV_HIGH:
+		/* we do not allow a range, indicated by the presence of '-' */
+		if (strchr(rulestr, '-'))
+			return -EINVAL;
+		break;
+	default:
+		/* only the above fields are valid */
+		return -EINVAL;
+	}
+
+	tmprule = kzalloc_obj(struct selinux_audit_rule, gfp);
+	if (!tmprule)
+		return -ENOMEM;
+	context_init(&tmprule->au_ctxt);
+
+	rcu_read_lock();
+	policy = rcu_dereference(state->policy);
+	policydb = &policy->policydb;
+	tmprule->au_seqno = policy->latest_granting;
+	switch (field) {
+	case AUDIT_SUBJ_USER:
+	case AUDIT_OBJ_USER:
+		userdatum = symtab_search(&policydb->p_users, rulestr);
+		if (!userdatum) {
+			rc = -EINVAL;
+			goto err;
+		}
+		tmprule->au_ctxt.user = userdatum->value;
+		break;
+	case AUDIT_SUBJ_ROLE:
+	case AUDIT_OBJ_ROLE:
+		roledatum = symtab_search(&policydb->p_roles, rulestr);
+		if (!roledatum) {
+			rc = -EINVAL;
+			goto err;
+		}
+		tmprule->au_ctxt.role = roledatum->value;
+		break;
+	case AUDIT_SUBJ_TYPE:
+	case AUDIT_OBJ_TYPE:
+		typedatum = symtab_search(&policydb->p_types, rulestr);
+		if (!typedatum) {
+			rc = -EINVAL;
+			goto err;
+		}
+		tmprule->au_ctxt.type = typedatum->value;
+		break;
+	case AUDIT_SUBJ_SEN:
+	case AUDIT_SUBJ_CLR:
+	case AUDIT_OBJ_LEV_LOW:
+	case AUDIT_OBJ_LEV_HIGH:
+		rc = mls_from_string(policydb, rulestr, &tmprule->au_ctxt,
+				     GFP_ATOMIC);
+		if (rc)
+			goto err;
+		break;
+	}
+	rcu_read_unlock();
+
+	*rule = tmprule;
+	return 0;
+
+err:
+	rcu_read_unlock();
+	selinux_audit_rule_free(tmprule);
+	*rule = NULL;
+	return rc;
+}
+
+/* Check to see if the rule contains any selinux fields */
+int selinux_audit_rule_known(struct audit_krule *rule)
+{
+	u32 i;
+
+	for (i = 0; i < rule->field_count; i++) {
+		struct audit_field *f = &rule->fields[i];
+		switch (f->type) {
+		case AUDIT_SUBJ_USER:
+		case AUDIT_SUBJ_ROLE:
+		case AUDIT_SUBJ_TYPE:
+		case AUDIT_SUBJ_SEN:
+		case AUDIT_SUBJ_CLR:
+		case AUDIT_OBJ_USER:
+		case AUDIT_OBJ_ROLE:
+		case AUDIT_OBJ_TYPE:
+		case AUDIT_OBJ_LEV_LOW:
+		case AUDIT_OBJ_LEV_HIGH:
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+int selinux_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *policy;
+	struct context *ctxt;
+	struct mls_level *level;
+	struct selinux_audit_rule *rule = vrule;
+	int match = 0;
+
+	if (unlikely(!rule)) {
+		WARN_ONCE(1, "selinux_audit_rule_match: missing rule\n");
+		return -ENOENT;
+	}
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+
+	policy = rcu_dereference(state->policy);
+
+	if (rule->au_seqno < policy->latest_granting) {
+		match = -ESTALE;
+		goto out;
+	}
+
+	ctxt = sidtab_search(policy->sidtab, prop->selinux.secid);
+	if (unlikely(!ctxt)) {
+		WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n",
+			  prop->selinux.secid);
+		match = -ENOENT;
+		goto out;
+	}
+
+	/* a field/op pair that is not caught here will simply fall through
+	   without a match */
+	switch (field) {
+	case AUDIT_SUBJ_USER:
+	case AUDIT_OBJ_USER:
+		switch (op) {
+		case Audit_equal:
+			match = (ctxt->user == rule->au_ctxt.user);
+			break;
+		case Audit_not_equal:
+			match = (ctxt->user != rule->au_ctxt.user);
+			break;
+		}
+		break;
+	case AUDIT_SUBJ_ROLE:
+	case AUDIT_OBJ_ROLE:
+		switch (op) {
+		case Audit_equal:
+			match = (ctxt->role == rule->au_ctxt.role);
+			break;
+		case Audit_not_equal:
+			match = (ctxt->role != rule->au_ctxt.role);
+			break;
+		}
+		break;
+	case AUDIT_SUBJ_TYPE:
+	case AUDIT_OBJ_TYPE:
+		switch (op) {
+		case Audit_equal:
+			match = (ctxt->type == rule->au_ctxt.type);
+			break;
+		case Audit_not_equal:
+			match = (ctxt->type != rule->au_ctxt.type);
+			break;
+		}
+		break;
+	case AUDIT_SUBJ_SEN:
+	case AUDIT_SUBJ_CLR:
+	case AUDIT_OBJ_LEV_LOW:
+	case AUDIT_OBJ_LEV_HIGH:
+		level = ((field == AUDIT_SUBJ_SEN ||
+			  field == AUDIT_OBJ_LEV_LOW) ?
+			 &ctxt->range.level[0] : &ctxt->range.level[1]);
+		switch (op) {
+		case Audit_equal:
+			match = mls_level_eq(&rule->au_ctxt.range.level[0],
+					     level);
+			break;
+		case Audit_not_equal:
+			match = !mls_level_eq(&rule->au_ctxt.range.level[0],
+					      level);
+			break;
+		case Audit_lt:
+			match = (mls_level_dom(&rule->au_ctxt.range.level[0],
+					       level) &&
+				 !mls_level_eq(&rule->au_ctxt.range.level[0],
+					       level));
+			break;
+		case Audit_le:
+			match = mls_level_dom(&rule->au_ctxt.range.level[0],
+					      level);
+			break;
+		case Audit_gt:
+			match = (mls_level_dom(level,
+					      &rule->au_ctxt.range.level[0]) &&
+				 !mls_level_eq(level,
+					       &rule->au_ctxt.range.level[0]));
+			break;
+		case Audit_ge:
+			match = mls_level_dom(level,
+					      &rule->au_ctxt.range.level[0]);
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	return match;
+}
+
+#ifdef CONFIG_NETLABEL
+/**
+ * security_netlbl_cache_add - Add an entry to the NetLabel cache
+ * @secattr: the NetLabel packet security attributes
+ * @sid: the SELinux SID
+ *
+ * Description:
+ * Attempt to cache the context in @ctx, which was derived from the packet in
+ * @skb, in the NetLabel subsystem cache.  This function assumes @secattr has
+ * already been initialized.
+ *
+ */
+static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr,
+				      u32 sid)
+{
+	u32 *sid_cache;
+
+	sid_cache = kmalloc_obj(*sid_cache, GFP_ATOMIC);
+	if (sid_cache == NULL)
+		return;
+	secattr->cache = netlbl_secattr_cache_alloc(GFP_ATOMIC);
+	if (secattr->cache == NULL) {
+		kfree(sid_cache);
+		return;
+	}
+
+	*sid_cache = sid;
+	secattr->cache->free = kfree;
+	secattr->cache->data = sid_cache;
+	secattr->flags |= NETLBL_SECATTR_CACHE;
+}
+
+/**
+ * security_netlbl_secattr_to_sid - Convert a NetLabel secattr to a SELinux SID
+ * @secattr: the NetLabel packet security attributes
+ * @sid: the SELinux SID
+ *
+ * Description:
+ * Convert the given NetLabel security attributes in @secattr into a
+ * SELinux SID.  If the @secattr field does not contain a full SELinux
+ * SID/context then use SECINITSID_NETMSG as the foundation.  If possible the
+ * 'cache' field of @secattr is set and the CACHE flag is set; this is to
+ * allow the @secattr to be used by NetLabel to cache the secattr to SID
+ * conversion for future lookups.  Returns zero on success, negative values on
+ * failure.
+ *
+ */
+int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr,
+				   u32 *sid)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	struct sidtab *sidtab;
+	int rc;
+	struct context *ctx;
+	struct context ctx_new;
+
+	if (!selinux_initialized()) {
+		*sid = SECSID_NULL;
+		return 0;
+	}
+
+retry:
+	rc = 0;
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+	sidtab = policy->sidtab;
+
+	if (secattr->flags & NETLBL_SECATTR_CACHE)
+		*sid = *(u32 *)secattr->cache->data;
+	else if (secattr->flags & NETLBL_SECATTR_SECID)
+		*sid = secattr->attr.secid;
+	else if (secattr->flags & NETLBL_SECATTR_MLS_LVL) {
+		rc = -EIDRM;
+		ctx = sidtab_search(sidtab, SECINITSID_NETMSG);
+		if (ctx == NULL)
+			goto out;
+
+		context_init(&ctx_new);
+		ctx_new.user = ctx->user;
+		ctx_new.role = ctx->role;
+		ctx_new.type = ctx->type;
+		mls_import_netlbl_lvl(policydb, &ctx_new, secattr);
+		if (secattr->flags & NETLBL_SECATTR_MLS_CAT) {
+			rc = mls_import_netlbl_cat(policydb, &ctx_new, secattr);
+			if (rc)
+				goto out;
+		}
+		rc = -EIDRM;
+		if (!mls_context_isvalid(policydb, &ctx_new)) {
+			ebitmap_destroy(&ctx_new.range.level[0].cat);
+			goto out;
+		}
+
+		rc = sidtab_context_to_sid(sidtab, &ctx_new, sid);
+		ebitmap_destroy(&ctx_new.range.level[0].cat);
+		if (rc == -ESTALE) {
+			rcu_read_unlock();
+			goto retry;
+		}
+		if (rc)
+			goto out;
+
+		security_netlbl_cache_add(secattr, *sid);
+	} else
+		*sid = SECSID_NULL;
+
+out:
+	rcu_read_unlock();
+	return rc;
+}
+
+/**
+ * security_netlbl_sid_to_secattr - Convert a SELinux SID to a NetLabel secattr
+ * @sid: the SELinux SID
+ * @secattr: the NetLabel packet security attributes
+ *
+ * Description:
+ * Convert the given SELinux SID in @sid into a NetLabel security attribute.
+ * Returns zero on success, negative values on failure.
+ *
+ */
+int security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr)
+{
+	struct selinux_policy *policy;
+	struct policydb *policydb;
+	int rc;
+	struct context *ctx;
+
+	if (!selinux_initialized())
+		return 0;
+
+	rcu_read_lock();
+	policy = rcu_dereference(selinux_state.policy);
+	policydb = &policy->policydb;
+
+	rc = -ENOENT;
+	ctx = sidtab_search(policy->sidtab, sid);
+	if (ctx == NULL)
+		goto out;
+
+	rc = -ENOMEM;
+	secattr->domain = kstrdup(sym_name(policydb, SYM_TYPES, ctx->type - 1),
+				  GFP_ATOMIC);
+	if (secattr->domain == NULL)
+		goto out;
+
+	secattr->attr.secid = sid;
+	secattr->flags |= NETLBL_SECATTR_DOMAIN_CPY | NETLBL_SECATTR_SECID;
+	mls_export_netlbl_lvl(policydb, ctx, secattr);
+	rc = mls_export_netlbl_cat(policydb, ctx, secattr);
+out:
+	rcu_read_unlock();
+	return rc;
+}
+#endif /* CONFIG_NETLABEL */
+
+/**
+ * __security_read_policy - read the policy.
+ * @policy: SELinux policy
+ * @data: binary policy data
+ * @len: length of data in bytes
+ *
+ */
+static int __security_read_policy(struct selinux_policy *policy,
+				  void *data, size_t *len)
+{
+	int rc;
+	struct policy_file fp;
+
+	fp.data = data;
+	fp.len = *len;
+
+	rc = policydb_write(&policy->policydb, &fp);
+	if (rc)
+		return rc;
+
+	*len = (unsigned long)fp.data - (unsigned long)data;
+	return 0;
+}
+
+/**
+ * security_read_policy - read the policy.
+ * @data: binary policy data
+ * @len: length of data in bytes
+ *
+ */
+int security_read_policy(void **data, size_t *len)
+{
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *policy;
+
+	policy = rcu_dereference_protected(
+			state->policy, lockdep_is_held(&state->policy_mutex));
+	if (!policy)
+		return -EINVAL;
+
+	*len = policy->policydb.len;
+	*data = vmalloc_user(*len);
+	if (!*data)
+		return -ENOMEM;
+
+	return __security_read_policy(policy, *data, len);
+}
+
+/**
+ * security_read_state_kernel - read the policy.
+ * @data: binary policy data
+ * @len: length of data in bytes
+ *
+ * Allocates kernel memory for reading SELinux policy.
+ * This function is for internal use only and should not
+ * be used for returning data to user space.
+ *
+ * This function must be called with policy_mutex held.
+ */
+int security_read_state_kernel(void **data, size_t *len)
+{
+	int err;
+	struct selinux_state *state = &selinux_state;
+	struct selinux_policy *policy;
+
+	policy = rcu_dereference_protected(
+			state->policy, lockdep_is_held(&state->policy_mutex));
+	if (!policy)
+		return -EINVAL;
+
+	*len = policy->policydb.len;
+	*data = vmalloc(*len);
+	if (!*data)
+		return -ENOMEM;
+
+	err = __security_read_policy(policy, *data, len);
+	if (err) {
+		vfree(*data);
+		*data = NULL;
+		*len = 0;
+	}
+	return err;
+}
diff --git a/security/selinux/ss/services.h b/security/selinux/ss/services.h
new file mode 100644
index 000000000..93358e7a6
--- /dev/null
+++ b/security/selinux/ss/services.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Implementation of the security services.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_SERVICES_H_
+#define _SS_SERVICES_H_
+
+#include "policydb.h"
+
+/* Mapping for a single class */
+struct selinux_mapping {
+	u16 value; /* policy value for class */
+	u16 num_perms; /* number of permissions in class */
+	u32 perms[sizeof(u32) * 8]; /* policy values for permissions */
+};
+
+/* Map for all of the classes, with array size */
+struct selinux_map {
+	struct selinux_mapping *mapping; /* indexed by class */
+	u16 size; /* array size of mapping */
+};
+
+struct selinux_policy {
+	struct sidtab *sidtab;
+	struct policydb policydb;
+	struct selinux_map map;
+	u32 latest_granting;
+} __randomize_layout;
+
+struct convert_context_args {
+	struct policydb *oldp;
+	struct policydb *newp;
+};
+
+void services_compute_xperms_drivers(struct extended_perms *xperms,
+				     struct avtab_node *node);
+void services_compute_xperms_decision(struct extended_perms_decision *xpermd,
+				      struct avtab_node *node);
+
+int services_convert_context(struct convert_context_args *args,
+			     struct context *oldc, struct context *newc,
+			     gfp_t gfp_flags);
+
+#endif /* _SS_SERVICES_H_ */
diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c
new file mode 100644
index 000000000..118af0aa2
--- /dev/null
+++ b/security/selinux/ss/sidtab.c
@@ -0,0 +1,638 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the SID table type.
+ *
+ * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com>
+ * Author: Ondrej Mosnacek, <omosnacek@gmail.com>
+ *
+ * Copyright (C) 2018 Red Hat, Inc.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <asm/barrier.h>
+#include "flask.h"
+#include "security.h"
+#include "sidtab.h"
+#include "services.h"
+
+struct sidtab_str_cache {
+	struct rcu_head rcu_member;
+	struct list_head lru_member;
+	struct sidtab_entry *parent;
+	u32 len;
+	char str[] __counted_by(len);
+};
+
+#define index_to_sid(index) ((index) + SECINITSID_NUM + 1)
+#define sid_to_index(sid)   ((sid) - (SECINITSID_NUM + 1))
+
+int sidtab_init(struct sidtab *s)
+{
+	u32 i;
+
+	memset(s->roots, 0, sizeof(s->roots));
+
+	for (i = 0; i < SECINITSID_NUM; i++)
+		s->isids[i].set = 0;
+
+	s->frozen = false;
+	s->count = 0;
+	s->convert = NULL;
+	hash_init(s->context_to_sid);
+
+	spin_lock_init(&s->lock);
+
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+	s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE;
+	INIT_LIST_HEAD(&s->cache_lru_list);
+	spin_lock_init(&s->cache_lock);
+#endif
+
+	return 0;
+}
+
+static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash)
+{
+	struct sidtab_entry *entry;
+	u32 sid = 0;
+
+	rcu_read_lock();
+	hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) {
+		if (entry->hash != hash)
+			continue;
+		if (context_equal(&entry->context, context)) {
+			sid = entry->sid;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return sid;
+}
+
+int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context)
+{
+	struct sidtab_isid_entry *isid;
+	u32 hash;
+	int rc;
+
+	if (sid == 0 || sid > SECINITSID_NUM)
+		return -EINVAL;
+
+	isid = &s->isids[sid - 1];
+
+	rc = context_cpy(&isid->entry.context, context);
+	if (rc)
+		return rc;
+
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+	isid->entry.cache = NULL;
+#endif
+	isid->set = 1;
+
+	hash = context_compute_hash(context);
+
+	/*
+	 * Multiple initial sids may map to the same context. Check that this
+	 * context is not already represented in the context_to_sid hashtable
+	 * to avoid duplicate entries and long linked lists upon hash
+	 * collision.
+	 */
+	if (!context_to_sid(s, context, hash)) {
+		isid->entry.sid = sid;
+		isid->entry.hash = hash;
+		hash_add(s->context_to_sid, &isid->entry.list, hash);
+	}
+
+	return 0;
+}
+
+int sidtab_hash_stats(struct sidtab *sidtab, char *page)
+{
+	unsigned int i;
+	int chain_len = 0;
+	int slots_used = 0;
+	int entries = 0;
+	int max_chain_len = 0;
+	unsigned int cur_bucket = 0;
+	struct sidtab_entry *entry;
+
+	rcu_read_lock();
+	hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) {
+		entries++;
+		if (i == cur_bucket) {
+			chain_len++;
+			if (chain_len == 1)
+				slots_used++;
+		} else {
+			cur_bucket = i;
+			if (chain_len > max_chain_len)
+				max_chain_len = chain_len;
+			chain_len = 0;
+		}
+	}
+	rcu_read_unlock();
+
+	if (chain_len > max_chain_len)
+		max_chain_len = chain_len;
+
+	return scnprintf(page, PAGE_SIZE,
+			 "entries: %d\nbuckets used: %d/%d\n"
+			 "longest chain: %d\n",
+			 entries, slots_used, SIDTAB_HASH_BUCKETS,
+			 max_chain_len);
+}
+
+static u32 sidtab_level_from_count(u32 count)
+{
+	u32 capacity = SIDTAB_LEAF_ENTRIES;
+	u32 level = 0;
+
+	while (count > capacity) {
+		capacity <<= SIDTAB_INNER_SHIFT;
+		++level;
+	}
+	return level;
+}
+
+static int sidtab_alloc_roots(struct sidtab *s, u32 level)
+{
+	u32 l;
+
+	if (!s->roots[0].ptr_leaf) {
+		s->roots[0].ptr_leaf =
+			kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC);
+		if (!s->roots[0].ptr_leaf)
+			return -ENOMEM;
+	}
+	for (l = 1; l <= level; ++l)
+		if (!s->roots[l].ptr_inner) {
+			s->roots[l].ptr_inner =
+				kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC);
+			if (!s->roots[l].ptr_inner)
+				return -ENOMEM;
+			s->roots[l].ptr_inner->entries[0] = s->roots[l - 1];
+		}
+	return 0;
+}
+
+static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index,
+					     int alloc)
+{
+	union sidtab_entry_inner *entry;
+	u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES;
+
+	/* find the level of the subtree we need */
+	level = sidtab_level_from_count(index + 1);
+	capacity_shift = level * SIDTAB_INNER_SHIFT;
+
+	/* allocate roots if needed */
+	if (alloc && sidtab_alloc_roots(s, level) != 0)
+		return NULL;
+
+	/* lookup inside the subtree */
+	entry = &s->roots[level];
+	while (level != 0) {
+		capacity_shift -= SIDTAB_INNER_SHIFT;
+		--level;
+
+		entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift];
+		leaf_index &= ((u32)1 << capacity_shift) - 1;
+
+		if (!entry->ptr_inner) {
+			if (alloc)
+				entry->ptr_inner = kzalloc(
+					SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC);
+			if (!entry->ptr_inner)
+				return NULL;
+		}
+	}
+	if (!entry->ptr_leaf) {
+		if (alloc)
+			entry->ptr_leaf =
+				kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC);
+		if (!entry->ptr_leaf)
+			return NULL;
+	}
+	return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES];
+}
+
+static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index)
+{
+	/* read entries only after reading count */
+	u32 count = smp_load_acquire(&s->count);
+
+	if (index >= count)
+		return NULL;
+
+	return sidtab_do_lookup(s, index, 0);
+}
+
+static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid)
+{
+	return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL;
+}
+
+static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid,
+					       int force)
+{
+	if (sid != 0) {
+		struct sidtab_entry *entry;
+
+		if (sid > SECINITSID_NUM)
+			entry = sidtab_lookup(s, sid_to_index(sid));
+		else
+			entry = sidtab_lookup_initial(s, sid);
+		if (entry && (!entry->context.len || force))
+			return entry;
+	}
+
+	return sidtab_lookup_initial(s, SECINITSID_UNLABELED);
+}
+
+struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid)
+{
+	return sidtab_search_core(s, sid, 0);
+}
+
+struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid)
+{
+	return sidtab_search_core(s, sid, 1);
+}
+
+int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid)
+{
+	unsigned long flags;
+	u32 count, hash = context_compute_hash(context);
+	struct sidtab_convert_params *convert;
+	struct sidtab_entry *dst, *dst_convert;
+	int rc;
+
+	*sid = context_to_sid(s, context, hash);
+	if (*sid)
+		return 0;
+
+	/* lock-free search failed: lock, re-search, and insert if not found */
+	spin_lock_irqsave(&s->lock, flags);
+
+	rc = 0;
+	*sid = context_to_sid(s, context, hash);
+	if (*sid)
+		goto out_unlock;
+
+	if (unlikely(s->frozen)) {
+		/*
+		 * This sidtab is now frozen - tell the caller to abort and
+		 * get the new one.
+		 */
+		rc = -ESTALE;
+		goto out_unlock;
+	}
+
+	count = s->count;
+
+	/* bail out if we already reached max entries */
+	rc = -EOVERFLOW;
+	if (count >= SIDTAB_MAX)
+		goto out_unlock;
+
+	/* insert context into new entry */
+	rc = -ENOMEM;
+	dst = sidtab_do_lookup(s, count, 1);
+	if (!dst)
+		goto out_unlock;
+
+	dst->sid = index_to_sid(count);
+	dst->hash = hash;
+
+	rc = context_cpy(&dst->context, context);
+	if (rc)
+		goto out_unlock;
+
+	/*
+	 * if we are building a new sidtab, we need to convert the context
+	 * and insert it there as well
+	 */
+	convert = s->convert;
+	if (convert) {
+		struct sidtab *target = convert->target;
+
+		rc = -ENOMEM;
+		dst_convert = sidtab_do_lookup(target, count, 1);
+		if (!dst_convert) {
+			context_destroy(&dst->context);
+			goto out_unlock;
+		}
+
+		rc = services_convert_context(convert->args, context,
+					      &dst_convert->context,
+					      GFP_ATOMIC);
+		if (rc) {
+			context_destroy(&dst->context);
+			goto out_unlock;
+		}
+		dst_convert->sid = index_to_sid(count);
+		dst_convert->hash = context_compute_hash(&dst_convert->context);
+		target->count = count + 1;
+
+		hash_add_rcu(target->context_to_sid, &dst_convert->list,
+			     dst_convert->hash);
+	}
+
+	if (context->len)
+		pr_info("SELinux:  Context %s is not valid (left unmapped).\n",
+			context->str);
+
+	*sid = index_to_sid(count);
+
+	/* write entries before updating count */
+	smp_store_release(&s->count, count + 1);
+	hash_add_rcu(s->context_to_sid, &dst->list, dst->hash);
+
+	rc = 0;
+out_unlock:
+	spin_unlock_irqrestore(&s->lock, flags);
+	return rc;
+}
+
+static void sidtab_convert_hashtable(struct sidtab *s, u32 count)
+{
+	struct sidtab_entry *entry;
+	u32 i;
+
+	for (i = 0; i < count; i++) {
+		entry = sidtab_do_lookup(s, i, 0);
+		entry->sid = index_to_sid(i);
+		entry->hash = context_compute_hash(&entry->context);
+
+		hash_add_rcu(s->context_to_sid, &entry->list, entry->hash);
+	}
+}
+
+static int sidtab_convert_tree(union sidtab_entry_inner *edst,
+			       union sidtab_entry_inner *esrc, u32 *pos,
+			       u32 count, u32 level,
+			       struct sidtab_convert_params *convert)
+{
+	int rc;
+	u32 i;
+
+	if (level != 0) {
+		if (!edst->ptr_inner) {
+			edst->ptr_inner =
+				kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL);
+			if (!edst->ptr_inner)
+				return -ENOMEM;
+		}
+		i = 0;
+		while (i < SIDTAB_INNER_ENTRIES && *pos < count) {
+			rc = sidtab_convert_tree(&edst->ptr_inner->entries[i],
+						 &esrc->ptr_inner->entries[i],
+						 pos, count, level - 1,
+						 convert);
+			if (rc)
+				return rc;
+			i++;
+		}
+	} else {
+		if (!edst->ptr_leaf) {
+			edst->ptr_leaf =
+				kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL);
+			if (!edst->ptr_leaf)
+				return -ENOMEM;
+		}
+		i = 0;
+		while (i < SIDTAB_LEAF_ENTRIES && *pos < count) {
+			rc = services_convert_context(
+				convert->args,
+				&esrc->ptr_leaf->entries[i].context,
+				&edst->ptr_leaf->entries[i].context,
+				GFP_KERNEL);
+			if (rc)
+				return rc;
+			(*pos)++;
+			i++;
+		}
+		cond_resched();
+	}
+	return 0;
+}
+
+int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params)
+{
+	unsigned long flags;
+	u32 count, level, pos;
+	int rc;
+
+	spin_lock_irqsave(&s->lock, flags);
+
+	/* concurrent policy loads are not allowed */
+	if (s->convert) {
+		spin_unlock_irqrestore(&s->lock, flags);
+		return -EBUSY;
+	}
+
+	count = s->count;
+	level = sidtab_level_from_count(count);
+
+	/* allocate last leaf in the new sidtab (to avoid race with
+	 * live convert)
+	 */
+	rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM;
+	if (rc) {
+		spin_unlock_irqrestore(&s->lock, flags);
+		return rc;
+	}
+
+	/* set count in case no new entries are added during conversion */
+	params->target->count = count;
+
+	/* enable live convert of new entries */
+	s->convert = params;
+
+	/* we can safely convert the tree outside the lock */
+	spin_unlock_irqrestore(&s->lock, flags);
+
+	pr_info("SELinux:  Converting %u SID table entries...\n", count);
+
+	/* convert all entries not covered by live convert */
+	pos = 0;
+	rc = sidtab_convert_tree(&params->target->roots[level],
+				 &s->roots[level], &pos, count, level, params);
+	if (rc) {
+		/* we need to keep the old table - disable live convert */
+		spin_lock_irqsave(&s->lock, flags);
+		s->convert = NULL;
+		spin_unlock_irqrestore(&s->lock, flags);
+		return rc;
+	}
+	/*
+	 * The hashtable can also be modified in sidtab_context_to_sid()
+	 * so we must re-acquire the lock here.
+	 */
+	spin_lock_irqsave(&s->lock, flags);
+	sidtab_convert_hashtable(params->target, count);
+	spin_unlock_irqrestore(&s->lock, flags);
+
+	return 0;
+}
+
+void sidtab_cancel_convert(struct sidtab *s)
+{
+	unsigned long flags;
+
+	/* cancelling policy load - disable live convert of sidtab */
+	spin_lock_irqsave(&s->lock, flags);
+	s->convert = NULL;
+	spin_unlock_irqrestore(&s->lock, flags);
+}
+
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags)
+	__acquires(&s->lock)
+{
+	spin_lock_irqsave(&s->lock, *flags);
+	s->frozen = true;
+	s->convert = NULL;
+}
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags)
+	__releases(&s->lock)
+{
+	spin_unlock_irqrestore(&s->lock, *flags);
+}
+
+static void sidtab_destroy_entry(struct sidtab_entry *entry)
+{
+	context_destroy(&entry->context);
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+	kfree(rcu_dereference_raw(entry->cache));
+#endif
+}
+
+static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level)
+{
+	u32 i;
+
+	if (level != 0) {
+		struct sidtab_node_inner *node = entry.ptr_inner;
+
+		if (!node)
+			return;
+
+		for (i = 0; i < SIDTAB_INNER_ENTRIES; i++)
+			sidtab_destroy_tree(node->entries[i], level - 1);
+		kfree(node);
+	} else {
+		struct sidtab_node_leaf *node = entry.ptr_leaf;
+
+		if (!node)
+			return;
+
+		for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++)
+			sidtab_destroy_entry(&node->entries[i]);
+		kfree(node);
+	}
+}
+
+void sidtab_destroy(struct sidtab *s)
+{
+	u32 i, level;
+
+	for (i = 0; i < SECINITSID_NUM; i++)
+		if (s->isids[i].set)
+			sidtab_destroy_entry(&s->isids[i].entry);
+
+	level = SIDTAB_MAX_LEVEL;
+	while (level && !s->roots[level].ptr_inner)
+		--level;
+
+	sidtab_destroy_tree(s->roots[level], level);
+	/*
+	 * The context_to_sid hashtable's objects are all shared
+	 * with the isids array and context tree, and so don't need
+	 * to be cleaned up here.
+	 */
+}
+
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+
+void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry,
+			const char *str, u32 str_len)
+{
+	struct sidtab_str_cache *cache, *victim = NULL;
+	unsigned long flags;
+
+	/* do not cache invalid contexts */
+	if (entry->context.len)
+		return;
+
+	spin_lock_irqsave(&s->cache_lock, flags);
+
+	cache = rcu_dereference_protected(entry->cache,
+					  lockdep_is_held(&s->cache_lock));
+	if (cache) {
+		/* entry in cache - just bump to the head of LRU list */
+		list_move(&cache->lru_member, &s->cache_lru_list);
+		goto out_unlock;
+	}
+
+	cache = kmalloc_flex(*cache, str, str_len, GFP_ATOMIC);
+	if (!cache)
+		goto out_unlock;
+
+	if (s->cache_free_slots == 0) {
+		/* pop a cache entry from the tail and free it */
+		victim = container_of(s->cache_lru_list.prev,
+				      struct sidtab_str_cache, lru_member);
+		list_del(&victim->lru_member);
+		rcu_assign_pointer(victim->parent->cache, NULL);
+	} else {
+		s->cache_free_slots--;
+	}
+	cache->parent = entry;
+	cache->len = str_len;
+	memcpy(cache->str, str, str_len);
+	list_add(&cache->lru_member, &s->cache_lru_list);
+
+	rcu_assign_pointer(entry->cache, cache);
+
+out_unlock:
+	spin_unlock_irqrestore(&s->cache_lock, flags);
+	kfree_rcu(victim, rcu_member);
+}
+
+int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out,
+		       u32 *out_len)
+{
+	struct sidtab_str_cache *cache;
+	int rc = 0;
+
+	if (entry->context.len)
+		return -ENOENT; /* do not cache invalid contexts */
+
+	rcu_read_lock();
+
+	cache = rcu_dereference(entry->cache);
+	if (!cache) {
+		rc = -ENOENT;
+	} else {
+		*out_len = cache->len;
+		if (out) {
+			*out = kmemdup(cache->str, cache->len, GFP_ATOMIC);
+			if (!*out)
+				rc = -ENOMEM;
+		}
+	}
+
+	rcu_read_unlock();
+
+	if (!rc && out)
+		sidtab_sid2str_put(s, entry, *out, *out_len);
+	return rc;
+}
+
+#endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */
diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h
new file mode 100644
index 000000000..832c85c70
--- /dev/null
+++ b/security/selinux/ss/sidtab.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A security identifier table (sidtab) is a lookup table
+ * of security context structures indexed by SID value.
+ *
+ * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com>
+ * Author: Ondrej Mosnacek, <omosnacek@gmail.com>
+ *
+ * Copyright (C) 2018 Red Hat, Inc.
+ */
+
+#ifndef _SS_SIDTAB_H_
+#define _SS_SIDTAB_H_
+
+#include <linux/spinlock_types.h>
+#include <linux/log2.h>
+#include <linux/hashtable.h>
+
+#include "context.h"
+
+struct sidtab_entry {
+	u32 sid;
+	u32 hash;
+	struct context context;
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+	struct sidtab_str_cache __rcu *cache;
+#endif
+	struct hlist_node list;
+};
+
+union sidtab_entry_inner {
+	struct sidtab_node_inner *ptr_inner;
+	struct sidtab_node_leaf *ptr_leaf;
+};
+
+/* align node size to page boundary */
+#define SIDTAB_NODE_ALLOC_SHIFT PAGE_SHIFT
+#define SIDTAB_NODE_ALLOC_SIZE	PAGE_SIZE
+
+#define size_to_shift(size) ((size) == 1 ? 1 : (const_ilog2((size)-1) + 1))
+
+#define SIDTAB_INNER_SHIFT         \
+	(SIDTAB_NODE_ALLOC_SHIFT - \
+	 size_to_shift(sizeof(union sidtab_entry_inner)))
+#define SIDTAB_INNER_ENTRIES ((size_t)1 << SIDTAB_INNER_SHIFT)
+#define SIDTAB_LEAF_ENTRIES \
+	(SIDTAB_NODE_ALLOC_SIZE / sizeof(struct sidtab_entry))
+
+#define SIDTAB_MAX_BITS 32
+#define SIDTAB_MAX	U32_MAX
+/* ensure enough tree levels for SIDTAB_MAX entries */
+#define SIDTAB_MAX_LEVEL                                                   \
+	DIV_ROUND_UP(SIDTAB_MAX_BITS - size_to_shift(SIDTAB_LEAF_ENTRIES), \
+		     SIDTAB_INNER_SHIFT)
+
+struct sidtab_node_leaf {
+	struct sidtab_entry entries[SIDTAB_LEAF_ENTRIES];
+};
+
+struct sidtab_node_inner {
+	union sidtab_entry_inner entries[SIDTAB_INNER_ENTRIES];
+};
+
+struct sidtab_isid_entry {
+	int set;
+	struct sidtab_entry entry;
+};
+
+struct sidtab_convert_params {
+	struct convert_context_args *args;
+	struct sidtab *target;
+};
+
+#define SIDTAB_HASH_BITS    CONFIG_SECURITY_SELINUX_SIDTAB_HASH_BITS
+#define SIDTAB_HASH_BUCKETS (1 << SIDTAB_HASH_BITS)
+
+struct sidtab {
+	/*
+	 * lock-free read access only for as many items as a prior read of
+	 * 'count'
+	 */
+	union sidtab_entry_inner roots[SIDTAB_MAX_LEVEL + 1];
+	/*
+	 * access atomically via {READ|WRITE}_ONCE(); only increment under
+	 * spinlock
+	 */
+	u32 count;
+	/* access only under spinlock */
+	struct sidtab_convert_params *convert;
+	bool frozen;
+	spinlock_t lock;
+
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+	/* SID -> context string cache */
+	u32 cache_free_slots;
+	struct list_head cache_lru_list;
+	spinlock_t cache_lock;
+#endif
+
+	/* index == SID - 1 (no entry for SECSID_NULL) */
+	struct sidtab_isid_entry isids[SECINITSID_NUM];
+
+	/* Hash table for fast reverse context-to-sid lookups. */
+	DECLARE_HASHTABLE(context_to_sid, SIDTAB_HASH_BITS);
+};
+
+int sidtab_init(struct sidtab *s);
+int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context);
+struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid);
+struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid);
+
+static inline struct context *sidtab_search(struct sidtab *s, u32 sid)
+{
+	struct sidtab_entry *entry = sidtab_search_entry(s, sid);
+
+	return entry ? &entry->context : NULL;
+}
+
+static inline struct context *sidtab_search_force(struct sidtab *s, u32 sid)
+{
+	struct sidtab_entry *entry = sidtab_search_entry_force(s, sid);
+
+	return entry ? &entry->context : NULL;
+}
+
+int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params);
+
+void sidtab_cancel_convert(struct sidtab *s);
+
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags)
+	__acquires(&s->lock);
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags)
+	__releases(&s->lock);
+
+int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid);
+
+void sidtab_destroy(struct sidtab *s);
+
+int sidtab_hash_stats(struct sidtab *sidtab, char *page);
+
+#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
+void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry,
+			const char *str, u32 str_len);
+int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out,
+		       u32 *out_len);
+#else
+static inline void sidtab_sid2str_put(struct sidtab *s,
+				      struct sidtab_entry *entry,
+				      const char *str, u32 str_len)
+{
+}
+static inline int sidtab_sid2str_get(struct sidtab *s,
+				     struct sidtab_entry *entry, char **out,
+				     u32 *out_len)
+{
+	return -ENOENT;
+}
+#endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */
+
+#endif /* _SS_SIDTAB_H_ */
diff --git a/security/selinux/ss/symtab.c b/security/selinux/ss/symtab.c
new file mode 100644
index 000000000..a756554e7
--- /dev/null
+++ b/security/selinux/ss/symtab.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the symbol table type.
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include "symtab.h"
+
+static unsigned int symhash(const void *key)
+{
+	/*
+	 * djb2a
+	 * Public domain from cdb v0.75
+	 */
+	unsigned int hash = 5381;
+	unsigned char c;
+
+	while ((c = *(const unsigned char *)key++))
+		hash = ((hash << 5) + hash) ^ c;
+
+	return hash;
+}
+
+static int symcmp(const void *key1, const void *key2)
+{
+	const char *keyp1, *keyp2;
+
+	keyp1 = key1;
+	keyp2 = key2;
+	return strcmp(keyp1, keyp2);
+}
+
+static const struct hashtab_key_params symtab_key_params = {
+	.hash = symhash,
+	.cmp = symcmp,
+};
+
+int symtab_init(struct symtab *s, u32 size)
+{
+	s->nprim = 0;
+	return hashtab_init(&s->table, size);
+}
+
+int symtab_insert(struct symtab *s, char *name, void *datum)
+{
+	return hashtab_insert(&s->table, name, datum, symtab_key_params);
+}
+
+void *symtab_search(const struct symtab *s, const char *name)
+{
+	return hashtab_search(&s->table, name, symtab_key_params);
+}
diff --git a/security/selinux/ss/symtab.h b/security/selinux/ss/symtab.h
new file mode 100644
index 000000000..7cfa3b449
--- /dev/null
+++ b/security/selinux/ss/symtab.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A symbol table (symtab) maintains associations between symbol
+ * strings and datum values.  The type of the datum values
+ * is arbitrary.  The symbol table type is implemented
+ * using the hash table type (hashtab).
+ *
+ * Author : Stephen Smalley, <stephen.smalley.work@gmail.com>
+ */
+
+#ifndef _SS_SYMTAB_H_
+#define _SS_SYMTAB_H_
+
+#include "hashtab.h"
+
+struct symtab {
+	struct hashtab table; /* hash table (keyed on a string) */
+	u32 nprim; /* number of primary names in table */
+};
+
+int symtab_init(struct symtab *s, u32 size);
+
+int symtab_insert(struct symtab *s, char *name, void *datum);
+void *symtab_search(const struct symtab *s, const char *name);
+
+#endif /* _SS_SYMTAB_H_ */
diff --git a/security/selinux/status.c b/security/selinux/status.c
new file mode 100644
index 000000000..dffca22ce
--- /dev/null
+++ b/security/selinux/status.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * mmap based event notifications for SELinux
+ *
+ * Author: KaiGai Kohei <kaigai@ak.jp.nec.com>
+ *
+ * Copyright (C) 2010 NEC corporation
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include "avc.h"
+#include "security.h"
+
+/*
+ * The selinux_status_page shall be exposed to userspace applications
+ * using mmap interface on /selinux/status.
+ * It enables to notify applications a few events that will cause reset
+ * of userspace access vector without context switching.
+ *
+ * The selinux_kernel_status structure on the head of status page is
+ * protected from concurrent accesses using seqlock logic, so userspace
+ * application should reference the status page according to the seqlock
+ * logic.
+ *
+ * Typically, application checks status->sequence at the head of access
+ * control routine. If it is odd-number, kernel is updating the status,
+ * so please wait for a moment. If it is changed from the last sequence
+ * number, it means something happen, so application will reset userspace
+ * avc, if needed.
+ * In most cases, application shall confirm the kernel status is not
+ * changed without any system call invocations.
+ */
+
+/*
+ * selinux_kernel_status_page
+ *
+ * It returns a reference to selinux_status_page. If the status page is
+ * not allocated yet, it also tries to allocate it at the first time.
+ */
+struct page *selinux_kernel_status_page(void)
+{
+	struct selinux_kernel_status   *status;
+	struct page		       *result = NULL;
+
+	mutex_lock(&selinux_state.status_lock);
+	if (!selinux_state.status_page) {
+		selinux_state.status_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
+
+		if (selinux_state.status_page) {
+			status = page_address(selinux_state.status_page);
+
+			status->version = SELINUX_KERNEL_STATUS_VERSION;
+			status->sequence = 0;
+			status->enforcing = enforcing_enabled();
+			/*
+			 * NOTE: the next policyload event shall set
+			 * a positive value on the status->policyload,
+			 * although it may not be 1, but never zero.
+			 * So, application can know it was updated.
+			 */
+			status->policyload = 0;
+			status->deny_unknown =
+				!security_get_allow_unknown();
+		}
+	}
+	result = selinux_state.status_page;
+	mutex_unlock(&selinux_state.status_lock);
+
+	return result;
+}
+
+/*
+ * selinux_status_update_setenforce
+ *
+ * It updates status of the current enforcing/permissive mode.
+ */
+void selinux_status_update_setenforce(bool enforcing)
+{
+	struct selinux_kernel_status   *status;
+
+	mutex_lock(&selinux_state.status_lock);
+	if (selinux_state.status_page) {
+		status = page_address(selinux_state.status_page);
+
+		status->sequence++;
+		smp_wmb();
+
+		status->enforcing = enforcing ? 1 : 0;
+
+		smp_wmb();
+		status->sequence++;
+	}
+	mutex_unlock(&selinux_state.status_lock);
+}
+
+/*
+ * selinux_status_update_policyload
+ *
+ * It updates status of the times of policy reloaded, and current
+ * setting of deny_unknown.
+ */
+void selinux_status_update_policyload(u32 seqno)
+{
+	struct selinux_kernel_status   *status;
+
+	mutex_lock(&selinux_state.status_lock);
+	if (selinux_state.status_page) {
+		status = page_address(selinux_state.status_page);
+
+		status->sequence++;
+		smp_wmb();
+
+		status->policyload = seqno;
+		status->deny_unknown = !security_get_allow_unknown();
+
+		smp_wmb();
+		status->sequence++;
+	}
+	mutex_unlock(&selinux_state.status_lock);
+}
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
new file mode 100644
index 000000000..8e00b3306
--- /dev/null
+++ b/security/selinux/xfrm.c
@@ -0,0 +1,466 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Security-Enhanced Linux (SELinux) security module
+ *
+ *  This file contains the SELinux XFRM hook function implementations.
+ *
+ *  Authors:  Serge Hallyn <sergeh@us.ibm.com>
+ *	      Trent Jaeger <jaegert@us.ibm.com>
+ *
+ *  Updated: Venkat Yekkirala <vyekkirala@TrustedCS.com>
+ *
+ *           Granular IPSec Associations for use in MLS environments.
+ *
+ *  Copyright (C) 2005 International Business Machines Corporation
+ *  Copyright (C) 2006 Trusted Computer Solutions, Inc.
+ */
+
+/*
+ * USAGE:
+ * NOTES:
+ *   1. Make sure to enable the following options in your kernel config:
+ *	CONFIG_SECURITY=y
+ *	CONFIG_SECURITY_NETWORK=y
+ *	CONFIG_SECURITY_NETWORK_XFRM=y
+ *	CONFIG_SECURITY_SELINUX=m/y
+ * ISSUES:
+ *   1. Caching packets, so they are not dropped during negotiation
+ *   2. Emulating a reasonable SO_PEERSEC across machines
+ *   3. Testing addition of sk_policy's with security context via setsockopt
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/security.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/skbuff.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+#include <net/checksum.h>
+#include <net/udp.h>
+#include <linux/atomic.h>
+
+#include "avc.h"
+#include "objsec.h"
+#include "xfrm.h"
+
+/* Labeled XFRM instance counter */
+atomic_t selinux_xfrm_refcount __read_mostly = ATOMIC_INIT(0);
+
+/*
+ * Returns true if the context is an LSM/SELinux context.
+ */
+static inline int selinux_authorizable_ctx(struct xfrm_sec_ctx *ctx)
+{
+	return (ctx &&
+		(ctx->ctx_doi == XFRM_SC_DOI_LSM) &&
+		(ctx->ctx_alg == XFRM_SC_ALG_SELINUX));
+}
+
+/*
+ * Returns true if the xfrm contains a security blob for SELinux.
+ */
+static inline int selinux_authorizable_xfrm(struct xfrm_state *x)
+{
+	return selinux_authorizable_ctx(x->security);
+}
+
+/*
+ * Allocates a xfrm_sec_state and populates it using the supplied security
+ * xfrm_user_sec_ctx context.
+ */
+static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
+				   struct xfrm_user_sec_ctx *uctx,
+				   gfp_t gfp)
+{
+	int rc;
+	struct xfrm_sec_ctx *ctx = NULL;
+	u32 str_len;
+
+	if (ctxp == NULL || uctx == NULL ||
+	    uctx->ctx_doi != XFRM_SC_DOI_LSM ||
+	    uctx->ctx_alg != XFRM_SC_ALG_SELINUX)
+		return -EINVAL;
+
+	str_len = uctx->ctx_len;
+	if (str_len >= PAGE_SIZE)
+		return -ENOMEM;
+
+	ctx = kmalloc_flex(*ctx, ctx_str, str_len + 1, gfp);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->ctx_doi = XFRM_SC_DOI_LSM;
+	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+	ctx->ctx_len = str_len + 1;
+	memcpy(ctx->ctx_str, &uctx[1], str_len);
+	ctx->ctx_str[str_len] = '\0';
+	rc = security_context_to_sid(ctx->ctx_str, str_len,
+				     &ctx->ctx_sid, gfp);
+	if (rc)
+		goto err;
+
+	rc = avc_has_perm(current_sid(), ctx->ctx_sid,
+			  SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT, NULL);
+	if (rc)
+		goto err;
+
+	*ctxp = ctx;
+	atomic_inc(&selinux_xfrm_refcount);
+	return 0;
+
+err:
+	kfree(ctx);
+	return rc;
+}
+
+/*
+ * Free the xfrm_sec_ctx structure.
+ */
+static void selinux_xfrm_free(struct xfrm_sec_ctx *ctx)
+{
+	if (!ctx)
+		return;
+
+	atomic_dec(&selinux_xfrm_refcount);
+	kfree(ctx);
+}
+
+/*
+ * Authorize the deletion of a labeled SA or policy rule.
+ */
+static int selinux_xfrm_delete(struct xfrm_sec_ctx *ctx)
+{
+	if (!ctx)
+		return 0;
+
+	return avc_has_perm(current_sid(), ctx->ctx_sid,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__SETCONTEXT,
+			    NULL);
+}
+
+/*
+ * LSM hook implementation that authorizes that a flow can use a xfrm policy
+ * rule.
+ */
+int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid)
+{
+	int rc;
+
+	/* All flows should be treated as polmatch'ing an otherwise applicable
+	 * "non-labeled" policy. This would prevent inadvertent "leaks". */
+	if (!ctx)
+		return 0;
+
+	/* Context sid is either set to label or ANY_ASSOC */
+	if (!selinux_authorizable_ctx(ctx))
+		return -EINVAL;
+
+	rc = avc_has_perm(fl_secid, ctx->ctx_sid,
+			  SECCLASS_ASSOCIATION, ASSOCIATION__POLMATCH, NULL);
+	return (rc == -EACCES ? -ESRCH : rc);
+}
+
+/*
+ * LSM hook implementation that authorizes that a state matches
+ * the given policy, flow combo.
+ */
+int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x,
+				      struct xfrm_policy *xp,
+				      const struct flowi_common *flic)
+{
+	u32 state_sid;
+	u32 flic_sid;
+
+	if (!xp->security)
+		if (x->security)
+			/* unlabeled policy and labeled SA can't match */
+			return 0;
+		else
+			/* unlabeled policy and unlabeled SA match all flows */
+			return 1;
+	else
+		if (!x->security)
+			/* unlabeled SA and labeled policy can't match */
+			return 0;
+		else
+			if (!selinux_authorizable_xfrm(x))
+				/* Not a SELinux-labeled SA */
+				return 0;
+
+	state_sid = x->security->ctx_sid;
+	flic_sid = flic->flowic_secid;
+
+	if (flic_sid != state_sid)
+		return 0;
+
+	/* We don't need a separate SA Vs. policy polmatch check since the SA
+	 * is now of the same label as the flow and a flow Vs. policy polmatch
+	 * check had already happened in selinux_xfrm_policy_lookup() above. */
+	return (avc_has_perm(flic_sid, state_sid,
+			     SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO,
+			     NULL) ? 0 : 1);
+}
+
+static u32 selinux_xfrm_skb_sid_egress(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct xfrm_state *x;
+
+	if (dst == NULL)
+		return SECSID_NULL;
+	x = dst->xfrm;
+	if (x == NULL || !selinux_authorizable_xfrm(x))
+		return SECSID_NULL;
+
+	return x->security->ctx_sid;
+}
+
+static int selinux_xfrm_skb_sid_ingress(struct sk_buff *skb,
+					u32 *sid, int ckall)
+{
+	u32 sid_session = SECSID_NULL;
+	struct sec_path *sp = skb_sec_path(skb);
+
+	if (sp) {
+		int i;
+
+		for (i = sp->len - 1; i >= 0; i--) {
+			struct xfrm_state *x = sp->xvec[i];
+			if (selinux_authorizable_xfrm(x)) {
+				struct xfrm_sec_ctx *ctx = x->security;
+
+				if (sid_session == SECSID_NULL) {
+					sid_session = ctx->ctx_sid;
+					if (!ckall)
+						goto out;
+				} else if (sid_session != ctx->ctx_sid) {
+					*sid = SECSID_NULL;
+					return -EINVAL;
+				}
+			}
+		}
+	}
+
+out:
+	*sid = sid_session;
+	return 0;
+}
+
+/*
+ * LSM hook implementation that checks and/or returns the xfrm sid for the
+ * incoming packet.
+ */
+int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall)
+{
+	if (skb == NULL) {
+		*sid = SECSID_NULL;
+		return 0;
+	}
+	return selinux_xfrm_skb_sid_ingress(skb, sid, ckall);
+}
+
+int selinux_xfrm_skb_sid(struct sk_buff *skb, u32 *sid)
+{
+	int rc;
+
+	rc = selinux_xfrm_skb_sid_ingress(skb, sid, 0);
+	if (rc == 0 && *sid == SECSID_NULL)
+		*sid = selinux_xfrm_skb_sid_egress(skb);
+
+	return rc;
+}
+
+/*
+ * LSM hook implementation that allocs and transfers uctx spec to xfrm_policy.
+ */
+int selinux_xfrm_policy_alloc(struct xfrm_sec_ctx **ctxp,
+			      struct xfrm_user_sec_ctx *uctx,
+			      gfp_t gfp)
+{
+	return selinux_xfrm_alloc_user(ctxp, uctx, gfp);
+}
+
+/*
+ * LSM hook implementation that copies security data structure from old to new
+ * for policy cloning.
+ */
+int selinux_xfrm_policy_clone(struct xfrm_sec_ctx *old_ctx,
+			      struct xfrm_sec_ctx **new_ctxp)
+{
+	struct xfrm_sec_ctx *new_ctx;
+
+	if (!old_ctx)
+		return 0;
+
+	new_ctx = kmemdup(old_ctx, sizeof(*old_ctx) + old_ctx->ctx_len,
+			  GFP_ATOMIC);
+	if (!new_ctx)
+		return -ENOMEM;
+	atomic_inc(&selinux_xfrm_refcount);
+	*new_ctxp = new_ctx;
+
+	return 0;
+}
+
+/*
+ * LSM hook implementation that frees xfrm_sec_ctx security information.
+ */
+void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx)
+{
+	selinux_xfrm_free(ctx);
+}
+
+/*
+ * LSM hook implementation that authorizes deletion of labeled policies.
+ */
+int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx)
+{
+	return selinux_xfrm_delete(ctx);
+}
+
+/*
+ * LSM hook implementation that allocates a xfrm_sec_state, populates it using
+ * the supplied security context, and assigns it to the xfrm_state.
+ */
+int selinux_xfrm_state_alloc(struct xfrm_state *x,
+			     struct xfrm_user_sec_ctx *uctx)
+{
+	return selinux_xfrm_alloc_user(&x->security, uctx, GFP_KERNEL);
+}
+
+/*
+ * LSM hook implementation that allocates a xfrm_sec_state and populates based
+ * on a secid.
+ */
+int selinux_xfrm_state_alloc_acquire(struct xfrm_state *x,
+				     struct xfrm_sec_ctx *polsec, u32 secid)
+{
+	int rc;
+	struct xfrm_sec_ctx *ctx;
+	char *ctx_str = NULL;
+	u32 str_len;
+
+	if (!polsec)
+		return 0;
+
+	if (secid == 0)
+		return -EINVAL;
+
+	rc = security_sid_to_context(secid, &ctx_str,
+				     &str_len);
+	if (rc)
+		return rc;
+
+	ctx = kmalloc_flex(*ctx, ctx_str, str_len, GFP_ATOMIC);
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	ctx->ctx_doi = XFRM_SC_DOI_LSM;
+	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
+	ctx->ctx_sid = secid;
+	ctx->ctx_len = str_len;
+	memcpy(ctx->ctx_str, ctx_str, str_len);
+
+	x->security = ctx;
+	atomic_inc(&selinux_xfrm_refcount);
+out:
+	kfree(ctx_str);
+	return rc;
+}
+
+/*
+ * LSM hook implementation that frees xfrm_state security information.
+ */
+void selinux_xfrm_state_free(struct xfrm_state *x)
+{
+	selinux_xfrm_free(x->security);
+}
+
+/*
+ * LSM hook implementation that authorizes deletion of labeled SAs.
+ */
+int selinux_xfrm_state_delete(struct xfrm_state *x)
+{
+	return selinux_xfrm_delete(x->security);
+}
+
+/*
+ * LSM hook that controls access to unlabelled packets.  If
+ * a xfrm_state is authorizable (defined by macro) then it was
+ * already authorized by the IPSec process.  If not, then
+ * we need to check for unlabelled access since this may not have
+ * gone thru the IPSec process.
+ */
+int selinux_xfrm_sock_rcv_skb(u32 sk_sid, struct sk_buff *skb,
+			      struct common_audit_data *ad)
+{
+	int i;
+	struct sec_path *sp = skb_sec_path(skb);
+	u32 peer_sid = SECINITSID_UNLABELED;
+
+	if (sp) {
+		for (i = 0; i < sp->len; i++) {
+			struct xfrm_state *x = sp->xvec[i];
+
+			if (x && selinux_authorizable_xfrm(x)) {
+				struct xfrm_sec_ctx *ctx = x->security;
+				peer_sid = ctx->ctx_sid;
+				break;
+			}
+		}
+	}
+
+	/* This check even when there's no association involved is intended,
+	 * according to Trent Jaeger, to make sure a process can't engage in
+	 * non-IPsec communication unless explicitly allowed by policy. */
+	return avc_has_perm(sk_sid, peer_sid,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__RECVFROM, ad);
+}
+
+/*
+ * POSTROUTE_LAST hook's XFRM processing:
+ * If we have no security association, then we need to determine
+ * whether the socket is allowed to send to an unlabelled destination.
+ * If we do have a authorizable security association, then it has already been
+ * checked in the selinux_xfrm_state_pol_flow_match hook above.
+ */
+int selinux_xfrm_postroute_last(u32 sk_sid, struct sk_buff *skb,
+				struct common_audit_data *ad, u8 proto)
+{
+	struct dst_entry *dst;
+
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+	case IPPROTO_COMP:
+		/* We should have already seen this packet once before it
+		 * underwent xfrm(s). No need to subject it to the unlabeled
+		 * check. */
+		return 0;
+	default:
+		break;
+	}
+
+	dst = skb_dst(skb);
+	if (dst) {
+		struct dst_entry *iter;
+
+		for (iter = dst; iter != NULL; iter = xfrm_dst_child(iter)) {
+			struct xfrm_state *x = iter->xfrm;
+
+			if (x && selinux_authorizable_xfrm(x))
+				return 0;
+		}
+	}
+
+	/* This check even when there's no association involved is intended,
+	 * according to Trent Jaeger, to make sure a process can't engage in
+	 * non-IPsec communication unless explicitly allowed by policy. */
+	return avc_has_perm(sk_sid, SECINITSID_UNLABELED,
+			    SECCLASS_ASSOCIATION, ASSOCIATION__SENDTO, ad);
+}
diff --git a/security/smack/Kconfig b/security/smack/Kconfig
new file mode 100644
index 000000000..5a8dfad46
--- /dev/null
+++ b/security/smack/Kconfig
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_SMACK
+	bool "Simplified Mandatory Access Control Kernel Support"
+	depends on NET
+	depends on INET
+	depends on SECURITY
+	select NETLABEL
+	select SECURITY_NETWORK
+	default n
+	help
+	  This selects the Simplified Mandatory Access Control Kernel.
+	  Smack is useful for sensitivity, integrity, and a variety
+	  of other mandatory security schemes.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_SMACK_BRINGUP
+	bool "Reporting on access granted by Smack rules"
+	depends on SECURITY_SMACK
+	default n
+	help
+	  Enable the bring-up ("b") access mode in Smack rules.
+	  When access is granted by a rule with the "b" mode a
+	  message about the access requested is generated. The
+	  intention is that a process can be granted a wide set
+	  of access initially with the bringup mode set on the
+	  rules. The developer can use the information to
+	  identify which rules are necessary and what accesses
+	  may be inappropriate. The developer can reduce the
+	  access rule set once the behavior is well understood.
+	  This is a superior mechanism to the oft abused
+	  "permissive" mode of other systems.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_SMACK_NETFILTER
+	bool "Packet marking using secmarks for netfilter"
+	depends on SECURITY_SMACK
+	depends on NETWORK_SECMARK
+	depends on NETFILTER
+	default n
+	help
+	  This enables security marking of network packets using
+	  Smack labels.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_SMACK_APPEND_SIGNALS
+	bool "Treat delivering signals as an append operation"
+	depends on SECURITY_SMACK
+	default n
+	help
+	  Sending a signal has been treated as a write operation to the
+	  receiving process. If this option is selected, the delivery
+	  will be an append operation instead. This makes it possible
+	  to differentiate between delivering a network packet and
+	  delivering a signal in the Smack rules.
+	  If you are unsure how to answer this question, answer N.
diff --git a/security/smack/Makefile b/security/smack/Makefile
new file mode 100644
index 000000000..6dbf6e22a
--- /dev/null
+++ b/security/smack/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the SMACK LSM
+#
+
+obj-$(CONFIG_SECURITY_SMACK) := smack.o
+
+smack-y := smack_lsm.o smack_access.o smackfs.o
+smack-$(CONFIG_SECURITY_SMACK_NETFILTER) += smack_netfilter.o
diff --git a/security/smack/smack.h b/security/smack/smack.h
new file mode 100644
index 000000000..2a60a045b
--- /dev/null
+++ b/security/smack/smack.h
@@ -0,0 +1,543 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com>
+ *
+ * Author:
+ *      Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#ifndef _SECURITY_SMACK_H
+#define _SECURITY_SMACK_H
+
+#include <linux/capability.h>
+#include <linux/spinlock.h>
+#include <linux/lsm_hooks.h>
+#include <linux/in.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#endif /* CONFIG_IPV6 */
+#include <net/netlabel.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/lsm_audit.h>
+#include <linux/msg.h>
+
+/*
+ * Use IPv6 port labeling if IPv6 is enabled and secmarks
+ * are not being used.
+ */
+#if IS_ENABLED(CONFIG_IPV6) && !defined(CONFIG_SECURITY_SMACK_NETFILTER)
+#define SMACK_IPV6_PORT_LABELING 1
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6) && defined(CONFIG_SECURITY_SMACK_NETFILTER)
+#define SMACK_IPV6_SECMARK_LABELING 1
+#endif
+
+/*
+ * Smack labels were limited to 23 characters for a long time.
+ */
+#define SMK_LABELLEN	24
+#define SMK_LONGLABEL	256
+
+/*
+ * This is the repository for labels seen so that it is
+ * not necessary to keep allocating tiny chunks of memory
+ * and so that they can be shared.
+ *
+ * Labels are never modified in place. Anytime a label
+ * is imported (e.g. xattrset on a file) the list is checked
+ * for it and it is added if it doesn't exist. The address
+ * is passed out in either case. Entries are added, but
+ * never deleted.
+ *
+ * Since labels are hanging around anyway it doesn't
+ * hurt to maintain a secid for those awkward situations
+ * where kernel components that ought to use LSM independent
+ * interfaces don't. The secid should go away when all of
+ * these components have been repaired.
+ *
+ * The cipso value associated with the label gets stored here, too.
+ *
+ * Keep the access rules for this subject label here so that
+ * the entire set of rules does not need to be examined every
+ * time.
+ */
+struct smack_known {
+	struct list_head		list;
+	struct hlist_node		smk_hashed;
+	char				*smk_known;
+	u32				smk_secid;
+	struct netlbl_lsm_secattr	smk_netlabel;	/* on wire labels */
+	struct list_head		smk_rules;	/* access rules */
+	struct mutex			smk_rules_lock;	/* lock for rules */
+};
+
+/*
+ * Maximum number of bytes for the levels in a CIPSO IP option.
+ * Why 23? CIPSO is constrained to 30, so a 32 byte buffer is
+ * bigger than can be used, and 24 is the next lower multiple
+ * of 8, and there are too many issues if there isn't space set
+ * aside for the terminating null byte.
+ */
+#define SMK_CIPSOLEN	24
+
+struct superblock_smack {
+	struct smack_known	*smk_root;
+	struct smack_known	*smk_floor;
+	struct smack_known	*smk_hat;
+	struct smack_known	*smk_default;
+	int			smk_flags;
+};
+
+/*
+ * Superblock flags
+ */
+#define SMK_SB_INITIALIZED	0x01
+#define SMK_SB_UNTRUSTED	0x02
+
+struct socket_smack {
+	struct smack_known	*smk_out;	/* outbound label */
+	struct smack_known	*smk_in;	/* inbound label */
+	struct smack_known	*smk_packet;	/* TCP peer label */
+	int			smk_state;	/* netlabel socket states */
+};
+#define	SMK_NETLBL_UNSET	0
+#define	SMK_NETLBL_UNLABELED	1
+#define	SMK_NETLBL_LABELED	2
+#define	SMK_NETLBL_REQSKB	3
+
+/*
+ * Inode smack data
+ */
+struct inode_smack {
+	struct smack_known	*smk_inode;	/* label of the fso */
+	struct smack_known	*smk_task;	/* label of the task */
+	struct smack_known	*smk_mmap;	/* label of the mmap domain */
+	int			smk_flags;	/* smack inode flags */
+};
+
+struct task_smack {
+	struct smack_known	*smk_task;	/* label for access control */
+	struct smack_known	*smk_forked;	/* label when forked */
+	struct smack_known	*smk_transmuted;/* label when transmuted */
+	struct list_head	smk_rules;	/* per task access rules */
+	struct mutex		smk_rules_lock;	/* lock for the rules */
+	struct list_head	smk_relabel;	/* transit allowed labels */
+};
+
+#define	SMK_INODE_INSTANT	0x01	/* inode is instantiated */
+#define	SMK_INODE_TRANSMUTE	0x02	/* directory is transmuting */
+#define	SMK_INODE_CHANGED	0x04	/* smack was transmuted (unused) */
+#define	SMK_INODE_IMPURE	0x08	/* involved in an impure transaction */
+
+/*
+ * A label access rule.
+ */
+struct smack_rule {
+	struct list_head	list;
+	struct smack_known	*smk_subject;
+	struct smack_known	*smk_object;
+	int			smk_access;
+};
+
+/*
+ * An entry in the table identifying IPv4 hosts.
+ */
+struct smk_net4addr {
+	struct list_head	list;
+	struct in_addr		smk_host;	/* network address */
+	struct in_addr		smk_mask;	/* network mask */
+	int			smk_masks;	/* mask size */
+	struct smack_known	*smk_label;	/* label */
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+/*
+ * An entry in the table identifying IPv6 hosts.
+ */
+struct smk_net6addr {
+	struct list_head	list;
+	struct in6_addr		smk_host;	/* network address */
+	struct in6_addr		smk_mask;	/* network mask */
+	int			smk_masks;	/* mask size */
+	struct smack_known	*smk_label;	/* label */
+};
+#endif /* CONFIG_IPV6 */
+
+#ifdef SMACK_IPV6_PORT_LABELING
+/*
+ * An entry in the table identifying ports.
+ */
+struct smk_port_label {
+	struct list_head	list;
+	struct sock		*smk_sock;	/* socket initialized on */
+	unsigned short		smk_port;	/* the port number */
+	struct smack_known	*smk_in;	/* inbound label */
+	struct smack_known	*smk_out;	/* outgoing label */
+	short			smk_sock_type;	/* Socket type */
+	short			smk_can_reuse;
+};
+#endif /* SMACK_IPV6_PORT_LABELING */
+
+struct smack_known_list_elem {
+	struct list_head	list;
+	struct smack_known	*smk_label;
+};
+
+enum {
+	Opt_error = -1,
+	Opt_fsdefault = 0,
+	Opt_fsfloor = 1,
+	Opt_fshat = 2,
+	Opt_fsroot = 3,
+	Opt_fstransmute = 4,
+};
+
+#define SMACK_DELETE_OPTION	"-DELETE"
+#define SMACK_CIPSO_OPTION 	"-CIPSO"
+
+/*
+ * CIPSO defaults.
+ */
+#define SMACK_CIPSO_DOI_DEFAULT		3	/* Historical */
+#define SMACK_CIPSO_DOI_INVALID		-1	/* Not a DOI */
+#define SMACK_CIPSO_DIRECT_DEFAULT	250	/* Arbitrary */
+#define SMACK_CIPSO_MAPPED_DEFAULT	251	/* Also arbitrary */
+#define SMACK_CIPSO_MAXLEVEL            255     /* CIPSO 2.2 standard */
+/*
+ * CIPSO 2.2 standard is 239, but Smack wants to use the
+ * categories in a structured way that limits the value to
+ * the bits in 23 bytes, hence the unusual number.
+ */
+#define SMACK_CIPSO_MAXCATNUM           184     /* 23 * 8 */
+
+/*
+ * Ptrace rules
+ */
+#define SMACK_PTRACE_DEFAULT	0
+#define SMACK_PTRACE_EXACT	1
+#define SMACK_PTRACE_DRACONIAN	2
+#define SMACK_PTRACE_MAX	SMACK_PTRACE_DRACONIAN
+
+/*
+ * Flags for untraditional access modes.
+ * It shouldn't be necessary to avoid conflicts with definitions
+ * in fs.h, but do so anyway.
+ */
+#define MAY_TRANSMUTE	0x00001000	/* Controls directory labeling */
+#define MAY_LOCK	0x00002000	/* Locks should be writes, but ... */
+#define MAY_BRINGUP	0x00004000	/* Report use of this rule */
+
+/*
+ * The policy for delivering signals is configurable.
+ * It is usually "write", but can be "append".
+ */
+#ifdef CONFIG_SECURITY_SMACK_APPEND_SIGNALS
+#define MAY_DELIVER	MAY_APPEND	/* Signal delivery requires append */
+#else
+#define MAY_DELIVER	MAY_WRITE	/* Signal delivery requires write */
+#endif
+
+#define SMACK_BRINGUP_ALLOW		1	/* Allow bringup mode */
+#define SMACK_UNCONFINED_SUBJECT	2	/* Allow unconfined label */
+#define SMACK_UNCONFINED_OBJECT		3	/* Allow unconfined label */
+
+/*
+ * Just to make the common cases easier to deal with
+ */
+#define MAY_ANYREAD	(MAY_READ | MAY_EXEC)
+#define MAY_READWRITE	(MAY_READ | MAY_WRITE)
+#define MAY_NOT		0
+
+/*
+ * Number of access types used by Smack (rwxatlb)
+ */
+#define SMK_NUM_ACCESS_TYPE 7
+
+/* SMACK data */
+struct smack_audit_data {
+	const char *function;
+	char *subject;
+	char *object;
+	char *request;
+	struct task_struct *subj_tsk;
+	int result;
+};
+
+/*
+ * Smack audit data; is empty if CONFIG_AUDIT not set
+ * to save some stack
+ */
+struct smk_audit_info {
+#ifdef CONFIG_AUDIT
+	struct common_audit_data a;
+	struct smack_audit_data sad;
+#endif
+};
+
+/*
+ * Initialization
+ */
+#if defined(CONFIG_SECURITY_SMACK_NETFILTER)
+int smack_nf_ip_init(void);
+#else
+static inline int smack_nf_ip_init(void)
+{
+	return 0;
+}
+#endif
+int init_smk_fs(void);
+int smack_initcall(void);
+
+/*
+ * These functions are in smack_access.c
+ */
+int smk_access_entry(char *, char *, struct list_head *);
+int smk_access(struct smack_known *, struct smack_known *,
+	       int, struct smk_audit_info *);
+int smk_tskacc(struct task_smack *, struct smack_known *,
+	       u32, struct smk_audit_info *);
+int smk_curacc(struct smack_known *, u32, struct smk_audit_info *);
+int smack_str_from_perm(char *string, int access);
+struct smack_known *smack_from_secid(const u32);
+int smk_parse_label_len(const char *string, int len);
+char *smk_parse_smack(const char *string, int len);
+int smk_netlbl_mls(int, char *, struct netlbl_lsm_secattr *, int);
+struct smack_known *smk_import_entry(const char *, int);
+struct smack_known *smk_import_valid_label(const char *label, int label_len,
+					   gfp_t gfp);
+void smk_insert_entry(struct smack_known *skp);
+struct smack_known *smk_find_entry(const char *);
+bool smack_privileged(int cap);
+bool smack_privileged_cred(int cap, const struct cred *cred);
+void smk_destroy_label_list(struct list_head *list);
+int smack_populate_secattr(struct smack_known *skp);
+
+/*
+ * Shared data.
+ */
+extern int smack_enabled __initdata;
+extern u8  smack_cipso_auto_level[2];
+#define smack_cipso_direct (+smack_cipso_auto_level[0])
+#define smack_cipso_mapped (+smack_cipso_auto_level[1])
+extern struct smack_known *smack_net_ambient;
+extern struct smack_known *smack_syslog_label;
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+extern struct smack_known *smack_unconfined;
+#endif
+extern int smack_ptrace_rule;
+extern struct lsm_blob_sizes smack_blob_sizes;
+
+extern struct smack_known smack_known_floor;
+extern struct smack_known smack_known_hat;
+extern struct smack_known smack_known_huh;
+extern struct smack_known smack_known_star;
+extern struct smack_known smack_known_web;
+
+extern struct mutex	smack_known_lock;
+extern struct list_head smack_known_list;
+extern struct list_head smk_net4addr_list;
+#if IS_ENABLED(CONFIG_IPV6)
+extern struct list_head smk_net6addr_list;
+#endif /* CONFIG_IPV6 */
+
+extern struct mutex     smack_onlycap_lock;
+extern struct list_head smack_onlycap_list;
+
+#define SMACK_HASH_SLOTS 16
+extern struct hlist_head smack_known_hash[SMACK_HASH_SLOTS];
+extern struct kmem_cache *smack_rule_cache;
+
+static inline struct task_smack *smack_cred(const struct cred *cred)
+{
+	return cred->security + smack_blob_sizes.lbs_cred;
+}
+
+static inline struct smack_known **smack_file(const struct file *file)
+{
+	return (struct smack_known **)(file->f_security +
+				       smack_blob_sizes.lbs_file);
+}
+
+static inline struct inode_smack *smack_inode(const struct inode *inode)
+{
+	return inode->i_security + smack_blob_sizes.lbs_inode;
+}
+
+static inline struct smack_known **smack_msg_msg(const struct msg_msg *msg)
+{
+	return msg->security + smack_blob_sizes.lbs_msg_msg;
+}
+
+static inline struct smack_known **smack_ipc(const struct kern_ipc_perm *ipc)
+{
+	return ipc->security + smack_blob_sizes.lbs_ipc;
+}
+
+static inline struct superblock_smack *smack_superblock(
+					const struct super_block *superblock)
+{
+	return superblock->s_security + smack_blob_sizes.lbs_superblock;
+}
+
+static inline struct socket_smack *smack_sock(const struct sock *sock)
+{
+	return sock->sk_security + smack_blob_sizes.lbs_sock;
+}
+
+#ifdef CONFIG_KEYS
+static inline struct smack_known **smack_key(const struct key *key)
+{
+	return key->security + smack_blob_sizes.lbs_key;
+}
+#endif /* CONFIG_KEYS */
+
+/*
+ * Is the directory transmuting?
+ */
+static inline int smk_inode_transmutable(const struct inode *isp)
+{
+	struct inode_smack *sip = smack_inode(isp);
+	return (sip->smk_flags & SMK_INODE_TRANSMUTE) != 0;
+}
+
+/*
+ * Present a pointer to the smack label entry in an inode blob.
+ */
+static inline struct smack_known *smk_of_inode(const struct inode *isp)
+{
+	struct inode_smack *sip = smack_inode(isp);
+	return sip->smk_inode;
+}
+
+/*
+ * Present a pointer to the smack label entry in an task blob.
+ */
+static inline struct smack_known *smk_of_task(const struct task_smack *tsp)
+{
+	return tsp->smk_task;
+}
+
+static inline struct smack_known *smk_of_task_struct_obj(
+						const struct task_struct *t)
+{
+	struct smack_known *skp;
+	const struct cred *cred;
+
+	rcu_read_lock();
+
+	cred = __task_cred(t);
+	skp = smk_of_task(smack_cred(cred));
+
+	rcu_read_unlock();
+
+	return skp;
+}
+
+/*
+ * Present a pointer to the forked smack label entry in an task blob.
+ */
+static inline struct smack_known *smk_of_forked(const struct task_smack *tsp)
+{
+	return tsp->smk_forked;
+}
+
+/*
+ * Present a pointer to the smack label in the current task blob.
+ */
+static inline struct smack_known *smk_of_current(void)
+{
+	return smk_of_task(smack_cred(current_cred()));
+}
+
+void smack_log(char *subject_label, char *object_label,
+		int request,
+		int result, struct smk_audit_info *auditdata);
+
+#ifdef CONFIG_AUDIT
+
+/*
+ * logging functions
+ */
+#define SMACK_AUDIT_DENIED 0x1
+#define SMACK_AUDIT_ACCEPT 0x2
+extern int log_policy;
+
+/*
+ * some inline functions to set up audit data
+ * they do nothing if CONFIG_AUDIT is not set
+ *
+ */
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+			       char type)
+{
+	memset(&a->sad, 0, sizeof(a->sad));
+	a->a.type = type;
+	a->a.smack_audit_data = &a->sad;
+	a->a.smack_audit_data->function = func;
+}
+
+static inline void smk_ad_init_net(struct smk_audit_info *a, const char *func,
+				   char type, struct lsm_network_audit *net)
+{
+	smk_ad_init(a, func, type);
+	memset(net, 0, sizeof(*net));
+	a->a.u.net = net;
+}
+
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+					 struct task_struct *t)
+{
+	a->a.u.tsk = t;
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+						    struct dentry *d)
+{
+	a->a.u.dentry = d;
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+					      struct inode *i)
+{
+	a->a.u.inode = i;
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+					     struct path p)
+{
+	a->a.u.path = p;
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+					    struct sock *sk)
+{
+	a->a.u.net->sk = sk;
+}
+
+#else /* no AUDIT */
+
+static inline void smk_ad_init(struct smk_audit_info *a, const char *func,
+			       char type)
+{
+}
+static inline void smk_ad_setfield_u_tsk(struct smk_audit_info *a,
+					 struct task_struct *t)
+{
+}
+static inline void smk_ad_setfield_u_fs_path_dentry(struct smk_audit_info *a,
+						    struct dentry *d)
+{
+}
+static inline void smk_ad_setfield_u_fs_inode(struct smk_audit_info *a,
+					      struct inode *i)
+{
+}
+static inline void smk_ad_setfield_u_fs_path(struct smk_audit_info *a,
+					     struct path p)
+{
+}
+static inline void smk_ad_setfield_u_net_sk(struct smk_audit_info *a,
+					    struct sock *sk)
+{
+}
+#endif
+
+#endif  /* _SECURITY_SMACK_H */
diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c
new file mode 100644
index 000000000..fb8535626
--- /dev/null
+++ b/security/smack/smack_access.c
@@ -0,0 +1,765 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com>
+ *
+ * Author:
+ *      Casey Schaufler <casey@schaufler-ca.com>
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include "smack.h"
+
+struct smack_known smack_known_huh = {
+	.smk_known	= "?",
+	.smk_secid	= 2,
+};
+
+struct smack_known smack_known_hat = {
+	.smk_known	= "^",
+	.smk_secid	= 3,
+};
+
+struct smack_known smack_known_star = {
+	.smk_known	= "*",
+	.smk_secid	= 4,
+};
+
+struct smack_known smack_known_floor = {
+	.smk_known	= "_",
+	.smk_secid	= 5,
+};
+
+struct smack_known smack_known_web = {
+	.smk_known	= "@",
+	.smk_secid	= 7,
+};
+
+LIST_HEAD(smack_known_list);
+
+/*
+ * The initial value needs to be bigger than any of the
+ * known values above.
+ */
+static u32 smack_next_secid = 10;
+
+#ifdef CONFIG_AUDIT
+/*
+ * what events do we log
+ * can be overwritten at run-time by /smack/logging
+ */
+int log_policy = SMACK_AUDIT_DENIED;
+#endif /* CONFIG_AUDIT */
+
+/**
+ * smk_access_entry - look up matching access rule
+ * @subject_label: a pointer to the subject's Smack label
+ * @object_label: a pointer to the object's Smack label
+ * @rule_list: the list of rules to search
+ *
+ * This function looks up the subject/object pair in the
+ * access rule list and returns the access mode. If no
+ * entry is found returns -ENOENT.
+ *
+ * NOTE:
+ *
+ * Earlier versions of this function allowed for labels that
+ * were not on the label list. This was done to allow for
+ * labels to come over the network that had never been seen
+ * before on this host. Unless the receiving socket has the
+ * star label this will always result in a failure check. The
+ * star labeled socket case is now handled in the networking
+ * hooks so there is no case where the label is not on the
+ * label list. Checking to see if the address of two labels
+ * is the same is now a reliable test.
+ *
+ * Do the object check first because that is more
+ * likely to differ.
+ *
+ * Allowing write access implies allowing locking.
+ */
+int smk_access_entry(char *subject_label, char *object_label,
+			struct list_head *rule_list)
+{
+	struct smack_rule *srp;
+
+	list_for_each_entry_rcu(srp, rule_list, list) {
+		if (srp->smk_object->smk_known == object_label &&
+		    srp->smk_subject->smk_known == subject_label) {
+			int may = srp->smk_access;
+			/*
+			 * MAY_WRITE implies MAY_LOCK.
+			 */
+			if ((may & MAY_WRITE) == MAY_WRITE)
+				may |= MAY_LOCK;
+			return may;
+		}
+	}
+
+	return -ENOENT;
+}
+
+/**
+ * smk_access - determine if a subject has a specific access to an object
+ * @subject: a pointer to the subject's Smack label entry
+ * @object: a pointer to the object's Smack label entry
+ * @request: the access requested, in "MAY" format
+ * @a : a pointer to the audit data
+ *
+ * This function looks up the subject/object pair in the
+ * access rule list and returns 0 if the access is permitted,
+ * non zero otherwise.
+ *
+ * Smack labels are shared on smack_list
+ */
+int smk_access(struct smack_known *subject, struct smack_known *object,
+	       int request, struct smk_audit_info *a)
+{
+	int may = MAY_NOT;
+	int rc = 0;
+
+	/*
+	 * Hardcoded comparisons.
+	 */
+	/*
+	 * A star subject can't access any object.
+	 */
+	if (subject == &smack_known_star) {
+		rc = -EACCES;
+		goto out_audit;
+	}
+	/*
+	 * An internet object can be accessed by any subject.
+	 * Tasks cannot be assigned the internet label.
+	 * An internet subject can access any object.
+	 */
+	if (object == &smack_known_web || subject == &smack_known_web)
+		goto out_audit;
+	/*
+	 * A star object can be accessed by any subject.
+	 */
+	if (object == &smack_known_star)
+		goto out_audit;
+	/*
+	 * An object can be accessed in any way by a subject
+	 * with the same label.
+	 */
+	if (subject->smk_known == object->smk_known)
+		goto out_audit;
+	/*
+	 * A hat subject can read or lock any object.
+	 * A floor object can be read or locked by any subject.
+	 */
+	if ((request & MAY_ANYREAD) == request ||
+	    (request & MAY_LOCK) == request) {
+		if (object == &smack_known_floor)
+			goto out_audit;
+		if (subject == &smack_known_hat)
+			goto out_audit;
+	}
+	/*
+	 * Beyond here an explicit relationship is required.
+	 * If the requested access is contained in the available
+	 * access (e.g. read is included in readwrite) it's
+	 * good. A negative response from smk_access_entry()
+	 * indicates there is no entry for this pair.
+	 */
+	rcu_read_lock();
+	may = smk_access_entry(subject->smk_known, object->smk_known,
+			       &subject->smk_rules);
+	rcu_read_unlock();
+
+	if (may <= 0 || (request & may) != request) {
+		rc = -EACCES;
+		goto out_audit;
+	}
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	/*
+	 * Return a positive value if using bringup mode.
+	 * This allows the hooks to identify checks that
+	 * succeed because of "b" rules.
+	 */
+	if (may & MAY_BRINGUP)
+		rc = SMACK_BRINGUP_ALLOW;
+#endif
+
+out_audit:
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	if (rc < 0) {
+		if (object == smack_unconfined)
+			rc = SMACK_UNCONFINED_OBJECT;
+		if (subject == smack_unconfined)
+			rc = SMACK_UNCONFINED_SUBJECT;
+	}
+#endif
+
+#ifdef CONFIG_AUDIT
+	if (a)
+		smack_log(subject->smk_known, object->smk_known,
+			  request, rc, a);
+#endif
+
+	return rc;
+}
+
+/**
+ * smk_tskacc - determine if a task has a specific access to an object
+ * @tsp: a pointer to the subject's task
+ * @obj_known: a pointer to the object's label entry
+ * @mode: the access requested, in "MAY" format
+ * @a : common audit data
+ *
+ * This function checks the subject task's label/object label pair
+ * in the access rule list and returns 0 if the access is permitted,
+ * non zero otherwise. It allows that the task may have the capability
+ * to override the rules.
+ */
+int smk_tskacc(struct task_smack *tsp, struct smack_known *obj_known,
+	       u32 mode, struct smk_audit_info *a)
+{
+	struct smack_known *sbj_known = smk_of_task(tsp);
+	int may;
+	int rc;
+
+	/*
+	 * Check the global rule list
+	 */
+	rc = smk_access(sbj_known, obj_known, mode, NULL);
+	if (rc >= 0) {
+		/*
+		 * If there is an entry in the task's rule list
+		 * it can further restrict access.
+		 */
+		may = smk_access_entry(sbj_known->smk_known,
+				       obj_known->smk_known,
+				       &tsp->smk_rules);
+		if (may < 0)
+			goto out_audit;
+		if ((mode & may) == mode)
+			goto out_audit;
+		rc = -EACCES;
+	}
+
+	/*
+	 * Allow for privileged to override policy.
+	 */
+	if (rc != 0 && smack_privileged(CAP_MAC_OVERRIDE))
+		rc = 0;
+
+out_audit:
+#ifdef CONFIG_AUDIT
+	if (a)
+		smack_log(sbj_known->smk_known, obj_known->smk_known,
+			  mode, rc, a);
+#endif
+	return rc;
+}
+
+/**
+ * smk_curacc - determine if current has a specific access to an object
+ * @obj_known: a pointer to the object's Smack label entry
+ * @mode: the access requested, in "MAY" format
+ * @a : common audit data
+ *
+ * This function checks the current subject label/object label pair
+ * in the access rule list and returns 0 if the access is permitted,
+ * non zero otherwise. It allows that current may have the capability
+ * to override the rules.
+ */
+int smk_curacc(struct smack_known *obj_known,
+	       u32 mode, struct smk_audit_info *a)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_tskacc(tsp, obj_known, mode, a);
+}
+
+/**
+ * smack_str_from_perm : helper to translate an int to a
+ * readable string
+ * @string : the string to fill
+ * @access : the int
+ *
+ */
+int smack_str_from_perm(char *string, int access)
+{
+	int i = 0;
+
+	if (access & MAY_READ)
+		string[i++] = 'r';
+	if (access & MAY_WRITE)
+		string[i++] = 'w';
+	if (access & MAY_EXEC)
+		string[i++] = 'x';
+	if (access & MAY_APPEND)
+		string[i++] = 'a';
+	if (access & MAY_TRANSMUTE)
+		string[i++] = 't';
+	if (access & MAY_LOCK)
+		string[i++] = 'l';
+	if (access & MAY_BRINGUP)
+		string[i++] = 'b';
+	if (i == 0)
+		string[i++] = '-';
+	string[i] = '\0';
+	return i;
+}
+
+#ifdef CONFIG_AUDIT
+/**
+ * smack_log_callback - SMACK specific information
+ * will be called by generic audit code
+ * @ab : the audit_buffer
+ * @a  : audit_data
+ *
+ */
+static void smack_log_callback(struct audit_buffer *ab, void *a)
+{
+	struct common_audit_data *ad = a;
+	struct smack_audit_data *sad = ad->smack_audit_data;
+	audit_log_format(ab, "lsm=SMACK fn=%s action=%s",
+			 ad->smack_audit_data->function,
+			 sad->result ? "denied" : "granted");
+	audit_log_format(ab, " subject=");
+	audit_log_untrustedstring(ab, sad->subject);
+	audit_log_format(ab, " object=");
+	audit_log_untrustedstring(ab, sad->object);
+	if (sad->request[0] == '\0')
+		audit_log_format(ab, " labels_differ");
+	else
+		audit_log_format(ab, " requested=%s", sad->request);
+
+	if (sad->subj_tsk) {
+		char comm[TASK_COMM_LEN];
+
+		audit_log_format(ab, " subj_pid=%d subj_comm=",
+			task_tgid_nr(sad->subj_tsk));
+		audit_log_untrustedstring(ab,
+			get_task_comm(comm, sad->subj_tsk));
+	}
+}
+
+/**
+ *  smack_log - Audit the granting or denial of permissions.
+ *  @subject_label : smack label of the requester
+ *  @object_label  : smack label of the object being accessed
+ *  @request: requested permissions
+ *  @result: result from smk_access
+ *  @ad:  auxiliary audit data
+ *
+ * Audit the granting or denial of permissions in accordance
+ * with the policy.
+ */
+void smack_log(char *subject_label, char *object_label, int request,
+	       int result, struct smk_audit_info *ad)
+{
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	char request_buffer[SMK_NUM_ACCESS_TYPE + 5];
+#else
+	char request_buffer[SMK_NUM_ACCESS_TYPE + 1];
+#endif
+	struct smack_audit_data *sad;
+	struct common_audit_data *a = &ad->a;
+
+	/* check if we have to log the current event */
+	if (result < 0 && (log_policy & SMACK_AUDIT_DENIED) == 0)
+		return;
+	if (result == 0 && (log_policy & SMACK_AUDIT_ACCEPT) == 0)
+		return;
+
+	sad = a->smack_audit_data;
+
+	if (sad->function == NULL)
+		sad->function = "unknown";
+
+	/* end preparing the audit data */
+	smack_str_from_perm(request_buffer, request);
+	sad->subject = subject_label;
+	sad->object  = object_label;
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	/*
+	 * The result may be positive in bringup mode.
+	 * A positive result is an allow, but not for normal reasons.
+	 * Mark it as successful, but don't filter it out even if
+	 * the logging policy says to do so.
+	 */
+	if (result == SMACK_UNCONFINED_SUBJECT)
+		strcat(request_buffer, "(US)");
+	else if (result == SMACK_UNCONFINED_OBJECT)
+		strcat(request_buffer, "(UO)");
+
+	if (result > 0)
+		result = 0;
+#endif
+	sad->request = request_buffer;
+	sad->result  = result;
+
+	common_lsm_audit(a, smack_log_callback, NULL);
+}
+#else /* #ifdef CONFIG_AUDIT */
+void smack_log(char *subject_label, char *object_label, int request,
+	       int result, struct smk_audit_info *ad)
+{
+}
+#endif
+
+DEFINE_MUTEX(smack_known_lock);
+
+struct hlist_head smack_known_hash[SMACK_HASH_SLOTS];
+
+/**
+ * smk_insert_entry - insert a smack label into a hash map,
+ * @skp: smack label
+ *
+ * this function must be called under smack_known_lock
+ */
+void smk_insert_entry(struct smack_known *skp)
+{
+	unsigned int hash;
+	struct hlist_head *head;
+
+	hash = full_name_hash(NULL, skp->smk_known, strlen(skp->smk_known));
+	head = &smack_known_hash[hash & (SMACK_HASH_SLOTS - 1)];
+
+	hlist_add_head_rcu(&skp->smk_hashed, head);
+	list_add_rcu(&skp->list, &smack_known_list);
+}
+
+/**
+ * smk_find_entry - find a label on the list, return the list entry
+ * @string: a text string that might be a Smack label
+ *
+ * Returns a pointer to the entry in the label list that
+ * matches the passed string or NULL if not found.
+ */
+struct smack_known *smk_find_entry(const char *string)
+{
+	unsigned int hash;
+	struct hlist_head *head;
+	struct smack_known *skp;
+
+	hash = full_name_hash(NULL, string, strlen(string));
+	head = &smack_known_hash[hash & (SMACK_HASH_SLOTS - 1)];
+
+	hlist_for_each_entry_rcu(skp, head, smk_hashed)
+		if (strcmp(skp->smk_known, string) == 0)
+			return skp;
+
+	return NULL;
+}
+
+/**
+ * smk_parse_label_len - calculate the length of the starting segment
+ *                       in the string that constitutes a valid smack label
+ * @string: a text string that might contain a Smack label at the beginning
+ * @len: the maximum size to look into, may be zero if string is null-terminated
+ *
+ * Returns the length of the segment (0 < L < SMK_LONGLABEL) or an error code.
+ */
+int smk_parse_label_len(const char *string, int len)
+{
+	int i;
+
+	if (len <= 0 || len > SMK_LONGLABEL)
+		len = SMK_LONGLABEL;
+
+	/*
+	 * Reserve a leading '-' as an indicator that
+	 * this isn't a label, but an option to interfaces
+	 * including /smack/cipso and /smack/cipso2
+	 */
+	if (string[0] == '-')
+		return -EINVAL;
+
+	for (i = 0; i < len; i++)
+		if (string[i] > '~' || string[i] <= ' ' || string[i] == '/' ||
+		    string[i] == '"' || string[i] == '\\' || string[i] == '\'')
+			break;
+
+	if (i == 0 || i >= SMK_LONGLABEL)
+		return -EINVAL;
+
+	return i;
+}
+
+/**
+ * smk_parse_smack - copy the starting segment in the string
+ *                   that constitutes a valid smack label
+ * @string: a text string that might contain a Smack label at the beginning
+ * @len: the maximum size to look into, may be zero if string is null-terminated
+ *
+ * Returns a pointer to the copy of the label or an error code.
+ */
+char *smk_parse_smack(const char *string, int len)
+{
+	char *smack;
+	int i = smk_parse_label_len(string, len);
+
+	if (i < 0)
+		return ERR_PTR(-EINVAL);
+
+	smack = kstrndup(string, i, GFP_NOFS);
+	if (!smack)
+		return ERR_PTR(-ENOMEM);
+	return smack;
+}
+
+/**
+ * smk_netlbl_mls - convert a catset to netlabel mls categories
+ * @level: MLS sensitivity level
+ * @catset: the Smack categories
+ * @sap: where to put the netlabel categories
+ * @len: number of bytes for the levels in a CIPSO IP option
+ *
+ * Allocates and fills attr.mls
+ * Returns 0 on success, error code on failure.
+ */
+int smk_netlbl_mls(int level, char *catset, struct netlbl_lsm_secattr *sap,
+			int len)
+{
+	unsigned char *cp;
+	unsigned char m;
+	int cat;
+	int rc;
+	int byte;
+
+	sap->flags |= NETLBL_SECATTR_MLS_CAT;
+	sap->attr.mls.lvl = level;
+	sap->attr.mls.cat = NULL;
+
+	for (cat = 1, cp = catset, byte = 0; byte < len; cp++, byte++)
+		for (m = 0x80; m != 0; m >>= 1, cat++) {
+			if ((m & *cp) == 0)
+				continue;
+			rc = netlbl_catmap_setbit(&sap->attr.mls.cat,
+						  cat, GFP_NOFS);
+			if (rc < 0) {
+				netlbl_catmap_free(sap->attr.mls.cat);
+				return rc;
+			}
+		}
+
+	return 0;
+}
+
+/**
+ * smack_populate_secattr - fill in the smack_known netlabel information
+ * @skp: pointer to the structure to fill
+ *
+ * Populate the netlabel secattr structure for a Smack label.
+ *
+ * Returns 0 unless creating the category mapping fails
+ */
+int smack_populate_secattr(struct smack_known *skp)
+{
+	int slen;
+
+	skp->smk_netlabel.attr.secid = skp->smk_secid;
+	skp->smk_netlabel.domain = skp->smk_known;
+	skp->smk_netlabel.cache = netlbl_secattr_cache_alloc(GFP_ATOMIC);
+	if (skp->smk_netlabel.cache != NULL) {
+		skp->smk_netlabel.flags |= NETLBL_SECATTR_CACHE;
+		skp->smk_netlabel.cache->free = NULL;
+		skp->smk_netlabel.cache->data = skp;
+	}
+	skp->smk_netlabel.flags |= NETLBL_SECATTR_SECID |
+				   NETLBL_SECATTR_MLS_LVL |
+				   NETLBL_SECATTR_DOMAIN;
+	/*
+	 * If direct labeling works use it.
+	 * Otherwise use mapped labeling.
+	 */
+	slen = strlen(skp->smk_known);
+	if (slen < SMK_CIPSOLEN)
+		return smk_netlbl_mls(smack_cipso_direct, skp->smk_known,
+				      &skp->smk_netlabel, slen);
+
+	return smk_netlbl_mls(smack_cipso_mapped, (char *)&skp->smk_secid,
+			      &skp->smk_netlabel, sizeof(skp->smk_secid));
+}
+
+/**
+ * smk_import_valid_allocated_label - import a label, return the list entry
+ * @smack: a text string that is a valid Smack label and may be kfree()ed.
+ *         It is consumed: either becomes a part of the entry or kfree'ed.
+ * @gfp: Allocation type
+ *
+ * Returns: see description of smk_import_entry()
+ */
+static struct smack_known *
+smk_import_allocated_label(char *smack, gfp_t gfp)
+{
+	struct smack_known *skp;
+	int rc;
+
+	mutex_lock(&smack_known_lock);
+
+	skp = smk_find_entry(smack);
+	if (skp != NULL)
+		goto freeout;
+
+	skp = kzalloc_obj(*skp, gfp);
+	if (skp == NULL) {
+		skp = ERR_PTR(-ENOMEM);
+		goto freeout;
+	}
+
+	skp->smk_known = smack;
+	skp->smk_secid = smack_next_secid++;
+
+	rc = smack_populate_secattr(skp);
+	if (rc >= 0) {
+		INIT_LIST_HEAD(&skp->smk_rules);
+		mutex_init(&skp->smk_rules_lock);
+		/*
+		 * Make sure that the entry is actually
+		 * filled before putting it on the list.
+		 */
+		smk_insert_entry(skp);
+		goto unlockout;
+	}
+	kfree(skp);
+	skp = ERR_PTR(rc);
+freeout:
+	kfree(smack);
+unlockout:
+	mutex_unlock(&smack_known_lock);
+
+	return skp;
+}
+
+/**
+ * smk_import_entry - import a label, return the list entry
+ * @string: a text string that might contain a Smack label at the beginning
+ * @len: the maximum size to look into, may be zero if string is null-terminated
+ *
+ * Returns a pointer to the entry in the label list that
+ * matches the passed string, adding it if necessary,
+ * or an error code.
+ */
+struct smack_known *smk_import_entry(const char *string, int len)
+{
+	char *smack = smk_parse_smack(string, len);
+
+	if (IS_ERR(smack))
+		return ERR_CAST(smack);
+
+	return smk_import_allocated_label(smack, GFP_NOFS);
+}
+
+/**
+ * smk_import_valid_label - import a label, return the list entry
+ * @label: a text string that is a valid Smack label, not null-terminated
+ * @label_len: the length of the text string in the @label
+ * @gfp: the GFP mask used for allocating memory for the @label text string copy
+ *
+ * Return: see description of smk_import_entry()
+ */
+struct smack_known *
+smk_import_valid_label(const char *label, int label_len, gfp_t gfp)
+{
+	char *smack = kstrndup(label, label_len, gfp);
+
+	if  (!smack)
+		return ERR_PTR(-ENOMEM);
+
+	return smk_import_allocated_label(smack, gfp);
+}
+
+/**
+ * smack_from_secid - find the Smack label associated with a secid
+ * @secid: an integer that might be associated with a Smack label
+ *
+ * Returns a pointer to the appropriate Smack label entry if there is one,
+ * otherwise a pointer to the invalid Smack label.
+ */
+struct smack_known *smack_from_secid(const u32 secid)
+{
+	struct smack_known *skp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(skp, &smack_known_list, list) {
+		if (skp->smk_secid == secid) {
+			rcu_read_unlock();
+			return skp;
+		}
+	}
+
+	/*
+	 * If we got this far someone asked for the translation
+	 * of a secid that is not on the list.
+	 */
+	rcu_read_unlock();
+	return &smack_known_huh;
+}
+
+/*
+ * Unless a process is running with one of these labels
+ * even having CAP_MAC_OVERRIDE isn't enough to grant
+ * privilege to violate MAC policy. If no labels are
+ * designated (the empty list case) capabilities apply to
+ * everyone.
+ */
+LIST_HEAD(smack_onlycap_list);
+DEFINE_MUTEX(smack_onlycap_lock);
+
+/**
+ * smack_privileged_cred - are all privilege requirements met by cred
+ * @cap: The requested capability
+ * @cred: the credential to use
+ *
+ * Is the task privileged and allowed to be privileged
+ * by the onlycap rule.
+ *
+ * Returns true if the task is allowed to be privileged, false if it's not.
+ */
+bool smack_privileged_cred(int cap, const struct cred *cred)
+{
+	struct task_smack *tsp = smack_cred(cred);
+	struct smack_known *skp = tsp->smk_task;
+	struct smack_known_list_elem *sklep;
+	int rc;
+
+	rc = cap_capable(cred, &init_user_ns, cap, CAP_OPT_NONE);
+	if (rc)
+		return false;
+
+	rcu_read_lock();
+	if (list_empty(&smack_onlycap_list)) {
+		rcu_read_unlock();
+		return true;
+	}
+
+	list_for_each_entry_rcu(sklep, &smack_onlycap_list, list) {
+		if (sklep->smk_label == skp) {
+			rcu_read_unlock();
+			return true;
+		}
+	}
+	rcu_read_unlock();
+
+	return false;
+}
+
+/**
+ * smack_privileged - are all privilege requirements met
+ * @cap: The requested capability
+ *
+ * Is the task privileged and allowed to be privileged
+ * by the onlycap rule.
+ *
+ * Returns true if the task is allowed to be privileged, false if it's not.
+ */
+bool smack_privileged(int cap)
+{
+	/*
+	 * All kernel tasks are privileged
+	 */
+	if (unlikely(current->flags & PF_KTHREAD))
+		return true;
+
+	return smack_privileged_cred(cap, current_cred());
+}
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
new file mode 100644
index 000000000..8e88ac65f
--- /dev/null
+++ b/security/smack/smack_lsm.c
@@ -0,0 +1,5411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Simplified MAC Kernel (smack) security module
+ *
+ *  This file contains the smack hook function implementations.
+ *
+ *  Authors:
+ *	Casey Schaufler <casey@schaufler-ca.com>
+ *	Jarkko Sakkinen <jarkko.sakkinen@intel.com>
+ *
+ *  Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com>
+ *  Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
+ *                Paul Moore <paul@paul-moore.com>
+ *  Copyright (C) 2010 Nokia Corporation
+ *  Copyright (C) 2011 Intel Corporation.
+ */
+
+#include <linux/xattr.h>
+#include <linux/pagemap.h>
+#include <linux/mount.h>
+#include <linux/stat.h>
+#include <linux/kd.h>
+#include <asm/ioctls.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmpv6.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <net/cipso_ipv4.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/audit.h>
+#include <linux/magic.h>
+#include <linux/dcache.h>
+#include <linux/personality.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <uapi/linux/shm.h>
+#include <linux/binfmts.h>
+#include <linux/parser.h>
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+#include <linux/watch_queue.h>
+#include <linux/io_uring/cmd.h>
+#include <uapi/linux/lsm.h>
+#include "smack.h"
+
+#define TRANS_TRUE	"TRUE"
+#define TRANS_TRUE_SIZE	4
+
+#define SMK_CONNECTING	0
+#define SMK_RECEIVING	1
+#define SMK_SENDING	2
+
+/*
+ * Smack uses multiple xattrs.
+ * SMACK64 - for access control,
+ * SMACK64TRANSMUTE - label initialization,
+ * Not saved on files - SMACK64IPIN and SMACK64IPOUT,
+ * Must be set explicitly - SMACK64EXEC and SMACK64MMAP
+ */
+#define SMACK_INODE_INIT_XATTRS 2
+
+#ifdef SMACK_IPV6_PORT_LABELING
+static DEFINE_MUTEX(smack_ipv6_lock);
+static LIST_HEAD(smk_ipv6_port_list);
+#endif
+struct kmem_cache *smack_rule_cache;
+int smack_enabled __initdata;
+
+#define A(s) {"smack"#s, sizeof("smack"#s) - 1, Opt_##s}
+static struct {
+	const char *name;
+	int len;
+	int opt;
+} smk_mount_opts[] = {
+	{"smackfsdef", sizeof("smackfsdef") - 1, Opt_fsdefault},
+	A(fsdefault), A(fsfloor), A(fshat), A(fsroot), A(fstransmute)
+};
+#undef A
+
+static int match_opt_prefix(char *s, int l, char **arg)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(smk_mount_opts); i++) {
+		size_t len = smk_mount_opts[i].len;
+		if (len > l || memcmp(s, smk_mount_opts[i].name, len))
+			continue;
+		if (len == l || s[len] != '=')
+			continue;
+		*arg = s + len + 1;
+		return smk_mount_opts[i].opt;
+	}
+	return Opt_error;
+}
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static char *smk_bu_mess[] = {
+	"Bringup Error",	/* Unused */
+	"Bringup",		/* SMACK_BRINGUP_ALLOW */
+	"Unconfined Subject",	/* SMACK_UNCONFINED_SUBJECT */
+	"Unconfined Object",	/* SMACK_UNCONFINED_OBJECT */
+};
+
+static void smk_bu_mode(int mode, char *s)
+{
+	smack_str_from_perm(s, mode);
+}
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_note(char *note, struct smack_known *sskp,
+		       struct smack_known *oskp, int mode, int rc)
+{
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack %s: (%s %s %s) %s\n", smk_bu_mess[rc],
+		sskp->smk_known, oskp->smk_known, acc, note);
+	return 0;
+}
+#else
+#define smk_bu_note(note, sskp, oskp, mode, RC) (RC)
+#endif
+
+static int
+smk_bu_tsk_to_obj(struct task_struct *tsk, const struct task_smack *tsp,
+		  char *note, struct smack_known *oskp, int mode, int rc)
+{
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+	char comm[TASK_COMM_LEN];
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+
+	smk_bu_mode(mode, acc);
+
+	pr_info("Smack %s: (%s %s %s) %s %s\n", smk_bu_mess[rc],
+		smk_of_task(tsp)->smk_known, oskp->smk_known,
+		acc, get_task_comm(comm, tsk), note);
+	return 0;
+#else
+	return rc;
+#endif
+}
+
+static int smk_bu_current(char *note, struct smack_known *oskp,
+			  int mode, int rc)
+{
+	return smk_bu_tsk_to_obj(current, smack_cred(current_cred()),
+				 note, oskp, mode, rc);
+}
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_task(struct task_struct *otp, int mode, int rc)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct smack_known *smk_task = smk_of_task_struct_obj(otp);
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack %s: (%s %s %s) %s to %s\n", smk_bu_mess[rc],
+		tsp->smk_task->smk_known, smk_task->smk_known, acc,
+		current->comm, otp->comm);
+	return 0;
+}
+#else
+#define smk_bu_task(otp, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_inode(struct inode *inode, int mode, int rc)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct inode_smack *isp = smack_inode(inode);
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (isp->smk_flags & SMK_INODE_IMPURE)
+		pr_info("Smack Unconfined Corruption: inode=(%s %llu) %s\n",
+			inode->i_sb->s_id, inode->i_ino, current->comm);
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+	if (rc == SMACK_UNCONFINED_SUBJECT &&
+	    (mode & (MAY_WRITE | MAY_APPEND)))
+		isp->smk_flags |= SMK_INODE_IMPURE;
+
+	smk_bu_mode(mode, acc);
+
+	pr_info("Smack %s: (%s %s %s) inode=(%s %llu) %s\n", smk_bu_mess[rc],
+		tsp->smk_task->smk_known, isp->smk_inode->smk_known, acc,
+		inode->i_sb->s_id, inode->i_ino, current->comm);
+	return 0;
+}
+#else
+#define smk_bu_inode(inode, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_file(struct file *file, int mode, int rc)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct smack_known *sskp = tsp->smk_task;
+	struct inode *inode = file_inode(file);
+	struct inode_smack *isp = smack_inode(inode);
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (isp->smk_flags & SMK_INODE_IMPURE)
+		pr_info("Smack Unconfined Corruption: inode=(%s %llu) %s\n",
+			inode->i_sb->s_id, inode->i_ino, current->comm);
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack %s: (%s %s %s) file=(%s %llu %pD) %s\n", smk_bu_mess[rc],
+		sskp->smk_known, smk_of_inode(inode)->smk_known, acc,
+		inode->i_sb->s_id, inode->i_ino, file,
+		current->comm);
+	return 0;
+}
+#else
+#define smk_bu_file(file, mode, RC) (RC)
+#endif
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+static int smk_bu_credfile(const struct cred *cred, struct file *file,
+				int mode, int rc)
+{
+	struct task_smack *tsp = smack_cred(cred);
+	struct smack_known *sskp = tsp->smk_task;
+	struct inode *inode = file_inode(file);
+	struct inode_smack *isp = smack_inode(inode);
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+
+	if (isp->smk_flags & SMK_INODE_IMPURE)
+		pr_info("Smack Unconfined Corruption: inode=(%s %llu) %s\n",
+			inode->i_sb->s_id, inode->i_ino, current->comm);
+
+	if (rc <= 0)
+		return rc;
+	if (rc > SMACK_UNCONFINED_OBJECT)
+		rc = 0;
+
+	smk_bu_mode(mode, acc);
+	pr_info("Smack %s: (%s %s %s) file=(%s %llu %pD) %s\n", smk_bu_mess[rc],
+		sskp->smk_known, smk_of_inode(inode)->smk_known, acc,
+		inode->i_sb->s_id, inode->i_ino, file,
+		current->comm);
+	return 0;
+}
+#else
+#define smk_bu_credfile(cred, file, mode, RC) (RC)
+#endif
+
+/**
+ * smk_fetch - Fetch the smack label from a file.
+ * @name: type of the label (attribute)
+ * @ip: a pointer to the inode
+ * @dp: a pointer to the dentry
+ *
+ * Returns a pointer to the master list entry for the Smack label,
+ * NULL if there was no label to fetch, or an error code.
+ */
+static struct smack_known *smk_fetch(const char *name, struct inode *ip,
+					struct dentry *dp)
+{
+	int rc;
+	char *buffer;
+	struct smack_known *skp = NULL;
+
+	if (!(ip->i_opflags & IOP_XATTR))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	buffer = kzalloc(SMK_LONGLABEL, GFP_NOFS);
+	if (buffer == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	rc = __vfs_getxattr(dp, ip, name, buffer, SMK_LONGLABEL);
+	if (rc < 0)
+		skp = ERR_PTR(rc);
+	else if (rc == 0)
+		skp = NULL;
+	else
+		skp = smk_import_entry(buffer, rc);
+
+	kfree(buffer);
+
+	return skp;
+}
+
+/**
+ * init_inode_smack - initialize an inode security blob
+ * @inode: inode to extract the info from
+ * @skp: a pointer to the Smack label entry to use in the blob
+ *
+ */
+static void init_inode_smack(struct inode *inode, struct smack_known *skp)
+{
+	struct inode_smack *isp = smack_inode(inode);
+
+	isp->smk_inode = skp;
+	isp->smk_flags = 0;
+}
+
+/**
+ * init_task_smack - initialize a task security blob
+ * @tsp: blob to initialize
+ * @task: a pointer to the Smack label for the running task
+ * @forked: a pointer to the Smack label for the forked task
+ *
+ */
+static void init_task_smack(struct task_smack *tsp, struct smack_known *task,
+					struct smack_known *forked)
+{
+	tsp->smk_task = task;
+	tsp->smk_forked = forked;
+	INIT_LIST_HEAD(&tsp->smk_rules);
+	INIT_LIST_HEAD(&tsp->smk_relabel);
+	mutex_init(&tsp->smk_rules_lock);
+}
+
+/**
+ * smk_copy_rules - copy a rule set
+ * @nhead: new rules header pointer
+ * @ohead: old rules header pointer
+ * @gfp: type of the memory for the allocation
+ *
+ * Returns 0 on success, -ENOMEM on error
+ */
+static int smk_copy_rules(struct list_head *nhead, struct list_head *ohead,
+				gfp_t gfp)
+{
+	struct smack_rule *nrp;
+	struct smack_rule *orp;
+	int rc = 0;
+
+	list_for_each_entry_rcu(orp, ohead, list) {
+		nrp = kmem_cache_zalloc(smack_rule_cache, gfp);
+		if (nrp == NULL) {
+			rc = -ENOMEM;
+			break;
+		}
+		*nrp = *orp;
+		list_add_rcu(&nrp->list, nhead);
+	}
+	return rc;
+}
+
+/**
+ * smk_copy_relabel - copy smk_relabel labels list
+ * @nhead: new rules header pointer
+ * @ohead: old rules header pointer
+ * @gfp: type of the memory for the allocation
+ *
+ * Returns 0 on success, -ENOMEM on error
+ */
+static int smk_copy_relabel(struct list_head *nhead, struct list_head *ohead,
+				gfp_t gfp)
+{
+	struct smack_known_list_elem *nklep;
+	struct smack_known_list_elem *oklep;
+
+	list_for_each_entry(oklep, ohead, list) {
+		nklep = kzalloc_obj(struct smack_known_list_elem, gfp);
+		if (nklep == NULL) {
+			smk_destroy_label_list(nhead);
+			return -ENOMEM;
+		}
+		nklep->smk_label = oklep->smk_label;
+		list_add(&nklep->list, nhead);
+	}
+
+	return 0;
+}
+
+/**
+ * smk_ptrace_mode - helper function for converting PTRACE_MODE_* into MAY_*
+ * @mode: input mode in form of PTRACE_MODE_*
+ *
+ * Returns a converted MAY_* mode usable by smack rules
+ */
+static inline unsigned int smk_ptrace_mode(unsigned int mode)
+{
+	if (mode & PTRACE_MODE_ATTACH)
+		return MAY_READWRITE;
+	if (mode & PTRACE_MODE_READ)
+		return MAY_READ;
+
+	return 0;
+}
+
+/**
+ * smk_ptrace_rule_check - helper for ptrace access
+ * @tracer: tracer process
+ * @tracee_known: label entry of the process that's about to be traced
+ * @mode: ptrace attachment mode (PTRACE_MODE_*)
+ * @func: name of the function that called us, used for audit
+ *
+ * Returns 0 on access granted, -error on error
+ */
+static int smk_ptrace_rule_check(struct task_struct *tracer,
+				 struct smack_known *tracee_known,
+				 unsigned int mode, const char *func)
+{
+	int rc;
+	struct smk_audit_info ad, *saip = NULL;
+	struct task_smack *tsp;
+	struct smack_known *tracer_known;
+	const struct cred *tracercred;
+
+	if ((mode & PTRACE_MODE_NOAUDIT) == 0) {
+		smk_ad_init(&ad, func, LSM_AUDIT_DATA_TASK);
+		smk_ad_setfield_u_tsk(&ad, tracer);
+		saip = &ad;
+	}
+
+	rcu_read_lock();
+	tracercred = __task_cred(tracer);
+	tsp = smack_cred(tracercred);
+	tracer_known = smk_of_task(tsp);
+
+	if ((mode & PTRACE_MODE_ATTACH) &&
+	    (smack_ptrace_rule == SMACK_PTRACE_EXACT ||
+	     smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)) {
+		if (tracer_known->smk_known == tracee_known->smk_known)
+			rc = 0;
+		else if (smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)
+			rc = -EACCES;
+		else if (smack_privileged_cred(CAP_SYS_PTRACE, tracercred))
+			rc = 0;
+		else
+			rc = -EACCES;
+
+		if (saip)
+			smack_log(tracer_known->smk_known,
+				  tracee_known->smk_known,
+				  0, rc, saip);
+
+		rcu_read_unlock();
+		return rc;
+	}
+
+	/* In case of rule==SMACK_PTRACE_DEFAULT or mode==PTRACE_MODE_READ */
+	rc = smk_tskacc(tsp, tracee_known, smk_ptrace_mode(mode), saip);
+
+	rcu_read_unlock();
+	return rc;
+}
+
+/*
+ * LSM hooks.
+ * We he, that is fun!
+ */
+
+/**
+ * smack_ptrace_access_check - Smack approval on PTRACE_ATTACH
+ * @ctp: child task pointer
+ * @mode: ptrace attachment mode (PTRACE_MODE_*)
+ *
+ * Returns 0 if access is OK, an error code otherwise
+ *
+ * Do the capability checks.
+ */
+static int smack_ptrace_access_check(struct task_struct *ctp, unsigned int mode)
+{
+	struct smack_known *skp;
+
+	skp = smk_of_task_struct_obj(ctp);
+
+	return smk_ptrace_rule_check(current, skp, mode, __func__);
+}
+
+/**
+ * smack_ptrace_traceme - Smack approval on PTRACE_TRACEME
+ * @ptp: parent task pointer
+ *
+ * Returns 0 if access is OK, an error code otherwise
+ *
+ * Do the capability checks, and require PTRACE_MODE_ATTACH.
+ */
+static int smack_ptrace_traceme(struct task_struct *ptp)
+{
+	struct smack_known *skp;
+
+	skp = smk_of_task(smack_cred(current_cred()));
+
+	return smk_ptrace_rule_check(ptp, skp, PTRACE_MODE_ATTACH, __func__);
+}
+
+/**
+ * smack_syslog - Smack approval on syslog
+ * @typefrom_file: unused
+ *
+ * Returns 0 on success, error code otherwise.
+ */
+static int smack_syslog(int typefrom_file)
+{
+	int rc = 0;
+	struct smack_known *skp = smk_of_current();
+
+	if (smack_privileged(CAP_MAC_OVERRIDE))
+		return 0;
+
+	if (smack_syslog_label != NULL && smack_syslog_label != skp)
+		rc = -EACCES;
+
+	return rc;
+}
+
+/*
+ * Superblock Hooks.
+ */
+
+/**
+ * smack_sb_alloc_security - allocate a superblock blob
+ * @sb: the superblock getting the blob
+ *
+ * Returns 0 on success or -ENOMEM on error.
+ */
+static int smack_sb_alloc_security(struct super_block *sb)
+{
+	struct superblock_smack *sbsp = smack_superblock(sb);
+
+	sbsp->smk_root = &smack_known_floor;
+	sbsp->smk_default = &smack_known_floor;
+	sbsp->smk_floor = &smack_known_floor;
+	sbsp->smk_hat = &smack_known_hat;
+	/*
+	 * SMK_SB_INITIALIZED will be zero from kzalloc.
+	 */
+
+	return 0;
+}
+
+struct smack_mnt_opts {
+	const char *fsdefault;
+	const char *fsfloor;
+	const char *fshat;
+	const char *fsroot;
+	const char *fstransmute;
+};
+
+static void smack_free_mnt_opts(void *mnt_opts)
+{
+	kfree(mnt_opts);
+}
+
+static int smack_add_opt(int token, const char *s, void **mnt_opts)
+{
+	struct smack_mnt_opts *opts = *mnt_opts;
+	struct smack_known *skp;
+
+	if (!opts) {
+		opts = kzalloc_obj(struct smack_mnt_opts);
+		if (!opts)
+			return -ENOMEM;
+		*mnt_opts = opts;
+	}
+	if (!s)
+		return -ENOMEM;
+
+	skp = smk_import_entry(s, 0);
+	if (IS_ERR(skp))
+		return PTR_ERR(skp);
+
+	switch (token) {
+	case Opt_fsdefault:
+		if (opts->fsdefault)
+			goto out_opt_err;
+		opts->fsdefault = skp->smk_known;
+		break;
+	case Opt_fsfloor:
+		if (opts->fsfloor)
+			goto out_opt_err;
+		opts->fsfloor = skp->smk_known;
+		break;
+	case Opt_fshat:
+		if (opts->fshat)
+			goto out_opt_err;
+		opts->fshat = skp->smk_known;
+		break;
+	case Opt_fsroot:
+		if (opts->fsroot)
+			goto out_opt_err;
+		opts->fsroot = skp->smk_known;
+		break;
+	case Opt_fstransmute:
+		if (opts->fstransmute)
+			goto out_opt_err;
+		opts->fstransmute = skp->smk_known;
+		break;
+	}
+	return 0;
+
+out_opt_err:
+	pr_warn("Smack: duplicate mount options\n");
+	return -EINVAL;
+}
+
+/**
+ * smack_fs_context_submount - Initialise security data for a filesystem context
+ * @fc: The filesystem context.
+ * @reference: reference superblock
+ *
+ * Returns 0 on success or -ENOMEM on error.
+ */
+static int smack_fs_context_submount(struct fs_context *fc,
+				 struct super_block *reference)
+{
+	struct superblock_smack *sbsp;
+	struct smack_mnt_opts *ctx;
+	struct inode_smack *isp;
+
+	ctx = kzalloc_obj(*ctx);
+	if (!ctx)
+		return -ENOMEM;
+	fc->security = ctx;
+
+	sbsp = smack_superblock(reference);
+	isp = smack_inode(reference->s_root->d_inode);
+
+	if (sbsp->smk_default) {
+		ctx->fsdefault = kstrdup(sbsp->smk_default->smk_known, GFP_KERNEL);
+		if (!ctx->fsdefault)
+			return -ENOMEM;
+	}
+
+	if (sbsp->smk_floor) {
+		ctx->fsfloor = kstrdup(sbsp->smk_floor->smk_known, GFP_KERNEL);
+		if (!ctx->fsfloor)
+			return -ENOMEM;
+	}
+
+	if (sbsp->smk_hat) {
+		ctx->fshat = kstrdup(sbsp->smk_hat->smk_known, GFP_KERNEL);
+		if (!ctx->fshat)
+			return -ENOMEM;
+	}
+
+	if (isp->smk_flags & SMK_INODE_TRANSMUTE) {
+		if (sbsp->smk_root) {
+			ctx->fstransmute = kstrdup(sbsp->smk_root->smk_known, GFP_KERNEL);
+			if (!ctx->fstransmute)
+				return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ * smack_fs_context_dup - Duplicate the security data on fs_context duplication
+ * @fc: The new filesystem context.
+ * @src_fc: The source filesystem context being duplicated.
+ *
+ * Returns 0 on success or -ENOMEM on error.
+ */
+static int smack_fs_context_dup(struct fs_context *fc,
+				struct fs_context *src_fc)
+{
+	struct smack_mnt_opts *dst, *src = src_fc->security;
+
+	if (!src)
+		return 0;
+
+	fc->security = kzalloc_obj(struct smack_mnt_opts);
+	if (!fc->security)
+		return -ENOMEM;
+
+	dst = fc->security;
+	dst->fsdefault = src->fsdefault;
+	dst->fsfloor = src->fsfloor;
+	dst->fshat = src->fshat;
+	dst->fsroot = src->fsroot;
+	dst->fstransmute = src->fstransmute;
+
+	return 0;
+}
+
+static const struct fs_parameter_spec smack_fs_parameters[] = {
+	fsparam_string("smackfsdef",		Opt_fsdefault),
+	fsparam_string("smackfsdefault",	Opt_fsdefault),
+	fsparam_string("smackfsfloor",		Opt_fsfloor),
+	fsparam_string("smackfshat",		Opt_fshat),
+	fsparam_string("smackfsroot",		Opt_fsroot),
+	fsparam_string("smackfstransmute",	Opt_fstransmute),
+	{}
+};
+
+/**
+ * smack_fs_context_parse_param - Parse a single mount parameter
+ * @fc: The new filesystem context being constructed.
+ * @param: The parameter.
+ *
+ * Returns 0 on success, -ENOPARAM to pass the parameter on or anything else on
+ * error.
+ */
+static int smack_fs_context_parse_param(struct fs_context *fc,
+					struct fs_parameter *param)
+{
+	struct fs_parse_result result;
+	int opt, rc;
+
+	opt = fs_parse(fc, smack_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	rc = smack_add_opt(opt, param->string, &fc->security);
+	if (!rc)
+		param->string = NULL;
+	return rc;
+}
+
+static int smack_sb_eat_lsm_opts(char *options, void **mnt_opts)
+{
+	char *from = options, *to = options;
+	bool first = true;
+
+	while (1) {
+		char *next = strchr(from, ',');
+		int token, len, rc;
+		char *arg = NULL;
+
+		if (next)
+			len = next - from;
+		else
+			len = strlen(from);
+
+		token = match_opt_prefix(from, len, &arg);
+		if (token != Opt_error) {
+			arg = kmemdup_nul(arg, from + len - arg, GFP_KERNEL);
+			rc = smack_add_opt(token, arg, mnt_opts);
+			kfree(arg);
+			if (unlikely(rc)) {
+				if (*mnt_opts)
+					smack_free_mnt_opts(*mnt_opts);
+				*mnt_opts = NULL;
+				return rc;
+			}
+		} else {
+			if (!first) {	// copy with preceding comma
+				from--;
+				len++;
+			}
+			if (to != from)
+				memmove(to, from, len);
+			to += len;
+			first = false;
+		}
+		if (!from[len])
+			break;
+		from += len + 1;
+	}
+	*to = '\0';
+	return 0;
+}
+
+/**
+ * smack_set_mnt_opts - set Smack specific mount options
+ * @sb: the file system superblock
+ * @mnt_opts: Smack mount options
+ * @kern_flags: mount option from kernel space or user space
+ * @set_kern_flags: where to store converted mount opts
+ *
+ * Returns 0 on success, an error code on failure
+ *
+ * Allow filesystems with binary mount data to explicitly set Smack mount
+ * labels.
+ */
+static int smack_set_mnt_opts(struct super_block *sb,
+		void *mnt_opts,
+		unsigned long kern_flags,
+		unsigned long *set_kern_flags)
+{
+	struct dentry *root = sb->s_root;
+	struct inode *inode = d_backing_inode(root);
+	struct superblock_smack *sp = smack_superblock(sb);
+	struct inode_smack *isp;
+	struct smack_known *skp;
+	struct smack_mnt_opts *opts = mnt_opts;
+	bool transmute = false;
+
+	if (sp->smk_flags & SMK_SB_INITIALIZED)
+		return 0;
+
+	if (!smack_privileged(CAP_MAC_ADMIN)) {
+		/*
+		 * Unprivileged mounts don't get to specify Smack values.
+		 */
+		if (opts)
+			return -EPERM;
+		/*
+		 * Unprivileged mounts get root and default from the caller.
+		 */
+		skp = smk_of_current();
+		sp->smk_root = skp;
+		sp->smk_default = skp;
+		/*
+		 * For a handful of fs types with no user-controlled
+		 * backing store it's okay to trust security labels
+		 * in the filesystem. The rest are untrusted.
+		 */
+		if (sb->s_user_ns != &init_user_ns &&
+		    sb->s_magic != SYSFS_MAGIC && sb->s_magic != TMPFS_MAGIC &&
+		    sb->s_magic != RAMFS_MAGIC) {
+			transmute = true;
+			sp->smk_flags |= SMK_SB_UNTRUSTED;
+		}
+	}
+
+	sp->smk_flags |= SMK_SB_INITIALIZED;
+
+	if (opts) {
+		if (opts->fsdefault) {
+			skp = smk_import_entry(opts->fsdefault, 0);
+			if (IS_ERR(skp))
+				return PTR_ERR(skp);
+			sp->smk_default = skp;
+		}
+		if (opts->fsfloor) {
+			skp = smk_import_entry(opts->fsfloor, 0);
+			if (IS_ERR(skp))
+				return PTR_ERR(skp);
+			sp->smk_floor = skp;
+		}
+		if (opts->fshat) {
+			skp = smk_import_entry(opts->fshat, 0);
+			if (IS_ERR(skp))
+				return PTR_ERR(skp);
+			sp->smk_hat = skp;
+		}
+		if (opts->fsroot) {
+			skp = smk_import_entry(opts->fsroot, 0);
+			if (IS_ERR(skp))
+				return PTR_ERR(skp);
+			sp->smk_root = skp;
+		}
+		if (opts->fstransmute) {
+			skp = smk_import_entry(opts->fstransmute, 0);
+			if (IS_ERR(skp))
+				return PTR_ERR(skp);
+			sp->smk_root = skp;
+			transmute = true;
+		}
+	}
+
+	/*
+	 * Initialize the root inode.
+	 */
+	init_inode_smack(inode, sp->smk_root);
+
+	if (transmute) {
+		isp = smack_inode(inode);
+		isp->smk_flags |= SMK_INODE_TRANSMUTE;
+	}
+
+	return 0;
+}
+
+/**
+ * smack_sb_statfs - Smack check on statfs
+ * @dentry: identifies the file system in question
+ *
+ * Returns 0 if current can read the floor of the filesystem,
+ * and error code otherwise
+ */
+static int smack_sb_statfs(struct dentry *dentry)
+{
+	struct superblock_smack *sbp = smack_superblock(dentry->d_sb);
+	int rc;
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(sbp->smk_floor, MAY_READ, &ad);
+	rc = smk_bu_current("statfs", sbp->smk_floor, MAY_READ, rc);
+	return rc;
+}
+
+/*
+ * BPRM hooks
+ */
+
+/**
+ * smack_bprm_creds_for_exec - Update bprm->cred if needed for exec
+ * @bprm: the exec information
+ *
+ * Returns 0 if it gets a blob, -EPERM if exec forbidden and -ENOMEM otherwise
+ */
+static int smack_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	struct inode *inode = file_inode(bprm->file);
+	struct task_smack *bsp = smack_cred(bprm->cred);
+	struct inode_smack *isp;
+	struct superblock_smack *sbsp;
+	int rc;
+
+	isp = smack_inode(inode);
+	if (isp->smk_task == NULL || isp->smk_task == bsp->smk_task)
+		return 0;
+
+	sbsp = smack_superblock(inode->i_sb);
+	if ((sbsp->smk_flags & SMK_SB_UNTRUSTED) &&
+	    isp->smk_task != sbsp->smk_root)
+		return 0;
+
+	if (bprm->unsafe & LSM_UNSAFE_PTRACE) {
+		struct task_struct *tracer;
+		rc = 0;
+
+		rcu_read_lock();
+		tracer = ptrace_parent(current);
+		if (likely(tracer != NULL))
+			rc = smk_ptrace_rule_check(tracer,
+						   isp->smk_task,
+						   PTRACE_MODE_ATTACH,
+						   __func__);
+		rcu_read_unlock();
+
+		if (rc != 0)
+			return rc;
+	}
+	if (bprm->unsafe & ~LSM_UNSAFE_PTRACE)
+		return -EPERM;
+
+	bsp->smk_task = isp->smk_task;
+	bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+	/* Decide if this is a secure exec. */
+	if (bsp->smk_task != bsp->smk_forked)
+		bprm->secureexec = 1;
+
+	return 0;
+}
+
+/*
+ * Inode hooks
+ */
+
+/**
+ * smack_inode_alloc_security - allocate an inode blob
+ * @inode: the inode in need of a blob
+ *
+ * Returns 0
+ */
+static int smack_inode_alloc_security(struct inode *inode)
+{
+	struct smack_known *skp = smk_of_current();
+
+	init_inode_smack(inode, skp);
+	return 0;
+}
+
+/**
+ * smk_rule_transmutes - does access rule for (subject,object) contain 't'?
+ * @subject: a pointer to the subject's Smack label entry
+ * @object: a pointer to the object's Smack label entry
+ */
+static bool
+smk_rule_transmutes(struct smack_known *subject,
+	      const struct smack_known *object)
+{
+	int may;
+
+	rcu_read_lock();
+	may = smk_access_entry(subject->smk_known, object->smk_known,
+			       &subject->smk_rules);
+	rcu_read_unlock();
+	return (may > 0) && (may & MAY_TRANSMUTE);
+}
+
+static int
+xattr_dupval(struct xattr *xattrs, int *xattr_count,
+	     const char *name, const void *value, unsigned int vallen)
+{
+	struct xattr * const xattr = lsm_get_xattr_slot(xattrs, xattr_count);
+
+	if (!xattr)
+		return 0;
+
+	xattr->value = kmemdup(value, vallen, GFP_NOFS);
+	if (!xattr->value)
+		return -ENOMEM;
+
+	xattr->value_len = vallen;
+	xattr->name = name;
+	return 0;
+}
+
+/**
+ * smack_inode_init_security - copy out the smack from an inode
+ * @inode: the newly created inode
+ * @dir: containing directory object
+ * @qstr: unused
+ * @xattrs: where to put the attributes
+ * @xattr_count: current number of LSM-provided xattrs (updated)
+ *
+ * Returns 0 if it all works out, -ENOMEM if there's no memory
+ */
+static int smack_inode_init_security(struct inode *inode, struct inode *dir,
+				     const struct qstr *qstr,
+				     struct xattr *xattrs, int *xattr_count)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct inode_smack * const issp = smack_inode(inode);
+	struct smack_known *dsp = smk_of_inode(dir);
+	int rc = 0;
+	int transflag = 0;
+	bool trans_cred;
+	bool trans_rule;
+
+	/*
+	 * UNIX domain sockets use lower level socket data. Let
+	 * UDS inode have fixed * label to keep smack_inode_permission() calm
+	 * when called from unix_find_bsd()
+	 */
+	if (S_ISSOCK(inode->i_mode)) {
+		/* forced label, no need to save to xattrs */
+		issp->smk_inode = &smack_known_star;
+		goto instant_inode;
+	}
+	/*
+	 * If equal, transmuting already occurred in
+	 * smack_dentry_create_files_as(). No need to check again.
+	 */
+	trans_cred = (tsp->smk_task == tsp->smk_transmuted);
+	if (!trans_cred)
+		trans_rule = smk_rule_transmutes(smk_of_task(tsp), dsp);
+
+	/*
+	 * In addition to having smk_task equal to smk_transmuted,
+	 * if the access rule allows transmutation and the directory
+	 * requests transmutation then by all means transmute.
+	 * Mark the inode as changed.
+	 */
+	if (trans_cred || (trans_rule && smk_inode_transmutable(dir))) {
+		/*
+		 * The caller of smack_dentry_create_files_as()
+		 * should have overridden the current cred, so the
+		 * inode label was already set correctly in
+		 * smack_inode_alloc_security().
+		 */
+		if (!trans_cred)
+			issp->smk_inode = dsp;
+
+		if (S_ISDIR(inode->i_mode)) {
+			transflag = SMK_INODE_TRANSMUTE;
+
+			if (xattr_dupval(xattrs, xattr_count,
+				XATTR_SMACK_TRANSMUTE,
+				TRANS_TRUE,
+				TRANS_TRUE_SIZE
+			))
+				rc = -ENOMEM;
+		}
+	}
+
+	if (rc == 0)
+		if (xattr_dupval(xattrs, xattr_count,
+			    XATTR_SMACK_SUFFIX,
+			    issp->smk_inode->smk_known,
+		     strlen(issp->smk_inode->smk_known)
+		))
+			rc = -ENOMEM;
+instant_inode:
+	issp->smk_flags |= (SMK_INODE_INSTANT | transflag);
+	return rc;
+}
+
+/**
+ * smack_inode_link - Smack check on link
+ * @old_dentry: the existing object
+ * @dir: unused
+ * @new_dentry: the new object
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_link(struct dentry *old_dentry, struct inode *dir,
+			    struct dentry *new_dentry)
+{
+	struct smack_known *isp;
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
+
+	isp = smk_of_inode(d_backing_inode(old_dentry));
+	rc = smk_curacc(isp, MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(old_dentry), MAY_WRITE, rc);
+
+	if (rc == 0 && d_is_positive(new_dentry)) {
+		isp = smk_of_inode(d_backing_inode(new_dentry));
+		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+		rc = smk_curacc(isp, MAY_WRITE, &ad);
+		rc = smk_bu_inode(d_backing_inode(new_dentry), MAY_WRITE, rc);
+	}
+
+	return rc;
+}
+
+/**
+ * smack_inode_unlink - Smack check on inode deletion
+ * @dir: containing directory object
+ * @dentry: file to unlink
+ *
+ * Returns 0 if current can write the containing directory
+ * and the object, error code otherwise
+ */
+static int smack_inode_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *ip = d_backing_inode(dentry);
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	/*
+	 * You need write access to the thing you're unlinking
+	 */
+	rc = smk_curacc(smk_of_inode(ip), MAY_WRITE, &ad);
+	rc = smk_bu_inode(ip, MAY_WRITE, rc);
+	if (rc == 0) {
+		/*
+		 * You also need write access to the containing directory
+		 */
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
+		smk_ad_setfield_u_fs_inode(&ad, dir);
+		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+		rc = smk_bu_inode(dir, MAY_WRITE, rc);
+	}
+	return rc;
+}
+
+/**
+ * smack_inode_rmdir - Smack check on directory deletion
+ * @dir: containing directory object
+ * @dentry: directory to unlink
+ *
+ * Returns 0 if current can write the containing directory
+ * and the directory, error code otherwise
+ */
+static int smack_inode_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	/*
+	 * You need write access to the thing you're removing
+	 */
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	if (rc == 0) {
+		/*
+		 * You also need write access to the containing directory
+		 */
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
+		smk_ad_setfield_u_fs_inode(&ad, dir);
+		rc = smk_curacc(smk_of_inode(dir), MAY_WRITE, &ad);
+		rc = smk_bu_inode(dir, MAY_WRITE, rc);
+	}
+
+	return rc;
+}
+
+/**
+ * smack_inode_rename - Smack check on rename
+ * @old_inode: unused
+ * @old_dentry: the old object
+ * @new_inode: unused
+ * @new_dentry: the new object
+ *
+ * Read and write access is required on both the old and
+ * new directories.
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_rename(struct inode *old_inode,
+			      struct dentry *old_dentry,
+			      struct inode *new_inode,
+			      struct dentry *new_dentry)
+{
+	int rc;
+	struct smack_known *isp;
+	struct smk_audit_info ad;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, old_dentry);
+
+	isp = smk_of_inode(d_backing_inode(old_dentry));
+	rc = smk_curacc(isp, MAY_READWRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(old_dentry), MAY_READWRITE, rc);
+
+	if (rc == 0 && d_is_positive(new_dentry)) {
+		isp = smk_of_inode(d_backing_inode(new_dentry));
+		smk_ad_setfield_u_fs_path_dentry(&ad, new_dentry);
+		rc = smk_curacc(isp, MAY_READWRITE, &ad);
+		rc = smk_bu_inode(d_backing_inode(new_dentry), MAY_READWRITE, rc);
+	}
+	return rc;
+}
+
+/**
+ * smack_inode_permission - Smack version of permission()
+ * @inode: the inode in question
+ * @mask: the access requested
+ *
+ * This is the important Smack hook.
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_permission(struct inode *inode, int mask)
+{
+	struct superblock_smack *sbsp = smack_superblock(inode->i_sb);
+	struct smk_audit_info ad;
+	int no_block = mask & MAY_NOT_BLOCK;
+	int rc;
+
+	mask &= (MAY_READ|MAY_WRITE|MAY_EXEC|MAY_APPEND);
+	/*
+	 * No permission to check. Existence test. Yup, it's there.
+	 */
+	if (mask == 0)
+		return 0;
+
+	if (sbsp->smk_flags & SMK_SB_UNTRUSTED) {
+		if (smk_of_inode(inode) != sbsp->smk_root)
+			return -EACCES;
+	}
+
+	/* May be droppable after audit */
+	if (no_block)
+		return -ECHILD;
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_INODE);
+	smk_ad_setfield_u_fs_inode(&ad, inode);
+	rc = smk_curacc(smk_of_inode(inode), mask, &ad);
+	rc = smk_bu_inode(inode, mask, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_setattr - Smack check for setting attributes
+ * @idmap: idmap of the mount
+ * @dentry: the object
+ * @iattr: for the force flag
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+			       struct iattr *iattr)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	/*
+	 * Need to allow for clearing the setuid bit.
+	 */
+	if (iattr->ia_valid & ATTR_FORCE)
+		return 0;
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_getattr - Smack check for getting attributes
+ * @path: path to extract the info from
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_getattr(const struct path *path)
+{
+	struct smk_audit_info ad;
+	struct inode *inode = d_backing_inode(path->dentry);
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, *path);
+	rc = smk_curacc(smk_of_inode(inode), MAY_READ, &ad);
+	rc = smk_bu_inode(inode, MAY_READ, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_xattr_skipcap - Skip the xattr capability checks?
+ * @name: name of the xattr
+ *
+ * Returns 1 to indicate that Smack "owns" the access control rights to xattrs
+ * named @name; the LSM layer should avoid enforcing any traditional
+ * capability based access controls on this xattr.  Returns 0 to indicate that
+ * Smack does not "own" the access control rights to xattrs named @name and is
+ * deferring to the LSM layer for further access controls, including capability
+ * based controls.
+ */
+static int smack_inode_xattr_skipcap(const char *name)
+{
+	if (strncmp(name, XATTR_SMACK_SUFFIX, strlen(XATTR_SMACK_SUFFIX)) == 0)
+		return 0;
+
+	if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKMMAP) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * smack_inode_setxattr - Smack check for setting xattrs
+ * @idmap: idmap of the mount
+ * @dentry: the object
+ * @name: name of the attribute
+ * @value: value of the attribute
+ * @size: size of the value
+ * @flags: unused
+ *
+ * This protects the Smack attribute explicitly.
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_setxattr(struct mnt_idmap *idmap,
+				struct dentry *dentry, const char *name,
+				const void *value, size_t size, int flags)
+{
+	struct smk_audit_info ad;
+	struct smack_known *skp;
+	int check_priv = 0;
+	int check_import = 0;
+	int check_star = 0;
+	int rc = 0;
+	umode_t const i_mode = d_backing_inode(dentry)->i_mode;
+
+	/*
+	 * Check label validity here so import won't fail in post_setxattr
+	 */
+	if (strcmp(name, XATTR_NAME_SMACK) == 0) {
+		/*
+		 * UDS inode has fixed label
+		 */
+		if (S_ISSOCK(i_mode)) {
+			rc = -EINVAL;
+		} else {
+			check_priv = 1;
+			check_import = 1;
+		}
+	} else if (strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
+		   strcmp(name, XATTR_NAME_SMACKIPOUT) == 0) {
+		check_priv = 1;
+		check_import = 1;
+	} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
+		   strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+		check_priv = 1;
+		check_import = 1;
+		check_star = 1;
+	} else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) {
+		check_priv = 1;
+		if (!S_ISDIR(i_mode) ||
+		    size != TRANS_TRUE_SIZE ||
+		    strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0)
+			rc = -EINVAL;
+	}
+
+	if (check_priv && !smack_privileged(CAP_MAC_ADMIN))
+		rc = -EPERM;
+
+	if (rc == 0 && check_import) {
+		skp = size ? smk_import_entry(value, size) : NULL;
+		if (IS_ERR(skp))
+			rc = PTR_ERR(skp);
+		else if (skp == NULL || (check_star &&
+		    (skp == &smack_known_star || skp == &smack_known_web)))
+			rc = -EINVAL;
+	}
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	if (rc == 0) {
+		rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+		rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	}
+
+	return rc;
+}
+
+/**
+ * smack_inode_post_setxattr - Apply the Smack update approved above
+ * @dentry: object
+ * @name: attribute name
+ * @value: attribute value
+ * @size: attribute size
+ * @flags: unused
+ *
+ * Set the pointer in the inode blob to the entry found
+ * in the master label list.
+ */
+static void smack_inode_post_setxattr(struct dentry *dentry, const char *name,
+				      const void *value, size_t size, int flags)
+{
+	struct smack_known *skp;
+	struct inode_smack *isp = smack_inode(d_backing_inode(dentry));
+
+	if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0) {
+		isp->smk_flags |= SMK_INODE_TRANSMUTE;
+		return;
+	}
+
+	if (strcmp(name, XATTR_NAME_SMACK) == 0) {
+		skp = smk_import_entry(value, size);
+		if (!IS_ERR(skp))
+			isp->smk_inode = skp;
+	} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0) {
+		skp = smk_import_entry(value, size);
+		if (!IS_ERR(skp))
+			isp->smk_task = skp;
+	} else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+		skp = smk_import_entry(value, size);
+		if (!IS_ERR(skp))
+			isp->smk_mmap = skp;
+	}
+
+	return;
+}
+
+/**
+ * smack_inode_getxattr - Smack check on getxattr
+ * @dentry: the object
+ * @name: unused
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_getxattr(struct dentry *dentry, const char *name)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_READ, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_READ, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_removexattr - Smack check on removexattr
+ * @idmap: idmap of the mount
+ * @dentry: the object
+ * @name: name of the attribute
+ *
+ * Removing the Smack attribute requires CAP_MAC_ADMIN
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_removexattr(struct mnt_idmap *idmap,
+				   struct dentry *dentry, const char *name)
+{
+	struct inode_smack *isp;
+	struct smk_audit_info ad;
+	int rc = 0;
+
+	if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0 ||
+	    strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+		if (!smack_privileged(CAP_MAC_ADMIN))
+			rc = -EPERM;
+	}
+
+	if (rc != 0)
+		return rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	if (rc != 0)
+		return rc;
+
+	isp = smack_inode(d_backing_inode(dentry));
+	/*
+	 * Don't do anything special for these.
+	 *	XATTR_NAME_SMACKIPIN
+	 *	XATTR_NAME_SMACKIPOUT
+	 *	XATTR_NAME_SMACK if S_ISSOCK (UDS inode has fixed label)
+	 */
+	if (strcmp(name, XATTR_NAME_SMACK) == 0) {
+		if (!S_ISSOCK(d_backing_inode(dentry)->i_mode)) {
+			struct super_block *sbp = dentry->d_sb;
+			struct superblock_smack *sbsp = smack_superblock(sbp);
+
+			isp->smk_inode = sbsp->smk_default;
+		}
+	} else if (strcmp(name, XATTR_NAME_SMACKEXEC) == 0)
+		isp->smk_task = NULL;
+	else if (strcmp(name, XATTR_NAME_SMACKMMAP) == 0)
+		isp->smk_mmap = NULL;
+	else if (strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0)
+		isp->smk_flags &= ~SMK_INODE_TRANSMUTE;
+
+	return 0;
+}
+
+/**
+ * smack_inode_set_acl - Smack check for setting posix acls
+ * @idmap: idmap of the mnt this request came from
+ * @dentry: the object
+ * @acl_name: name of the posix acl
+ * @kacl: the posix acls
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_set_acl(struct mnt_idmap *idmap,
+			       struct dentry *dentry, const char *acl_name,
+			       struct posix_acl *kacl)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_get_acl - Smack check for getting posix acls
+ * @idmap: idmap of the mnt this request came from
+ * @dentry: the object
+ * @acl_name: name of the posix acl
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_get_acl(struct mnt_idmap *idmap,
+			       struct dentry *dentry, const char *acl_name)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_READ, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_READ, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_remove_acl - Smack check for getting posix acls
+ * @idmap: idmap of the mnt this request came from
+ * @dentry: the object
+ * @acl_name: name of the posix acl
+ *
+ * Returns 0 if access is permitted, an error code otherwise
+ */
+static int smack_inode_remove_acl(struct mnt_idmap *idmap,
+				  struct dentry *dentry, const char *acl_name)
+{
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_DENTRY);
+	smk_ad_setfield_u_fs_path_dentry(&ad, dentry);
+
+	rc = smk_curacc(smk_of_inode(d_backing_inode(dentry)), MAY_WRITE, &ad);
+	rc = smk_bu_inode(d_backing_inode(dentry), MAY_WRITE, rc);
+	return rc;
+}
+
+/**
+ * smack_inode_getsecurity - get smack xattrs
+ * @idmap: idmap of the mount
+ * @inode: the object
+ * @name: attribute name
+ * @buffer: where to put the result
+ * @alloc: duplicate memory
+ *
+ * Returns the size of the attribute or an error code
+ */
+static int smack_inode_getsecurity(struct mnt_idmap *idmap,
+				   struct inode *inode, const char *name,
+				   void **buffer, bool alloc)
+{
+	struct socket_smack *ssp;
+	struct socket *sock;
+	struct super_block *sbp;
+	struct inode *ip = inode;
+	struct smack_known *isp;
+	struct inode_smack *ispp;
+	size_t label_len;
+	char *label = NULL;
+
+	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
+		isp = smk_of_inode(inode);
+	} else if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) {
+		ispp = smack_inode(inode);
+		if (ispp->smk_flags & SMK_INODE_TRANSMUTE)
+			label = TRANS_TRUE;
+		else
+			label = "";
+	} else {
+		/*
+		 * The rest of the Smack xattrs are only on sockets.
+		 */
+		sbp = ip->i_sb;
+		if (sbp->s_magic != SOCKFS_MAGIC)
+			return -EOPNOTSUPP;
+
+		sock = SOCKET_I(ip);
+		if (sock == NULL || sock->sk == NULL)
+			return -EOPNOTSUPP;
+
+		ssp = smack_sock(sock->sk);
+
+		if (strcmp(name, XATTR_SMACK_IPIN) == 0)
+			isp = ssp->smk_in;
+		else if (strcmp(name, XATTR_SMACK_IPOUT) == 0)
+			isp = ssp->smk_out;
+		else
+			return -EOPNOTSUPP;
+	}
+
+	if (!label)
+		label = isp->smk_known;
+
+	label_len = strlen(label);
+
+	if (alloc) {
+		*buffer = kstrdup(label, GFP_KERNEL);
+		if (*buffer == NULL)
+			return -ENOMEM;
+	}
+
+	return label_len;
+}
+
+
+/**
+ * smack_inode_listsecurity - list the Smack attributes
+ * @inode: the object
+ * @buffer: where they go
+ * @remaining_size: size of buffer
+ */
+static int smack_inode_listsecurity(struct inode *inode, char **buffer,
+				    ssize_t *remaining_size)
+{
+	return xattr_list_one(buffer, remaining_size, XATTR_NAME_SMACK);
+}
+
+/**
+ * smack_inode_getlsmprop - Extract inode's security id
+ * @inode: inode to extract the info from
+ * @prop: where result will be saved
+ */
+static void smack_inode_getlsmprop(struct inode *inode, struct lsm_prop *prop)
+{
+	prop->smack.skp = smk_of_inode(inode);
+}
+
+/*
+ * File Hooks
+ */
+
+/*
+ * There is no smack_file_permission hook
+ *
+ * Should access checks be done on each read or write?
+ * UNICOS and SELinux say yes.
+ * Trusted Solaris, Trusted Irix, and just about everyone else says no.
+ *
+ * I'll say no for now. Smack does not do the frequent
+ * label changing that SELinux does.
+ */
+
+/**
+ * smack_file_alloc_security - assign a file security blob
+ * @file: the object
+ *
+ * The security blob for a file is a pointer to the master
+ * label list, so no allocation is done.
+ *
+ * f_security is the owner security information. It
+ * isn't used on file access checks, it's for send_sigio.
+ *
+ * Returns 0
+ */
+static int smack_file_alloc_security(struct file *file)
+{
+	struct smack_known **blob = smack_file(file);
+
+	*blob = smk_of_current();
+	return 0;
+}
+
+/**
+ * smack_file_ioctl - Smack check on ioctls
+ * @file: the object
+ * @cmd: what to do
+ * @arg: unused
+ *
+ * Relies heavily on the correct use of the ioctl command conventions.
+ *
+ * Returns 0 if allowed, error code otherwise
+ */
+static int smack_file_ioctl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
+{
+	int rc = 0;
+	struct smk_audit_info ad;
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+
+	if (_IOC_DIR(cmd) & _IOC_WRITE) {
+		rc = smk_curacc(smk_of_inode(inode), MAY_WRITE, &ad);
+		rc = smk_bu_file(file, MAY_WRITE, rc);
+	}
+
+	if (rc == 0 && (_IOC_DIR(cmd) & _IOC_READ)) {
+		rc = smk_curacc(smk_of_inode(inode), MAY_READ, &ad);
+		rc = smk_bu_file(file, MAY_READ, rc);
+	}
+
+	return rc;
+}
+
+/**
+ * smack_file_lock - Smack check on file locking
+ * @file: the object
+ * @cmd: unused
+ *
+ * Returns 0 if current has lock access, error code otherwise
+ */
+static int smack_file_lock(struct file *file, unsigned int cmd)
+{
+	struct smk_audit_info ad;
+	int rc;
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+	rc = smk_curacc(smk_of_inode(inode), MAY_LOCK, &ad);
+	rc = smk_bu_file(file, MAY_LOCK, rc);
+	return rc;
+}
+
+/**
+ * smack_file_fcntl - Smack check on fcntl
+ * @file: the object
+ * @cmd: what action to check
+ * @arg: unused
+ *
+ * Generally these operations are harmless.
+ * File locking operations present an obvious mechanism
+ * for passing information, so they require write access.
+ *
+ * Returns 0 if current has access, error code otherwise
+ */
+static int smack_file_fcntl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
+{
+	struct smk_audit_info ad;
+	int rc = 0;
+	struct inode *inode = file_inode(file);
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	switch (cmd) {
+	case F_GETLK:
+		break;
+	case F_SETLK:
+	case F_SETLKW:
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+		smk_ad_setfield_u_fs_path(&ad, file->f_path);
+		rc = smk_curacc(smk_of_inode(inode), MAY_LOCK, &ad);
+		rc = smk_bu_file(file, MAY_LOCK, rc);
+		break;
+	case F_SETOWN:
+	case F_SETSIG:
+		smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+		smk_ad_setfield_u_fs_path(&ad, file->f_path);
+		rc = smk_curacc(smk_of_inode(inode), MAY_WRITE, &ad);
+		rc = smk_bu_file(file, MAY_WRITE, rc);
+		break;
+	default:
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * smack_mmap_file - Check permissions for a mmap operation.
+ * @file: contains the file structure for file to map (may be NULL).
+ * @reqprot: contains the protection requested by the application.
+ * @prot: contains the protection that will be applied by the kernel.
+ * @flags: contains the operational flags.
+ *
+ * The @file may be NULL, e.g. if mapping anonymous memory.
+ *
+ * Return 0 if permission is granted.
+ */
+static int smack_mmap_file(struct file *file,
+			   unsigned long reqprot, unsigned long prot,
+			   unsigned long flags)
+{
+	struct smack_known *skp;
+	struct smack_known *mkp;
+	struct smack_rule *srp;
+	struct task_smack *tsp;
+	struct smack_known *okp;
+	struct inode_smack *isp;
+	struct superblock_smack *sbsp;
+	int may;
+	int mmay;
+	int tmay;
+	int rc;
+
+	if (file == NULL)
+		return 0;
+
+	if (unlikely(IS_PRIVATE(file_inode(file))))
+		return 0;
+
+	isp = smack_inode(file_inode(file));
+	if (isp->smk_mmap == NULL)
+		return 0;
+	sbsp = smack_superblock(file_inode(file)->i_sb);
+	if (sbsp->smk_flags & SMK_SB_UNTRUSTED &&
+	    isp->smk_mmap != sbsp->smk_root)
+		return -EACCES;
+	mkp = isp->smk_mmap;
+
+	tsp = smack_cred(current_cred());
+	skp = smk_of_current();
+	rc = 0;
+
+	rcu_read_lock();
+	/*
+	 * For each Smack rule associated with the subject
+	 * label verify that the SMACK64MMAP also has access
+	 * to that rule's object label.
+	 */
+	list_for_each_entry_rcu(srp, &skp->smk_rules, list) {
+		okp = srp->smk_object;
+		/*
+		 * Matching labels always allows access.
+		 */
+		if (mkp->smk_known == okp->smk_known)
+			continue;
+		/*
+		 * If there is a matching local rule take
+		 * that into account as well.
+		 */
+		may = smk_access_entry(srp->smk_subject->smk_known,
+				       okp->smk_known,
+				       &tsp->smk_rules);
+		if (may == -ENOENT)
+			may = srp->smk_access;
+		else
+			may &= srp->smk_access;
+		/*
+		 * If may is zero the SMACK64MMAP subject can't
+		 * possibly have less access.
+		 */
+		if (may == 0)
+			continue;
+
+		/*
+		 * Fetch the global list entry.
+		 * If there isn't one a SMACK64MMAP subject
+		 * can't have as much access as current.
+		 */
+		mmay = smk_access_entry(mkp->smk_known, okp->smk_known,
+					&mkp->smk_rules);
+		if (mmay == -ENOENT) {
+			rc = -EACCES;
+			break;
+		}
+		/*
+		 * If there is a local entry it modifies the
+		 * potential access, too.
+		 */
+		tmay = smk_access_entry(mkp->smk_known, okp->smk_known,
+					&tsp->smk_rules);
+		if (tmay != -ENOENT)
+			mmay &= tmay;
+
+		/*
+		 * If there is any access available to current that is
+		 * not available to a SMACK64MMAP subject
+		 * deny access.
+		 */
+		if ((may | mmay) != mmay) {
+			rc = -EACCES;
+			break;
+		}
+	}
+
+	rcu_read_unlock();
+
+	return rc;
+}
+
+/**
+ * smack_file_set_fowner - set the file security blob value
+ * @file: object in question
+ *
+ */
+static void smack_file_set_fowner(struct file *file)
+{
+	struct smack_known **blob = smack_file(file);
+
+	*blob = smk_of_current();
+}
+
+/**
+ * smack_file_send_sigiotask - Smack on sigio
+ * @tsk: The target task
+ * @fown: the object the signal come from
+ * @signum: unused
+ *
+ * Allow a privileged task to get signals even if it shouldn't
+ *
+ * Returns 0 if a subject with the object's smack could
+ * write to the task, an error code otherwise.
+ */
+static int smack_file_send_sigiotask(struct task_struct *tsk,
+				     struct fown_struct *fown, int signum)
+{
+	struct smack_known **blob;
+	struct smack_known *skp;
+	struct smack_known *tkp = smk_of_task_struct_obj(tsk);
+	const struct cred *tcred;
+	struct file *file;
+	int rc;
+	struct smk_audit_info ad;
+
+	/*
+	 * struct fown_struct is never outside the context of a struct file
+	 */
+	file = fown->file;
+
+	/* we don't log here as rc can be overridden */
+	blob = smack_file(file);
+	skp = *blob;
+	rc = smk_access(skp, tkp, MAY_DELIVER, NULL);
+	rc = smk_bu_note("sigiotask", skp, tkp, MAY_DELIVER, rc);
+
+	rcu_read_lock();
+	tcred = __task_cred(tsk);
+	if (rc != 0 && smack_privileged_cred(CAP_MAC_OVERRIDE, tcred))
+		rc = 0;
+	rcu_read_unlock();
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, tsk);
+	smack_log(skp->smk_known, tkp->smk_known, MAY_DELIVER, rc, &ad);
+	return rc;
+}
+
+/**
+ * smack_file_receive - Smack file receive check
+ * @file: the object
+ *
+ * Returns 0 if current has access, error code otherwise
+ */
+static int smack_file_receive(struct file *file)
+{
+	int rc;
+	int may = 0;
+	struct smk_audit_info ad;
+	struct inode *inode = file_inode(file);
+	struct socket *sock;
+	struct task_smack *tsp;
+	struct socket_smack *ssp;
+
+	if (unlikely(IS_PRIVATE(inode)))
+		return 0;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+
+	if (inode->i_sb->s_magic == SOCKFS_MAGIC) {
+		sock = SOCKET_I(inode);
+		ssp = smack_sock(sock->sk);
+		tsp = smack_cred(current_cred());
+		/*
+		 * If the receiving process can't write to the
+		 * passed socket or if the passed socket can't
+		 * write to the receiving process don't accept
+		 * the passed socket.
+		 */
+		rc = smk_access(tsp->smk_task, ssp->smk_out, MAY_WRITE, &ad);
+		rc = smk_bu_file(file, may, rc);
+		if (rc < 0)
+			return rc;
+		rc = smk_access(ssp->smk_in, tsp->smk_task, MAY_WRITE, &ad);
+		rc = smk_bu_file(file, may, rc);
+		return rc;
+	}
+	/*
+	 * This code relies on bitmasks.
+	 */
+	if (file->f_mode & FMODE_READ)
+		may = MAY_READ;
+	if (file->f_mode & FMODE_WRITE)
+		may |= MAY_WRITE;
+
+	rc = smk_curacc(smk_of_inode(inode), may, &ad);
+	rc = smk_bu_file(file, may, rc);
+	return rc;
+}
+
+/**
+ * smack_file_open - Smack dentry open processing
+ * @file: the object
+ *
+ * Set the security blob in the file structure.
+ * Allow the open only if the task has read access. There are
+ * many read operations (e.g. fstat) that you can do with an
+ * fd even if you have the file open write-only.
+ *
+ * Returns 0 if current has access, error code otherwise
+ */
+static int smack_file_open(struct file *file)
+{
+	struct task_smack *tsp = smack_cred(file->f_cred);
+	struct inode *inode = file_inode(file);
+	struct smk_audit_info ad;
+	int rc;
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
+
+	return rc;
+}
+
+/*
+ * Task hooks
+ */
+
+/**
+ * smack_cred_alloc_blank - "allocate" blank task-level security credentials
+ * @cred: the new credentials
+ * @gfp: the atomicity of any memory allocations
+ *
+ * Prepare a blank set of credentials for modification.  This must allocate all
+ * the memory the LSM module might require such that cred_transfer() can
+ * complete without error.
+ */
+static int smack_cred_alloc_blank(struct cred *cred, gfp_t gfp)
+{
+	init_task_smack(smack_cred(cred), NULL, NULL);
+	return 0;
+}
+
+
+/**
+ * smack_cred_free - "free" task-level security credentials
+ * @cred: the credentials in question
+ *
+ */
+static void smack_cred_free(struct cred *cred)
+{
+	struct task_smack *tsp = smack_cred(cred);
+	struct smack_rule *rp;
+	struct list_head *l;
+	struct list_head *n;
+
+	smk_destroy_label_list(&tsp->smk_relabel);
+
+	list_for_each_safe(l, n, &tsp->smk_rules) {
+		rp = list_entry(l, struct smack_rule, list);
+		list_del(&rp->list);
+		kmem_cache_free(smack_rule_cache, rp);
+	}
+}
+
+/**
+ * smack_cred_prepare - prepare new set of credentials for modification
+ * @new: the new credentials
+ * @old: the original credentials
+ * @gfp: the atomicity of any memory allocations
+ *
+ * Prepare a new set of credentials for modification.
+ */
+static int smack_cred_prepare(struct cred *new, const struct cred *old,
+			      gfp_t gfp)
+{
+	struct task_smack *old_tsp = smack_cred(old);
+	struct task_smack *new_tsp = smack_cred(new);
+	int rc;
+
+	init_task_smack(new_tsp, old_tsp->smk_task, old_tsp->smk_task);
+
+	rc = smk_copy_rules(&new_tsp->smk_rules, &old_tsp->smk_rules, gfp);
+	if (rc != 0)
+		return rc;
+
+	rc = smk_copy_relabel(&new_tsp->smk_relabel, &old_tsp->smk_relabel,
+				gfp);
+	return rc;
+}
+
+/**
+ * smack_cred_transfer - Transfer the old credentials to the new credentials
+ * @new: the new credentials
+ * @old: the original credentials
+ *
+ * Fill in a set of blank credentials from another set of credentials.
+ */
+static void smack_cred_transfer(struct cred *new, const struct cred *old)
+{
+	struct task_smack *old_tsp = smack_cred(old);
+	struct task_smack *new_tsp = smack_cred(new);
+
+	init_task_smack(new_tsp, old_tsp->smk_task, old_tsp->smk_task);
+}
+
+/**
+ * smack_cred_getsecid - get the secid corresponding to a creds structure
+ * @cred: the object creds
+ * @secid: where to put the result
+ *
+ * Sets the secid to contain a u32 version of the smack label.
+ */
+static void smack_cred_getsecid(const struct cred *cred, u32 *secid)
+{
+	struct smack_known *skp;
+
+	rcu_read_lock();
+	skp = smk_of_task(smack_cred(cred));
+	*secid = skp->smk_secid;
+	rcu_read_unlock();
+}
+
+/**
+ * smack_cred_getlsmprop - get the Smack label for a creds structure
+ * @cred: the object creds
+ * @prop: where to put the data
+ *
+ * Sets the Smack part of the ref
+ */
+static void smack_cred_getlsmprop(const struct cred *cred,
+				  struct lsm_prop *prop)
+{
+	rcu_read_lock();
+	prop->smack.skp = smk_of_task(smack_cred(cred));
+	rcu_read_unlock();
+}
+
+/**
+ * smack_kernel_act_as - Set the subjective context in a set of credentials
+ * @new: points to the set of credentials to be modified.
+ * @secid: specifies the security ID to be set
+ *
+ * Set the security data for a kernel service.
+ */
+static int smack_kernel_act_as(struct cred *new, u32 secid)
+{
+	struct task_smack *new_tsp = smack_cred(new);
+
+	new_tsp->smk_task = smack_from_secid(secid);
+	return 0;
+}
+
+/**
+ * smack_kernel_create_files_as - Set the file creation label in a set of creds
+ * @new: points to the set of credentials to be modified
+ * @inode: points to the inode to use as a reference
+ *
+ * Set the file creation context in a set of credentials to the same
+ * as the objective context of the specified inode
+ */
+static int smack_kernel_create_files_as(struct cred *new,
+					struct inode *inode)
+{
+	struct inode_smack *isp = smack_inode(inode);
+	struct task_smack *tsp = smack_cred(new);
+
+	tsp->smk_forked = isp->smk_inode;
+	tsp->smk_task = tsp->smk_forked;
+	return 0;
+}
+
+/**
+ * smk_curacc_on_task - helper to log task related access
+ * @p: the task object
+ * @access: the access requested
+ * @caller: name of the calling function for audit
+ *
+ * Return 0 if access is permitted
+ */
+static int smk_curacc_on_task(struct task_struct *p, int access,
+				const char *caller)
+{
+	struct smk_audit_info ad;
+	struct smack_known *skp = smk_of_task_struct_obj(p);
+	int rc;
+
+	smk_ad_init(&ad, caller, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, p);
+	rc = smk_curacc(skp, access, &ad);
+	rc = smk_bu_task(p, access, rc);
+	return rc;
+}
+
+/**
+ * smack_task_setpgid - Smack check on setting pgid
+ * @p: the task object
+ * @pgid: unused
+ *
+ * Return 0 if write access is permitted
+ */
+static int smack_task_setpgid(struct task_struct *p, pid_t pgid)
+{
+	return smk_curacc_on_task(p, MAY_WRITE, __func__);
+}
+
+/**
+ * smack_task_getpgid - Smack access check for getpgid
+ * @p: the object task
+ *
+ * Returns 0 if current can read the object task, error code otherwise
+ */
+static int smack_task_getpgid(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_READ, __func__);
+}
+
+/**
+ * smack_task_getsid - Smack access check for getsid
+ * @p: the object task
+ *
+ * Returns 0 if current can read the object task, error code otherwise
+ */
+static int smack_task_getsid(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_READ, __func__);
+}
+
+/**
+ * smack_current_getlsmprop_subj - get the subjective secid of the current task
+ * @prop: where to put the result
+ *
+ * Sets the secid to contain a u32 version of the task's subjective smack label.
+ */
+static void smack_current_getlsmprop_subj(struct lsm_prop *prop)
+{
+	prop->smack.skp = smk_of_current();
+}
+
+/**
+ * smack_task_getlsmprop_obj - get the objective data of the task
+ * @p: the task
+ * @prop: where to put the result
+ *
+ * Sets the secid to contain a u32 version of the task's objective smack label.
+ */
+static void smack_task_getlsmprop_obj(struct task_struct *p,
+				      struct lsm_prop *prop)
+{
+	prop->smack.skp = smk_of_task_struct_obj(p);
+}
+
+/**
+ * smack_task_setnice - Smack check on setting nice
+ * @p: the task object
+ * @nice: unused
+ *
+ * Return 0 if write access is permitted
+ */
+static int smack_task_setnice(struct task_struct *p, int nice)
+{
+	return smk_curacc_on_task(p, MAY_WRITE, __func__);
+}
+
+/**
+ * smack_task_setioprio - Smack check on setting ioprio
+ * @p: the task object
+ * @ioprio: unused
+ *
+ * Return 0 if write access is permitted
+ */
+static int smack_task_setioprio(struct task_struct *p, int ioprio)
+{
+	return smk_curacc_on_task(p, MAY_WRITE, __func__);
+}
+
+/**
+ * smack_task_getioprio - Smack check on reading ioprio
+ * @p: the task object
+ *
+ * Return 0 if read access is permitted
+ */
+static int smack_task_getioprio(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_READ, __func__);
+}
+
+/**
+ * smack_task_setscheduler - Smack check on setting scheduler
+ * @p: the task object
+ *
+ * Return 0 if read access is permitted
+ */
+static int smack_task_setscheduler(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_WRITE, __func__);
+}
+
+/**
+ * smack_task_getscheduler - Smack check on reading scheduler
+ * @p: the task object
+ *
+ * Return 0 if read access is permitted
+ */
+static int smack_task_getscheduler(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_READ, __func__);
+}
+
+/**
+ * smack_task_movememory - Smack check on moving memory
+ * @p: the task object
+ *
+ * Return 0 if write access is permitted
+ */
+static int smack_task_movememory(struct task_struct *p)
+{
+	return smk_curacc_on_task(p, MAY_WRITE, __func__);
+}
+
+/**
+ * smack_task_kill - Smack check on signal delivery
+ * @p: the task object
+ * @info: unused
+ * @sig: unused
+ * @cred: identifies the cred to use in lieu of current's
+ *
+ * Return 0 if write access is permitted
+ *
+ */
+static int smack_task_kill(struct task_struct *p, struct kernel_siginfo *info,
+			   int sig, const struct cred *cred)
+{
+	struct smk_audit_info ad;
+	struct smack_known *skp;
+	struct smack_known *tkp = smk_of_task_struct_obj(p);
+	int rc;
+
+	if (!sig)
+		return 0; /* null signal; existence test */
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
+	smk_ad_setfield_u_tsk(&ad, p);
+	/*
+	 * Sending a signal requires that the sender
+	 * can write the receiver.
+	 */
+	if (cred == NULL) {
+		rc = smk_curacc(tkp, MAY_DELIVER, &ad);
+		rc = smk_bu_task(p, MAY_DELIVER, rc);
+		return rc;
+	}
+	/*
+	 * If the cred isn't NULL we're dealing with some USB IO
+	 * specific behavior. This is not clean. For one thing
+	 * we can't take privilege into account.
+	 */
+	skp = smk_of_task(smack_cred(cred));
+	rc = smk_access(skp, tkp, MAY_DELIVER, &ad);
+	rc = smk_bu_note("USB signal", skp, tkp, MAY_DELIVER, rc);
+	return rc;
+}
+
+/**
+ * smack_task_to_inode - copy task smack into the inode blob
+ * @p: task to copy from
+ * @inode: inode to copy to
+ *
+ * Sets the smack pointer in the inode security blob
+ */
+static void smack_task_to_inode(struct task_struct *p, struct inode *inode)
+{
+	struct inode_smack *isp = smack_inode(inode);
+	struct smack_known *skp = smk_of_task_struct_obj(p);
+
+	isp->smk_inode = skp;
+	isp->smk_flags |= SMK_INODE_INSTANT;
+}
+
+/*
+ * Socket hooks.
+ */
+
+/**
+ * smack_sk_alloc_security - Allocate a socket blob
+ * @sk: the socket
+ * @family: unused
+ * @gfp_flags: memory allocation flags
+ *
+ * Assign Smack pointers to current
+ *
+ * Returns 0 on success, -ENOMEM is there's no memory
+ */
+static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags)
+{
+	struct smack_known *skp = smk_of_current();
+	struct socket_smack *ssp = smack_sock(sk);
+
+	/*
+	 * Sockets created by kernel threads receive web label.
+	 */
+	if (unlikely(current->flags & PF_KTHREAD)) {
+		ssp->smk_in = &smack_known_web;
+		ssp->smk_out = &smack_known_web;
+	} else {
+		ssp->smk_in = skp;
+		ssp->smk_out = skp;
+	}
+	ssp->smk_packet = NULL;
+
+	return 0;
+}
+
+#ifdef SMACK_IPV6_PORT_LABELING
+/**
+ * smack_sk_free_security - Free a socket blob
+ * @sk: the socket
+ *
+ * Clears the blob pointer
+ */
+static void smack_sk_free_security(struct sock *sk)
+{
+	struct smk_port_label *spp;
+
+	if (sk->sk_family == PF_INET6) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(spp, &smk_ipv6_port_list, list) {
+			if (spp->smk_sock != sk)
+				continue;
+			spp->smk_can_reuse = 1;
+			break;
+		}
+		rcu_read_unlock();
+	}
+}
+#endif
+
+/**
+ * smack_sk_clone_security - Copy security context
+ * @sk: the old socket
+ * @newsk: the new socket
+ *
+ * Copy the security context of the old socket pointer to the cloned
+ */
+static void smack_sk_clone_security(const struct sock *sk, struct sock *newsk)
+{
+	struct socket_smack *ssp_old = smack_sock(sk);
+	struct socket_smack *ssp_new = smack_sock(newsk);
+
+	*ssp_new = *ssp_old;
+}
+
+/**
+* smack_ipv4host_label - check host based restrictions
+* @sip: the object end
+*
+* looks for host based access restrictions
+*
+* This version will only be appropriate for really small sets of single label
+* hosts.  The caller is responsible for ensuring that the RCU read lock is
+* taken before calling this function.
+*
+* Returns the label of the far end or NULL if it's not special.
+*/
+static struct smack_known *smack_ipv4host_label(struct sockaddr_in *sip)
+{
+	struct smk_net4addr *snp;
+	struct in_addr *siap = &sip->sin_addr;
+
+	if (siap->s_addr == 0)
+		return NULL;
+
+	list_for_each_entry_rcu(snp, &smk_net4addr_list, list)
+		/*
+		 * we break after finding the first match because
+		 * the list is sorted from longest to shortest mask
+		 * so we have found the most specific match
+		 */
+		if (snp->smk_host.s_addr ==
+		    (siap->s_addr & snp->smk_mask.s_addr))
+			return snp->smk_label;
+
+	return NULL;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+/*
+ * smk_ipv6_localhost - Check for local ipv6 host address
+ * @sip: the address
+ *
+ * Returns boolean true if this is the localhost address
+ */
+static bool smk_ipv6_localhost(struct sockaddr_in6 *sip)
+{
+	__be16 *be16p = (__be16 *)&sip->sin6_addr;
+	__be32 *be32p = (__be32 *)&sip->sin6_addr;
+
+	if (be32p[0] == 0 && be32p[1] == 0 && be32p[2] == 0 && be16p[6] == 0 &&
+	    ntohs(be16p[7]) == 1)
+		return true;
+	return false;
+}
+
+/**
+* smack_ipv6host_label - check host based restrictions
+* @sip: the object end
+*
+* looks for host based access restrictions
+*
+* This version will only be appropriate for really small sets of single label
+* hosts.  The caller is responsible for ensuring that the RCU read lock is
+* taken before calling this function.
+*
+* Returns the label of the far end or NULL if it's not special.
+*/
+static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip)
+{
+	struct smk_net6addr *snp;
+	struct in6_addr *sap = &sip->sin6_addr;
+	int i;
+	int found = 0;
+
+	/*
+	 * It's local. Don't look for a host label.
+	 */
+	if (smk_ipv6_localhost(sip))
+		return NULL;
+
+	list_for_each_entry_rcu(snp, &smk_net6addr_list, list) {
+		/*
+		 * If the label is NULL the entry has
+		 * been renounced. Ignore it.
+		 */
+		if (snp->smk_label == NULL)
+			continue;
+		/*
+		* we break after finding the first match because
+		* the list is sorted from longest to shortest mask
+		* so we have found the most specific match
+		*/
+		for (found = 1, i = 0; i < 8; i++) {
+			if ((sap->s6_addr16[i] & snp->smk_mask.s6_addr16[i]) !=
+			    snp->smk_host.s6_addr16[i]) {
+				found = 0;
+				break;
+			}
+		}
+		if (found)
+			return snp->smk_label;
+	}
+
+	return NULL;
+}
+#endif /* CONFIG_IPV6 */
+
+/**
+ * smack_netlbl_add - Set the secattr on a socket
+ * @sk: the socket
+ *
+ * Attach the outbound smack value (smk_out) to the socket.
+ *
+ * Returns 0 on success or an error code
+ */
+static int smack_netlbl_add(struct sock *sk)
+{
+	struct socket_smack *ssp = smack_sock(sk);
+	struct smack_known *skp = ssp->smk_out;
+	int rc;
+
+	local_bh_disable();
+	bh_lock_sock_nested(sk);
+
+	rc = netlbl_sock_setattr(sk, sk->sk_family, &skp->smk_netlabel,
+				 netlbl_sk_lock_check(sk));
+	switch (rc) {
+	case 0:
+		ssp->smk_state = SMK_NETLBL_LABELED;
+		break;
+	case -EDESTADDRREQ:
+		ssp->smk_state = SMK_NETLBL_REQSKB;
+		rc = 0;
+		break;
+	}
+
+	bh_unlock_sock(sk);
+	local_bh_enable();
+
+	return rc;
+}
+
+/**
+ * smack_netlbl_delete - Remove the secattr from a socket
+ * @sk: the socket
+ *
+ * Remove the outbound smack value from a socket
+ */
+static void smack_netlbl_delete(struct sock *sk)
+{
+	struct socket_smack *ssp = smack_sock(sk);
+
+	/*
+	 * Take the label off the socket if one is set.
+	 */
+	if (ssp->smk_state != SMK_NETLBL_LABELED)
+		return;
+
+	local_bh_disable();
+	bh_lock_sock_nested(sk);
+	netlbl_sock_delattr(sk);
+	bh_unlock_sock(sk);
+	local_bh_enable();
+	ssp->smk_state = SMK_NETLBL_UNLABELED;
+}
+
+/**
+ * smk_ipv4_check - Perform IPv4 host access checks
+ * @sk: the socket
+ * @sap: the destination address
+ *
+ * Set the correct secattr for the given socket based on the destination
+ * address and perform any outbound access checks needed.
+ *
+ * Returns 0 on success or an error code.
+ *
+ */
+static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap)
+{
+	struct smack_known *skp;
+	int rc = 0;
+	struct smack_known *hkp;
+	struct socket_smack *ssp = smack_sock(sk);
+	struct smk_audit_info ad;
+
+	rcu_read_lock();
+	hkp = smack_ipv4host_label(sap);
+	if (hkp != NULL) {
+#ifdef CONFIG_AUDIT
+		struct lsm_network_audit net;
+
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		ad.a.u.net->family = sap->sin_family;
+		ad.a.u.net->dport = sap->sin_port;
+		ad.a.u.net->v4info.daddr = sap->sin_addr.s_addr;
+#endif
+		skp = ssp->smk_out;
+		rc = smk_access(skp, hkp, MAY_WRITE, &ad);
+		rc = smk_bu_note("IPv4 host check", skp, hkp, MAY_WRITE, rc);
+		/*
+		 * Clear the socket netlabel if it's set.
+		 */
+		if (!rc)
+			smack_netlbl_delete(sk);
+	}
+	rcu_read_unlock();
+
+	return rc;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * smk_ipv6_check - check Smack access
+ * @subject: subject Smack label
+ * @object: object Smack label
+ * @address: address
+ * @act: the action being taken
+ *
+ * Check an IPv6 access
+ */
+static int smk_ipv6_check(struct smack_known *subject,
+				struct smack_known *object,
+				struct sockaddr_in6 *address, int act)
+{
+#ifdef CONFIG_AUDIT
+	struct lsm_network_audit net;
+#endif
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+	ad.a.u.net->family = PF_INET6;
+	ad.a.u.net->dport = address->sin6_port;
+	if (act == SMK_RECEIVING)
+		ad.a.u.net->v6info.saddr = address->sin6_addr;
+	else
+		ad.a.u.net->v6info.daddr = address->sin6_addr;
+#endif
+	rc = smk_access(subject, object, MAY_WRITE, &ad);
+	rc = smk_bu_note("IPv6 check", subject, object, MAY_WRITE, rc);
+	return rc;
+}
+#endif /* CONFIG_IPV6 */
+
+#ifdef SMACK_IPV6_PORT_LABELING
+/**
+ * smk_ipv6_port_label - Smack port access table management
+ * @sock: socket
+ * @address: address
+ *
+ * Create or update the port list entry
+ */
+static void smk_ipv6_port_label(struct socket *sock, struct sockaddr *address)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_in6 *addr6;
+	struct socket_smack *ssp = smack_sock(sock->sk);
+	struct smk_port_label *spp;
+	unsigned short port = 0;
+
+	if (address == NULL) {
+		/*
+		 * This operation is changing the Smack information
+		 * on the bound socket. Take the changes to the port
+		 * as well.
+		 */
+		rcu_read_lock();
+		list_for_each_entry_rcu(spp, &smk_ipv6_port_list, list) {
+			if (sk != spp->smk_sock)
+				continue;
+			spp->smk_in = ssp->smk_in;
+			spp->smk_out = ssp->smk_out;
+			rcu_read_unlock();
+			return;
+		}
+		/*
+		 * A NULL address is only used for updating existing
+		 * bound entries. If there isn't one, it's OK.
+		 */
+		rcu_read_unlock();
+		return;
+	}
+
+	addr6 = (struct sockaddr_in6 *)address;
+	port = ntohs(addr6->sin6_port);
+	/*
+	 * This is a special case that is safely ignored.
+	 */
+	if (port == 0)
+		return;
+
+	/*
+	 * Look for an existing port list entry.
+	 * This is an indication that a port is getting reused.
+	 */
+	rcu_read_lock();
+	list_for_each_entry_rcu(spp, &smk_ipv6_port_list, list) {
+		if (spp->smk_port != port || spp->smk_sock_type != sock->type)
+			continue;
+		if (spp->smk_can_reuse != 1) {
+			rcu_read_unlock();
+			return;
+		}
+		spp->smk_port = port;
+		spp->smk_sock = sk;
+		spp->smk_in = ssp->smk_in;
+		spp->smk_out = ssp->smk_out;
+		spp->smk_can_reuse = 0;
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+	/*
+	 * A new port entry is required.
+	 */
+	spp = kzalloc_obj(*spp);
+	if (spp == NULL)
+		return;
+
+	spp->smk_port = port;
+	spp->smk_sock = sk;
+	spp->smk_in = ssp->smk_in;
+	spp->smk_out = ssp->smk_out;
+	spp->smk_sock_type = sock->type;
+	spp->smk_can_reuse = 0;
+
+	mutex_lock(&smack_ipv6_lock);
+	list_add_rcu(&spp->list, &smk_ipv6_port_list);
+	mutex_unlock(&smack_ipv6_lock);
+	return;
+}
+
+/**
+ * smk_ipv6_port_check - check Smack port access
+ * @sk: socket
+ * @address: address
+ * @act: the action being taken
+ *
+ * Create or update the port list entry
+ */
+static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
+				int act)
+{
+	struct smk_port_label *spp;
+	struct socket_smack *ssp = smack_sock(sk);
+	struct smack_known *skp = NULL;
+	unsigned short port;
+	struct smack_known *object;
+
+	if (act == SMK_RECEIVING) {
+		skp = smack_ipv6host_label(address);
+		object = ssp->smk_in;
+	} else {
+		skp = ssp->smk_out;
+		object = smack_ipv6host_label(address);
+	}
+
+	/*
+	 * The other end is a single label host.
+	 */
+	if (skp != NULL && object != NULL)
+		return smk_ipv6_check(skp, object, address, act);
+	if (skp == NULL)
+		skp = smack_net_ambient;
+	if (object == NULL)
+		object = smack_net_ambient;
+
+	/*
+	 * It's remote, so port lookup does no good.
+	 */
+	if (!smk_ipv6_localhost(address))
+		return smk_ipv6_check(skp, object, address, act);
+
+	/*
+	 * It's local so the send check has to have passed.
+	 */
+	if (act == SMK_RECEIVING)
+		return 0;
+
+	port = ntohs(address->sin6_port);
+	rcu_read_lock();
+	list_for_each_entry_rcu(spp, &smk_ipv6_port_list, list) {
+		if (spp->smk_port != port || spp->smk_sock_type != sk->sk_type)
+			continue;
+		object = spp->smk_in;
+		if (act == SMK_CONNECTING)
+			ssp->smk_packet = spp->smk_out;
+		break;
+	}
+	rcu_read_unlock();
+
+	return smk_ipv6_check(skp, object, address, act);
+}
+#endif
+
+/**
+ * smack_inode_setsecurity - set smack xattrs
+ * @inode: the object
+ * @name: attribute name
+ * @value: attribute value
+ * @size: size of the attribute
+ * @flags: unused
+ *
+ * Sets the named attribute in the appropriate blob
+ *
+ * Returns 0 on success, or an error code
+ */
+static int smack_inode_setsecurity(struct inode *inode, const char *name,
+				   const void *value, size_t size, int flags)
+{
+	struct smack_known *skp;
+	struct inode_smack *nsp = smack_inode(inode);
+	struct socket_smack *ssp;
+	struct socket *sock;
+	int rc = 0;
+
+	if (value == NULL || size > SMK_LONGLABEL || size == 0)
+		return -EINVAL;
+
+	if (strcmp(name, XATTR_SMACK_TRANSMUTE) == 0) {
+		if (!S_ISDIR(inode->i_mode) || size != TRANS_TRUE_SIZE ||
+		    strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0)
+			return -EINVAL;
+
+		nsp->smk_flags |= SMK_INODE_TRANSMUTE;
+		return 0;
+	}
+
+	skp = smk_import_entry(value, size);
+	if (IS_ERR(skp))
+		return PTR_ERR(skp);
+
+	if (strcmp(name, XATTR_SMACK_SUFFIX) == 0) {
+		nsp->smk_inode = skp;
+		nsp->smk_flags |= SMK_INODE_INSTANT;
+		return 0;
+	}
+	/*
+	 * The rest of the Smack xattrs are only on sockets.
+	 */
+	if (inode->i_sb->s_magic != SOCKFS_MAGIC)
+		return -EOPNOTSUPP;
+
+	sock = SOCKET_I(inode);
+	if (sock == NULL || sock->sk == NULL)
+		return -EOPNOTSUPP;
+
+	ssp = smack_sock(sock->sk);
+
+	if (strcmp(name, XATTR_SMACK_IPIN) == 0)
+		ssp->smk_in = skp;
+	else if (strcmp(name, XATTR_SMACK_IPOUT) == 0) {
+		ssp->smk_out = skp;
+		if (sock->sk->sk_family == PF_INET) {
+			rc = smack_netlbl_add(sock->sk);
+			if (rc != 0)
+				printk(KERN_WARNING
+					"Smack: \"%s\" netlbl error %d.\n",
+					__func__, -rc);
+		}
+	} else
+		return -EOPNOTSUPP;
+
+#ifdef SMACK_IPV6_PORT_LABELING
+	if (sock->sk->sk_family == PF_INET6)
+		smk_ipv6_port_label(sock, NULL);
+#endif
+
+	return 0;
+}
+
+/**
+ * smack_socket_post_create - finish socket setup
+ * @sock: the socket
+ * @family: protocol family
+ * @type: unused
+ * @protocol: unused
+ * @kern: unused
+ *
+ * Sets the netlabel information on the socket
+ *
+ * Returns 0 on success, and error code otherwise
+ */
+static int smack_socket_post_create(struct socket *sock, int family,
+				    int type, int protocol, int kern)
+{
+	struct socket_smack *ssp;
+
+	if (sock->sk == NULL)
+		return 0;
+
+	/*
+	 * Sockets created by kernel threads receive web label.
+	 */
+	if (unlikely(current->flags & PF_KTHREAD)) {
+		ssp = smack_sock(sock->sk);
+		ssp->smk_in = &smack_known_web;
+		ssp->smk_out = &smack_known_web;
+	}
+
+	if (family != PF_INET)
+		return 0;
+	/*
+	 * Set the outbound netlbl.
+	 */
+	return smack_netlbl_add(sock->sk);
+}
+
+/**
+ * smack_socket_socketpair - create socket pair
+ * @socka: one socket
+ * @sockb: another socket
+ *
+ * Cross reference the peer labels for SO_PEERSEC
+ *
+ * Returns 0
+ */
+static int smack_socket_socketpair(struct socket *socka,
+		                   struct socket *sockb)
+{
+	struct socket_smack *asp = smack_sock(socka->sk);
+	struct socket_smack *bsp = smack_sock(sockb->sk);
+
+	asp->smk_packet = bsp->smk_out;
+	bsp->smk_packet = asp->smk_out;
+
+	return 0;
+}
+
+#ifdef SMACK_IPV6_PORT_LABELING
+/**
+ * smack_socket_bind - record port binding information.
+ * @sock: the socket
+ * @address: the port address
+ * @addrlen: size of the address
+ *
+ * Records the label bound to a port.
+ *
+ * Returns 0 on success, and error code otherwise
+ */
+static int smack_socket_bind(struct socket *sock, struct sockaddr *address,
+				int addrlen)
+{
+	if (sock->sk != NULL && sock->sk->sk_family == PF_INET6) {
+		if (addrlen < SIN6_LEN_RFC2133 ||
+		    address->sa_family != AF_INET6)
+			return -EINVAL;
+		smk_ipv6_port_label(sock, address);
+	}
+	return 0;
+}
+#endif /* SMACK_IPV6_PORT_LABELING */
+
+/**
+ * smack_socket_connect - connect access check
+ * @sock: the socket
+ * @sap: the other end
+ * @addrlen: size of sap
+ *
+ * Verifies that a connection may be possible
+ *
+ * Returns 0 on success, and error code otherwise
+ */
+static int smack_socket_connect(struct socket *sock, struct sockaddr *sap,
+				int addrlen)
+{
+	int rc = 0;
+
+	if (sock->sk == NULL)
+		return 0;
+	if (sock->sk->sk_family != PF_INET &&
+	    (!IS_ENABLED(CONFIG_IPV6) || sock->sk->sk_family != PF_INET6))
+		return 0;
+	if (addrlen < offsetofend(struct sockaddr, sa_family))
+		return 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sap->sa_family == AF_INET6) {
+		struct sockaddr_in6 *sip = (struct sockaddr_in6 *)sap;
+		struct smack_known *rsp = NULL;
+
+		if (addrlen < SIN6_LEN_RFC2133)
+			return 0;
+		if (__is_defined(SMACK_IPV6_SECMARK_LABELING))
+			rsp = smack_ipv6host_label(sip);
+		if (rsp != NULL) {
+			struct socket_smack *ssp = smack_sock(sock->sk);
+
+			rc = smk_ipv6_check(ssp->smk_out, rsp, sip,
+					    SMK_CONNECTING);
+		}
+#ifdef SMACK_IPV6_PORT_LABELING
+		rc = smk_ipv6_port_check(sock->sk, sip, SMK_CONNECTING);
+#endif
+
+		return rc;
+	}
+#endif /* CONFIG_IPV6 */
+
+	if (sap->sa_family != AF_INET || addrlen < sizeof(struct sockaddr_in))
+		return 0;
+	rc = smk_ipv4_check(sock->sk, (struct sockaddr_in *)sap);
+	return rc;
+}
+
+/**
+ * smack_flags_to_may - convert S_ to MAY_ values
+ * @flags: the S_ value
+ *
+ * Returns the equivalent MAY_ value
+ */
+static int smack_flags_to_may(int flags)
+{
+	int may = 0;
+
+	if (flags & S_IRUGO)
+		may |= MAY_READ;
+	if (flags & S_IWUGO)
+		may |= MAY_WRITE;
+	if (flags & S_IXUGO)
+		may |= MAY_EXEC;
+
+	return may;
+}
+
+/**
+ * smack_msg_msg_alloc_security - Set the security blob for msg_msg
+ * @msg: the object
+ *
+ * Returns 0
+ */
+static int smack_msg_msg_alloc_security(struct msg_msg *msg)
+{
+	struct smack_known **blob = smack_msg_msg(msg);
+
+	*blob = smk_of_current();
+	return 0;
+}
+
+/**
+ * smack_of_ipc - the smack pointer for the ipc
+ * @isp: the object
+ *
+ * Returns a pointer to the smack value
+ */
+static struct smack_known *smack_of_ipc(struct kern_ipc_perm *isp)
+{
+	struct smack_known **blob = smack_ipc(isp);
+
+	return *blob;
+}
+
+/**
+ * smack_ipc_alloc_security - Set the security blob for ipc
+ * @isp: the object
+ *
+ * Returns 0
+ */
+static int smack_ipc_alloc_security(struct kern_ipc_perm *isp)
+{
+	struct smack_known **blob = smack_ipc(isp);
+
+	*blob = smk_of_current();
+	return 0;
+}
+
+/**
+ * smk_curacc_shm : check if current has access on shm
+ * @isp : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_shm(struct kern_ipc_perm *isp, int access)
+{
+	struct smack_known *ssp = smack_of_ipc(isp);
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = isp->id;
+#endif
+	rc = smk_curacc(ssp, access, &ad);
+	rc = smk_bu_current("shm", ssp, access, rc);
+	return rc;
+}
+
+/**
+ * smack_shm_associate - Smack access check for shm
+ * @isp: the object
+ * @shmflg: access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_shm_associate(struct kern_ipc_perm *isp, int shmflg)
+{
+	int may;
+
+	may = smack_flags_to_may(shmflg);
+	return smk_curacc_shm(isp, may);
+}
+
+/**
+ * smack_shm_shmctl - Smack access check for shm
+ * @isp: the object
+ * @cmd: what it wants to do
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_shm_shmctl(struct kern_ipc_perm *isp, int cmd)
+{
+	int may;
+
+	switch (cmd) {
+	case IPC_STAT:
+	case SHM_STAT:
+	case SHM_STAT_ANY:
+		may = MAY_READ;
+		break;
+	case IPC_SET:
+	case SHM_LOCK:
+	case SHM_UNLOCK:
+	case IPC_RMID:
+		may = MAY_READWRITE;
+		break;
+	case IPC_INFO:
+	case SHM_INFO:
+		/*
+		 * System level information.
+		 */
+		return 0;
+	default:
+		return -EINVAL;
+	}
+	return smk_curacc_shm(isp, may);
+}
+
+/**
+ * smack_shm_shmat - Smack access for shmat
+ * @isp: the object
+ * @shmaddr: unused
+ * @shmflg: access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_shm_shmat(struct kern_ipc_perm *isp, char __user *shmaddr,
+			   int shmflg)
+{
+	int may;
+
+	may = smack_flags_to_may(shmflg);
+	return smk_curacc_shm(isp, may);
+}
+
+/**
+ * smk_curacc_sem : check if current has access on sem
+ * @isp : the object
+ * @access : access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smk_curacc_sem(struct kern_ipc_perm *isp, int access)
+{
+	struct smack_known *ssp = smack_of_ipc(isp);
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = isp->id;
+#endif
+	rc = smk_curacc(ssp, access, &ad);
+	rc = smk_bu_current("sem", ssp, access, rc);
+	return rc;
+}
+
+/**
+ * smack_sem_associate - Smack access check for sem
+ * @isp: the object
+ * @semflg: access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_sem_associate(struct kern_ipc_perm *isp, int semflg)
+{
+	int may;
+
+	may = smack_flags_to_may(semflg);
+	return smk_curacc_sem(isp, may);
+}
+
+/**
+ * smack_sem_semctl - Smack access check for sem
+ * @isp: the object
+ * @cmd: what it wants to do
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_sem_semctl(struct kern_ipc_perm *isp, int cmd)
+{
+	int may;
+
+	switch (cmd) {
+	case GETPID:
+	case GETNCNT:
+	case GETZCNT:
+	case GETVAL:
+	case GETALL:
+	case IPC_STAT:
+	case SEM_STAT:
+	case SEM_STAT_ANY:
+		may = MAY_READ;
+		break;
+	case SETVAL:
+	case SETALL:
+	case IPC_RMID:
+	case IPC_SET:
+		may = MAY_READWRITE;
+		break;
+	case IPC_INFO:
+	case SEM_INFO:
+		/*
+		 * System level information
+		 */
+		return 0;
+	default:
+		return -EINVAL;
+	}
+
+	return smk_curacc_sem(isp, may);
+}
+
+/**
+ * smack_sem_semop - Smack checks of semaphore operations
+ * @isp: the object
+ * @sops: unused
+ * @nsops: unused
+ * @alter: unused
+ *
+ * Treated as read and write in all cases.
+ *
+ * Returns 0 if access is allowed, error code otherwise
+ */
+static int smack_sem_semop(struct kern_ipc_perm *isp, struct sembuf *sops,
+			   unsigned nsops, int alter)
+{
+	return smk_curacc_sem(isp, MAY_READWRITE);
+}
+
+/**
+ * smk_tskacc_msq : helper to check if tsk has access on msq
+ * @tsk: the task that requests access
+ * @isp : the sysv msg queue permissions
+ * @access : access requested
+ *
+ * return 0 if tsk has access, error otherwise
+ */
+static int
+smk_tskacc_msq(struct task_struct *tsk, struct kern_ipc_perm *isp, int access)
+{
+	const bool tsk_is_current = (tsk == current);
+	const struct cred * const tsk_cred =
+			(tsk_is_current ? current_cred() : get_task_cred(tsk));
+	struct task_smack * const tsp = smack_cred(tsk_cred);
+	struct smack_known *msp = smack_of_ipc(isp);
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = isp->id;
+	if (!tsk_is_current)
+		ad.sad.subj_tsk = tsk;
+#endif
+	rc = smk_tskacc(tsp, msp, access, &ad);
+	rc = smk_bu_tsk_to_obj(tsk, tsp, "msq", msp, access, rc);
+	if (!tsk_is_current)
+		put_cred(tsk_cred);
+	return rc;
+}
+
+/**
+ * smk_curacc_msq : helper to check if current has access on msq
+ * @isp : the sysv msg queue permissions
+ * @access : access requested
+ *
+ * return 0 if current has access, error otherwise
+ */
+static int smk_curacc_msq(struct kern_ipc_perm *isp, int access)
+{
+	return smk_tskacc_msq(current, isp, access);
+}
+
+/**
+ * smack_msg_queue_associate - Smack access check for msg_queue
+ * @isp: the object
+ * @msqflg: access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_msg_queue_associate(struct kern_ipc_perm *isp, int msqflg)
+{
+	int may;
+
+	may = smack_flags_to_may(msqflg);
+	return smk_curacc_msq(isp, may);
+}
+
+/**
+ * smack_msg_queue_msgctl - Smack access check for msg_queue
+ * @isp: the object
+ * @cmd: what it wants to do
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_msg_queue_msgctl(struct kern_ipc_perm *isp, int cmd)
+{
+	int may;
+
+	switch (cmd) {
+	case IPC_STAT:
+	case MSG_STAT:
+	case MSG_STAT_ANY:
+		may = MAY_READ;
+		break;
+	case IPC_SET:
+	case IPC_RMID:
+		may = MAY_READWRITE;
+		break;
+	case IPC_INFO:
+	case MSG_INFO:
+		/*
+		 * System level information
+		 */
+		return 0;
+	default:
+		return -EINVAL;
+	}
+
+	return smk_curacc_msq(isp, may);
+}
+
+/**
+ * smack_msg_queue_msgsnd - Smack access check for msg_queue
+ * @isp: the object
+ * @msg: unused
+ * @msqflg: access requested
+ *
+ * Returns 0 if current has the requested access, error code otherwise
+ */
+static int smack_msg_queue_msgsnd(struct kern_ipc_perm *isp, struct msg_msg *msg,
+				  int msqflg)
+{
+	int may;
+
+	may = smack_flags_to_may(msqflg);
+	return smk_curacc_msq(isp, may);
+}
+
+/**
+ * smack_msg_queue_msgrcv - check it target has r/w access to msg_queue
+ * @isp: the object
+ * @msg: unused
+ * @target: the task that msgrcv() from the queue
+ * @type: unused
+ * @mode: unused
+ *
+ * Returns 0 if target has read and write access, error code otherwise
+ */
+static int smack_msg_queue_msgrcv(struct kern_ipc_perm *isp,
+				  struct msg_msg *msg,
+				  struct task_struct *target, long type,
+				  int mode)
+{
+	return smk_tskacc_msq(target, isp, MAY_READWRITE);
+}
+
+/**
+ * smack_ipc_permission - Smack access for ipc_permission()
+ * @ipp: the object permissions
+ * @flag: access requested
+ *
+ * Returns 0 if current has read and write access, error code otherwise
+ */
+static int smack_ipc_permission(struct kern_ipc_perm *ipp, short flag)
+{
+	struct smack_known **blob = smack_ipc(ipp);
+	struct smack_known *iskp = *blob;
+	int may = smack_flags_to_may(flag);
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_IPC);
+	ad.a.u.ipc_id = ipp->id;
+#endif
+	rc = smk_curacc(iskp, may, &ad);
+	rc = smk_bu_current("svipc", iskp, may, rc);
+	return rc;
+}
+
+/**
+ * smack_ipc_getlsmprop - Extract smack security data
+ * @ipp: the object permissions
+ * @prop: where result will be saved
+ */
+static void smack_ipc_getlsmprop(struct kern_ipc_perm *ipp, struct lsm_prop *prop)
+{
+	struct smack_known **iskpp = smack_ipc(ipp);
+
+	prop->smack.skp = *iskpp;
+}
+
+/**
+ * smack_d_instantiate - Make sure the blob is correct on an inode
+ * @opt_dentry: dentry where inode will be attached
+ * @inode: the object
+ *
+ * Set the inode's security blob if it hasn't been done already.
+ */
+static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode)
+{
+	struct super_block *sbp;
+	struct superblock_smack *sbsp;
+	struct inode_smack *isp;
+	struct smack_known *skp;
+	struct smack_known *ckp = smk_of_current();
+	struct smack_known *final;
+	char trattr[TRANS_TRUE_SIZE];
+	int transflag = 0;
+	int rc;
+	struct dentry *dp;
+
+	if (inode == NULL)
+		return;
+
+	isp = smack_inode(inode);
+
+	/*
+	 * If the inode is already instantiated
+	 * take the quick way out
+	 */
+	if (isp->smk_flags & SMK_INODE_INSTANT)
+		return;
+
+	sbp = inode->i_sb;
+	sbsp = smack_superblock(sbp);
+	/*
+	 * We're going to use the superblock default label
+	 * if there's no label on the file.
+	 */
+	final = sbsp->smk_default;
+
+	/*
+	 * If this is the root inode the superblock
+	 * may be in the process of initialization.
+	 * If that is the case use the root value out
+	 * of the superblock.
+	 */
+	if (opt_dentry->d_parent == opt_dentry) {
+		switch (sbp->s_magic) {
+		case CGROUP_SUPER_MAGIC:
+		case CGROUP2_SUPER_MAGIC:
+			/*
+			 * The cgroup filesystem is never mounted,
+			 * so there's no opportunity to set the mount
+			 * options.
+			 */
+			sbsp->smk_root = &smack_known_star;
+			sbsp->smk_default = &smack_known_star;
+			isp->smk_inode = sbsp->smk_root;
+			break;
+		case TMPFS_MAGIC:
+			/*
+			 * What about shmem/tmpfs anonymous files with dentry
+			 * obtained from d_alloc_pseudo()?
+			 */
+			isp->smk_inode = smk_of_current();
+			break;
+		case PIPEFS_MAGIC:
+			isp->smk_inode = smk_of_current();
+			break;
+		case SOCKFS_MAGIC:
+			/*
+			 * Socket access is controlled by the socket
+			 * structures associated with the task involved.
+			 */
+			isp->smk_inode = &smack_known_star;
+			break;
+		default:
+			isp->smk_inode = sbsp->smk_root;
+			break;
+		}
+		isp->smk_flags |= SMK_INODE_INSTANT;
+		return;
+	}
+
+	/*
+	 * This is pretty hackish.
+	 * Casey says that we shouldn't have to do
+	 * file system specific code, but it does help
+	 * with keeping it simple.
+	 */
+	switch (sbp->s_magic) {
+	case SMACK_MAGIC:
+	case CGROUP_SUPER_MAGIC:
+	case CGROUP2_SUPER_MAGIC:
+		/*
+		 * Casey says that it's a little embarrassing
+		 * that the smack file system doesn't do
+		 * extended attributes.
+		 *
+		 * Cgroupfs is special
+		 */
+		final = &smack_known_star;
+		break;
+	case DEVPTS_SUPER_MAGIC:
+		/*
+		 * devpts seems content with the label of the task.
+		 * Programs that change smack have to treat the
+		 * pty with respect.
+		 */
+		final = ckp;
+		break;
+	case PROC_SUPER_MAGIC:
+		/*
+		 * Casey says procfs appears not to care.
+		 * The superblock default suffices.
+		 */
+		break;
+	case TMPFS_MAGIC:
+		/*
+		 * Device labels should come from the filesystem,
+		 * but watch out, because they're volitile,
+		 * getting recreated on every reboot.
+		 */
+		final = &smack_known_star;
+		/*
+		 * If a smack value has been set we want to use it,
+		 * but since tmpfs isn't giving us the opportunity
+		 * to set mount options simulate setting the
+		 * superblock default.
+		 */
+		fallthrough;
+	default:
+		/*
+		 * This isn't an understood special case.
+		 * Get the value from the xattr.
+		 */
+
+		/*
+		 * UDS inode has fixed label (*)
+		 */
+		if (S_ISSOCK(inode->i_mode)) {
+			final = &smack_known_star;
+			break;
+		}
+		/*
+		 * No xattr support means, alas, no SMACK label.
+		 * Use the aforeapplied default.
+		 * It would be curious if the label of the task
+		 * does not match that assigned.
+		 */
+		if (!(inode->i_opflags & IOP_XATTR))
+		        break;
+		/*
+		 * Get the dentry for xattr.
+		 */
+		dp = dget(opt_dentry);
+		skp = smk_fetch(XATTR_NAME_SMACK, inode, dp);
+		if (!IS_ERR_OR_NULL(skp))
+			final = skp;
+
+		/*
+		 * Transmuting directory
+		 */
+		if (S_ISDIR(inode->i_mode)) {
+			/*
+			 * If this is a new directory and the label was
+			 * transmuted when the inode was initialized
+			 * set the transmute attribute on the directory
+			 * and mark the inode.
+			 *
+			 * If there is a transmute attribute on the
+			 * directory mark the inode.
+			 */
+			rc = __vfs_getxattr(dp, inode,
+					    XATTR_NAME_SMACKTRANSMUTE, trattr,
+					    TRANS_TRUE_SIZE);
+			if (rc >= 0 && strncmp(trattr, TRANS_TRUE,
+					       TRANS_TRUE_SIZE) != 0)
+				rc = -EINVAL;
+			if (rc >= 0)
+				transflag = SMK_INODE_TRANSMUTE;
+		}
+		/*
+		 * Don't let the exec or mmap label be "*" or "@".
+		 */
+		skp = smk_fetch(XATTR_NAME_SMACKEXEC, inode, dp);
+		if (IS_ERR(skp) || skp == &smack_known_star ||
+		    skp == &smack_known_web)
+			skp = NULL;
+		isp->smk_task = skp;
+
+		skp = smk_fetch(XATTR_NAME_SMACKMMAP, inode, dp);
+		if (IS_ERR(skp) || skp == &smack_known_star ||
+		    skp == &smack_known_web)
+			skp = NULL;
+		isp->smk_mmap = skp;
+
+		dput(dp);
+		break;
+	}
+
+	if (final == NULL)
+		isp->smk_inode = ckp;
+	else
+		isp->smk_inode = final;
+
+	isp->smk_flags |= (SMK_INODE_INSTANT | transflag);
+
+	return;
+}
+
+/**
+ * smack_getselfattr - Smack current process attribute
+ * @attr: which attribute to fetch
+ * @ctx: buffer to receive the result
+ * @size: available size in, actual size out
+ * @flags: reserved, currently zero
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns the number of attributes on success, an error code otherwise.
+ * There will only ever be one attribute.
+ */
+static int smack_getselfattr(unsigned int attr, struct lsm_ctx __user *ctx,
+			     u32 *size, u32 flags)
+{
+	int rc;
+	struct smack_known *skp;
+
+	if (attr != LSM_ATTR_CURRENT)
+		return -EOPNOTSUPP;
+
+	skp = smk_of_current();
+	rc = lsm_fill_user_ctx(ctx, size,
+			       skp->smk_known, strlen(skp->smk_known) + 1,
+			       LSM_ID_SMACK, 0);
+	return (!rc ? 1 : rc);
+}
+
+/**
+ * smack_getprocattr - Smack process attribute access
+ * @p: the object task
+ * @name: the name of the attribute in /proc/.../attr
+ * @value: where to put the result
+ *
+ * Places a copy of the task Smack into value
+ *
+ * Returns the length of the smack label or an error code
+ */
+static int smack_getprocattr(struct task_struct *p, const char *name, char **value)
+{
+	struct smack_known *skp = smk_of_task_struct_obj(p);
+	char *cp;
+	int slen;
+
+	if (strcmp(name, "current") != 0)
+		return -EINVAL;
+
+	cp = kstrdup(skp->smk_known, GFP_KERNEL);
+	if (cp == NULL)
+		return -ENOMEM;
+
+	slen = strlen(cp);
+	*value = cp;
+	return slen;
+}
+
+/**
+ * do_setattr - Smack process attribute setting
+ * @attr: the ID of the attribute
+ * @value: the value to set
+ * @size: the size of the value
+ *
+ * Sets the Smack value of the task. Only setting self
+ * is permitted and only with privilege
+ *
+ * Returns zero on success or an error code
+ */
+static int do_setattr(unsigned int attr, void *value, size_t size)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct cred *new;
+	struct smack_known *skp;
+	int label_len;
+
+	/*
+	 * let unprivileged user validate input, check permissions later
+	 */
+	if (value == NULL || size == 0 || size >= SMK_LONGLABEL)
+		return -EINVAL;
+
+	label_len = smk_parse_label_len(value, size);
+	if (label_len < 0 || label_len != size)
+		return -EINVAL;
+
+	/*
+	 * No process is ever allowed the web ("@") label
+	 * and the star ("*") label.
+	 */
+	if (label_len == 1 /* '@', '*' */) {
+		const char c = *(const char *)value;
+
+		if (c == *smack_known_web.smk_known ||
+		    c == *smack_known_star.smk_known)
+			return -EPERM;
+	}
+
+	if (!smack_privileged(CAP_MAC_ADMIN)) {
+		const struct smack_known_list_elem *sklep;
+		list_for_each_entry(sklep, &tsp->smk_relabel, list) {
+			const char *cp = sklep->smk_label->smk_known;
+
+			if (strlen(cp) == label_len &&
+			    strncmp(cp, value, label_len) == 0)
+				goto in_relabel;
+		}
+		return -EPERM;
+in_relabel:
+		;
+	}
+
+	skp = smk_import_valid_label(value, label_len, GFP_KERNEL);
+	if (IS_ERR(skp))
+		return PTR_ERR(skp);
+
+	new = prepare_creds();
+	if (new == NULL)
+		return -ENOMEM;
+
+	tsp = smack_cred(new);
+	tsp->smk_task = skp;
+	/*
+	 * process can change its label only once
+	 */
+	smk_destroy_label_list(&tsp->smk_relabel);
+
+	commit_creds(new);
+	return 0;
+}
+
+/**
+ * smack_setselfattr - Set a Smack process attribute
+ * @attr: which attribute to set
+ * @ctx: buffer containing the data
+ * @size: size of @ctx
+ * @flags: reserved, must be zero
+ *
+ * Fill the passed user space @ctx with the details of the requested
+ * attribute.
+ *
+ * Returns 0 on success, an error code otherwise.
+ */
+static int smack_setselfattr(unsigned int attr, struct lsm_ctx *ctx,
+			     u32 size, u32 flags)
+{
+	if (attr != LSM_ATTR_CURRENT)
+		return -EOPNOTSUPP;
+
+	if (ctx->flags)
+		return -EINVAL;
+	/*
+	 * string must have \0 terminator, included in ctx->ctx
+	 * (see description of struct lsm_ctx)
+	 */
+	if (ctx->ctx_len == 0)
+		return -EINVAL;
+
+	if (ctx->ctx[ctx->ctx_len - 1] != '\0')
+		return -EINVAL;
+	/*
+	 * other do_setattr() caller, smack_setprocattr(),
+	 * does not count \0 into size, so
+	 * decreasing length by 1 to accommodate the divergence.
+	 */
+	return do_setattr(attr, ctx->ctx, ctx->ctx_len - 1);
+}
+
+/**
+ * smack_setprocattr - Smack process attribute setting
+ * @name: the name of the attribute in /proc/.../attr
+ * @value: the value to set
+ * @size: the size of the value
+ *
+ * Sets the Smack value of the task. Only setting self
+ * is permitted and only with privilege
+ *
+ * Returns the size of the input value or an error code
+ */
+static int smack_setprocattr(const char *name, void *value, size_t size)
+{
+	size_t realsize = size;
+	unsigned int attr = lsm_name_to_attr(name);
+
+	switch (attr) {
+	case LSM_ATTR_UNDEF:   return -EINVAL;
+	default:               return -EOPNOTSUPP;
+	case LSM_ATTR_CURRENT:
+		;
+	}
+
+	/*
+	 * The value for the "current" attribute is the label
+	 * followed by one of the 4 trailers: none, \0, \n, \n\0
+	 *
+	 * I.e. following inputs are accepted as 3-characters long label "foo":
+	 *
+	 *   "foo"     (3 characters)
+	 *   "foo\0"   (4 characters)
+	 *   "foo\n"   (4 characters)
+	 *   "foo\n\0" (5 characters)
+	 */
+
+	if (realsize && (((const char *)value)[realsize - 1] == '\0'))
+		--realsize;
+
+	if (realsize && (((const char *)value)[realsize - 1] == '\n'))
+		--realsize;
+
+	return do_setattr(attr, value, realsize) ? : size;
+}
+
+/**
+ * smack_unix_stream_connect - Smack access on UDS
+ * @sock: one sock
+ * @other: the other sock
+ * @newsk: unused
+ *
+ * Return 0 if a subject with the smack of sock could access
+ * an object with the smack of other, otherwise an error code
+ */
+static int smack_unix_stream_connect(struct sock *sock,
+				     struct sock *other, struct sock *newsk)
+{
+	struct smack_known *skp;
+	struct smack_known *okp;
+	struct socket_smack *ssp = smack_sock(sock);
+	struct socket_smack *osp = smack_sock(other);
+	struct socket_smack *nsp = smack_sock(newsk);
+	struct smk_audit_info ad;
+	int rc = 0;
+#ifdef CONFIG_AUDIT
+	struct lsm_network_audit net;
+#endif
+
+	if (!smack_privileged(CAP_MAC_OVERRIDE)) {
+		skp = ssp->smk_out;
+		okp = osp->smk_in;
+#ifdef CONFIG_AUDIT
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		smk_ad_setfield_u_net_sk(&ad, other);
+#endif
+		rc = smk_access(skp, okp, MAY_WRITE, &ad);
+		rc = smk_bu_note("UDS connect", skp, okp, MAY_WRITE, rc);
+		if (rc == 0) {
+			okp = osp->smk_out;
+			skp = ssp->smk_in;
+			rc = smk_access(okp, skp, MAY_WRITE, &ad);
+			rc = smk_bu_note("UDS connect", okp, skp,
+						MAY_WRITE, rc);
+		}
+	}
+
+	if (rc == 0) {
+		/*
+		 * Cross reference the peer labels for SO_PEERSEC.
+		 */
+		nsp->smk_packet = ssp->smk_out;
+		ssp->smk_packet = osp->smk_out;
+
+		/*
+		 * new/child/established socket must inherit listening socket labels
+		 */
+		nsp->smk_out = osp->smk_out;
+		nsp->smk_in  = osp->smk_in;
+	}
+
+	return rc;
+}
+
+/**
+ * smack_unix_may_send - Smack access on UDS
+ * @sock: one socket
+ * @other: the other socket
+ *
+ * Return 0 if a subject with the smack of sock could access
+ * an object with the smack of other, otherwise an error code
+ */
+static int smack_unix_may_send(struct socket *sock, struct socket *other)
+{
+	struct socket_smack *ssp = smack_sock(sock->sk);
+	struct socket_smack *osp = smack_sock(other->sk);
+	struct smk_audit_info ad;
+	int rc;
+
+#ifdef CONFIG_AUDIT
+	struct lsm_network_audit net;
+
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+	smk_ad_setfield_u_net_sk(&ad, other->sk);
+#endif
+
+	if (smack_privileged(CAP_MAC_OVERRIDE))
+		return 0;
+
+	rc = smk_access(ssp->smk_out, osp->smk_in, MAY_WRITE, &ad);
+	rc = smk_bu_note("UDS send", ssp->smk_out, osp->smk_in, MAY_WRITE, rc);
+	return rc;
+}
+
+/**
+ * smack_socket_sendmsg - Smack check based on destination host
+ * @sock: the socket
+ * @msg: the message
+ * @size: the size of the message
+ *
+ * Return 0 if the current subject can write to the destination host.
+ * For IPv4 this is only a question if the destination is a single label host.
+ * For IPv6 this is a check against the label of the port.
+ */
+static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg,
+				int size)
+{
+	struct sockaddr_in *sip = (struct sockaddr_in *) msg->msg_name;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct sockaddr_in6 *sap = (struct sockaddr_in6 *) msg->msg_name;
+#endif
+#ifdef SMACK_IPV6_SECMARK_LABELING
+	struct socket_smack *ssp = smack_sock(sock->sk);
+	struct smack_known *rsp;
+#endif
+	int rc = 0;
+
+	/*
+	 * Perfectly reasonable for this to be NULL
+	 */
+	if (sip == NULL)
+		return 0;
+
+	switch (sock->sk->sk_family) {
+	case AF_INET:
+		if (msg->msg_namelen < sizeof(struct sockaddr_in) ||
+		    sip->sin_family != AF_INET)
+			return -EINVAL;
+		rc = smk_ipv4_check(sock->sk, sip);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		if (msg->msg_namelen < SIN6_LEN_RFC2133 ||
+		    sap->sin6_family != AF_INET6)
+			return -EINVAL;
+#ifdef SMACK_IPV6_SECMARK_LABELING
+		rsp = smack_ipv6host_label(sap);
+		if (rsp != NULL)
+			rc = smk_ipv6_check(ssp->smk_out, rsp, sap,
+						SMK_CONNECTING);
+#endif
+#ifdef SMACK_IPV6_PORT_LABELING
+		rc = smk_ipv6_port_check(sock->sk, sap, SMK_SENDING);
+#endif
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+		break;
+	}
+	return rc;
+}
+
+/**
+ * smack_from_secattr - Convert a netlabel attr.mls.lvl/attr.mls.cat pair to smack
+ * @sap: netlabel secattr
+ * @ssp: socket security information
+ *
+ * Returns a pointer to a Smack label entry found on the label list.
+ */
+static struct smack_known *smack_from_secattr(struct netlbl_lsm_secattr *sap,
+						struct socket_smack *ssp)
+{
+	struct smack_known *skp;
+	int found = 0;
+	int acat;
+	int kcat;
+
+	/*
+	 * Netlabel found it in the cache.
+	 */
+	if ((sap->flags & NETLBL_SECATTR_CACHE) != 0)
+		return (struct smack_known *)sap->cache->data;
+
+	if ((sap->flags & NETLBL_SECATTR_SECID) != 0)
+		/*
+		 * Looks like a fallback, which gives us a secid.
+		 */
+		return smack_from_secid(sap->attr.secid);
+
+	if ((sap->flags & NETLBL_SECATTR_MLS_LVL) != 0) {
+		/*
+		 * Looks like a CIPSO packet.
+		 * If there are flags but no level netlabel isn't
+		 * behaving the way we expect it to.
+		 *
+		 * Look it up in the label table
+		 * Without guidance regarding the smack value
+		 * for the packet fall back on the network
+		 * ambient value.
+		 */
+		rcu_read_lock();
+		list_for_each_entry_rcu(skp, &smack_known_list, list) {
+			if (sap->attr.mls.lvl != skp->smk_netlabel.attr.mls.lvl)
+				continue;
+			/*
+			 * Compare the catsets. Use the netlbl APIs.
+			 */
+			if ((sap->flags & NETLBL_SECATTR_MLS_CAT) == 0) {
+				if ((skp->smk_netlabel.flags &
+				     NETLBL_SECATTR_MLS_CAT) == 0)
+					found = 1;
+				break;
+			}
+			for (acat = -1, kcat = -1; acat == kcat; ) {
+				acat = netlbl_catmap_walk(sap->attr.mls.cat,
+							  acat + 1);
+				kcat = netlbl_catmap_walk(
+					skp->smk_netlabel.attr.mls.cat,
+					kcat + 1);
+				if (acat < 0 || kcat < 0)
+					break;
+			}
+			if (acat == kcat) {
+				found = 1;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (found)
+			return skp;
+
+		if (ssp != NULL && ssp->smk_in == &smack_known_star)
+			return &smack_known_web;
+		return &smack_known_star;
+	}
+	/*
+	 * Without guidance regarding the smack value
+	 * for the packet fall back on the network
+	 * ambient value.
+	 */
+	return smack_net_ambient;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip)
+{
+	u8 nexthdr;
+	int offset;
+	int proto = -EINVAL;
+	struct ipv6hdr _ipv6h;
+	struct ipv6hdr *ip6;
+	__be16 frag_off;
+	struct tcphdr _tcph, *th;
+	struct udphdr _udph, *uh;
+
+	sip->sin6_port = 0;
+
+	offset = skb_network_offset(skb);
+	ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
+	if (ip6 == NULL)
+		return -EINVAL;
+	sip->sin6_addr = ip6->saddr;
+
+	nexthdr = ip6->nexthdr;
+	offset += sizeof(_ipv6h);
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+	if (offset < 0)
+		return -EINVAL;
+
+	proto = nexthdr;
+	switch (proto) {
+	case IPPROTO_TCP:
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th != NULL)
+			sip->sin6_port = th->source;
+		break;
+	case IPPROTO_UDP:
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh != NULL)
+			sip->sin6_port = uh->source;
+		break;
+	}
+	return proto;
+}
+#endif /* CONFIG_IPV6 */
+
+/**
+ * smack_from_skb - Smack data from the secmark in an skb
+ * @skb: packet
+ *
+ * Returns smack_known of the secmark or NULL if that won't work.
+ */
+#ifdef CONFIG_NETWORK_SECMARK
+static struct smack_known *smack_from_skb(struct sk_buff *skb)
+{
+	if (skb == NULL || skb->secmark == 0)
+		return NULL;
+
+	return smack_from_secid(skb->secmark);
+}
+#else
+static inline struct smack_known *smack_from_skb(struct sk_buff *skb)
+{
+	return NULL;
+}
+#endif
+
+/**
+ * smack_from_netlbl - Smack data from the IP options in an skb
+ * @sk: socket data came in on
+ * @family: address family
+ * @skb: packet
+ *
+ * Find the Smack label in the IP options. If it hasn't been
+ * added to the netlabel cache, add it here.
+ *
+ * Returns smack_known of the IP options or NULL if that won't work.
+ */
+static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family,
+					     struct sk_buff *skb)
+{
+	struct netlbl_lsm_secattr secattr;
+	struct socket_smack *ssp = NULL;
+	struct smack_known *skp = NULL;
+
+	netlbl_secattr_init(&secattr);
+
+	if (sk)
+		ssp = smack_sock(sk);
+
+	if (netlbl_skbuff_getattr(skb, family, &secattr) == 0) {
+		skp = smack_from_secattr(&secattr, ssp);
+		if (secattr.flags & NETLBL_SECATTR_CACHEABLE)
+			netlbl_cache_add(skb, family, &skp->smk_netlabel);
+	}
+
+	netlbl_secattr_destroy(&secattr);
+
+	return skp;
+}
+
+/**
+ * smack_socket_sock_rcv_skb - Smack packet delivery access check
+ * @sk: socket
+ * @skb: packet
+ *
+ * Returns 0 if the packet should be delivered, an error code otherwise
+ */
+static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct socket_smack *ssp = smack_sock(sk);
+	struct smack_known *skp = NULL;
+	int rc = 0;
+	struct smk_audit_info ad;
+	u16 family = sk->sk_family;
+#ifdef CONFIG_AUDIT
+	struct lsm_network_audit net;
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	struct sockaddr_in6 sadd;
+	int proto;
+
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
+#endif /* CONFIG_IPV6 */
+
+	switch (family) {
+	case PF_INET:
+		/*
+		 * If there is a secmark use it rather than the CIPSO label.
+		 * If there is no secmark fall back to CIPSO.
+		 * The secmark is assumed to reflect policy better.
+		 */
+		skp = smack_from_skb(skb);
+		if (skp == NULL) {
+			skp = smack_from_netlbl(sk, family, skb);
+			if (skp == NULL)
+				skp = smack_net_ambient;
+		}
+
+#ifdef CONFIG_AUDIT
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		ad.a.u.net->family = family;
+		ad.a.u.net->netif = skb->skb_iif;
+		ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
+		/*
+		 * Receiving a packet requires that the other end
+		 * be able to write here. Read access is not required.
+		 * This is the simplest possible security model
+		 * for networking.
+		 */
+		rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+		rc = smk_bu_note("IPv4 delivery", skp, ssp->smk_in,
+					MAY_WRITE, rc);
+		if (rc != 0)
+			netlbl_skbuff_err(skb, family, rc, 0);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case PF_INET6:
+		proto = smk_skb_to_addr_ipv6(skb, &sadd);
+		if (proto != IPPROTO_UDP && proto != IPPROTO_TCP)
+			break;
+#ifdef SMACK_IPV6_SECMARK_LABELING
+		skp = smack_from_skb(skb);
+		if (skp == NULL) {
+			if (smk_ipv6_localhost(&sadd))
+				break;
+			skp = smack_ipv6host_label(&sadd);
+			if (skp == NULL)
+				skp = smack_net_ambient;
+		}
+#ifdef CONFIG_AUDIT
+		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+		ad.a.u.net->family = family;
+		ad.a.u.net->netif = skb->skb_iif;
+		ipv6_skb_to_auditdata(skb, &ad.a, NULL);
+#endif /* CONFIG_AUDIT */
+		rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+		rc = smk_bu_note("IPv6 delivery", skp, ssp->smk_in,
+					MAY_WRITE, rc);
+#endif /* SMACK_IPV6_SECMARK_LABELING */
+#ifdef SMACK_IPV6_PORT_LABELING
+		rc = smk_ipv6_port_check(sk, &sadd, SMK_RECEIVING);
+#endif /* SMACK_IPV6_PORT_LABELING */
+		if (rc != 0)
+			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
+					ICMPV6_ADM_PROHIBITED, 0);
+		break;
+#endif /* CONFIG_IPV6 */
+	}
+
+	return rc;
+}
+
+/**
+ * smack_socket_getpeersec_stream - pull in packet label
+ * @sock: the socket
+ * @optval: user's destination
+ * @optlen: size thereof
+ * @len: max thereof
+ *
+ * returns zero on success, an error code otherwise
+ */
+static int smack_socket_getpeersec_stream(struct socket *sock,
+					  sockptr_t optval, sockptr_t optlen,
+					  unsigned int len)
+{
+	struct socket_smack *ssp;
+	char *rcp = "";
+	u32 slen = 1;
+	int rc = 0;
+
+	ssp = smack_sock(sock->sk);
+	if (ssp->smk_packet != NULL) {
+		rcp = ssp->smk_packet->smk_known;
+		slen = strlen(rcp) + 1;
+	}
+	if (slen > len) {
+		rc = -ERANGE;
+		goto out_len;
+	}
+
+	if (copy_to_sockptr(optval, rcp, slen))
+		rc = -EFAULT;
+out_len:
+	if (copy_to_sockptr(optlen, &slen, sizeof(slen)))
+		rc = -EFAULT;
+	return rc;
+}
+
+
+/**
+ * smack_socket_getpeersec_dgram - pull in packet label
+ * @sock: the peer socket
+ * @skb: packet data
+ * @secid: pointer to where to put the secid of the packet
+ *
+ * Sets the netlabel socket state on sk from parent
+ */
+static int smack_socket_getpeersec_dgram(struct socket *sock,
+					 struct sk_buff *skb, u32 *secid)
+
+{
+	struct socket_smack *ssp = NULL;
+	struct smack_known *skp;
+	struct sock *sk = NULL;
+	int family = PF_UNSPEC;
+	u32 s = 0;	/* 0 is the invalid secid */
+
+	if (skb != NULL) {
+		if (skb->protocol == htons(ETH_P_IP))
+			family = PF_INET;
+#if IS_ENABLED(CONFIG_IPV6)
+		else if (skb->protocol == htons(ETH_P_IPV6))
+			family = PF_INET6;
+#endif /* CONFIG_IPV6 */
+	}
+	if (family == PF_UNSPEC && sock != NULL)
+		family = sock->sk->sk_family;
+
+	switch (family) {
+	case PF_UNIX:
+		ssp = smack_sock(sock->sk);
+		s = ssp->smk_out->smk_secid;
+		break;
+	case PF_INET:
+		skp = smack_from_skb(skb);
+		if (skp) {
+			s = skp->smk_secid;
+			break;
+		}
+		/*
+		 * Translate what netlabel gave us.
+		 */
+		if (sock != NULL)
+			sk = sock->sk;
+		skp = smack_from_netlbl(sk, family, skb);
+		if (skp != NULL)
+			s = skp->smk_secid;
+		break;
+	case PF_INET6:
+#ifdef SMACK_IPV6_SECMARK_LABELING
+		skp = smack_from_skb(skb);
+		if (skp)
+			s = skp->smk_secid;
+#endif
+		break;
+	}
+	*secid = s;
+	if (s == 0)
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * smack_inet_conn_request - Smack access check on connect
+ * @sk: socket involved
+ * @skb: packet
+ * @req: unused
+ *
+ * Returns 0 if a task with the packet label could write to
+ * the socket, otherwise an error code
+ */
+static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+				   struct request_sock *req)
+{
+	u16 family = sk->sk_family;
+	struct smack_known *skp;
+	struct socket_smack *ssp = smack_sock(sk);
+	struct sockaddr_in addr;
+	struct iphdr *hdr;
+	struct smack_known *hskp;
+	int rc;
+	struct smk_audit_info ad;
+#ifdef CONFIG_AUDIT
+	struct lsm_network_audit net;
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (family == PF_INET6) {
+		/*
+		 * Handle mapped IPv4 packets arriving
+		 * via IPv6 sockets. Don't set up netlabel
+		 * processing on IPv6.
+		 */
+		if (skb->protocol == htons(ETH_P_IP))
+			family = PF_INET;
+		else
+			return 0;
+	}
+#endif /* CONFIG_IPV6 */
+
+	/*
+	 * If there is a secmark use it rather than the CIPSO label.
+	 * If there is no secmark fall back to CIPSO.
+	 * The secmark is assumed to reflect policy better.
+	 */
+	skp = smack_from_skb(skb);
+	if (skp == NULL) {
+		skp = smack_from_netlbl(sk, family, skb);
+		if (skp == NULL)
+			skp = &smack_known_huh;
+	}
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
+	ad.a.u.net->family = family;
+	ad.a.u.net->netif = skb->skb_iif;
+	ipv4_skb_to_auditdata(skb, &ad.a, NULL);
+#endif
+	/*
+	 * Receiving a packet requires that the other end be able to write
+	 * here. Read access is not required.
+	 */
+	rc = smk_access(skp, ssp->smk_in, MAY_WRITE, &ad);
+	rc = smk_bu_note("IPv4 connect", skp, ssp->smk_in, MAY_WRITE, rc);
+	if (rc != 0)
+		return rc;
+
+	/*
+	 * Save the peer's label in the request_sock so we can later setup
+	 * smk_packet in the child socket so that SO_PEERCRED can report it.
+	 */
+	req->peer_secid = skp->smk_secid;
+
+	/*
+	 * We need to decide if we want to label the incoming connection here
+	 * if we do we only need to label the request_sock and the stack will
+	 * propagate the wire-label to the sock when it is created.
+	 */
+	hdr = ip_hdr(skb);
+	addr.sin_addr.s_addr = hdr->saddr;
+	rcu_read_lock();
+	hskp = smack_ipv4host_label(&addr);
+	rcu_read_unlock();
+
+	if (hskp == NULL)
+		rc = netlbl_req_setattr(req, &ssp->smk_out->smk_netlabel);
+	else
+		netlbl_req_delattr(req);
+
+	return rc;
+}
+
+/**
+ * smack_inet_csk_clone - Copy the connection information to the new socket
+ * @sk: the new socket
+ * @req: the connection's request_sock
+ *
+ * Transfer the connection's peer label to the newly created socket.
+ */
+static void smack_inet_csk_clone(struct sock *sk,
+				 const struct request_sock *req)
+{
+	struct socket_smack *ssp = smack_sock(sk);
+	struct smack_known *skp;
+
+	if (req->peer_secid != 0) {
+		skp = smack_from_secid(req->peer_secid);
+		ssp->smk_packet = skp;
+	} else
+		ssp->smk_packet = NULL;
+}
+
+/*
+ * Key management security hooks
+ *
+ * Casey has not tested key support very heavily.
+ * The permission check is most likely too restrictive.
+ * If you care about keys please have a look.
+ */
+#ifdef CONFIG_KEYS
+
+/**
+ * smack_key_alloc - Set the key security blob
+ * @key: object
+ * @cred: the credentials to use
+ * @flags: unused
+ *
+ * No allocation required
+ *
+ * Returns 0
+ */
+static int smack_key_alloc(struct key *key, const struct cred *cred,
+			   unsigned long flags)
+{
+	struct smack_known **blob = smack_key(key);
+	struct smack_known *skp = smk_of_task(smack_cred(cred));
+
+	*blob = skp;
+	return 0;
+}
+
+/**
+ * smack_key_permission - Smack access on a key
+ * @key_ref: gets to the object
+ * @cred: the credentials to use
+ * @need_perm: requested key permission
+ *
+ * Return 0 if the task has read and write to the object,
+ * an error code otherwise
+ */
+static int smack_key_permission(key_ref_t key_ref,
+				const struct cred *cred,
+				enum key_need_perm need_perm)
+{
+	struct smack_known **blob;
+	struct smack_known *skp;
+	struct key *keyp;
+	struct smk_audit_info ad;
+	struct smack_known *tkp = smk_of_task(smack_cred(cred));
+	int request = 0;
+	int rc;
+
+	/*
+	 * Validate requested permissions
+	 */
+	switch (need_perm) {
+	case KEY_NEED_READ:
+	case KEY_NEED_SEARCH:
+	case KEY_NEED_VIEW:
+		request |= MAY_READ;
+		break;
+	case KEY_NEED_WRITE:
+	case KEY_NEED_LINK:
+	case KEY_NEED_SETATTR:
+		request |= MAY_WRITE;
+		break;
+	case KEY_NEED_UNSPECIFIED:
+	case KEY_NEED_UNLINK:
+	case KEY_SYSADMIN_OVERRIDE:
+	case KEY_AUTHTOKEN_OVERRIDE:
+	case KEY_DEFER_PERM_CHECK:
+		return 0;
+	default:
+		return -EINVAL;
+	}
+
+	keyp = key_ref_to_ptr(key_ref);
+	if (keyp == NULL)
+		return -EINVAL;
+	/*
+	 * If the key hasn't been initialized give it access so that
+	 * it may do so.
+	 */
+	blob = smack_key(keyp);
+	skp = *blob;
+	if (skp == NULL)
+		return 0;
+	/*
+	 * This should not occur
+	 */
+	if (tkp == NULL)
+		return -EACCES;
+
+	if (smack_privileged(CAP_MAC_OVERRIDE))
+		return 0;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_KEY);
+	ad.a.u.key_struct.key = keyp->serial;
+	ad.a.u.key_struct.key_desc = keyp->description;
+#endif
+	rc = smk_access(tkp, skp, request, &ad);
+	rc = smk_bu_note("key access", tkp, skp, request, rc);
+	return rc;
+}
+
+/*
+ * smack_key_getsecurity - Smack label tagging the key
+ * @key points to the key to be queried
+ * @_buffer points to a pointer that should be set to point to the
+ * resulting string (if no label or an error occurs).
+ * Return the length of the string (including terminating NUL) or -ve if
+ * an error.
+ * May also return 0 (and a NULL buffer pointer) if there is no label.
+ */
+static int smack_key_getsecurity(struct key *key, char **_buffer)
+{
+	struct smack_known **blob = smack_key(key);
+	struct smack_known *skp = *blob;
+	size_t length;
+	char *copy;
+
+	if (skp == NULL) {
+		*_buffer = NULL;
+		return 0;
+	}
+
+	copy = kstrdup(skp->smk_known, GFP_KERNEL);
+	if (copy == NULL)
+		return -ENOMEM;
+	length = strlen(copy) + 1;
+
+	*_buffer = copy;
+	return length;
+}
+
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+/**
+ * smack_watch_key - Smack access to watch a key for notifications.
+ * @key: The key to be watched
+ *
+ * Return 0 if the @watch->cred has permission to read from the key object and
+ * an error otherwise.
+ */
+static int smack_watch_key(struct key *key)
+{
+	struct smk_audit_info ad;
+	struct smack_known *tkp = smk_of_current();
+	struct smack_known **blob = smack_key(key);
+	int rc;
+
+	/*
+	 * This should not occur
+	 */
+	if (tkp == NULL)
+		return -EACCES;
+
+	if (smack_privileged_cred(CAP_MAC_OVERRIDE, current_cred()))
+		return 0;
+
+#ifdef CONFIG_AUDIT
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_KEY);
+	ad.a.u.key_struct.key = key->serial;
+	ad.a.u.key_struct.key_desc = key->description;
+#endif
+	rc = smk_access(tkp, *blob, MAY_READ, &ad);
+	rc = smk_bu_note("key watch", tkp, *blob, MAY_READ, rc);
+	return rc;
+}
+#endif /* CONFIG_KEY_NOTIFICATIONS */
+#endif /* CONFIG_KEYS */
+
+#ifdef CONFIG_WATCH_QUEUE
+/**
+ * smack_post_notification - Smack access to post a notification to a queue
+ * @w_cred: The credentials of the watcher.
+ * @cred: The credentials of the event source (may be NULL).
+ * @n: The notification message to be posted.
+ */
+static int smack_post_notification(const struct cred *w_cred,
+				   const struct cred *cred,
+				   struct watch_notification *n)
+{
+	struct smk_audit_info ad;
+	struct smack_known *subj, *obj;
+	int rc;
+
+	/* Always let maintenance notifications through. */
+	if (n->type == WATCH_TYPE_META)
+		return 0;
+
+	if (!cred)
+		return 0;
+	subj = smk_of_task(smack_cred(cred));
+	obj = smk_of_task(smack_cred(w_cred));
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NOTIFICATION);
+	rc = smk_access(subj, obj, MAY_WRITE, &ad);
+	rc = smk_bu_note("notification", subj, obj, MAY_WRITE, rc);
+	return rc;
+}
+#endif /* CONFIG_WATCH_QUEUE */
+
+/*
+ * Smack Audit hooks
+ *
+ * Audit requires a unique representation of each Smack specific
+ * rule. This unique representation is used to distinguish the
+ * object to be audited from remaining kernel objects and also
+ * works as a glue between the audit hooks.
+ *
+ * Since repository entries are added but never deleted, we'll use
+ * the smack_known label address related to the given audit rule as
+ * the needed unique representation. This also better fits the smack
+ * model where nearly everything is a label.
+ */
+#ifdef CONFIG_AUDIT
+
+/**
+ * smack_audit_rule_init - Initialize a smack audit rule
+ * @field: audit rule fields given from user-space (audit.h)
+ * @op: required testing operator (=, !=, >, <, ...)
+ * @rulestr: smack label to be audited
+ * @vrule: pointer to save our own audit rule representation
+ * @gfp: type of the memory for the allocation
+ *
+ * Prepare to audit cases where (@field @op @rulestr) is true.
+ * The label to be audited is created if necessary.
+ */
+static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule,
+				 gfp_t gfp)
+{
+	struct smack_known *skp;
+	char **rule = (char **)vrule;
+	*rule = NULL;
+
+	if (field != AUDIT_SUBJ_USER && field != AUDIT_OBJ_USER)
+		return -EINVAL;
+
+	if (op != Audit_equal && op != Audit_not_equal)
+		return -EINVAL;
+
+	skp = smk_import_entry(rulestr, 0);
+	if (IS_ERR(skp))
+		return PTR_ERR(skp);
+
+	*rule = skp->smk_known;
+
+	return 0;
+}
+
+/**
+ * smack_audit_rule_known - Distinguish Smack audit rules
+ * @krule: rule of interest, in Audit kernel representation format
+ *
+ * This is used to filter Smack rules from remaining Audit ones.
+ * If it's proved that this rule belongs to us, the
+ * audit_rule_match hook will be called to do the final judgement.
+ */
+static int smack_audit_rule_known(struct audit_krule *krule)
+{
+	struct audit_field *f;
+	int i;
+
+	for (i = 0; i < krule->field_count; i++) {
+		f = &krule->fields[i];
+
+		if (f->type == AUDIT_SUBJ_USER || f->type == AUDIT_OBJ_USER)
+			return 1;
+	}
+
+	return 0;
+}
+
+/**
+ * smack_audit_rule_match - Audit given object ?
+ * @prop: security id for identifying the object to test
+ * @field: audit rule flags given from user-space
+ * @op: required testing operator
+ * @vrule: smack internal rule presentation
+ *
+ * The core Audit hook. It's used to take the decision of
+ * whether to audit or not to audit a given object.
+ */
+static int smack_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op,
+				  void *vrule)
+{
+	struct smack_known *skp = prop->smack.skp;
+	char *rule = vrule;
+
+	if (unlikely(!rule)) {
+		WARN_ONCE(1, "Smack: missing rule\n");
+		return -ENOENT;
+	}
+
+	if (field != AUDIT_SUBJ_USER && field != AUDIT_OBJ_USER)
+		return 0;
+
+	/*
+	 * No need to do string comparisons. If a match occurs,
+	 * both pointers will point to the same smack_known
+	 * label.
+	 */
+	if (op == Audit_equal)
+		return (rule == skp->smk_known);
+	if (op == Audit_not_equal)
+		return (rule != skp->smk_known);
+
+	return 0;
+}
+
+/*
+ * There is no need for a smack_audit_rule_free hook.
+ * No memory was allocated.
+ */
+
+#endif /* CONFIG_AUDIT */
+
+/**
+ * smack_ismaclabel - check if xattr @name references a smack MAC label
+ * @name: Full xattr name to check.
+ */
+static int smack_ismaclabel(const char *name)
+{
+	return (strcmp(name, XATTR_SMACK_SUFFIX) == 0);
+}
+
+/**
+ * smack_to_secctx - fill a lsm_context
+ * @skp: Smack label
+ * @cp: destination
+ *
+ * Fill the passed @cp and return the length of the string
+ */
+static int smack_to_secctx(struct smack_known *skp, struct lsm_context *cp)
+{
+	int len = strlen(skp->smk_known);
+
+	if (cp) {
+		cp->context = skp->smk_known;
+		cp->len = len;
+		cp->id = LSM_ID_SMACK;
+	}
+	return len;
+}
+
+/**
+ * smack_secid_to_secctx - return the smack label for a secid
+ * @secid: incoming integer
+ * @cp: destination
+ *
+ * Exists for networking code.
+ */
+static int smack_secid_to_secctx(u32 secid, struct lsm_context *cp)
+{
+	return smack_to_secctx(smack_from_secid(secid), cp);
+}
+
+/**
+ * smack_lsmprop_to_secctx - return the smack label
+ * @prop: includes incoming Smack data
+ * @cp: destination
+ *
+ * Exists for audit code.
+ */
+static int smack_lsmprop_to_secctx(struct lsm_prop *prop,
+				   struct lsm_context *cp)
+{
+	return smack_to_secctx(prop->smack.skp, cp);
+}
+
+/**
+ * smack_secctx_to_secid - return the secid for a smack label
+ * @secdata: smack label
+ * @seclen: how long result is
+ * @secid: outgoing integer
+ *
+ * Exists for audit and networking code.
+ */
+static int smack_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
+{
+	struct smack_known *skp = smk_find_entry(secdata);
+
+	if (skp)
+		*secid = skp->smk_secid;
+	else
+		*secid = 0;
+	return 0;
+}
+
+/*
+ * There used to be a smack_release_secctx hook
+ * that did nothing back when hooks were in a vector.
+ * Now that there's a list such a hook adds cost.
+ */
+
+static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
+{
+	/*
+	 * UDS inode has fixed label. Ignore nfs label.
+	 */
+	if (S_ISSOCK(inode->i_mode))
+		return 0;
+	return smack_inode_setsecurity(inode, XATTR_SMACK_SUFFIX, ctx,
+				       ctxlen, 0);
+}
+
+static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
+{
+	return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK,
+				     ctx, ctxlen, 0, NULL);
+}
+
+static int smack_inode_getsecctx(struct inode *inode, struct lsm_context *cp)
+{
+	struct smack_known *skp = smk_of_inode(inode);
+
+	cp->context = skp->smk_known;
+	cp->len = strlen(skp->smk_known);
+	cp->id = LSM_ID_SMACK;
+	return 0;
+}
+
+static int smack_inode_copy_up(struct dentry *dentry, struct cred **new)
+{
+
+	struct task_smack *tsp;
+	struct smack_known *skp;
+	struct inode_smack *isp;
+	struct cred *new_creds = *new;
+
+	if (new_creds == NULL) {
+		new_creds = prepare_creds();
+		if (new_creds == NULL)
+			return -ENOMEM;
+	}
+
+	tsp = smack_cred(new_creds);
+
+	/*
+	 * Get label from overlay inode and set it in create_sid
+	 */
+	isp = smack_inode(d_inode(dentry));
+	skp = isp->smk_inode;
+	tsp->smk_task = skp;
+	*new = new_creds;
+	return 0;
+}
+
+static int smack_inode_copy_up_xattr(struct dentry *src, const char *name)
+{
+	/*
+	 * Return -ECANCELED if this is the smack access Smack attribute.
+	 */
+	if (!strcmp(name, XATTR_NAME_SMACK))
+		return -ECANCELED;
+
+	return -EOPNOTSUPP;
+}
+
+static int smack_dentry_create_files_as(struct dentry *dentry, int mode,
+					const struct qstr *name,
+					const struct cred *old,
+					struct cred *new)
+{
+	struct task_smack *otsp = smack_cred(old);
+	struct task_smack *ntsp = smack_cred(new);
+	struct inode_smack *isp;
+
+	/*
+	 * Use the process credential unless all of
+	 * the transmuting criteria are met
+	 */
+	ntsp->smk_task = otsp->smk_task;
+
+	/*
+	 * the attribute of the containing directory
+	 */
+	isp = smack_inode(d_inode(dentry->d_parent));
+
+	if (isp->smk_flags & SMK_INODE_TRANSMUTE) {
+		/*
+		 * If the directory is transmuting and the rule
+		 * providing access is transmuting use the containing
+		 * directory label instead of the process label.
+		 */
+		if (smk_rule_transmutes(otsp->smk_task, isp->smk_inode)) {
+			ntsp->smk_task = isp->smk_inode;
+			ntsp->smk_transmuted = ntsp->smk_task;
+		}
+	}
+	return 0;
+}
+
+#ifdef CONFIG_IO_URING
+/**
+ * smack_uring_override_creds - Is io_uring cred override allowed?
+ * @new: the target creds
+ *
+ * Check to see if the current task is allowed to override it's credentials
+ * to service an io_uring operation.
+ */
+static int smack_uring_override_creds(const struct cred *new)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+	struct task_smack *nsp = smack_cred(new);
+
+	/*
+	 * Allow the degenerate case where the new Smack value is
+	 * the same as the current Smack value.
+	 */
+	if (tsp->smk_task == nsp->smk_task)
+		return 0;
+
+	if (smack_privileged_cred(CAP_MAC_OVERRIDE, current_cred()))
+		return 0;
+
+	return -EPERM;
+}
+
+/**
+ * smack_uring_sqpoll - check if a io_uring polling thread can be created
+ *
+ * Check to see if the current task is allowed to create a new io_uring
+ * kernel polling thread.
+ */
+static int smack_uring_sqpoll(void)
+{
+	if (smack_privileged_cred(CAP_MAC_ADMIN, current_cred()))
+		return 0;
+
+	return -EPERM;
+}
+
+/**
+ * smack_uring_cmd - check on file operations for io_uring
+ * @ioucmd: the command in question
+ *
+ * Make a best guess about whether a io_uring "command" should
+ * be allowed. Use the same logic used for determining if the
+ * file could be opened for read in the absence of better criteria.
+ */
+static int smack_uring_cmd(struct io_uring_cmd *ioucmd)
+{
+	struct file *file = ioucmd->file;
+	struct smk_audit_info ad;
+	struct task_smack *tsp;
+	struct inode *inode;
+	int rc;
+
+	if (!file)
+		return -EINVAL;
+
+	tsp = smack_cred(file->f_cred);
+	inode = file_inode(file);
+
+	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
+	smk_ad_setfield_u_fs_path(&ad, file->f_path);
+	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
+
+	return rc;
+}
+
+#endif /* CONFIG_IO_URING */
+
+struct lsm_blob_sizes smack_blob_sizes __ro_after_init = {
+	.lbs_cred = sizeof(struct task_smack),
+	.lbs_file = sizeof(struct smack_known *),
+	.lbs_inode = sizeof(struct inode_smack),
+	.lbs_ipc = sizeof(struct smack_known *),
+	.lbs_key = sizeof(struct smack_known *),
+	.lbs_msg_msg = sizeof(struct smack_known *),
+	.lbs_sock = sizeof(struct socket_smack),
+	.lbs_superblock = sizeof(struct superblock_smack),
+	.lbs_xattr_count = SMACK_INODE_INIT_XATTRS,
+};
+
+static const struct lsm_id smack_lsmid = {
+	.name = "smack",
+	.id = LSM_ID_SMACK,
+};
+
+static struct security_hook_list smack_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(ptrace_access_check, smack_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, smack_ptrace_traceme),
+	LSM_HOOK_INIT(syslog, smack_syslog),
+
+	LSM_HOOK_INIT(fs_context_submount, smack_fs_context_submount),
+	LSM_HOOK_INIT(fs_context_dup, smack_fs_context_dup),
+	LSM_HOOK_INIT(fs_context_parse_param, smack_fs_context_parse_param),
+
+	LSM_HOOK_INIT(sb_alloc_security, smack_sb_alloc_security),
+	LSM_HOOK_INIT(sb_free_mnt_opts, smack_free_mnt_opts),
+	LSM_HOOK_INIT(sb_eat_lsm_opts, smack_sb_eat_lsm_opts),
+	LSM_HOOK_INIT(sb_statfs, smack_sb_statfs),
+	LSM_HOOK_INIT(sb_set_mnt_opts, smack_set_mnt_opts),
+
+	LSM_HOOK_INIT(bprm_creds_for_exec, smack_bprm_creds_for_exec),
+
+	LSM_HOOK_INIT(inode_alloc_security, smack_inode_alloc_security),
+	LSM_HOOK_INIT(inode_init_security, smack_inode_init_security),
+	LSM_HOOK_INIT(inode_link, smack_inode_link),
+	LSM_HOOK_INIT(inode_unlink, smack_inode_unlink),
+	LSM_HOOK_INIT(inode_rmdir, smack_inode_rmdir),
+	LSM_HOOK_INIT(inode_rename, smack_inode_rename),
+	LSM_HOOK_INIT(inode_permission, smack_inode_permission),
+	LSM_HOOK_INIT(inode_setattr, smack_inode_setattr),
+	LSM_HOOK_INIT(inode_getattr, smack_inode_getattr),
+	LSM_HOOK_INIT(inode_xattr_skipcap, smack_inode_xattr_skipcap),
+	LSM_HOOK_INIT(inode_setxattr, smack_inode_setxattr),
+	LSM_HOOK_INIT(inode_post_setxattr, smack_inode_post_setxattr),
+	LSM_HOOK_INIT(inode_getxattr, smack_inode_getxattr),
+	LSM_HOOK_INIT(inode_removexattr, smack_inode_removexattr),
+	LSM_HOOK_INIT(inode_set_acl, smack_inode_set_acl),
+	LSM_HOOK_INIT(inode_get_acl, smack_inode_get_acl),
+	LSM_HOOK_INIT(inode_remove_acl, smack_inode_remove_acl),
+	LSM_HOOK_INIT(inode_getsecurity, smack_inode_getsecurity),
+	LSM_HOOK_INIT(inode_setsecurity, smack_inode_setsecurity),
+	LSM_HOOK_INIT(inode_listsecurity, smack_inode_listsecurity),
+	LSM_HOOK_INIT(inode_getlsmprop, smack_inode_getlsmprop),
+
+	LSM_HOOK_INIT(file_alloc_security, smack_file_alloc_security),
+	LSM_HOOK_INIT(file_ioctl, smack_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, smack_file_ioctl),
+	LSM_HOOK_INIT(file_lock, smack_file_lock),
+	LSM_HOOK_INIT(file_fcntl, smack_file_fcntl),
+	LSM_HOOK_INIT(mmap_file, smack_mmap_file),
+	LSM_HOOK_INIT(mmap_addr, cap_mmap_addr),
+	LSM_HOOK_INIT(file_set_fowner, smack_file_set_fowner),
+	LSM_HOOK_INIT(file_send_sigiotask, smack_file_send_sigiotask),
+	LSM_HOOK_INIT(file_receive, smack_file_receive),
+
+	LSM_HOOK_INIT(file_open, smack_file_open),
+
+	LSM_HOOK_INIT(cred_alloc_blank, smack_cred_alloc_blank),
+	LSM_HOOK_INIT(cred_free, smack_cred_free),
+	LSM_HOOK_INIT(cred_prepare, smack_cred_prepare),
+	LSM_HOOK_INIT(cred_transfer, smack_cred_transfer),
+	LSM_HOOK_INIT(cred_getsecid, smack_cred_getsecid),
+	LSM_HOOK_INIT(cred_getlsmprop, smack_cred_getlsmprop),
+	LSM_HOOK_INIT(kernel_act_as, smack_kernel_act_as),
+	LSM_HOOK_INIT(kernel_create_files_as, smack_kernel_create_files_as),
+	LSM_HOOK_INIT(task_setpgid, smack_task_setpgid),
+	LSM_HOOK_INIT(task_getpgid, smack_task_getpgid),
+	LSM_HOOK_INIT(task_getsid, smack_task_getsid),
+	LSM_HOOK_INIT(current_getlsmprop_subj, smack_current_getlsmprop_subj),
+	LSM_HOOK_INIT(task_getlsmprop_obj, smack_task_getlsmprop_obj),
+	LSM_HOOK_INIT(task_setnice, smack_task_setnice),
+	LSM_HOOK_INIT(task_setioprio, smack_task_setioprio),
+	LSM_HOOK_INIT(task_getioprio, smack_task_getioprio),
+	LSM_HOOK_INIT(task_setscheduler, smack_task_setscheduler),
+	LSM_HOOK_INIT(task_getscheduler, smack_task_getscheduler),
+	LSM_HOOK_INIT(task_movememory, smack_task_movememory),
+	LSM_HOOK_INIT(task_kill, smack_task_kill),
+	LSM_HOOK_INIT(task_to_inode, smack_task_to_inode),
+
+	LSM_HOOK_INIT(ipc_permission, smack_ipc_permission),
+	LSM_HOOK_INIT(ipc_getlsmprop, smack_ipc_getlsmprop),
+
+	LSM_HOOK_INIT(msg_msg_alloc_security, smack_msg_msg_alloc_security),
+
+	LSM_HOOK_INIT(msg_queue_alloc_security, smack_ipc_alloc_security),
+	LSM_HOOK_INIT(msg_queue_associate, smack_msg_queue_associate),
+	LSM_HOOK_INIT(msg_queue_msgctl, smack_msg_queue_msgctl),
+	LSM_HOOK_INIT(msg_queue_msgsnd, smack_msg_queue_msgsnd),
+	LSM_HOOK_INIT(msg_queue_msgrcv, smack_msg_queue_msgrcv),
+
+	LSM_HOOK_INIT(shm_alloc_security, smack_ipc_alloc_security),
+	LSM_HOOK_INIT(shm_associate, smack_shm_associate),
+	LSM_HOOK_INIT(shm_shmctl, smack_shm_shmctl),
+	LSM_HOOK_INIT(shm_shmat, smack_shm_shmat),
+
+	LSM_HOOK_INIT(sem_alloc_security, smack_ipc_alloc_security),
+	LSM_HOOK_INIT(sem_associate, smack_sem_associate),
+	LSM_HOOK_INIT(sem_semctl, smack_sem_semctl),
+	LSM_HOOK_INIT(sem_semop, smack_sem_semop),
+
+	LSM_HOOK_INIT(d_instantiate, smack_d_instantiate),
+
+	LSM_HOOK_INIT(getselfattr, smack_getselfattr),
+	LSM_HOOK_INIT(setselfattr, smack_setselfattr),
+	LSM_HOOK_INIT(getprocattr, smack_getprocattr),
+	LSM_HOOK_INIT(setprocattr, smack_setprocattr),
+
+	LSM_HOOK_INIT(unix_stream_connect, smack_unix_stream_connect),
+	LSM_HOOK_INIT(unix_may_send, smack_unix_may_send),
+
+	LSM_HOOK_INIT(socket_post_create, smack_socket_post_create),
+	LSM_HOOK_INIT(socket_socketpair, smack_socket_socketpair),
+#ifdef SMACK_IPV6_PORT_LABELING
+	LSM_HOOK_INIT(socket_bind, smack_socket_bind),
+#endif
+	LSM_HOOK_INIT(socket_connect, smack_socket_connect),
+	LSM_HOOK_INIT(socket_sendmsg, smack_socket_sendmsg),
+	LSM_HOOK_INIT(socket_sock_rcv_skb, smack_socket_sock_rcv_skb),
+	LSM_HOOK_INIT(socket_getpeersec_stream, smack_socket_getpeersec_stream),
+	LSM_HOOK_INIT(socket_getpeersec_dgram, smack_socket_getpeersec_dgram),
+	LSM_HOOK_INIT(sk_alloc_security, smack_sk_alloc_security),
+#ifdef SMACK_IPV6_PORT_LABELING
+	LSM_HOOK_INIT(sk_free_security, smack_sk_free_security),
+#endif
+	LSM_HOOK_INIT(sk_clone_security, smack_sk_clone_security),
+	LSM_HOOK_INIT(inet_conn_request, smack_inet_conn_request),
+	LSM_HOOK_INIT(inet_csk_clone, smack_inet_csk_clone),
+
+ /* key management security hooks */
+#ifdef CONFIG_KEYS
+	LSM_HOOK_INIT(key_alloc, smack_key_alloc),
+	LSM_HOOK_INIT(key_permission, smack_key_permission),
+	LSM_HOOK_INIT(key_getsecurity, smack_key_getsecurity),
+#ifdef CONFIG_KEY_NOTIFICATIONS
+	LSM_HOOK_INIT(watch_key, smack_watch_key),
+#endif
+#endif /* CONFIG_KEYS */
+
+#ifdef CONFIG_WATCH_QUEUE
+	LSM_HOOK_INIT(post_notification, smack_post_notification),
+#endif
+
+ /* Audit hooks */
+#ifdef CONFIG_AUDIT
+	LSM_HOOK_INIT(audit_rule_init, smack_audit_rule_init),
+	LSM_HOOK_INIT(audit_rule_known, smack_audit_rule_known),
+	LSM_HOOK_INIT(audit_rule_match, smack_audit_rule_match),
+#endif /* CONFIG_AUDIT */
+
+	LSM_HOOK_INIT(ismaclabel, smack_ismaclabel),
+	LSM_HOOK_INIT(secid_to_secctx, smack_secid_to_secctx),
+	LSM_HOOK_INIT(lsmprop_to_secctx, smack_lsmprop_to_secctx),
+	LSM_HOOK_INIT(secctx_to_secid, smack_secctx_to_secid),
+	LSM_HOOK_INIT(inode_notifysecctx, smack_inode_notifysecctx),
+	LSM_HOOK_INIT(inode_setsecctx, smack_inode_setsecctx),
+	LSM_HOOK_INIT(inode_getsecctx, smack_inode_getsecctx),
+	LSM_HOOK_INIT(inode_copy_up, smack_inode_copy_up),
+	LSM_HOOK_INIT(inode_copy_up_xattr, smack_inode_copy_up_xattr),
+	LSM_HOOK_INIT(dentry_create_files_as, smack_dentry_create_files_as),
+#ifdef CONFIG_IO_URING
+	LSM_HOOK_INIT(uring_override_creds, smack_uring_override_creds),
+	LSM_HOOK_INIT(uring_sqpoll, smack_uring_sqpoll),
+	LSM_HOOK_INIT(uring_cmd, smack_uring_cmd),
+#endif
+};
+
+
+static __init void init_smack_known_list(void)
+{
+	/*
+	 * Initialize rule list locks
+	 */
+	mutex_init(&smack_known_huh.smk_rules_lock);
+	mutex_init(&smack_known_hat.smk_rules_lock);
+	mutex_init(&smack_known_floor.smk_rules_lock);
+	mutex_init(&smack_known_star.smk_rules_lock);
+	mutex_init(&smack_known_web.smk_rules_lock);
+	/*
+	 * Initialize rule lists
+	 */
+	INIT_LIST_HEAD(&smack_known_huh.smk_rules);
+	INIT_LIST_HEAD(&smack_known_hat.smk_rules);
+	INIT_LIST_HEAD(&smack_known_star.smk_rules);
+	INIT_LIST_HEAD(&smack_known_floor.smk_rules);
+	INIT_LIST_HEAD(&smack_known_web.smk_rules);
+	/*
+	 * Create the known labels list
+	 */
+	smk_insert_entry(&smack_known_huh);
+	smk_insert_entry(&smack_known_hat);
+	smk_insert_entry(&smack_known_star);
+	smk_insert_entry(&smack_known_floor);
+	smk_insert_entry(&smack_known_web);
+}
+
+/**
+ * smack_init - initialize the smack system
+ *
+ * Returns 0 on success, -ENOMEM is there's no memory
+ */
+static __init int smack_init(void)
+{
+	struct cred *cred = (struct cred *) current->cred;
+	struct task_smack *tsp;
+
+	smack_rule_cache = KMEM_CACHE(smack_rule, 0);
+	if (!smack_rule_cache)
+		return -ENOMEM;
+
+	/*
+	 * Set the security state for the initial task.
+	 */
+	tsp = smack_cred(cred);
+	init_task_smack(tsp, &smack_known_floor, &smack_known_floor);
+
+	/*
+	 * Register with LSM
+	 */
+	security_add_hooks(smack_hooks, ARRAY_SIZE(smack_hooks), &smack_lsmid);
+	smack_enabled = 1;
+
+	pr_info("Smack:  Initializing.\n");
+#ifdef CONFIG_SECURITY_SMACK_NETFILTER
+	pr_info("Smack:  Netfilter enabled.\n");
+#endif
+#ifdef SMACK_IPV6_PORT_LABELING
+	pr_info("Smack:  IPv6 port labeling enabled.\n");
+#endif
+#ifdef SMACK_IPV6_SECMARK_LABELING
+	pr_info("Smack:  IPv6 Netfilter enabled.\n");
+#endif
+
+	/* initialize the smack_known_list */
+	init_smack_known_list();
+
+	/* Inform the audit system that secctx is used */
+	audit_cfg_lsm(&smack_lsmid,
+		      AUDIT_CFG_LSM_SECCTX_SUBJECT |
+		      AUDIT_CFG_LSM_SECCTX_OBJECT);
+
+	return 0;
+}
+
+int __init smack_initcall(void)
+{
+	int rc_fs = init_smk_fs();
+	int rc_nf = smack_nf_ip_init();
+
+	return rc_fs ? rc_fs : rc_nf;
+}
+
+/*
+ * Smack requires early initialization in order to label
+ * all processes and objects when they are created.
+ */
+DEFINE_LSM(smack) = {
+	.id = &smack_lsmid,
+	.flags = LSM_FLAG_LEGACY_MAJOR | LSM_FLAG_EXCLUSIVE,
+	.blobs = &smack_blob_sizes,
+	.init = smack_init,
+	.initcall_device = smack_initcall,
+};
diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c
new file mode 100644
index 000000000..17ba578b1
--- /dev/null
+++ b/security/smack/smack_netfilter.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Simplified MAC Kernel (smack) security module
+ *
+ *  This file contains the Smack netfilter implementation
+ *
+ *  Author:
+ *	Casey Schaufler <casey@schaufler-ca.com>
+ *
+ *  Copyright (C) 2014 Casey Schaufler <casey@schaufler-ca.com>
+ *  Copyright (C) 2014 Intel Corporation.
+ */
+
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netdevice.h>
+#include <net/inet_sock.h>
+#include <net/net_namespace.h>
+#include "smack.h"
+
+static unsigned int smack_ip_output(void *priv,
+				    struct sk_buff *skb,
+				    const struct nf_hook_state *state)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+	struct socket_smack *ssp;
+	struct smack_known *skp;
+
+	if (sk) {
+		ssp = smack_sock(sk);
+		skp = ssp->smk_out;
+		skb->secmark = skp->smk_secid;
+	}
+
+	return NF_ACCEPT;
+}
+
+static const struct nf_hook_ops smack_nf_ops[] = {
+	{
+		.hook =		smack_ip_output,
+		.pf =		NFPROTO_IPV4,
+		.hooknum =	NF_INET_LOCAL_OUT,
+		.priority =	NF_IP_PRI_SELINUX_FIRST,
+	},
+#if IS_ENABLED(CONFIG_IPV6)
+	{
+		.hook =		smack_ip_output,
+		.pf =		NFPROTO_IPV6,
+		.hooknum =	NF_INET_LOCAL_OUT,
+		.priority =	NF_IP6_PRI_SELINUX_FIRST,
+	},
+#endif	/* IPV6 */
+};
+
+static int __net_init smack_nf_register(struct net *net)
+{
+	return nf_register_net_hooks(net, smack_nf_ops,
+				     ARRAY_SIZE(smack_nf_ops));
+}
+
+static void __net_exit smack_nf_unregister(struct net *net)
+{
+	nf_unregister_net_hooks(net, smack_nf_ops, ARRAY_SIZE(smack_nf_ops));
+}
+
+static struct pernet_operations smack_net_ops = {
+	.init = smack_nf_register,
+	.exit = smack_nf_unregister,
+};
+
+int __init smack_nf_ip_init(void)
+{
+	if (smack_enabled == 0)
+		return 0;
+
+	printk(KERN_DEBUG "Smack: Registering netfilter hooks\n");
+	return register_pernet_subsys(&smack_net_ops);
+}
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
new file mode 100644
index 000000000..a72bc7fab
--- /dev/null
+++ b/security/smack/smackfs.c
@@ -0,0 +1,2954 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2007 Casey Schaufler <casey@schaufler-ca.com>
+ *
+ * Authors:
+ * 	Casey Schaufler <casey@schaufler-ca.com>
+ * 	Ahmed S. Darwish <darwish.07@gmail.com>
+ *
+ * Special thanks to the authors of selinuxfs.
+ *
+ *	Karl MacMillan <kmacmillan@tresys.com>
+ *	James Morris <jmorris@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/vmalloc.h>
+#include <linux/security.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <net/net_namespace.h>
+#include <net/cipso_ipv4.h>
+#include <linux/seq_file.h>
+#include <linux/ctype.h>
+#include <linux/audit.h>
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/fs_context.h>
+#include "smack.h"
+
+#define BEBITS	(sizeof(__be32) * 8)
+/*
+ * smackfs pseudo filesystem.
+ */
+
+enum smk_inos {
+	SMK_ROOT_INO	= 2,
+	SMK_LOAD	= 3,	/* load policy */
+	SMK_CIPSO	= 4,	/* load label -> CIPSO mapping */
+	SMK_DOI		= 5,	/* CIPSO DOI */
+	SMK_DIRECT	= 6,	/* CIPSO level indicating direct label */
+	SMK_AMBIENT	= 7,	/* internet ambient label */
+	SMK_NET4ADDR	= 8,	/* single label hosts */
+	SMK_ONLYCAP	= 9,	/* the only "capable" label */
+#ifdef CONFIG_AUDIT
+	SMK_LOGGING	= 10,	/* logging */
+#endif /* CONFIG_AUDIT */
+	SMK_LOAD_SELF	= 11,	/* task specific rules */
+	SMK_ACCESSES	= 12,	/* access policy */
+	SMK_MAPPED	= 13,	/* CIPSO level indicating mapped label */
+	SMK_LOAD2	= 14,	/* load policy with long labels */
+	SMK_LOAD_SELF2	= 15,	/* load task specific rules with long labels */
+	SMK_ACCESS2	= 16,	/* make an access check with long labels */
+	SMK_CIPSO2	= 17,	/* load long label -> CIPSO mapping */
+	SMK_REVOKE_SUBJ	= 18,	/* set rules with subject label to '-' */
+	SMK_CHANGE_RULE	= 19,	/* change or add rules (long labels) */
+	SMK_SYSLOG	= 20,	/* change syslog label) */
+	SMK_PTRACE	= 21,	/* set ptrace rule */
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+	SMK_UNCONFINED	= 22,	/* define an unconfined label */
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	SMK_NET6ADDR	= 23,	/* single label IPv6 hosts */
+#endif /* CONFIG_IPV6 */
+	SMK_RELABEL_SELF = 24, /* relabel possible without CAP_MAC_ADMIN */
+};
+
+/*
+ * List locks
+ */
+static DEFINE_MUTEX(smack_cipso_lock);
+static DEFINE_MUTEX(smack_ambient_lock);
+static DEFINE_MUTEX(smk_net4addr_lock);
+static DEFINE_MUTEX(smk_cipso_doi_lock);
+#if IS_ENABLED(CONFIG_IPV6)
+static DEFINE_MUTEX(smk_net6addr_lock);
+#endif /* CONFIG_IPV6 */
+
+/*
+ * This is the "ambient" label for network traffic.
+ * If it isn't somehow marked, use this.
+ * It can be reset via smackfs/ambient
+ */
+struct smack_known *smack_net_ambient;
+
+/*
+ * Sensitivity levels for automatically created CIPSO labels.
+ * See smack_access.c`smack_populate_secattr()
+ *
+ * [0] "direct" labeling, label length < SMK_CIPSOLEN(24):
+ * smack label is contained directly in the category set.
+ * It can be reset via smackfs/direct
+ *
+ * [1] "mapped" labeling, label length >= SMK_CIPSOLEN(24):
+ * secid is contained directly in the category set.
+ * It can be reset via smackfs/mapped
+ */
+u8 smack_cipso_auto_level[2] = {
+	SMACK_CIPSO_DIRECT_DEFAULT,
+	SMACK_CIPSO_MAPPED_DEFAULT,
+};
+
+static int
+smk_cipso_auto_level_idx(const struct file *file)
+{
+	return (file_inode(file)->i_ino != SMK_DIRECT);
+}
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+/*
+ * Allow one label to be unconfined. This is for
+ * debugging and application bring-up purposes only.
+ * It is bad and wrong, but everyone seems to expect
+ * to have it.
+ */
+struct smack_known *smack_unconfined;
+#endif
+
+/*
+ * If this value is set restrict syslog use to the label specified.
+ * It can be reset via smackfs/syslog
+ */
+struct smack_known *smack_syslog_label;
+
+/*
+ * Ptrace current rule
+ * SMACK_PTRACE_DEFAULT    regular smack ptrace rules (/proc based)
+ * SMACK_PTRACE_EXACT      labels must match, but can be overridden with
+ *			   CAP_SYS_PTRACE
+ * SMACK_PTRACE_DRACONIAN  labels must match, CAP_SYS_PTRACE has no effect
+ */
+int smack_ptrace_rule = SMACK_PTRACE_DEFAULT;
+
+/*
+ * Certain IP addresses may be designated as single label hosts.
+ * Packets are sent there unlabeled, but only from tasks that
+ * can write to the specified label.
+ */
+
+LIST_HEAD(smk_net4addr_list);
+#if IS_ENABLED(CONFIG_IPV6)
+LIST_HEAD(smk_net6addr_list);
+#endif /* CONFIG_IPV6 */
+
+/*
+ * Rule lists are maintained for each label.
+ */
+struct smack_parsed_rule {
+	struct smack_known	*smk_subject;
+	struct smack_known	*smk_object;
+	int			smk_access1;
+	int			smk_access2;
+};
+
+static u32 smk_cipso_doi_value = CIPSO_V4_DOI_UNKNOWN;
+
+/*
+ * Values for parsing cipso rules
+ * SMK_DIGITLEN: Length of a digit field in a rule.
+ * SMK_CIPSOMIN: Minimum possible cipso rule length.
+ * SMK_CIPSOMAX: Maximum possible cipso rule length.
+ */
+#define SMK_DIGITLEN 4
+#define SMK_CIPSOMIN (SMK_LABELLEN + 2 * SMK_DIGITLEN)
+#define SMK_CIPSOMAX (SMK_CIPSOMIN + SMACK_CIPSO_MAXCATNUM * SMK_DIGITLEN)
+
+/*
+ * Values for parsing MAC rules
+ * SMK_ACCESS: Maximum possible combination of access permissions
+ * SMK_ACCESSLEN: Maximum length for a rule access field
+ * SMK_LOADLEN: Smack rule length
+ */
+#define SMK_OACCESS	"rwxa"
+#define SMK_ACCESS	"rwxatl"
+#define SMK_OACCESSLEN	(sizeof(SMK_OACCESS) - 1)
+#define SMK_ACCESSLEN	(sizeof(SMK_ACCESS) - 1)
+#define SMK_OLOADLEN	(SMK_LABELLEN + SMK_LABELLEN + SMK_OACCESSLEN)
+#define SMK_LOADLEN	(SMK_LABELLEN + SMK_LABELLEN + SMK_ACCESSLEN)
+
+/*
+ * Strictly for CIPSO level manipulation.
+ * Set the category bit number in a smack label sized buffer.
+ */
+static inline void smack_catset_bit(unsigned int cat, char *catsetp)
+{
+	if (cat == 0 || cat > (SMK_CIPSOLEN * 8))
+		return;
+
+	catsetp[(cat - 1) / 8] |= 0x80 >> ((cat - 1) % 8);
+}
+
+/**
+ * smk_netlabel_audit_set - fill a netlbl_audit struct
+ * @nap: structure to fill
+ */
+static void smk_netlabel_audit_set(struct netlbl_audit *nap)
+{
+	nap->loginuid = audit_get_loginuid(current);
+	nap->sessionid = audit_get_sessionid(current);
+	nap->prop.smack.skp = smk_of_current();
+}
+
+/*
+ * Value for parsing single label host rules
+ * "1.2.3.4 X"
+ */
+#define SMK_NETLBLADDRMIN	9
+
+/**
+ * smk_set_access - add a rule to the rule list or replace an old rule
+ * @srp: the rule to add or replace
+ * @rule_list: the list of rules
+ * @rule_lock: the rule list lock
+ *
+ * Looks through the current subject/object/access list for
+ * the subject/object pair and replaces the access that was
+ * there. If the pair isn't found add it with the specified
+ * access.
+ *
+ * Returns 0 if nothing goes wrong or -ENOMEM if it fails
+ * during the allocation of the new pair to add.
+ */
+static int smk_set_access(struct smack_parsed_rule *srp,
+				struct list_head *rule_list,
+				struct mutex *rule_lock)
+{
+	struct smack_rule *sp;
+	int found = 0;
+	int rc = 0;
+
+	mutex_lock(rule_lock);
+
+	/*
+	 * Because the object label is less likely to match
+	 * than the subject label check it first
+	 */
+	list_for_each_entry_rcu(sp, rule_list, list) {
+		if (sp->smk_object == srp->smk_object &&
+		    sp->smk_subject == srp->smk_subject) {
+			found = 1;
+			sp->smk_access |= srp->smk_access1;
+			sp->smk_access &= ~srp->smk_access2;
+			break;
+		}
+	}
+
+	if (found == 0) {
+		sp = kmem_cache_zalloc(smack_rule_cache, GFP_KERNEL);
+		if (sp == NULL) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		sp->smk_subject = srp->smk_subject;
+		sp->smk_object = srp->smk_object;
+		sp->smk_access = srp->smk_access1 & ~srp->smk_access2;
+
+		list_add_rcu(&sp->list, rule_list);
+	}
+
+out:
+	mutex_unlock(rule_lock);
+	return rc;
+}
+
+/**
+ * smk_perm_from_str - parse smack accesses from a text string
+ * @string: a text string that contains a Smack accesses code
+ *
+ * Returns an integer with respective bits set for specified accesses.
+ */
+static int smk_perm_from_str(const char *string)
+{
+	int perm = 0;
+	const char *cp;
+
+	for (cp = string; ; cp++)
+		switch (*cp) {
+		case '-':
+			break;
+		case 'r':
+		case 'R':
+			perm |= MAY_READ;
+			break;
+		case 'w':
+		case 'W':
+			perm |= MAY_WRITE;
+			break;
+		case 'x':
+		case 'X':
+			perm |= MAY_EXEC;
+			break;
+		case 'a':
+		case 'A':
+			perm |= MAY_APPEND;
+			break;
+		case 't':
+		case 'T':
+			perm |= MAY_TRANSMUTE;
+			break;
+		case 'l':
+		case 'L':
+			perm |= MAY_LOCK;
+			break;
+		case 'b':
+		case 'B':
+			perm |= MAY_BRINGUP;
+			break;
+		default:
+			return perm;
+		}
+}
+
+/**
+ * smk_fill_rule - Fill Smack rule from strings
+ * @subject: subject label string
+ * @object: object label string
+ * @access1: access string
+ * @access2: string with permissions to be removed
+ * @rule: Smack rule
+ * @import: if non-zero, import labels
+ * @len: label length limit
+ *
+ * Returns 0 on success, appropriate error code on failure.
+ */
+static int smk_fill_rule(const char *subject, const char *object,
+				const char *access1, const char *access2,
+				struct smack_parsed_rule *rule, int import,
+				int len)
+{
+	const char *cp;
+	struct smack_known *skp;
+
+	if (import) {
+		rule->smk_subject = smk_import_entry(subject, len);
+		if (IS_ERR(rule->smk_subject))
+			return PTR_ERR(rule->smk_subject);
+
+		rule->smk_object = smk_import_entry(object, len);
+		if (IS_ERR(rule->smk_object))
+			return PTR_ERR(rule->smk_object);
+	} else {
+		cp = smk_parse_smack(subject, len);
+		if (IS_ERR(cp))
+			return PTR_ERR(cp);
+		skp = smk_find_entry(cp);
+		kfree(cp);
+		if (skp == NULL)
+			return -ENOENT;
+		rule->smk_subject = skp;
+
+		cp = smk_parse_smack(object, len);
+		if (IS_ERR(cp))
+			return PTR_ERR(cp);
+		skp = smk_find_entry(cp);
+		kfree(cp);
+		if (skp == NULL)
+			return -ENOENT;
+		rule->smk_object = skp;
+	}
+
+	rule->smk_access1 = smk_perm_from_str(access1);
+	if (access2)
+		rule->smk_access2 = smk_perm_from_str(access2);
+	else
+		rule->smk_access2 = ~rule->smk_access1;
+
+	return 0;
+}
+
+/**
+ * smk_parse_rule - parse Smack rule from load string
+ * @data: string to be parsed whose size is SMK_LOADLEN
+ * @rule: Smack rule
+ * @import: if non-zero, import labels
+ *
+ * Returns 0 on success, -1 on errors.
+ */
+static int smk_parse_rule(const char *data, struct smack_parsed_rule *rule,
+				int import)
+{
+	int rc;
+
+	rc = smk_fill_rule(data, data + SMK_LABELLEN,
+			   data + SMK_LABELLEN + SMK_LABELLEN, NULL, rule,
+			   import, SMK_LABELLEN);
+	return rc;
+}
+
+/**
+ * smk_parse_long_rule - parse Smack rule from rule string
+ * @data: string to be parsed, null terminated
+ * @rule: Will be filled with Smack parsed rule
+ * @import: if non-zero, import labels
+ * @tokens: number of substrings expected in data
+ *
+ * Returns number of processed bytes on success, -ERRNO on failure.
+ */
+static ssize_t smk_parse_long_rule(char *data, struct smack_parsed_rule *rule,
+				int import, int tokens)
+{
+	ssize_t cnt = 0;
+	char *tok[4];
+	int rc;
+	int i;
+
+	/*
+	 * Parsing the rule in-place, filling all white-spaces with '\0'
+	 */
+	for (i = 0; i < tokens; ++i) {
+		while (isspace(data[cnt]))
+			data[cnt++] = '\0';
+
+		if (data[cnt] == '\0')
+			/* Unexpected end of data */
+			return -EINVAL;
+
+		tok[i] = data + cnt;
+
+		while (data[cnt] && !isspace(data[cnt]))
+			++cnt;
+	}
+	while (isspace(data[cnt]))
+		data[cnt++] = '\0';
+
+	while (i < 4)
+		tok[i++] = NULL;
+
+	rc = smk_fill_rule(tok[0], tok[1], tok[2], tok[3], rule, import, 0);
+	return rc == 0 ? cnt : rc;
+}
+
+#define SMK_FIXED24_FMT	0	/* Fixed 24byte label format */
+#define SMK_LONG_FMT	1	/* Variable long label format */
+#define SMK_CHANGE_FMT	2	/* Rule modification format */
+/**
+ * smk_write_rules_list - write() for any /smack rule file
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ * @rule_list: the list of rules to write to
+ * @rule_lock: lock for the rule list
+ * @format: /smack/load or /smack/load2 or /smack/change-rule format.
+ *
+ * Get one smack access rule from above.
+ * The format for SMK_LONG_FMT is:
+ *	"subject<whitespace>object<whitespace>access[<whitespace>...]"
+ * The format for SMK_FIXED24_FMT is exactly:
+ *	"subject                 object                  rwxat"
+ * The format for SMK_CHANGE_FMT is:
+ *	"subject<whitespace>object<whitespace>
+ *	 acc_enable<whitespace>acc_disable[<whitespace>...]"
+ */
+static ssize_t smk_write_rules_list(struct file *file, const char __user *buf,
+					size_t count, loff_t *ppos,
+					struct list_head *rule_list,
+					struct mutex *rule_lock, int format)
+{
+	struct smack_parsed_rule rule;
+	char *data;
+	int rc;
+	int trunc = 0;
+	int tokens;
+	ssize_t cnt = 0;
+
+	/*
+	 * No partial writes.
+	 * Enough data must be present.
+	 */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	if (format == SMK_FIXED24_FMT) {
+		/*
+		 * Minor hack for backward compatibility
+		 */
+		if (count < SMK_OLOADLEN || count > SMK_LOADLEN)
+			return -EINVAL;
+	} else {
+		if (count >= PAGE_SIZE) {
+			count = PAGE_SIZE - 1;
+			trunc = 1;
+		}
+	}
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	/*
+	 * In case of parsing only part of user buf,
+	 * avoid having partial rule at the data buffer
+	 */
+	if (trunc) {
+		while (count > 0 && (data[count - 1] != '\n'))
+			--count;
+		if (count == 0) {
+			rc = -EINVAL;
+			goto out;
+		}
+	}
+
+	data[count] = '\0';
+	tokens = (format == SMK_CHANGE_FMT ? 4 : 3);
+	while (cnt < count) {
+		if (format == SMK_FIXED24_FMT) {
+			rc = smk_parse_rule(data, &rule, 1);
+			if (rc < 0)
+				goto out;
+			cnt = count;
+		} else {
+			rc = smk_parse_long_rule(data + cnt, &rule, 1, tokens);
+			if (rc < 0)
+				goto out;
+			if (rc == 0) {
+				rc = -EINVAL;
+				goto out;
+			}
+			cnt += rc;
+		}
+
+		if (rule_list == NULL)
+			rc = smk_set_access(&rule, &rule.smk_subject->smk_rules,
+				&rule.smk_subject->smk_rules_lock);
+		else
+			rc = smk_set_access(&rule, rule_list, rule_lock);
+
+		if (rc)
+			goto out;
+	}
+
+	rc = cnt;
+out:
+	kfree(data);
+	return rc;
+}
+
+/*
+ * Core logic for smackfs seq list operations.
+ */
+
+static void *smk_seq_start(struct seq_file *s, loff_t *pos,
+				struct list_head *head)
+{
+	struct list_head *list;
+	int i = *pos;
+
+	rcu_read_lock();
+	for (list = rcu_dereference(list_next_rcu(head));
+		list != head;
+		list = rcu_dereference(list_next_rcu(list))) {
+		if (i-- == 0)
+			return list;
+	}
+
+	return NULL;
+}
+
+static void *smk_seq_next(struct seq_file *s, void *v, loff_t *pos,
+				struct list_head *head)
+{
+	struct list_head *list = v;
+
+	++*pos;
+	list = rcu_dereference(list_next_rcu(list));
+
+	return (list == head) ? NULL : list;
+}
+
+static void smk_seq_stop(struct seq_file *s, void *v)
+{
+	rcu_read_unlock();
+}
+
+static void smk_rule_show(struct seq_file *s, struct smack_rule *srp, int max)
+{
+	char acc[SMK_NUM_ACCESS_TYPE + 1];
+	/*
+	 * Don't show any rules with label names too long for
+	 * interface file (/smack/load or /smack/load2)
+	 * because you should expect to be able to write
+	 * anything you read back.
+	 */
+	if (strlen(srp->smk_subject->smk_known) >= max ||
+	    strlen(srp->smk_object->smk_known) >= max)
+		return;
+
+	if (srp->smk_access == 0)
+		return;
+
+	smack_str_from_perm(acc, srp->smk_access);
+	seq_printf(s, "%s %s %s\n",
+		   srp->smk_subject->smk_known,
+		   srp->smk_object->smk_known,
+		   acc);
+}
+
+/*
+ * Seq_file read operations for /smack/load
+ */
+
+static void *load2_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smack_known_list);
+}
+
+static void *load2_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smack_known_list);
+}
+
+static int load_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp;
+	struct smack_known *skp =
+		list_entry_rcu(list, struct smack_known, list);
+
+	list_for_each_entry_rcu(srp, &skp->smk_rules, list)
+		smk_rule_show(s, srp, SMK_LABELLEN);
+
+	return 0;
+}
+
+static const struct seq_operations load_seq_ops = {
+	.start = load2_seq_start,
+	.next  = load2_seq_next,
+	.show  = load_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_load - open() for /smack/load
+ * @inode: inode structure representing file
+ * @file: "load" file pointer
+ *
+ * For reading, use load_seq_* seq_file reading operations.
+ */
+static int smk_open_load(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load_seq_ops);
+}
+
+/**
+ * smk_write_load - write() for /smack/load
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	/*
+	 * Must have privilege.
+	 * No partial writes.
+	 * Enough data must be present.
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	return smk_write_rules_list(file, buf, count, ppos, NULL, NULL,
+				    SMK_FIXED24_FMT);
+}
+
+static const struct file_operations smk_load_ops = {
+	.open           = smk_open_load,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_load,
+	.release        = seq_release,
+};
+
+/**
+ * smk_cipso_doi - set netlabel maps
+ * @ndoi: new value for our CIPSO DOI
+ * @gfp_flags: kmalloc allocation context
+ */
+static int
+smk_cipso_doi(u32 ndoi, gfp_t gfp_flags)
+{
+	int rc = 0;
+	struct cipso_v4_doi *doip;
+	struct netlbl_audit nai;
+
+	mutex_lock(&smk_cipso_doi_lock);
+
+	if (smk_cipso_doi_value == ndoi)
+		goto clr_doi_lock;
+
+	smk_netlabel_audit_set(&nai);
+
+	doip = kmalloc_obj(struct cipso_v4_doi, gfp_flags);
+	if (!doip) {
+		rc = -ENOMEM;
+		goto clr_doi_lock;
+	}
+	doip->map.std = NULL;
+	doip->doi = ndoi;
+	doip->type = CIPSO_V4_MAP_PASS;
+	doip->tags[0] = CIPSO_V4_TAG_RBITMAP;
+	for (rc = 1; rc < CIPSO_V4_TAG_MAXCNT; rc++)
+		doip->tags[rc] = CIPSO_V4_TAG_INVALID;
+
+	rc = netlbl_cfg_cipsov4_add(doip, &nai);
+	if (rc) {
+		kfree(doip);
+		goto clr_doi_lock;
+	}
+
+	if (smk_cipso_doi_value != CIPSO_V4_DOI_UNKNOWN) {
+		rc = netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai);
+		if (rc && rc != -ENOENT)
+			goto clr_ndoi_def;
+
+		netlbl_cfg_cipsov4_del(smk_cipso_doi_value, &nai);
+	}
+
+	rc = netlbl_cfg_cipsov4_map_add(ndoi, NULL, NULL, NULL, &nai);
+	if (rc) {
+		smk_cipso_doi_value = CIPSO_V4_DOI_UNKNOWN; // no default map
+clr_ndoi_def:	netlbl_cfg_cipsov4_del(ndoi, &nai);
+	} else
+		smk_cipso_doi_value = ndoi;
+
+clr_doi_lock:
+	mutex_unlock(&smk_cipso_doi_lock);
+	return rc;
+}
+
+/**
+ * smk_unlbl_ambient - initialize the unlabeled domain
+ * @oldambient: previous domain string
+ */
+static void smk_unlbl_ambient(char *oldambient)
+{
+	int rc;
+	struct netlbl_audit nai;
+
+	smk_netlabel_audit_set(&nai);
+
+	if (oldambient != NULL) {
+		rc = netlbl_cfg_map_del(oldambient, PF_INET, NULL, NULL, &nai);
+		if (rc != 0)
+			printk(KERN_WARNING "%s:%d remove rc = %d\n",
+			       __func__, __LINE__, rc);
+	}
+	if (smack_net_ambient == NULL)
+		smack_net_ambient = &smack_known_floor;
+
+	rc = netlbl_cfg_unlbl_map_add(smack_net_ambient->smk_known, PF_INET,
+				      NULL, NULL, &nai);
+	if (rc != 0)
+		printk(KERN_WARNING "%s:%d add rc = %d\n",
+		       __func__, __LINE__, rc);
+}
+
+/*
+ * Seq_file read operations for /smack/cipso
+ */
+
+static void *cipso_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smack_known_list);
+}
+
+static void *cipso_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smack_known_list);
+}
+
+/*
+ * Print cipso labels in format:
+ * label level[/cat[,cat]]
+ */
+static int cipso_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head  *list = v;
+	struct smack_known *skp =
+		list_entry_rcu(list, struct smack_known, list);
+	struct netlbl_lsm_catmap *cmp = skp->smk_netlabel.attr.mls.cat;
+	char sep = '/';
+	int i;
+
+	/*
+	 * Don't show a label that could not have been set using
+	 * /smack/cipso. This is in support of the notion that
+	 * anything read from /smack/cipso ought to be writeable
+	 * to /smack/cipso.
+	 *
+	 * /smack/cipso2 should be used instead.
+	 */
+	if (strlen(skp->smk_known) >= SMK_LABELLEN)
+		return 0;
+
+	seq_printf(s, "%s %3d", skp->smk_known, skp->smk_netlabel.attr.mls.lvl);
+
+	for (i = netlbl_catmap_walk(cmp, 0); i >= 0;
+	     i = netlbl_catmap_walk(cmp, i + 1)) {
+		seq_printf(s, "%c%d", sep, i);
+		sep = ',';
+	}
+
+	seq_putc(s, '\n');
+
+	return 0;
+}
+
+static const struct seq_operations cipso_seq_ops = {
+	.start = cipso_seq_start,
+	.next  = cipso_seq_next,
+	.show  = cipso_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_cipso - open() for /smack/cipso
+ * @inode: inode structure representing file
+ * @file: "cipso" file pointer
+ *
+ * Connect our cipso_seq_* operations with /smack/cipso
+ * file_operations
+ */
+static int smk_open_cipso(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cipso_seq_ops);
+}
+
+/**
+ * smk_set_cipso - do the work for write() for cipso and cipso2
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ * @format: /smack/cipso or /smack/cipso2
+ *
+ * Accepts only one cipso rule per write call.
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos, int format)
+{
+	struct netlbl_lsm_catmap *old_cat;
+	struct smack_known *skp;
+	struct netlbl_lsm_secattr ncats;
+	char mapcatset[SMK_CIPSOLEN];
+	int maplevel;
+	unsigned int cat;
+	int catlen;
+	ssize_t rc = -EINVAL;
+	char *data = NULL;
+	char *rule;
+	int ret;
+	int i;
+
+	/*
+	 * Must have privilege.
+	 * No partial writes.
+	 * Enough data must be present.
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+	if (*ppos != 0)
+		return -EINVAL;
+	if (format == SMK_FIXED24_FMT &&
+	    (count < SMK_CIPSOMIN || count > SMK_CIPSOMAX))
+		return -EINVAL;
+	if (count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	rule = data;
+	/*
+	 * Only allow one writer at a time. Writes should be
+	 * quite rare and small in any case.
+	 */
+	mutex_lock(&smack_cipso_lock);
+
+	skp = smk_import_entry(rule, 0);
+	if (IS_ERR(skp)) {
+		rc = PTR_ERR(skp);
+		goto out;
+	}
+
+	if (format == SMK_FIXED24_FMT)
+		rule += SMK_LABELLEN;
+	else
+		rule += strlen(skp->smk_known) + 1;
+
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
+	ret = sscanf(rule, "%d", &maplevel);
+	if (ret != 1 || maplevel < 0 || maplevel > SMACK_CIPSO_MAXLEVEL)
+		goto out;
+
+	rule += SMK_DIGITLEN;
+	if (rule > data + count) {
+		rc = -EOVERFLOW;
+		goto out;
+	}
+
+	ret = sscanf(rule, "%d", &catlen);
+	if (ret != 1 || catlen < 0 || catlen > SMACK_CIPSO_MAXCATNUM)
+		goto out;
+
+	if (format == SMK_FIXED24_FMT &&
+	    count != (SMK_CIPSOMIN + catlen * SMK_DIGITLEN))
+		goto out;
+
+	memset(mapcatset, 0, sizeof(mapcatset));
+
+	for (i = 0; i < catlen; i++) {
+		rule += SMK_DIGITLEN;
+		if (rule > data + count) {
+			rc = -EOVERFLOW;
+			goto out;
+		}
+		ret = sscanf(rule, "%u", &cat);
+		if (ret != 1 || cat > SMACK_CIPSO_MAXCATNUM)
+			goto out;
+
+		smack_catset_bit(cat, mapcatset);
+	}
+
+	rc = smk_netlbl_mls(maplevel, mapcatset, &ncats, SMK_CIPSOLEN);
+	if (rc >= 0) {
+		old_cat = skp->smk_netlabel.attr.mls.cat;
+		rcu_assign_pointer(skp->smk_netlabel.attr.mls.cat, ncats.attr.mls.cat);
+		if (ncats.attr.mls.cat)
+			skp->smk_netlabel.flags |= NETLBL_SECATTR_MLS_CAT;
+		else
+			skp->smk_netlabel.flags &= ~(u32)NETLBL_SECATTR_MLS_CAT;
+		skp->smk_netlabel.attr.mls.lvl = ncats.attr.mls.lvl;
+		synchronize_rcu();
+		netlbl_catmap_free(old_cat);
+		rc = count;
+		/*
+		 * This mapping may have been cached, so clear the cache.
+		 */
+		netlbl_cache_invalidate();
+	}
+
+out:
+	mutex_unlock(&smack_cipso_lock);
+	kfree(data);
+	return rc;
+}
+
+/**
+ * smk_write_cipso - write() for /smack/cipso
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Accepts only one cipso rule per write call.
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_cipso(struct file *file, const char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	return smk_set_cipso(file, buf, count, ppos, SMK_FIXED24_FMT);
+}
+
+static const struct file_operations smk_cipso_ops = {
+	.open           = smk_open_cipso,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_cipso,
+	.release        = seq_release,
+};
+
+/*
+ * Seq_file read operations for /smack/cipso2
+ */
+
+/*
+ * Print cipso labels in format:
+ * label level[/cat[,cat]]
+ */
+static int cipso2_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head  *list = v;
+	struct smack_known *skp =
+		list_entry_rcu(list, struct smack_known, list);
+	struct netlbl_lsm_catmap *cmp = skp->smk_netlabel.attr.mls.cat;
+	char sep = '/';
+	int i;
+
+	seq_printf(s, "%s %3d", skp->smk_known, skp->smk_netlabel.attr.mls.lvl);
+
+	for (i = netlbl_catmap_walk(cmp, 0); i >= 0;
+	     i = netlbl_catmap_walk(cmp, i + 1)) {
+		seq_printf(s, "%c%d", sep, i);
+		sep = ',';
+	}
+
+	seq_putc(s, '\n');
+
+	return 0;
+}
+
+static const struct seq_operations cipso2_seq_ops = {
+	.start = cipso_seq_start,
+	.next  = cipso_seq_next,
+	.show  = cipso2_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_cipso2 - open() for /smack/cipso2
+ * @inode: inode structure representing file
+ * @file: "cipso2" file pointer
+ *
+ * Connect our cipso_seq_* operations with /smack/cipso2
+ * file_operations
+ */
+static int smk_open_cipso2(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cipso2_seq_ops);
+}
+
+/**
+ * smk_write_cipso2 - write() for /smack/cipso2
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Accepts only one cipso rule per write call.
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_cipso2(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	return smk_set_cipso(file, buf, count, ppos, SMK_LONG_FMT);
+}
+
+static const struct file_operations smk_cipso2_ops = {
+	.open           = smk_open_cipso2,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_cipso2,
+	.release        = seq_release,
+};
+
+/*
+ * Seq_file read operations for /smack/netlabel
+ */
+
+static void *net4addr_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smk_net4addr_list);
+}
+
+static void *net4addr_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smk_net4addr_list);
+}
+
+/*
+ * Print host/label pairs
+ */
+static int net4addr_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smk_net4addr *skp =
+			list_entry_rcu(list, struct smk_net4addr, list);
+	char *kp = SMACK_CIPSO_OPTION;
+
+	if (skp->smk_label != NULL)
+		kp = skp->smk_label->smk_known;
+	seq_printf(s, "%pI4/%d %s\n", &skp->smk_host.s_addr,
+			skp->smk_masks, kp);
+
+	return 0;
+}
+
+static const struct seq_operations net4addr_seq_ops = {
+	.start = net4addr_seq_start,
+	.next  = net4addr_seq_next,
+	.show  = net4addr_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_net4addr - open() for /smack/netlabel
+ * @inode: inode structure representing file
+ * @file: "netlabel" file pointer
+ *
+ * Connect our net4addr_seq_* operations with /smack/netlabel
+ * file_operations
+ */
+static int smk_open_net4addr(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &net4addr_seq_ops);
+}
+
+/**
+ * smk_net4addr_insert - insert a new entry into the net4addrs list
+ * @new : netlabel to insert
+ *
+ * This helper inserts netlabel in the smack_net4addrs list
+ * sorted by netmask length (longest to smallest)
+ * locked by &smk_net4addr_lock in smk_write_net4addr.
+ */
+static void smk_net4addr_insert(struct smk_net4addr *new)
+{
+	struct smk_net4addr *m;
+	struct smk_net4addr *m_next;
+
+	if (list_empty(&smk_net4addr_list)) {
+		list_add_rcu(&new->list, &smk_net4addr_list);
+		return;
+	}
+
+	m = list_entry_rcu(smk_net4addr_list.next,
+			   struct smk_net4addr, list);
+
+	/* the comparison '>' is a bit hacky, but works */
+	if (new->smk_masks > m->smk_masks) {
+		list_add_rcu(&new->list, &smk_net4addr_list);
+		return;
+	}
+
+	list_for_each_entry_rcu(m, &smk_net4addr_list, list) {
+		if (list_is_last(&m->list, &smk_net4addr_list)) {
+			list_add_rcu(&new->list, &m->list);
+			return;
+		}
+		m_next = list_entry_rcu(m->list.next,
+					struct smk_net4addr, list);
+		if (new->smk_masks > m_next->smk_masks) {
+			list_add_rcu(&new->list, &m->list);
+			return;
+		}
+	}
+}
+
+
+/**
+ * smk_write_net4addr - write() for /smack/netlabel
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Accepts only one net4addr per write call.
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_net4addr(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct smk_net4addr *snp;
+	struct sockaddr_in newname;
+	char *smack;
+	struct smack_known *skp = NULL;
+	char *data;
+	char *host = (char *)&newname.sin_addr.s_addr;
+	int rc;
+	struct netlbl_audit audit_info;
+	struct in_addr mask;
+	unsigned int m;
+	unsigned int masks;
+	int found;
+	u32 mask_bits = (1<<31);
+	__be32 nsa;
+	u32 temp_mask;
+
+	/*
+	 * Must have privilege.
+	 * No partial writes.
+	 * Enough data must be present.
+	 * "<addr/mask, as a.b.c.d/e><space><label>"
+	 * "<addr, as a.b.c.d><space><label>"
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+	if (*ppos != 0)
+		return -EINVAL;
+	if (count < SMK_NETLBLADDRMIN || count > PAGE_SIZE - 1)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	smack = kzalloc(count + 1, GFP_KERNEL);
+	if (smack == NULL) {
+		rc = -ENOMEM;
+		goto free_data_out;
+	}
+
+	rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd/%u %s",
+		&host[0], &host[1], &host[2], &host[3], &masks, smack);
+	if (rc != 6) {
+		rc = sscanf(data, "%hhd.%hhd.%hhd.%hhd %s",
+			&host[0], &host[1], &host[2], &host[3], smack);
+		if (rc != 5) {
+			rc = -EINVAL;
+			goto free_out;
+		}
+		masks = 32;
+	}
+	if (masks > BEBITS) {
+		rc = -EINVAL;
+		goto free_out;
+	}
+
+	/*
+	 * If smack begins with '-', it is an option, don't import it
+	 */
+	if (smack[0] != '-') {
+		skp = smk_import_entry(smack, 0);
+		if (IS_ERR(skp)) {
+			rc = PTR_ERR(skp);
+			goto free_out;
+		}
+	} else {
+		/*
+		 * Only the -CIPSO option is supported for IPv4
+		 */
+		if (strcmp(smack, SMACK_CIPSO_OPTION) != 0) {
+			rc = -EINVAL;
+			goto free_out;
+		}
+	}
+
+	for (m = masks, temp_mask = 0; m > 0; m--) {
+		temp_mask |= mask_bits;
+		mask_bits >>= 1;
+	}
+	mask.s_addr = cpu_to_be32(temp_mask);
+
+	newname.sin_addr.s_addr &= mask.s_addr;
+	/*
+	 * Only allow one writer at a time. Writes should be
+	 * quite rare and small in any case.
+	 */
+	mutex_lock(&smk_net4addr_lock);
+
+	nsa = newname.sin_addr.s_addr;
+	/* try to find if the prefix is already in the list */
+	found = 0;
+	list_for_each_entry_rcu(snp, &smk_net4addr_list, list) {
+		if (snp->smk_host.s_addr == nsa && snp->smk_masks == masks) {
+			found = 1;
+			break;
+		}
+	}
+	smk_netlabel_audit_set(&audit_info);
+
+	if (found == 0) {
+		snp = kzalloc_obj(*snp);
+		if (snp == NULL)
+			rc = -ENOMEM;
+		else {
+			rc = 0;
+			snp->smk_host.s_addr = newname.sin_addr.s_addr;
+			snp->smk_mask.s_addr = mask.s_addr;
+			snp->smk_label = skp;
+			snp->smk_masks = masks;
+			smk_net4addr_insert(snp);
+		}
+	} else {
+		/*
+		 * Delete the unlabeled entry, only if the previous label
+		 * wasn't the special CIPSO option
+		 */
+		if (snp->smk_label != NULL)
+			rc = netlbl_cfg_unlbl_static_del(&init_net, NULL,
+					&snp->smk_host, &snp->smk_mask,
+					PF_INET, &audit_info);
+		else
+			rc = 0;
+		snp->smk_label = skp;
+	}
+
+	/*
+	 * Now tell netlabel about the single label nature of
+	 * this host so that incoming packets get labeled.
+	 * but only if we didn't get the special CIPSO option
+	 */
+	if (rc == 0 && skp != NULL)
+		rc = netlbl_cfg_unlbl_static_add(&init_net, NULL,
+			&snp->smk_host, &snp->smk_mask, PF_INET,
+			snp->smk_label->smk_secid, &audit_info);
+
+	if (rc == 0)
+		rc = count;
+
+	mutex_unlock(&smk_net4addr_lock);
+
+free_out:
+	kfree(smack);
+free_data_out:
+	kfree(data);
+
+	return rc;
+}
+
+static const struct file_operations smk_net4addr_ops = {
+	.open           = smk_open_net4addr,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_net4addr,
+	.release        = seq_release,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+/*
+ * Seq_file read operations for /smack/netlabel6
+ */
+
+static void *net6addr_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smk_net6addr_list);
+}
+
+static void *net6addr_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smk_net6addr_list);
+}
+
+/*
+ * Print host/label pairs
+ */
+static int net6addr_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smk_net6addr *skp =
+			 list_entry(list, struct smk_net6addr, list);
+
+	if (skp->smk_label != NULL)
+		seq_printf(s, "%pI6/%d %s\n", &skp->smk_host, skp->smk_masks,
+				skp->smk_label->smk_known);
+
+	return 0;
+}
+
+static const struct seq_operations net6addr_seq_ops = {
+	.start = net6addr_seq_start,
+	.next  = net6addr_seq_next,
+	.show  = net6addr_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_net6addr - open() for /smack/netlabel
+ * @inode: inode structure representing file
+ * @file: "netlabel" file pointer
+ *
+ * Connect our net6addr_seq_* operations with /smack/netlabel
+ * file_operations
+ */
+static int smk_open_net6addr(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &net6addr_seq_ops);
+}
+
+/**
+ * smk_net6addr_insert - insert a new entry into the net6addrs list
+ * @new : entry to insert
+ *
+ * This inserts an entry in the smack_net6addrs list
+ * sorted by netmask length (longest to smallest)
+ * locked by &smk_net6addr_lock in smk_write_net6addr.
+ */
+static void smk_net6addr_insert(struct smk_net6addr *new)
+{
+	struct smk_net6addr *m_next;
+	struct smk_net6addr *m;
+
+	if (list_empty(&smk_net6addr_list)) {
+		list_add_rcu(&new->list, &smk_net6addr_list);
+		return;
+	}
+
+	m = list_entry_rcu(smk_net6addr_list.next,
+			   struct smk_net6addr, list);
+
+	if (new->smk_masks > m->smk_masks) {
+		list_add_rcu(&new->list, &smk_net6addr_list);
+		return;
+	}
+
+	list_for_each_entry_rcu(m, &smk_net6addr_list, list) {
+		if (list_is_last(&m->list, &smk_net6addr_list)) {
+			list_add_rcu(&new->list, &m->list);
+			return;
+		}
+		m_next = list_entry_rcu(m->list.next,
+					struct smk_net6addr, list);
+		if (new->smk_masks > m_next->smk_masks) {
+			list_add_rcu(&new->list, &m->list);
+			return;
+		}
+	}
+}
+
+
+/**
+ * smk_write_net6addr - write() for /smack/netlabel
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Accepts only one net6addr per write call.
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_net6addr(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct smk_net6addr *snp;
+	struct in6_addr newname;
+	struct in6_addr fullmask;
+	struct smack_known *skp = NULL;
+	char *smack;
+	char *data;
+	int rc = 0;
+	int found = 0;
+	int i;
+	unsigned int scanned[8];
+	unsigned int m;
+	unsigned int mask = 128;
+
+	/*
+	 * Must have privilege.
+	 * No partial writes.
+	 * Enough data must be present.
+	 * "<addr/mask, as a:b:c:d:e:f:g:h/e><space><label>"
+	 * "<addr, as a:b:c:d:e:f:g:h><space><label>"
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+	if (*ppos != 0)
+		return -EINVAL;
+	if (count < SMK_NETLBLADDRMIN || count > PAGE_SIZE - 1)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	smack = kzalloc(count + 1, GFP_KERNEL);
+	if (smack == NULL) {
+		rc = -ENOMEM;
+		goto free_data_out;
+	}
+
+	i = sscanf(data, "%x:%x:%x:%x:%x:%x:%x:%x/%u %s",
+			&scanned[0], &scanned[1], &scanned[2], &scanned[3],
+			&scanned[4], &scanned[5], &scanned[6], &scanned[7],
+			&mask, smack);
+	if (i != 10) {
+		i = sscanf(data, "%x:%x:%x:%x:%x:%x:%x:%x %s",
+				&scanned[0], &scanned[1], &scanned[2],
+				&scanned[3], &scanned[4], &scanned[5],
+				&scanned[6], &scanned[7], smack);
+		if (i != 9) {
+			rc = -EINVAL;
+			goto free_out;
+		}
+	}
+	if (mask > 128) {
+		rc = -EINVAL;
+		goto free_out;
+	}
+	for (i = 0; i < 8; i++) {
+		if (scanned[i] > 0xffff) {
+			rc = -EINVAL;
+			goto free_out;
+		}
+		newname.s6_addr16[i] = htons(scanned[i]);
+	}
+
+	/*
+	 * If smack begins with '-', it is an option, don't import it
+	 */
+	if (smack[0] != '-') {
+		skp = smk_import_entry(smack, 0);
+		if (IS_ERR(skp)) {
+			rc = PTR_ERR(skp);
+			goto free_out;
+		}
+	} else {
+		/*
+		 * Only -DELETE is supported for IPv6
+		 */
+		if (strcmp(smack, SMACK_DELETE_OPTION) != 0) {
+			rc = -EINVAL;
+			goto free_out;
+		}
+	}
+
+	for (i = 0, m = mask; i < 8; i++) {
+		if (m >= 16) {
+			fullmask.s6_addr16[i] = 0xffff;
+			m -= 16;
+		} else if (m > 0) {
+			fullmask.s6_addr16[i] = (1 << m) - 1;
+			m = 0;
+		} else
+			fullmask.s6_addr16[i] = 0;
+		newname.s6_addr16[i] &= fullmask.s6_addr16[i];
+	}
+
+	/*
+	 * Only allow one writer at a time. Writes should be
+	 * quite rare and small in any case.
+	 */
+	mutex_lock(&smk_net6addr_lock);
+	/*
+	 * Try to find the prefix in the list
+	 */
+	list_for_each_entry_rcu(snp, &smk_net6addr_list, list) {
+		if (mask != snp->smk_masks)
+			continue;
+		for (found = 1, i = 0; i < 8; i++) {
+			if (newname.s6_addr16[i] !=
+			    snp->smk_host.s6_addr16[i]) {
+				found = 0;
+				break;
+			}
+		}
+		if (found == 1)
+			break;
+	}
+	if (found == 0) {
+		snp = kzalloc_obj(*snp);
+		if (snp == NULL)
+			rc = -ENOMEM;
+		else {
+			snp->smk_host = newname;
+			snp->smk_mask = fullmask;
+			snp->smk_masks = mask;
+			snp->smk_label = skp;
+			smk_net6addr_insert(snp);
+		}
+	} else {
+		snp->smk_label = skp;
+	}
+
+	if (rc == 0)
+		rc = count;
+
+	mutex_unlock(&smk_net6addr_lock);
+
+free_out:
+	kfree(smack);
+free_data_out:
+	kfree(data);
+
+	return rc;
+}
+
+static const struct file_operations smk_net6addr_ops = {
+	.open           = smk_open_net6addr,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_net6addr,
+	.release        = seq_release,
+};
+#endif /* CONFIG_IPV6 */
+
+/**
+ * smk_read_doi - read() for /smack/doi
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_doi(struct file *filp, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	char temp[80];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%lu", (unsigned long)smk_cipso_doi_value);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+
+	return rc;
+}
+
+/**
+ * smk_write_doi - write() for /smack/doi
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_doi(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	int ret;
+	u32 u;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	ret = kstrtou32_from_user(buf, count, 10, &u);
+	if (unlikely(ret))
+		return ret;
+
+	if (u == CIPSO_V4_DOI_UNKNOWN)
+		return -EINVAL;
+
+	return smk_cipso_doi(u, GFP_KERNEL) ? : count;
+}
+
+static const struct file_operations smk_doi_ops = {
+	.read		= smk_read_doi,
+	.write		= smk_write_doi,
+	.llseek		= default_llseek,
+};
+
+/**
+ * smk_read_cipso_auto_level - read() for smackfs/direct and smackfs/mapped
+ * @filp: file pointer
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_cipso_auto_level(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	char temp[sizeof "255"];
+	int n;
+
+	if (*ppos != 0)
+		return 0;
+
+	n = sprintf(temp, "%u", (unsigned int)smack_cipso_auto_level[
+		smk_cipso_auto_level_idx(filp)]);
+	return simple_read_from_buffer(buf, count, ppos, temp, n);
+}
+
+/**
+ * smk_write_cipso_auto_level - write() for smackfs/direct and smackfs/mapped
+ * @filp: file pointer
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t
+smk_write_cipso_auto_level(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	int ret, idx;
+	u8  i, old_lvl;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+	/*
+	 * draft-ietf-cipso-ipsecurity-01 (CIPSO 2.2), 3.4.2.4:
+	 * "Sensitivity Level is 1 octet in length. Its value is from 0 to 255"
+	 */
+	ret = kstrtou8_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
+
+	/*
+	 * Don't do anything if the value hasn't actually changed.
+	 * If it is changing reset the level on entries that were
+	 * set up to be "auto" level when they were created.
+	 */
+	idx = smk_cipso_auto_level_idx(filp);
+	old_lvl = smack_cipso_auto_level[idx];
+
+	if (old_lvl != i) {
+		struct smack_known *skp;
+		mutex_lock(&smack_known_lock);
+		list_for_each_entry_rcu(skp, &smack_known_list, list)
+			if (skp->smk_netlabel.attr.mls.lvl ==
+			    old_lvl)
+				skp->smk_netlabel.attr.mls.lvl = i;
+		smack_cipso_auto_level[idx] = i;
+		mutex_unlock(&smack_known_lock);
+	}
+
+	return count;
+}
+
+static const struct file_operations
+smk_cipso_auto_level_ops = {
+	.read		= smk_read_cipso_auto_level,
+	.write		= smk_write_cipso_auto_level,
+	.llseek		= default_llseek,
+};
+
+/**
+ * smk_read_ambient - read() for /smack/ambient
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @cn: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_ambient(struct file *filp, char __user *buf,
+				size_t cn, loff_t *ppos)
+{
+	ssize_t rc;
+	int asize;
+
+	if (*ppos != 0)
+		return 0;
+	/*
+	 * Being careful to avoid a problem in the case where
+	 * smack_net_ambient gets changed in midstream.
+	 */
+	mutex_lock(&smack_ambient_lock);
+
+	asize = strlen(smack_net_ambient->smk_known) + 1;
+
+	if (cn >= asize)
+		rc = simple_read_from_buffer(buf, cn, ppos,
+					     smack_net_ambient->smk_known,
+					     asize);
+	else
+		rc = -EINVAL;
+
+	mutex_unlock(&smack_ambient_lock);
+
+	return rc;
+}
+
+/**
+ * smk_write_ambient - write() for /smack/ambient
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_ambient(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct smack_known *skp;
+	char *oldambient;
+	char *data;
+	int rc = count;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	/* Enough data must be present */
+	if (count == 0 || count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	skp = smk_import_entry(data, count);
+	if (IS_ERR(skp)) {
+		rc = PTR_ERR(skp);
+		goto out;
+	}
+
+	mutex_lock(&smack_ambient_lock);
+
+	oldambient = smack_net_ambient->smk_known;
+	smack_net_ambient = skp;
+	smk_unlbl_ambient(oldambient);
+
+	mutex_unlock(&smack_ambient_lock);
+
+out:
+	kfree(data);
+	return rc;
+}
+
+static const struct file_operations smk_ambient_ops = {
+	.read		= smk_read_ambient,
+	.write		= smk_write_ambient,
+	.llseek		= default_llseek,
+};
+
+/*
+ * Seq_file operations for /smack/onlycap
+ */
+static void *onlycap_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smack_onlycap_list);
+}
+
+static void *onlycap_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smack_onlycap_list);
+}
+
+static int onlycap_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_known_list_elem *sklep =
+		list_entry_rcu(list, struct smack_known_list_elem, list);
+
+	seq_puts(s, sklep->smk_label->smk_known);
+	seq_putc(s, ' ');
+
+	return 0;
+}
+
+static const struct seq_operations onlycap_seq_ops = {
+	.start = onlycap_seq_start,
+	.next  = onlycap_seq_next,
+	.show  = onlycap_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+static int smk_open_onlycap(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &onlycap_seq_ops);
+}
+
+/**
+ * smk_list_swap_rcu - swap public list with a private one in RCU-safe way
+ * The caller must hold appropriate mutex to prevent concurrent modifications
+ * to the public list.
+ * Private list is assumed to be not accessible to other threads yet.
+ *
+ * @public: public list
+ * @private: private list
+ */
+static void smk_list_swap_rcu(struct list_head *public,
+			      struct list_head *private)
+{
+	struct list_head *first, *last;
+
+	if (list_empty(public)) {
+		list_splice_init_rcu(private, public, synchronize_rcu);
+	} else {
+		/* Remember public list before replacing it */
+		first = public->next;
+		last = public->prev;
+
+		/* Publish private list in place of public in RCU-safe way */
+		private->prev->next = public;
+		private->next->prev = public;
+		rcu_assign_pointer(public->next, private->next);
+		public->prev = private->prev;
+
+		synchronize_rcu();
+
+		/* When all readers are done with the old public list,
+		 * attach it in place of private */
+		private->next = first;
+		private->prev = last;
+		first->prev = private;
+		last->next = private;
+	}
+}
+
+/**
+ * smk_parse_label_list - parse list of Smack labels, separated by spaces
+ *
+ * @data: the string to parse
+ * @list: destination list
+ *
+ * Returns zero on success or error code, as appropriate
+ */
+static int smk_parse_label_list(char *data, struct list_head *list)
+{
+	char *tok;
+	struct smack_known *skp;
+	struct smack_known_list_elem *sklep;
+
+	while ((tok = strsep(&data, " ")) != NULL) {
+		if (!*tok)
+			continue;
+
+		skp = smk_import_entry(tok, 0);
+		if (IS_ERR(skp))
+			return PTR_ERR(skp);
+
+		sklep = kzalloc_obj(*sklep);
+		if (sklep == NULL)
+			return -ENOMEM;
+
+		sklep->smk_label = skp;
+		list_add(&sklep->list, list);
+	}
+
+	return 0;
+}
+
+/**
+ * smk_destroy_label_list - destroy a list of smack_known_list_elem
+ * @list: header pointer of the list to destroy
+ */
+void smk_destroy_label_list(struct list_head *list)
+{
+	struct smack_known_list_elem *sklep;
+	struct smack_known_list_elem *sklep2;
+
+	list_for_each_entry_safe(sklep, sklep2, list, list)
+		kfree(sklep);
+
+	INIT_LIST_HEAD(list);
+}
+
+/**
+ * smk_write_onlycap - write() for smackfs/onlycap
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_onlycap(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	char *data;
+	LIST_HEAD(list_tmp);
+	int rc;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	rc = smk_parse_label_list(data, &list_tmp);
+	kfree(data);
+
+	/*
+	 * Clear the smack_onlycap on invalid label errors. This means
+	 * that we can pass a null string to unset the onlycap value.
+	 *
+	 * Importing will also reject a label beginning with '-',
+	 * so "-usecapabilities" will also work.
+	 *
+	 * But do so only on invalid label, not on system errors.
+	 * The invalid label must be first to count as clearing attempt.
+	 */
+	if (!rc || (rc == -EINVAL && list_empty(&list_tmp))) {
+		mutex_lock(&smack_onlycap_lock);
+		smk_list_swap_rcu(&smack_onlycap_list, &list_tmp);
+		mutex_unlock(&smack_onlycap_lock);
+		rc = count;
+	}
+
+	smk_destroy_label_list(&list_tmp);
+
+	return rc;
+}
+
+static const struct file_operations smk_onlycap_ops = {
+	.open		= smk_open_onlycap,
+	.read		= seq_read,
+	.write		= smk_write_onlycap,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+/**
+ * smk_read_unconfined - read() for smackfs/unconfined
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @cn: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_unconfined(struct file *filp, char __user *buf,
+					size_t cn, loff_t *ppos)
+{
+	char *smack = "";
+	ssize_t rc = -EINVAL;
+	int asize;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (smack_unconfined != NULL)
+		smack = smack_unconfined->smk_known;
+
+	asize = strlen(smack) + 1;
+
+	if (cn >= asize)
+		rc = simple_read_from_buffer(buf, cn, ppos, smack, asize);
+
+	return rc;
+}
+
+/**
+ * smk_write_unconfined - write() for smackfs/unconfined
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_unconfined(struct file *file, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	char *data;
+	struct smack_known *skp;
+	int rc = count;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	/*
+	 * Clear the smack_unconfined on invalid label errors. This means
+	 * that we can pass a null string to unset the unconfined value.
+	 *
+	 * Importing will also reject a label beginning with '-',
+	 * so "-confine" will also work.
+	 *
+	 * But do so only on invalid label, not on system errors.
+	 */
+	skp = smk_import_entry(data, count);
+	if (PTR_ERR(skp) == -EINVAL)
+		skp = NULL;
+	else if (IS_ERR(skp)) {
+		rc = PTR_ERR(skp);
+		goto freeout;
+	}
+
+	smack_unconfined = skp;
+
+freeout:
+	kfree(data);
+	return rc;
+}
+
+static const struct file_operations smk_unconfined_ops = {
+	.read		= smk_read_unconfined,
+	.write		= smk_write_unconfined,
+	.llseek		= default_llseek,
+};
+#endif /* CONFIG_SECURITY_SMACK_BRINGUP */
+
+#ifdef CONFIG_AUDIT
+/**
+ * smk_read_logging - read() for /smack/logging
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_logging(struct file *filp, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char temp[32];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d\n", log_policy);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+	return rc;
+}
+
+/**
+ * smk_write_logging - write() for /smack/logging
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_logging(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	int i, ret;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
+
+	if (i < 0 || i > 3)
+		return -EINVAL;
+	log_policy = i;
+	return count;
+}
+
+
+
+static const struct file_operations smk_logging_ops = {
+	.read		= smk_read_logging,
+	.write		= smk_write_logging,
+	.llseek		= default_llseek,
+};
+#endif /* CONFIG_AUDIT */
+
+/*
+ * Seq_file read operations for /smack/load-self
+ */
+
+static void *load_self_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_start(s, pos, &tsp->smk_rules);
+}
+
+static void *load_self_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_next(s, v, pos, &tsp->smk_rules);
+}
+
+static int load_self_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp =
+		list_entry_rcu(list, struct smack_rule, list);
+
+	smk_rule_show(s, srp, SMK_LABELLEN);
+
+	return 0;
+}
+
+static const struct seq_operations load_self_seq_ops = {
+	.start = load_self_seq_start,
+	.next  = load_self_seq_next,
+	.show  = load_self_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+
+/**
+ * smk_open_load_self - open() for /smack/load-self2
+ * @inode: inode structure representing file
+ * @file: "load" file pointer
+ *
+ * For reading, use load_seq_* seq_file reading operations.
+ */
+static int smk_open_load_self(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load_self_seq_ops);
+}
+
+/**
+ * smk_write_load_self - write() for /smack/load-self
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load_self(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_write_rules_list(file, buf, count, ppos, &tsp->smk_rules,
+				    &tsp->smk_rules_lock, SMK_FIXED24_FMT);
+}
+
+static const struct file_operations smk_load_self_ops = {
+	.open           = smk_open_load_self,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_load_self,
+	.release        = seq_release,
+};
+
+/**
+ * smk_user_access - handle access check transaction
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ * @format: /smack/load or /smack/load2 or /smack/change-rule format.
+ */
+static ssize_t smk_user_access(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos, int format)
+{
+	struct smack_parsed_rule rule;
+	char *data;
+	int res;
+
+	data = simple_transaction_get(file, buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	if (format == SMK_FIXED24_FMT) {
+		if (count < SMK_LOADLEN)
+			return -EINVAL;
+		res = smk_parse_rule(data, &rule, 0);
+	} else {
+		/*
+		 * simple_transaction_get() returns null-terminated data
+		 */
+		res = smk_parse_long_rule(data, &rule, 0, 3);
+	}
+
+	if (res >= 0)
+		res = smk_access(rule.smk_subject, rule.smk_object,
+				 rule.smk_access1, NULL);
+	else if (res != -ENOENT)
+		return res;
+
+	/*
+	 * smk_access() can return a value > 0 in the "bringup" case.
+	 */
+	data[0] = res >= 0 ? '1' : '0';
+	data[1] = '\0';
+
+	simple_transaction_set(file, 2);
+
+	if (format == SMK_FIXED24_FMT)
+		return SMK_LOADLEN;
+	return count;
+}
+
+/**
+ * smk_write_access - handle access check transaction
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_access(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	return smk_user_access(file, buf, count, ppos, SMK_FIXED24_FMT);
+}
+
+static const struct file_operations smk_access_ops = {
+	.write		= smk_write_access,
+	.read		= simple_transaction_read,
+	.release	= simple_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+
+/*
+ * Seq_file read operations for /smack/load2
+ */
+
+static int load2_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp;
+	struct smack_known *skp =
+		list_entry_rcu(list, struct smack_known, list);
+
+	list_for_each_entry_rcu(srp, &skp->smk_rules, list)
+		smk_rule_show(s, srp, SMK_LONGLABEL);
+
+	return 0;
+}
+
+static const struct seq_operations load2_seq_ops = {
+	.start = load2_seq_start,
+	.next  = load2_seq_next,
+	.show  = load2_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_load2 - open() for /smack/load2
+ * @inode: inode structure representing file
+ * @file: "load2" file pointer
+ *
+ * For reading, use load2_seq_* seq_file reading operations.
+ */
+static int smk_open_load2(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load2_seq_ops);
+}
+
+/**
+ * smk_write_load2 - write() for /smack/load2
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load2(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	/*
+	 * Must have privilege.
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	return smk_write_rules_list(file, buf, count, ppos, NULL, NULL,
+				    SMK_LONG_FMT);
+}
+
+static const struct file_operations smk_load2_ops = {
+	.open           = smk_open_load2,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_load2,
+	.release        = seq_release,
+};
+
+/*
+ * Seq_file read operations for /smack/load-self2
+ */
+
+static void *load_self2_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_start(s, pos, &tsp->smk_rules);
+}
+
+static void *load_self2_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_next(s, v, pos, &tsp->smk_rules);
+}
+
+static int load_self2_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_rule *srp =
+		list_entry_rcu(list, struct smack_rule, list);
+
+	smk_rule_show(s, srp, SMK_LONGLABEL);
+
+	return 0;
+}
+
+static const struct seq_operations load_self2_seq_ops = {
+	.start = load_self2_seq_start,
+	.next  = load_self2_seq_next,
+	.show  = load_self2_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_load_self2 - open() for /smack/load-self2
+ * @inode: inode structure representing file
+ * @file: "load" file pointer
+ *
+ * For reading, use load_seq_* seq_file reading operations.
+ */
+static int smk_open_load_self2(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &load_self2_seq_ops);
+}
+
+/**
+ * smk_write_load_self2 - write() for /smack/load-self2
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_load_self2(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_write_rules_list(file, buf, count, ppos, &tsp->smk_rules,
+				    &tsp->smk_rules_lock, SMK_LONG_FMT);
+}
+
+static const struct file_operations smk_load_self2_ops = {
+	.open           = smk_open_load_self2,
+	.read		= seq_read,
+	.llseek         = seq_lseek,
+	.write		= smk_write_load_self2,
+	.release        = seq_release,
+};
+
+/**
+ * smk_write_access2 - handle access check transaction
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_access2(struct file *file, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	return smk_user_access(file, buf, count, ppos, SMK_LONG_FMT);
+}
+
+static const struct file_operations smk_access2_ops = {
+	.write		= smk_write_access2,
+	.read		= simple_transaction_read,
+	.release	= simple_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+/**
+ * smk_write_revoke_subj - write() for /smack/revoke-subject
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_revoke_subj(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char *data;
+	const char *cp;
+	struct smack_known *skp;
+	struct smack_rule *sp;
+	struct list_head *rule_list;
+	struct mutex *rule_lock;
+	int rc = count;
+
+	if (*ppos != 0)
+		return -EINVAL;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (count == 0 || count > SMK_LONGLABEL)
+		return -EINVAL;
+
+	data = memdup_user(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	cp = smk_parse_smack(data, count);
+	if (IS_ERR(cp)) {
+		rc = PTR_ERR(cp);
+		goto out_data;
+	}
+
+	skp = smk_find_entry(cp);
+	if (skp == NULL)
+		goto out_cp;
+
+	rule_list = &skp->smk_rules;
+	rule_lock = &skp->smk_rules_lock;
+
+	mutex_lock(rule_lock);
+
+	list_for_each_entry_rcu(sp, rule_list, list)
+		sp->smk_access = 0;
+
+	mutex_unlock(rule_lock);
+
+out_cp:
+	kfree(cp);
+out_data:
+	kfree(data);
+
+	return rc;
+}
+
+static const struct file_operations smk_revoke_subj_ops = {
+	.write		= smk_write_revoke_subj,
+	.read		= simple_transaction_read,
+	.release	= simple_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+/**
+ * smk_init_sysfs - initialize /sys/fs/smackfs
+ *
+ */
+static int smk_init_sysfs(void)
+{
+	return sysfs_create_mount_point(fs_kobj, "smackfs");
+}
+
+/**
+ * smk_write_change_rule - write() for /smack/change-rule
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_change_rule(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	/*
+	 * Must have privilege.
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	return smk_write_rules_list(file, buf, count, ppos, NULL, NULL,
+				    SMK_CHANGE_FMT);
+}
+
+static const struct file_operations smk_change_rule_ops = {
+	.write		= smk_write_change_rule,
+	.read		= simple_transaction_read,
+	.release	= simple_transaction_release,
+	.llseek		= generic_file_llseek,
+};
+
+/**
+ * smk_read_syslog - read() for smackfs/syslog
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @cn: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_syslog(struct file *filp, char __user *buf,
+				size_t cn, loff_t *ppos)
+{
+	struct smack_known *skp;
+	ssize_t rc = -EINVAL;
+	int asize;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (smack_syslog_label == NULL)
+		skp = &smack_known_star;
+	else
+		skp = smack_syslog_label;
+
+	asize = strlen(skp->smk_known) + 1;
+
+	if (cn >= asize)
+		rc = simple_read_from_buffer(buf, cn, ppos, skp->smk_known,
+						asize);
+
+	return rc;
+}
+
+/**
+ * smk_write_syslog - write() for smackfs/syslog
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t smk_write_syslog(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char *data;
+	struct smack_known *skp;
+	int rc = count;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	/* Enough data must be present */
+	if (count == 0 || count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	skp = smk_import_entry(data, count);
+	if (IS_ERR(skp))
+		rc = PTR_ERR(skp);
+	else
+		smack_syslog_label = skp;
+
+	kfree(data);
+	return rc;
+}
+
+static const struct file_operations smk_syslog_ops = {
+	.read		= smk_read_syslog,
+	.write		= smk_write_syslog,
+	.llseek		= default_llseek,
+};
+
+/*
+ * Seq_file read operations for /smack/relabel-self
+ */
+
+static void *relabel_self_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_start(s, pos, &tsp->smk_relabel);
+}
+
+static void *relabel_self_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct task_smack *tsp = smack_cred(current_cred());
+
+	return smk_seq_next(s, v, pos, &tsp->smk_relabel);
+}
+
+static int relabel_self_seq_show(struct seq_file *s, void *v)
+{
+	struct list_head *list = v;
+	struct smack_known_list_elem *sklep =
+		list_entry(list, struct smack_known_list_elem, list);
+
+	seq_puts(s, sklep->smk_label->smk_known);
+	seq_putc(s, ' ');
+
+	return 0;
+}
+
+static const struct seq_operations relabel_self_seq_ops = {
+	.start = relabel_self_seq_start,
+	.next  = relabel_self_seq_next,
+	.show  = relabel_self_seq_show,
+	.stop  = smk_seq_stop,
+};
+
+/**
+ * smk_open_relabel_self - open() for /smack/relabel-self
+ * @inode: inode structure representing file
+ * @file: "relabel-self" file pointer
+ *
+ * Connect our relabel_self_seq_* operations with /smack/relabel-self
+ * file_operations
+ */
+static int smk_open_relabel_self(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &relabel_self_seq_ops);
+}
+
+/**
+ * smk_write_relabel_self - write() for /smack/relabel-self
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ *
+ */
+static ssize_t smk_write_relabel_self(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	char *data;
+	int rc;
+	LIST_HEAD(list_tmp);
+
+	/*
+	 * Must have privilege.
+	 */
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	/*
+	 * No partial write.
+	 * Enough data must be present.
+	 */
+	if (*ppos != 0)
+		return -EINVAL;
+	if (count == 0 || count > PAGE_SIZE)
+		return -EINVAL;
+
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
+	rc = smk_parse_label_list(data, &list_tmp);
+	kfree(data);
+
+	if (!rc || (rc == -EINVAL && list_empty(&list_tmp))) {
+		struct cred *new;
+		struct task_smack *tsp;
+
+		new = prepare_creds();
+		if (!new) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		tsp = smack_cred(new);
+		smk_destroy_label_list(&tsp->smk_relabel);
+		list_splice(&list_tmp, &tsp->smk_relabel);
+		commit_creds(new);
+		return count;
+	}
+out:
+	smk_destroy_label_list(&list_tmp);
+	return rc;
+}
+
+static const struct file_operations smk_relabel_self_ops = {
+	.open		= smk_open_relabel_self,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.write		= smk_write_relabel_self,
+	.release	= seq_release,
+};
+
+/**
+ * smk_read_ptrace - read() for /smack/ptrace
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t smk_read_ptrace(struct file *filp, char __user *buf,
+			       size_t count, loff_t *ppos)
+{
+	char temp[32];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d\n", smack_ptrace_rule);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+	return rc;
+}
+
+/**
+ * smk_write_ptrace - write() for /smack/ptrace
+ * @file: file pointer
+ * @buf: data from user space
+ * @count: bytes sent
+ * @ppos: where to start - must be 0
+ */
+static ssize_t smk_write_ptrace(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	int i, ret;
+
+	if (!smack_privileged(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	ret = kstrtos32_from_user(buf, count, 10, &i);
+	if (unlikely(ret))
+		return ret;
+
+	if (i < SMACK_PTRACE_DEFAULT || i > SMACK_PTRACE_MAX)
+		return -EINVAL;
+	smack_ptrace_rule = i;
+
+	return count;
+}
+
+static const struct file_operations smk_ptrace_ops = {
+	.write		= smk_write_ptrace,
+	.read		= smk_read_ptrace,
+	.llseek		= default_llseek,
+};
+
+/**
+ * smk_fill_super - fill the smackfs superblock
+ * @sb: the empty superblock
+ * @fc: unused
+ *
+ * Fill in the well known entries for the smack filesystem
+ *
+ * Returns 0 on success, an error code on failure
+ */
+static int smk_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	int rc;
+
+	static const struct tree_descr smack_files[] = {
+		[SMK_LOAD] = {
+			"load", &smk_load_ops, S_IRUGO|S_IWUSR},
+		[SMK_CIPSO] = {
+			"cipso", &smk_cipso_ops, S_IRUGO|S_IWUSR},
+		[SMK_DOI] = {
+			"doi", &smk_doi_ops, S_IRUGO|S_IWUSR},
+		[SMK_DIRECT] = {
+			"direct", &smk_cipso_auto_level_ops, 0644},
+		[SMK_AMBIENT] = {
+			"ambient", &smk_ambient_ops, S_IRUGO|S_IWUSR},
+		[SMK_NET4ADDR] = {
+			"netlabel", &smk_net4addr_ops, S_IRUGO|S_IWUSR},
+		[SMK_ONLYCAP] = {
+			"onlycap", &smk_onlycap_ops, S_IRUGO|S_IWUSR},
+#ifdef CONFIG_AUDIT
+		[SMK_LOGGING] = {
+			"logging", &smk_logging_ops, S_IRUGO|S_IWUSR},
+#endif /* CONFIG_AUDIT */
+		[SMK_LOAD_SELF] = {
+			"load-self", &smk_load_self_ops, S_IRUGO|S_IWUGO},
+		[SMK_ACCESSES] = {
+			"access", &smk_access_ops, S_IRUGO|S_IWUGO},
+		[SMK_MAPPED] = {
+			"mapped", &smk_cipso_auto_level_ops, 0644},
+		[SMK_LOAD2] = {
+			"load2", &smk_load2_ops, S_IRUGO|S_IWUSR},
+		[SMK_LOAD_SELF2] = {
+			"load-self2", &smk_load_self2_ops, S_IRUGO|S_IWUGO},
+		[SMK_ACCESS2] = {
+			"access2", &smk_access2_ops, S_IRUGO|S_IWUGO},
+		[SMK_CIPSO2] = {
+			"cipso2", &smk_cipso2_ops, S_IRUGO|S_IWUSR},
+		[SMK_REVOKE_SUBJ] = {
+			"revoke-subject", &smk_revoke_subj_ops,
+			S_IRUGO|S_IWUSR},
+		[SMK_CHANGE_RULE] = {
+			"change-rule", &smk_change_rule_ops, S_IRUGO|S_IWUSR},
+		[SMK_SYSLOG] = {
+			"syslog", &smk_syslog_ops, S_IRUGO|S_IWUSR},
+		[SMK_PTRACE] = {
+			"ptrace", &smk_ptrace_ops, S_IRUGO|S_IWUSR},
+#ifdef CONFIG_SECURITY_SMACK_BRINGUP
+		[SMK_UNCONFINED] = {
+			"unconfined", &smk_unconfined_ops, S_IRUGO|S_IWUSR},
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+		[SMK_NET6ADDR] = {
+			"ipv6host", &smk_net6addr_ops, S_IRUGO|S_IWUSR},
+#endif /* CONFIG_IPV6 */
+		[SMK_RELABEL_SELF] = {
+			"relabel-self", &smk_relabel_self_ops,
+				S_IRUGO|S_IWUGO},
+		/* last one */
+			{""}
+	};
+
+	rc = simple_fill_super(sb, SMACK_MAGIC, smack_files);
+	if (rc != 0) {
+		printk(KERN_ERR "%s failed %d while creating inodes\n",
+			__func__, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/**
+ * smk_get_tree - get the smackfs superblock
+ * @fc: The mount context, including any options
+ *
+ * Just passes everything along.
+ *
+ * Returns what the lower level code does.
+ */
+static int smk_get_tree(struct fs_context *fc)
+{
+	return get_tree_single(fc, smk_fill_super);
+}
+
+static const struct fs_context_operations smk_context_ops = {
+	.get_tree	= smk_get_tree,
+};
+
+/**
+ * smk_init_fs_context - Initialise a filesystem context for smackfs
+ * @fc: The blank mount context
+ */
+static int smk_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &smk_context_ops;
+	return 0;
+}
+
+static struct file_system_type smk_fs_type = {
+	.name		= "smackfs",
+	.init_fs_context = smk_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+static struct vfsmount *smackfs_mount;
+
+/**
+ * init_smk_fs - get the smackfs superblock
+ *
+ * register the smackfs
+ *
+ * Do not register smackfs if Smack wasn't enabled
+ * on boot. We can not put this method normally under the
+ * smack_init() code path since the security subsystem get
+ * initialized before the vfs caches.
+ *
+ * Returns true if we were not chosen on boot or if
+ * we were chosen and filesystem registration succeeded.
+ */
+int __init init_smk_fs(void)
+{
+	int err;
+	int rc;
+	struct netlbl_audit nai;
+
+	if (smack_enabled == 0)
+		return 0;
+
+	err = smk_init_sysfs();
+	if (err)
+		printk(KERN_ERR "smackfs: sysfs mountpoint problem.\n");
+
+	err = register_filesystem(&smk_fs_type);
+	if (!err) {
+		smackfs_mount = kern_mount(&smk_fs_type);
+		if (IS_ERR(smackfs_mount)) {
+			printk(KERN_ERR "smackfs:  could not mount!\n");
+			err = PTR_ERR(smackfs_mount);
+			smackfs_mount = NULL;
+		}
+	}
+
+	smk_netlabel_audit_set(&nai);
+	(void) netlbl_cfg_map_del(NULL, PF_INET, NULL, NULL, &nai);
+	(void) smk_cipso_doi(SMACK_CIPSO_DOI_DEFAULT,
+			     GFP_KERNEL | __GFP_NOFAIL);
+	smk_unlbl_ambient(NULL);
+
+	rc = smack_populate_secattr(&smack_known_floor);
+	if (err == 0 && rc < 0)
+		err = rc;
+	rc = smack_populate_secattr(&smack_known_hat);
+	if (err == 0 && rc < 0)
+		err = rc;
+	rc = smack_populate_secattr(&smack_known_huh);
+	if (err == 0 && rc < 0)
+		err = rc;
+	rc = smack_populate_secattr(&smack_known_star);
+	if (err == 0 && rc < 0)
+		err = rc;
+	rc = smack_populate_secattr(&smack_known_web);
+	if (err == 0 && rc < 0)
+		err = rc;
+
+	return err;
+}
diff --git a/security/tomoyo/.gitignore b/security/tomoyo/.gitignore
new file mode 100644
index 000000000..9f300cdce
--- /dev/null
+++ b/security/tomoyo/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+builtin-policy.h
+policy/*.conf
diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig
new file mode 100644
index 000000000..1e0dd1a6d
--- /dev/null
+++ b/security/tomoyo/Kconfig
@@ -0,0 +1,85 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_TOMOYO
+	bool "TOMOYO Linux Support"
+	depends on SECURITY
+	depends on NET
+	select SECURITYFS
+	select SECURITY_PATH
+	select SECURITY_NETWORK
+	default n
+	help
+	  This selects TOMOYO Linux, pathname-based access control.
+	  Required userspace tools and further information may be
+	  found at <https://tomoyo.sourceforge.net/>.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY
+	int "Default maximal count for learning mode"
+	default 2048
+	range 0 2147483647
+	depends on SECURITY_TOMOYO
+	help
+	  This is the default value for maximal ACL entries
+	  that are automatically appended into policy at "learning mode".
+	  Some programs access thousands of objects, so running
+	  such programs in "learning mode" dulls the system response
+	  and consumes much memory.
+	  This is the safeguard for such programs.
+
+config SECURITY_TOMOYO_MAX_AUDIT_LOG
+	int "Default maximal count for audit log"
+	default 1024
+	range 0 2147483647
+	depends on SECURITY_TOMOYO
+	help
+	  This is the default value for maximal entries for
+	  audit logs that the kernel can hold on memory.
+	  You can read the log via /sys/kernel/security/tomoyo/audit.
+	  If you don't need audit logs, you may set this value to 0.
+
+config SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	bool "Activate without calling userspace policy loader."
+	default n
+	depends on SECURITY_TOMOYO
+	help
+	  Say Y here if you want to activate access control as soon as built-in
+	  policy was loaded. This option will be useful for systems where
+	  operations which can lead to the hijacking of the boot sequence are
+	  needed before loading the policy. For example, you can activate
+	  immediately after loading the fixed part of policy which will allow
+	  only operations needed for mounting a partition which contains the
+	  variant part of policy and verifying (e.g. running GPG check) and
+	  loading the variant part of policy. Since you can start using
+	  enforcing mode from the beginning, you can reduce the possibility of
+	  hijacking the boot sequence.
+
+config SECURITY_TOMOYO_POLICY_LOADER
+	string "Location of userspace policy loader"
+	default "/sbin/tomoyo-init"
+	depends on SECURITY_TOMOYO
+	depends on !SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	help
+	  This is the default pathname of policy loader which is called before
+	  activation. You can override this setting via TOMOYO_loader= kernel
+	  command line option.
+
+config SECURITY_TOMOYO_ACTIVATION_TRIGGER
+	string "Trigger for calling userspace policy loader"
+	default "/sbin/init"
+	depends on SECURITY_TOMOYO
+	depends on !SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	help
+	  This is the default pathname of activation trigger.
+	  You can override this setting via TOMOYO_trigger= kernel command line
+	  option. For example, if you pass init=/bin/systemd option, you may
+	  want to also pass TOMOYO_trigger=/bin/systemd option.
+
+config SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
+	bool "Use insecure built-in settings for fuzzing tests."
+	default n
+	depends on SECURITY_TOMOYO
+	select SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	help
+	  Enabling this option forces minimal built-in policy and disables
+	  domain/program checks for run-time policy modifications. Please enable
+	  this option only if this kernel is built for doing fuzzing tests.
diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile
new file mode 100644
index 000000000..e3c0f853a
--- /dev/null
+++ b/security/tomoyo/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+CONTEXT_ANALYSIS := y
+
+obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o
+
+targets += builtin-policy.h
+
+quiet_cmd_policy = POLICY  $@
+      cmd_policy = { \
+	$(foreach x, profile exception_policy domain_policy manager stat, \
+	printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \
+	sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null);  \
+	printf '\t"";\n';) \
+	} > $@
+
+$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE
+	$(call if_changed,policy)
+
+ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
+$(obj)/common.o: $(obj)/builtin-policy.h
+endif
diff --git a/security/tomoyo/audit.c b/security/tomoyo/audit.c
new file mode 100644
index 000000000..1fba46aa3
--- /dev/null
+++ b/security/tomoyo/audit.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/audit.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/slab.h>
+
+/**
+ * tomoyo_print_bprm - Print "struct linux_binprm" for auditing.
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ * @dump: Pointer to "struct tomoyo_page_dump".
+ *
+ * Returns the contents of @bprm on success, NULL otherwise.
+ *
+ * This function uses kzalloc(), so caller must kfree() if this function
+ * didn't return NULL.
+ */
+static char *tomoyo_print_bprm(struct linux_binprm *bprm,
+			       struct tomoyo_page_dump *dump)
+{
+	static const int tomoyo_buffer_len = 4096 * 2;
+	char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS);
+	char *cp;
+	char *last_start;
+	int len;
+	unsigned long pos = bprm->p;
+	int offset = pos % PAGE_SIZE;
+	int argv_count = bprm->argc;
+	int envp_count = bprm->envc;
+	bool truncated = false;
+
+	if (!buffer)
+		return NULL;
+	len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ");
+	cp = buffer + len;
+	if (!argv_count) {
+		memmove(cp, "} envp[]={ ", 11);
+		cp += 11;
+	}
+	last_start = cp;
+	while (argv_count || envp_count) {
+		if (!tomoyo_dump_page(bprm, pos, dump))
+			goto out;
+		pos += PAGE_SIZE - offset;
+		/* Read. */
+		while (offset < PAGE_SIZE) {
+			const char *kaddr = dump->data;
+			const unsigned char c = kaddr[offset++];
+
+			if (cp == last_start)
+				*cp++ = '"';
+			if (cp >= buffer + tomoyo_buffer_len - 32) {
+				/* Reserve some room for "..." string. */
+				truncated = true;
+			} else if (c == '\\') {
+				*cp++ = '\\';
+				*cp++ = '\\';
+			} else if (c > ' ' && c < 127) {
+				*cp++ = c;
+			} else if (!c) {
+				*cp++ = '"';
+				*cp++ = ' ';
+				last_start = cp;
+			} else {
+				*cp++ = '\\';
+				*cp++ = (c >> 6) + '0';
+				*cp++ = ((c >> 3) & 7) + '0';
+				*cp++ = (c & 7) + '0';
+			}
+			if (c)
+				continue;
+			if (argv_count) {
+				if (--argv_count == 0) {
+					if (truncated) {
+						cp = last_start;
+						memmove(cp, "... ", 4);
+						cp += 4;
+					}
+					memmove(cp, "} envp[]={ ", 11);
+					cp += 11;
+					last_start = cp;
+					truncated = false;
+				}
+			} else if (envp_count) {
+				if (--envp_count == 0) {
+					if (truncated) {
+						cp = last_start;
+						memmove(cp, "... ", 4);
+						cp += 4;
+					}
+				}
+			}
+			if (!argv_count && !envp_count)
+				break;
+		}
+		offset = 0;
+	}
+	*cp++ = '}';
+	*cp = '\0';
+	return buffer;
+out:
+	snprintf(buffer, tomoyo_buffer_len - 1,
+		 "argv[]={ ... } envp[]= { ... }");
+	return buffer;
+}
+
+/**
+ * tomoyo_filetype - Get string representation of file type.
+ *
+ * @mode: Mode value for stat().
+ *
+ * Returns file type string.
+ */
+static inline const char *tomoyo_filetype(const umode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+	case 0:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE];
+	case S_IFDIR:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY];
+	case S_IFLNK:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK];
+	case S_IFIFO:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO];
+	case S_IFSOCK:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET];
+	case S_IFBLK:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV];
+	case S_IFCHR:
+		return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV];
+	}
+	return "unknown"; /* This should not happen. */
+}
+
+/**
+ * tomoyo_print_header - Get header line of audit log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns string representation.
+ *
+ * This function uses kmalloc(), so caller must kfree() if this function
+ * didn't return NULL.
+ */
+static char *tomoyo_print_header(struct tomoyo_request_info *r)
+{
+	struct tomoyo_time stamp;
+	const pid_t gpid = task_pid_nr(current);
+	struct tomoyo_obj_info *obj = r->obj;
+	static const int tomoyo_buffer_len = 4096;
+	char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS);
+	int pos;
+	u8 i;
+
+	if (!buffer)
+		return NULL;
+
+	tomoyo_convert_time(ktime_get_real_seconds(), &stamp);
+
+	pos = snprintf(buffer, tomoyo_buffer_len - 1,
+		       "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }",
+		       stamp.year, stamp.month, stamp.day, stamp.hour,
+		       stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode],
+		       str_yes_no(r->granted), gpid, tomoyo_sys_getpid(),
+		       tomoyo_sys_getppid(),
+		       from_kuid(&init_user_ns, current_uid()),
+		       from_kgid(&init_user_ns, current_gid()),
+		       from_kuid(&init_user_ns, current_euid()),
+		       from_kgid(&init_user_ns, current_egid()),
+		       from_kuid(&init_user_ns, current_suid()),
+		       from_kgid(&init_user_ns, current_sgid()),
+		       from_kuid(&init_user_ns, current_fsuid()),
+		       from_kgid(&init_user_ns, current_fsgid()));
+	if (!obj)
+		goto no_obj_info;
+	if (!obj->validate_done) {
+		tomoyo_get_attributes(obj);
+		obj->validate_done = true;
+	}
+	for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) {
+		struct tomoyo_mini_stat *stat;
+		unsigned int dev;
+		umode_t mode;
+
+		if (!obj->stat_valid[i])
+			continue;
+		stat = &obj->stat[i];
+		dev = stat->dev;
+		mode = stat->mode;
+		if (i & 1) {
+			pos += snprintf(buffer + pos,
+					tomoyo_buffer_len - 1 - pos,
+					" path%u.parent={ uid=%u gid=%u ino=%llu perm=0%o }",
+					(i >> 1) + 1,
+					from_kuid(&init_user_ns, stat->uid),
+					from_kgid(&init_user_ns, stat->gid),
+					stat->ino, stat->mode & S_IALLUGO);
+			continue;
+		}
+		pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos,
+				" path%u={ uid=%u gid=%u ino=%llu major=%u minor=%u perm=0%o type=%s",
+				(i >> 1) + 1,
+				from_kuid(&init_user_ns, stat->uid),
+				from_kgid(&init_user_ns, stat->gid),
+				stat->ino, MAJOR(dev), MINOR(dev),
+				mode & S_IALLUGO, tomoyo_filetype(mode));
+		if (S_ISCHR(mode) || S_ISBLK(mode)) {
+			dev = stat->rdev;
+			pos += snprintf(buffer + pos,
+					tomoyo_buffer_len - 1 - pos,
+					" dev_major=%u dev_minor=%u",
+					MAJOR(dev), MINOR(dev));
+		}
+		pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos,
+				" }");
+	}
+no_obj_info:
+	if (pos < tomoyo_buffer_len - 1)
+		return buffer;
+	kfree(buffer);
+	return NULL;
+}
+
+/**
+ * tomoyo_init_log - Allocate buffer for audit logs.
+ *
+ * @r:    Pointer to "struct tomoyo_request_info".
+ * @len:  Buffer size needed for @fmt and @args.
+ * @fmt:  The printf()'s format string.
+ * @args: va_list structure for @fmt.
+ *
+ * Returns pointer to allocated memory.
+ *
+ * This function uses kzalloc(), so caller must kfree() if this function
+ * didn't return NULL.
+ */
+char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt,
+		      va_list args)
+{
+	char *buf = NULL;
+	char *bprm_info = NULL;
+	const char *header = NULL;
+	char *realpath = NULL;
+	const char *symlink = NULL;
+	int pos;
+	const char *domainname = r->domain->domainname->name;
+
+	header = tomoyo_print_header(r);
+	if (!header)
+		return NULL;
+	/* +10 is for '\n' etc. and '\0'. */
+	len += strlen(domainname) + strlen(header) + 10;
+	if (r->ee) {
+		struct file *file = r->ee->bprm->file;
+
+		realpath = tomoyo_realpath_from_path(&file->f_path);
+		bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump);
+		if (!realpath || !bprm_info)
+			goto out;
+		/* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */
+		len += strlen(realpath) + 80 + strlen(bprm_info);
+	} else if (r->obj && r->obj->symlink_target) {
+		symlink = r->obj->symlink_target->name;
+		/* +18 is for " symlink.target=\"%s\"" */
+		len += 18 + strlen(symlink);
+	}
+	len = kmalloc_size_roundup(len);
+	buf = kzalloc(len, GFP_NOFS);
+	if (!buf)
+		goto out;
+	len--;
+	pos = snprintf(buf, len, "%s", header);
+	if (realpath) {
+		struct linux_binprm *bprm = r->ee->bprm;
+
+		pos += snprintf(buf + pos, len - pos,
+				" exec={ realpath=\"%s\" argc=%d envc=%d %s }",
+				realpath, bprm->argc, bprm->envc, bprm_info);
+	} else if (symlink)
+		pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"",
+				symlink);
+	pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname);
+	vsnprintf(buf + pos, len - pos, fmt, args);
+out:
+	kfree(realpath);
+	kfree(bprm_info);
+	kfree(header);
+	return buf;
+}
+
+/* Wait queue for /sys/kernel/security/tomoyo/audit. */
+static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait);
+
+/* Structure for audit log. */
+struct tomoyo_log {
+	struct list_head list;
+	char *log;
+	int size;
+};
+
+/* The list for "struct tomoyo_log". */
+static LIST_HEAD(tomoyo_log);
+
+/* Lock for "struct list_head tomoyo_log". */
+static DEFINE_SPINLOCK(tomoyo_log_lock);
+
+/* Length of "struct list_head tomoyo_log". */
+static unsigned int tomoyo_log_count;
+
+/**
+ * tomoyo_get_audit - Get audit mode.
+ *
+ * @ns:          Pointer to "struct tomoyo_policy_namespace".
+ * @profile:     Profile number.
+ * @index:       Index number of functionality.
+ * @matched_acl: Pointer to "struct tomoyo_acl_info".
+ * @is_granted:  True if granted log, false otherwise.
+ *
+ * Returns true if this request should be audited, false otherwise.
+ */
+static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns,
+			     const u8 profile, const u8 index,
+			     const struct tomoyo_acl_info *matched_acl,
+			     const bool is_granted)
+{
+	u8 mode;
+	const u8 category = tomoyo_index2category[index] +
+		TOMOYO_MAX_MAC_INDEX;
+	struct tomoyo_profile *p;
+
+	if (!tomoyo_policy_loaded)
+		return false;
+	p = tomoyo_profile(ns, profile);
+	if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG])
+		return false;
+	if (is_granted && matched_acl && matched_acl->cond &&
+	    matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO)
+		return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES;
+	mode = p->config[index];
+	if (mode == TOMOYO_CONFIG_USE_DEFAULT)
+		mode = p->config[category];
+	if (mode == TOMOYO_CONFIG_USE_DEFAULT)
+		mode = p->default_config;
+	if (is_granted)
+		return mode & TOMOYO_CONFIG_WANT_GRANT_LOG;
+	return mode & TOMOYO_CONFIG_WANT_REJECT_LOG;
+}
+
+/**
+ * tomoyo_write_log2 - Write an audit log.
+ *
+ * @r:    Pointer to "struct tomoyo_request_info".
+ * @len:  Buffer size needed for @fmt and @args.
+ * @fmt:  The printf()'s format string.
+ * @args: va_list structure for @fmt.
+ *
+ * Returns nothing.
+ */
+void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt,
+		       va_list args)
+{
+	char *buf;
+	struct tomoyo_log *entry;
+	bool quota_exceeded = false;
+
+	if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type,
+			      r->matched_acl, r->granted))
+		goto out;
+	buf = tomoyo_init_log(r, len, fmt, args);
+	if (!buf)
+		goto out;
+	entry = kzalloc_obj(*entry, GFP_NOFS);
+	if (!entry) {
+		kfree(buf);
+		goto out;
+	}
+	entry->log = buf;
+	len = kmalloc_size_roundup(strlen(buf) + 1);
+	/*
+	 * The entry->size is used for memory quota checks.
+	 * Don't go beyond strlen(entry->log).
+	 */
+	entry->size = len + kmalloc_size_roundup(sizeof(*entry));
+	spin_lock(&tomoyo_log_lock);
+	if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] &&
+	    tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >=
+	    tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) {
+		quota_exceeded = true;
+	} else {
+		tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size;
+		list_add_tail(&entry->list, &tomoyo_log);
+		tomoyo_log_count++;
+	}
+	spin_unlock(&tomoyo_log_lock);
+	if (quota_exceeded) {
+		kfree(buf);
+		kfree(entry);
+		goto out;
+	}
+	wake_up(&tomoyo_log_wait);
+out:
+	return;
+}
+
+/**
+ * tomoyo_write_log - Write an audit log.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @fmt: The printf()'s format string, followed by parameters.
+ *
+ * Returns nothing.
+ */
+void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+
+	va_start(args, fmt);
+	len = vsnprintf(NULL, 0, fmt, args) + 1;
+	va_end(args);
+	va_start(args, fmt);
+	tomoyo_write_log2(r, len, fmt, args);
+	va_end(args);
+}
+
+/**
+ * tomoyo_read_log - Read an audit log.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+void tomoyo_read_log(struct tomoyo_io_buffer *head)
+{
+	struct tomoyo_log *ptr = NULL;
+
+	if (head->r.w_pos)
+		return;
+	kfree(head->read_buf);
+	head->read_buf = NULL;
+	spin_lock(&tomoyo_log_lock);
+	if (!list_empty(&tomoyo_log)) {
+		ptr = list_entry(tomoyo_log.next, typeof(*ptr), list);
+		list_del(&ptr->list);
+		tomoyo_log_count--;
+		tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size;
+	}
+	spin_unlock(&tomoyo_log_lock);
+	if (ptr) {
+		head->read_buf = ptr->log;
+		head->r.w[head->r.w_pos++] = head->read_buf;
+		kfree(ptr);
+	}
+}
+
+/**
+ * tomoyo_poll_log - Wait for an audit log.
+ *
+ * @file: Pointer to "struct file".
+ * @wait: Pointer to "poll_table". Maybe NULL.
+ *
+ * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log.
+ */
+__poll_t tomoyo_poll_log(struct file *file, poll_table *wait)
+{
+	if (tomoyo_log_count)
+		return EPOLLIN | EPOLLRDNORM;
+	poll_wait(file, &tomoyo_log_wait, wait);
+	if (tomoyo_log_count)
+		return EPOLLIN | EPOLLRDNORM;
+	return 0;
+}
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
new file mode 100644
index 000000000..fdaeaff01
--- /dev/null
+++ b/security/tomoyo/common.c
@@ -0,0 +1,3025 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/common.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/uaccess.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <linux/string_helpers.h>
+#include "common.h"
+
+/* String table for operation mode. */
+const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE] = {
+	[TOMOYO_CONFIG_DISABLED]   = "disabled",
+	[TOMOYO_CONFIG_LEARNING]   = "learning",
+	[TOMOYO_CONFIG_PERMISSIVE] = "permissive",
+	[TOMOYO_CONFIG_ENFORCING]  = "enforcing"
+};
+
+/* String table for /sys/kernel/security/tomoyo/profile */
+const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX
+				       + TOMOYO_MAX_MAC_CATEGORY_INDEX] = {
+	/* CONFIG::file group */
+	[TOMOYO_MAC_FILE_EXECUTE]    = "execute",
+	[TOMOYO_MAC_FILE_OPEN]       = "open",
+	[TOMOYO_MAC_FILE_CREATE]     = "create",
+	[TOMOYO_MAC_FILE_UNLINK]     = "unlink",
+	[TOMOYO_MAC_FILE_GETATTR]    = "getattr",
+	[TOMOYO_MAC_FILE_MKDIR]      = "mkdir",
+	[TOMOYO_MAC_FILE_RMDIR]      = "rmdir",
+	[TOMOYO_MAC_FILE_MKFIFO]     = "mkfifo",
+	[TOMOYO_MAC_FILE_MKSOCK]     = "mksock",
+	[TOMOYO_MAC_FILE_TRUNCATE]   = "truncate",
+	[TOMOYO_MAC_FILE_SYMLINK]    = "symlink",
+	[TOMOYO_MAC_FILE_MKBLOCK]    = "mkblock",
+	[TOMOYO_MAC_FILE_MKCHAR]     = "mkchar",
+	[TOMOYO_MAC_FILE_LINK]       = "link",
+	[TOMOYO_MAC_FILE_RENAME]     = "rename",
+	[TOMOYO_MAC_FILE_CHMOD]      = "chmod",
+	[TOMOYO_MAC_FILE_CHOWN]      = "chown",
+	[TOMOYO_MAC_FILE_CHGRP]      = "chgrp",
+	[TOMOYO_MAC_FILE_IOCTL]      = "ioctl",
+	[TOMOYO_MAC_FILE_CHROOT]     = "chroot",
+	[TOMOYO_MAC_FILE_MOUNT]      = "mount",
+	[TOMOYO_MAC_FILE_UMOUNT]     = "unmount",
+	[TOMOYO_MAC_FILE_PIVOT_ROOT] = "pivot_root",
+	/* CONFIG::network group */
+	[TOMOYO_MAC_NETWORK_INET_STREAM_BIND]       = "inet_stream_bind",
+	[TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN]     = "inet_stream_listen",
+	[TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT]    = "inet_stream_connect",
+	[TOMOYO_MAC_NETWORK_INET_DGRAM_BIND]        = "inet_dgram_bind",
+	[TOMOYO_MAC_NETWORK_INET_DGRAM_SEND]        = "inet_dgram_send",
+	[TOMOYO_MAC_NETWORK_INET_RAW_BIND]          = "inet_raw_bind",
+	[TOMOYO_MAC_NETWORK_INET_RAW_SEND]          = "inet_raw_send",
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND]       = "unix_stream_bind",
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN]     = "unix_stream_listen",
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT]    = "unix_stream_connect",
+	[TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND]        = "unix_dgram_bind",
+	[TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND]        = "unix_dgram_send",
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND]    = "unix_seqpacket_bind",
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN]  = "unix_seqpacket_listen",
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = "unix_seqpacket_connect",
+	/* CONFIG::misc group */
+	[TOMOYO_MAC_ENVIRON] = "env",
+	/* CONFIG group */
+	[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_FILE] = "file",
+	[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_NETWORK] = "network",
+	[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAC_CATEGORY_MISC] = "misc",
+};
+
+/* String table for conditions. */
+const char * const tomoyo_condition_keyword[TOMOYO_MAX_CONDITION_KEYWORD] = {
+	[TOMOYO_TASK_UID]             = "task.uid",
+	[TOMOYO_TASK_EUID]            = "task.euid",
+	[TOMOYO_TASK_SUID]            = "task.suid",
+	[TOMOYO_TASK_FSUID]           = "task.fsuid",
+	[TOMOYO_TASK_GID]             = "task.gid",
+	[TOMOYO_TASK_EGID]            = "task.egid",
+	[TOMOYO_TASK_SGID]            = "task.sgid",
+	[TOMOYO_TASK_FSGID]           = "task.fsgid",
+	[TOMOYO_TASK_PID]             = "task.pid",
+	[TOMOYO_TASK_PPID]            = "task.ppid",
+	[TOMOYO_EXEC_ARGC]            = "exec.argc",
+	[TOMOYO_EXEC_ENVC]            = "exec.envc",
+	[TOMOYO_TYPE_IS_SOCKET]       = "socket",
+	[TOMOYO_TYPE_IS_SYMLINK]      = "symlink",
+	[TOMOYO_TYPE_IS_FILE]         = "file",
+	[TOMOYO_TYPE_IS_BLOCK_DEV]    = "block",
+	[TOMOYO_TYPE_IS_DIRECTORY]    = "directory",
+	[TOMOYO_TYPE_IS_CHAR_DEV]     = "char",
+	[TOMOYO_TYPE_IS_FIFO]         = "fifo",
+	[TOMOYO_MODE_SETUID]          = "setuid",
+	[TOMOYO_MODE_SETGID]          = "setgid",
+	[TOMOYO_MODE_STICKY]          = "sticky",
+	[TOMOYO_MODE_OWNER_READ]      = "owner_read",
+	[TOMOYO_MODE_OWNER_WRITE]     = "owner_write",
+	[TOMOYO_MODE_OWNER_EXECUTE]   = "owner_execute",
+	[TOMOYO_MODE_GROUP_READ]      = "group_read",
+	[TOMOYO_MODE_GROUP_WRITE]     = "group_write",
+	[TOMOYO_MODE_GROUP_EXECUTE]   = "group_execute",
+	[TOMOYO_MODE_OTHERS_READ]     = "others_read",
+	[TOMOYO_MODE_OTHERS_WRITE]    = "others_write",
+	[TOMOYO_MODE_OTHERS_EXECUTE]  = "others_execute",
+	[TOMOYO_EXEC_REALPATH]        = "exec.realpath",
+	[TOMOYO_SYMLINK_TARGET]       = "symlink.target",
+	[TOMOYO_PATH1_UID]            = "path1.uid",
+	[TOMOYO_PATH1_GID]            = "path1.gid",
+	[TOMOYO_PATH1_INO]            = "path1.ino",
+	[TOMOYO_PATH1_MAJOR]          = "path1.major",
+	[TOMOYO_PATH1_MINOR]          = "path1.minor",
+	[TOMOYO_PATH1_PERM]           = "path1.perm",
+	[TOMOYO_PATH1_TYPE]           = "path1.type",
+	[TOMOYO_PATH1_DEV_MAJOR]      = "path1.dev_major",
+	[TOMOYO_PATH1_DEV_MINOR]      = "path1.dev_minor",
+	[TOMOYO_PATH2_UID]            = "path2.uid",
+	[TOMOYO_PATH2_GID]            = "path2.gid",
+	[TOMOYO_PATH2_INO]            = "path2.ino",
+	[TOMOYO_PATH2_MAJOR]          = "path2.major",
+	[TOMOYO_PATH2_MINOR]          = "path2.minor",
+	[TOMOYO_PATH2_PERM]           = "path2.perm",
+	[TOMOYO_PATH2_TYPE]           = "path2.type",
+	[TOMOYO_PATH2_DEV_MAJOR]      = "path2.dev_major",
+	[TOMOYO_PATH2_DEV_MINOR]      = "path2.dev_minor",
+	[TOMOYO_PATH1_PARENT_UID]     = "path1.parent.uid",
+	[TOMOYO_PATH1_PARENT_GID]     = "path1.parent.gid",
+	[TOMOYO_PATH1_PARENT_INO]     = "path1.parent.ino",
+	[TOMOYO_PATH1_PARENT_PERM]    = "path1.parent.perm",
+	[TOMOYO_PATH2_PARENT_UID]     = "path2.parent.uid",
+	[TOMOYO_PATH2_PARENT_GID]     = "path2.parent.gid",
+	[TOMOYO_PATH2_PARENT_INO]     = "path2.parent.ino",
+	[TOMOYO_PATH2_PARENT_PERM]    = "path2.parent.perm",
+};
+
+/* String table for PREFERENCE keyword. */
+static const char * const tomoyo_pref_keywords[TOMOYO_MAX_PREF] = {
+	[TOMOYO_PREF_MAX_AUDIT_LOG]      = "max_audit_log",
+	[TOMOYO_PREF_MAX_LEARNING_ENTRY] = "max_learning_entry",
+};
+
+/* String table for path operation. */
+const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION] = {
+	[TOMOYO_TYPE_EXECUTE]    = "execute",
+	[TOMOYO_TYPE_READ]       = "read",
+	[TOMOYO_TYPE_WRITE]      = "write",
+	[TOMOYO_TYPE_APPEND]     = "append",
+	[TOMOYO_TYPE_UNLINK]     = "unlink",
+	[TOMOYO_TYPE_GETATTR]    = "getattr",
+	[TOMOYO_TYPE_RMDIR]      = "rmdir",
+	[TOMOYO_TYPE_TRUNCATE]   = "truncate",
+	[TOMOYO_TYPE_SYMLINK]    = "symlink",
+	[TOMOYO_TYPE_CHROOT]     = "chroot",
+	[TOMOYO_TYPE_UMOUNT]     = "unmount",
+};
+
+/* String table for socket's operation. */
+const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION] = {
+	[TOMOYO_NETWORK_BIND]    = "bind",
+	[TOMOYO_NETWORK_LISTEN]  = "listen",
+	[TOMOYO_NETWORK_CONNECT] = "connect",
+	[TOMOYO_NETWORK_SEND]    = "send",
+};
+
+/* String table for categories. */
+static const char * const tomoyo_category_keywords
+[TOMOYO_MAX_MAC_CATEGORY_INDEX] = {
+	[TOMOYO_MAC_CATEGORY_FILE]    = "file",
+	[TOMOYO_MAC_CATEGORY_NETWORK] = "network",
+	[TOMOYO_MAC_CATEGORY_MISC]    = "misc",
+};
+
+/* Permit policy management by non-root user? */
+static bool tomoyo_manage_by_non_root;
+
+/* Utility functions. */
+
+/**
+ * tomoyo_addprintf - strncat()-like-snprintf().
+ *
+ * @buffer: Buffer to write to. Must be '\0'-terminated.
+ * @len:    Size of @buffer.
+ * @fmt:    The printf()'s format string, followed by parameters.
+ *
+ * Returns nothing.
+ */
+__printf(3, 4)
+static void tomoyo_addprintf(char *buffer, int len, const char *fmt, ...)
+{
+	va_list args;
+	const int pos = strlen(buffer);
+
+	va_start(args, fmt);
+	vsnprintf(buffer + pos, len - pos - 1, fmt, args);
+	va_end(args);
+}
+
+/**
+ * tomoyo_flush - Flush queued string to userspace's buffer.
+ *
+ * @head:   Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns true if all data was flushed, false otherwise.
+ */
+static bool tomoyo_flush(struct tomoyo_io_buffer *head)
+{
+	while (head->r.w_pos) {
+		const char *w = head->r.w[0];
+		size_t len = strlen(w);
+
+		if (len) {
+			if (len > head->read_user_buf_avail)
+				len = head->read_user_buf_avail;
+			if (!len)
+				return false;
+			if (copy_to_user(head->read_user_buf, w, len))
+				return false;
+			head->read_user_buf_avail -= len;
+			head->read_user_buf += len;
+			w += len;
+		}
+		head->r.w[0] = w;
+		if (*w)
+			return false;
+		/* Add '\0' for audit logs and query. */
+		if (head->poll) {
+			if (!head->read_user_buf_avail ||
+			    copy_to_user(head->read_user_buf, "", 1))
+				return false;
+			head->read_user_buf_avail--;
+			head->read_user_buf++;
+		}
+		head->r.w_pos--;
+		for (len = 0; len < head->r.w_pos; len++)
+			head->r.w[len] = head->r.w[len + 1];
+	}
+	head->r.avail = 0;
+	return true;
+}
+
+/**
+ * tomoyo_set_string - Queue string to "struct tomoyo_io_buffer" structure.
+ *
+ * @head:   Pointer to "struct tomoyo_io_buffer".
+ * @string: String to print.
+ *
+ * Note that @string has to be kept valid until @head is kfree()d.
+ * This means that char[] allocated on stack memory cannot be passed to
+ * this function. Use tomoyo_io_printf() for char[] allocated on stack memory.
+ */
+static void tomoyo_set_string(struct tomoyo_io_buffer *head, const char *string)
+{
+	if (head->r.w_pos < TOMOYO_MAX_IO_READ_QUEUE) {
+		head->r.w[head->r.w_pos++] = string;
+		tomoyo_flush(head);
+	} else
+		WARN_ON(1);
+}
+
+static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt,
+			     ...) __printf(2, 3);
+
+/**
+ * tomoyo_io_printf - printf() to "struct tomoyo_io_buffer" structure.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @fmt:  The printf()'s format string, followed by parameters.
+ */
+static void tomoyo_io_printf(struct tomoyo_io_buffer *head, const char *fmt,
+			     ...)
+	__must_hold(&head->io_sem)
+{
+	va_list args;
+	size_t len;
+	size_t pos = head->r.avail;
+	int size = head->readbuf_size - pos;
+
+	if (size <= 0)
+		return;
+	va_start(args, fmt);
+	len = vsnprintf(head->read_buf + pos, size, fmt, args) + 1;
+	va_end(args);
+	if (pos + len >= head->readbuf_size) {
+		WARN_ON(1);
+		return;
+	}
+	head->r.avail += len;
+	tomoyo_set_string(head, head->read_buf + pos);
+}
+
+/**
+ * tomoyo_set_space - Put a space to "struct tomoyo_io_buffer" structure.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_set_space(struct tomoyo_io_buffer *head)
+{
+	tomoyo_set_string(head, " ");
+}
+
+/**
+ * tomoyo_set_lf - Put a line feed to "struct tomoyo_io_buffer" structure.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static bool tomoyo_set_lf(struct tomoyo_io_buffer *head)
+{
+	tomoyo_set_string(head, "\n");
+	return !head->r.w_pos;
+}
+
+/**
+ * tomoyo_set_slash - Put a shash to "struct tomoyo_io_buffer" structure.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_set_slash(struct tomoyo_io_buffer *head)
+{
+	tomoyo_set_string(head, "/");
+}
+
+/* List of namespaces. */
+LIST_HEAD(tomoyo_namespace_list);
+/* True if namespace other than tomoyo_kernel_namespace is defined. */
+static bool tomoyo_namespace_enabled;
+
+/**
+ * tomoyo_init_policy_namespace - Initialize namespace.
+ *
+ * @ns: Pointer to "struct tomoyo_policy_namespace".
+ *
+ * Returns nothing.
+ */
+void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns)
+{
+	unsigned int idx;
+
+	for (idx = 0; idx < TOMOYO_MAX_ACL_GROUPS; idx++)
+		INIT_LIST_HEAD(&ns->acl_group[idx]);
+	for (idx = 0; idx < TOMOYO_MAX_GROUP; idx++)
+		INIT_LIST_HEAD(&ns->group_list[idx]);
+	for (idx = 0; idx < TOMOYO_MAX_POLICY; idx++)
+		INIT_LIST_HEAD(&ns->policy_list[idx]);
+	ns->profile_version = 20150505;
+	tomoyo_namespace_enabled = !list_empty(&tomoyo_namespace_list);
+	list_add_tail_rcu(&ns->namespace_list, &tomoyo_namespace_list);
+}
+
+/**
+ * tomoyo_print_namespace - Print namespace header.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_print_namespace(struct tomoyo_io_buffer *head)
+{
+	if (!tomoyo_namespace_enabled)
+		return;
+	tomoyo_set_string(head,
+			  container_of(head->r.ns,
+				       struct tomoyo_policy_namespace,
+				       namespace_list)->name);
+	tomoyo_set_space(head);
+}
+
+/**
+ * tomoyo_print_name_union - Print a tomoyo_name_union.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @ptr:  Pointer to "struct tomoyo_name_union".
+ */
+static void tomoyo_print_name_union(struct tomoyo_io_buffer *head,
+				    const struct tomoyo_name_union *ptr)
+{
+	tomoyo_set_space(head);
+	if (ptr->group) {
+		tomoyo_set_string(head, "@");
+		tomoyo_set_string(head, ptr->group->group_name->name);
+	} else {
+		tomoyo_set_string(head, ptr->filename->name);
+	}
+}
+
+/**
+ * tomoyo_print_name_union_quoted - Print a tomoyo_name_union with a quote.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @ptr:  Pointer to "struct tomoyo_name_union".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_print_name_union_quoted(struct tomoyo_io_buffer *head,
+					   const struct tomoyo_name_union *ptr)
+{
+	if (ptr->group) {
+		tomoyo_set_string(head, "@");
+		tomoyo_set_string(head, ptr->group->group_name->name);
+	} else {
+		tomoyo_set_string(head, "\"");
+		tomoyo_set_string(head, ptr->filename->name);
+		tomoyo_set_string(head, "\"");
+	}
+}
+
+/**
+ * tomoyo_print_number_union_nospace - Print a tomoyo_number_union without a space.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @ptr:  Pointer to "struct tomoyo_number_union".
+ *
+ * Returns nothing.
+ */
+static void
+tomoyo_print_number_union_nospace(struct tomoyo_io_buffer *head, const struct tomoyo_number_union *ptr)
+	__must_hold(&head->io_sem)
+{
+	if (ptr->group) {
+		tomoyo_set_string(head, "@");
+		tomoyo_set_string(head, ptr->group->group_name->name);
+	} else {
+		int i;
+		unsigned long min = ptr->values[0];
+		const unsigned long max = ptr->values[1];
+		u8 min_type = ptr->value_type[0];
+		const u8 max_type = ptr->value_type[1];
+		char buffer[128];
+
+		buffer[0] = '\0';
+		for (i = 0; i < 2; i++) {
+			switch (min_type) {
+			case TOMOYO_VALUE_TYPE_HEXADECIMAL:
+				tomoyo_addprintf(buffer, sizeof(buffer),
+						 "0x%lX", min);
+				break;
+			case TOMOYO_VALUE_TYPE_OCTAL:
+				tomoyo_addprintf(buffer, sizeof(buffer),
+						 "0%lo", min);
+				break;
+			default:
+				tomoyo_addprintf(buffer, sizeof(buffer), "%lu",
+						 min);
+				break;
+			}
+			if (min == max && min_type == max_type)
+				break;
+			tomoyo_addprintf(buffer, sizeof(buffer), "-");
+			min_type = max_type;
+			min = max;
+		}
+		tomoyo_io_printf(head, "%s", buffer);
+	}
+}
+
+/**
+ * tomoyo_print_number_union - Print a tomoyo_number_union.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @ptr:  Pointer to "struct tomoyo_number_union".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_print_number_union(struct tomoyo_io_buffer *head,
+				      const struct tomoyo_number_union *ptr)
+	__must_hold(&head->io_sem)
+{
+	tomoyo_set_space(head);
+	tomoyo_print_number_union_nospace(head, ptr);
+}
+
+/**
+ * tomoyo_assign_profile - Create a new profile.
+ *
+ * @ns:      Pointer to "struct tomoyo_policy_namespace".
+ * @profile: Profile number to create.
+ *
+ * Returns pointer to "struct tomoyo_profile" on success, NULL otherwise.
+ */
+static struct tomoyo_profile *tomoyo_assign_profile
+(struct tomoyo_policy_namespace *ns, const unsigned int profile)
+{
+	struct tomoyo_profile *ptr;
+	struct tomoyo_profile *entry;
+
+	if (profile >= TOMOYO_MAX_PROFILES)
+		return NULL;
+	ptr = ns->profile_ptr[profile];
+	if (ptr)
+		return ptr;
+	entry = kzalloc_obj(*entry, GFP_NOFS | __GFP_NOWARN);
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		goto out;
+	ptr = ns->profile_ptr[profile];
+	if (!ptr && tomoyo_memory_ok(entry)) {
+		ptr = entry;
+		ptr->default_config = TOMOYO_CONFIG_DISABLED |
+			TOMOYO_CONFIG_WANT_GRANT_LOG |
+			TOMOYO_CONFIG_WANT_REJECT_LOG;
+		memset(ptr->config, TOMOYO_CONFIG_USE_DEFAULT,
+		       sizeof(ptr->config));
+		ptr->pref[TOMOYO_PREF_MAX_AUDIT_LOG] =
+			CONFIG_SECURITY_TOMOYO_MAX_AUDIT_LOG;
+		ptr->pref[TOMOYO_PREF_MAX_LEARNING_ENTRY] =
+			CONFIG_SECURITY_TOMOYO_MAX_ACCEPT_ENTRY;
+		mb(); /* Avoid out-of-order execution. */
+		ns->profile_ptr[profile] = ptr;
+		entry = NULL;
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+ out:
+	kfree(entry);
+	return ptr;
+}
+
+/**
+ * tomoyo_profile - Find a profile.
+ *
+ * @ns:      Pointer to "struct tomoyo_policy_namespace".
+ * @profile: Profile number to find.
+ *
+ * Returns pointer to "struct tomoyo_profile".
+ */
+struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns,
+				      const u8 profile)
+{
+	static struct tomoyo_profile tomoyo_null_profile;
+	struct tomoyo_profile *ptr = ns->profile_ptr[profile];
+
+	if (!ptr)
+		ptr = &tomoyo_null_profile;
+	return ptr;
+}
+
+/**
+ * tomoyo_find_yesno - Find values for specified keyword.
+ *
+ * @string: String to check.
+ * @find:   Name of keyword.
+ *
+ * Returns 1 if "@find=yes" was found, 0 if "@find=no" was found, -1 otherwise.
+ */
+static s8 tomoyo_find_yesno(const char *string, const char *find)
+{
+	const char *cp = strstr(string, find);
+
+	if (cp) {
+		cp += strlen(find);
+		if (!strncmp(cp, "=yes", 4))
+			return 1;
+		else if (!strncmp(cp, "=no", 3))
+			return 0;
+	}
+	return -1;
+}
+
+/**
+ * tomoyo_set_uint - Set value for specified preference.
+ *
+ * @i:      Pointer to "unsigned int".
+ * @string: String to check.
+ * @find:   Name of keyword.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_set_uint(unsigned int *i, const char *string,
+			    const char *find)
+{
+	const char *cp = strstr(string, find);
+
+	if (cp)
+		sscanf(cp + strlen(find), "=%u", i);
+}
+
+/**
+ * tomoyo_set_mode - Set mode for specified profile.
+ *
+ * @name:    Name of functionality.
+ * @value:   Mode for @name.
+ * @profile: Pointer to "struct tomoyo_profile".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_set_mode(char *name, const char *value,
+			   struct tomoyo_profile *profile)
+{
+	u8 i;
+	u8 config;
+
+	if (!strcmp(name, "CONFIG")) {
+		i = TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX;
+		config = profile->default_config;
+	} else if (tomoyo_str_starts(&name, "CONFIG::")) {
+		config = 0;
+		for (i = 0; i < TOMOYO_MAX_MAC_INDEX
+			     + TOMOYO_MAX_MAC_CATEGORY_INDEX; i++) {
+			int len = 0;
+
+			if (i < TOMOYO_MAX_MAC_INDEX) {
+				const u8 c = tomoyo_index2category[i];
+				const char *category =
+					tomoyo_category_keywords[c];
+
+				len = strlen(category);
+				if (strncmp(name, category, len) ||
+				    name[len++] != ':' || name[len++] != ':')
+					continue;
+			}
+			if (strcmp(name + len, tomoyo_mac_keywords[i]))
+				continue;
+			config = profile->config[i];
+			break;
+		}
+		if (i == TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+	if (strstr(value, "use_default")) {
+		config = TOMOYO_CONFIG_USE_DEFAULT;
+	} else {
+		u8 mode;
+
+		for (mode = 0; mode < 4; mode++)
+			if (strstr(value, tomoyo_mode[mode]))
+				/*
+				 * Update lower 3 bits in order to distinguish
+				 * 'config' from 'TOMOYO_CONFIG_USE_DEFAULT'.
+				 */
+				config = (config & ~7) | mode;
+		if (config != TOMOYO_CONFIG_USE_DEFAULT) {
+			switch (tomoyo_find_yesno(value, "grant_log")) {
+			case 1:
+				config |= TOMOYO_CONFIG_WANT_GRANT_LOG;
+				break;
+			case 0:
+				config &= ~TOMOYO_CONFIG_WANT_GRANT_LOG;
+				break;
+			}
+			switch (tomoyo_find_yesno(value, "reject_log")) {
+			case 1:
+				config |= TOMOYO_CONFIG_WANT_REJECT_LOG;
+				break;
+			case 0:
+				config &= ~TOMOYO_CONFIG_WANT_REJECT_LOG;
+				break;
+			}
+		}
+	}
+	if (i < TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX)
+		profile->config[i] = config;
+	else if (config != TOMOYO_CONFIG_USE_DEFAULT)
+		profile->default_config = config;
+	return 0;
+}
+
+/**
+ * tomoyo_write_profile - Write profile table.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_write_profile(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	char *data = head->write_buf;
+	unsigned int i;
+	char *cp;
+	struct tomoyo_profile *profile;
+
+	if (sscanf(data, "PROFILE_VERSION=%u", &head->w.ns->profile_version)
+	    == 1)
+		return 0;
+	i = simple_strtoul(data, &cp, 10);
+	if (*cp != '-')
+		return -EINVAL;
+	data = cp + 1;
+	profile = tomoyo_assign_profile(head->w.ns, i);
+	if (!profile)
+		return -EINVAL;
+	cp = strchr(data, '=');
+	if (!cp)
+		return -EINVAL;
+	*cp++ = '\0';
+	if (!strcmp(data, "COMMENT")) {
+		static DEFINE_SPINLOCK(lock);
+		const struct tomoyo_path_info *new_comment
+			= tomoyo_get_name(cp);
+		const struct tomoyo_path_info *old_comment;
+
+		if (!new_comment)
+			return -ENOMEM;
+		spin_lock(&lock);
+		old_comment = profile->comment;
+		profile->comment = new_comment;
+		spin_unlock(&lock);
+		tomoyo_put_name(old_comment);
+		return 0;
+	}
+	if (!strcmp(data, "PREFERENCE")) {
+		for (i = 0; i < TOMOYO_MAX_PREF; i++)
+			tomoyo_set_uint(&profile->pref[i], cp,
+					tomoyo_pref_keywords[i]);
+		return 0;
+	}
+	return tomoyo_set_mode(data, cp, profile);
+}
+
+/**
+ * tomoyo_print_config - Print mode for specified functionality.
+ *
+ * @head:   Pointer to "struct tomoyo_io_buffer".
+ * @config: Mode for that functionality.
+ *
+ * Returns nothing.
+ *
+ * Caller prints functionality's name.
+ */
+static void tomoyo_print_config(struct tomoyo_io_buffer *head, const u8 config)
+	__must_hold(&head->io_sem)
+{
+	tomoyo_io_printf(head, "={ mode=%s grant_log=%s reject_log=%s }\n",
+			 tomoyo_mode[config & 3],
+			 str_yes_no(config & TOMOYO_CONFIG_WANT_GRANT_LOG),
+			 str_yes_no(config & TOMOYO_CONFIG_WANT_REJECT_LOG));
+}
+
+/**
+ * tomoyo_read_profile - Read profile table.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_read_profile(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	u8 index;
+	struct tomoyo_policy_namespace *ns =
+		container_of(head->r.ns, typeof(*ns), namespace_list);
+	const struct tomoyo_profile *profile;
+
+	if (head->r.eof)
+		return;
+ next:
+	index = head->r.index;
+	profile = ns->profile_ptr[index];
+	switch (head->r.step) {
+	case 0:
+		tomoyo_print_namespace(head);
+		tomoyo_io_printf(head, "PROFILE_VERSION=%u\n",
+				 ns->profile_version);
+		head->r.step++;
+		break;
+	case 1:
+		for ( ; head->r.index < TOMOYO_MAX_PROFILES;
+		      head->r.index++)
+			if (ns->profile_ptr[head->r.index])
+				break;
+		if (head->r.index == TOMOYO_MAX_PROFILES) {
+			head->r.eof = true;
+			return;
+		}
+		head->r.step++;
+		break;
+	case 2:
+		{
+			u8 i;
+			const struct tomoyo_path_info *comment =
+				profile->comment;
+
+			tomoyo_print_namespace(head);
+			tomoyo_io_printf(head, "%u-COMMENT=", index);
+			tomoyo_set_string(head, comment ? comment->name : "");
+			tomoyo_set_lf(head);
+			tomoyo_print_namespace(head);
+			tomoyo_io_printf(head, "%u-PREFERENCE={ ", index);
+			for (i = 0; i < TOMOYO_MAX_PREF; i++)
+				tomoyo_io_printf(head, "%s=%u ",
+						 tomoyo_pref_keywords[i],
+						 profile->pref[i]);
+			tomoyo_set_string(head, "}\n");
+			head->r.step++;
+		}
+		break;
+	case 3:
+		{
+			tomoyo_print_namespace(head);
+			tomoyo_io_printf(head, "%u-%s", index, "CONFIG");
+			tomoyo_print_config(head, profile->default_config);
+			head->r.bit = 0;
+			head->r.step++;
+		}
+		break;
+	case 4:
+		for ( ; head->r.bit < TOMOYO_MAX_MAC_INDEX
+			      + TOMOYO_MAX_MAC_CATEGORY_INDEX; head->r.bit++) {
+			const u8 i = head->r.bit;
+			const u8 config = profile->config[i];
+
+			if (config == TOMOYO_CONFIG_USE_DEFAULT)
+				continue;
+			tomoyo_print_namespace(head);
+			if (i < TOMOYO_MAX_MAC_INDEX)
+				tomoyo_io_printf(head, "%u-CONFIG::%s::%s",
+						 index,
+						 tomoyo_category_keywords
+						 [tomoyo_index2category[i]],
+						 tomoyo_mac_keywords[i]);
+			else
+				tomoyo_io_printf(head, "%u-CONFIG::%s", index,
+						 tomoyo_mac_keywords[i]);
+			tomoyo_print_config(head, config);
+			head->r.bit++;
+			break;
+		}
+		if (head->r.bit == TOMOYO_MAX_MAC_INDEX
+		    + TOMOYO_MAX_MAC_CATEGORY_INDEX) {
+			head->r.index++;
+			head->r.step = 1;
+		}
+		break;
+	}
+	if (tomoyo_flush(head))
+		goto next;
+}
+
+/**
+ * tomoyo_same_manager - Check for duplicated "struct tomoyo_manager" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_manager(const struct tomoyo_acl_head *a,
+				const struct tomoyo_acl_head *b)
+{
+	return container_of(a, struct tomoyo_manager, head)->manager ==
+		container_of(b, struct tomoyo_manager, head)->manager;
+}
+
+/**
+ * tomoyo_update_manager_entry - Add a manager entry.
+ *
+ * @manager:   The path to manager or the domainnamme.
+ * @is_delete: True if it is a delete request.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_update_manager_entry(const char *manager,
+				       const bool is_delete)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_manager e = { };
+	struct tomoyo_acl_param param = {
+		/* .ns = &tomoyo_kernel_namespace, */
+		.is_delete = is_delete,
+		.list = &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER],
+	};
+	int error = is_delete ? -ENOENT : -ENOMEM;
+
+	if (!tomoyo_correct_domain(manager) &&
+	    !tomoyo_correct_word(manager))
+		return -EINVAL;
+	e.manager = tomoyo_get_name(manager);
+	if (e.manager) {
+		error = tomoyo_update_policy(&e.head, sizeof(e), &param,
+					     tomoyo_same_manager);
+		tomoyo_put_name(e.manager);
+	}
+	return error;
+}
+
+/**
+ * tomoyo_write_manager - Write manager policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_manager(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	char *data = head->write_buf;
+
+	if (!strcmp(data, "manage_by_non_root")) {
+		tomoyo_manage_by_non_root = !head->w.is_delete;
+		return 0;
+	}
+	return tomoyo_update_manager_entry(data, head->w.is_delete);
+}
+
+/**
+ * tomoyo_read_manager - Read manager policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static void tomoyo_read_manager(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+{
+	if (head->r.eof)
+		return;
+	list_for_each_cookie(head->r.acl, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER]) {
+		struct tomoyo_manager *ptr =
+			list_entry(head->r.acl, typeof(*ptr), head.list);
+
+		if (ptr->head.is_deleted)
+			continue;
+		if (!tomoyo_flush(head))
+			return;
+		tomoyo_set_string(head, ptr->manager->name);
+		tomoyo_set_lf(head);
+	}
+	head->r.eof = true;
+}
+
+/**
+ * tomoyo_manager - Check whether the current process is a policy manager.
+ *
+ * Returns true if the current process is permitted to modify policy
+ * via /sys/kernel/security/tomoyo/ interface.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static bool tomoyo_manager(void)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_manager *ptr;
+	const char *exe;
+	const struct task_struct *task = current;
+	const struct tomoyo_path_info *domainname = tomoyo_domain()->domainname;
+	bool found = IS_ENABLED(CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING);
+
+	if (!tomoyo_policy_loaded)
+		return true;
+	if (!tomoyo_manage_by_non_root &&
+	    (!uid_eq(task->cred->uid,  GLOBAL_ROOT_UID) ||
+	     !uid_eq(task->cred->euid, GLOBAL_ROOT_UID)))
+		return false;
+	exe = tomoyo_get_exe();
+	if (!exe)
+		return false;
+	list_for_each_entry_rcu(ptr, &tomoyo_kernel_namespace.policy_list[TOMOYO_ID_MANAGER], head.list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (!ptr->head.is_deleted &&
+		    (!tomoyo_pathcmp(domainname, ptr->manager) ||
+		     !strcmp(exe, ptr->manager->name))) {
+			found = true;
+			break;
+		}
+	}
+	if (!found) { /* Reduce error messages. */
+		static pid_t last_pid;
+		const pid_t pid = current->pid;
+
+		if (last_pid != pid) {
+			pr_warn("%s ( %s ) is not permitted to update policies.\n",
+				domainname->name, exe);
+			last_pid = pid;
+		}
+	}
+	kfree(exe);
+	return found;
+}
+
+static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
+(unsigned int serial);
+
+/**
+ * tomoyo_select_domain - Parse select command.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @data: String to parse.
+ *
+ * Returns true on success, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static bool tomoyo_select_domain(struct tomoyo_io_buffer *head,
+				 const char *data)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	unsigned int pid;
+	struct tomoyo_domain_info *domain = NULL;
+	bool global_pid = false;
+
+	if (strncmp(data, "select ", 7))
+		return false;
+	data += 7;
+	if (sscanf(data, "pid=%u", &pid) == 1 ||
+	    (global_pid = true, sscanf(data, "global-pid=%u", &pid) == 1)) {
+		struct task_struct *p;
+
+		rcu_read_lock();
+		if (global_pid)
+			p = find_task_by_pid_ns(pid, &init_pid_ns);
+		else
+			p = find_task_by_vpid(pid);
+		if (p)
+			domain = tomoyo_task(p)->domain_info;
+		rcu_read_unlock();
+	} else if (!strncmp(data, "domain=", 7)) {
+		if (tomoyo_domain_def(data + 7))
+			domain = tomoyo_find_domain(data + 7);
+	} else if (sscanf(data, "Q=%u", &pid) == 1) {
+		domain = tomoyo_find_domain_by_qid(pid);
+	} else
+		return false;
+	head->w.domain = domain;
+	/* Accessing read_buf is safe because head->io_sem is held. */
+	if (!head->read_buf)
+		return true; /* Do nothing if open(O_WRONLY). */
+	memset(&head->r, 0, sizeof(head->r));
+	head->r.print_this_domain_only = true;
+	if (domain)
+		head->r.domain = &domain->list;
+	else
+		head->r.eof = true;
+	tomoyo_io_printf(head, "# select %s\n", data);
+	if (domain && domain->is_deleted)
+		tomoyo_io_printf(head, "# This is a deleted domain.\n");
+	return true;
+}
+
+/**
+ * tomoyo_same_task_acl - Check for duplicated "struct tomoyo_task_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_task_acl(const struct tomoyo_acl_info *a,
+				 const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_task_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_task_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return p1->domainname == p2->domainname;
+}
+
+/**
+ * tomoyo_write_task - Update task related list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_task(struct tomoyo_acl_param *param)
+	__must_hold_shared(&tomoyo_ss)
+{
+	int error = -EINVAL;
+
+	if (tomoyo_str_starts(&param->data, "manual_domain_transition ")) {
+		struct tomoyo_task_acl e = {
+			.head.type = TOMOYO_TYPE_MANUAL_TASK_ACL,
+			.domainname = tomoyo_get_domainname(param),
+		};
+
+		if (e.domainname)
+			error = tomoyo_update_domain(&e.head, sizeof(e), param,
+						     tomoyo_same_task_acl,
+						     NULL);
+		tomoyo_put_name(e.domainname);
+	}
+	return error;
+}
+
+/**
+ * tomoyo_delete_domain - Delete a domain.
+ *
+ * @domainname: The name of domain.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_delete_domain(char *domainname)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_domain_info *domain;
+	struct tomoyo_path_info name;
+
+	name.name = domainname;
+	tomoyo_fill_path_info(&name);
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		return -EINTR;
+	/* Is there an active domain? */
+	list_for_each_entry_rcu(domain, &tomoyo_domain_list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		/* Never delete tomoyo_kernel_domain */
+		if (domain == &tomoyo_kernel_domain)
+			continue;
+		if (domain->is_deleted ||
+		    tomoyo_pathcmp(domain->domainname, &name))
+			continue;
+		domain->is_deleted = true;
+		break;
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+	return 0;
+}
+
+/**
+ * tomoyo_write_domain2 - Write domain policy.
+ *
+ * @ns:        Pointer to "struct tomoyo_policy_namespace".
+ * @list:      Pointer to "struct list_head".
+ * @data:      Policy to be interpreted.
+ * @is_delete: True if it is a delete request.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_domain2(struct tomoyo_policy_namespace *ns,
+				struct list_head *list, char *data,
+				const bool is_delete)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_acl_param param = {
+		.ns = ns,
+		.list = list,
+		.data = data,
+		.is_delete = is_delete,
+	};
+	static const struct {
+		const char *keyword;
+		int (*write)(struct tomoyo_acl_param *param);
+	} tomoyo_callback[5] = {
+		{ "file ", tomoyo_write_file },
+		{ "network inet ", tomoyo_write_inet_network },
+		{ "network unix ", tomoyo_write_unix_network },
+		{ "misc ", tomoyo_write_misc },
+		{ "task ", tomoyo_write_task },
+	};
+	u8 i;
+
+	for (i = 0; i < ARRAY_SIZE(tomoyo_callback); i++) {
+		if (!tomoyo_str_starts(&param.data,
+				       tomoyo_callback[i].keyword))
+			continue;
+		return tomoyo_callback[i].write(&param);
+	}
+	return -EINVAL;
+}
+
+/* String table for domain flags. */
+const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS] = {
+	[TOMOYO_DIF_QUOTA_WARNED]      = "quota_exceeded\n",
+	[TOMOYO_DIF_TRANSITION_FAILED] = "transition_failed\n",
+};
+
+/**
+ * tomoyo_write_domain - Write domain policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_domain(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	char *data = head->write_buf;
+	struct tomoyo_policy_namespace *ns;
+	struct tomoyo_domain_info *domain = head->w.domain;
+	const bool is_delete = head->w.is_delete;
+	bool is_select = !is_delete && tomoyo_str_starts(&data, "select ");
+	unsigned int idx;
+
+	if (*data == '<') {
+		int ret = 0;
+
+		domain = NULL;
+		if (is_delete)
+			ret = tomoyo_delete_domain(data);
+		else if (is_select)
+			domain = tomoyo_find_domain(data);
+		else
+			domain = tomoyo_assign_domain(data, false);
+		head->w.domain = domain;
+		return ret;
+	}
+	if (!domain)
+		return -EINVAL;
+	ns = domain->ns;
+	if (sscanf(data, "use_profile %u", &idx) == 1
+	    && idx < TOMOYO_MAX_PROFILES) {
+		if (!tomoyo_policy_loaded || ns->profile_ptr[idx])
+			if (!is_delete)
+				domain->profile = (u8) idx;
+		return 0;
+	}
+	if (sscanf(data, "use_group %u\n", &idx) == 1
+	    && idx < TOMOYO_MAX_ACL_GROUPS) {
+		if (!is_delete)
+			set_bit(idx, domain->group);
+		else
+			clear_bit(idx, domain->group);
+		return 0;
+	}
+	for (idx = 0; idx < TOMOYO_MAX_DOMAIN_INFO_FLAGS; idx++) {
+		const char *cp = tomoyo_dif[idx];
+
+		if (strncmp(data, cp, strlen(cp) - 1))
+			continue;
+		domain->flags[idx] = !is_delete;
+		return 0;
+	}
+	return tomoyo_write_domain2(ns, &domain->acl_info_list, data,
+				    is_delete);
+}
+
+/**
+ * tomoyo_print_condition - Print condition part.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @cond: Pointer to "struct tomoyo_condition".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_print_condition(struct tomoyo_io_buffer *head,
+				   const struct tomoyo_condition *cond)
+	__must_hold(&head->io_sem)
+{
+	switch (head->r.cond_step) {
+	case 0:
+		head->r.cond_index = 0;
+		head->r.cond_step++;
+		if (cond->transit) {
+			tomoyo_set_space(head);
+			tomoyo_set_string(head, cond->transit->name);
+		}
+		fallthrough;
+	case 1:
+		{
+			const u16 condc = cond->condc;
+			const struct tomoyo_condition_element *condp =
+				(typeof(condp)) (cond + 1);
+			const struct tomoyo_number_union *numbers_p =
+				(typeof(numbers_p)) (condp + condc);
+			const struct tomoyo_name_union *names_p =
+				(typeof(names_p))
+				(numbers_p + cond->numbers_count);
+			const struct tomoyo_argv *argv =
+				(typeof(argv)) (names_p + cond->names_count);
+			const struct tomoyo_envp *envp =
+				(typeof(envp)) (argv + cond->argc);
+			u16 skip;
+
+			for (skip = 0; skip < head->r.cond_index; skip++) {
+				const u8 left = condp->left;
+				const u8 right = condp->right;
+
+				condp++;
+				switch (left) {
+				case TOMOYO_ARGV_ENTRY:
+					argv++;
+					continue;
+				case TOMOYO_ENVP_ENTRY:
+					envp++;
+					continue;
+				case TOMOYO_NUMBER_UNION:
+					numbers_p++;
+					break;
+				}
+				switch (right) {
+				case TOMOYO_NAME_UNION:
+					names_p++;
+					break;
+				case TOMOYO_NUMBER_UNION:
+					numbers_p++;
+					break;
+				}
+			}
+			while (head->r.cond_index < condc) {
+				const u8 match = condp->equals;
+				const u8 left = condp->left;
+				const u8 right = condp->right;
+
+				if (!tomoyo_flush(head))
+					return false;
+				condp++;
+				head->r.cond_index++;
+				tomoyo_set_space(head);
+				switch (left) {
+				case TOMOYO_ARGV_ENTRY:
+					tomoyo_io_printf(head,
+							 "exec.argv[%lu]%s=\"",
+							 argv->index, argv->is_not ? "!" : "");
+					tomoyo_set_string(head,
+							  argv->value->name);
+					tomoyo_set_string(head, "\"");
+					argv++;
+					continue;
+				case TOMOYO_ENVP_ENTRY:
+					tomoyo_set_string(head,
+							  "exec.envp[\"");
+					tomoyo_set_string(head,
+							  envp->name->name);
+					tomoyo_io_printf(head, "\"]%s=", envp->is_not ? "!" : "");
+					if (envp->value) {
+						tomoyo_set_string(head, "\"");
+						tomoyo_set_string(head, envp->value->name);
+						tomoyo_set_string(head, "\"");
+					} else {
+						tomoyo_set_string(head,
+								  "NULL");
+					}
+					envp++;
+					continue;
+				case TOMOYO_NUMBER_UNION:
+					tomoyo_print_number_union_nospace
+						(head, numbers_p++);
+					break;
+				default:
+					tomoyo_set_string(head,
+					       tomoyo_condition_keyword[left]);
+					break;
+				}
+				tomoyo_set_string(head, match ? "=" : "!=");
+				switch (right) {
+				case TOMOYO_NAME_UNION:
+					tomoyo_print_name_union_quoted
+						(head, names_p++);
+					break;
+				case TOMOYO_NUMBER_UNION:
+					tomoyo_print_number_union_nospace
+						(head, numbers_p++);
+					break;
+				default:
+					tomoyo_set_string(head,
+					  tomoyo_condition_keyword[right]);
+					break;
+				}
+			}
+		}
+		head->r.cond_step++;
+		fallthrough;
+	case 2:
+		if (!tomoyo_flush(head))
+			break;
+		head->r.cond_step++;
+		fallthrough;
+	case 3:
+		if (cond->grant_log != TOMOYO_GRANTLOG_AUTO)
+			tomoyo_io_printf(head, " grant_log=%s",
+					 str_yes_no(cond->grant_log ==
+						    TOMOYO_GRANTLOG_YES));
+		tomoyo_set_lf(head);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * tomoyo_set_group - Print "acl_group " header keyword and category name.
+ *
+ * @head:     Pointer to "struct tomoyo_io_buffer".
+ * @category: Category name.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_set_group(struct tomoyo_io_buffer *head,
+			     const char *category)
+	__must_hold(&head->io_sem)
+{
+	if (head->type == TOMOYO_EXCEPTIONPOLICY) {
+		tomoyo_print_namespace(head);
+		tomoyo_io_printf(head, "acl_group %u ",
+				 head->r.acl_group_index);
+	}
+	tomoyo_set_string(head, category);
+}
+
+/**
+ * tomoyo_print_entry - Print an ACL entry.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @acl:  Pointer to an ACL entry.
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_print_entry(struct tomoyo_io_buffer *head,
+			       struct tomoyo_acl_info *acl)
+	__must_hold(&head->io_sem)
+{
+	const u8 acl_type = acl->type;
+	bool first = true;
+	u8 bit;
+
+	if (head->r.print_cond_part)
+		goto print_cond_part;
+	if (acl->is_deleted)
+		return true;
+	if (!tomoyo_flush(head))
+		return false;
+	else if (acl_type == TOMOYO_TYPE_PATH_ACL) {
+		struct tomoyo_path_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u16 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_PATH_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (head->r.print_transition_related_only &&
+			    bit != TOMOYO_TYPE_EXECUTE)
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "file ");
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_path_keyword[bit]);
+		}
+		if (first)
+			return true;
+		tomoyo_print_name_union(head, &ptr->name);
+	} else if (acl_type == TOMOYO_TYPE_MANUAL_TASK_ACL) {
+		struct tomoyo_task_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+
+		tomoyo_set_group(head, "task ");
+		tomoyo_set_string(head, "manual_domain_transition ");
+		tomoyo_set_string(head, ptr->domainname->name);
+	} else if (head->r.print_transition_related_only) {
+		return true;
+	} else if (acl_type == TOMOYO_TYPE_PATH2_ACL) {
+		struct tomoyo_path2_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u8 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_PATH2_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "file ");
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_mac_keywords
+					  [tomoyo_pp2mac[bit]]);
+		}
+		if (first)
+			return true;
+		tomoyo_print_name_union(head, &ptr->name1);
+		tomoyo_print_name_union(head, &ptr->name2);
+	} else if (acl_type == TOMOYO_TYPE_PATH_NUMBER_ACL) {
+		struct tomoyo_path_number_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u8 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_PATH_NUMBER_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "file ");
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_mac_keywords
+					  [tomoyo_pn2mac[bit]]);
+		}
+		if (first)
+			return true;
+		tomoyo_print_name_union(head, &ptr->name);
+		tomoyo_print_number_union(head, &ptr->number);
+	} else if (acl_type == TOMOYO_TYPE_MKDEV_ACL) {
+		struct tomoyo_mkdev_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u8 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_MKDEV_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "file ");
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_mac_keywords
+					  [tomoyo_pnnn2mac[bit]]);
+		}
+		if (first)
+			return true;
+		tomoyo_print_name_union(head, &ptr->name);
+		tomoyo_print_number_union(head, &ptr->mode);
+		tomoyo_print_number_union(head, &ptr->major);
+		tomoyo_print_number_union(head, &ptr->minor);
+	} else if (acl_type == TOMOYO_TYPE_INET_ACL) {
+		struct tomoyo_inet_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u8 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "network inet ");
+				tomoyo_set_string(head, tomoyo_proto_keyword
+						  [ptr->protocol]);
+				tomoyo_set_space(head);
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_socket_keyword[bit]);
+		}
+		if (first)
+			return true;
+		tomoyo_set_space(head);
+		if (ptr->address.group) {
+			tomoyo_set_string(head, "@");
+			tomoyo_set_string(head, ptr->address.group->group_name
+					  ->name);
+		} else {
+			char buf[128];
+
+			tomoyo_print_ip(buf, sizeof(buf), &ptr->address);
+			tomoyo_io_printf(head, "%s", buf);
+		}
+		tomoyo_print_number_union(head, &ptr->port);
+	} else if (acl_type == TOMOYO_TYPE_UNIX_ACL) {
+		struct tomoyo_unix_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+		const u8 perm = ptr->perm;
+
+		for (bit = 0; bit < TOMOYO_MAX_NETWORK_OPERATION; bit++) {
+			if (!(perm & (1 << bit)))
+				continue;
+			if (first) {
+				tomoyo_set_group(head, "network unix ");
+				tomoyo_set_string(head, tomoyo_proto_keyword
+						  [ptr->protocol]);
+				tomoyo_set_space(head);
+				first = false;
+			} else {
+				tomoyo_set_slash(head);
+			}
+			tomoyo_set_string(head, tomoyo_socket_keyword[bit]);
+		}
+		if (first)
+			return true;
+		tomoyo_print_name_union(head, &ptr->name);
+	} else if (acl_type == TOMOYO_TYPE_MOUNT_ACL) {
+		struct tomoyo_mount_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+
+		tomoyo_set_group(head, "file mount");
+		tomoyo_print_name_union(head, &ptr->dev_name);
+		tomoyo_print_name_union(head, &ptr->dir_name);
+		tomoyo_print_name_union(head, &ptr->fs_type);
+		tomoyo_print_number_union(head, &ptr->flags);
+	} else if (acl_type == TOMOYO_TYPE_ENV_ACL) {
+		struct tomoyo_env_acl *ptr =
+			container_of(acl, typeof(*ptr), head);
+
+		tomoyo_set_group(head, "misc env ");
+		tomoyo_set_string(head, ptr->env->name);
+	}
+	if (acl->cond) {
+		head->r.print_cond_part = true;
+		head->r.cond_step = 0;
+		if (!tomoyo_flush(head))
+			return false;
+print_cond_part:
+		if (!tomoyo_print_condition(head, acl->cond))
+			return false;
+		head->r.print_cond_part = false;
+	} else {
+		tomoyo_set_lf(head);
+	}
+	return true;
+}
+
+/**
+ * tomoyo_read_domain2 - Read domain policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @list: Pointer to "struct list_head".
+ *
+ * Caller holds tomoyo_read_lock().
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_read_domain2(struct tomoyo_io_buffer *head,
+				struct list_head *list)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	list_for_each_cookie(head->r.acl, list) {
+		struct tomoyo_acl_info *ptr =
+			list_entry(head->r.acl, typeof(*ptr), list);
+
+		if (!tomoyo_print_entry(head, ptr))
+			return false;
+	}
+	head->r.acl = NULL;
+	return true;
+}
+
+/**
+ * tomoyo_read_domain - Read domain policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static void tomoyo_read_domain(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	if (head->r.eof)
+		return;
+	list_for_each_cookie(head->r.domain, &tomoyo_domain_list) {
+		struct tomoyo_domain_info *domain =
+			list_entry(head->r.domain, typeof(*domain), list);
+		u8 i;
+
+		switch (head->r.step) {
+		case 0:
+			if (domain->is_deleted &&
+			    !head->r.print_this_domain_only)
+				continue;
+			/* Print domainname and flags. */
+			tomoyo_set_string(head, domain->domainname->name);
+			tomoyo_set_lf(head);
+			tomoyo_io_printf(head, "use_profile %u\n",
+					 domain->profile);
+			for (i = 0; i < TOMOYO_MAX_DOMAIN_INFO_FLAGS; i++)
+				if (domain->flags[i])
+					tomoyo_set_string(head, tomoyo_dif[i]);
+			head->r.index = 0;
+			head->r.step++;
+			fallthrough;
+		case 1:
+			while (head->r.index < TOMOYO_MAX_ACL_GROUPS) {
+				i = head->r.index++;
+				if (!test_bit(i, domain->group))
+					continue;
+				tomoyo_io_printf(head, "use_group %u\n", i);
+				if (!tomoyo_flush(head))
+					return;
+			}
+			head->r.index = 0;
+			head->r.step++;
+			tomoyo_set_lf(head);
+			fallthrough;
+		case 2:
+			if (!tomoyo_read_domain2(head, &domain->acl_info_list))
+				return;
+			head->r.step++;
+			if (!tomoyo_set_lf(head))
+				return;
+			fallthrough;
+		case 3:
+			head->r.step = 0;
+			if (head->r.print_this_domain_only)
+				goto done;
+		}
+	}
+ done:
+	head->r.eof = true;
+}
+
+/**
+ * tomoyo_write_pid: Specify PID to obtain domainname.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0.
+ */
+static int tomoyo_write_pid(struct tomoyo_io_buffer *head)
+{
+	head->r.eof = false;
+	return 0;
+}
+
+/**
+ * tomoyo_read_pid - Get domainname of the specified PID.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns the domainname which the specified PID is in on success,
+ * empty string otherwise.
+ * The PID is specified by tomoyo_write_pid() so that the user can obtain
+ * using read()/write() interface rather than sysctl() interface.
+ */
+static void tomoyo_read_pid(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	char *buf = head->write_buf;
+	bool global_pid = false;
+	unsigned int pid;
+	struct task_struct *p;
+	struct tomoyo_domain_info *domain = NULL;
+
+	/* Accessing write_buf is safe because head->io_sem is held. */
+	if (!buf) {
+		head->r.eof = true;
+		return; /* Do nothing if open(O_RDONLY). */
+	}
+	if (head->r.w_pos || head->r.eof)
+		return;
+	head->r.eof = true;
+	if (tomoyo_str_starts(&buf, "global-pid "))
+		global_pid = true;
+	if (kstrtouint(buf, 10, &pid))
+		return;
+	rcu_read_lock();
+	if (global_pid)
+		p = find_task_by_pid_ns(pid, &init_pid_ns);
+	else
+		p = find_task_by_vpid(pid);
+	if (p)
+		domain = tomoyo_task(p)->domain_info;
+	rcu_read_unlock();
+	if (!domain)
+		return;
+	tomoyo_io_printf(head, "%u %u ", pid, domain->profile);
+	tomoyo_set_string(head, domain->domainname->name);
+}
+
+/* String table for domain transition control keywords. */
+static const char *tomoyo_transition_type[TOMOYO_MAX_TRANSITION_TYPE] = {
+	[TOMOYO_TRANSITION_CONTROL_NO_RESET]      = "no_reset_domain ",
+	[TOMOYO_TRANSITION_CONTROL_RESET]         = "reset_domain ",
+	[TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE] = "no_initialize_domain ",
+	[TOMOYO_TRANSITION_CONTROL_INITIALIZE]    = "initialize_domain ",
+	[TOMOYO_TRANSITION_CONTROL_NO_KEEP]       = "no_keep_domain ",
+	[TOMOYO_TRANSITION_CONTROL_KEEP]          = "keep_domain ",
+};
+
+/* String table for grouping keywords. */
+static const char *tomoyo_group_name[TOMOYO_MAX_GROUP] = {
+	[TOMOYO_PATH_GROUP]    = "path_group ",
+	[TOMOYO_NUMBER_GROUP]  = "number_group ",
+	[TOMOYO_ADDRESS_GROUP] = "address_group ",
+};
+
+/**
+ * tomoyo_write_exception - Write exception policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_exception(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	const bool is_delete = head->w.is_delete;
+	struct tomoyo_acl_param param = {
+		.ns = head->w.ns,
+		.is_delete = is_delete,
+		.data = head->write_buf,
+	};
+	u8 i;
+
+	if (tomoyo_str_starts(&param.data, "aggregator "))
+		return tomoyo_write_aggregator(&param);
+	for (i = 0; i < TOMOYO_MAX_TRANSITION_TYPE; i++)
+		if (tomoyo_str_starts(&param.data, tomoyo_transition_type[i]))
+			return tomoyo_write_transition_control(&param, i);
+	for (i = 0; i < TOMOYO_MAX_GROUP; i++)
+		if (tomoyo_str_starts(&param.data, tomoyo_group_name[i]))
+			return tomoyo_write_group(&param, i);
+	if (tomoyo_str_starts(&param.data, "acl_group ")) {
+		unsigned int group;
+		char *data;
+
+		group = simple_strtoul(param.data, &data, 10);
+		if (group < TOMOYO_MAX_ACL_GROUPS && *data++ == ' ')
+			return tomoyo_write_domain2
+				(head->w.ns, &head->w.ns->acl_group[group],
+				 data, is_delete);
+	}
+	return -EINVAL;
+}
+
+/**
+ * tomoyo_read_group - Read "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @idx:  Index number.
+ *
+ * Returns true on success, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static bool tomoyo_read_group(struct tomoyo_io_buffer *head, const int idx)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	struct tomoyo_policy_namespace *ns =
+		container_of(head->r.ns, typeof(*ns), namespace_list);
+	struct list_head *list = &ns->group_list[idx];
+
+	list_for_each_cookie(head->r.group, list) {
+		struct tomoyo_group *group =
+			list_entry(head->r.group, typeof(*group), head.list);
+
+		list_for_each_cookie(head->r.acl, &group->member_list) {
+			struct tomoyo_acl_head *ptr =
+				list_entry(head->r.acl, typeof(*ptr), list);
+
+			if (ptr->is_deleted)
+				continue;
+			if (!tomoyo_flush(head))
+				return false;
+			tomoyo_print_namespace(head);
+			tomoyo_set_string(head, tomoyo_group_name[idx]);
+			tomoyo_set_string(head, group->group_name->name);
+			if (idx == TOMOYO_PATH_GROUP) {
+				tomoyo_set_space(head);
+				tomoyo_set_string(head, container_of
+					       (ptr, struct tomoyo_path_group,
+						head)->member_name->name);
+			} else if (idx == TOMOYO_NUMBER_GROUP) {
+				tomoyo_print_number_union(head, &container_of
+							  (ptr,
+						   struct tomoyo_number_group,
+							   head)->number);
+			} else if (idx == TOMOYO_ADDRESS_GROUP) {
+				char buffer[128];
+				struct tomoyo_address_group *member =
+					container_of(ptr, typeof(*member),
+						     head);
+
+				tomoyo_print_ip(buffer, sizeof(buffer),
+						&member->address);
+				tomoyo_io_printf(head, " %s", buffer);
+			}
+			tomoyo_set_lf(head);
+		}
+		head->r.acl = NULL;
+	}
+	head->r.group = NULL;
+	return true;
+}
+
+/**
+ * tomoyo_read_policy - Read "struct tomoyo_..._entry" list.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @idx:  Index number.
+ *
+ * Returns true on success, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static bool tomoyo_read_policy(struct tomoyo_io_buffer *head, const int idx)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_policy_namespace *ns =
+		container_of(head->r.ns, typeof(*ns), namespace_list);
+	struct list_head *list = &ns->policy_list[idx];
+
+	list_for_each_cookie(head->r.acl, list) {
+		struct tomoyo_acl_head *acl =
+			container_of(head->r.acl, typeof(*acl), list);
+		if (acl->is_deleted)
+			continue;
+		if (!tomoyo_flush(head))
+			return false;
+		switch (idx) {
+		case TOMOYO_ID_TRANSITION_CONTROL:
+			{
+				struct tomoyo_transition_control *ptr =
+					container_of(acl, typeof(*ptr), head);
+
+				tomoyo_print_namespace(head);
+				tomoyo_set_string(head, tomoyo_transition_type
+						  [ptr->type]);
+				tomoyo_set_string(head, ptr->program ?
+						  ptr->program->name : "any");
+				tomoyo_set_string(head, " from ");
+				tomoyo_set_string(head, ptr->domainname ?
+						  ptr->domainname->name :
+						  "any");
+			}
+			break;
+		case TOMOYO_ID_AGGREGATOR:
+			{
+				struct tomoyo_aggregator *ptr =
+					container_of(acl, typeof(*ptr), head);
+
+				tomoyo_print_namespace(head);
+				tomoyo_set_string(head, "aggregator ");
+				tomoyo_set_string(head,
+						  ptr->original_name->name);
+				tomoyo_set_space(head);
+				tomoyo_set_string(head,
+					       ptr->aggregated_name->name);
+			}
+			break;
+		default:
+			continue;
+		}
+		tomoyo_set_lf(head);
+	}
+	head->r.acl = NULL;
+	return true;
+}
+
+/**
+ * tomoyo_read_exception - Read exception policy.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static void tomoyo_read_exception(struct tomoyo_io_buffer *head)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	struct tomoyo_policy_namespace *ns =
+		container_of(head->r.ns, typeof(*ns), namespace_list);
+
+	if (head->r.eof)
+		return;
+	while (head->r.step < TOMOYO_MAX_POLICY &&
+	       tomoyo_read_policy(head, head->r.step))
+		head->r.step++;
+	if (head->r.step < TOMOYO_MAX_POLICY)
+		return;
+	while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP &&
+	       tomoyo_read_group(head, head->r.step - TOMOYO_MAX_POLICY))
+		head->r.step++;
+	if (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP)
+		return;
+	while (head->r.step < TOMOYO_MAX_POLICY + TOMOYO_MAX_GROUP
+	       + TOMOYO_MAX_ACL_GROUPS) {
+		head->r.acl_group_index = head->r.step - TOMOYO_MAX_POLICY
+			- TOMOYO_MAX_GROUP;
+		if (!tomoyo_read_domain2(head, &ns->acl_group
+					 [head->r.acl_group_index]))
+			return;
+		head->r.step++;
+	}
+	head->r.eof = true;
+}
+
+/* Wait queue for kernel -> userspace notification. */
+static DECLARE_WAIT_QUEUE_HEAD(tomoyo_query_wait);
+/* Wait queue for userspace -> kernel notification. */
+static DECLARE_WAIT_QUEUE_HEAD(tomoyo_answer_wait);
+
+/* Structure for query. */
+struct tomoyo_query {
+	struct list_head list;
+	struct tomoyo_domain_info *domain;
+	char *query;
+	size_t query_len;
+	unsigned int serial;
+	u8 timer;
+	u8 answer;
+	u8 retry;
+};
+
+/* The list for "struct tomoyo_query". */
+static LIST_HEAD(tomoyo_query_list);
+
+/* Lock for manipulating tomoyo_query_list. */
+static DEFINE_SPINLOCK(tomoyo_query_list_lock);
+
+/*
+ * Number of "struct file" referring /sys/kernel/security/tomoyo/query
+ * interface.
+ */
+static atomic_t tomoyo_query_observers = ATOMIC_INIT(0);
+
+/**
+ * tomoyo_truncate - Truncate a line.
+ *
+ * @str: String to truncate.
+ *
+ * Returns length of truncated @str.
+ */
+static int tomoyo_truncate(char *str)
+{
+	char *start = str;
+
+	while (*(unsigned char *) str > (unsigned char) ' ')
+		str++;
+	*str = '\0';
+	return strlen(start) + 1;
+}
+
+/**
+ * tomoyo_numscan - sscanf() which stores the length of a decimal integer value.
+ *
+ * @str:   String to scan.
+ * @head:  Leading string that must start with.
+ * @width: Pointer to "int" for storing length of a decimal integer value after @head.
+ * @tail:  Optional character that must match after a decimal integer value.
+ *
+ * Returns whether @str starts with @head and a decimal value follows @head.
+ */
+static bool tomoyo_numscan(const char *str, const char *head, int *width, const char tail)
+{
+	const char *cp;
+	const int n = strlen(head);
+
+	if (!strncmp(str, head, n)) {
+		cp = str + n;
+		while (*cp && *cp >= '0' && *cp <= '9')
+			cp++;
+		if (*cp == tail || !tail) {
+			*width = cp - (str + n);
+			return *width != 0;
+		}
+	}
+	*width = 0;
+	return 0;
+}
+
+/**
+ * tomoyo_patternize_path - Make patterns for file path. Used by learning mode.
+ *
+ * @buffer: Destination buffer.
+ * @len:    Size of @buffer.
+ * @entry:  Original line.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_patternize_path(char *buffer, const int len, char *entry)
+{
+	int width;
+	char *cp = entry;
+
+	/* Nothing to do if this line is not for "file" related entry. */
+	if (strncmp(entry, "file ", 5))
+		goto flush;
+	/*
+	 * Nothing to do if there is no colon in this line, for this rewriting
+	 * applies to only filesystems where numeric values in the path are volatile.
+	 */
+	cp = strchr(entry + 5, ':');
+	if (!cp) {
+		cp = entry;
+		goto flush;
+	}
+	/* Flush e.g. "file ioctl" part. */
+	while (*cp != ' ')
+		cp--;
+	*cp++ = '\0';
+	tomoyo_addprintf(buffer, len, "%s ", entry);
+	/* e.g. file ioctl pipe:[$INO] $CMD */
+	if (tomoyo_numscan(cp, "pipe:[", &width, ']')) {
+		cp += width + 7;
+		tomoyo_addprintf(buffer, len, "pipe:[\\$]");
+		goto flush;
+	}
+	/* e.g. file ioctl socket:[$INO] $CMD */
+	if (tomoyo_numscan(cp, "socket:[", &width, ']')) {
+		cp += width + 9;
+		tomoyo_addprintf(buffer, len, "socket:[\\$]");
+		goto flush;
+	}
+	if (!strncmp(cp, "proc:/self", 10)) {
+		/* e.g. file read proc:/self/task/$TID/fdinfo/$FD */
+		cp += 10;
+		tomoyo_addprintf(buffer, len, "proc:/self");
+	} else if (tomoyo_numscan(cp, "proc:/", &width, 0)) {
+		/* e.g. file read proc:/$PID/task/$TID/fdinfo/$FD */
+		/*
+		 * Don't patternize $PID part if $PID == 1, for several
+		 * programs access only files in /proc/1/ directory.
+		 */
+		cp += width + 6;
+		if (width == 1 && *(cp - 1) == '1')
+			tomoyo_addprintf(buffer, len, "proc:/1");
+		else
+			tomoyo_addprintf(buffer, len, "proc:/\\$");
+	} else {
+		goto flush;
+	}
+	/* Patternize $TID part if "/task/" follows. */
+	if (tomoyo_numscan(cp, "/task/", &width, 0)) {
+		cp += width + 6;
+		tomoyo_addprintf(buffer, len, "/task/\\$");
+	}
+	/* Patternize $FD part if "/fd/" or "/fdinfo/" follows. */
+	if (tomoyo_numscan(cp, "/fd/", &width, 0)) {
+		cp += width + 4;
+		tomoyo_addprintf(buffer, len, "/fd/\\$");
+	} else if (tomoyo_numscan(cp, "/fdinfo/", &width, 0)) {
+		cp += width + 8;
+		tomoyo_addprintf(buffer, len, "/fdinfo/\\$");
+	}
+flush:
+	/* Flush remaining part if any. */
+	if (*cp)
+		tomoyo_addprintf(buffer, len, "%s", cp);
+}
+
+/**
+ * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode.
+ *
+ * @domain: Pointer to "struct tomoyo_domain_info".
+ * @header: Lines containing ACL.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header)
+	__must_hold_shared(&tomoyo_ss)
+{
+	char *buffer;
+	char *realpath = NULL;
+	char *argv0 = NULL;
+	char *symlink = NULL;
+	char *cp = strchr(header, '\n');
+	int len;
+
+	if (!cp)
+		return;
+	cp = strchr(cp + 1, '\n');
+	if (!cp)
+		return;
+	*cp++ = '\0';
+	/* Reserve some space for potentially using patterns. */
+	len = strlen(cp) + 16;
+	/* strstr() will return NULL if ordering is wrong. */
+	if (*cp == 'f') {
+		argv0 = strstr(header, " argv[]={ \"");
+		if (argv0) {
+			argv0 += 10;
+			len += tomoyo_truncate(argv0) + 14;
+		}
+		realpath = strstr(header, " exec={ realpath=\"");
+		if (realpath) {
+			realpath += 8;
+			len += tomoyo_truncate(realpath) + 6;
+		}
+		symlink = strstr(header, " symlink.target=\"");
+		if (symlink)
+			len += tomoyo_truncate(symlink + 1) + 1;
+	}
+	buffer = kmalloc(len, GFP_NOFS | __GFP_ZERO);
+	if (!buffer)
+		return;
+	tomoyo_patternize_path(buffer, len, cp);
+	if (realpath)
+		tomoyo_addprintf(buffer, len, " exec.%s", realpath);
+	if (argv0)
+		tomoyo_addprintf(buffer, len, " exec.argv[0]=%s", argv0);
+	if (symlink)
+		tomoyo_addprintf(buffer, len, "%s", symlink);
+	tomoyo_normalize_line(buffer);
+	if (!tomoyo_write_domain2(domain->ns, &domain->acl_info_list, buffer,
+				  false))
+		tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES);
+	kfree(buffer);
+}
+
+/**
+ * tomoyo_supervisor - Ask for the supervisor's decision.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @fmt: The printf()'s format string, followed by parameters.
+ *
+ * Returns 0 if the supervisor decided to permit the access request which
+ * violated the policy in enforcing mode, TOMOYO_RETRY_REQUEST if the
+ * supervisor decided to retry the access request which violated the policy in
+ * enforcing mode, 0 if it is not in enforcing mode, -EPERM otherwise.
+ */
+int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...)
+{
+	va_list args;
+	int error;
+	int len;
+	static unsigned int tomoyo_serial;
+	struct tomoyo_query entry = { };
+	bool quota_exceeded = false;
+
+	va_start(args, fmt);
+	len = vsnprintf(NULL, 0, fmt, args) + 1;
+	va_end(args);
+	/* Write /sys/kernel/security/tomoyo/audit. */
+	va_start(args, fmt);
+	tomoyo_write_log2(r, len, fmt, args);
+	va_end(args);
+	/* Nothing more to do if granted. */
+	if (r->granted)
+		return 0;
+	if (r->mode)
+		tomoyo_update_stat(r->mode);
+	switch (r->mode) {
+	case TOMOYO_CONFIG_ENFORCING:
+		error = -EPERM;
+		if (atomic_read(&tomoyo_query_observers))
+			break;
+		goto out;
+	case TOMOYO_CONFIG_LEARNING:
+		error = 0;
+		/* Check max_learning_entry parameter. */
+		if (tomoyo_domain_quota_is_ok(r))
+			break;
+		fallthrough;
+	default:
+		return 0;
+	}
+	/* Get message. */
+	va_start(args, fmt);
+	entry.query = tomoyo_init_log(r, len, fmt, args);
+	va_end(args);
+	if (!entry.query)
+		goto out;
+	entry.query_len = strlen(entry.query) + 1;
+	if (!error) {
+		tomoyo_add_entry(r->domain, entry.query);
+		goto out;
+	}
+	len = kmalloc_size_roundup(entry.query_len);
+	entry.domain = r->domain;
+	spin_lock(&tomoyo_query_list_lock);
+	if (tomoyo_memory_quota[TOMOYO_MEMORY_QUERY] &&
+	    tomoyo_memory_used[TOMOYO_MEMORY_QUERY] + len
+	    >= tomoyo_memory_quota[TOMOYO_MEMORY_QUERY]) {
+		quota_exceeded = true;
+	} else {
+		entry.serial = tomoyo_serial++;
+		entry.retry = r->retry;
+		tomoyo_memory_used[TOMOYO_MEMORY_QUERY] += len;
+		list_add_tail(&entry.list, &tomoyo_query_list);
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	if (quota_exceeded)
+		goto out;
+	/* Give 10 seconds for supervisor's opinion. */
+	while (entry.timer < 10) {
+		wake_up_all(&tomoyo_query_wait);
+		if (wait_event_interruptible_timeout
+		    (tomoyo_answer_wait, entry.answer ||
+		     !atomic_read(&tomoyo_query_observers), HZ))
+			break;
+		entry.timer++;
+	}
+	spin_lock(&tomoyo_query_list_lock);
+	list_del(&entry.list);
+	tomoyo_memory_used[TOMOYO_MEMORY_QUERY] -= len;
+	spin_unlock(&tomoyo_query_list_lock);
+	switch (entry.answer) {
+	case 3: /* Asked to retry by administrator. */
+		error = TOMOYO_RETRY_REQUEST;
+		r->retry++;
+		break;
+	case 1:
+		/* Granted by administrator. */
+		error = 0;
+		break;
+	default:
+		/* Timed out or rejected by administrator. */
+		break;
+	}
+out:
+	kfree(entry.query);
+	return error;
+}
+
+/**
+ * tomoyo_find_domain_by_qid - Get domain by query id.
+ *
+ * @serial: Query ID assigned by tomoyo_supervisor().
+ *
+ * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise.
+ */
+static struct tomoyo_domain_info *tomoyo_find_domain_by_qid
+(unsigned int serial)
+{
+	struct tomoyo_query *ptr;
+	struct tomoyo_domain_info *domain = NULL;
+
+	spin_lock(&tomoyo_query_list_lock);
+	list_for_each_entry(ptr, &tomoyo_query_list, list) {
+		if (ptr->serial != serial)
+			continue;
+		domain = ptr->domain;
+		break;
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	return domain;
+}
+
+/**
+ * tomoyo_poll_query - poll() for /sys/kernel/security/tomoyo/query.
+ *
+ * @file: Pointer to "struct file".
+ * @wait: Pointer to "poll_table".
+ *
+ * Returns EPOLLIN | EPOLLRDNORM when ready to read, 0 otherwise.
+ *
+ * Waits for access requests which violated policy in enforcing mode.
+ */
+static __poll_t tomoyo_poll_query(struct file *file, poll_table *wait)
+{
+	if (!list_empty(&tomoyo_query_list))
+		return EPOLLIN | EPOLLRDNORM;
+	poll_wait(file, &tomoyo_query_wait, wait);
+	if (!list_empty(&tomoyo_query_list))
+		return EPOLLIN | EPOLLRDNORM;
+	return 0;
+}
+
+/**
+ * tomoyo_read_query - Read access requests which violated policy in enforcing mode.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ */
+static void tomoyo_read_query(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	struct list_head *tmp;
+	unsigned int pos = 0;
+	size_t len = 0;
+	char *buf;
+
+	if (head->r.w_pos)
+		return;
+	kfree(head->read_buf);
+	head->read_buf = NULL;
+	spin_lock(&tomoyo_query_list_lock);
+	list_for_each(tmp, &tomoyo_query_list) {
+		struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
+
+		if (pos++ != head->r.query_index)
+			continue;
+		len = ptr->query_len;
+		break;
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	if (!len) {
+		head->r.query_index = 0;
+		return;
+	}
+	buf = kzalloc(len + 32, GFP_NOFS);
+	if (!buf)
+		return;
+	pos = 0;
+	spin_lock(&tomoyo_query_list_lock);
+	list_for_each(tmp, &tomoyo_query_list) {
+		struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
+
+		if (pos++ != head->r.query_index)
+			continue;
+		/*
+		 * Some query can be skipped because tomoyo_query_list
+		 * can change, but I don't care.
+		 */
+		if (len == ptr->query_len)
+			snprintf(buf, len + 31, "Q%u-%hu\n%s", ptr->serial,
+				 ptr->retry, ptr->query);
+		break;
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	if (buf[0]) {
+		head->read_buf = buf;
+		head->r.w[head->r.w_pos++] = buf;
+		head->r.query_index++;
+	} else {
+		kfree(buf);
+	}
+}
+
+/**
+ * tomoyo_write_answer - Write the supervisor's decision.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0 on success, -EINVAL otherwise.
+ */
+static int tomoyo_write_answer(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	char *data = head->write_buf;
+	struct list_head *tmp;
+	unsigned int serial;
+	unsigned int answer;
+
+	spin_lock(&tomoyo_query_list_lock);
+	list_for_each(tmp, &tomoyo_query_list) {
+		struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
+
+		ptr->timer = 0;
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	if (sscanf(data, "A%u=%u", &serial, &answer) != 2)
+		return -EINVAL;
+	spin_lock(&tomoyo_query_list_lock);
+	list_for_each(tmp, &tomoyo_query_list) {
+		struct tomoyo_query *ptr = list_entry(tmp, typeof(*ptr), list);
+
+		if (ptr->serial != serial)
+			continue;
+		ptr->answer = answer;
+		/* Remove from tomoyo_query_list. */
+		if (ptr->answer)
+			list_del_init(&ptr->list);
+		break;
+	}
+	spin_unlock(&tomoyo_query_list_lock);
+	return 0;
+}
+
+/**
+ * tomoyo_read_version: Get version.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns version information.
+ */
+static void tomoyo_read_version(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	if (!head->r.eof) {
+		tomoyo_io_printf(head, "2.6.0");
+		head->r.eof = true;
+	}
+}
+
+/* String table for /sys/kernel/security/tomoyo/stat interface. */
+static const char * const tomoyo_policy_headers[TOMOYO_MAX_POLICY_STAT] = {
+	[TOMOYO_STAT_POLICY_UPDATES]    = "update:",
+	[TOMOYO_STAT_POLICY_LEARNING]   = "violation in learning mode:",
+	[TOMOYO_STAT_POLICY_PERMISSIVE] = "violation in permissive mode:",
+	[TOMOYO_STAT_POLICY_ENFORCING]  = "violation in enforcing mode:",
+};
+
+/* String table for /sys/kernel/security/tomoyo/stat interface. */
+static const char * const tomoyo_memory_headers[TOMOYO_MAX_MEMORY_STAT] = {
+	[TOMOYO_MEMORY_POLICY] = "policy:",
+	[TOMOYO_MEMORY_AUDIT]  = "audit log:",
+	[TOMOYO_MEMORY_QUERY]  = "query message:",
+};
+
+/* Counter for number of updates. */
+static atomic_t tomoyo_stat_updated[TOMOYO_MAX_POLICY_STAT];
+/* Timestamp counter for last updated. */
+static time64_t tomoyo_stat_modified[TOMOYO_MAX_POLICY_STAT];
+
+/**
+ * tomoyo_update_stat - Update statistic counters.
+ *
+ * @index: Index for policy type.
+ *
+ * Returns nothing.
+ */
+void tomoyo_update_stat(const u8 index)
+{
+	atomic_inc(&tomoyo_stat_updated[index]);
+	tomoyo_stat_modified[index] = ktime_get_real_seconds();
+}
+
+/**
+ * tomoyo_read_stat - Read statistic data.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_read_stat(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	u8 i;
+	unsigned int total = 0;
+
+	if (head->r.eof)
+		return;
+	for (i = 0; i < TOMOYO_MAX_POLICY_STAT; i++) {
+		tomoyo_io_printf(head, "Policy %-30s %10u",
+				 tomoyo_policy_headers[i],
+				 atomic_read(&tomoyo_stat_updated[i]));
+		if (tomoyo_stat_modified[i]) {
+			struct tomoyo_time stamp;
+
+			tomoyo_convert_time(tomoyo_stat_modified[i], &stamp);
+			tomoyo_io_printf(head, " (Last: %04u/%02u/%02u %02u:%02u:%02u)",
+					 stamp.year, stamp.month, stamp.day,
+					 stamp.hour, stamp.min, stamp.sec);
+		}
+		tomoyo_set_lf(head);
+	}
+	for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++) {
+		unsigned int used = tomoyo_memory_used[i];
+
+		total += used;
+		tomoyo_io_printf(head, "Memory used by %-22s %10u",
+				 tomoyo_memory_headers[i], used);
+		used = tomoyo_memory_quota[i];
+		if (used)
+			tomoyo_io_printf(head, " (Quota: %10u)", used);
+		tomoyo_set_lf(head);
+	}
+	tomoyo_io_printf(head, "Total memory used:                    %10u\n",
+			 total);
+	head->r.eof = true;
+}
+
+/**
+ * tomoyo_write_stat - Set memory quota.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns 0.
+ */
+static int tomoyo_write_stat(struct tomoyo_io_buffer *head)
+	__must_hold(&head->io_sem)
+{
+	char *data = head->write_buf;
+	u8 i;
+
+	if (tomoyo_str_starts(&data, "Memory used by "))
+		for (i = 0; i < TOMOYO_MAX_MEMORY_STAT; i++)
+			if (tomoyo_str_starts(&data, tomoyo_memory_headers[i]))
+				sscanf(data, "%u", &tomoyo_memory_quota[i]);
+	return 0;
+}
+
+/**
+ * tomoyo_open_control - open() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @type: Type of interface.
+ * @file: Pointer to "struct file".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_open_control(const u8 type, struct file *file)
+{
+	struct tomoyo_io_buffer *head = kzalloc_obj(*head, GFP_NOFS);
+
+	if (!head)
+		return -ENOMEM;
+	guard(mutex_init)(&head->io_sem);
+	head->type = type;
+	switch (type) {
+	case TOMOYO_DOMAINPOLICY:
+		/* /sys/kernel/security/tomoyo/domain_policy */
+		head->write = tomoyo_write_domain;
+		head->read = tomoyo_read_domain;
+		break;
+	case TOMOYO_EXCEPTIONPOLICY:
+		/* /sys/kernel/security/tomoyo/exception_policy */
+		head->write = tomoyo_write_exception;
+		head->read = tomoyo_read_exception;
+		break;
+	case TOMOYO_AUDIT:
+		/* /sys/kernel/security/tomoyo/audit */
+		head->poll = tomoyo_poll_log;
+		head->read = tomoyo_read_log;
+		break;
+	case TOMOYO_PROCESS_STATUS:
+		/* /sys/kernel/security/tomoyo/.process_status */
+		head->write = tomoyo_write_pid;
+		head->read = tomoyo_read_pid;
+		break;
+	case TOMOYO_VERSION:
+		/* /sys/kernel/security/tomoyo/version */
+		head->read = tomoyo_read_version;
+		head->readbuf_size = 128;
+		break;
+	case TOMOYO_STAT:
+		/* /sys/kernel/security/tomoyo/stat */
+		head->write = tomoyo_write_stat;
+		head->read = tomoyo_read_stat;
+		head->readbuf_size = 1024;
+		break;
+	case TOMOYO_PROFILE:
+		/* /sys/kernel/security/tomoyo/profile */
+		head->write = tomoyo_write_profile;
+		head->read = tomoyo_read_profile;
+		break;
+	case TOMOYO_QUERY: /* /sys/kernel/security/tomoyo/query */
+		head->poll = tomoyo_poll_query;
+		head->write = tomoyo_write_answer;
+		head->read = tomoyo_read_query;
+		break;
+	case TOMOYO_MANAGER:
+		/* /sys/kernel/security/tomoyo/manager */
+		head->write = tomoyo_write_manager;
+		head->read = tomoyo_read_manager;
+		break;
+	}
+	if (!(file->f_mode & FMODE_READ)) {
+		/*
+		 * No need to allocate read_buf since it is not opened
+		 * for reading.
+		 */
+		head->read = NULL;
+		head->poll = NULL;
+	} else if (!head->poll) {
+		/* Don't allocate read_buf for poll() access. */
+		if (!head->readbuf_size)
+			head->readbuf_size = 4096 * 2;
+		head->read_buf = kzalloc(head->readbuf_size, GFP_NOFS);
+		if (!head->read_buf) {
+			kfree(head);
+			return -ENOMEM;
+		}
+	}
+	if (!(file->f_mode & FMODE_WRITE)) {
+		/*
+		 * No need to allocate write_buf since it is not opened
+		 * for writing.
+		 */
+		head->write = NULL;
+	} else if (head->write) {
+		head->writebuf_size = 4096 * 2;
+		head->write_buf = kzalloc(head->writebuf_size, GFP_NOFS);
+		if (!head->write_buf) {
+			kfree(head->read_buf);
+			kfree(head);
+			return -ENOMEM;
+		}
+	}
+	/*
+	 * If the file is /sys/kernel/security/tomoyo/query , increment the
+	 * observer counter.
+	 * The obserber counter is used by tomoyo_supervisor() to see if
+	 * there is some process monitoring /sys/kernel/security/tomoyo/query.
+	 */
+	if (type == TOMOYO_QUERY)
+		atomic_inc(&tomoyo_query_observers);
+	file->private_data = head;
+	tomoyo_notify_gc(head, true);
+	return 0;
+}
+
+/**
+ * tomoyo_poll_control - poll() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @file: Pointer to "struct file".
+ * @wait: Pointer to "poll_table". Maybe NULL.
+ *
+ * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write,
+ * EPOLLOUT | EPOLLWRNORM otherwise.
+ */
+__poll_t tomoyo_poll_control(struct file *file, poll_table *wait)
+{
+	struct tomoyo_io_buffer *head = file->private_data;
+
+	if (head->poll)
+		return head->poll(file, wait) | EPOLLOUT | EPOLLWRNORM;
+	return EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM;
+}
+
+/**
+ * tomoyo_set_namespace_cursor - Set namespace to read.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_set_namespace_cursor(struct tomoyo_io_buffer *head)
+{
+	struct list_head *ns;
+
+	if (head->type != TOMOYO_EXCEPTIONPOLICY &&
+	    head->type != TOMOYO_PROFILE)
+		return;
+	/*
+	 * If this is the first read, or reading previous namespace finished
+	 * and has more namespaces to read, update the namespace cursor.
+	 */
+	ns = head->r.ns;
+	if (!ns || (head->r.eof && ns->next != &tomoyo_namespace_list)) {
+		/* Clearing is OK because tomoyo_flush() returned true. */
+		memset(&head->r, 0, sizeof(head->r));
+		head->r.ns = ns ? ns->next : tomoyo_namespace_list.next;
+	}
+}
+
+/**
+ * tomoyo_has_more_namespace - Check for unread namespaces.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ *
+ * Returns true if we have more entries to print, false otherwise.
+ */
+static inline bool tomoyo_has_more_namespace(struct tomoyo_io_buffer *head)
+{
+	return (head->type == TOMOYO_EXCEPTIONPOLICY ||
+		head->type == TOMOYO_PROFILE) && head->r.eof &&
+		head->r.ns->next != &tomoyo_namespace_list;
+}
+
+/**
+ * tomoyo_read_control - read() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @head:       Pointer to "struct tomoyo_io_buffer".
+ * @buffer:     Pointer to buffer to write to.
+ * @buffer_len: Size of @buffer.
+ *
+ * Returns bytes read on success, negative value otherwise.
+ */
+ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer,
+			    const int buffer_len)
+{
+	int len;
+	int idx;
+
+	if (!head->read)
+		return -EINVAL;
+	if (mutex_lock_interruptible(&head->io_sem))
+		return -EINTR;
+	head->read_user_buf = buffer;
+	head->read_user_buf_avail = buffer_len;
+	idx = tomoyo_read_lock();
+	if (tomoyo_flush(head))
+		/* Call the policy handler. */
+		do {
+			tomoyo_set_namespace_cursor(head);
+			head->read(head);
+		} while (tomoyo_flush(head) &&
+			 tomoyo_has_more_namespace(head));
+	tomoyo_read_unlock(idx);
+	len = head->read_user_buf - buffer;
+	mutex_unlock(&head->io_sem);
+	return len;
+}
+
+/**
+ * tomoyo_parse_policy - Parse a policy line.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ * @line: Line to parse.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_parse_policy(struct tomoyo_io_buffer *head, char *line)
+	__must_hold_shared(&tomoyo_ss)
+	__must_hold(&head->io_sem)
+{
+	/* Delete request? */
+	head->w.is_delete = !strncmp(line, "delete ", 7);
+	if (head->w.is_delete)
+		memmove(line, line + 7, strlen(line + 7) + 1);
+	/* Selecting namespace to update. */
+	if (head->type == TOMOYO_EXCEPTIONPOLICY ||
+	    head->type == TOMOYO_PROFILE) {
+		if (*line == '<') {
+			char *cp = strchr(line, ' ');
+
+			if (cp) {
+				*cp++ = '\0';
+				head->w.ns = tomoyo_assign_namespace(line);
+				memmove(line, cp, strlen(cp) + 1);
+			} else
+				head->w.ns = NULL;
+		} else
+			head->w.ns = &tomoyo_kernel_namespace;
+		/* Don't allow updating if namespace is invalid. */
+		if (!head->w.ns)
+			return -ENOENT;
+	}
+	/* Do the update. */
+	return head->write(head);
+}
+
+/**
+ * tomoyo_write_control - write() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @head:       Pointer to "struct tomoyo_io_buffer".
+ * @buffer:     Pointer to buffer to read from.
+ * @buffer_len: Size of @buffer.
+ *
+ * Returns @buffer_len on success, negative value otherwise.
+ */
+ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
+			     const char __user *buffer, const int buffer_len)
+{
+	int error = buffer_len;
+	size_t avail_len = buffer_len;
+	char *cp0;
+	int idx;
+
+	if (!head->write)
+		return -EINVAL;
+	if (mutex_lock_interruptible(&head->io_sem))
+		return -EINTR;
+	cp0 = head->write_buf;
+	head->read_user_buf_avail = 0;
+	idx = tomoyo_read_lock();
+	/* Read a line and dispatch it to the policy handler. */
+	while (avail_len > 0) {
+		char c;
+
+		if (head->w.avail >= head->writebuf_size - 1) {
+			const int len = head->writebuf_size * 2;
+			char *cp = kzalloc(len, GFP_NOFS | __GFP_NOWARN);
+
+			if (!cp) {
+				error = -ENOMEM;
+				break;
+			}
+			memmove(cp, cp0, head->w.avail);
+			kfree(cp0);
+			head->write_buf = cp;
+			cp0 = cp;
+			head->writebuf_size = len;
+		}
+		if (get_user(c, buffer)) {
+			error = -EFAULT;
+			break;
+		}
+		buffer++;
+		avail_len--;
+		cp0[head->w.avail++] = c;
+		if (c != '\n')
+			continue;
+		cp0[head->w.avail - 1] = '\0';
+		head->w.avail = 0;
+		tomoyo_normalize_line(cp0);
+		if (!strcmp(cp0, "reset")) {
+			head->w.ns = &tomoyo_kernel_namespace;
+			head->w.domain = NULL;
+			memset(&head->r, 0, sizeof(head->r));
+			continue;
+		}
+		/* Don't allow updating policies by non manager programs. */
+		switch (head->type) {
+		case TOMOYO_PROCESS_STATUS:
+			/* This does not write anything. */
+			break;
+		case TOMOYO_DOMAINPOLICY:
+			if (tomoyo_select_domain(head, cp0))
+				continue;
+			fallthrough;
+		case TOMOYO_EXCEPTIONPOLICY:
+			if (!strcmp(cp0, "select transition_only")) {
+				head->r.print_transition_related_only = true;
+				continue;
+			}
+			fallthrough;
+		default:
+			if (!tomoyo_manager()) {
+				error = -EPERM;
+				goto out;
+			}
+		}
+		switch (tomoyo_parse_policy(head, cp0)) {
+		case -EPERM:
+			error = -EPERM;
+			goto out;
+		case 0:
+			switch (head->type) {
+			case TOMOYO_DOMAINPOLICY:
+			case TOMOYO_EXCEPTIONPOLICY:
+			case TOMOYO_STAT:
+			case TOMOYO_PROFILE:
+			case TOMOYO_MANAGER:
+				tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES);
+				break;
+			default:
+				break;
+			}
+			break;
+		}
+	}
+out:
+	tomoyo_read_unlock(idx);
+	mutex_unlock(&head->io_sem);
+	return error;
+}
+
+/**
+ * tomoyo_close_control - close() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @head: Pointer to "struct tomoyo_io_buffer".
+ */
+void tomoyo_close_control(struct tomoyo_io_buffer *head)
+{
+	/*
+	 * If the file is /sys/kernel/security/tomoyo/query , decrement the
+	 * observer counter.
+	 */
+	if (head->type == TOMOYO_QUERY &&
+	    atomic_dec_and_test(&tomoyo_query_observers))
+		wake_up_all(&tomoyo_answer_wait);
+	tomoyo_notify_gc(head, false);
+}
+
+/**
+ * tomoyo_check_profile - Check all profiles currently assigned to domains are defined.
+ */
+void tomoyo_check_profile(void)
+{
+	struct tomoyo_domain_info *domain;
+	const int idx = tomoyo_read_lock();
+
+	tomoyo_policy_loaded = true;
+	pr_info("TOMOYO: 2.6.0\n");
+	list_for_each_entry_rcu(domain, &tomoyo_domain_list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		const u8 profile = domain->profile;
+		struct tomoyo_policy_namespace *ns = domain->ns;
+
+		if (ns->profile_version == 20110903) {
+			pr_info_once("Converting profile version from %u to %u.\n",
+				     20110903, 20150505);
+			ns->profile_version = 20150505;
+		}
+		if (ns->profile_version != 20150505)
+			pr_err("Profile version %u is not supported.\n",
+			       ns->profile_version);
+		else if (!ns->profile_ptr[profile])
+			pr_err("Profile %u (used by '%s') is not defined.\n",
+			       profile, domain->domainname->name);
+		else
+			continue;
+		pr_err("Userland tools for TOMOYO 2.6 must be installed and policy must be initialized.\n");
+		pr_err("Please see https://tomoyo.sourceforge.net/2.6/ for more information.\n");
+		panic("STOP!");
+	}
+	tomoyo_read_unlock(idx);
+	pr_info("Mandatory Access Control activated.\n");
+}
+
+/**
+ * tomoyo_load_builtin_policy - Load built-in policy.
+ *
+ * Returns nothing.
+ */
+void __init tomoyo_load_builtin_policy(void)
+{
+#ifdef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
+	static char tomoyo_builtin_profile[] __initdata =
+		"PROFILE_VERSION=20150505\n"
+		"0-CONFIG={ mode=learning grant_log=no reject_log=yes }\n";
+	static char tomoyo_builtin_exception_policy[] __initdata =
+		"aggregator proc:/self/exe /proc/self/exe\n";
+	static char tomoyo_builtin_domain_policy[] __initdata = "";
+	static char tomoyo_builtin_manager[] __initdata = "";
+	static char tomoyo_builtin_stat[] __initdata = "";
+#else
+	/*
+	 * This include file is manually created and contains built-in policy
+	 * named "tomoyo_builtin_profile", "tomoyo_builtin_exception_policy",
+	 * "tomoyo_builtin_domain_policy", "tomoyo_builtin_manager",
+	 * "tomoyo_builtin_stat" in the form of "static char [] __initdata".
+	 */
+#include "builtin-policy.h"
+#endif
+	u8 i;
+	const int idx = tomoyo_read_lock();
+
+	for (i = 0; i < 5; i++) {
+		struct tomoyo_io_buffer head = { };
+		char *start = "";
+
+		switch (i) {
+		case 0:
+			start = tomoyo_builtin_profile;
+			head.type = TOMOYO_PROFILE;
+			head.write = tomoyo_write_profile;
+			break;
+		case 1:
+			start = tomoyo_builtin_exception_policy;
+			head.type = TOMOYO_EXCEPTIONPOLICY;
+			head.write = tomoyo_write_exception;
+			break;
+		case 2:
+			start = tomoyo_builtin_domain_policy;
+			head.type = TOMOYO_DOMAINPOLICY;
+			head.write = tomoyo_write_domain;
+			break;
+		case 3:
+			start = tomoyo_builtin_manager;
+			head.type = TOMOYO_MANAGER;
+			head.write = tomoyo_write_manager;
+			break;
+		case 4:
+			start = tomoyo_builtin_stat;
+			head.type = TOMOYO_STAT;
+			head.write = tomoyo_write_stat;
+			break;
+		}
+		while (1) {
+			char *end = strchr(start, '\n');
+
+			if (!end)
+				break;
+			*end = '\0';
+			tomoyo_normalize_line(start);
+			/* head is stack-local and not shared. */
+			context_unsafe(
+				head.write_buf = start;
+				tomoyo_parse_policy(&head, start);
+			);
+			start = end + 1;
+		}
+	}
+	tomoyo_read_unlock(idx);
+#ifdef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	tomoyo_check_profile();
+#endif
+}
diff --git a/security/tomoyo/common.h b/security/tomoyo/common.h
new file mode 100644
index 000000000..d098cf8aa
--- /dev/null
+++ b/security/tomoyo/common.h
@@ -0,0 +1,1292 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * security/tomoyo/common.h
+ *
+ * Header file for TOMOYO.
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#ifndef _SECURITY_TOMOYO_COMMON_H
+#define _SECURITY_TOMOYO_COMMON_H
+
+#define pr_fmt(fmt) fmt
+
+#include <linux/ctype.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/list.h>
+#include <linux/cred.h>
+#include <linux/poll.h>
+#include <linux/binfmts.h>
+#include <linux/highmem.h>
+#include <linux/net.h>
+#include <linux/inet.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/un.h>
+#include <linux/lsm_hooks.h>
+#include <net/sock.h>
+#include <net/af_unix.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+
+/********** Constants definitions. **********/
+
+/*
+ * TOMOYO uses this hash only when appending a string into the string
+ * table. Frequency of appending strings is very low. So we don't need
+ * large (e.g. 64k) hash size. 256 will be sufficient.
+ */
+#define TOMOYO_HASH_BITS  8
+#define TOMOYO_MAX_HASH (1u<<TOMOYO_HASH_BITS)
+
+/*
+ * TOMOYO checks only SOCK_STREAM, SOCK_DGRAM, SOCK_RAW, SOCK_SEQPACKET.
+ * Therefore, we don't need SOCK_MAX.
+ */
+#define TOMOYO_SOCK_MAX 6
+
+#define TOMOYO_EXEC_TMPSIZE     4096
+
+/* Garbage collector is trying to kfree() this element. */
+#define TOMOYO_GC_IN_PROGRESS -1
+
+/* Profile number is an integer between 0 and 255. */
+#define TOMOYO_MAX_PROFILES 256
+
+/* Group number is an integer between 0 and 255. */
+#define TOMOYO_MAX_ACL_GROUPS 256
+
+/* Index numbers for "struct tomoyo_condition". */
+enum tomoyo_conditions_index {
+	TOMOYO_TASK_UID,             /* current_uid()   */
+	TOMOYO_TASK_EUID,            /* current_euid()  */
+	TOMOYO_TASK_SUID,            /* current_suid()  */
+	TOMOYO_TASK_FSUID,           /* current_fsuid() */
+	TOMOYO_TASK_GID,             /* current_gid()   */
+	TOMOYO_TASK_EGID,            /* current_egid()  */
+	TOMOYO_TASK_SGID,            /* current_sgid()  */
+	TOMOYO_TASK_FSGID,           /* current_fsgid() */
+	TOMOYO_TASK_PID,             /* sys_getpid()   */
+	TOMOYO_TASK_PPID,            /* sys_getppid()  */
+	TOMOYO_EXEC_ARGC,            /* "struct linux_binprm *"->argc */
+	TOMOYO_EXEC_ENVC,            /* "struct linux_binprm *"->envc */
+	TOMOYO_TYPE_IS_SOCKET,       /* S_IFSOCK */
+	TOMOYO_TYPE_IS_SYMLINK,      /* S_IFLNK */
+	TOMOYO_TYPE_IS_FILE,         /* S_IFREG */
+	TOMOYO_TYPE_IS_BLOCK_DEV,    /* S_IFBLK */
+	TOMOYO_TYPE_IS_DIRECTORY,    /* S_IFDIR */
+	TOMOYO_TYPE_IS_CHAR_DEV,     /* S_IFCHR */
+	TOMOYO_TYPE_IS_FIFO,         /* S_IFIFO */
+	TOMOYO_MODE_SETUID,          /* S_ISUID */
+	TOMOYO_MODE_SETGID,          /* S_ISGID */
+	TOMOYO_MODE_STICKY,          /* S_ISVTX */
+	TOMOYO_MODE_OWNER_READ,      /* S_IRUSR */
+	TOMOYO_MODE_OWNER_WRITE,     /* S_IWUSR */
+	TOMOYO_MODE_OWNER_EXECUTE,   /* S_IXUSR */
+	TOMOYO_MODE_GROUP_READ,      /* S_IRGRP */
+	TOMOYO_MODE_GROUP_WRITE,     /* S_IWGRP */
+	TOMOYO_MODE_GROUP_EXECUTE,   /* S_IXGRP */
+	TOMOYO_MODE_OTHERS_READ,     /* S_IROTH */
+	TOMOYO_MODE_OTHERS_WRITE,    /* S_IWOTH */
+	TOMOYO_MODE_OTHERS_EXECUTE,  /* S_IXOTH */
+	TOMOYO_EXEC_REALPATH,
+	TOMOYO_SYMLINK_TARGET,
+	TOMOYO_PATH1_UID,
+	TOMOYO_PATH1_GID,
+	TOMOYO_PATH1_INO,
+	TOMOYO_PATH1_MAJOR,
+	TOMOYO_PATH1_MINOR,
+	TOMOYO_PATH1_PERM,
+	TOMOYO_PATH1_TYPE,
+	TOMOYO_PATH1_DEV_MAJOR,
+	TOMOYO_PATH1_DEV_MINOR,
+	TOMOYO_PATH2_UID,
+	TOMOYO_PATH2_GID,
+	TOMOYO_PATH2_INO,
+	TOMOYO_PATH2_MAJOR,
+	TOMOYO_PATH2_MINOR,
+	TOMOYO_PATH2_PERM,
+	TOMOYO_PATH2_TYPE,
+	TOMOYO_PATH2_DEV_MAJOR,
+	TOMOYO_PATH2_DEV_MINOR,
+	TOMOYO_PATH1_PARENT_UID,
+	TOMOYO_PATH1_PARENT_GID,
+	TOMOYO_PATH1_PARENT_INO,
+	TOMOYO_PATH1_PARENT_PERM,
+	TOMOYO_PATH2_PARENT_UID,
+	TOMOYO_PATH2_PARENT_GID,
+	TOMOYO_PATH2_PARENT_INO,
+	TOMOYO_PATH2_PARENT_PERM,
+	TOMOYO_MAX_CONDITION_KEYWORD,
+	TOMOYO_NUMBER_UNION,
+	TOMOYO_NAME_UNION,
+	TOMOYO_ARGV_ENTRY,
+	TOMOYO_ENVP_ENTRY,
+};
+
+
+/* Index numbers for stat(). */
+enum tomoyo_path_stat_index {
+	/* Do not change this order. */
+	TOMOYO_PATH1,
+	TOMOYO_PATH1_PARENT,
+	TOMOYO_PATH2,
+	TOMOYO_PATH2_PARENT,
+	TOMOYO_MAX_PATH_STAT
+};
+
+/* Index numbers for operation mode. */
+enum tomoyo_mode_index {
+	TOMOYO_CONFIG_DISABLED,
+	TOMOYO_CONFIG_LEARNING,
+	TOMOYO_CONFIG_PERMISSIVE,
+	TOMOYO_CONFIG_ENFORCING,
+	TOMOYO_CONFIG_MAX_MODE,
+	TOMOYO_CONFIG_WANT_REJECT_LOG =  64,
+	TOMOYO_CONFIG_WANT_GRANT_LOG  = 128,
+	TOMOYO_CONFIG_USE_DEFAULT     = 255,
+};
+
+/* Index numbers for entry type. */
+enum tomoyo_policy_id {
+	TOMOYO_ID_GROUP,
+	TOMOYO_ID_ADDRESS_GROUP,
+	TOMOYO_ID_PATH_GROUP,
+	TOMOYO_ID_NUMBER_GROUP,
+	TOMOYO_ID_TRANSITION_CONTROL,
+	TOMOYO_ID_AGGREGATOR,
+	TOMOYO_ID_MANAGER,
+	TOMOYO_ID_CONDITION,
+	TOMOYO_ID_NAME,
+	TOMOYO_ID_ACL,
+	TOMOYO_ID_DOMAIN,
+	TOMOYO_MAX_POLICY
+};
+
+/* Index numbers for domain's attributes. */
+enum tomoyo_domain_info_flags_index {
+	/* Quota warnning flag.   */
+	TOMOYO_DIF_QUOTA_WARNED,
+	/*
+	 * This domain was unable to create a new domain at
+	 * tomoyo_find_next_domain() because the name of the domain to be
+	 * created was too long or it could not allocate memory.
+	 * More than one process continued execve() without domain transition.
+	 */
+	TOMOYO_DIF_TRANSITION_FAILED,
+	TOMOYO_MAX_DOMAIN_INFO_FLAGS
+};
+
+/* Index numbers for audit type. */
+enum tomoyo_grant_log {
+	/* Follow profile's configuration. */
+	TOMOYO_GRANTLOG_AUTO,
+	/* Do not generate grant log. */
+	TOMOYO_GRANTLOG_NO,
+	/* Generate grant_log. */
+	TOMOYO_GRANTLOG_YES,
+};
+
+/* Index numbers for group entries. */
+enum tomoyo_group_id {
+	TOMOYO_PATH_GROUP,
+	TOMOYO_NUMBER_GROUP,
+	TOMOYO_ADDRESS_GROUP,
+	TOMOYO_MAX_GROUP
+};
+
+/* Index numbers for type of numeric values. */
+enum tomoyo_value_type {
+	TOMOYO_VALUE_TYPE_INVALID,
+	TOMOYO_VALUE_TYPE_DECIMAL,
+	TOMOYO_VALUE_TYPE_OCTAL,
+	TOMOYO_VALUE_TYPE_HEXADECIMAL,
+};
+
+/* Index numbers for domain transition control keywords. */
+enum tomoyo_transition_type {
+	/* Do not change this order, */
+	TOMOYO_TRANSITION_CONTROL_NO_RESET,
+	TOMOYO_TRANSITION_CONTROL_RESET,
+	TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE,
+	TOMOYO_TRANSITION_CONTROL_INITIALIZE,
+	TOMOYO_TRANSITION_CONTROL_NO_KEEP,
+	TOMOYO_TRANSITION_CONTROL_KEEP,
+	TOMOYO_MAX_TRANSITION_TYPE
+};
+
+/* Index numbers for Access Controls. */
+enum tomoyo_acl_entry_type_index {
+	TOMOYO_TYPE_PATH_ACL,
+	TOMOYO_TYPE_PATH2_ACL,
+	TOMOYO_TYPE_PATH_NUMBER_ACL,
+	TOMOYO_TYPE_MKDEV_ACL,
+	TOMOYO_TYPE_MOUNT_ACL,
+	TOMOYO_TYPE_INET_ACL,
+	TOMOYO_TYPE_UNIX_ACL,
+	TOMOYO_TYPE_ENV_ACL,
+	TOMOYO_TYPE_MANUAL_TASK_ACL,
+};
+
+/* Index numbers for access controls with one pathname. */
+enum tomoyo_path_acl_index {
+	TOMOYO_TYPE_EXECUTE,
+	TOMOYO_TYPE_READ,
+	TOMOYO_TYPE_WRITE,
+	TOMOYO_TYPE_APPEND,
+	TOMOYO_TYPE_UNLINK,
+	TOMOYO_TYPE_GETATTR,
+	TOMOYO_TYPE_RMDIR,
+	TOMOYO_TYPE_TRUNCATE,
+	TOMOYO_TYPE_SYMLINK,
+	TOMOYO_TYPE_CHROOT,
+	TOMOYO_TYPE_UMOUNT,
+	TOMOYO_MAX_PATH_OPERATION
+};
+
+/* Index numbers for /sys/kernel/security/tomoyo/stat interface. */
+enum tomoyo_memory_stat_type {
+	TOMOYO_MEMORY_POLICY,
+	TOMOYO_MEMORY_AUDIT,
+	TOMOYO_MEMORY_QUERY,
+	TOMOYO_MAX_MEMORY_STAT
+};
+
+enum tomoyo_mkdev_acl_index {
+	TOMOYO_TYPE_MKBLOCK,
+	TOMOYO_TYPE_MKCHAR,
+	TOMOYO_MAX_MKDEV_OPERATION
+};
+
+/* Index numbers for socket operations. */
+enum tomoyo_network_acl_index {
+	TOMOYO_NETWORK_BIND,    /* bind() operation. */
+	TOMOYO_NETWORK_LISTEN,  /* listen() operation. */
+	TOMOYO_NETWORK_CONNECT, /* connect() operation. */
+	TOMOYO_NETWORK_SEND,    /* send() operation. */
+	TOMOYO_MAX_NETWORK_OPERATION
+};
+
+/* Index numbers for access controls with two pathnames. */
+enum tomoyo_path2_acl_index {
+	TOMOYO_TYPE_LINK,
+	TOMOYO_TYPE_RENAME,
+	TOMOYO_TYPE_PIVOT_ROOT,
+	TOMOYO_MAX_PATH2_OPERATION
+};
+
+/* Index numbers for access controls with one pathname and one number. */
+enum tomoyo_path_number_acl_index {
+	TOMOYO_TYPE_CREATE,
+	TOMOYO_TYPE_MKDIR,
+	TOMOYO_TYPE_MKFIFO,
+	TOMOYO_TYPE_MKSOCK,
+	TOMOYO_TYPE_IOCTL,
+	TOMOYO_TYPE_CHMOD,
+	TOMOYO_TYPE_CHOWN,
+	TOMOYO_TYPE_CHGRP,
+	TOMOYO_MAX_PATH_NUMBER_OPERATION
+};
+
+/* Index numbers for /sys/kernel/security/tomoyo/ interfaces. */
+enum tomoyo_securityfs_interface_index {
+	TOMOYO_DOMAINPOLICY,
+	TOMOYO_EXCEPTIONPOLICY,
+	TOMOYO_PROCESS_STATUS,
+	TOMOYO_STAT,
+	TOMOYO_AUDIT,
+	TOMOYO_VERSION,
+	TOMOYO_PROFILE,
+	TOMOYO_QUERY,
+	TOMOYO_MANAGER
+};
+
+/* Index numbers for special mount operations. */
+enum tomoyo_special_mount {
+	TOMOYO_MOUNT_BIND,            /* mount --bind /source /dest   */
+	TOMOYO_MOUNT_MOVE,            /* mount --move /old /new       */
+	TOMOYO_MOUNT_REMOUNT,         /* mount -o remount /dir        */
+	TOMOYO_MOUNT_MAKE_UNBINDABLE, /* mount --make-unbindable /dir */
+	TOMOYO_MOUNT_MAKE_PRIVATE,    /* mount --make-private /dir    */
+	TOMOYO_MOUNT_MAKE_SLAVE,      /* mount --make-slave /dir      */
+	TOMOYO_MOUNT_MAKE_SHARED,     /* mount --make-shared /dir     */
+	TOMOYO_MAX_SPECIAL_MOUNT
+};
+
+/* Index numbers for functionality. */
+enum tomoyo_mac_index {
+	TOMOYO_MAC_FILE_EXECUTE,
+	TOMOYO_MAC_FILE_OPEN,
+	TOMOYO_MAC_FILE_CREATE,
+	TOMOYO_MAC_FILE_UNLINK,
+	TOMOYO_MAC_FILE_GETATTR,
+	TOMOYO_MAC_FILE_MKDIR,
+	TOMOYO_MAC_FILE_RMDIR,
+	TOMOYO_MAC_FILE_MKFIFO,
+	TOMOYO_MAC_FILE_MKSOCK,
+	TOMOYO_MAC_FILE_TRUNCATE,
+	TOMOYO_MAC_FILE_SYMLINK,
+	TOMOYO_MAC_FILE_MKBLOCK,
+	TOMOYO_MAC_FILE_MKCHAR,
+	TOMOYO_MAC_FILE_LINK,
+	TOMOYO_MAC_FILE_RENAME,
+	TOMOYO_MAC_FILE_CHMOD,
+	TOMOYO_MAC_FILE_CHOWN,
+	TOMOYO_MAC_FILE_CHGRP,
+	TOMOYO_MAC_FILE_IOCTL,
+	TOMOYO_MAC_FILE_CHROOT,
+	TOMOYO_MAC_FILE_MOUNT,
+	TOMOYO_MAC_FILE_UMOUNT,
+	TOMOYO_MAC_FILE_PIVOT_ROOT,
+	TOMOYO_MAC_NETWORK_INET_STREAM_BIND,
+	TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN,
+	TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT,
+	TOMOYO_MAC_NETWORK_INET_DGRAM_BIND,
+	TOMOYO_MAC_NETWORK_INET_DGRAM_SEND,
+	TOMOYO_MAC_NETWORK_INET_RAW_BIND,
+	TOMOYO_MAC_NETWORK_INET_RAW_SEND,
+	TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND,
+	TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN,
+	TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT,
+	TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND,
+	TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND,
+	TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND,
+	TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN,
+	TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT,
+	TOMOYO_MAC_ENVIRON,
+	TOMOYO_MAX_MAC_INDEX
+};
+
+/* Index numbers for category of functionality. */
+enum tomoyo_mac_category_index {
+	TOMOYO_MAC_CATEGORY_FILE,
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	TOMOYO_MAC_CATEGORY_MISC,
+	TOMOYO_MAX_MAC_CATEGORY_INDEX
+};
+
+/*
+ * Retry this request. Returned by tomoyo_supervisor() if policy violation has
+ * occurred in enforcing mode and the userspace daemon decided to retry.
+ *
+ * We must choose a positive value in order to distinguish "granted" (which is
+ * 0) and "rejected" (which is a negative value) and "retry".
+ */
+#define TOMOYO_RETRY_REQUEST 1
+
+/* Index numbers for /sys/kernel/security/tomoyo/stat interface. */
+enum tomoyo_policy_stat_type {
+	/* Do not change this order. */
+	TOMOYO_STAT_POLICY_UPDATES,
+	TOMOYO_STAT_POLICY_LEARNING,   /* == TOMOYO_CONFIG_LEARNING */
+	TOMOYO_STAT_POLICY_PERMISSIVE, /* == TOMOYO_CONFIG_PERMISSIVE */
+	TOMOYO_STAT_POLICY_ENFORCING,  /* == TOMOYO_CONFIG_ENFORCING */
+	TOMOYO_MAX_POLICY_STAT
+};
+
+/* Index numbers for profile's PREFERENCE values. */
+enum tomoyo_pref_index {
+	TOMOYO_PREF_MAX_AUDIT_LOG,
+	TOMOYO_PREF_MAX_LEARNING_ENTRY,
+	TOMOYO_MAX_PREF
+};
+
+/********** Structure definitions. **********/
+
+/* Common header for holding ACL entries. */
+struct tomoyo_acl_head {
+	struct list_head list;
+	s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */
+} __packed;
+
+/* Common header for shared entries. */
+struct tomoyo_shared_acl_head {
+	struct list_head list;
+	atomic_t users;
+} __packed;
+
+struct tomoyo_policy_namespace;
+
+/* Structure for request info. */
+struct tomoyo_request_info {
+	/*
+	 * For holding parameters specific to operations which deal files.
+	 * NULL if not dealing files.
+	 */
+	struct tomoyo_obj_info *obj;
+	/*
+	 * For holding parameters specific to execve() request.
+	 * NULL if not dealing execve().
+	 */
+	struct tomoyo_execve *ee;
+	struct tomoyo_domain_info *domain;
+	/* For holding parameters. */
+	union {
+		struct {
+			const struct tomoyo_path_info *filename;
+			/* For using wildcards at tomoyo_find_next_domain(). */
+			const struct tomoyo_path_info *matched_path;
+			/* One of values in "enum tomoyo_path_acl_index". */
+			u8 operation;
+		} path;
+		struct {
+			const struct tomoyo_path_info *filename1;
+			const struct tomoyo_path_info *filename2;
+			/* One of values in "enum tomoyo_path2_acl_index". */
+			u8 operation;
+		} path2;
+		struct {
+			const struct tomoyo_path_info *filename;
+			unsigned int mode;
+			unsigned int major;
+			unsigned int minor;
+			/* One of values in "enum tomoyo_mkdev_acl_index". */
+			u8 operation;
+		} mkdev;
+		struct {
+			const struct tomoyo_path_info *filename;
+			unsigned long number;
+			/*
+			 * One of values in
+			 * "enum tomoyo_path_number_acl_index".
+			 */
+			u8 operation;
+		} path_number;
+		struct {
+			const struct tomoyo_path_info *name;
+		} environ;
+		struct {
+			const __be32 *address;
+			u16 port;
+			/* One of values smaller than TOMOYO_SOCK_MAX. */
+			u8 protocol;
+			/* One of values in "enum tomoyo_network_acl_index". */
+			u8 operation;
+			bool is_ipv6;
+		} inet_network;
+		struct {
+			const struct tomoyo_path_info *address;
+			/* One of values smaller than TOMOYO_SOCK_MAX. */
+			u8 protocol;
+			/* One of values in "enum tomoyo_network_acl_index". */
+			u8 operation;
+		} unix_network;
+		struct {
+			const struct tomoyo_path_info *type;
+			const struct tomoyo_path_info *dir;
+			const struct tomoyo_path_info *dev;
+			unsigned long flags;
+			int need_dev;
+		} mount;
+		struct {
+			const struct tomoyo_path_info *domainname;
+		} task;
+	} param;
+	struct tomoyo_acl_info *matched_acl;
+	u8 param_type;
+	bool granted;
+	u8 retry;
+	u8 profile;
+	u8 mode; /* One of tomoyo_mode_index . */
+	u8 type;
+};
+
+/* Structure for holding a token. */
+struct tomoyo_path_info {
+	const char *name;
+	u32 hash;          /* = full_name_hash(name, strlen(name)) */
+	u16 const_len;     /* = tomoyo_const_part_length(name)     */
+	bool is_dir;       /* = tomoyo_strendswith(name, "/")      */
+	bool is_patterned; /* = tomoyo_path_contains_pattern(name) */
+};
+
+/* Structure for holding string data. */
+struct tomoyo_name {
+	struct tomoyo_shared_acl_head head;
+	struct tomoyo_path_info entry;
+};
+
+/* Structure for holding a word. */
+struct tomoyo_name_union {
+	/* Either @filename or @group is NULL. */
+	const struct tomoyo_path_info *filename;
+	struct tomoyo_group *group;
+};
+
+/* Structure for holding a number. */
+struct tomoyo_number_union {
+	unsigned long values[2];
+	struct tomoyo_group *group; /* Maybe NULL. */
+	/* One of values in "enum tomoyo_value_type". */
+	u8 value_type[2];
+};
+
+/* Structure for holding an IP address. */
+struct tomoyo_ipaddr_union {
+	struct in6_addr ip[2]; /* Big endian. */
+	struct tomoyo_group *group; /* Pointer to address group. */
+	bool is_ipv6; /* Valid only if @group == NULL. */
+};
+
+/* Structure for "path_group"/"number_group"/"address_group" directive. */
+struct tomoyo_group {
+	struct tomoyo_shared_acl_head head;
+	const struct tomoyo_path_info *group_name;
+	struct list_head member_list;
+};
+
+/* Structure for "path_group" directive. */
+struct tomoyo_path_group {
+	struct tomoyo_acl_head head;
+	const struct tomoyo_path_info *member_name;
+};
+
+/* Structure for "number_group" directive. */
+struct tomoyo_number_group {
+	struct tomoyo_acl_head head;
+	struct tomoyo_number_union number;
+};
+
+/* Structure for "address_group" directive. */
+struct tomoyo_address_group {
+	struct tomoyo_acl_head head;
+	/* Structure for holding an IP address. */
+	struct tomoyo_ipaddr_union address;
+};
+
+/* Subset of "struct stat". Used by conditional ACL and audit logs. */
+struct tomoyo_mini_stat {
+	kuid_t uid;
+	kgid_t gid;
+	u64 ino;
+	umode_t mode;
+	dev_t dev;
+	dev_t rdev;
+};
+
+/* Structure for dumping argv[] and envp[] of "struct linux_binprm". */
+struct tomoyo_page_dump {
+	struct page *page;    /* Previously dumped page. */
+	char *data;           /* Contents of "page". Size is PAGE_SIZE. */
+};
+
+/* Structure for attribute checks in addition to pathname checks. */
+struct tomoyo_obj_info {
+	/*
+	 * True if tomoyo_get_attributes() was already called, false otherwise.
+	 */
+	bool validate_done;
+	/* True if @stat[] is valid. */
+	bool stat_valid[TOMOYO_MAX_PATH_STAT];
+	/* First pathname. Initialized with { NULL, NULL } if no path. */
+	struct path path1;
+	/* Second pathname. Initialized with { NULL, NULL } if no path. */
+	struct path path2;
+	/*
+	 * Information on @path1, @path1's parent directory, @path2, @path2's
+	 * parent directory.
+	 */
+	struct tomoyo_mini_stat stat[TOMOYO_MAX_PATH_STAT];
+	/*
+	 * Content of symbolic link to be created. NULL for operations other
+	 * than symlink().
+	 */
+	struct tomoyo_path_info *symlink_target;
+};
+
+/* Structure for argv[]. */
+struct tomoyo_argv {
+	unsigned long index;
+	const struct tomoyo_path_info *value;
+	bool is_not;
+};
+
+/* Structure for envp[]. */
+struct tomoyo_envp {
+	const struct tomoyo_path_info *name;
+	const struct tomoyo_path_info *value;
+	bool is_not;
+};
+
+/* Structure for execve() operation. */
+struct tomoyo_execve {
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj;
+	struct linux_binprm *bprm;
+	const struct tomoyo_path_info *transition;
+	/* For dumping argv[] and envp[]. */
+	struct tomoyo_page_dump dump;
+	/* For temporary use. */
+	char *tmp; /* Size is TOMOYO_EXEC_TMPSIZE bytes */
+};
+
+/* Structure for entries which follows "struct tomoyo_condition". */
+struct tomoyo_condition_element {
+	/*
+	 * Left hand operand. A "struct tomoyo_argv" for TOMOYO_ARGV_ENTRY, a
+	 * "struct tomoyo_envp" for TOMOYO_ENVP_ENTRY is attached to the tail
+	 * of the array of this struct.
+	 */
+	u8 left;
+	/*
+	 * Right hand operand. A "struct tomoyo_number_union" for
+	 * TOMOYO_NUMBER_UNION, a "struct tomoyo_name_union" for
+	 * TOMOYO_NAME_UNION is attached to the tail of the array of this
+	 * struct.
+	 */
+	u8 right;
+	/* Equation operator. True if equals or overlaps, false otherwise. */
+	bool equals;
+};
+
+/* Structure for optional arguments. */
+struct tomoyo_condition {
+	struct tomoyo_shared_acl_head head;
+	u32 size; /* Memory size allocated for this entry. */
+	u16 condc; /* Number of conditions in this struct. */
+	u16 numbers_count; /* Number of "struct tomoyo_number_union values". */
+	u16 names_count; /* Number of "struct tomoyo_name_union names". */
+	u16 argc; /* Number of "struct tomoyo_argv". */
+	u16 envc; /* Number of "struct tomoyo_envp". */
+	u8 grant_log; /* One of values in "enum tomoyo_grant_log". */
+	const struct tomoyo_path_info *transit; /* Maybe NULL. */
+	/*
+	 * struct tomoyo_condition_element condition[condc];
+	 * struct tomoyo_number_union values[numbers_count];
+	 * struct tomoyo_name_union names[names_count];
+	 * struct tomoyo_argv argv[argc];
+	 * struct tomoyo_envp envp[envc];
+	 */
+};
+
+/* Common header for individual entries. */
+struct tomoyo_acl_info {
+	struct list_head list;
+	struct tomoyo_condition *cond; /* Maybe NULL. */
+	s8 is_deleted; /* true or false or TOMOYO_GC_IN_PROGRESS */
+	u8 type; /* One of values in "enum tomoyo_acl_entry_type_index". */
+} __packed;
+
+/* Structure for domain information. */
+struct tomoyo_domain_info {
+	struct list_head list;
+	struct list_head acl_info_list;
+	/* Name of this domain. Never NULL.          */
+	const struct tomoyo_path_info *domainname;
+	/* Namespace for this domain. Never NULL. */
+	struct tomoyo_policy_namespace *ns;
+	/* Group numbers to use.   */
+	unsigned long group[TOMOYO_MAX_ACL_GROUPS / BITS_PER_LONG];
+	u8 profile;        /* Profile number to use. */
+	bool is_deleted;   /* Delete flag.           */
+	bool flags[TOMOYO_MAX_DOMAIN_INFO_FLAGS];
+	atomic_t users; /* Number of referring tasks. */
+};
+
+/*
+ * Structure for "task manual_domain_transition" directive.
+ */
+struct tomoyo_task_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MANUAL_TASK_ACL */
+	/* Pointer to domainname. */
+	const struct tomoyo_path_info *domainname;
+};
+
+/*
+ * Structure for "file execute", "file read", "file write", "file append",
+ * "file unlink", "file getattr", "file rmdir", "file truncate",
+ * "file symlink", "file chroot" and "file unmount" directive.
+ */
+struct tomoyo_path_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_ACL */
+	u16 perm; /* Bitmask of values in "enum tomoyo_path_acl_index". */
+	struct tomoyo_name_union name;
+};
+
+/*
+ * Structure for "file create", "file mkdir", "file mkfifo", "file mksock",
+ * "file ioctl", "file chmod", "file chown" and "file chgrp" directive.
+ */
+struct tomoyo_path_number_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH_NUMBER_ACL */
+	/* Bitmask of values in "enum tomoyo_path_number_acl_index". */
+	u8 perm;
+	struct tomoyo_name_union name;
+	struct tomoyo_number_union number;
+};
+
+/* Structure for "file mkblock" and "file mkchar" directive. */
+struct tomoyo_mkdev_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MKDEV_ACL */
+	u8 perm; /* Bitmask of values in "enum tomoyo_mkdev_acl_index". */
+	struct tomoyo_name_union name;
+	struct tomoyo_number_union mode;
+	struct tomoyo_number_union major;
+	struct tomoyo_number_union minor;
+};
+
+/*
+ * Structure for "file rename", "file link" and "file pivot_root" directive.
+ */
+struct tomoyo_path2_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_PATH2_ACL */
+	u8 perm; /* Bitmask of values in "enum tomoyo_path2_acl_index". */
+	struct tomoyo_name_union name1;
+	struct tomoyo_name_union name2;
+};
+
+/* Structure for "file mount" directive. */
+struct tomoyo_mount_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_MOUNT_ACL */
+	struct tomoyo_name_union dev_name;
+	struct tomoyo_name_union dir_name;
+	struct tomoyo_name_union fs_type;
+	struct tomoyo_number_union flags;
+};
+
+/* Structure for "misc env" directive in domain policy. */
+struct tomoyo_env_acl {
+	struct tomoyo_acl_info head;        /* type = TOMOYO_TYPE_ENV_ACL  */
+	const struct tomoyo_path_info *env; /* environment variable */
+};
+
+/* Structure for "network inet" directive. */
+struct tomoyo_inet_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_INET_ACL */
+	u8 protocol;
+	u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */
+	struct tomoyo_ipaddr_union address;
+	struct tomoyo_number_union port;
+};
+
+/* Structure for "network unix" directive. */
+struct tomoyo_unix_acl {
+	struct tomoyo_acl_info head; /* type = TOMOYO_TYPE_UNIX_ACL */
+	u8 protocol;
+	u8 perm; /* Bitmask of values in "enum tomoyo_network_acl_index" */
+	struct tomoyo_name_union name;
+};
+
+/* Structure for holding a line from /sys/kernel/security/tomoyo/ interface. */
+struct tomoyo_acl_param {
+	char *data;
+	struct list_head *list;
+	struct tomoyo_policy_namespace *ns;
+	bool is_delete;
+};
+
+#define TOMOYO_MAX_IO_READ_QUEUE 64
+
+/*
+ * Structure for reading/writing policy via /sys/kernel/security/tomoyo
+ * interfaces.
+ */
+struct tomoyo_io_buffer {
+	void (*read)(struct tomoyo_io_buffer *head);
+	int (*write)(struct tomoyo_io_buffer *head);
+	__poll_t (*poll)(struct file *file, poll_table *wait);
+	/* Exclusive lock for this structure.   */
+	struct mutex io_sem;
+	char __user *read_user_buf;
+	size_t read_user_buf_avail;
+	struct {
+		struct list_head *ns;
+		struct list_head *domain;
+		struct list_head *group;
+		struct list_head *acl;
+		size_t avail;
+		unsigned int step;
+		unsigned int query_index;
+		u16 index;
+		u16 cond_index;
+		u8 acl_group_index;
+		u8 cond_step;
+		u8 bit;
+		u8 w_pos;
+		bool eof;
+		bool print_this_domain_only;
+		bool print_transition_related_only;
+		bool print_cond_part;
+		const char *w[TOMOYO_MAX_IO_READ_QUEUE];
+	} r;
+	struct {
+		struct tomoyo_policy_namespace *ns;
+		/* The position currently writing to.   */
+		struct tomoyo_domain_info *domain;
+		/* Bytes available for writing.         */
+		size_t avail;
+		bool is_delete;
+	} w;
+	/* Buffer for reading.                  */
+	char *read_buf		__guarded_by(&io_sem);
+	/* Size of read buffer.                 */
+	size_t readbuf_size	__guarded_by(&io_sem);
+	/* Buffer for writing.                  */
+	char *write_buf		__guarded_by(&io_sem);
+	/* Size of write buffer.                */
+	size_t writebuf_size	__guarded_by(&io_sem);
+	/* Type of this interface.              */
+	enum tomoyo_securityfs_interface_index type;
+	/* Users counter protected by tomoyo_io_buffer_list_lock. */
+	u8 users;
+	/* List for telling GC not to kfree() elements. */
+	struct list_head list;
+};
+
+/*
+ * Structure for "initialize_domain"/"no_initialize_domain"/"keep_domain"/
+ * "no_keep_domain" keyword.
+ */
+struct tomoyo_transition_control {
+	struct tomoyo_acl_head head;
+	u8 type; /* One of values in "enum tomoyo_transition_type".  */
+	/* True if the domainname is tomoyo_get_last_name(). */
+	bool is_last_name;
+	const struct tomoyo_path_info *domainname; /* Maybe NULL */
+	const struct tomoyo_path_info *program;    /* Maybe NULL */
+};
+
+/* Structure for "aggregator" keyword. */
+struct tomoyo_aggregator {
+	struct tomoyo_acl_head head;
+	const struct tomoyo_path_info *original_name;
+	const struct tomoyo_path_info *aggregated_name;
+};
+
+/* Structure for policy manager. */
+struct tomoyo_manager {
+	struct tomoyo_acl_head head;
+	/* A path to program or a domainname. */
+	const struct tomoyo_path_info *manager;
+};
+
+struct tomoyo_preference {
+	unsigned int learning_max_entry;
+	bool enforcing_verbose;
+	bool learning_verbose;
+	bool permissive_verbose;
+};
+
+/* Structure for /sys/kernel/security/tomnoyo/profile interface. */
+struct tomoyo_profile {
+	const struct tomoyo_path_info *comment;
+	struct tomoyo_preference *learning;
+	struct tomoyo_preference *permissive;
+	struct tomoyo_preference *enforcing;
+	struct tomoyo_preference preference;
+	u8 default_config;
+	u8 config[TOMOYO_MAX_MAC_INDEX + TOMOYO_MAX_MAC_CATEGORY_INDEX];
+	unsigned int pref[TOMOYO_MAX_PREF];
+};
+
+/* Structure for representing YYYY/MM/DD hh/mm/ss. */
+struct tomoyo_time {
+	u16 year;
+	u8 month;
+	u8 day;
+	u8 hour;
+	u8 min;
+	u8 sec;
+};
+
+/* Structure for policy namespace. */
+struct tomoyo_policy_namespace {
+	/* Profile table. Memory is allocated as needed. */
+	struct tomoyo_profile *profile_ptr[TOMOYO_MAX_PROFILES];
+	/* List of "struct tomoyo_group". */
+	struct list_head group_list[TOMOYO_MAX_GROUP];
+	/* List of policy. */
+	struct list_head policy_list[TOMOYO_MAX_POLICY];
+	/* The global ACL referred by "use_group" keyword. */
+	struct list_head acl_group[TOMOYO_MAX_ACL_GROUPS];
+	/* List for connecting to tomoyo_namespace_list list. */
+	struct list_head namespace_list;
+	/* Profile version. Currently only 20150505 is defined. */
+	unsigned int profile_version;
+	/* Name of this namespace (e.g. "<kernel>", "</usr/sbin/httpd>" ). */
+	const char *name;
+};
+
+/* Structure for "struct task_struct"->security. */
+struct tomoyo_task {
+	struct tomoyo_domain_info *domain_info;
+	struct tomoyo_domain_info *old_domain_info;
+};
+
+/********** External variable definitions. **********/
+
+extern bool tomoyo_policy_loaded;
+extern int tomoyo_enabled;
+extern const char * const tomoyo_condition_keyword
+[TOMOYO_MAX_CONDITION_KEYWORD];
+extern const char * const tomoyo_dif[TOMOYO_MAX_DOMAIN_INFO_FLAGS];
+extern const char * const tomoyo_mac_keywords[TOMOYO_MAX_MAC_INDEX
+					      + TOMOYO_MAX_MAC_CATEGORY_INDEX];
+extern const char * const tomoyo_mode[TOMOYO_CONFIG_MAX_MODE];
+extern const char * const tomoyo_path_keyword[TOMOYO_MAX_PATH_OPERATION];
+extern const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX];
+extern const char * const tomoyo_socket_keyword[TOMOYO_MAX_NETWORK_OPERATION];
+extern const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX];
+extern const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION];
+extern const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION];
+extern const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION];
+extern struct list_head tomoyo_condition_list;
+extern struct list_head tomoyo_domain_list;
+extern struct list_head tomoyo_name_list[TOMOYO_MAX_HASH];
+extern struct list_head tomoyo_namespace_list;
+extern struct mutex tomoyo_policy_lock;
+extern struct srcu_struct tomoyo_ss;
+extern struct tomoyo_domain_info tomoyo_kernel_domain;
+extern struct tomoyo_policy_namespace tomoyo_kernel_namespace;
+extern unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT];
+extern unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT];
+extern struct lsm_blob_sizes tomoyo_blob_sizes;
+
+/********** Function prototypes. **********/
+
+int tomoyo_interface_init(void);
+
+bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address,
+				  const struct tomoyo_group *group);
+bool tomoyo_compare_number_union(const unsigned long value,
+				 const struct tomoyo_number_union *ptr);
+bool tomoyo_condition(struct tomoyo_request_info *r,
+		      const struct tomoyo_condition *cond);
+bool tomoyo_correct_domain(const unsigned char *domainname);
+bool tomoyo_correct_path(const char *filename);
+bool tomoyo_correct_word(const char *string);
+bool tomoyo_domain_def(const unsigned char *buffer);
+bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r);
+bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
+		      struct tomoyo_page_dump *dump);
+bool tomoyo_memory_ok(void *ptr);
+bool tomoyo_number_matches_group(const unsigned long min,
+				 const unsigned long max,
+				 const struct tomoyo_group *group);
+bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param,
+			       struct tomoyo_ipaddr_union *ptr);
+bool tomoyo_parse_name_union(struct tomoyo_acl_param *param,
+			     struct tomoyo_name_union *ptr);
+bool tomoyo_parse_number_union(struct tomoyo_acl_param *param,
+			       struct tomoyo_number_union *ptr);
+bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename,
+				 const struct tomoyo_path_info *pattern);
+bool tomoyo_permstr(const char *string, const char *keyword);
+bool tomoyo_str_starts(char **src, const char *find);
+char *tomoyo_encode(const char *str);
+char *tomoyo_encode2(const char *str, int str_len);
+char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt,
+		      va_list args) __printf(3, 0);
+char *tomoyo_read_token(struct tomoyo_acl_param *param);
+char *tomoyo_realpath_from_path(const struct path *path);
+char *tomoyo_realpath_nofollow(const char *pathname);
+const char *tomoyo_get_exe(void);
+const struct tomoyo_path_info *tomoyo_compare_name_union
+(const struct tomoyo_path_info *name, const struct tomoyo_name_union *ptr);
+const struct tomoyo_path_info *tomoyo_get_domainname
+(struct tomoyo_acl_param *param);
+const struct tomoyo_path_info *tomoyo_get_name(const char *name);
+const struct tomoyo_path_info *tomoyo_path_matches_group
+(const struct tomoyo_path_info *pathname, const struct tomoyo_group *group);
+int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
+				 const struct path *path, const int flag);
+void tomoyo_close_control(struct tomoyo_io_buffer *head);
+int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env) __must_hold_shared(&tomoyo_ss);
+int tomoyo_execute_permission(struct tomoyo_request_info *r,
+			      const struct tomoyo_path_info *filename) __must_hold_shared(&tomoyo_ss);
+int tomoyo_find_next_domain(struct linux_binprm *bprm) __must_hold_shared(&tomoyo_ss);
+int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile,
+		    const u8 index);
+int tomoyo_init_request_info(struct tomoyo_request_info *r,
+			     struct tomoyo_domain_info *domain,
+			     const u8 index);
+int tomoyo_mkdev_perm(const u8 operation, const struct path *path,
+		      const unsigned int mode, unsigned int dev);
+int tomoyo_mount_permission(const char *dev_name, const struct path *path,
+			    const char *type, unsigned long flags,
+			    void *data_page);
+int tomoyo_open_control(const u8 type, struct file *file);
+int tomoyo_path2_perm(const u8 operation, const struct path *path1,
+		      const struct path *path2);
+int tomoyo_path_number_perm(const u8 operation, const struct path *path,
+			    unsigned long number);
+int tomoyo_path_perm(const u8 operation, const struct path *path,
+		     const char *target);
+__poll_t tomoyo_poll_control(struct file *file, poll_table *wait);
+__poll_t tomoyo_poll_log(struct file *file, poll_table *wait);
+int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr,
+				  int addr_len);
+int tomoyo_socket_connect_permission(struct socket *sock,
+				     struct sockaddr *addr, int addr_len);
+int tomoyo_socket_listen_permission(struct socket *sock);
+int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg,
+				     int size);
+int tomoyo_supervisor(struct tomoyo_request_info *r, const char *fmt, ...)
+	__must_hold_shared(&tomoyo_ss)
+	__printf(2, 3);
+int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size,
+			 struct tomoyo_acl_param *param,
+			 bool (*check_duplicate)
+			 (const struct tomoyo_acl_info *,
+			  const struct tomoyo_acl_info *),
+			 bool (*merge_duplicate)
+			 (struct tomoyo_acl_info *, struct tomoyo_acl_info *,
+			  const bool));
+int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size,
+			 struct tomoyo_acl_param *param,
+			 bool (*check_duplicate)
+			 (const struct tomoyo_acl_head *,
+			  const struct tomoyo_acl_head *));
+int tomoyo_write_aggregator(struct tomoyo_acl_param *param);
+int tomoyo_write_file(struct tomoyo_acl_param *param);
+int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type);
+int tomoyo_write_misc(struct tomoyo_acl_param *param);
+int tomoyo_write_inet_network(struct tomoyo_acl_param *param);
+int tomoyo_write_transition_control(struct tomoyo_acl_param *param,
+				    const u8 type);
+int tomoyo_write_unix_network(struct tomoyo_acl_param *param);
+ssize_t tomoyo_read_control(struct tomoyo_io_buffer *head, char __user *buffer,
+			    const int buffer_len);
+ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head,
+			     const char __user *buffer, const int buffer_len);
+struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param);
+struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname,
+						const bool transit);
+struct tomoyo_domain_info *tomoyo_domain(void);
+struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname);
+struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param,
+				      const u8 idx);
+struct tomoyo_policy_namespace *tomoyo_assign_namespace
+(const char *domainname);
+struct tomoyo_profile *tomoyo_profile(const struct tomoyo_policy_namespace *ns,
+				      const u8 profile);
+u8 tomoyo_parse_ulong(unsigned long *result, char **str);
+void *tomoyo_commit_ok(void *data, const unsigned int size);
+void __init tomoyo_load_builtin_policy(void);
+void __init tomoyo_mm_init(void);
+void tomoyo_check_acl(struct tomoyo_request_info *r,
+		      bool (*check_entry)(struct tomoyo_request_info *,
+					  const struct tomoyo_acl_info *));
+void tomoyo_check_profile(void);
+void tomoyo_convert_time(time64_t time, struct tomoyo_time *stamp);
+void tomoyo_del_condition(struct list_head *element);
+void tomoyo_fill_path_info(struct tomoyo_path_info *ptr);
+void tomoyo_get_attributes(struct tomoyo_obj_info *obj);
+void tomoyo_init_policy_namespace(struct tomoyo_policy_namespace *ns);
+void tomoyo_load_policy(const char *filename);
+void tomoyo_normalize_line(unsigned char *buffer);
+void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register);
+void tomoyo_print_ip(char *buf, const unsigned int size,
+		     const struct tomoyo_ipaddr_union *ptr);
+void tomoyo_print_ulong(char *buffer, const int buffer_len,
+			const unsigned long value, const u8 type);
+void tomoyo_put_name_union(struct tomoyo_name_union *ptr);
+void tomoyo_put_number_union(struct tomoyo_number_union *ptr);
+void tomoyo_read_log(struct tomoyo_io_buffer *head) __must_hold(&head->io_sem);
+void tomoyo_update_stat(const u8 index);
+void tomoyo_warn_oom(const char *function);
+void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...)
+	__printf(2, 3);
+void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt,
+		       va_list args) __printf(3, 0);
+
+/********** Inlined functions. **********/
+
+/**
+ * tomoyo_read_lock - Take lock for protecting policy.
+ *
+ * Returns index number for tomoyo_read_unlock().
+ */
+static inline int tomoyo_read_lock(void)
+	__acquires_shared(&tomoyo_ss)
+{
+	return srcu_read_lock(&tomoyo_ss);
+}
+
+/**
+ * tomoyo_read_unlock - Release lock for protecting policy.
+ *
+ * @idx: Index number returned by tomoyo_read_lock().
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_read_unlock(int idx)
+	__releases_shared(&tomoyo_ss)
+{
+	srcu_read_unlock(&tomoyo_ss, idx);
+}
+
+/**
+ * tomoyo_sys_getppid - Copy of getppid().
+ *
+ * Returns parent process's PID.
+ *
+ * Alpha does not have getppid() defined. To be able to build this module on
+ * Alpha, I have to copy getppid() from kernel/timer.c.
+ */
+static inline pid_t tomoyo_sys_getppid(void)
+{
+	pid_t pid;
+
+	rcu_read_lock();
+	pid = task_tgid_vnr(rcu_dereference(current->real_parent));
+	rcu_read_unlock();
+	return pid;
+}
+
+/**
+ * tomoyo_sys_getpid - Copy of getpid().
+ *
+ * Returns current thread's PID.
+ *
+ * Alpha does not have getpid() defined. To be able to build this module on
+ * Alpha, I have to copy getpid() from kernel/timer.c.
+ */
+static inline pid_t tomoyo_sys_getpid(void)
+{
+	return task_tgid_vnr(current);
+}
+
+/**
+ * tomoyo_pathcmp - strcmp() for "struct tomoyo_path_info" structure.
+ *
+ * @a: Pointer to "struct tomoyo_path_info".
+ * @b: Pointer to "struct tomoyo_path_info".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_pathcmp(const struct tomoyo_path_info *a,
+				  const struct tomoyo_path_info *b)
+{
+	return a->hash != b->hash || strcmp(a->name, b->name);
+}
+
+/**
+ * tomoyo_put_name - Drop reference on "struct tomoyo_name".
+ *
+ * @name: Pointer to "struct tomoyo_path_info". Maybe NULL.
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_put_name(const struct tomoyo_path_info *name)
+{
+	if (name) {
+		struct tomoyo_name *ptr =
+			container_of(name, typeof(*ptr), entry);
+		atomic_dec(&ptr->head.users);
+	}
+}
+
+/**
+ * tomoyo_put_condition - Drop reference on "struct tomoyo_condition".
+ *
+ * @cond: Pointer to "struct tomoyo_condition". Maybe NULL.
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_put_condition(struct tomoyo_condition *cond)
+{
+	if (cond)
+		atomic_dec(&cond->head.users);
+}
+
+/**
+ * tomoyo_put_group - Drop reference on "struct tomoyo_group".
+ *
+ * @group: Pointer to "struct tomoyo_group". Maybe NULL.
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_put_group(struct tomoyo_group *group)
+{
+	if (group)
+		atomic_dec(&group->head.users);
+}
+
+/**
+ * tomoyo_task - Get "struct tomoyo_task" for specified thread.
+ *
+ * @task - Pointer to "struct task_struct".
+ *
+ * Returns pointer to "struct tomoyo_task" for specified thread.
+ */
+static inline struct tomoyo_task *tomoyo_task(struct task_struct *task)
+{
+	return task->security + tomoyo_blob_sizes.lbs_task;
+}
+
+/**
+ * tomoyo_same_name_union - Check for duplicated "struct tomoyo_name_union" entry.
+ *
+ * @a: Pointer to "struct tomoyo_name_union".
+ * @b: Pointer to "struct tomoyo_name_union".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_same_name_union
+(const struct tomoyo_name_union *a, const struct tomoyo_name_union *b)
+{
+	return a->filename == b->filename && a->group == b->group;
+}
+
+/**
+ * tomoyo_same_number_union - Check for duplicated "struct tomoyo_number_union" entry.
+ *
+ * @a: Pointer to "struct tomoyo_number_union".
+ * @b: Pointer to "struct tomoyo_number_union".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_same_number_union
+(const struct tomoyo_number_union *a, const struct tomoyo_number_union *b)
+{
+	return a->values[0] == b->values[0] && a->values[1] == b->values[1] &&
+		a->group == b->group && a->value_type[0] == b->value_type[0] &&
+		a->value_type[1] == b->value_type[1];
+}
+
+/**
+ * tomoyo_same_ipaddr_union - Check for duplicated "struct tomoyo_ipaddr_union" entry.
+ *
+ * @a: Pointer to "struct tomoyo_ipaddr_union".
+ * @b: Pointer to "struct tomoyo_ipaddr_union".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_same_ipaddr_union
+(const struct tomoyo_ipaddr_union *a, const struct tomoyo_ipaddr_union *b)
+{
+	return !memcmp(a->ip, b->ip, sizeof(a->ip)) && a->group == b->group &&
+		a->is_ipv6 == b->is_ipv6;
+}
+
+/**
+ * tomoyo_current_namespace - Get "struct tomoyo_policy_namespace" for current thread.
+ *
+ * Returns pointer to "struct tomoyo_policy_namespace" for current thread.
+ */
+static inline struct tomoyo_policy_namespace *tomoyo_current_namespace(void)
+{
+	return tomoyo_domain()->ns;
+}
+
+/**
+ * list_for_each_cookie - iterate over a list with cookie.
+ * @pos:        the &struct list_head to use as a loop cursor.
+ * @head:       the head for your list.
+ */
+#define list_for_each_cookie(pos, head)					\
+	if (!pos)							\
+		pos =  srcu_dereference((head)->next, &tomoyo_ss);	\
+	for ( ; pos != (head); pos = srcu_dereference(pos->next, &tomoyo_ss))
+
+#endif /* !defined(_SECURITY_TOMOYO_COMMON_H) */
diff --git a/security/tomoyo/condition.c b/security/tomoyo/condition.c
new file mode 100644
index 000000000..8b107b1ff
--- /dev/null
+++ b/security/tomoyo/condition.c
@@ -0,0 +1,1122 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/condition.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/slab.h>
+
+/* List of "struct tomoyo_condition". */
+LIST_HEAD(tomoyo_condition_list);
+
+/**
+ * tomoyo_argv - Check argv[] in "struct linux_binbrm".
+ *
+ * @index:   Index number of @arg_ptr.
+ * @arg_ptr: Contents of argv[@index].
+ * @argc:    Length of @argv.
+ * @argv:    Pointer to "struct tomoyo_argv".
+ * @checked: Set to true if @argv[@index] was found.
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_argv(const unsigned int index, const char *arg_ptr,
+			const int argc, const struct tomoyo_argv *argv,
+			u8 *checked)
+{
+	int i;
+	struct tomoyo_path_info arg;
+
+	arg.name = arg_ptr;
+	for (i = 0; i < argc; argv++, checked++, i++) {
+		bool result;
+
+		if (index != argv->index)
+			continue;
+		*checked = 1;
+		tomoyo_fill_path_info(&arg);
+		result = tomoyo_path_matches_pattern(&arg, argv->value);
+		if (argv->is_not)
+			result = !result;
+		if (!result)
+			return false;
+	}
+	return true;
+}
+
+/**
+ * tomoyo_envp - Check envp[] in "struct linux_binbrm".
+ *
+ * @env_name:  The name of environment variable.
+ * @env_value: The value of environment variable.
+ * @envc:      Length of @envp.
+ * @envp:      Pointer to "struct tomoyo_envp".
+ * @checked:   Set to true if @envp[@env_name] was found.
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_envp(const char *env_name, const char *env_value,
+			const int envc, const struct tomoyo_envp *envp,
+			u8 *checked)
+{
+	int i;
+	struct tomoyo_path_info name;
+	struct tomoyo_path_info value;
+
+	name.name = env_name;
+	tomoyo_fill_path_info(&name);
+	value.name = env_value;
+	tomoyo_fill_path_info(&value);
+	for (i = 0; i < envc; envp++, checked++, i++) {
+		bool result;
+
+		if (!tomoyo_path_matches_pattern(&name, envp->name))
+			continue;
+		*checked = 1;
+		if (envp->value) {
+			result = tomoyo_path_matches_pattern(&value,
+							     envp->value);
+			if (envp->is_not)
+				result = !result;
+		} else {
+			result = true;
+			if (!envp->is_not)
+				result = !result;
+		}
+		if (!result)
+			return false;
+	}
+	return true;
+}
+
+/**
+ * tomoyo_scan_bprm - Scan "struct linux_binprm".
+ *
+ * @ee:   Pointer to "struct tomoyo_execve".
+ * @argc: Length of @argc.
+ * @argv: Pointer to "struct tomoyo_argv".
+ * @envc: Length of @envp.
+ * @envp: Pointer to "struct tomoyo_envp".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_scan_bprm(struct tomoyo_execve *ee,
+			     const u16 argc, const struct tomoyo_argv *argv,
+			     const u16 envc, const struct tomoyo_envp *envp)
+{
+	struct linux_binprm *bprm = ee->bprm;
+	struct tomoyo_page_dump *dump = &ee->dump;
+	char *arg_ptr = ee->tmp;
+	int arg_len = 0;
+	unsigned long pos = bprm->p;
+	int offset = pos % PAGE_SIZE;
+	int argv_count = bprm->argc;
+	int envp_count = bprm->envc;
+	bool result = true;
+	u8 local_checked[32];
+	u8 *checked;
+
+	if (argc + envc <= sizeof(local_checked)) {
+		checked = local_checked;
+		memset(local_checked, 0, sizeof(local_checked));
+	} else {
+		checked = kzalloc(argc + envc, GFP_NOFS);
+		if (!checked)
+			return false;
+	}
+	while (argv_count || envp_count) {
+		if (!tomoyo_dump_page(bprm, pos, dump)) {
+			result = false;
+			goto out;
+		}
+		pos += PAGE_SIZE - offset;
+		while (offset < PAGE_SIZE) {
+			/* Read. */
+			const char *kaddr = dump->data;
+			const unsigned char c = kaddr[offset++];
+
+			if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) {
+				if (c == '\\') {
+					arg_ptr[arg_len++] = '\\';
+					arg_ptr[arg_len++] = '\\';
+				} else if (c > ' ' && c < 127) {
+					arg_ptr[arg_len++] = c;
+				} else {
+					arg_ptr[arg_len++] = '\\';
+					arg_ptr[arg_len++] = (c >> 6) + '0';
+					arg_ptr[arg_len++] =
+						((c >> 3) & 7) + '0';
+					arg_ptr[arg_len++] = (c & 7) + '0';
+				}
+			} else {
+				arg_ptr[arg_len] = '\0';
+			}
+			if (c)
+				continue;
+			/* Check. */
+			if (argv_count) {
+				if (!tomoyo_argv(bprm->argc - argv_count,
+						 arg_ptr, argc, argv,
+						 checked)) {
+					result = false;
+					break;
+				}
+				argv_count--;
+			} else if (envp_count) {
+				char *cp = strchr(arg_ptr, '=');
+
+				if (cp) {
+					*cp = '\0';
+					if (!tomoyo_envp(arg_ptr, cp + 1,
+							 envc, envp,
+							 checked + argc)) {
+						result = false;
+						break;
+					}
+				}
+				envp_count--;
+			} else {
+				break;
+			}
+			arg_len = 0;
+		}
+		offset = 0;
+		if (!result)
+			break;
+	}
+out:
+	if (result) {
+		int i;
+
+		/* Check not-yet-checked entries. */
+		for (i = 0; i < argc; i++) {
+			if (checked[i])
+				continue;
+			/*
+			 * Return true only if all unchecked indexes in
+			 * bprm->argv[] are not matched.
+			 */
+			if (argv[i].is_not)
+				continue;
+			result = false;
+			break;
+		}
+		for (i = 0; i < envc; envp++, i++) {
+			if (checked[argc + i])
+				continue;
+			/*
+			 * Return true only if all unchecked environ variables
+			 * in bprm->envp[] are either undefined or not matched.
+			 */
+			if ((!envp->value && !envp->is_not) ||
+			    (envp->value && envp->is_not))
+				continue;
+			result = false;
+			break;
+		}
+	}
+	if (checked != local_checked)
+		kfree(checked);
+	return result;
+}
+
+/**
+ * tomoyo_scan_exec_realpath - Check "exec.realpath" parameter of "struct tomoyo_condition".
+ *
+ * @file:  Pointer to "struct file".
+ * @ptr:   Pointer to "struct tomoyo_name_union".
+ * @match: True if "exec.realpath=", false if "exec.realpath!=".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_scan_exec_realpath(struct file *file,
+				      const struct tomoyo_name_union *ptr,
+				      const bool match)
+{
+	bool result;
+	struct tomoyo_path_info exe;
+
+	if (!file)
+		return false;
+	exe.name = tomoyo_realpath_from_path(&file->f_path);
+	if (!exe.name)
+		return false;
+	tomoyo_fill_path_info(&exe);
+	result = tomoyo_compare_name_union(&exe, ptr);
+	kfree(exe.name);
+	return result == match;
+}
+
+/**
+ * tomoyo_get_dqword - tomoyo_get_name() for a quoted string.
+ *
+ * @start: String to save.
+ *
+ * Returns pointer to "struct tomoyo_path_info" on success, NULL otherwise.
+ */
+static const struct tomoyo_path_info *tomoyo_get_dqword(char *start)
+{
+	char *cp = start + strlen(start) - 1;
+
+	if (cp == start || *start++ != '"' || *cp != '"')
+		return NULL;
+	*cp = '\0';
+	if (*start && !tomoyo_correct_word(start))
+		return NULL;
+	return tomoyo_get_name(start);
+}
+
+/**
+ * tomoyo_parse_name_union_quoted - Parse a quoted word.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @ptr:   Pointer to "struct tomoyo_name_union".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_parse_name_union_quoted(struct tomoyo_acl_param *param,
+					   struct tomoyo_name_union *ptr)
+{
+	char *filename = param->data;
+
+	if (*filename == '@')
+		return tomoyo_parse_name_union(param, ptr);
+	ptr->filename = tomoyo_get_dqword(filename);
+	return ptr->filename != NULL;
+}
+
+/**
+ * tomoyo_parse_argv - Parse an argv[] condition part.
+ *
+ * @left:  Lefthand value.
+ * @right: Righthand value.
+ * @argv:  Pointer to "struct tomoyo_argv".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_parse_argv(char *left, char *right,
+			      struct tomoyo_argv *argv)
+{
+	if (tomoyo_parse_ulong(&argv->index, &left) !=
+	    TOMOYO_VALUE_TYPE_DECIMAL || *left++ != ']' || *left)
+		return false;
+	argv->value = tomoyo_get_dqword(right);
+	return argv->value != NULL;
+}
+
+/**
+ * tomoyo_parse_envp - Parse an envp[] condition part.
+ *
+ * @left:  Lefthand value.
+ * @right: Righthand value.
+ * @envp:  Pointer to "struct tomoyo_envp".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_parse_envp(char *left, char *right,
+			      struct tomoyo_envp *envp)
+{
+	const struct tomoyo_path_info *name;
+	const struct tomoyo_path_info *value;
+	char *cp = left + strlen(left) - 1;
+
+	if (*cp-- != ']' || *cp != '"')
+		goto out;
+	*cp = '\0';
+	if (!tomoyo_correct_word(left))
+		goto out;
+	name = tomoyo_get_name(left);
+	if (!name)
+		goto out;
+	if (!strcmp(right, "NULL")) {
+		value = NULL;
+	} else {
+		value = tomoyo_get_dqword(right);
+		if (!value) {
+			tomoyo_put_name(name);
+			goto out;
+		}
+	}
+	envp->name = name;
+	envp->value = value;
+	return true;
+out:
+	return false;
+}
+
+/**
+ * tomoyo_same_condition - Check for duplicated "struct tomoyo_condition" entry.
+ *
+ * @a: Pointer to "struct tomoyo_condition".
+ * @b: Pointer to "struct tomoyo_condition".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_same_condition(const struct tomoyo_condition *a,
+					 const struct tomoyo_condition *b)
+{
+	return a->size == b->size && a->condc == b->condc &&
+		a->numbers_count == b->numbers_count &&
+		a->names_count == b->names_count &&
+		a->argc == b->argc && a->envc == b->envc &&
+		a->grant_log == b->grant_log && a->transit == b->transit &&
+		!memcmp(a + 1, b + 1, a->size - sizeof(*a));
+}
+
+/**
+ * tomoyo_condition_type - Get condition type.
+ *
+ * @word: Keyword string.
+ *
+ * Returns one of values in "enum tomoyo_conditions_index" on success,
+ * TOMOYO_MAX_CONDITION_KEYWORD otherwise.
+ */
+static u8 tomoyo_condition_type(const char *word)
+{
+	u8 i;
+
+	for (i = 0; i < TOMOYO_MAX_CONDITION_KEYWORD; i++) {
+		if (!strcmp(word, tomoyo_condition_keyword[i]))
+			break;
+	}
+	return i;
+}
+
+/* Define this to enable debug mode. */
+/* #define DEBUG_CONDITION */
+
+#ifdef DEBUG_CONDITION
+#define dprintk printk
+#else
+#define dprintk(...) do { } while (0)
+#endif
+
+/**
+ * tomoyo_commit_condition - Commit "struct tomoyo_condition".
+ *
+ * @entry: Pointer to "struct tomoyo_condition".
+ *
+ * Returns pointer to "struct tomoyo_condition" on success, NULL otherwise.
+ *
+ * This function merges duplicated entries. This function returns NULL if
+ * @entry is not duplicated but memory quota for policy has exceeded.
+ */
+static struct tomoyo_condition *tomoyo_commit_condition
+(struct tomoyo_condition *entry)
+{
+	struct tomoyo_condition *ptr;
+	bool found = false;
+
+	if (mutex_lock_interruptible(&tomoyo_policy_lock)) {
+		dprintk(KERN_WARNING "%u: %s failed\n", __LINE__, __func__);
+		ptr = NULL;
+		found = true;
+		goto out;
+	}
+	list_for_each_entry(ptr, &tomoyo_condition_list, head.list) {
+		if (!tomoyo_same_condition(ptr, entry) ||
+		    atomic_read(&ptr->head.users) == TOMOYO_GC_IN_PROGRESS)
+			continue;
+		/* Same entry found. Share this entry. */
+		atomic_inc(&ptr->head.users);
+		found = true;
+		break;
+	}
+	if (!found) {
+		if (tomoyo_memory_ok(entry)) {
+			atomic_set(&entry->head.users, 1);
+			list_add(&entry->head.list, &tomoyo_condition_list);
+		} else {
+			found = true;
+			ptr = NULL;
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+out:
+	if (found) {
+		tomoyo_del_condition(&entry->head.list);
+		kfree(entry);
+		entry = ptr;
+	}
+	return entry;
+}
+
+/**
+ * tomoyo_get_transit_preference - Parse domain transition preference for execve().
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @e:     Pointer to "struct tomoyo_condition".
+ *
+ * Returns the condition string part.
+ */
+static char *tomoyo_get_transit_preference(struct tomoyo_acl_param *param,
+					   struct tomoyo_condition *e)
+{
+	char * const pos = param->data;
+	bool flag;
+
+	if (*pos == '<') {
+		e->transit = tomoyo_get_domainname(param);
+		goto done;
+	}
+	{
+		char *cp = strchr(pos, ' ');
+
+		if (cp)
+			*cp = '\0';
+		flag = tomoyo_correct_path(pos) || !strcmp(pos, "keep") ||
+			!strcmp(pos, "initialize") || !strcmp(pos, "reset") ||
+			!strcmp(pos, "child") || !strcmp(pos, "parent");
+		if (cp)
+			*cp = ' ';
+	}
+	if (!flag)
+		return pos;
+	e->transit = tomoyo_get_name(tomoyo_read_token(param));
+done:
+	if (e->transit)
+		return param->data;
+	/*
+	 * Return a bad read-only condition string that will let
+	 * tomoyo_get_condition() return NULL.
+	 */
+	return "/";
+}
+
+/**
+ * tomoyo_get_condition - Parse condition part.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns pointer to "struct tomoyo_condition" on success, NULL otherwise.
+ */
+struct tomoyo_condition *tomoyo_get_condition(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_condition *entry = NULL;
+	struct tomoyo_condition_element *condp = NULL;
+	struct tomoyo_number_union *numbers_p = NULL;
+	struct tomoyo_name_union *names_p = NULL;
+	struct tomoyo_argv *argv = NULL;
+	struct tomoyo_envp *envp = NULL;
+	struct tomoyo_condition e = { };
+	char * const start_of_string =
+		tomoyo_get_transit_preference(param, &e);
+	char * const end_of_string = start_of_string + strlen(start_of_string);
+	char *pos;
+
+rerun:
+	pos = start_of_string;
+	while (1) {
+		u8 left = -1;
+		u8 right = -1;
+		char *left_word = pos;
+		char *cp;
+		char *right_word;
+		bool is_not;
+
+		if (!*left_word)
+			break;
+		/*
+		 * Since left-hand condition does not allow use of "path_group"
+		 * or "number_group" and environment variable's names do not
+		 * accept '=', it is guaranteed that the original line consists
+		 * of one or more repetition of $left$operator$right blocks
+		 * where "$left is free from '=' and ' '" and "$operator is
+		 * either '=' or '!='" and "$right is free from ' '".
+		 * Therefore, we can reconstruct the original line at the end
+		 * of dry run even if we overwrite $operator with '\0'.
+		 */
+		cp = strchr(pos, ' ');
+		if (cp) {
+			*cp = '\0'; /* Will restore later. */
+			pos = cp + 1;
+		} else {
+			pos = "";
+		}
+		right_word = strchr(left_word, '=');
+		if (!right_word || right_word == left_word)
+			goto out;
+		is_not = *(right_word - 1) == '!';
+		if (is_not)
+			*(right_word++ - 1) = '\0'; /* Will restore later. */
+		else if (*(right_word + 1) != '=')
+			*right_word++ = '\0'; /* Will restore later. */
+		else
+			goto out;
+		dprintk(KERN_WARNING "%u: <%s>%s=<%s>\n", __LINE__, left_word,
+			is_not ? "!" : "", right_word);
+		if (!strcmp(left_word, "grant_log")) {
+			if (entry) {
+				if (is_not ||
+				    entry->grant_log != TOMOYO_GRANTLOG_AUTO)
+					goto out;
+				else if (!strcmp(right_word, "yes"))
+					entry->grant_log = TOMOYO_GRANTLOG_YES;
+				else if (!strcmp(right_word, "no"))
+					entry->grant_log = TOMOYO_GRANTLOG_NO;
+				else
+					goto out;
+			}
+			continue;
+		}
+		if (!strncmp(left_word, "exec.argv[", 10)) {
+			if (!argv) {
+				e.argc++;
+				e.condc++;
+			} else {
+				e.argc--;
+				e.condc--;
+				left = TOMOYO_ARGV_ENTRY;
+				argv->is_not = is_not;
+				if (!tomoyo_parse_argv(left_word + 10,
+						       right_word, argv++))
+					goto out;
+			}
+			goto store_value;
+		}
+		if (!strncmp(left_word, "exec.envp[\"", 11)) {
+			if (!envp) {
+				e.envc++;
+				e.condc++;
+			} else {
+				e.envc--;
+				e.condc--;
+				left = TOMOYO_ENVP_ENTRY;
+				envp->is_not = is_not;
+				if (!tomoyo_parse_envp(left_word + 11,
+						       right_word, envp++))
+					goto out;
+			}
+			goto store_value;
+		}
+		left = tomoyo_condition_type(left_word);
+		dprintk(KERN_WARNING "%u: <%s> left=%u\n", __LINE__, left_word,
+			left);
+		if (left == TOMOYO_MAX_CONDITION_KEYWORD) {
+			if (!numbers_p) {
+				e.numbers_count++;
+			} else {
+				e.numbers_count--;
+				left = TOMOYO_NUMBER_UNION;
+				param->data = left_word;
+				if (*left_word == '@' ||
+				    !tomoyo_parse_number_union(param,
+							       numbers_p++))
+					goto out;
+			}
+		}
+		if (!condp)
+			e.condc++;
+		else
+			e.condc--;
+		if (left == TOMOYO_EXEC_REALPATH ||
+		    left == TOMOYO_SYMLINK_TARGET) {
+			if (!names_p) {
+				e.names_count++;
+			} else {
+				e.names_count--;
+				right = TOMOYO_NAME_UNION;
+				param->data = right_word;
+				if (!tomoyo_parse_name_union_quoted(param,
+								    names_p++))
+					goto out;
+			}
+			goto store_value;
+		}
+		right = tomoyo_condition_type(right_word);
+		if (right == TOMOYO_MAX_CONDITION_KEYWORD) {
+			if (!numbers_p) {
+				e.numbers_count++;
+			} else {
+				e.numbers_count--;
+				right = TOMOYO_NUMBER_UNION;
+				param->data = right_word;
+				if (!tomoyo_parse_number_union(param,
+							       numbers_p++))
+					goto out;
+			}
+		}
+store_value:
+		if (!condp) {
+			dprintk(KERN_WARNING "%u: dry_run left=%u right=%u match=%u\n",
+				__LINE__, left, right, !is_not);
+			continue;
+		}
+		condp->left = left;
+		condp->right = right;
+		condp->equals = !is_not;
+		dprintk(KERN_WARNING "%u: left=%u right=%u match=%u\n",
+			__LINE__, condp->left, condp->right,
+			condp->equals);
+		condp++;
+	}
+	dprintk(KERN_INFO "%u: cond=%u numbers=%u names=%u ac=%u ec=%u\n",
+		__LINE__, e.condc, e.numbers_count, e.names_count, e.argc,
+		e.envc);
+	if (entry) {
+		BUG_ON(e.names_count | e.numbers_count | e.argc | e.envc |
+		       e.condc);
+		return tomoyo_commit_condition(entry);
+	}
+	e.size = sizeof(*entry)
+		+ e.condc * sizeof(struct tomoyo_condition_element)
+		+ e.numbers_count * sizeof(struct tomoyo_number_union)
+		+ e.names_count * sizeof(struct tomoyo_name_union)
+		+ e.argc * sizeof(struct tomoyo_argv)
+		+ e.envc * sizeof(struct tomoyo_envp);
+	entry = kzalloc(e.size, GFP_NOFS);
+	if (!entry)
+		goto out2;
+	*entry = e;
+	e.transit = NULL;
+	condp = (struct tomoyo_condition_element *) (entry + 1);
+	numbers_p = (struct tomoyo_number_union *) (condp + e.condc);
+	names_p = (struct tomoyo_name_union *) (numbers_p + e.numbers_count);
+	argv = (struct tomoyo_argv *) (names_p + e.names_count);
+	envp = (struct tomoyo_envp *) (argv + e.argc);
+	{
+		bool flag = false;
+
+		for (pos = start_of_string; pos < end_of_string; pos++) {
+			if (*pos)
+				continue;
+			if (flag) /* Restore " ". */
+				*pos = ' ';
+			else if (*(pos + 1) == '=') /* Restore "!=". */
+				*pos = '!';
+			else /* Restore "=". */
+				*pos = '=';
+			flag = !flag;
+		}
+	}
+	goto rerun;
+out:
+	dprintk(KERN_WARNING "%u: %s failed\n", __LINE__, __func__);
+	if (entry) {
+		tomoyo_del_condition(&entry->head.list);
+		kfree(entry);
+	}
+out2:
+	tomoyo_put_name(e.transit);
+	return NULL;
+}
+
+/**
+ * tomoyo_get_attributes - Revalidate "struct inode".
+ *
+ * @obj: Pointer to "struct tomoyo_obj_info".
+ *
+ * Returns nothing.
+ */
+void tomoyo_get_attributes(struct tomoyo_obj_info *obj)
+{
+	u8 i;
+	struct dentry *dentry = NULL;
+
+	for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) {
+		struct inode *inode;
+
+		switch (i) {
+		case TOMOYO_PATH1:
+			dentry = obj->path1.dentry;
+			if (!dentry)
+				continue;
+			break;
+		case TOMOYO_PATH2:
+			dentry = obj->path2.dentry;
+			if (!dentry)
+				continue;
+			break;
+		default:
+			if (!dentry)
+				continue;
+			dentry = dget_parent(dentry);
+			break;
+		}
+		inode = d_backing_inode(dentry);
+		if (inode) {
+			struct tomoyo_mini_stat *stat = &obj->stat[i];
+
+			stat->uid  = inode->i_uid;
+			stat->gid  = inode->i_gid;
+			stat->ino  = inode->i_ino;
+			stat->mode = inode->i_mode;
+			stat->dev  = inode->i_sb->s_dev;
+			stat->rdev = inode->i_rdev;
+			obj->stat_valid[i] = true;
+		}
+		if (i & 1) /* TOMOYO_PATH1_PARENT or TOMOYO_PATH2_PARENT */
+			dput(dentry);
+	}
+}
+
+/**
+ * tomoyo_condition - Check condition part.
+ *
+ * @r:    Pointer to "struct tomoyo_request_info".
+ * @cond: Pointer to "struct tomoyo_condition". Maybe NULL.
+ *
+ * Returns true on success, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+bool tomoyo_condition(struct tomoyo_request_info *r,
+		      const struct tomoyo_condition *cond)
+{
+	u32 i;
+	u64 min_v[2] = { 0, 0 };
+	u64 max_v[2] = { 0, 0 };
+	const struct tomoyo_condition_element *condp;
+	const struct tomoyo_number_union *numbers_p;
+	const struct tomoyo_name_union *names_p;
+	const struct tomoyo_argv *argv;
+	const struct tomoyo_envp *envp;
+	struct tomoyo_obj_info *obj;
+	u16 condc;
+	u16 argc;
+	u16 envc;
+	struct linux_binprm *bprm = NULL;
+
+	if (!cond)
+		return true;
+	condc = cond->condc;
+	argc = cond->argc;
+	envc = cond->envc;
+	obj = r->obj;
+	if (r->ee)
+		bprm = r->ee->bprm;
+	if (!bprm && (argc || envc))
+		return false;
+	condp = (struct tomoyo_condition_element *) (cond + 1);
+	numbers_p = (const struct tomoyo_number_union *) (condp + condc);
+	names_p = (const struct tomoyo_name_union *)
+		(numbers_p + cond->numbers_count);
+	argv = (const struct tomoyo_argv *) (names_p + cond->names_count);
+	envp = (const struct tomoyo_envp *) (argv + argc);
+	for (i = 0; i < condc; i++) {
+		const bool match = condp->equals;
+		const u8 left = condp->left;
+		const u8 right = condp->right;
+		bool is_bitop[2] = { false, false };
+		u8 j;
+
+		condp++;
+		/* Check argv[] and envp[] later. */
+		if (left == TOMOYO_ARGV_ENTRY || left == TOMOYO_ENVP_ENTRY)
+			continue;
+		/* Check string expressions. */
+		if (right == TOMOYO_NAME_UNION) {
+			const struct tomoyo_name_union *ptr = names_p++;
+			struct tomoyo_path_info *symlink;
+			struct tomoyo_execve *ee;
+			struct file *file;
+
+			switch (left) {
+			case TOMOYO_SYMLINK_TARGET:
+				symlink = obj ? obj->symlink_target : NULL;
+				if (!symlink ||
+				    !tomoyo_compare_name_union(symlink, ptr)
+				    == match)
+					goto out;
+				break;
+			case TOMOYO_EXEC_REALPATH:
+				ee = r->ee;
+				file = ee ? ee->bprm->file : NULL;
+				if (!tomoyo_scan_exec_realpath(file, ptr,
+							       match))
+					goto out;
+				break;
+			}
+			continue;
+		}
+		/* Check numeric or bit-op expressions. */
+		for (j = 0; j < 2; j++) {
+			const u8 index = j ? right : left;
+			u64 value = 0;
+
+			switch (index) {
+			case TOMOYO_TASK_UID:
+				value = from_kuid(&init_user_ns, current_uid());
+				break;
+			case TOMOYO_TASK_EUID:
+				value = from_kuid(&init_user_ns, current_euid());
+				break;
+			case TOMOYO_TASK_SUID:
+				value = from_kuid(&init_user_ns, current_suid());
+				break;
+			case TOMOYO_TASK_FSUID:
+				value = from_kuid(&init_user_ns, current_fsuid());
+				break;
+			case TOMOYO_TASK_GID:
+				value = from_kgid(&init_user_ns, current_gid());
+				break;
+			case TOMOYO_TASK_EGID:
+				value = from_kgid(&init_user_ns, current_egid());
+				break;
+			case TOMOYO_TASK_SGID:
+				value = from_kgid(&init_user_ns, current_sgid());
+				break;
+			case TOMOYO_TASK_FSGID:
+				value = from_kgid(&init_user_ns, current_fsgid());
+				break;
+			case TOMOYO_TASK_PID:
+				value = tomoyo_sys_getpid();
+				break;
+			case TOMOYO_TASK_PPID:
+				value = tomoyo_sys_getppid();
+				break;
+			case TOMOYO_TYPE_IS_SOCKET:
+				value = S_IFSOCK;
+				break;
+			case TOMOYO_TYPE_IS_SYMLINK:
+				value = S_IFLNK;
+				break;
+			case TOMOYO_TYPE_IS_FILE:
+				value = S_IFREG;
+				break;
+			case TOMOYO_TYPE_IS_BLOCK_DEV:
+				value = S_IFBLK;
+				break;
+			case TOMOYO_TYPE_IS_DIRECTORY:
+				value = S_IFDIR;
+				break;
+			case TOMOYO_TYPE_IS_CHAR_DEV:
+				value = S_IFCHR;
+				break;
+			case TOMOYO_TYPE_IS_FIFO:
+				value = S_IFIFO;
+				break;
+			case TOMOYO_MODE_SETUID:
+				value = S_ISUID;
+				break;
+			case TOMOYO_MODE_SETGID:
+				value = S_ISGID;
+				break;
+			case TOMOYO_MODE_STICKY:
+				value = S_ISVTX;
+				break;
+			case TOMOYO_MODE_OWNER_READ:
+				value = 0400;
+				break;
+			case TOMOYO_MODE_OWNER_WRITE:
+				value = 0200;
+				break;
+			case TOMOYO_MODE_OWNER_EXECUTE:
+				value = 0100;
+				break;
+			case TOMOYO_MODE_GROUP_READ:
+				value = 0040;
+				break;
+			case TOMOYO_MODE_GROUP_WRITE:
+				value = 0020;
+				break;
+			case TOMOYO_MODE_GROUP_EXECUTE:
+				value = 0010;
+				break;
+			case TOMOYO_MODE_OTHERS_READ:
+				value = 0004;
+				break;
+			case TOMOYO_MODE_OTHERS_WRITE:
+				value = 0002;
+				break;
+			case TOMOYO_MODE_OTHERS_EXECUTE:
+				value = 0001;
+				break;
+			case TOMOYO_EXEC_ARGC:
+				if (!bprm)
+					goto out;
+				value = bprm->argc;
+				break;
+			case TOMOYO_EXEC_ENVC:
+				if (!bprm)
+					goto out;
+				value = bprm->envc;
+				break;
+			case TOMOYO_NUMBER_UNION:
+				/* Fetch values later. */
+				break;
+			default:
+				if (!obj)
+					goto out;
+				if (!obj->validate_done) {
+					tomoyo_get_attributes(obj);
+					obj->validate_done = true;
+				}
+				{
+					u8 stat_index;
+					struct tomoyo_mini_stat *stat;
+
+					switch (index) {
+					case TOMOYO_PATH1_UID:
+					case TOMOYO_PATH1_GID:
+					case TOMOYO_PATH1_INO:
+					case TOMOYO_PATH1_MAJOR:
+					case TOMOYO_PATH1_MINOR:
+					case TOMOYO_PATH1_TYPE:
+					case TOMOYO_PATH1_DEV_MAJOR:
+					case TOMOYO_PATH1_DEV_MINOR:
+					case TOMOYO_PATH1_PERM:
+						stat_index = TOMOYO_PATH1;
+						break;
+					case TOMOYO_PATH2_UID:
+					case TOMOYO_PATH2_GID:
+					case TOMOYO_PATH2_INO:
+					case TOMOYO_PATH2_MAJOR:
+					case TOMOYO_PATH2_MINOR:
+					case TOMOYO_PATH2_TYPE:
+					case TOMOYO_PATH2_DEV_MAJOR:
+					case TOMOYO_PATH2_DEV_MINOR:
+					case TOMOYO_PATH2_PERM:
+						stat_index = TOMOYO_PATH2;
+						break;
+					case TOMOYO_PATH1_PARENT_UID:
+					case TOMOYO_PATH1_PARENT_GID:
+					case TOMOYO_PATH1_PARENT_INO:
+					case TOMOYO_PATH1_PARENT_PERM:
+						stat_index =
+							TOMOYO_PATH1_PARENT;
+						break;
+					case TOMOYO_PATH2_PARENT_UID:
+					case TOMOYO_PATH2_PARENT_GID:
+					case TOMOYO_PATH2_PARENT_INO:
+					case TOMOYO_PATH2_PARENT_PERM:
+						stat_index =
+							TOMOYO_PATH2_PARENT;
+						break;
+					default:
+						goto out;
+					}
+					if (!obj->stat_valid[stat_index])
+						goto out;
+					stat = &obj->stat[stat_index];
+					switch (index) {
+					case TOMOYO_PATH1_UID:
+					case TOMOYO_PATH2_UID:
+					case TOMOYO_PATH1_PARENT_UID:
+					case TOMOYO_PATH2_PARENT_UID:
+						value = from_kuid(&init_user_ns, stat->uid);
+						break;
+					case TOMOYO_PATH1_GID:
+					case TOMOYO_PATH2_GID:
+					case TOMOYO_PATH1_PARENT_GID:
+					case TOMOYO_PATH2_PARENT_GID:
+						value = from_kgid(&init_user_ns, stat->gid);
+						break;
+					case TOMOYO_PATH1_INO:
+					case TOMOYO_PATH2_INO:
+					case TOMOYO_PATH1_PARENT_INO:
+					case TOMOYO_PATH2_PARENT_INO:
+						value = stat->ino;
+						break;
+					case TOMOYO_PATH1_MAJOR:
+					case TOMOYO_PATH2_MAJOR:
+						value = MAJOR(stat->dev);
+						break;
+					case TOMOYO_PATH1_MINOR:
+					case TOMOYO_PATH2_MINOR:
+						value = MINOR(stat->dev);
+						break;
+					case TOMOYO_PATH1_TYPE:
+					case TOMOYO_PATH2_TYPE:
+						value = stat->mode & S_IFMT;
+						break;
+					case TOMOYO_PATH1_DEV_MAJOR:
+					case TOMOYO_PATH2_DEV_MAJOR:
+						value = MAJOR(stat->rdev);
+						break;
+					case TOMOYO_PATH1_DEV_MINOR:
+					case TOMOYO_PATH2_DEV_MINOR:
+						value = MINOR(stat->rdev);
+						break;
+					case TOMOYO_PATH1_PERM:
+					case TOMOYO_PATH2_PERM:
+					case TOMOYO_PATH1_PARENT_PERM:
+					case TOMOYO_PATH2_PARENT_PERM:
+						value = stat->mode & S_IALLUGO;
+						break;
+					}
+				}
+				break;
+			}
+			max_v[j] = value;
+			min_v[j] = value;
+			switch (index) {
+			case TOMOYO_MODE_SETUID:
+			case TOMOYO_MODE_SETGID:
+			case TOMOYO_MODE_STICKY:
+			case TOMOYO_MODE_OWNER_READ:
+			case TOMOYO_MODE_OWNER_WRITE:
+			case TOMOYO_MODE_OWNER_EXECUTE:
+			case TOMOYO_MODE_GROUP_READ:
+			case TOMOYO_MODE_GROUP_WRITE:
+			case TOMOYO_MODE_GROUP_EXECUTE:
+			case TOMOYO_MODE_OTHERS_READ:
+			case TOMOYO_MODE_OTHERS_WRITE:
+			case TOMOYO_MODE_OTHERS_EXECUTE:
+				is_bitop[j] = true;
+			}
+		}
+		if (left == TOMOYO_NUMBER_UNION) {
+			/* Fetch values now. */
+			const struct tomoyo_number_union *ptr = numbers_p++;
+
+			min_v[0] = ptr->values[0];
+			max_v[0] = ptr->values[1];
+		}
+		if (right == TOMOYO_NUMBER_UNION) {
+			/* Fetch values now. */
+			const struct tomoyo_number_union *ptr = numbers_p++;
+
+			if (ptr->group) {
+				if (tomoyo_number_matches_group(min_v[0],
+								max_v[0],
+								ptr->group)
+				    == match)
+					continue;
+			} else {
+				if ((min_v[0] <= ptr->values[1] &&
+				     max_v[0] >= ptr->values[0]) == match)
+					continue;
+			}
+			goto out;
+		}
+		/*
+		 * Bit operation is valid only when counterpart value
+		 * represents permission.
+		 */
+		if (is_bitop[0] && is_bitop[1]) {
+			goto out;
+		} else if (is_bitop[0]) {
+			switch (right) {
+			case TOMOYO_PATH1_PERM:
+			case TOMOYO_PATH1_PARENT_PERM:
+			case TOMOYO_PATH2_PERM:
+			case TOMOYO_PATH2_PARENT_PERM:
+				if (!(max_v[0] & max_v[1]) == !match)
+					continue;
+			}
+			goto out;
+		} else if (is_bitop[1]) {
+			switch (left) {
+			case TOMOYO_PATH1_PERM:
+			case TOMOYO_PATH1_PARENT_PERM:
+			case TOMOYO_PATH2_PERM:
+			case TOMOYO_PATH2_PARENT_PERM:
+				if (!(max_v[0] & max_v[1]) == !match)
+					continue;
+			}
+			goto out;
+		}
+		/* Normal value range comparison. */
+		if ((min_v[0] <= max_v[1] && max_v[0] >= min_v[1]) == match)
+			continue;
+out:
+		return false;
+	}
+	/* Check argv[] and envp[] now. */
+	if (r->ee && (argc || envc))
+		return tomoyo_scan_bprm(r->ee, argc, argv, envc, envp);
+	return true;
+}
diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c
new file mode 100644
index 000000000..eeaad421f
--- /dev/null
+++ b/security/tomoyo/domain.c
@@ -0,0 +1,950 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/domain.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+
+#include <linux/binfmts.h>
+#include <linux/slab.h>
+#include <linux/rculist.h>
+
+/* Variables definitions.*/
+
+/* The initial domain. */
+struct tomoyo_domain_info tomoyo_kernel_domain;
+
+/**
+ * tomoyo_update_policy - Update an entry for exception policy.
+ *
+ * @new_entry:       Pointer to "struct tomoyo_acl_info".
+ * @size:            Size of @new_entry in bytes.
+ * @param:           Pointer to "struct tomoyo_acl_param".
+ * @check_duplicate: Callback function to find duplicated entry.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size,
+			 struct tomoyo_acl_param *param,
+			 bool (*check_duplicate)(const struct tomoyo_acl_head
+						 *,
+						 const struct tomoyo_acl_head
+						 *))
+{
+	int error = param->is_delete ? -ENOENT : -ENOMEM;
+	struct tomoyo_acl_head *entry;
+	struct list_head *list = param->list;
+
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		return -ENOMEM;
+	list_for_each_entry_rcu(entry, list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS)
+			continue;
+		if (!check_duplicate(entry, new_entry))
+			continue;
+		entry->is_deleted = param->is_delete;
+		error = 0;
+		break;
+	}
+	if (error && !param->is_delete) {
+		entry = tomoyo_commit_ok(new_entry, size);
+		if (entry) {
+			list_add_tail_rcu(&entry->list, list);
+			error = 0;
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+	return error;
+}
+
+/**
+ * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a,
+					const struct tomoyo_acl_info *b)
+{
+	return a->type == b->type && a->cond == b->cond;
+}
+
+/**
+ * tomoyo_update_domain - Update an entry for domain policy.
+ *
+ * @new_entry:       Pointer to "struct tomoyo_acl_info".
+ * @size:            Size of @new_entry in bytes.
+ * @param:           Pointer to "struct tomoyo_acl_param".
+ * @check_duplicate: Callback function to find duplicated entry.
+ * @merge_duplicate: Callback function to merge duplicated entry.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size,
+			 struct tomoyo_acl_param *param,
+			 bool (*check_duplicate)(const struct tomoyo_acl_info
+						 *,
+						 const struct tomoyo_acl_info
+						 *),
+			 bool (*merge_duplicate)(struct tomoyo_acl_info *,
+						 struct tomoyo_acl_info *,
+						 const bool))
+{
+	const bool is_delete = param->is_delete;
+	int error = is_delete ? -ENOENT : -ENOMEM;
+	struct tomoyo_acl_info *entry;
+	struct list_head * const list = param->list;
+
+	if (param->data[0]) {
+		new_entry->cond = tomoyo_get_condition(param);
+		if (!new_entry->cond)
+			return -EINVAL;
+		/*
+		 * Domain transition preference is allowed for only
+		 * "file execute" entries.
+		 */
+		if (new_entry->cond->transit &&
+		    !(new_entry->type == TOMOYO_TYPE_PATH_ACL &&
+		      container_of(new_entry, struct tomoyo_path_acl, head)
+		      ->perm == 1 << TOMOYO_TYPE_EXECUTE))
+			goto out;
+	}
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		goto out;
+	list_for_each_entry_rcu(entry, list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS)
+			continue;
+		if (!tomoyo_same_acl_head(entry, new_entry) ||
+		    !check_duplicate(entry, new_entry))
+			continue;
+		if (merge_duplicate)
+			entry->is_deleted = merge_duplicate(entry, new_entry,
+							    is_delete);
+		else
+			entry->is_deleted = is_delete;
+		error = 0;
+		break;
+	}
+	if (error && !is_delete) {
+		entry = tomoyo_commit_ok(new_entry, size);
+		if (entry) {
+			list_add_tail_rcu(&entry->list, list);
+			error = 0;
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+out:
+	tomoyo_put_condition(new_entry->cond);
+	return error;
+}
+
+/**
+ * tomoyo_check_acl - Do permission check.
+ *
+ * @r:           Pointer to "struct tomoyo_request_info".
+ * @check_entry: Callback function to check type specific parameters.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+void tomoyo_check_acl(struct tomoyo_request_info *r,
+		      bool (*check_entry)(struct tomoyo_request_info *,
+					  const struct tomoyo_acl_info *))
+{
+	const struct tomoyo_domain_info *domain = r->domain;
+	struct tomoyo_acl_info *ptr;
+	const struct list_head *list = &domain->acl_info_list;
+	u16 i = 0;
+
+retry:
+	list_for_each_entry_rcu(ptr, list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (ptr->is_deleted || ptr->type != r->param_type)
+			continue;
+		if (!check_entry(r, ptr))
+			continue;
+		if (!tomoyo_condition(r, ptr->cond))
+			continue;
+		r->matched_acl = ptr;
+		r->granted = true;
+		return;
+	}
+	for (; i < TOMOYO_MAX_ACL_GROUPS; i++) {
+		if (!test_bit(i, domain->group))
+			continue;
+		list = &domain->ns->acl_group[i++];
+		goto retry;
+	}
+	r->granted = false;
+}
+
+/* The list for "struct tomoyo_domain_info". */
+LIST_HEAD(tomoyo_domain_list);
+
+/**
+ * tomoyo_last_word - Get last component of a domainname.
+ *
+ * @name: Domainname to check.
+ *
+ * Returns the last word of @domainname.
+ */
+static const char *tomoyo_last_word(const char *name)
+{
+	const char *cp = strrchr(name, ' ');
+
+	if (cp)
+		return cp + 1;
+	return name;
+}
+
+/**
+ * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a,
+					   const struct tomoyo_acl_head *b)
+{
+	const struct tomoyo_transition_control *p1 = container_of(a,
+								  typeof(*p1),
+								  head);
+	const struct tomoyo_transition_control *p2 = container_of(b,
+								  typeof(*p2),
+								  head);
+
+	return p1->type == p2->type && p1->is_last_name == p2->is_last_name
+		&& p1->domainname == p2->domainname
+		&& p1->program == p2->program;
+}
+
+/**
+ * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @type:  Type of this entry.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_write_transition_control(struct tomoyo_acl_param *param,
+				    const u8 type)
+{
+	struct tomoyo_transition_control e = { .type = type };
+	int error = param->is_delete ? -ENOENT : -ENOMEM;
+	char *program = param->data;
+	char *domainname = strstr(program, " from ");
+
+	if (domainname) {
+		*domainname = '\0';
+		domainname += 6;
+	} else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP ||
+		   type == TOMOYO_TRANSITION_CONTROL_KEEP) {
+		domainname = program;
+		program = NULL;
+	}
+	if (program && strcmp(program, "any")) {
+		if (!tomoyo_correct_path(program))
+			return -EINVAL;
+		e.program = tomoyo_get_name(program);
+		if (!e.program)
+			goto out;
+	}
+	if (domainname && strcmp(domainname, "any")) {
+		if (!tomoyo_correct_domain(domainname)) {
+			if (!tomoyo_correct_path(domainname))
+				goto out;
+			e.is_last_name = true;
+		}
+		e.domainname = tomoyo_get_name(domainname);
+		if (!e.domainname)
+			goto out;
+	}
+	param->list = &param->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL];
+	error = tomoyo_update_policy(&e.head, sizeof(e), param,
+				     tomoyo_same_transition_control);
+out:
+	tomoyo_put_name(e.domainname);
+	tomoyo_put_name(e.program);
+	return error;
+}
+
+/**
+ * tomoyo_scan_transition - Try to find specific domain transition type.
+ *
+ * @list:       Pointer to "struct list_head".
+ * @domainname: The name of current domain.
+ * @program:    The name of requested program.
+ * @last_name:  The last component of @domainname.
+ * @type:       One of values in "enum tomoyo_transition_type".
+ *
+ * Returns true if found one, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static inline bool tomoyo_scan_transition
+(const struct list_head *list, const struct tomoyo_path_info *domainname,
+ const struct tomoyo_path_info *program, const char *last_name,
+ const enum tomoyo_transition_type type)
+{
+	const struct tomoyo_transition_control *ptr;
+
+	list_for_each_entry_rcu(ptr, list, head.list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (ptr->head.is_deleted || ptr->type != type)
+			continue;
+		if (ptr->domainname) {
+			if (!ptr->is_last_name) {
+				if (ptr->domainname != domainname)
+					continue;
+			} else {
+				/*
+				 * Use direct strcmp() since this is
+				 * unlikely used.
+				 */
+				if (strcmp(ptr->domainname->name, last_name))
+					continue;
+			}
+		}
+		if (ptr->program && tomoyo_pathcmp(ptr->program, program))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * tomoyo_transition_type - Get domain transition type.
+ *
+ * @ns:         Pointer to "struct tomoyo_policy_namespace".
+ * @domainname: The name of current domain.
+ * @program:    The name of requested program.
+ *
+ * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes
+ * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if
+ * executing @program reinitializes domain transition within that namespace,
+ * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname ,
+ * others otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static enum tomoyo_transition_type tomoyo_transition_type
+(const struct tomoyo_policy_namespace *ns,
+ const struct tomoyo_path_info *domainname,
+ const struct tomoyo_path_info *program)
+{
+	const char *last_name = tomoyo_last_word(domainname->name);
+	enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET;
+
+	while (type < TOMOYO_MAX_TRANSITION_TYPE) {
+		const struct list_head * const list =
+			&ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL];
+
+		if (!tomoyo_scan_transition(list, domainname, program,
+					    last_name, type)) {
+			type++;
+			continue;
+		}
+		if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET &&
+		    type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE)
+			break;
+		/*
+		 * Do not check for reset_domain if no_reset_domain matched.
+		 * Do not check for initialize_domain if no_initialize_domain
+		 * matched.
+		 */
+		type++;
+		type++;
+	}
+	return type;
+}
+
+/**
+ * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a,
+				   const struct tomoyo_acl_head *b)
+{
+	const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1),
+							  head);
+	const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2),
+							  head);
+
+	return p1->original_name == p2->original_name &&
+		p1->aggregated_name == p2->aggregated_name;
+}
+
+/**
+ * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_write_aggregator(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_aggregator e = { };
+	int error = param->is_delete ? -ENOENT : -ENOMEM;
+	const char *original_name = tomoyo_read_token(param);
+	const char *aggregated_name = tomoyo_read_token(param);
+
+	if (!tomoyo_correct_word(original_name) ||
+	    !tomoyo_correct_path(aggregated_name))
+		return -EINVAL;
+	e.original_name = tomoyo_get_name(original_name);
+	e.aggregated_name = tomoyo_get_name(aggregated_name);
+	if (!e.original_name || !e.aggregated_name ||
+	    e.aggregated_name->is_patterned) /* No patterns allowed. */
+		goto out;
+	param->list = &param->ns->policy_list[TOMOYO_ID_AGGREGATOR];
+	error = tomoyo_update_policy(&e.head, sizeof(e), param,
+				     tomoyo_same_aggregator);
+out:
+	tomoyo_put_name(e.original_name);
+	tomoyo_put_name(e.aggregated_name);
+	return error;
+}
+
+/**
+ * tomoyo_find_namespace - Find specified namespace.
+ *
+ * @name: Name of namespace to find.
+ * @len:  Length of @name.
+ *
+ * Returns pointer to "struct tomoyo_policy_namespace" if found,
+ * NULL otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static struct tomoyo_policy_namespace *tomoyo_find_namespace
+(const char *name, const unsigned int len)
+{
+	struct tomoyo_policy_namespace *ns;
+
+	list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) {
+		if (strncmp(name, ns->name, len) ||
+		    (name[len] && name[len] != ' '))
+			continue;
+		return ns;
+	}
+	return NULL;
+}
+
+/**
+ * tomoyo_assign_namespace - Create a new namespace.
+ *
+ * @domainname: Name of namespace to create.
+ *
+ * Returns pointer to "struct tomoyo_policy_namespace" on success,
+ * NULL otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname)
+{
+	struct tomoyo_policy_namespace *ptr;
+	struct tomoyo_policy_namespace *entry;
+	const char *cp = domainname;
+	unsigned int len = 0;
+
+	while (*cp && *cp++ != ' ')
+		len++;
+	ptr = tomoyo_find_namespace(domainname, len);
+	if (ptr)
+		return ptr;
+	if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname))
+		return NULL;
+	entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN);
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		goto out;
+	ptr = tomoyo_find_namespace(domainname, len);
+	if (!ptr && tomoyo_memory_ok(entry)) {
+		char *name = (char *) (entry + 1);
+
+		ptr = entry;
+		memmove(name, domainname, len);
+		name[len] = '\0';
+		entry->name = name;
+		tomoyo_init_policy_namespace(entry);
+		entry = NULL;
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+out:
+	kfree(entry);
+	return ptr;
+}
+
+/**
+ * tomoyo_namespace_jump - Check for namespace jump.
+ *
+ * @domainname: Name of domain.
+ *
+ * Returns true if namespace differs, false otherwise.
+ */
+static bool tomoyo_namespace_jump(const char *domainname)
+{
+	const char *namespace = tomoyo_current_namespace()->name;
+	const int len = strlen(namespace);
+
+	return strncmp(domainname, namespace, len) ||
+		(domainname[len] && domainname[len] != ' ');
+}
+
+/**
+ * tomoyo_assign_domain - Create a domain or a namespace.
+ *
+ * @domainname: The name of domain.
+ * @transit:    True if transit to domain found or created.
+ *
+ * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname,
+						const bool transit)
+{
+	struct tomoyo_domain_info e = { };
+	struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname);
+	bool created = false;
+
+	if (entry) {
+		if (transit) {
+			/*
+			 * Since namespace is created at runtime, profiles may
+			 * not be created by the moment the process transits to
+			 * that domain. Do not perform domain transition if
+			 * profile for that domain is not yet created.
+			 */
+			if (tomoyo_policy_loaded &&
+			    !entry->ns->profile_ptr[entry->profile])
+				return NULL;
+		}
+		return entry;
+	}
+	/* Requested domain does not exist. */
+	/* Don't create requested domain if domainname is invalid. */
+	if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 ||
+	    !tomoyo_correct_domain(domainname))
+		return NULL;
+	/*
+	 * Since definition of profiles and acl_groups may differ across
+	 * namespaces, do not inherit "use_profile" and "use_group" settings
+	 * by automatically creating requested domain upon domain transition.
+	 */
+	if (transit && tomoyo_namespace_jump(domainname))
+		return NULL;
+	e.ns = tomoyo_assign_namespace(domainname);
+	if (!e.ns)
+		return NULL;
+	/*
+	 * "use_profile" and "use_group" settings for automatically created
+	 * domains are inherited from current domain. These are 0 for manually
+	 * created domains.
+	 */
+	if (transit) {
+		const struct tomoyo_domain_info *domain = tomoyo_domain();
+
+		e.profile = domain->profile;
+		memcpy(e.group, domain->group, sizeof(e.group));
+	}
+	e.domainname = tomoyo_get_name(domainname);
+	if (!e.domainname)
+		return NULL;
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		goto out;
+	entry = tomoyo_find_domain(domainname);
+	if (!entry) {
+		entry = tomoyo_commit_ok(&e, sizeof(e));
+		if (entry) {
+			INIT_LIST_HEAD(&entry->acl_info_list);
+			list_add_tail_rcu(&entry->list, &tomoyo_domain_list);
+			created = true;
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+out:
+	tomoyo_put_name(e.domainname);
+	if (entry && transit) {
+		if (created) {
+			struct tomoyo_request_info r;
+			int i;
+
+			tomoyo_init_request_info(&r, entry,
+						 TOMOYO_MAC_FILE_EXECUTE);
+			r.granted = false;
+			tomoyo_write_log(&r, "use_profile %u\n",
+					 entry->profile);
+			for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++)
+				if (test_bit(i, entry->group))
+					tomoyo_write_log(&r, "use_group %u\n",
+							 i);
+			tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES);
+		}
+	}
+	return entry;
+}
+
+/**
+ * tomoyo_environ - Check permission for environment variable names.
+ *
+ * @ee: Pointer to "struct tomoyo_execve".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_environ(struct tomoyo_execve *ee)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_request_info *r = &ee->r;
+	struct linux_binprm *bprm = ee->bprm;
+	/* env_page.data is allocated by tomoyo_dump_page(). */
+	struct tomoyo_page_dump env_page = { };
+	char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */
+	int arg_len = 0;
+	unsigned long pos = bprm->p;
+	int offset = pos % PAGE_SIZE;
+	int argv_count = bprm->argc;
+	int envp_count = bprm->envc;
+	int error = -ENOMEM;
+
+	ee->r.type = TOMOYO_MAC_ENVIRON;
+	ee->r.profile = r->domain->profile;
+	ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile,
+				     TOMOYO_MAC_ENVIRON);
+	if (!r->mode || !envp_count)
+		return 0;
+	arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS);
+	if (!arg_ptr)
+		goto out;
+	while (error == -ENOMEM) {
+		if (!tomoyo_dump_page(bprm, pos, &env_page))
+			goto out;
+		pos += PAGE_SIZE - offset;
+		/* Read. */
+		while (argv_count && offset < PAGE_SIZE) {
+			if (!env_page.data[offset++])
+				argv_count--;
+		}
+		if (argv_count) {
+			offset = 0;
+			continue;
+		}
+		while (offset < PAGE_SIZE) {
+			const unsigned char c = env_page.data[offset++];
+
+			if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) {
+				if (c == '=') {
+					arg_ptr[arg_len++] = '\0';
+				} else if (c == '\\') {
+					arg_ptr[arg_len++] = '\\';
+					arg_ptr[arg_len++] = '\\';
+				} else if (c > ' ' && c < 127) {
+					arg_ptr[arg_len++] = c;
+				} else {
+					arg_ptr[arg_len++] = '\\';
+					arg_ptr[arg_len++] = (c >> 6) + '0';
+					arg_ptr[arg_len++]
+						= ((c >> 3) & 7) + '0';
+					arg_ptr[arg_len++] = (c & 7) + '0';
+				}
+			} else {
+				arg_ptr[arg_len] = '\0';
+			}
+			if (c)
+				continue;
+			if (tomoyo_env_perm(r, arg_ptr)) {
+				error = -EPERM;
+				break;
+			}
+			if (!--envp_count) {
+				error = 0;
+				break;
+			}
+			arg_len = 0;
+		}
+		offset = 0;
+	}
+out:
+	if (r->mode != TOMOYO_CONFIG_ENFORCING)
+		error = 0;
+	kfree(env_page.data);
+	kfree(arg_ptr);
+	return error;
+}
+
+/**
+ * tomoyo_find_next_domain - Find a domain.
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_find_next_domain(struct linux_binprm *bprm)
+{
+	struct tomoyo_domain_info *old_domain = tomoyo_domain();
+	struct tomoyo_domain_info *domain = NULL;
+	const char *original_name = bprm->filename;
+	int retval = -ENOMEM;
+	bool reject_on_transition_failure = false;
+	const struct tomoyo_path_info *candidate;
+	struct tomoyo_path_info exename;
+	struct tomoyo_execve *ee = kzalloc_obj(*ee, GFP_NOFS);
+
+	if (!ee)
+		return -ENOMEM;
+	ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS);
+	if (!ee->tmp) {
+		kfree(ee);
+		return -ENOMEM;
+	}
+	/* ee->dump->data is allocated by tomoyo_dump_page(). */
+	tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE);
+	ee->r.ee = ee;
+	ee->bprm = bprm;
+	ee->r.obj = &ee->obj;
+	ee->obj.path1 = bprm->file->f_path;
+	/*
+	 * Get symlink's pathname of program, but fallback to realpath if
+	 * symlink's pathname does not exist or symlink's pathname refers
+	 * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ).
+	 */
+	exename.name = tomoyo_realpath_nofollow(original_name);
+	if (exename.name && !strncmp(exename.name, "proc:/", 6)) {
+		kfree(exename.name);
+		exename.name = NULL;
+	}
+	if (!exename.name) {
+		exename.name = tomoyo_realpath_from_path(&bprm->file->f_path);
+		if (!exename.name)
+			goto out;
+	}
+	tomoyo_fill_path_info(&exename);
+retry:
+	/* Check 'aggregator' directive. */
+	{
+		struct tomoyo_aggregator *ptr;
+		struct list_head *list =
+			&old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR];
+
+		/* Check 'aggregator' directive. */
+		candidate = &exename;
+		list_for_each_entry_rcu(ptr, list, head.list,
+					srcu_read_lock_held(&tomoyo_ss)) {
+			if (ptr->head.is_deleted ||
+			    !tomoyo_path_matches_pattern(&exename,
+							 ptr->original_name))
+				continue;
+			candidate = ptr->aggregated_name;
+			break;
+		}
+	}
+
+	/* Check execute permission. */
+	retval = tomoyo_execute_permission(&ee->r, candidate);
+	if (retval == TOMOYO_RETRY_REQUEST)
+		goto retry;
+	if (retval < 0)
+		goto out;
+	/*
+	 * To be able to specify domainnames with wildcards, use the
+	 * pathname specified in the policy (which may contain
+	 * wildcard) rather than the pathname passed to execve()
+	 * (which never contains wildcard).
+	 */
+	if (ee->r.param.path.matched_path)
+		candidate = ee->r.param.path.matched_path;
+
+	/*
+	 * Check for domain transition preference if "file execute" matched.
+	 * If preference is given, make execve() fail if domain transition
+	 * has failed, for domain transition preference should be used with
+	 * destination domain defined.
+	 */
+	if (ee->transition) {
+		const char *domainname = ee->transition->name;
+
+		reject_on_transition_failure = true;
+		if (!strcmp(domainname, "keep"))
+			goto force_keep_domain;
+		if (!strcmp(domainname, "child"))
+			goto force_child_domain;
+		if (!strcmp(domainname, "reset"))
+			goto force_reset_domain;
+		if (!strcmp(domainname, "initialize"))
+			goto force_initialize_domain;
+		if (!strcmp(domainname, "parent")) {
+			char *cp;
+
+			strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE);
+			cp = strrchr(ee->tmp, ' ');
+			if (cp)
+				*cp = '\0';
+		} else if (*domainname == '<')
+			strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE);
+		else
+			snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s",
+				 old_domain->domainname->name, domainname);
+		goto force_jump_domain;
+	}
+	/*
+	 * No domain transition preference specified.
+	 * Calculate domain to transit to.
+	 */
+	switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname,
+				       candidate)) {
+	case TOMOYO_TRANSITION_CONTROL_RESET:
+force_reset_domain:
+		/* Transit to the root of specified namespace. */
+		snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>",
+			 candidate->name);
+		/*
+		 * Make execve() fail if domain transition across namespaces
+		 * has failed.
+		 */
+		reject_on_transition_failure = true;
+		break;
+	case TOMOYO_TRANSITION_CONTROL_INITIALIZE:
+force_initialize_domain:
+		/* Transit to the child of current namespace's root. */
+		snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s",
+			 old_domain->ns->name, candidate->name);
+		break;
+	case TOMOYO_TRANSITION_CONTROL_KEEP:
+force_keep_domain:
+		/* Keep current domain. */
+		domain = old_domain;
+		break;
+	default:
+		if (old_domain == &tomoyo_kernel_domain &&
+		    !tomoyo_policy_loaded) {
+			/*
+			 * Needn't to transit from kernel domain before
+			 * starting /sbin/init. But transit from kernel domain
+			 * if executing initializers because they might start
+			 * before /sbin/init.
+			 */
+			domain = old_domain;
+			break;
+		}
+force_child_domain:
+		/* Normal domain transition. */
+		snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s",
+			 old_domain->domainname->name, candidate->name);
+		break;
+	}
+force_jump_domain:
+	if (!domain)
+		domain = tomoyo_assign_domain(ee->tmp, true);
+	if (domain)
+		retval = 0;
+	else if (reject_on_transition_failure) {
+		pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp);
+		retval = -ENOMEM;
+	} else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING)
+		retval = -ENOMEM;
+	else {
+		retval = 0;
+		if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) {
+			old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true;
+			ee->r.granted = false;
+			tomoyo_write_log(&ee->r, "%s", tomoyo_dif
+					 [TOMOYO_DIF_TRANSITION_FAILED]);
+			pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp);
+		}
+	}
+ out:
+	if (!domain)
+		domain = old_domain;
+	/* Update reference count on "struct tomoyo_domain_info". */
+	{
+		struct tomoyo_task *s = tomoyo_task(current);
+
+		s->old_domain_info = s->domain_info;
+		s->domain_info = domain;
+		atomic_inc(&domain->users);
+	}
+	kfree(exename.name);
+	if (!retval) {
+		ee->r.domain = domain;
+		retval = tomoyo_environ(ee);
+	}
+	kfree(ee->tmp);
+	kfree(ee->dump.data);
+	kfree(ee);
+	return retval;
+}
+
+/**
+ * tomoyo_dump_page - Dump a page to buffer.
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ * @pos:  Location to dump.
+ * @dump: Pointer to "struct tomoyo_page_dump".
+ *
+ * Returns true on success, false otherwise.
+ */
+bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos,
+		      struct tomoyo_page_dump *dump)
+{
+	struct page *page;
+#ifdef CONFIG_MMU
+	int ret;
+#endif
+
+	/* dump->data is released by tomoyo_find_next_domain(). */
+	if (!dump->data) {
+		dump->data = kzalloc(PAGE_SIZE, GFP_NOFS);
+		if (!dump->data)
+			return false;
+	}
+	/* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */
+#ifdef CONFIG_MMU
+	/*
+	 * This is called at execve() time in order to dig around
+	 * in the argv/environment of the new process
+	 * (represented by bprm).
+	 */
+	mmap_read_lock(bprm->mm);
+	ret = get_user_pages_remote(bprm->mm, pos, 1,
+				    FOLL_FORCE, &page, NULL);
+	mmap_read_unlock(bprm->mm);
+	if (ret <= 0)
+		return false;
+#else
+	page = bprm->page[pos / PAGE_SIZE];
+#endif
+	if (page != dump->page) {
+		const unsigned int offset = pos % PAGE_SIZE;
+		char *kaddr = kmap_local_page(page);
+
+		dump->page = page;
+		memcpy(dump->data + offset, kaddr + offset,
+		       PAGE_SIZE - offset);
+		kunmap_local(kaddr);
+	}
+	/* Same with put_arg_page(page) in fs/exec.c */
+#ifdef CONFIG_MMU
+	put_page(page);
+#endif
+	return true;
+}
diff --git a/security/tomoyo/environ.c b/security/tomoyo/environ.c
new file mode 100644
index 000000000..bcb05910f
--- /dev/null
+++ b/security/tomoyo/environ.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/environ.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+
+/**
+ * tomoyo_check_env_acl - Check permission for environment variable's name.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_env_acl(struct tomoyo_request_info *r,
+				 const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_env_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return tomoyo_path_matches_pattern(r->param.environ.name, acl->env);
+}
+
+/**
+ * tomoyo_audit_env_log - Audit environment variable name log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_env_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "misc env %s\n",
+				 r->param.environ.name->name);
+}
+
+/**
+ * tomoyo_env_perm - Check permission for environment variable's name.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @env: The name of environment variable.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_env_perm(struct tomoyo_request_info *r, const char *env)
+{
+	struct tomoyo_path_info environ;
+	int error;
+
+	if (!env || !*env)
+		return 0;
+	environ.name = env;
+	tomoyo_fill_path_info(&environ);
+	r->param_type = TOMOYO_TYPE_ENV_ACL;
+	r->param.environ.name = &environ;
+	do {
+		tomoyo_check_acl(r, tomoyo_check_env_acl);
+		error = tomoyo_audit_env_log(r);
+	} while (error == TOMOYO_RETRY_REQUEST);
+	return error;
+}
+
+/**
+ * tomoyo_same_env_acl - Check for duplicated "struct tomoyo_env_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_env_acl(const struct tomoyo_acl_info *a,
+				const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_env_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_env_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return p1->env == p2->env;
+}
+
+/**
+ * tomoyo_write_env - Write "struct tomoyo_env_acl" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_write_env(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_env_acl e = { .head.type = TOMOYO_TYPE_ENV_ACL };
+	int error = -ENOMEM;
+	const char *data = tomoyo_read_token(param);
+
+	if (!tomoyo_correct_word(data) || strchr(data, '='))
+		return -EINVAL;
+	e.env = tomoyo_get_name(data);
+	if (!e.env)
+		return error;
+	error = tomoyo_update_domain(&e.head, sizeof(e), param,
+				  tomoyo_same_env_acl, NULL);
+	tomoyo_put_name(e.env);
+	return error;
+}
+
+/**
+ * tomoyo_write_misc - Update environment variable list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_write_misc(struct tomoyo_acl_param *param)
+{
+	if (tomoyo_str_starts(&param->data, "env "))
+		return tomoyo_write_env(param);
+	return -EINVAL;
+}
diff --git a/security/tomoyo/file.c b/security/tomoyo/file.c
new file mode 100644
index 000000000..e9b67dbb3
--- /dev/null
+++ b/security/tomoyo/file.c
@@ -0,0 +1,1050 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/file.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/slab.h>
+
+/*
+ * Mapping table from "enum tomoyo_path_acl_index" to "enum tomoyo_mac_index".
+ */
+static const u8 tomoyo_p2mac[TOMOYO_MAX_PATH_OPERATION] = {
+	[TOMOYO_TYPE_EXECUTE]    = TOMOYO_MAC_FILE_EXECUTE,
+	[TOMOYO_TYPE_READ]       = TOMOYO_MAC_FILE_OPEN,
+	[TOMOYO_TYPE_WRITE]      = TOMOYO_MAC_FILE_OPEN,
+	[TOMOYO_TYPE_APPEND]     = TOMOYO_MAC_FILE_OPEN,
+	[TOMOYO_TYPE_UNLINK]     = TOMOYO_MAC_FILE_UNLINK,
+	[TOMOYO_TYPE_GETATTR]    = TOMOYO_MAC_FILE_GETATTR,
+	[TOMOYO_TYPE_RMDIR]      = TOMOYO_MAC_FILE_RMDIR,
+	[TOMOYO_TYPE_TRUNCATE]   = TOMOYO_MAC_FILE_TRUNCATE,
+	[TOMOYO_TYPE_SYMLINK]    = TOMOYO_MAC_FILE_SYMLINK,
+	[TOMOYO_TYPE_CHROOT]     = TOMOYO_MAC_FILE_CHROOT,
+	[TOMOYO_TYPE_UMOUNT]     = TOMOYO_MAC_FILE_UMOUNT,
+};
+
+/*
+ * Mapping table from "enum tomoyo_mkdev_acl_index" to "enum tomoyo_mac_index".
+ */
+const u8 tomoyo_pnnn2mac[TOMOYO_MAX_MKDEV_OPERATION] = {
+	[TOMOYO_TYPE_MKBLOCK] = TOMOYO_MAC_FILE_MKBLOCK,
+	[TOMOYO_TYPE_MKCHAR]  = TOMOYO_MAC_FILE_MKCHAR,
+};
+
+/*
+ * Mapping table from "enum tomoyo_path2_acl_index" to "enum tomoyo_mac_index".
+ */
+const u8 tomoyo_pp2mac[TOMOYO_MAX_PATH2_OPERATION] = {
+	[TOMOYO_TYPE_LINK]       = TOMOYO_MAC_FILE_LINK,
+	[TOMOYO_TYPE_RENAME]     = TOMOYO_MAC_FILE_RENAME,
+	[TOMOYO_TYPE_PIVOT_ROOT] = TOMOYO_MAC_FILE_PIVOT_ROOT,
+};
+
+/*
+ * Mapping table from "enum tomoyo_path_number_acl_index" to
+ * "enum tomoyo_mac_index".
+ */
+const u8 tomoyo_pn2mac[TOMOYO_MAX_PATH_NUMBER_OPERATION] = {
+	[TOMOYO_TYPE_CREATE] = TOMOYO_MAC_FILE_CREATE,
+	[TOMOYO_TYPE_MKDIR]  = TOMOYO_MAC_FILE_MKDIR,
+	[TOMOYO_TYPE_MKFIFO] = TOMOYO_MAC_FILE_MKFIFO,
+	[TOMOYO_TYPE_MKSOCK] = TOMOYO_MAC_FILE_MKSOCK,
+	[TOMOYO_TYPE_IOCTL]  = TOMOYO_MAC_FILE_IOCTL,
+	[TOMOYO_TYPE_CHMOD]  = TOMOYO_MAC_FILE_CHMOD,
+	[TOMOYO_TYPE_CHOWN]  = TOMOYO_MAC_FILE_CHOWN,
+	[TOMOYO_TYPE_CHGRP]  = TOMOYO_MAC_FILE_CHGRP,
+};
+
+/**
+ * tomoyo_put_name_union - Drop reference on "struct tomoyo_name_union".
+ *
+ * @ptr: Pointer to "struct tomoyo_name_union".
+ *
+ * Returns nothing.
+ */
+void tomoyo_put_name_union(struct tomoyo_name_union *ptr)
+{
+	tomoyo_put_group(ptr->group);
+	tomoyo_put_name(ptr->filename);
+}
+
+/**
+ * tomoyo_compare_name_union - Check whether a name matches "struct tomoyo_name_union" or not.
+ *
+ * @name: Pointer to "struct tomoyo_path_info".
+ * @ptr:  Pointer to "struct tomoyo_name_union".
+ *
+ * Returns "struct tomoyo_path_info" if @name matches @ptr, NULL otherwise.
+ */
+const struct tomoyo_path_info *
+tomoyo_compare_name_union(const struct tomoyo_path_info *name,
+			  const struct tomoyo_name_union *ptr)
+{
+	if (ptr->group)
+		return tomoyo_path_matches_group(name, ptr->group);
+	if (tomoyo_path_matches_pattern(name, ptr->filename))
+		return ptr->filename;
+	return NULL;
+}
+
+/**
+ * tomoyo_put_number_union - Drop reference on "struct tomoyo_number_union".
+ *
+ * @ptr: Pointer to "struct tomoyo_number_union".
+ *
+ * Returns nothing.
+ */
+void tomoyo_put_number_union(struct tomoyo_number_union *ptr)
+{
+	tomoyo_put_group(ptr->group);
+}
+
+/**
+ * tomoyo_compare_number_union - Check whether a value matches "struct tomoyo_number_union" or not.
+ *
+ * @value: Number to check.
+ * @ptr:   Pointer to "struct tomoyo_number_union".
+ *
+ * Returns true if @value matches @ptr, false otherwise.
+ */
+bool tomoyo_compare_number_union(const unsigned long value,
+				 const struct tomoyo_number_union *ptr)
+{
+	if (ptr->group)
+		return tomoyo_number_matches_group(value, value, ptr->group);
+	return value >= ptr->values[0] && value <= ptr->values[1];
+}
+
+/**
+ * tomoyo_add_slash - Add trailing '/' if needed.
+ *
+ * @buf: Pointer to "struct tomoyo_path_info".
+ *
+ * Returns nothing.
+ *
+ * @buf must be generated by tomoyo_encode() because this function does not
+ * allocate memory for adding '/'.
+ */
+static void tomoyo_add_slash(struct tomoyo_path_info *buf)
+{
+	if (buf->is_dir)
+		return;
+	/*
+	 * This is OK because tomoyo_encode() reserves space for appending "/".
+	 */
+	strcat((char *) buf->name, "/");
+	tomoyo_fill_path_info(buf);
+}
+
+/**
+ * tomoyo_get_realpath - Get realpath.
+ *
+ * @buf:  Pointer to "struct tomoyo_path_info".
+ * @path: Pointer to "struct path".
+ *
+ * Returns true on success, false otherwise.
+ */
+static bool tomoyo_get_realpath(struct tomoyo_path_info *buf, const struct path *path)
+{
+	buf->name = tomoyo_realpath_from_path(path);
+	if (buf->name) {
+		tomoyo_fill_path_info(buf);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * tomoyo_audit_path_log - Audit path request log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_path_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "file %s %s\n", tomoyo_path_keyword
+				 [r->param.path.operation],
+				 r->param.path.filename->name);
+}
+
+/**
+ * tomoyo_audit_path2_log - Audit path/path request log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_path2_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords
+				 [tomoyo_pp2mac[r->param.path2.operation]],
+				 r->param.path2.filename1->name,
+				 r->param.path2.filename2->name);
+}
+
+/**
+ * tomoyo_audit_mkdev_log - Audit path/number/number/number request log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_mkdev_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "file %s %s 0%o %u %u\n",
+				 tomoyo_mac_keywords
+				 [tomoyo_pnnn2mac[r->param.mkdev.operation]],
+				 r->param.mkdev.filename->name,
+				 r->param.mkdev.mode, r->param.mkdev.major,
+				 r->param.mkdev.minor);
+}
+
+/**
+ * tomoyo_audit_path_number_log - Audit path/number request log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_path_number_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	const u8 type = r->param.path_number.operation;
+	u8 radix;
+	char buffer[64];
+
+	switch (type) {
+	case TOMOYO_TYPE_CREATE:
+	case TOMOYO_TYPE_MKDIR:
+	case TOMOYO_TYPE_MKFIFO:
+	case TOMOYO_TYPE_MKSOCK:
+	case TOMOYO_TYPE_CHMOD:
+		radix = TOMOYO_VALUE_TYPE_OCTAL;
+		break;
+	case TOMOYO_TYPE_IOCTL:
+		radix = TOMOYO_VALUE_TYPE_HEXADECIMAL;
+		break;
+	default:
+		radix = TOMOYO_VALUE_TYPE_DECIMAL;
+		break;
+	}
+	tomoyo_print_ulong(buffer, sizeof(buffer), r->param.path_number.number,
+			   radix);
+	return tomoyo_supervisor(r, "file %s %s %s\n", tomoyo_mac_keywords
+				 [tomoyo_pn2mac[type]],
+				 r->param.path_number.filename->name, buffer);
+}
+
+/**
+ * tomoyo_check_path_acl - Check permission for path operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ *
+ * To be able to use wildcard for domain transition, this function sets
+ * matching entry on success. Since the caller holds tomoyo_read_lock(),
+ * it is safe to set matching entry.
+ */
+static bool tomoyo_check_path_acl(struct tomoyo_request_info *r,
+				  const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_path_acl *acl = container_of(ptr, typeof(*acl),
+							 head);
+
+	if (acl->perm & (1 << r->param.path.operation)) {
+		r->param.path.matched_path =
+			tomoyo_compare_name_union(r->param.path.filename,
+						  &acl->name);
+		return r->param.path.matched_path != NULL;
+	}
+	return false;
+}
+
+/**
+ * tomoyo_check_path_number_acl - Check permission for path number operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_path_number_acl(struct tomoyo_request_info *r,
+					 const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_path_number_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return (acl->perm & (1 << r->param.path_number.operation)) &&
+		tomoyo_compare_number_union(r->param.path_number.number,
+					    &acl->number) &&
+		tomoyo_compare_name_union(r->param.path_number.filename,
+					  &acl->name);
+}
+
+/**
+ * tomoyo_check_path2_acl - Check permission for path path operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_path2_acl(struct tomoyo_request_info *r,
+				   const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_path2_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return (acl->perm & (1 << r->param.path2.operation)) &&
+		tomoyo_compare_name_union(r->param.path2.filename1, &acl->name1)
+		&& tomoyo_compare_name_union(r->param.path2.filename2,
+					     &acl->name2);
+}
+
+/**
+ * tomoyo_check_mkdev_acl - Check permission for path number number number operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_mkdev_acl(struct tomoyo_request_info *r,
+				   const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_mkdev_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return (acl->perm & (1 << r->param.mkdev.operation)) &&
+		tomoyo_compare_number_union(r->param.mkdev.mode,
+					    &acl->mode) &&
+		tomoyo_compare_number_union(r->param.mkdev.major,
+					    &acl->major) &&
+		tomoyo_compare_number_union(r->param.mkdev.minor,
+					    &acl->minor) &&
+		tomoyo_compare_name_union(r->param.mkdev.filename,
+					  &acl->name);
+}
+
+/**
+ * tomoyo_same_path_acl - Check for duplicated "struct tomoyo_path_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_path_acl(const struct tomoyo_acl_info *a,
+				 const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_path_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_path_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return tomoyo_same_name_union(&p1->name, &p2->name);
+}
+
+/**
+ * tomoyo_merge_path_acl - Merge duplicated "struct tomoyo_path_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_path_acl(struct tomoyo_acl_info *a,
+				  struct tomoyo_acl_info *b,
+				  const bool is_delete)
+{
+	u16 * const a_perm = &container_of(a, struct tomoyo_path_acl, head)
+		->perm;
+	u16 perm = READ_ONCE(*a_perm);
+	const u16 b_perm = container_of(b, struct tomoyo_path_acl, head)->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_update_path_acl - Update "struct tomoyo_path_acl" list.
+ *
+ * @perm:  Permission.
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_update_path_acl(const u16 perm,
+				  struct tomoyo_acl_param *param)
+{
+	struct tomoyo_path_acl e = {
+		.head.type = TOMOYO_TYPE_PATH_ACL,
+		.perm = perm
+	};
+	int error;
+
+	if (!tomoyo_parse_name_union(param, &e.name))
+		error = -EINVAL;
+	else
+		error = tomoyo_update_domain(&e.head, sizeof(e), param,
+					     tomoyo_same_path_acl,
+					     tomoyo_merge_path_acl);
+	tomoyo_put_name_union(&e.name);
+	return error;
+}
+
+/**
+ * tomoyo_same_mkdev_acl - Check for duplicated "struct tomoyo_mkdev_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_mkdev_acl(const struct tomoyo_acl_info *a,
+					 const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_mkdev_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_mkdev_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return tomoyo_same_name_union(&p1->name, &p2->name) &&
+		tomoyo_same_number_union(&p1->mode, &p2->mode) &&
+		tomoyo_same_number_union(&p1->major, &p2->major) &&
+		tomoyo_same_number_union(&p1->minor, &p2->minor);
+}
+
+/**
+ * tomoyo_merge_mkdev_acl - Merge duplicated "struct tomoyo_mkdev_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_mkdev_acl(struct tomoyo_acl_info *a,
+				   struct tomoyo_acl_info *b,
+				   const bool is_delete)
+{
+	u8 *const a_perm = &container_of(a, struct tomoyo_mkdev_acl,
+					 head)->perm;
+	u8 perm = READ_ONCE(*a_perm);
+	const u8 b_perm = container_of(b, struct tomoyo_mkdev_acl, head)
+		->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_update_mkdev_acl - Update "struct tomoyo_mkdev_acl" list.
+ *
+ * @perm:  Permission.
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_update_mkdev_acl(const u8 perm,
+				   struct tomoyo_acl_param *param)
+{
+	struct tomoyo_mkdev_acl e = {
+		.head.type = TOMOYO_TYPE_MKDEV_ACL,
+		.perm = perm
+	};
+	int error;
+
+	if (!tomoyo_parse_name_union(param, &e.name) ||
+	    !tomoyo_parse_number_union(param, &e.mode) ||
+	    !tomoyo_parse_number_union(param, &e.major) ||
+	    !tomoyo_parse_number_union(param, &e.minor))
+		error = -EINVAL;
+	else
+		error = tomoyo_update_domain(&e.head, sizeof(e), param,
+					     tomoyo_same_mkdev_acl,
+					     tomoyo_merge_mkdev_acl);
+	tomoyo_put_name_union(&e.name);
+	tomoyo_put_number_union(&e.mode);
+	tomoyo_put_number_union(&e.major);
+	tomoyo_put_number_union(&e.minor);
+	return error;
+}
+
+/**
+ * tomoyo_same_path2_acl - Check for duplicated "struct tomoyo_path2_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_path2_acl(const struct tomoyo_acl_info *a,
+				  const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_path2_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_path2_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return tomoyo_same_name_union(&p1->name1, &p2->name1) &&
+		tomoyo_same_name_union(&p1->name2, &p2->name2);
+}
+
+/**
+ * tomoyo_merge_path2_acl - Merge duplicated "struct tomoyo_path2_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_path2_acl(struct tomoyo_acl_info *a,
+				   struct tomoyo_acl_info *b,
+				   const bool is_delete)
+{
+	u8 * const a_perm = &container_of(a, struct tomoyo_path2_acl, head)
+		->perm;
+	u8 perm = READ_ONCE(*a_perm);
+	const u8 b_perm = container_of(b, struct tomoyo_path2_acl, head)->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_update_path2_acl - Update "struct tomoyo_path2_acl" list.
+ *
+ * @perm:  Permission.
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_update_path2_acl(const u8 perm,
+				   struct tomoyo_acl_param *param)
+{
+	struct tomoyo_path2_acl e = {
+		.head.type = TOMOYO_TYPE_PATH2_ACL,
+		.perm = perm
+	};
+	int error;
+
+	if (!tomoyo_parse_name_union(param, &e.name1) ||
+	    !tomoyo_parse_name_union(param, &e.name2))
+		error = -EINVAL;
+	else
+		error = tomoyo_update_domain(&e.head, sizeof(e), param,
+					     tomoyo_same_path2_acl,
+					     tomoyo_merge_path2_acl);
+	tomoyo_put_name_union(&e.name1);
+	tomoyo_put_name_union(&e.name2);
+	return error;
+}
+
+/**
+ * tomoyo_path_permission - Check permission for single path operation.
+ *
+ * @r:         Pointer to "struct tomoyo_request_info".
+ * @operation: Type of operation.
+ * @filename:  Filename to check.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_path_permission(struct tomoyo_request_info *r, u8 operation,
+				  const struct tomoyo_path_info *filename)
+	__must_hold_shared(&tomoyo_ss)
+{
+	int error;
+
+	r->type = tomoyo_p2mac[operation];
+	r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type);
+	if (r->mode == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	r->param_type = TOMOYO_TYPE_PATH_ACL;
+	r->param.path.filename = filename;
+	r->param.path.operation = operation;
+	do {
+		tomoyo_check_acl(r, tomoyo_check_path_acl);
+		error = tomoyo_audit_path_log(r);
+	} while (error == TOMOYO_RETRY_REQUEST);
+	return error;
+}
+
+/**
+ * tomoyo_execute_permission - Check permission for execute operation.
+ *
+ * @r:         Pointer to "struct tomoyo_request_info".
+ * @filename:  Filename to check.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_execute_permission(struct tomoyo_request_info *r,
+			      const struct tomoyo_path_info *filename)
+{
+	/*
+	 * Unlike other permission checks, this check is done regardless of
+	 * profile mode settings in order to check for domain transition
+	 * preference.
+	 */
+	r->type = TOMOYO_MAC_FILE_EXECUTE;
+	r->mode = tomoyo_get_mode(r->domain->ns, r->profile, r->type);
+	r->param_type = TOMOYO_TYPE_PATH_ACL;
+	r->param.path.filename = filename;
+	r->param.path.operation = TOMOYO_TYPE_EXECUTE;
+	tomoyo_check_acl(r, tomoyo_check_path_acl);
+	r->ee->transition = r->matched_acl && r->matched_acl->cond ?
+		r->matched_acl->cond->transit : NULL;
+	if (r->mode != TOMOYO_CONFIG_DISABLED)
+		return tomoyo_audit_path_log(r);
+	return 0;
+}
+
+/**
+ * tomoyo_same_path_number_acl - Check for duplicated "struct tomoyo_path_number_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_path_number_acl(const struct tomoyo_acl_info *a,
+					const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_path_number_acl *p1 = container_of(a, typeof(*p1),
+							       head);
+	const struct tomoyo_path_number_acl *p2 = container_of(b, typeof(*p2),
+							       head);
+
+	return tomoyo_same_name_union(&p1->name, &p2->name) &&
+		tomoyo_same_number_union(&p1->number, &p2->number);
+}
+
+/**
+ * tomoyo_merge_path_number_acl - Merge duplicated "struct tomoyo_path_number_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_path_number_acl(struct tomoyo_acl_info *a,
+					 struct tomoyo_acl_info *b,
+					 const bool is_delete)
+{
+	u8 * const a_perm = &container_of(a, struct tomoyo_path_number_acl,
+					  head)->perm;
+	u8 perm = READ_ONCE(*a_perm);
+	const u8 b_perm = container_of(b, struct tomoyo_path_number_acl, head)
+		->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_update_path_number_acl - Update ioctl/chmod/chown/chgrp ACL.
+ *
+ * @perm:  Permission.
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_update_path_number_acl(const u8 perm,
+					 struct tomoyo_acl_param *param)
+{
+	struct tomoyo_path_number_acl e = {
+		.head.type = TOMOYO_TYPE_PATH_NUMBER_ACL,
+		.perm = perm
+	};
+	int error;
+
+	if (!tomoyo_parse_name_union(param, &e.name) ||
+	    !tomoyo_parse_number_union(param, &e.number))
+		error = -EINVAL;
+	else
+		error = tomoyo_update_domain(&e.head, sizeof(e), param,
+					     tomoyo_same_path_number_acl,
+					     tomoyo_merge_path_number_acl);
+	tomoyo_put_name_union(&e.name);
+	tomoyo_put_number_union(&e.number);
+	return error;
+}
+
+/**
+ * tomoyo_path_number_perm - Check permission for "create", "mkdir", "mkfifo", "mksock", "ioctl", "chmod", "chown", "chgrp".
+ *
+ * @type:   Type of operation.
+ * @path:   Pointer to "struct path".
+ * @number: Number.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_path_number_perm(const u8 type, const struct path *path,
+			    unsigned long number)
+{
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj = {
+		.path1 = { .mnt = path->mnt, .dentry = path->dentry },
+	};
+	int error = -ENOMEM;
+	struct tomoyo_path_info buf;
+	int idx;
+
+	if (tomoyo_init_request_info(&r, NULL, tomoyo_pn2mac[type])
+	    == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	idx = tomoyo_read_lock();
+	if (!tomoyo_get_realpath(&buf, path))
+		goto out;
+	r.obj = &obj;
+	if (type == TOMOYO_TYPE_MKDIR)
+		tomoyo_add_slash(&buf);
+	r.param_type = TOMOYO_TYPE_PATH_NUMBER_ACL;
+	r.param.path_number.operation = type;
+	r.param.path_number.filename = &buf;
+	r.param.path_number.number = number;
+	do {
+		tomoyo_check_acl(&r, tomoyo_check_path_number_acl);
+		error = tomoyo_audit_path_number_log(&r);
+	} while (error == TOMOYO_RETRY_REQUEST);
+	kfree(buf.name);
+ out:
+	tomoyo_read_unlock(idx);
+	if (r.mode != TOMOYO_CONFIG_ENFORCING)
+		error = 0;
+	return error;
+}
+
+/**
+ * tomoyo_check_open_permission - Check permission for "read" and "write".
+ *
+ * @domain: Pointer to "struct tomoyo_domain_info".
+ * @path:   Pointer to "struct path".
+ * @flag:   Flags for open().
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_check_open_permission(struct tomoyo_domain_info *domain,
+				 const struct path *path, const int flag)
+{
+	const u8 acc_mode = ACC_MODE(flag);
+	int error = 0;
+	struct tomoyo_path_info buf;
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj = {
+		.path1 = { .mnt = path->mnt, .dentry = path->dentry },
+	};
+	int idx;
+
+	buf.name = NULL;
+	r.mode = TOMOYO_CONFIG_DISABLED;
+	idx = tomoyo_read_lock();
+	if (acc_mode &&
+	    tomoyo_init_request_info(&r, domain, TOMOYO_MAC_FILE_OPEN)
+	    != TOMOYO_CONFIG_DISABLED) {
+		if (!tomoyo_get_realpath(&buf, path)) {
+			error = -ENOMEM;
+			goto out;
+		}
+		r.obj = &obj;
+		if (acc_mode & MAY_READ)
+			error = tomoyo_path_permission(&r, TOMOYO_TYPE_READ,
+						       &buf);
+		if (!error && (acc_mode & MAY_WRITE))
+			error = tomoyo_path_permission(&r, (flag & O_APPEND) ?
+						       TOMOYO_TYPE_APPEND :
+						       TOMOYO_TYPE_WRITE,
+						       &buf);
+	}
+ out:
+	kfree(buf.name);
+	tomoyo_read_unlock(idx);
+	if (r.mode != TOMOYO_CONFIG_ENFORCING)
+		error = 0;
+	return error;
+}
+
+/**
+ * tomoyo_path_perm - Check permission for "unlink", "rmdir", "truncate", "symlink", "append", "chroot" and "unmount".
+ *
+ * @operation: Type of operation.
+ * @path:      Pointer to "struct path".
+ * @target:    Symlink's target if @operation is TOMOYO_TYPE_SYMLINK,
+ *             NULL otherwise.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_path_perm(const u8 operation, const struct path *path, const char *target)
+{
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj = {
+		.path1 = { .mnt = path->mnt, .dentry = path->dentry },
+	};
+	int error;
+	struct tomoyo_path_info buf;
+	bool is_enforce;
+	struct tomoyo_path_info symlink_target;
+	int idx;
+
+	if (tomoyo_init_request_info(&r, NULL, tomoyo_p2mac[operation])
+	    == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	is_enforce = (r.mode == TOMOYO_CONFIG_ENFORCING);
+	error = -ENOMEM;
+	buf.name = NULL;
+	idx = tomoyo_read_lock();
+	if (!tomoyo_get_realpath(&buf, path))
+		goto out;
+	r.obj = &obj;
+	switch (operation) {
+	case TOMOYO_TYPE_RMDIR:
+	case TOMOYO_TYPE_CHROOT:
+		tomoyo_add_slash(&buf);
+		break;
+	case TOMOYO_TYPE_SYMLINK:
+		symlink_target.name = tomoyo_encode(target);
+		if (!symlink_target.name)
+			goto out;
+		tomoyo_fill_path_info(&symlink_target);
+		obj.symlink_target = &symlink_target;
+		break;
+	}
+	error = tomoyo_path_permission(&r, operation, &buf);
+	if (operation == TOMOYO_TYPE_SYMLINK)
+		kfree(symlink_target.name);
+ out:
+	kfree(buf.name);
+	tomoyo_read_unlock(idx);
+	if (!is_enforce)
+		error = 0;
+	return error;
+}
+
+/**
+ * tomoyo_mkdev_perm - Check permission for "mkblock" and "mkchar".
+ *
+ * @operation: Type of operation. (TOMOYO_TYPE_MKCHAR or TOMOYO_TYPE_MKBLOCK)
+ * @path:      Pointer to "struct path".
+ * @mode:      Create mode.
+ * @dev:       Device number.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_mkdev_perm(const u8 operation, const struct path *path,
+		      const unsigned int mode, unsigned int dev)
+{
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj = {
+		.path1 = { .mnt = path->mnt, .dentry = path->dentry },
+	};
+	int error = -ENOMEM;
+	struct tomoyo_path_info buf;
+	int idx;
+
+	if (tomoyo_init_request_info(&r, NULL, tomoyo_pnnn2mac[operation])
+	    == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	idx = tomoyo_read_lock();
+	error = -ENOMEM;
+	if (tomoyo_get_realpath(&buf, path)) {
+		r.obj = &obj;
+		dev = new_decode_dev(dev);
+		r.param_type = TOMOYO_TYPE_MKDEV_ACL;
+		r.param.mkdev.filename = &buf;
+		r.param.mkdev.operation = operation;
+		r.param.mkdev.mode = mode;
+		r.param.mkdev.major = MAJOR(dev);
+		r.param.mkdev.minor = MINOR(dev);
+		tomoyo_check_acl(&r, tomoyo_check_mkdev_acl);
+		error = tomoyo_audit_mkdev_log(&r);
+		kfree(buf.name);
+	}
+	tomoyo_read_unlock(idx);
+	if (r.mode != TOMOYO_CONFIG_ENFORCING)
+		error = 0;
+	return error;
+}
+
+/**
+ * tomoyo_path2_perm - Check permission for "rename", "link" and "pivot_root".
+ *
+ * @operation: Type of operation.
+ * @path1:      Pointer to "struct path".
+ * @path2:      Pointer to "struct path".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_path2_perm(const u8 operation, const struct path *path1,
+		      const struct path *path2)
+{
+	int error = -ENOMEM;
+	struct tomoyo_path_info buf1;
+	struct tomoyo_path_info buf2;
+	struct tomoyo_request_info r;
+	struct tomoyo_obj_info obj = {
+		.path1 = { .mnt = path1->mnt, .dentry = path1->dentry },
+		.path2 = { .mnt = path2->mnt, .dentry = path2->dentry }
+	};
+	int idx;
+
+	if (tomoyo_init_request_info(&r, NULL, tomoyo_pp2mac[operation])
+	    == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	buf1.name = NULL;
+	buf2.name = NULL;
+	idx = tomoyo_read_lock();
+	if (!tomoyo_get_realpath(&buf1, path1) ||
+	    !tomoyo_get_realpath(&buf2, path2))
+		goto out;
+	switch (operation) {
+	case TOMOYO_TYPE_RENAME:
+	case TOMOYO_TYPE_LINK:
+		if (!d_is_dir(path1->dentry))
+			break;
+		fallthrough;
+	case TOMOYO_TYPE_PIVOT_ROOT:
+		tomoyo_add_slash(&buf1);
+		tomoyo_add_slash(&buf2);
+		break;
+	}
+	r.obj = &obj;
+	r.param_type = TOMOYO_TYPE_PATH2_ACL;
+	r.param.path2.operation = operation;
+	r.param.path2.filename1 = &buf1;
+	r.param.path2.filename2 = &buf2;
+	do {
+		tomoyo_check_acl(&r, tomoyo_check_path2_acl);
+		error = tomoyo_audit_path2_log(&r);
+	} while (error == TOMOYO_RETRY_REQUEST);
+ out:
+	kfree(buf1.name);
+	kfree(buf2.name);
+	tomoyo_read_unlock(idx);
+	if (r.mode != TOMOYO_CONFIG_ENFORCING)
+		error = 0;
+	return error;
+}
+
+/**
+ * tomoyo_same_mount_acl - Check for duplicated "struct tomoyo_mount_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_mount_acl(const struct tomoyo_acl_info *a,
+				  const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_mount_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_mount_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return tomoyo_same_name_union(&p1->dev_name, &p2->dev_name) &&
+		tomoyo_same_name_union(&p1->dir_name, &p2->dir_name) &&
+		tomoyo_same_name_union(&p1->fs_type, &p2->fs_type) &&
+		tomoyo_same_number_union(&p1->flags, &p2->flags);
+}
+
+/**
+ * tomoyo_update_mount_acl - Write "struct tomoyo_mount_acl" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_update_mount_acl(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_mount_acl e = { .head.type = TOMOYO_TYPE_MOUNT_ACL };
+	int error;
+
+	if (!tomoyo_parse_name_union(param, &e.dev_name) ||
+	    !tomoyo_parse_name_union(param, &e.dir_name) ||
+	    !tomoyo_parse_name_union(param, &e.fs_type) ||
+	    !tomoyo_parse_number_union(param, &e.flags))
+		error = -EINVAL;
+	else
+		error = tomoyo_update_domain(&e.head, sizeof(e), param,
+					     tomoyo_same_mount_acl, NULL);
+	tomoyo_put_name_union(&e.dev_name);
+	tomoyo_put_name_union(&e.dir_name);
+	tomoyo_put_name_union(&e.fs_type);
+	tomoyo_put_number_union(&e.flags);
+	return error;
+}
+
+/**
+ * tomoyo_write_file - Update file related list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_write_file(struct tomoyo_acl_param *param)
+{
+	u16 perm = 0;
+	u8 type;
+	const char *operation = tomoyo_read_token(param);
+
+	for (type = 0; type < TOMOYO_MAX_PATH_OPERATION; type++)
+		if (tomoyo_permstr(operation, tomoyo_path_keyword[type]))
+			perm |= 1 << type;
+	if (perm)
+		return tomoyo_update_path_acl(perm, param);
+	for (type = 0; type < TOMOYO_MAX_PATH2_OPERATION; type++)
+		if (tomoyo_permstr(operation,
+				   tomoyo_mac_keywords[tomoyo_pp2mac[type]]))
+			perm |= 1 << type;
+	if (perm)
+		return tomoyo_update_path2_acl(perm, param);
+	for (type = 0; type < TOMOYO_MAX_PATH_NUMBER_OPERATION; type++)
+		if (tomoyo_permstr(operation,
+				   tomoyo_mac_keywords[tomoyo_pn2mac[type]]))
+			perm |= 1 << type;
+	if (perm)
+		return tomoyo_update_path_number_acl(perm, param);
+	for (type = 0; type < TOMOYO_MAX_MKDEV_OPERATION; type++)
+		if (tomoyo_permstr(operation,
+				   tomoyo_mac_keywords[tomoyo_pnnn2mac[type]]))
+			perm |= 1 << type;
+	if (perm)
+		return tomoyo_update_mkdev_acl(perm, param);
+	if (tomoyo_permstr(operation,
+			   tomoyo_mac_keywords[TOMOYO_MAC_FILE_MOUNT]))
+		return tomoyo_update_mount_acl(param);
+	return -EINVAL;
+}
diff --git a/security/tomoyo/gc.c b/security/tomoyo/gc.c
new file mode 100644
index 000000000..8e2008863
--- /dev/null
+++ b/security/tomoyo/gc.c
@@ -0,0 +1,682 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/gc.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/kthread.h>
+#include <linux/slab.h>
+
+/**
+ * tomoyo_memory_free - Free memory for elements.
+ *
+ * @ptr:  Pointer to allocated memory.
+ *
+ * Returns nothing.
+ *
+ * Caller holds tomoyo_policy_lock mutex.
+ */
+static inline void tomoyo_memory_free(void *ptr)
+{
+	tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= ksize(ptr);
+	kfree(ptr);
+}
+/* Lock for protecting tomoyo_io_buffer_list. */
+static DEFINE_SPINLOCK(tomoyo_io_buffer_list_lock);
+/* The list for "struct tomoyo_io_buffer". */
+static __guarded_by(&tomoyo_io_buffer_list_lock) LIST_HEAD(tomoyo_io_buffer_list);
+
+/**
+ * tomoyo_struct_used_by_io_buffer - Check whether the list element is used by /sys/kernel/security/tomoyo/ users or not.
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns true if @element is used by /sys/kernel/security/tomoyo/ users,
+ * false otherwise.
+ */
+static bool tomoyo_struct_used_by_io_buffer(const struct list_head *element)
+{
+	struct tomoyo_io_buffer *head;
+	bool in_use = false;
+
+	spin_lock(&tomoyo_io_buffer_list_lock);
+	list_for_each_entry(head, &tomoyo_io_buffer_list, list) {
+		head->users++;
+		spin_unlock(&tomoyo_io_buffer_list_lock);
+		mutex_lock(&head->io_sem);
+		if (head->r.domain == element || head->r.group == element ||
+		    head->r.acl == element || &head->w.domain->list == element)
+			in_use = true;
+		mutex_unlock(&head->io_sem);
+		spin_lock(&tomoyo_io_buffer_list_lock);
+		head->users--;
+		if (in_use)
+			break;
+	}
+	spin_unlock(&tomoyo_io_buffer_list_lock);
+	return in_use;
+}
+
+/**
+ * tomoyo_name_used_by_io_buffer - Check whether the string is used by /sys/kernel/security/tomoyo/ users or not.
+ *
+ * @string: String to check.
+ *
+ * Returns true if @string is used by /sys/kernel/security/tomoyo/ users,
+ * false otherwise.
+ */
+static bool tomoyo_name_used_by_io_buffer(const char *string)
+{
+	struct tomoyo_io_buffer *head;
+	const size_t size = strlen(string) + 1;
+	bool in_use = false;
+
+	spin_lock(&tomoyo_io_buffer_list_lock);
+	list_for_each_entry(head, &tomoyo_io_buffer_list, list) {
+		int i;
+
+		head->users++;
+		spin_unlock(&tomoyo_io_buffer_list_lock);
+		mutex_lock(&head->io_sem);
+		for (i = 0; i < TOMOYO_MAX_IO_READ_QUEUE; i++) {
+			const char *w = head->r.w[i];
+
+			if (w < string || w > string + size)
+				continue;
+			in_use = true;
+			break;
+		}
+		mutex_unlock(&head->io_sem);
+		spin_lock(&tomoyo_io_buffer_list_lock);
+		head->users--;
+		if (in_use)
+			break;
+	}
+	spin_unlock(&tomoyo_io_buffer_list_lock);
+	return in_use;
+}
+
+/**
+ * tomoyo_del_transition_control - Delete members in "struct tomoyo_transition_control".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_transition_control(struct list_head *element)
+{
+	struct tomoyo_transition_control *ptr =
+		container_of(element, typeof(*ptr), head.list);
+
+	tomoyo_put_name(ptr->domainname);
+	tomoyo_put_name(ptr->program);
+}
+
+/**
+ * tomoyo_del_aggregator - Delete members in "struct tomoyo_aggregator".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_aggregator(struct list_head *element)
+{
+	struct tomoyo_aggregator *ptr =
+		container_of(element, typeof(*ptr), head.list);
+
+	tomoyo_put_name(ptr->original_name);
+	tomoyo_put_name(ptr->aggregated_name);
+}
+
+/**
+ * tomoyo_del_manager - Delete members in "struct tomoyo_manager".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_manager(struct list_head *element)
+{
+	struct tomoyo_manager *ptr =
+		container_of(element, typeof(*ptr), head.list);
+
+	tomoyo_put_name(ptr->manager);
+}
+
+/**
+ * tomoyo_del_acl - Delete members in "struct tomoyo_acl_info".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_del_acl(struct list_head *element)
+{
+	struct tomoyo_acl_info *acl =
+		container_of(element, typeof(*acl), list);
+
+	tomoyo_put_condition(acl->cond);
+	switch (acl->type) {
+	case TOMOYO_TYPE_PATH_ACL:
+		{
+			struct tomoyo_path_acl *entry
+				= container_of(acl, typeof(*entry), head);
+			tomoyo_put_name_union(&entry->name);
+		}
+		break;
+	case TOMOYO_TYPE_PATH2_ACL:
+		{
+			struct tomoyo_path2_acl *entry
+				= container_of(acl, typeof(*entry), head);
+			tomoyo_put_name_union(&entry->name1);
+			tomoyo_put_name_union(&entry->name2);
+		}
+		break;
+	case TOMOYO_TYPE_PATH_NUMBER_ACL:
+		{
+			struct tomoyo_path_number_acl *entry
+				= container_of(acl, typeof(*entry), head);
+			tomoyo_put_name_union(&entry->name);
+			tomoyo_put_number_union(&entry->number);
+		}
+		break;
+	case TOMOYO_TYPE_MKDEV_ACL:
+		{
+			struct tomoyo_mkdev_acl *entry
+				= container_of(acl, typeof(*entry), head);
+			tomoyo_put_name_union(&entry->name);
+			tomoyo_put_number_union(&entry->mode);
+			tomoyo_put_number_union(&entry->major);
+			tomoyo_put_number_union(&entry->minor);
+		}
+		break;
+	case TOMOYO_TYPE_MOUNT_ACL:
+		{
+			struct tomoyo_mount_acl *entry
+				= container_of(acl, typeof(*entry), head);
+			tomoyo_put_name_union(&entry->dev_name);
+			tomoyo_put_name_union(&entry->dir_name);
+			tomoyo_put_name_union(&entry->fs_type);
+			tomoyo_put_number_union(&entry->flags);
+		}
+		break;
+	case TOMOYO_TYPE_ENV_ACL:
+		{
+			struct tomoyo_env_acl *entry =
+				container_of(acl, typeof(*entry), head);
+
+			tomoyo_put_name(entry->env);
+		}
+		break;
+	case TOMOYO_TYPE_INET_ACL:
+		{
+			struct tomoyo_inet_acl *entry =
+				container_of(acl, typeof(*entry), head);
+
+			tomoyo_put_group(entry->address.group);
+			tomoyo_put_number_union(&entry->port);
+		}
+		break;
+	case TOMOYO_TYPE_UNIX_ACL:
+		{
+			struct tomoyo_unix_acl *entry =
+				container_of(acl, typeof(*entry), head);
+
+			tomoyo_put_name_union(&entry->name);
+		}
+		break;
+	case TOMOYO_TYPE_MANUAL_TASK_ACL:
+		{
+			struct tomoyo_task_acl *entry =
+				container_of(acl, typeof(*entry), head);
+
+			tomoyo_put_name(entry->domainname);
+		}
+		break;
+	}
+}
+
+/**
+ * tomoyo_del_domain - Delete members in "struct tomoyo_domain_info".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ *
+ * Caller holds tomoyo_policy_lock mutex.
+ */
+static inline void tomoyo_del_domain(struct list_head *element)
+{
+	struct tomoyo_domain_info *domain =
+		container_of(element, typeof(*domain), list);
+	struct tomoyo_acl_info *acl;
+	struct tomoyo_acl_info *tmp;
+
+	/*
+	 * Since this domain is referenced from neither
+	 * "struct tomoyo_io_buffer" nor "struct cred"->security, we can delete
+	 * elements without checking for is_deleted flag.
+	 */
+	list_for_each_entry_safe(acl, tmp, &domain->acl_info_list, list) {
+		tomoyo_del_acl(&acl->list);
+		tomoyo_memory_free(acl);
+	}
+	tomoyo_put_name(domain->domainname);
+}
+
+/**
+ * tomoyo_del_condition - Delete members in "struct tomoyo_condition".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+void tomoyo_del_condition(struct list_head *element)
+{
+	struct tomoyo_condition *cond = container_of(element, typeof(*cond),
+						     head.list);
+	const u16 condc = cond->condc;
+	const u16 numbers_count = cond->numbers_count;
+	const u16 names_count = cond->names_count;
+	const u16 argc = cond->argc;
+	const u16 envc = cond->envc;
+	unsigned int i;
+	const struct tomoyo_condition_element *condp
+		= (const struct tomoyo_condition_element *) (cond + 1);
+	struct tomoyo_number_union *numbers_p
+		= (struct tomoyo_number_union *) (condp + condc);
+	struct tomoyo_name_union *names_p
+		= (struct tomoyo_name_union *) (numbers_p + numbers_count);
+	const struct tomoyo_argv *argv
+		= (const struct tomoyo_argv *) (names_p + names_count);
+	const struct tomoyo_envp *envp
+		= (const struct tomoyo_envp *) (argv + argc);
+
+	for (i = 0; i < numbers_count; i++)
+		tomoyo_put_number_union(numbers_p++);
+	for (i = 0; i < names_count; i++)
+		tomoyo_put_name_union(names_p++);
+	for (i = 0; i < argc; argv++, i++)
+		tomoyo_put_name(argv->value);
+	for (i = 0; i < envc; envp++, i++) {
+		tomoyo_put_name(envp->name);
+		tomoyo_put_name(envp->value);
+	}
+}
+
+/**
+ * tomoyo_del_name - Delete members in "struct tomoyo_name".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_name(struct list_head *element)
+{
+	/* Nothing to do. */
+}
+
+/**
+ * tomoyo_del_path_group - Delete members in "struct tomoyo_path_group".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_path_group(struct list_head *element)
+{
+	struct tomoyo_path_group *member =
+		container_of(element, typeof(*member), head.list);
+
+	tomoyo_put_name(member->member_name);
+}
+
+/**
+ * tomoyo_del_group - Delete "struct tomoyo_group".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_group(struct list_head *element)
+{
+	struct tomoyo_group *group =
+		container_of(element, typeof(*group), head.list);
+
+	tomoyo_put_name(group->group_name);
+}
+
+/**
+ * tomoyo_del_address_group - Delete members in "struct tomoyo_address_group".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_address_group(struct list_head *element)
+{
+	/* Nothing to do. */
+}
+
+/**
+ * tomoyo_del_number_group - Delete members in "struct tomoyo_number_group".
+ *
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static inline void tomoyo_del_number_group(struct list_head *element)
+{
+	/* Nothing to do. */
+}
+
+/**
+ * tomoyo_try_to_gc - Try to kfree() an entry.
+ *
+ * @type:    One of values in "enum tomoyo_policy_id".
+ * @element: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ *
+ * Caller holds tomoyo_policy_lock mutex.
+ */
+static void tomoyo_try_to_gc(const enum tomoyo_policy_id type,
+			     struct list_head *element)
+	__must_hold(&tomoyo_policy_lock)
+{
+	/*
+	 * __list_del_entry() guarantees that the list element became no longer
+	 * reachable from the list which the element was originally on (e.g.
+	 * tomoyo_domain_list). Also, synchronize_srcu() guarantees that the
+	 * list element became no longer referenced by syscall users.
+	 */
+	__list_del_entry(element);
+	mutex_unlock(&tomoyo_policy_lock);
+	synchronize_srcu(&tomoyo_ss);
+	/*
+	 * However, there are two users which may still be using the list
+	 * element. We need to defer until both users forget this element.
+	 *
+	 * Don't kfree() until "struct tomoyo_io_buffer"->r.{domain,group,acl}
+	 * and "struct tomoyo_io_buffer"->w.domain forget this element.
+	 */
+	if (tomoyo_struct_used_by_io_buffer(element))
+		goto reinject;
+	switch (type) {
+	case TOMOYO_ID_TRANSITION_CONTROL:
+		tomoyo_del_transition_control(element);
+		break;
+	case TOMOYO_ID_MANAGER:
+		tomoyo_del_manager(element);
+		break;
+	case TOMOYO_ID_AGGREGATOR:
+		tomoyo_del_aggregator(element);
+		break;
+	case TOMOYO_ID_GROUP:
+		tomoyo_del_group(element);
+		break;
+	case TOMOYO_ID_PATH_GROUP:
+		tomoyo_del_path_group(element);
+		break;
+	case TOMOYO_ID_ADDRESS_GROUP:
+		tomoyo_del_address_group(element);
+		break;
+	case TOMOYO_ID_NUMBER_GROUP:
+		tomoyo_del_number_group(element);
+		break;
+	case TOMOYO_ID_CONDITION:
+		tomoyo_del_condition(element);
+		break;
+	case TOMOYO_ID_NAME:
+		/*
+		 * Don't kfree() until all "struct tomoyo_io_buffer"->r.w[]
+		 * forget this element.
+		 */
+		if (tomoyo_name_used_by_io_buffer
+		    (container_of(element, typeof(struct tomoyo_name),
+				  head.list)->entry.name))
+			goto reinject;
+		tomoyo_del_name(element);
+		break;
+	case TOMOYO_ID_ACL:
+		tomoyo_del_acl(element);
+		break;
+	case TOMOYO_ID_DOMAIN:
+		/*
+		 * Don't kfree() until all "struct cred"->security forget this
+		 * element.
+		 */
+		if (atomic_read(&container_of
+				(element, typeof(struct tomoyo_domain_info),
+				 list)->users))
+			goto reinject;
+		break;
+	case TOMOYO_MAX_POLICY:
+		break;
+	}
+	mutex_lock(&tomoyo_policy_lock);
+	if (type == TOMOYO_ID_DOMAIN)
+		tomoyo_del_domain(element);
+	tomoyo_memory_free(element);
+	return;
+reinject:
+	/*
+	 * We can safely reinject this element here because
+	 * (1) Appending list elements and removing list elements are protected
+	 *     by tomoyo_policy_lock mutex.
+	 * (2) Only this function removes list elements and this function is
+	 *     exclusively executed by tomoyo_gc_mutex mutex.
+	 * are true.
+	 */
+	mutex_lock(&tomoyo_policy_lock);
+	list_add_rcu(element, element->prev);
+}
+
+/**
+ * tomoyo_collect_member - Delete elements with "struct tomoyo_acl_head".
+ *
+ * @id:          One of values in "enum tomoyo_policy_id".
+ * @member_list: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_collect_member(const enum tomoyo_policy_id id,
+				  struct list_head *member_list)
+	__must_hold(&tomoyo_policy_lock)
+{
+	struct tomoyo_acl_head *member;
+	struct tomoyo_acl_head *tmp;
+
+	list_for_each_entry_safe(member, tmp, member_list, list) {
+		if (!member->is_deleted)
+			continue;
+		member->is_deleted = TOMOYO_GC_IN_PROGRESS;
+		tomoyo_try_to_gc(id, &member->list);
+	}
+}
+
+/**
+ * tomoyo_collect_acl - Delete elements in "struct tomoyo_domain_info".
+ *
+ * @list: Pointer to "struct list_head".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_collect_acl(struct list_head *list)
+	__must_hold(&tomoyo_policy_lock)
+{
+	struct tomoyo_acl_info *acl;
+	struct tomoyo_acl_info *tmp;
+
+	list_for_each_entry_safe(acl, tmp, list, list) {
+		if (!acl->is_deleted)
+			continue;
+		acl->is_deleted = TOMOYO_GC_IN_PROGRESS;
+		tomoyo_try_to_gc(TOMOYO_ID_ACL, &acl->list);
+	}
+}
+
+/**
+ * tomoyo_collect_entry - Try to kfree() deleted elements.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_collect_entry(void)
+{
+	int i;
+	enum tomoyo_policy_id id;
+	struct tomoyo_policy_namespace *ns;
+
+	mutex_lock(&tomoyo_policy_lock);
+	{
+		struct tomoyo_domain_info *domain;
+		struct tomoyo_domain_info *tmp;
+
+		list_for_each_entry_safe(domain, tmp, &tomoyo_domain_list,
+					 list) {
+			tomoyo_collect_acl(&domain->acl_info_list);
+			if (!domain->is_deleted || atomic_read(&domain->users))
+				continue;
+			tomoyo_try_to_gc(TOMOYO_ID_DOMAIN, &domain->list);
+		}
+	}
+	list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) {
+		for (id = 0; id < TOMOYO_MAX_POLICY; id++)
+			tomoyo_collect_member(id, &ns->policy_list[id]);
+		for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++)
+			tomoyo_collect_acl(&ns->acl_group[i]);
+	}
+	{
+		struct tomoyo_shared_acl_head *ptr;
+		struct tomoyo_shared_acl_head *tmp;
+
+		list_for_each_entry_safe(ptr, tmp, &tomoyo_condition_list,
+					 list) {
+			if (atomic_read(&ptr->users) > 0)
+				continue;
+			atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS);
+			tomoyo_try_to_gc(TOMOYO_ID_CONDITION, &ptr->list);
+		}
+	}
+	list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) {
+		for (i = 0; i < TOMOYO_MAX_GROUP; i++) {
+			struct list_head *list = &ns->group_list[i];
+			struct tomoyo_group *group;
+			struct tomoyo_group *tmp;
+
+			switch (i) {
+			case 0:
+				id = TOMOYO_ID_PATH_GROUP;
+				break;
+			case 1:
+				id = TOMOYO_ID_NUMBER_GROUP;
+				break;
+			default:
+				id = TOMOYO_ID_ADDRESS_GROUP;
+				break;
+			}
+			list_for_each_entry_safe(group, tmp, list, head.list) {
+				tomoyo_collect_member(id, &group->member_list);
+				if (!list_empty(&group->member_list) ||
+				    atomic_read(&group->head.users) > 0)
+					continue;
+				atomic_set(&group->head.users,
+					   TOMOYO_GC_IN_PROGRESS);
+				tomoyo_try_to_gc(TOMOYO_ID_GROUP,
+						 &group->head.list);
+			}
+		}
+	}
+	for (i = 0; i < TOMOYO_MAX_HASH; i++) {
+		struct list_head *list = &tomoyo_name_list[i];
+		struct tomoyo_shared_acl_head *ptr;
+		struct tomoyo_shared_acl_head *tmp;
+
+		list_for_each_entry_safe(ptr, tmp, list, list) {
+			if (atomic_read(&ptr->users) > 0)
+				continue;
+			atomic_set(&ptr->users, TOMOYO_GC_IN_PROGRESS);
+			tomoyo_try_to_gc(TOMOYO_ID_NAME, &ptr->list);
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+}
+
+/**
+ * tomoyo_gc_thread - Garbage collector thread function.
+ *
+ * @unused: Unused.
+ *
+ * Returns 0.
+ */
+static int tomoyo_gc_thread(void *unused)
+{
+	/* Garbage collector thread is exclusive. */
+	static DEFINE_MUTEX(tomoyo_gc_mutex);
+
+	if (!mutex_trylock(&tomoyo_gc_mutex))
+		goto out;
+	tomoyo_collect_entry();
+	{
+		struct tomoyo_io_buffer *head;
+		struct tomoyo_io_buffer *tmp;
+
+		spin_lock(&tomoyo_io_buffer_list_lock);
+		list_for_each_entry_safe(head, tmp, &tomoyo_io_buffer_list,
+					 list) {
+			if (head->users)
+				continue;
+			list_del(&head->list);
+			/* Safe destruction because no users are left. */
+			context_unsafe(
+				kfree(head->read_buf);
+				kfree(head->write_buf);
+			);
+			kfree(head);
+		}
+		spin_unlock(&tomoyo_io_buffer_list_lock);
+	}
+	mutex_unlock(&tomoyo_gc_mutex);
+out:
+	/* This acts as do_exit(0). */
+	return 0;
+}
+
+/**
+ * tomoyo_notify_gc - Register/unregister /sys/kernel/security/tomoyo/ users.
+ *
+ * @head:        Pointer to "struct tomoyo_io_buffer".
+ * @is_register: True if register, false if unregister.
+ *
+ * Returns nothing.
+ */
+void tomoyo_notify_gc(struct tomoyo_io_buffer *head, const bool is_register)
+{
+	bool is_write = false;
+
+	spin_lock(&tomoyo_io_buffer_list_lock);
+	if (is_register) {
+		head->users = 1;
+		list_add(&head->list, &tomoyo_io_buffer_list);
+	} else {
+		/*
+		 * tomoyo_write_control() can concurrently update write_buf from
+		 * a non-NULL to new non-NULL pointer with io_sem held.
+		 */
+		is_write = data_race(head->write_buf != NULL);
+		if (!--head->users) {
+			list_del(&head->list);
+			/* Safe destruction because no users are left. */
+			context_unsafe(
+				kfree(head->read_buf);
+				kfree(head->write_buf);
+			);
+			kfree(head);
+		}
+	}
+	spin_unlock(&tomoyo_io_buffer_list_lock);
+	if (is_write)
+		kthread_run(tomoyo_gc_thread, NULL, "GC for TOMOYO");
+}
diff --git a/security/tomoyo/group.c b/security/tomoyo/group.c
new file mode 100644
index 000000000..1cecdd797
--- /dev/null
+++ b/security/tomoyo/group.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/group.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/slab.h>
+#include <linux/rculist.h>
+
+#include "common.h"
+
+/**
+ * tomoyo_same_path_group - Check for duplicated "struct tomoyo_path_group" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_path_group(const struct tomoyo_acl_head *a,
+				   const struct tomoyo_acl_head *b)
+{
+	return container_of(a, struct tomoyo_path_group, head)->member_name ==
+		container_of(b, struct tomoyo_path_group, head)->member_name;
+}
+
+/**
+ * tomoyo_same_number_group - Check for duplicated "struct tomoyo_number_group" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_number_group(const struct tomoyo_acl_head *a,
+				     const struct tomoyo_acl_head *b)
+{
+	return !memcmp(&container_of(a, struct tomoyo_number_group, head)
+		       ->number,
+		       &container_of(b, struct tomoyo_number_group, head)
+		       ->number,
+		       sizeof(container_of(a, struct tomoyo_number_group, head)
+			      ->number));
+}
+
+/**
+ * tomoyo_same_address_group - Check for duplicated "struct tomoyo_address_group" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_head".
+ * @b: Pointer to "struct tomoyo_acl_head".
+ *
+ * Returns true if @a == @b, false otherwise.
+ */
+static bool tomoyo_same_address_group(const struct tomoyo_acl_head *a,
+				      const struct tomoyo_acl_head *b)
+{
+	const struct tomoyo_address_group *p1 = container_of(a, typeof(*p1),
+							     head);
+	const struct tomoyo_address_group *p2 = container_of(b, typeof(*p2),
+							     head);
+
+	return tomoyo_same_ipaddr_union(&p1->address, &p2->address);
+}
+
+/**
+ * tomoyo_write_group - Write "struct tomoyo_path_group"/"struct tomoyo_number_group"/"struct tomoyo_address_group" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @type:  Type of this group.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_write_group(struct tomoyo_acl_param *param, const u8 type)
+{
+	struct tomoyo_group *group = tomoyo_get_group(param, type);
+	int error = -EINVAL;
+
+	if (!group)
+		return -ENOMEM;
+	param->list = &group->member_list;
+	if (type == TOMOYO_PATH_GROUP) {
+		struct tomoyo_path_group e = { };
+
+		e.member_name = tomoyo_get_name(tomoyo_read_token(param));
+		if (!e.member_name) {
+			error = -ENOMEM;
+			goto out;
+		}
+		error = tomoyo_update_policy(&e.head, sizeof(e), param,
+					  tomoyo_same_path_group);
+		tomoyo_put_name(e.member_name);
+	} else if (type == TOMOYO_NUMBER_GROUP) {
+		struct tomoyo_number_group e = { };
+
+		if (param->data[0] == '@' ||
+		    !tomoyo_parse_number_union(param, &e.number))
+			goto out;
+		error = tomoyo_update_policy(&e.head, sizeof(e), param,
+					  tomoyo_same_number_group);
+		/*
+		 * tomoyo_put_number_union() is not needed because
+		 * param->data[0] != '@'.
+		 */
+	} else {
+		struct tomoyo_address_group e = { };
+
+		if (param->data[0] == '@' ||
+		    !tomoyo_parse_ipaddr_union(param, &e.address))
+			goto out;
+		error = tomoyo_update_policy(&e.head, sizeof(e), param,
+					     tomoyo_same_address_group);
+	}
+out:
+	tomoyo_put_group(group);
+	return error;
+}
+
+/**
+ * tomoyo_path_matches_group - Check whether the given pathname matches members of the given pathname group.
+ *
+ * @pathname: The name of pathname.
+ * @group:    Pointer to "struct tomoyo_path_group".
+ *
+ * Returns matched member's pathname if @pathname matches pathnames in @group,
+ * NULL otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+const struct tomoyo_path_info *
+tomoyo_path_matches_group(const struct tomoyo_path_info *pathname,
+			  const struct tomoyo_group *group)
+{
+	struct tomoyo_path_group *member;
+
+	list_for_each_entry_rcu(member, &group->member_list, head.list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (member->head.is_deleted)
+			continue;
+		if (!tomoyo_path_matches_pattern(pathname, member->member_name))
+			continue;
+		return member->member_name;
+	}
+	return NULL;
+}
+
+/**
+ * tomoyo_number_matches_group - Check whether the given number matches members of the given number group.
+ *
+ * @min:   Min number.
+ * @max:   Max number.
+ * @group: Pointer to "struct tomoyo_number_group".
+ *
+ * Returns true if @min and @max partially overlaps @group, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+bool tomoyo_number_matches_group(const unsigned long min,
+				 const unsigned long max,
+				 const struct tomoyo_group *group)
+{
+	struct tomoyo_number_group *member;
+	bool matched = false;
+
+	list_for_each_entry_rcu(member, &group->member_list, head.list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (member->head.is_deleted)
+			continue;
+		if (min > member->number.values[1] ||
+		    max < member->number.values[0])
+			continue;
+		matched = true;
+		break;
+	}
+	return matched;
+}
+
+/**
+ * tomoyo_address_matches_group - Check whether the given address matches members of the given address group.
+ *
+ * @is_ipv6: True if @address is an IPv6 address.
+ * @address: An IPv4 or IPv6 address.
+ * @group:   Pointer to "struct tomoyo_address_group".
+ *
+ * Returns true if @address matches addresses in @group group, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+bool tomoyo_address_matches_group(const bool is_ipv6, const __be32 *address,
+				  const struct tomoyo_group *group)
+{
+	struct tomoyo_address_group *member;
+	bool matched = false;
+	const u8 size = is_ipv6 ? 16 : 4;
+
+	list_for_each_entry_rcu(member, &group->member_list, head.list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (member->head.is_deleted)
+			continue;
+		if (member->address.is_ipv6 != is_ipv6)
+			continue;
+		if (memcmp(&member->address.ip[0], address, size) > 0 ||
+		    memcmp(address, &member->address.ip[1], size) > 0)
+			continue;
+		matched = true;
+		break;
+	}
+	return matched;
+}
diff --git a/security/tomoyo/load_policy.c b/security/tomoyo/load_policy.c
new file mode 100644
index 000000000..363b65be8
--- /dev/null
+++ b/security/tomoyo/load_policy.c
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/load_policy.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+
+#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+
+/*
+ * Path to the policy loader. (default = CONFIG_SECURITY_TOMOYO_POLICY_LOADER)
+ */
+static const char *tomoyo_loader;
+
+/**
+ * tomoyo_loader_setup - Set policy loader.
+ *
+ * @str: Program to use as a policy loader (e.g. /sbin/tomoyo-init ).
+ *
+ * Returns 0.
+ */
+static int __init tomoyo_loader_setup(char *str)
+{
+	tomoyo_loader = str;
+	return 1;
+}
+
+__setup("TOMOYO_loader=", tomoyo_loader_setup);
+
+/**
+ * tomoyo_policy_loader_exists - Check whether /sbin/tomoyo-init exists.
+ *
+ * Returns true if /sbin/tomoyo-init exists, false otherwise.
+ */
+static bool tomoyo_policy_loader_exists(void)
+{
+	struct path path;
+
+	if (!tomoyo_loader)
+		tomoyo_loader = CONFIG_SECURITY_TOMOYO_POLICY_LOADER;
+	if (kern_path(tomoyo_loader, LOOKUP_FOLLOW, &path)) {
+		pr_info("Not activating Mandatory Access Control as %s does not exist.\n",
+			tomoyo_loader);
+		return false;
+	}
+	path_put(&path);
+	return true;
+}
+
+/*
+ * Path to the trigger. (default = CONFIG_SECURITY_TOMOYO_ACTIVATION_TRIGGER)
+ */
+static const char *tomoyo_trigger;
+
+/**
+ * tomoyo_trigger_setup - Set trigger for activation.
+ *
+ * @str: Program to use as an activation trigger (e.g. /sbin/init ).
+ *
+ * Returns 0.
+ */
+static int __init tomoyo_trigger_setup(char *str)
+{
+	tomoyo_trigger = str;
+	return 1;
+}
+
+__setup("TOMOYO_trigger=", tomoyo_trigger_setup);
+
+/**
+ * tomoyo_load_policy - Run external policy loader to load policy.
+ *
+ * @filename: The program about to start.
+ *
+ * This function checks whether @filename is /sbin/init , and if so
+ * invoke /sbin/tomoyo-init and wait for the termination of /sbin/tomoyo-init
+ * and then continues invocation of /sbin/init.
+ * /sbin/tomoyo-init reads policy files in /etc/tomoyo/ directory and
+ * writes to /sys/kernel/security/tomoyo/ interfaces.
+ *
+ * Returns nothing.
+ */
+void tomoyo_load_policy(const char *filename)
+{
+	static bool done;
+	char *argv[2];
+	char *envp[3];
+
+	if (tomoyo_policy_loaded || done)
+		return;
+	if (!tomoyo_trigger)
+		tomoyo_trigger = CONFIG_SECURITY_TOMOYO_ACTIVATION_TRIGGER;
+	if (strcmp(filename, tomoyo_trigger))
+		return;
+	if (!tomoyo_policy_loader_exists())
+		return;
+	done = true;
+	pr_info("Calling %s to load policy. Please wait.\n", tomoyo_loader);
+	argv[0] = (char *) tomoyo_loader;
+	argv[1] = NULL;
+	envp[0] = "HOME=/";
+	envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[2] = NULL;
+	call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	tomoyo_check_profile();
+}
+
+#endif
diff --git a/security/tomoyo/memory.c b/security/tomoyo/memory.c
new file mode 100644
index 000000000..1b570bde7
--- /dev/null
+++ b/security/tomoyo/memory.c
@@ -0,0 +1,207 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/memory.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/hash.h>
+#include <linux/slab.h>
+#include "common.h"
+
+/**
+ * tomoyo_warn_oom - Print out of memory warning message.
+ *
+ * @function: Function's name.
+ */
+void tomoyo_warn_oom(const char *function)
+{
+	/* Reduce error messages. */
+	static pid_t tomoyo_last_pid;
+	const pid_t pid = current->pid;
+
+	if (tomoyo_last_pid != pid) {
+		pr_warn("ERROR: Out of memory at %s.\n", function);
+		tomoyo_last_pid = pid;
+	}
+	if (!tomoyo_policy_loaded)
+		panic("MAC Initialization failed.\n");
+}
+
+/* Memoy currently used by policy/audit log/query. */
+unsigned int tomoyo_memory_used[TOMOYO_MAX_MEMORY_STAT];
+/* Memory quota for "policy"/"audit log"/"query". */
+unsigned int tomoyo_memory_quota[TOMOYO_MAX_MEMORY_STAT];
+
+/**
+ * tomoyo_memory_ok - Check memory quota.
+ *
+ * @ptr: Pointer to allocated memory.
+ *
+ * Returns true on success, false otherwise.
+ *
+ * Returns true if @ptr is not NULL and quota not exceeded, false otherwise.
+ *
+ * Caller holds tomoyo_policy_lock mutex.
+ */
+bool tomoyo_memory_ok(void *ptr)
+{
+	if (ptr) {
+		const size_t s = ksize(ptr);
+
+		tomoyo_memory_used[TOMOYO_MEMORY_POLICY] += s;
+		if (!tomoyo_memory_quota[TOMOYO_MEMORY_POLICY] ||
+		    tomoyo_memory_used[TOMOYO_MEMORY_POLICY] <=
+		    tomoyo_memory_quota[TOMOYO_MEMORY_POLICY])
+			return true;
+		tomoyo_memory_used[TOMOYO_MEMORY_POLICY] -= s;
+	}
+	tomoyo_warn_oom(__func__);
+	return false;
+}
+
+/**
+ * tomoyo_commit_ok - Check memory quota.
+ *
+ * @data:   Data to copy from.
+ * @size:   Size in byte.
+ *
+ * Returns pointer to allocated memory on success, NULL otherwise.
+ * @data is zero-cleared on success.
+ *
+ * Caller holds tomoyo_policy_lock mutex.
+ */
+void *tomoyo_commit_ok(void *data, const unsigned int size)
+{
+	void *ptr = kzalloc(size, GFP_NOFS | __GFP_NOWARN);
+
+	if (tomoyo_memory_ok(ptr)) {
+		memmove(ptr, data, size);
+		memset(data, 0, size);
+		return ptr;
+	}
+	kfree(ptr);
+	return NULL;
+}
+
+/**
+ * tomoyo_get_group - Allocate memory for "struct tomoyo_path_group"/"struct tomoyo_number_group".
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @idx:   Index number.
+ *
+ * Returns pointer to "struct tomoyo_group" on success, NULL otherwise.
+ */
+struct tomoyo_group *tomoyo_get_group(struct tomoyo_acl_param *param,
+				      const u8 idx)
+{
+	struct tomoyo_group e = { };
+	struct tomoyo_group *group = NULL;
+	struct list_head *list;
+	const char *group_name = tomoyo_read_token(param);
+	bool found = false;
+
+	if (!tomoyo_correct_word(group_name) || idx >= TOMOYO_MAX_GROUP)
+		return NULL;
+	e.group_name = tomoyo_get_name(group_name);
+	if (!e.group_name)
+		return NULL;
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		goto out;
+	list = &param->ns->group_list[idx];
+	list_for_each_entry(group, list, head.list) {
+		if (e.group_name != group->group_name ||
+		    atomic_read(&group->head.users) == TOMOYO_GC_IN_PROGRESS)
+			continue;
+		atomic_inc(&group->head.users);
+		found = true;
+		break;
+	}
+	if (!found) {
+		struct tomoyo_group *entry = tomoyo_commit_ok(&e, sizeof(e));
+
+		if (entry) {
+			INIT_LIST_HEAD(&entry->member_list);
+			atomic_set(&entry->head.users, 1);
+			list_add_tail_rcu(&entry->head.list, list);
+			group = entry;
+			found = true;
+		}
+	}
+	mutex_unlock(&tomoyo_policy_lock);
+out:
+	tomoyo_put_name(e.group_name);
+	return found ? group : NULL;
+}
+
+/*
+ * tomoyo_name_list is used for holding string data used by TOMOYO.
+ * Since same string data is likely used for multiple times (e.g.
+ * "/lib/libc-2.5.so"), TOMOYO shares string data in the form of
+ * "const struct tomoyo_path_info *".
+ */
+struct list_head tomoyo_name_list[TOMOYO_MAX_HASH];
+
+/**
+ * tomoyo_get_name - Allocate permanent memory for string data.
+ *
+ * @name: The string to store into the permernent memory.
+ *
+ * Returns pointer to "struct tomoyo_path_info" on success, NULL otherwise.
+ */
+const struct tomoyo_path_info *tomoyo_get_name(const char *name)
+{
+	struct tomoyo_name *ptr;
+	unsigned int hash;
+	int len;
+	struct list_head *head;
+
+	if (!name)
+		return NULL;
+	len = strlen(name) + 1;
+	hash = full_name_hash(NULL, (const unsigned char *) name, len - 1);
+	head = &tomoyo_name_list[hash_long(hash, TOMOYO_HASH_BITS)];
+	if (mutex_lock_interruptible(&tomoyo_policy_lock))
+		return NULL;
+	list_for_each_entry(ptr, head, head.list) {
+		if (hash != ptr->entry.hash || strcmp(name, ptr->entry.name) ||
+		    atomic_read(&ptr->head.users) == TOMOYO_GC_IN_PROGRESS)
+			continue;
+		atomic_inc(&ptr->head.users);
+		goto out;
+	}
+	ptr = kzalloc(sizeof(*ptr) + len, GFP_NOFS | __GFP_NOWARN);
+	if (tomoyo_memory_ok(ptr)) {
+		ptr->entry.name = ((char *) ptr) + sizeof(*ptr);
+		memmove((char *) ptr->entry.name, name, len);
+		atomic_set(&ptr->head.users, 1);
+		tomoyo_fill_path_info(&ptr->entry);
+		list_add_tail(&ptr->head.list, head);
+	} else {
+		kfree(ptr);
+		ptr = NULL;
+	}
+out:
+	mutex_unlock(&tomoyo_policy_lock);
+	return ptr ? &ptr->entry : NULL;
+}
+
+/* Initial namespace.*/
+struct tomoyo_policy_namespace tomoyo_kernel_namespace;
+
+/**
+ * tomoyo_mm_init - Initialize mm related code.
+ */
+void __init tomoyo_mm_init(void)
+{
+	int idx;
+
+	for (idx = 0; idx < TOMOYO_MAX_HASH; idx++)
+		INIT_LIST_HEAD(&tomoyo_name_list[idx]);
+	tomoyo_kernel_namespace.name = "<kernel>";
+	tomoyo_init_policy_namespace(&tomoyo_kernel_namespace);
+	tomoyo_kernel_domain.ns = &tomoyo_kernel_namespace;
+	INIT_LIST_HEAD(&tomoyo_kernel_domain.acl_info_list);
+	tomoyo_kernel_domain.domainname = tomoyo_get_name("<kernel>");
+	list_add_tail_rcu(&tomoyo_kernel_domain.list, &tomoyo_domain_list);
+}
diff --git a/security/tomoyo/mount.c b/security/tomoyo/mount.c
new file mode 100644
index 000000000..322dfd188
--- /dev/null
+++ b/security/tomoyo/mount.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/mount.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/slab.h>
+#include <uapi/linux/mount.h>
+#include "common.h"
+
+/* String table for special mount operations. */
+static const char * const tomoyo_mounts[TOMOYO_MAX_SPECIAL_MOUNT] = {
+	[TOMOYO_MOUNT_BIND]            = "--bind",
+	[TOMOYO_MOUNT_MOVE]            = "--move",
+	[TOMOYO_MOUNT_REMOUNT]         = "--remount",
+	[TOMOYO_MOUNT_MAKE_UNBINDABLE] = "--make-unbindable",
+	[TOMOYO_MOUNT_MAKE_PRIVATE]    = "--make-private",
+	[TOMOYO_MOUNT_MAKE_SLAVE]      = "--make-slave",
+	[TOMOYO_MOUNT_MAKE_SHARED]     = "--make-shared",
+};
+
+/**
+ * tomoyo_audit_mount_log - Audit mount log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_mount_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "file mount %s %s %s 0x%lX\n",
+				 r->param.mount.dev->name,
+				 r->param.mount.dir->name,
+				 r->param.mount.type->name,
+				 r->param.mount.flags);
+}
+
+/**
+ * tomoyo_check_mount_acl - Check permission for path path path number operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_mount_acl(struct tomoyo_request_info *r,
+				   const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_mount_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return tomoyo_compare_number_union(r->param.mount.flags,
+					   &acl->flags) &&
+		tomoyo_compare_name_union(r->param.mount.type,
+					  &acl->fs_type) &&
+		tomoyo_compare_name_union(r->param.mount.dir,
+					  &acl->dir_name) &&
+		(!r->param.mount.need_dev ||
+		 tomoyo_compare_name_union(r->param.mount.dev,
+					   &acl->dev_name));
+}
+
+/**
+ * tomoyo_mount_acl - Check permission for mount() operation.
+ *
+ * @r:        Pointer to "struct tomoyo_request_info".
+ * @dev_name: Name of device file. Maybe NULL.
+ * @dir:      Pointer to "struct path".
+ * @type:     Name of filesystem type.
+ * @flags:    Mount options.
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+static int tomoyo_mount_acl(struct tomoyo_request_info *r,
+			    const char *dev_name,
+			    const struct path *dir, const char *type,
+			    unsigned long flags)
+	__must_hold_shared(&tomoyo_ss)
+{
+	struct tomoyo_obj_info obj = { };
+	struct path path;
+	struct file_system_type *fstype = NULL;
+	const char *requested_type = NULL;
+	const char *requested_dir_name = NULL;
+	const char *requested_dev_name = NULL;
+	struct tomoyo_path_info rtype;
+	struct tomoyo_path_info rdev;
+	struct tomoyo_path_info rdir;
+	int need_dev = 0;
+	int error = -ENOMEM;
+
+	r->obj = &obj;
+
+	/* Get fstype. */
+	requested_type = tomoyo_encode(type);
+	if (!requested_type)
+		goto out;
+	rtype.name = requested_type;
+	tomoyo_fill_path_info(&rtype);
+
+	/* Get mount point. */
+	obj.path2 = *dir;
+	requested_dir_name = tomoyo_realpath_from_path(dir);
+	if (!requested_dir_name) {
+		error = -ENOMEM;
+		goto out;
+	}
+	rdir.name = requested_dir_name;
+	tomoyo_fill_path_info(&rdir);
+
+	/* Compare fs name. */
+	if (type == tomoyo_mounts[TOMOYO_MOUNT_REMOUNT]) {
+		/* dev_name is ignored. */
+	} else if (type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_UNBINDABLE] ||
+		   type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_PRIVATE] ||
+		   type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_SLAVE] ||
+		   type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_SHARED]) {
+		/* dev_name is ignored. */
+	} else if (type == tomoyo_mounts[TOMOYO_MOUNT_BIND] ||
+		   type == tomoyo_mounts[TOMOYO_MOUNT_MOVE]) {
+		need_dev = -1; /* dev_name is a directory */
+	} else {
+		fstype = get_fs_type(type);
+		if (!fstype) {
+			error = -ENODEV;
+			goto out;
+		}
+		if (fstype->fs_flags & FS_REQUIRES_DEV)
+			/* dev_name is a block device file. */
+			need_dev = 1;
+	}
+	if (need_dev) {
+		/* Get mount point or device file. */
+		if (!dev_name || kern_path(dev_name, LOOKUP_FOLLOW, &path)) {
+			error = -ENOENT;
+			goto out;
+		}
+		obj.path1 = path;
+		requested_dev_name = tomoyo_realpath_from_path(&path);
+		if (!requested_dev_name) {
+			error = -ENOENT;
+			goto out;
+		}
+	} else {
+		/* Map dev_name to "<NULL>" if no dev_name given. */
+		if (!dev_name)
+			dev_name = "<NULL>";
+		requested_dev_name = tomoyo_encode(dev_name);
+		if (!requested_dev_name) {
+			error = -ENOMEM;
+			goto out;
+		}
+	}
+	rdev.name = requested_dev_name;
+	tomoyo_fill_path_info(&rdev);
+	r->param_type = TOMOYO_TYPE_MOUNT_ACL;
+	r->param.mount.need_dev = need_dev;
+	r->param.mount.dev = &rdev;
+	r->param.mount.dir = &rdir;
+	r->param.mount.type = &rtype;
+	r->param.mount.flags = flags;
+	do {
+		tomoyo_check_acl(r, tomoyo_check_mount_acl);
+		error = tomoyo_audit_mount_log(r);
+	} while (error == TOMOYO_RETRY_REQUEST);
+ out:
+	kfree(requested_dev_name);
+	kfree(requested_dir_name);
+	if (fstype)
+		put_filesystem(fstype);
+	kfree(requested_type);
+	/* Drop refcount obtained by kern_path(). */
+	if (obj.path1.dentry)
+		path_put(&obj.path1);
+	return error;
+}
+
+/**
+ * tomoyo_mount_permission - Check permission for mount() operation.
+ *
+ * @dev_name:  Name of device file. Maybe NULL.
+ * @path:      Pointer to "struct path".
+ * @type:      Name of filesystem type. Maybe NULL.
+ * @flags:     Mount options.
+ * @data_page: Optional data. Maybe NULL.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_mount_permission(const char *dev_name, const struct path *path,
+			    const char *type, unsigned long flags,
+			    void *data_page)
+{
+	struct tomoyo_request_info r;
+	int error;
+	int idx;
+
+	if (tomoyo_init_request_info(&r, NULL, TOMOYO_MAC_FILE_MOUNT)
+	    == TOMOYO_CONFIG_DISABLED)
+		return 0;
+	if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+		flags &= ~MS_MGC_MSK;
+	if (flags & MS_REMOUNT) {
+		type = tomoyo_mounts[TOMOYO_MOUNT_REMOUNT];
+		flags &= ~MS_REMOUNT;
+	} else if (flags & MS_BIND) {
+		type = tomoyo_mounts[TOMOYO_MOUNT_BIND];
+		flags &= ~MS_BIND;
+	} else if (flags & MS_SHARED) {
+		if (flags & (MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
+			return -EINVAL;
+		type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_SHARED];
+		flags &= ~MS_SHARED;
+	} else if (flags & MS_PRIVATE) {
+		if (flags & (MS_SHARED | MS_SLAVE | MS_UNBINDABLE))
+			return -EINVAL;
+		type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_PRIVATE];
+		flags &= ~MS_PRIVATE;
+	} else if (flags & MS_SLAVE) {
+		if (flags & (MS_SHARED | MS_PRIVATE | MS_UNBINDABLE))
+			return -EINVAL;
+		type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_SLAVE];
+		flags &= ~MS_SLAVE;
+	} else if (flags & MS_UNBINDABLE) {
+		if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE))
+			return -EINVAL;
+		type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_UNBINDABLE];
+		flags &= ~MS_UNBINDABLE;
+	} else if (flags & MS_MOVE) {
+		type = tomoyo_mounts[TOMOYO_MOUNT_MOVE];
+		flags &= ~MS_MOVE;
+	}
+	if (!type)
+		type = "<NULL>";
+	idx = tomoyo_read_lock();
+	error = tomoyo_mount_acl(&r, dev_name, path, type, flags);
+	tomoyo_read_unlock(idx);
+	return error;
+}
diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c
new file mode 100644
index 000000000..cfc2a019d
--- /dev/null
+++ b/security/tomoyo/network.c
@@ -0,0 +1,780 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/network.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/slab.h>
+
+/* Structure for holding inet domain socket's address. */
+struct tomoyo_inet_addr_info {
+	__be16 port;           /* In network byte order. */
+	const __be32 *address; /* In network byte order. */
+	bool is_ipv6;
+};
+
+/* Structure for holding unix domain socket's address. */
+struct tomoyo_unix_addr_info {
+	u8 *addr; /* This may not be '\0' terminated string. */
+	unsigned int addr_len;
+};
+
+/* Structure for holding socket address. */
+struct tomoyo_addr_info {
+	u8 protocol;
+	u8 operation;
+	struct tomoyo_inet_addr_info inet;
+	struct tomoyo_unix_addr_info unix0;
+};
+
+/* String table for socket's protocols. */
+const char * const tomoyo_proto_keyword[TOMOYO_SOCK_MAX] = {
+	[SOCK_STREAM]    = "stream",
+	[SOCK_DGRAM]     = "dgram",
+	[SOCK_RAW]       = "raw",
+	[SOCK_SEQPACKET] = "seqpacket",
+	[0] = " ", /* Dummy for avoiding NULL pointer dereference. */
+	[4] = " ", /* Dummy for avoiding NULL pointer dereference. */
+};
+
+/**
+ * tomoyo_parse_ipaddr_union - Parse an IP address.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @ptr:   Pointer to "struct tomoyo_ipaddr_union".
+ *
+ * Returns true on success, false otherwise.
+ */
+bool tomoyo_parse_ipaddr_union(struct tomoyo_acl_param *param,
+			       struct tomoyo_ipaddr_union *ptr)
+{
+	u8 * const min = ptr->ip[0].in6_u.u6_addr8;
+	u8 * const max = ptr->ip[1].in6_u.u6_addr8;
+	char *address = tomoyo_read_token(param);
+	const char *end;
+
+	if (!strchr(address, ':') &&
+	    in4_pton(address, -1, min, '-', &end) > 0) {
+		ptr->is_ipv6 = false;
+		if (!*end)
+			ptr->ip[1].s6_addr32[0] = ptr->ip[0].s6_addr32[0];
+		else if (*end++ != '-' ||
+			 in4_pton(end, -1, max, '\0', &end) <= 0 || *end)
+			return false;
+		return true;
+	}
+	if (in6_pton(address, -1, min, '-', &end) > 0) {
+		ptr->is_ipv6 = true;
+		if (!*end)
+			memmove(max, min, sizeof(u16) * 8);
+		else if (*end++ != '-' ||
+			 in6_pton(end, -1, max, '\0', &end) <= 0 || *end)
+			return false;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * tomoyo_print_ipv4 - Print an IPv4 address.
+ *
+ * @buffer:     Buffer to write to.
+ * @buffer_len: Size of @buffer.
+ * @min_ip:     Pointer to __be32.
+ * @max_ip:     Pointer to __be32.
+ *
+ * Returns nothing.
+ */
+static void tomoyo_print_ipv4(char *buffer, const unsigned int buffer_len,
+			      const __be32 *min_ip, const __be32 *max_ip)
+{
+	snprintf(buffer, buffer_len, "%pI4%c%pI4", min_ip,
+		 *min_ip == *max_ip ? '\0' : '-', max_ip);
+}
+
+/**
+ * tomoyo_print_ipv6 - Print an IPv6 address.
+ *
+ * @buffer:     Buffer to write to.
+ * @buffer_len: Size of @buffer.
+ * @min_ip:     Pointer to "struct in6_addr".
+ * @max_ip:     Pointer to "struct in6_addr".
+ *
+ * Returns nothing.
+ */
+static void tomoyo_print_ipv6(char *buffer, const unsigned int buffer_len,
+			      const struct in6_addr *min_ip,
+			      const struct in6_addr *max_ip)
+{
+	snprintf(buffer, buffer_len, "%pI6c%c%pI6c", min_ip,
+		 !memcmp(min_ip, max_ip, 16) ? '\0' : '-', max_ip);
+}
+
+/**
+ * tomoyo_print_ip - Print an IP address.
+ *
+ * @buf:  Buffer to write to.
+ * @size: Size of @buf.
+ * @ptr:  Pointer to "struct ipaddr_union".
+ *
+ * Returns nothing.
+ */
+void tomoyo_print_ip(char *buf, const unsigned int size,
+		     const struct tomoyo_ipaddr_union *ptr)
+{
+	if (ptr->is_ipv6)
+		tomoyo_print_ipv6(buf, size, &ptr->ip[0], &ptr->ip[1]);
+	else
+		tomoyo_print_ipv4(buf, size, &ptr->ip[0].s6_addr32[0],
+				  &ptr->ip[1].s6_addr32[0]);
+}
+
+/*
+ * Mapping table from "enum tomoyo_network_acl_index" to
+ * "enum tomoyo_mac_index" for inet domain socket.
+ */
+static const u8 tomoyo_inet2mac
+[TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = {
+	[SOCK_STREAM] = {
+		[TOMOYO_NETWORK_BIND]    = TOMOYO_MAC_NETWORK_INET_STREAM_BIND,
+		[TOMOYO_NETWORK_LISTEN]  =
+		TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN,
+		[TOMOYO_NETWORK_CONNECT] =
+		TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT,
+	},
+	[SOCK_DGRAM] = {
+		[TOMOYO_NETWORK_BIND]    = TOMOYO_MAC_NETWORK_INET_DGRAM_BIND,
+		[TOMOYO_NETWORK_SEND]    = TOMOYO_MAC_NETWORK_INET_DGRAM_SEND,
+	},
+	[SOCK_RAW]    = {
+		[TOMOYO_NETWORK_BIND]    = TOMOYO_MAC_NETWORK_INET_RAW_BIND,
+		[TOMOYO_NETWORK_SEND]    = TOMOYO_MAC_NETWORK_INET_RAW_SEND,
+	},
+};
+
+/*
+ * Mapping table from "enum tomoyo_network_acl_index" to
+ * "enum tomoyo_mac_index" for unix domain socket.
+ */
+static const u8 tomoyo_unix2mac
+[TOMOYO_SOCK_MAX][TOMOYO_MAX_NETWORK_OPERATION] = {
+	[SOCK_STREAM] = {
+		[TOMOYO_NETWORK_BIND]    = TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND,
+		[TOMOYO_NETWORK_LISTEN]  =
+		TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN,
+		[TOMOYO_NETWORK_CONNECT] =
+		TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT,
+	},
+	[SOCK_DGRAM] = {
+		[TOMOYO_NETWORK_BIND]    = TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND,
+		[TOMOYO_NETWORK_SEND]    = TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND,
+	},
+	[SOCK_SEQPACKET] = {
+		[TOMOYO_NETWORK_BIND]    =
+		TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND,
+		[TOMOYO_NETWORK_LISTEN]  =
+		TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN,
+		[TOMOYO_NETWORK_CONNECT] =
+		TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT,
+	},
+};
+
+/**
+ * tomoyo_same_inet_acl - Check for duplicated "struct tomoyo_inet_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_inet_acl(const struct tomoyo_acl_info *a,
+				 const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_inet_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_inet_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return p1->protocol == p2->protocol &&
+		tomoyo_same_ipaddr_union(&p1->address, &p2->address) &&
+		tomoyo_same_number_union(&p1->port, &p2->port);
+}
+
+/**
+ * tomoyo_same_unix_acl - Check for duplicated "struct tomoyo_unix_acl" entry.
+ *
+ * @a: Pointer to "struct tomoyo_acl_info".
+ * @b: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if @a == @b except permission bits, false otherwise.
+ */
+static bool tomoyo_same_unix_acl(const struct tomoyo_acl_info *a,
+				 const struct tomoyo_acl_info *b)
+{
+	const struct tomoyo_unix_acl *p1 = container_of(a, typeof(*p1), head);
+	const struct tomoyo_unix_acl *p2 = container_of(b, typeof(*p2), head);
+
+	return p1->protocol == p2->protocol &&
+		tomoyo_same_name_union(&p1->name, &p2->name);
+}
+
+/**
+ * tomoyo_merge_inet_acl - Merge duplicated "struct tomoyo_inet_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_inet_acl(struct tomoyo_acl_info *a,
+				  struct tomoyo_acl_info *b,
+				  const bool is_delete)
+{
+	u8 * const a_perm =
+		&container_of(a, struct tomoyo_inet_acl, head)->perm;
+	u8 perm = READ_ONCE(*a_perm);
+	const u8 b_perm = container_of(b, struct tomoyo_inet_acl, head)->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_merge_unix_acl - Merge duplicated "struct tomoyo_unix_acl" entry.
+ *
+ * @a:         Pointer to "struct tomoyo_acl_info".
+ * @b:         Pointer to "struct tomoyo_acl_info".
+ * @is_delete: True for @a &= ~@b, false for @a |= @b.
+ *
+ * Returns true if @a is empty, false otherwise.
+ */
+static bool tomoyo_merge_unix_acl(struct tomoyo_acl_info *a,
+				  struct tomoyo_acl_info *b,
+				  const bool is_delete)
+{
+	u8 * const a_perm =
+		&container_of(a, struct tomoyo_unix_acl, head)->perm;
+	u8 perm = READ_ONCE(*a_perm);
+	const u8 b_perm = container_of(b, struct tomoyo_unix_acl, head)->perm;
+
+	if (is_delete)
+		perm &= ~b_perm;
+	else
+		perm |= b_perm;
+	WRITE_ONCE(*a_perm, perm);
+	return !perm;
+}
+
+/**
+ * tomoyo_write_inet_network - Write "struct tomoyo_inet_acl" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+int tomoyo_write_inet_network(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_inet_acl e = { .head.type = TOMOYO_TYPE_INET_ACL };
+	int error = -EINVAL;
+	u8 type;
+	const char *protocol = tomoyo_read_token(param);
+	const char *operation = tomoyo_read_token(param);
+
+	for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++)
+		if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol]))
+			break;
+	for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++)
+		if (tomoyo_permstr(operation, tomoyo_socket_keyword[type]))
+			e.perm |= 1 << type;
+	if (e.protocol == TOMOYO_SOCK_MAX || !e.perm)
+		return -EINVAL;
+	if (param->data[0] == '@') {
+		param->data++;
+		e.address.group =
+			tomoyo_get_group(param, TOMOYO_ADDRESS_GROUP);
+		if (!e.address.group)
+			return -ENOMEM;
+	} else {
+		if (!tomoyo_parse_ipaddr_union(param, &e.address))
+			goto out;
+	}
+	if (!tomoyo_parse_number_union(param, &e.port) ||
+	    e.port.values[1] > 65535)
+		goto out;
+	error = tomoyo_update_domain(&e.head, sizeof(e), param,
+				     tomoyo_same_inet_acl,
+				     tomoyo_merge_inet_acl);
+out:
+	tomoyo_put_group(e.address.group);
+	tomoyo_put_number_union(&e.port);
+	return error;
+}
+
+/**
+ * tomoyo_write_unix_network - Write "struct tomoyo_unix_acl" list.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_write_unix_network(struct tomoyo_acl_param *param)
+{
+	struct tomoyo_unix_acl e = { .head.type = TOMOYO_TYPE_UNIX_ACL };
+	int error;
+	u8 type;
+	const char *protocol = tomoyo_read_token(param);
+	const char *operation = tomoyo_read_token(param);
+
+	for (e.protocol = 0; e.protocol < TOMOYO_SOCK_MAX; e.protocol++)
+		if (!strcmp(protocol, tomoyo_proto_keyword[e.protocol]))
+			break;
+	for (type = 0; type < TOMOYO_MAX_NETWORK_OPERATION; type++)
+		if (tomoyo_permstr(operation, tomoyo_socket_keyword[type]))
+			e.perm |= 1 << type;
+	if (e.protocol == TOMOYO_SOCK_MAX || !e.perm)
+		return -EINVAL;
+	if (!tomoyo_parse_name_union(param, &e.name))
+		return -EINVAL;
+	error = tomoyo_update_domain(&e.head, sizeof(e), param,
+				     tomoyo_same_unix_acl,
+				     tomoyo_merge_unix_acl);
+	tomoyo_put_name_union(&e.name);
+	return error;
+}
+
+/**
+ * tomoyo_audit_net_log - Audit network log.
+ *
+ * @r:         Pointer to "struct tomoyo_request_info".
+ * @family:    Name of socket family ("inet" or "unix").
+ * @protocol:  Name of protocol in @family.
+ * @operation: Name of socket operation.
+ * @address:   Name of address.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_net_log(struct tomoyo_request_info *r,
+				const char *family, const u8 protocol,
+				const u8 operation, const char *address)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_supervisor(r, "network %s %s %s %s\n", family,
+				 tomoyo_proto_keyword[protocol],
+				 tomoyo_socket_keyword[operation], address);
+}
+
+/**
+ * tomoyo_audit_inet_log - Audit INET network log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_inet_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	char buf[128];
+	int len;
+	const __be32 *address = r->param.inet_network.address;
+
+	if (r->param.inet_network.is_ipv6)
+		tomoyo_print_ipv6(buf, sizeof(buf), (const struct in6_addr *)
+				  address, (const struct in6_addr *) address);
+	else
+		tomoyo_print_ipv4(buf, sizeof(buf), address, address);
+	len = strlen(buf);
+	snprintf(buf + len, sizeof(buf) - len, " %u",
+		 r->param.inet_network.port);
+	return tomoyo_audit_net_log(r, "inet", r->param.inet_network.protocol,
+				    r->param.inet_network.operation, buf);
+}
+
+/**
+ * tomoyo_audit_unix_log - Audit UNIX network log.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_audit_unix_log(struct tomoyo_request_info *r)
+	__must_hold_shared(&tomoyo_ss)
+{
+	return tomoyo_audit_net_log(r, "unix", r->param.unix_network.protocol,
+				    r->param.unix_network.operation,
+				    r->param.unix_network.address->name);
+}
+
+/**
+ * tomoyo_check_inet_acl - Check permission for inet domain socket operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_inet_acl(struct tomoyo_request_info *r,
+				  const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_inet_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+	const u8 size = r->param.inet_network.is_ipv6 ? 16 : 4;
+
+	if (!(acl->perm & (1 << r->param.inet_network.operation)) ||
+	    !tomoyo_compare_number_union(r->param.inet_network.port,
+					 &acl->port))
+		return false;
+	if (acl->address.group)
+		return tomoyo_address_matches_group
+			(r->param.inet_network.is_ipv6,
+			 r->param.inet_network.address, acl->address.group);
+	return acl->address.is_ipv6 == r->param.inet_network.is_ipv6 &&
+		memcmp(&acl->address.ip[0],
+		       r->param.inet_network.address, size) <= 0 &&
+		memcmp(r->param.inet_network.address,
+		       &acl->address.ip[1], size) <= 0;
+}
+
+/**
+ * tomoyo_check_unix_acl - Check permission for unix domain socket operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_unix_acl(struct tomoyo_request_info *r,
+				  const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_unix_acl *acl =
+		container_of(ptr, typeof(*acl), head);
+
+	return (acl->perm & (1 << r->param.unix_network.operation)) &&
+		tomoyo_compare_name_union(r->param.unix_network.address,
+					  &acl->name);
+}
+
+/**
+ * tomoyo_inet_entry - Check permission for INET network operation.
+ *
+ * @address: Pointer to "struct tomoyo_addr_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_inet_entry(const struct tomoyo_addr_info *address)
+{
+	const int idx = tomoyo_read_lock();
+	struct tomoyo_request_info r;
+	int error = 0;
+	const u8 type = tomoyo_inet2mac[address->protocol][address->operation];
+
+	if (type && tomoyo_init_request_info(&r, NULL, type)
+	    != TOMOYO_CONFIG_DISABLED) {
+		r.param_type = TOMOYO_TYPE_INET_ACL;
+		r.param.inet_network.protocol = address->protocol;
+		r.param.inet_network.operation = address->operation;
+		r.param.inet_network.is_ipv6 = address->inet.is_ipv6;
+		r.param.inet_network.address = address->inet.address;
+		r.param.inet_network.port = ntohs(address->inet.port);
+		do {
+			tomoyo_check_acl(&r, tomoyo_check_inet_acl);
+			error = tomoyo_audit_inet_log(&r);
+		} while (error == TOMOYO_RETRY_REQUEST);
+	}
+	tomoyo_read_unlock(idx);
+	return error;
+}
+
+/**
+ * tomoyo_check_inet_address - Check permission for inet domain socket's operation.
+ *
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ * @port:     Port number.
+ * @address:  Pointer to "struct tomoyo_addr_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_check_inet_address(const struct sockaddr *addr,
+				     const unsigned int addr_len,
+				     const u16 port,
+				     struct tomoyo_addr_info *address)
+{
+	struct tomoyo_inet_addr_info *i = &address->inet;
+
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return 0;
+	switch (addr->sa_family) {
+	case AF_INET6:
+		if (addr_len < SIN6_LEN_RFC2133)
+			goto skip;
+		i->is_ipv6 = true;
+		i->address = (__be32 *)
+			((struct sockaddr_in6 *) addr)->sin6_addr.s6_addr;
+		i->port = ((struct sockaddr_in6 *) addr)->sin6_port;
+		break;
+	case AF_INET:
+		if (addr_len < sizeof(struct sockaddr_in))
+			goto skip;
+		i->is_ipv6 = false;
+		i->address = (__be32 *)
+			&((struct sockaddr_in *) addr)->sin_addr;
+		i->port = ((struct sockaddr_in *) addr)->sin_port;
+		break;
+	default:
+		goto skip;
+	}
+	if (address->protocol == SOCK_RAW)
+		i->port = htons(port);
+	return tomoyo_inet_entry(address);
+skip:
+	return 0;
+}
+
+/**
+ * tomoyo_unix_entry - Check permission for UNIX network operation.
+ *
+ * @address: Pointer to "struct tomoyo_addr_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_unix_entry(const struct tomoyo_addr_info *address)
+{
+	const int idx = tomoyo_read_lock();
+	struct tomoyo_request_info r;
+	int error = 0;
+	const u8 type = tomoyo_unix2mac[address->protocol][address->operation];
+
+	if (type && tomoyo_init_request_info(&r, NULL, type)
+	    != TOMOYO_CONFIG_DISABLED) {
+		char *buf = address->unix0.addr;
+		int len = address->unix0.addr_len - sizeof(sa_family_t);
+
+		if (len <= 0) {
+			buf = "anonymous";
+			len = 9;
+		} else if (buf[0]) {
+			len = strnlen(buf, len);
+		}
+		buf = tomoyo_encode2(buf, len);
+		if (buf) {
+			struct tomoyo_path_info addr;
+
+			addr.name = buf;
+			tomoyo_fill_path_info(&addr);
+			r.param_type = TOMOYO_TYPE_UNIX_ACL;
+			r.param.unix_network.protocol = address->protocol;
+			r.param.unix_network.operation = address->operation;
+			r.param.unix_network.address = &addr;
+			do {
+				tomoyo_check_acl(&r, tomoyo_check_unix_acl);
+				error = tomoyo_audit_unix_log(&r);
+			} while (error == TOMOYO_RETRY_REQUEST);
+			kfree(buf);
+		} else
+			error = -ENOMEM;
+	}
+	tomoyo_read_unlock(idx);
+	return error;
+}
+
+/**
+ * tomoyo_check_unix_address - Check permission for unix domain socket's operation.
+ *
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ * @address:  Pointer to "struct tomoyo_addr_info".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_check_unix_address(struct sockaddr *addr,
+				     const unsigned int addr_len,
+				     struct tomoyo_addr_info *address)
+{
+	struct tomoyo_unix_addr_info *u = &address->unix0;
+
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return 0;
+	if (addr->sa_family != AF_UNIX)
+		return 0;
+	u->addr = ((struct sockaddr_un *) addr)->sun_path;
+	u->addr_len = addr_len;
+	return tomoyo_unix_entry(address);
+}
+
+/**
+ * tomoyo_kernel_service - Check whether I'm kernel service or not.
+ *
+ * Returns true if I'm kernel service, false otherwise.
+ */
+static bool tomoyo_kernel_service(void)
+{
+	/* Nothing to do if I am a kernel service. */
+	return current->flags & PF_KTHREAD;
+}
+
+/**
+ * tomoyo_sock_family - Get socket's family.
+ *
+ * @sk: Pointer to "struct sock".
+ *
+ * Returns one of PF_INET, PF_INET6, PF_UNIX or 0.
+ */
+static u8 tomoyo_sock_family(struct sock *sk)
+{
+	u8 family;
+
+	if (tomoyo_kernel_service())
+		return 0;
+	family = sk->sk_family;
+	switch (family) {
+	case PF_INET:
+	case PF_INET6:
+	case PF_UNIX:
+		return family;
+	default:
+		return 0;
+	}
+}
+
+/**
+ * tomoyo_socket_listen_permission - Check permission for listening a socket.
+ *
+ * @sock: Pointer to "struct socket".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_socket_listen_permission(struct socket *sock)
+{
+	struct tomoyo_addr_info address;
+	const u8 family = tomoyo_sock_family(sock->sk);
+	const unsigned int type = sock->type;
+	struct sockaddr_storage addr;
+	int addr_len;
+
+	if (!family || (type != SOCK_STREAM && type != SOCK_SEQPACKET))
+		return 0;
+	{
+		const int error = sock->ops->getname(sock, (struct sockaddr *)
+						     &addr, 0);
+
+		if (error < 0)
+			return error;
+		addr_len = error;
+	}
+	address.protocol = type;
+	address.operation = TOMOYO_NETWORK_LISTEN;
+	if (family == PF_UNIX)
+		return tomoyo_check_unix_address((struct sockaddr *) &addr,
+						 addr_len, &address);
+	return tomoyo_check_inet_address((struct sockaddr *) &addr, addr_len,
+					 0, &address);
+}
+
+/**
+ * tomoyo_socket_connect_permission - Check permission for setting the remote address of a socket.
+ *
+ * @sock:     Pointer to "struct socket".
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_socket_connect_permission(struct socket *sock,
+				     struct sockaddr *addr, int addr_len)
+{
+	struct tomoyo_addr_info address;
+	const u8 family = tomoyo_sock_family(sock->sk);
+	const unsigned int type = sock->type;
+
+	if (!family)
+		return 0;
+	address.protocol = type;
+	switch (type) {
+	case SOCK_DGRAM:
+	case SOCK_RAW:
+		address.operation = TOMOYO_NETWORK_SEND;
+		break;
+	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
+		address.operation = TOMOYO_NETWORK_CONNECT;
+		break;
+	default:
+		return 0;
+	}
+	if (family == PF_UNIX)
+		return tomoyo_check_unix_address(addr, addr_len, &address);
+	return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol,
+					 &address);
+}
+
+/**
+ * tomoyo_socket_bind_permission - Check permission for setting the local address of a socket.
+ *
+ * @sock:     Pointer to "struct socket".
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_socket_bind_permission(struct socket *sock, struct sockaddr *addr,
+				  int addr_len)
+{
+	struct tomoyo_addr_info address;
+	const u8 family = tomoyo_sock_family(sock->sk);
+	const unsigned int type = sock->type;
+
+	if (!family)
+		return 0;
+	switch (type) {
+	case SOCK_STREAM:
+	case SOCK_DGRAM:
+	case SOCK_RAW:
+	case SOCK_SEQPACKET:
+		address.protocol = type;
+		address.operation = TOMOYO_NETWORK_BIND;
+		break;
+	default:
+		return 0;
+	}
+	if (family == PF_UNIX)
+		return tomoyo_check_unix_address(addr, addr_len, &address);
+	return tomoyo_check_inet_address(addr, addr_len, sock->sk->sk_protocol,
+					 &address);
+}
+
+/**
+ * tomoyo_socket_sendmsg_permission - Check permission for sending a datagram.
+ *
+ * @sock: Pointer to "struct socket".
+ * @msg:  Pointer to "struct msghdr".
+ * @size: Unused.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+int tomoyo_socket_sendmsg_permission(struct socket *sock, struct msghdr *msg,
+				     int size)
+{
+	struct tomoyo_addr_info address;
+	const u8 family = tomoyo_sock_family(sock->sk);
+	const unsigned int type = sock->type;
+
+	if (!msg->msg_name || !family ||
+	    (type != SOCK_DGRAM && type != SOCK_RAW))
+		return 0;
+	address.protocol = type;
+	address.operation = TOMOYO_NETWORK_SEND;
+	if (family == PF_UNIX)
+		return tomoyo_check_unix_address((struct sockaddr *)
+						 msg->msg_name,
+						 msg->msg_namelen, &address);
+	return tomoyo_check_inet_address((struct sockaddr *) msg->msg_name,
+					 msg->msg_namelen,
+					 sock->sk->sk_protocol, &address);
+}
diff --git a/security/tomoyo/policy/exception_policy.conf.default b/security/tomoyo/policy/exception_policy.conf.default
new file mode 100644
index 000000000..2678df496
--- /dev/null
+++ b/security/tomoyo/policy/exception_policy.conf.default
@@ -0,0 +1,2 @@
+initialize_domain /sbin/modprobe from any
+initialize_domain /sbin/hotplug from any
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
new file mode 100644
index 000000000..1c483ee7f
--- /dev/null
+++ b/security/tomoyo/realpath.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/realpath.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include "common.h"
+#include <linux/magic.h>
+#include <linux/proc_fs.h>
+
+/**
+ * tomoyo_encode2 - Encode binary string to ascii string.
+ *
+ * @str:     String in binary format.
+ * @str_len: Size of @str in byte.
+ *
+ * Returns pointer to @str in ascii format on success, NULL otherwise.
+ *
+ * This function uses kzalloc(), so caller must kfree() if this function
+ * didn't return NULL.
+ */
+char *tomoyo_encode2(const char *str, int str_len)
+{
+	int i;
+	int len = 0;
+	const char *p = str;
+	char *cp;
+	char *cp0;
+
+	if (!p)
+		return NULL;
+	for (i = 0; i < str_len; i++) {
+		const unsigned char c = p[i];
+
+		if (c == '\\')
+			len += 2;
+		else if (c > ' ' && c < 127)
+			len++;
+		else
+			len += 4;
+	}
+	len++;
+	/* Reserve space for appending "/". */
+	cp = kzalloc(len + 10, GFP_NOFS);
+	if (!cp)
+		return NULL;
+	cp0 = cp;
+	p = str;
+	for (i = 0; i < str_len; i++) {
+		const unsigned char c = p[i];
+
+		if (c == '\\') {
+			*cp++ = '\\';
+			*cp++ = '\\';
+		} else if (c > ' ' && c < 127) {
+			*cp++ = c;
+		} else {
+			*cp++ = '\\';
+			*cp++ = (c >> 6) + '0';
+			*cp++ = ((c >> 3) & 7) + '0';
+			*cp++ = (c & 7) + '0';
+		}
+	}
+	return cp0;
+}
+
+/**
+ * tomoyo_encode - Encode binary string to ascii string.
+ *
+ * @str: String in binary format.
+ *
+ * Returns pointer to @str in ascii format on success, NULL otherwise.
+ *
+ * This function uses kzalloc(), so caller must kfree() if this function
+ * didn't return NULL.
+ */
+char *tomoyo_encode(const char *str)
+{
+	return str ? tomoyo_encode2(str, strlen(str)) : NULL;
+}
+
+/**
+ * tomoyo_get_absolute_path - Get the path of a dentry but ignores chroot'ed root.
+ *
+ * @path:   Pointer to "struct path".
+ * @buffer: Pointer to buffer to return value in.
+ * @buflen: Sizeof @buffer.
+ *
+ * Returns the buffer on success, an error code otherwise.
+ *
+ * If dentry is a directory, trailing '/' is appended.
+ */
+static char *tomoyo_get_absolute_path(const struct path *path, char * const buffer,
+				      const int buflen)
+{
+	char *pos = ERR_PTR(-ENOMEM);
+
+	if (buflen >= 256) {
+		/* go to whatever namespace root we are under */
+		pos = d_absolute_path(path, buffer, buflen - 1);
+		if (!IS_ERR(pos) && *pos == '/' && pos[1]) {
+			struct inode *inode = d_backing_inode(path->dentry);
+
+			if (inode && S_ISDIR(inode->i_mode)) {
+				buffer[buflen - 2] = '/';
+				buffer[buflen - 1] = '\0';
+			}
+		}
+	}
+	return pos;
+}
+
+/**
+ * tomoyo_get_dentry_path - Get the path of a dentry.
+ *
+ * @dentry: Pointer to "struct dentry".
+ * @buffer: Pointer to buffer to return value in.
+ * @buflen: Sizeof @buffer.
+ *
+ * Returns the buffer on success, an error code otherwise.
+ *
+ * If dentry is a directory, trailing '/' is appended.
+ */
+static char *tomoyo_get_dentry_path(struct dentry *dentry, char * const buffer,
+				    const int buflen)
+{
+	char *pos = ERR_PTR(-ENOMEM);
+
+	if (buflen >= 256) {
+		pos = dentry_path_raw(dentry, buffer, buflen - 1);
+		if (!IS_ERR(pos) && *pos == '/' && pos[1]) {
+			struct inode *inode = d_backing_inode(dentry);
+
+			if (inode && S_ISDIR(inode->i_mode)) {
+				buffer[buflen - 2] = '/';
+				buffer[buflen - 1] = '\0';
+			}
+		}
+	}
+	return pos;
+}
+
+/**
+ * tomoyo_get_local_path - Get the path of a dentry.
+ *
+ * @dentry: Pointer to "struct dentry".
+ * @buffer: Pointer to buffer to return value in.
+ * @buflen: Sizeof @buffer.
+ *
+ * Returns the buffer on success, an error code otherwise.
+ */
+static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer,
+				   const int buflen)
+{
+	struct super_block *sb = dentry->d_sb;
+	char *pos = tomoyo_get_dentry_path(dentry, buffer, buflen);
+
+	if (IS_ERR(pos))
+		return pos;
+	/* Convert from $PID to self if $PID is current thread. */
+	if (sb->s_magic == PROC_SUPER_MAGIC && *pos == '/') {
+		char *ep;
+		const pid_t pid = (pid_t) simple_strtoul(pos + 1, &ep, 10);
+		struct pid_namespace *proc_pidns = proc_pid_ns(sb);
+
+		if (*ep == '/' && pid && pid ==
+		    task_tgid_nr_ns(current, proc_pidns)) {
+			pos = ep - 5;
+			if (pos < buffer)
+				goto out;
+			memmove(pos, "/self", 5);
+		}
+		goto prepend_filesystem_name;
+	}
+	/* Use filesystem name for unnamed devices. */
+	if (!MAJOR(sb->s_dev))
+		goto prepend_filesystem_name;
+	{
+		struct inode *inode = d_backing_inode(sb->s_root);
+
+		/*
+		 * Use filesystem name if filesystem does not support rename()
+		 * operation.
+		 */
+		if (!inode->i_op->rename)
+			goto prepend_filesystem_name;
+	}
+	/* Prepend device name. */
+	{
+		char name[64];
+		int name_len;
+		const dev_t dev = sb->s_dev;
+
+		name[sizeof(name) - 1] = '\0';
+		snprintf(name, sizeof(name) - 1, "dev(%u,%u):", MAJOR(dev),
+			 MINOR(dev));
+		name_len = strlen(name);
+		pos -= name_len;
+		if (pos < buffer)
+			goto out;
+		memmove(pos, name, name_len);
+		return pos;
+	}
+	/* Prepend filesystem name. */
+prepend_filesystem_name:
+	{
+		const char *name = sb->s_type->name;
+		const int name_len = strlen(name);
+
+		pos -= name_len + 1;
+		if (pos < buffer)
+			goto out;
+		memmove(pos, name, name_len);
+		pos[name_len] = ':';
+	}
+	return pos;
+out:
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root.
+ *
+ * @path: Pointer to "struct path".
+ *
+ * Returns the realpath of the given @path on success, NULL otherwise.
+ *
+ * If dentry is a directory, trailing '/' is appended.
+ * Characters out of 0x20 < c < 0x7F range are converted to
+ * \ooo style octal string.
+ * Character \ is converted to \\ string.
+ *
+ * These functions use kzalloc(), so the caller must call kfree()
+ * if these functions didn't return NULL.
+ */
+char *tomoyo_realpath_from_path(const struct path *path)
+{
+	char *buf = NULL;
+	char *name = NULL;
+	unsigned int buf_len = PAGE_SIZE / 2;
+	struct dentry *dentry = path->dentry;
+	struct super_block *sb = dentry->d_sb;
+
+	while (1) {
+		char *pos;
+		struct inode *inode;
+
+		buf_len <<= 1;
+		kfree(buf);
+		buf = kmalloc(buf_len, GFP_NOFS);
+		if (!buf)
+			break;
+		/* To make sure that pos is '\0' terminated. */
+		buf[buf_len - 1] = '\0';
+		/* For "pipe:[\$]" and "socket:[\$]". */
+		if (dentry->d_op && dentry->d_op->d_dname) {
+			pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1);
+			goto encode;
+		}
+		inode = d_backing_inode(sb->s_root);
+		/*
+		 * Get local name for filesystems without rename() operation
+		 */
+		if ((!inode->i_op->rename &&
+		     !(sb->s_type->fs_flags & FS_REQUIRES_DEV)))
+			pos = tomoyo_get_local_path(path->dentry, buf,
+						    buf_len - 1);
+		/* Get absolute name for the rest. */
+		else {
+			pos = tomoyo_get_absolute_path(path, buf, buf_len - 1);
+			/*
+			 * Fall back to local name if absolute name is not
+			 * available.
+			 */
+			if (pos == ERR_PTR(-EINVAL))
+				pos = tomoyo_get_local_path(path->dentry, buf,
+							    buf_len - 1);
+		}
+encode:
+		if (IS_ERR(pos))
+			continue;
+		name = tomoyo_encode(pos);
+		break;
+	}
+	kfree(buf);
+	if (!name)
+		tomoyo_warn_oom(__func__);
+	return name;
+}
+
+/**
+ * tomoyo_realpath_nofollow - Get realpath of a pathname.
+ *
+ * @pathname: The pathname to solve.
+ *
+ * Returns the realpath of @pathname on success, NULL otherwise.
+ */
+char *tomoyo_realpath_nofollow(const char *pathname)
+{
+	struct path path;
+
+	if (pathname && kern_path(pathname, 0, &path) == 0) {
+		char *buf = tomoyo_realpath_from_path(&path);
+
+		path_put(&path);
+		return buf;
+	}
+	return NULL;
+}
diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c
new file mode 100644
index 000000000..33933645f
--- /dev/null
+++ b/security/tomoyo/securityfs_if.c
@@ -0,0 +1,271 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/securityfs_if.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/security.h>
+#include "common.h"
+
+/**
+ * tomoyo_check_task_acl - Check permission for task operation.
+ *
+ * @r:   Pointer to "struct tomoyo_request_info".
+ * @ptr: Pointer to "struct tomoyo_acl_info".
+ *
+ * Returns true if granted, false otherwise.
+ */
+static bool tomoyo_check_task_acl(struct tomoyo_request_info *r,
+				  const struct tomoyo_acl_info *ptr)
+{
+	const struct tomoyo_task_acl *acl = container_of(ptr, typeof(*acl),
+							 head);
+
+	return !tomoyo_pathcmp(r->param.task.domainname, acl->domainname);
+}
+
+/**
+ * tomoyo_write_self - write() for /sys/kernel/security/tomoyo/self_domain interface.
+ *
+ * @file:  Pointer to "struct file".
+ * @buf:   Domainname to transit to.
+ * @count: Size of @buf.
+ * @ppos:  Unused.
+ *
+ * Returns @count on success, negative value otherwise.
+ *
+ * If domain transition was permitted but the domain transition failed, this
+ * function returns error rather than terminating current thread with SIGKILL.
+ */
+static ssize_t tomoyo_write_self(struct file *file, const char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	char *data;
+	int error;
+
+	if (!count || count >= TOMOYO_EXEC_TMPSIZE - 10)
+		return -ENOMEM;
+	data = memdup_user_nul(buf, count);
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+	tomoyo_normalize_line(data);
+	if (tomoyo_correct_domain(data)) {
+		const int idx = tomoyo_read_lock();
+		struct tomoyo_path_info name;
+		struct tomoyo_request_info r;
+
+		name.name = data;
+		tomoyo_fill_path_info(&name);
+		/* Check "task manual_domain_transition" permission. */
+		tomoyo_init_request_info(&r, NULL, TOMOYO_MAC_FILE_EXECUTE);
+		r.param_type = TOMOYO_TYPE_MANUAL_TASK_ACL;
+		r.param.task.domainname = &name;
+		tomoyo_check_acl(&r, tomoyo_check_task_acl);
+		if (!r.granted)
+			error = -EPERM;
+		else {
+			struct tomoyo_domain_info *new_domain =
+				tomoyo_assign_domain(data, true);
+			if (!new_domain) {
+				error = -ENOENT;
+			} else {
+				struct tomoyo_task *s = tomoyo_task(current);
+				struct tomoyo_domain_info *old_domain =
+					s->domain_info;
+
+				s->domain_info = new_domain;
+				atomic_inc(&new_domain->users);
+				atomic_dec(&old_domain->users);
+				error = 0;
+			}
+		}
+		tomoyo_read_unlock(idx);
+	} else
+		error = -EINVAL;
+	kfree(data);
+	return error ? error : count;
+}
+
+/**
+ * tomoyo_read_self - read() for /sys/kernel/security/tomoyo/self_domain interface.
+ *
+ * @file:  Pointer to "struct file".
+ * @buf:   Domainname which current thread belongs to.
+ * @count: Size of @buf.
+ * @ppos:  Bytes read by now.
+ *
+ * Returns read size on success, negative value otherwise.
+ */
+static ssize_t tomoyo_read_self(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	const char *domain = tomoyo_domain()->domainname->name;
+	loff_t len = strlen(domain);
+	loff_t pos = *ppos;
+
+	if (pos >= len || !count)
+		return 0;
+	len -= pos;
+	if (count < len)
+		len = count;
+	if (copy_to_user(buf, domain + pos, len))
+		return -EFAULT;
+	*ppos += len;
+	return len;
+}
+
+/* Operations for /sys/kernel/security/tomoyo/self_domain interface. */
+static const struct file_operations tomoyo_self_operations = {
+	.write = tomoyo_write_self,
+	.read  = tomoyo_read_self,
+};
+
+/**
+ * tomoyo_open - open() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @inode: Pointer to "struct inode".
+ * @file:  Pointer to "struct file".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_open(struct inode *inode, struct file *file)
+{
+	const u8 key = (uintptr_t) file_inode(file)->i_private;
+
+	return tomoyo_open_control(key, file);
+}
+
+/**
+ * tomoyo_release - close() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @inode: Pointer to "struct inode".
+ * @file:  Pointer to "struct file".
+ *
+ */
+static int tomoyo_release(struct inode *inode, struct file *file)
+{
+	tomoyo_close_control(file->private_data);
+	return 0;
+}
+
+/**
+ * tomoyo_poll - poll() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @file: Pointer to "struct file".
+ * @wait: Pointer to "poll_table". Maybe NULL.
+ *
+ * Returns EPOLLIN | EPOLLRDNORM | EPOLLOUT | EPOLLWRNORM if ready to read/write,
+ * EPOLLOUT | EPOLLWRNORM otherwise.
+ */
+static __poll_t tomoyo_poll(struct file *file, poll_table *wait)
+{
+	return tomoyo_poll_control(file, wait);
+}
+
+/**
+ * tomoyo_read - read() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @file:  Pointer to "struct file".
+ * @buf:   Pointer to buffer.
+ * @count: Size of @buf.
+ * @ppos:  Unused.
+ *
+ * Returns bytes read on success, negative value otherwise.
+ */
+static ssize_t tomoyo_read(struct file *file, char __user *buf, size_t count,
+			   loff_t *ppos)
+{
+	return tomoyo_read_control(file->private_data, buf, count);
+}
+
+/**
+ * tomoyo_write - write() for /sys/kernel/security/tomoyo/ interface.
+ *
+ * @file:  Pointer to "struct file".
+ * @buf:   Pointer to buffer.
+ * @count: Size of @buf.
+ * @ppos:  Unused.
+ *
+ * Returns @count on success, negative value otherwise.
+ */
+static ssize_t tomoyo_write(struct file *file, const char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	return tomoyo_write_control(file->private_data, buf, count);
+}
+
+/*
+ * tomoyo_operations is a "struct file_operations" which is used for handling
+ * /sys/kernel/security/tomoyo/ interface.
+ *
+ * Some files under /sys/kernel/security/tomoyo/ directory accept open(O_RDWR).
+ * See tomoyo_io_buffer for internals.
+ */
+static const struct file_operations tomoyo_operations = {
+	.open    = tomoyo_open,
+	.release = tomoyo_release,
+	.poll    = tomoyo_poll,
+	.read    = tomoyo_read,
+	.write   = tomoyo_write,
+	.llseek  = noop_llseek,
+};
+
+/**
+ * tomoyo_create_entry - Create interface files under /sys/kernel/security/tomoyo/ directory.
+ *
+ * @name:   The name of the interface file.
+ * @mode:   The permission of the interface file.
+ * @parent: The parent directory.
+ * @key:    Type of interface.
+ *
+ * Returns nothing.
+ */
+static void __init tomoyo_create_entry(const char *name, const umode_t mode,
+				       struct dentry *parent, const u8 key)
+{
+	securityfs_create_file(name, mode, parent, (void *) (uintptr_t) key,
+			       &tomoyo_operations);
+}
+
+/**
+ * tomoyo_interface_init - Initialize /sys/kernel/security/tomoyo/ interface.
+ *
+ * Returns 0.
+ */
+int __init tomoyo_interface_init(void)
+{
+	struct tomoyo_domain_info *domain;
+	struct dentry *tomoyo_dir;
+
+	if (!tomoyo_enabled)
+		return 0;
+	domain = tomoyo_domain();
+	/* Don't create securityfs entries unless registered. */
+	if (domain != &tomoyo_kernel_domain)
+		return 0;
+
+	tomoyo_dir = securityfs_create_dir("tomoyo", NULL);
+	tomoyo_create_entry("query",            0600, tomoyo_dir,
+			    TOMOYO_QUERY);
+	tomoyo_create_entry("domain_policy",    0600, tomoyo_dir,
+			    TOMOYO_DOMAINPOLICY);
+	tomoyo_create_entry("exception_policy", 0600, tomoyo_dir,
+			    TOMOYO_EXCEPTIONPOLICY);
+	tomoyo_create_entry("audit",            0400, tomoyo_dir,
+			    TOMOYO_AUDIT);
+	tomoyo_create_entry(".process_status",  0600, tomoyo_dir,
+			    TOMOYO_PROCESS_STATUS);
+	tomoyo_create_entry("stat",             0644, tomoyo_dir,
+			    TOMOYO_STAT);
+	tomoyo_create_entry("profile",          0600, tomoyo_dir,
+			    TOMOYO_PROFILE);
+	tomoyo_create_entry("manager",          0600, tomoyo_dir,
+			    TOMOYO_MANAGER);
+	tomoyo_create_entry("version",          0400, tomoyo_dir,
+			    TOMOYO_VERSION);
+	securityfs_create_file("self_domain", 0666, tomoyo_dir, NULL,
+			       &tomoyo_self_operations);
+	tomoyo_load_builtin_policy();
+	return 0;
+}
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
new file mode 100644
index 000000000..c66e02ed8
--- /dev/null
+++ b/security/tomoyo/tomoyo.c
@@ -0,0 +1,621 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/tomoyo.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/lsm_hooks.h>
+#include <uapi/linux/lsm.h>
+#include "common.h"
+
+/**
+ * tomoyo_domain - Get "struct tomoyo_domain_info" for current thread.
+ *
+ * Returns pointer to "struct tomoyo_domain_info" for current thread.
+ */
+struct tomoyo_domain_info *tomoyo_domain(void)
+{
+	struct tomoyo_task *s = tomoyo_task(current);
+
+	if (s->old_domain_info && !current->in_execve) {
+		atomic_dec(&s->old_domain_info->users);
+		s->old_domain_info = NULL;
+	}
+	return s->domain_info;
+}
+
+/**
+ * tomoyo_cred_prepare - Target for security_prepare_creds().
+ *
+ * @new: Pointer to "struct cred".
+ * @old: Pointer to "struct cred".
+ * @gfp: Memory allocation flags.
+ *
+ * Returns 0.
+ */
+static int tomoyo_cred_prepare(struct cred *new, const struct cred *old,
+			       gfp_t gfp)
+{
+	/* Restore old_domain_info saved by previous execve() request. */
+	struct tomoyo_task *s = tomoyo_task(current);
+
+	if (s->old_domain_info && !current->in_execve) {
+		atomic_dec(&s->domain_info->users);
+		s->domain_info = s->old_domain_info;
+		s->old_domain_info = NULL;
+	}
+	return 0;
+}
+
+/**
+ * tomoyo_bprm_committed_creds - Target for security_bprm_committed_creds().
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ */
+static void tomoyo_bprm_committed_creds(const struct linux_binprm *bprm)
+{
+	/* Clear old_domain_info saved by execve() request. */
+	struct tomoyo_task *s = tomoyo_task(current);
+
+	atomic_dec(&s->old_domain_info->users);
+	s->old_domain_info = NULL;
+}
+
+#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+/**
+ * tomoyo_bprm_creds_for_exec - Target for security_bprm_creds_for_exec().
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ *
+ * Returns 0.
+ */
+static int tomoyo_bprm_creds_for_exec(struct linux_binprm *bprm)
+{
+	/*
+	 * Load policy if /sbin/tomoyo-init exists and /sbin/init is requested
+	 * for the first time.
+	 */
+	if (!tomoyo_policy_loaded)
+		tomoyo_load_policy(bprm->filename);
+	return 0;
+}
+#endif
+
+/**
+ * tomoyo_bprm_check_security - Target for security_bprm_check().
+ *
+ * @bprm: Pointer to "struct linux_binprm".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_bprm_check_security(struct linux_binprm *bprm)
+{
+	struct tomoyo_task *s = tomoyo_task(current);
+
+	/*
+	 * Execute permission is checked against pathname passed to execve()
+	 * using current domain.
+	 */
+	if (!s->old_domain_info) {
+		const int idx = tomoyo_read_lock();
+		const int err = tomoyo_find_next_domain(bprm);
+
+		tomoyo_read_unlock(idx);
+		return err;
+	}
+	/*
+	 * Read permission is checked against interpreters using next domain.
+	 */
+	return tomoyo_check_open_permission(s->domain_info,
+					    &bprm->file->f_path, O_RDONLY);
+}
+
+/**
+ * tomoyo_inode_getattr - Target for security_inode_getattr().
+ *
+ * @path: Pointer to "struct path".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_inode_getattr(const struct path *path)
+{
+	return tomoyo_path_perm(TOMOYO_TYPE_GETATTR, path, NULL);
+}
+
+/**
+ * tomoyo_path_truncate - Target for security_path_truncate().
+ *
+ * @path: Pointer to "struct path".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_truncate(const struct path *path)
+{
+	return tomoyo_path_perm(TOMOYO_TYPE_TRUNCATE, path, NULL);
+}
+
+/**
+ * tomoyo_file_truncate - Target for security_file_truncate().
+ *
+ * @file: Pointer to "struct file".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_file_truncate(struct file *file)
+{
+	return tomoyo_path_truncate(&file->f_path);
+}
+
+/**
+ * tomoyo_path_unlink - Target for security_path_unlink().
+ *
+ * @parent: Pointer to "struct path".
+ * @dentry: Pointer to "struct dentry".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_unlink(const struct path *parent, struct dentry *dentry)
+{
+	struct path path = { .mnt = parent->mnt, .dentry = dentry };
+
+	return tomoyo_path_perm(TOMOYO_TYPE_UNLINK, &path, NULL);
+}
+
+/**
+ * tomoyo_path_mkdir - Target for security_path_mkdir().
+ *
+ * @parent: Pointer to "struct path".
+ * @dentry: Pointer to "struct dentry".
+ * @mode:   DAC permission mode.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_mkdir(const struct path *parent, struct dentry *dentry,
+			     umode_t mode)
+{
+	struct path path = { .mnt = parent->mnt, .dentry = dentry };
+
+	return tomoyo_path_number_perm(TOMOYO_TYPE_MKDIR, &path,
+				       mode & S_IALLUGO);
+}
+
+/**
+ * tomoyo_path_rmdir - Target for security_path_rmdir().
+ *
+ * @parent: Pointer to "struct path".
+ * @dentry: Pointer to "struct dentry".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_rmdir(const struct path *parent, struct dentry *dentry)
+{
+	struct path path = { .mnt = parent->mnt, .dentry = dentry };
+
+	return tomoyo_path_perm(TOMOYO_TYPE_RMDIR, &path, NULL);
+}
+
+/**
+ * tomoyo_path_symlink - Target for security_path_symlink().
+ *
+ * @parent:   Pointer to "struct path".
+ * @dentry:   Pointer to "struct dentry".
+ * @old_name: Symlink's content.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_symlink(const struct path *parent, struct dentry *dentry,
+			       const char *old_name)
+{
+	struct path path = { .mnt = parent->mnt, .dentry = dentry };
+
+	return tomoyo_path_perm(TOMOYO_TYPE_SYMLINK, &path, old_name);
+}
+
+/**
+ * tomoyo_path_mknod - Target for security_path_mknod().
+ *
+ * @parent: Pointer to "struct path".
+ * @dentry: Pointer to "struct dentry".
+ * @mode:   DAC permission mode.
+ * @dev:    Device attributes.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_mknod(const struct path *parent, struct dentry *dentry,
+			     umode_t mode, unsigned int dev)
+{
+	struct path path = { .mnt = parent->mnt, .dentry = dentry };
+	int type = TOMOYO_TYPE_CREATE;
+	const unsigned int perm = mode & S_IALLUGO;
+
+	switch (mode & S_IFMT) {
+	case S_IFCHR:
+		type = TOMOYO_TYPE_MKCHAR;
+		break;
+	case S_IFBLK:
+		type = TOMOYO_TYPE_MKBLOCK;
+		break;
+	default:
+		goto no_dev;
+	}
+	return tomoyo_mkdev_perm(type, &path, perm, dev);
+ no_dev:
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+		type = TOMOYO_TYPE_MKFIFO;
+		break;
+	case S_IFSOCK:
+		type = TOMOYO_TYPE_MKSOCK;
+		break;
+	}
+	return tomoyo_path_number_perm(type, &path, perm);
+}
+
+/**
+ * tomoyo_path_link - Target for security_path_link().
+ *
+ * @old_dentry: Pointer to "struct dentry".
+ * @new_dir:    Pointer to "struct path".
+ * @new_dentry: Pointer to "struct dentry".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_link(struct dentry *old_dentry, const struct path *new_dir,
+			    struct dentry *new_dentry)
+{
+	struct path path1 = { .mnt = new_dir->mnt, .dentry = old_dentry };
+	struct path path2 = { .mnt = new_dir->mnt, .dentry = new_dentry };
+
+	return tomoyo_path2_perm(TOMOYO_TYPE_LINK, &path1, &path2);
+}
+
+/**
+ * tomoyo_path_rename - Target for security_path_rename().
+ *
+ * @old_parent: Pointer to "struct path".
+ * @old_dentry: Pointer to "struct dentry".
+ * @new_parent: Pointer to "struct path".
+ * @new_dentry: Pointer to "struct dentry".
+ * @flags: Rename options.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_rename(const struct path *old_parent,
+			      struct dentry *old_dentry,
+			      const struct path *new_parent,
+			      struct dentry *new_dentry,
+			      const unsigned int flags)
+{
+	struct path path1 = { .mnt = old_parent->mnt, .dentry = old_dentry };
+	struct path path2 = { .mnt = new_parent->mnt, .dentry = new_dentry };
+
+	if (flags & RENAME_EXCHANGE) {
+		const int err = tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path2,
+				&path1);
+
+		if (err)
+			return err;
+	}
+	return tomoyo_path2_perm(TOMOYO_TYPE_RENAME, &path1, &path2);
+}
+
+/**
+ * tomoyo_file_fcntl - Target for security_file_fcntl().
+ *
+ * @file: Pointer to "struct file".
+ * @cmd:  Command for fcntl().
+ * @arg:  Argument for @cmd.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	if (!(cmd == F_SETFL && ((arg ^ file->f_flags) & O_APPEND)))
+		return 0;
+	return tomoyo_check_open_permission(tomoyo_domain(), &file->f_path,
+					    O_WRONLY | (arg & O_APPEND));
+}
+
+/**
+ * tomoyo_file_open - Target for security_file_open().
+ *
+ * @f: Pointer to "struct file".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_file_open(struct file *f)
+{
+	/* Don't check read permission here if called from execve(). */
+	/* Illogically, FMODE_EXEC is in f_flags, not f_mode. */
+	if (f->f_flags & __FMODE_EXEC)
+		return 0;
+	return tomoyo_check_open_permission(tomoyo_domain(), &f->f_path,
+					    f->f_flags);
+}
+
+/**
+ * tomoyo_file_ioctl - Target for security_file_ioctl().
+ *
+ * @file: Pointer to "struct file".
+ * @cmd:  Command for ioctl().
+ * @arg:  Argument for @cmd.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_file_ioctl(struct file *file, unsigned int cmd,
+			     unsigned long arg)
+{
+	return tomoyo_path_number_perm(TOMOYO_TYPE_IOCTL, &file->f_path, cmd);
+}
+
+/**
+ * tomoyo_path_chmod - Target for security_path_chmod().
+ *
+ * @path: Pointer to "struct path".
+ * @mode: DAC permission mode.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_chmod(const struct path *path, umode_t mode)
+{
+	return tomoyo_path_number_perm(TOMOYO_TYPE_CHMOD, path,
+				       mode & S_IALLUGO);
+}
+
+/**
+ * tomoyo_path_chown - Target for security_path_chown().
+ *
+ * @path: Pointer to "struct path".
+ * @uid:  Owner ID.
+ * @gid:  Group ID.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_chown(const struct path *path, kuid_t uid, kgid_t gid)
+{
+	int error = 0;
+
+	if (uid_valid(uid))
+		error = tomoyo_path_number_perm(TOMOYO_TYPE_CHOWN, path,
+						from_kuid(&init_user_ns, uid));
+	if (!error && gid_valid(gid))
+		error = tomoyo_path_number_perm(TOMOYO_TYPE_CHGRP, path,
+						from_kgid(&init_user_ns, gid));
+	return error;
+}
+
+/**
+ * tomoyo_path_chroot - Target for security_path_chroot().
+ *
+ * @path: Pointer to "struct path".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_path_chroot(const struct path *path)
+{
+	return tomoyo_path_perm(TOMOYO_TYPE_CHROOT, path, NULL);
+}
+
+/**
+ * tomoyo_sb_mount - Target for security_sb_mount().
+ *
+ * @dev_name: Name of device file. Maybe NULL.
+ * @path:     Pointer to "struct path".
+ * @type:     Name of filesystem type. Maybe NULL.
+ * @flags:    Mount options.
+ * @data:     Optional data. Maybe NULL.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_sb_mount(const char *dev_name, const struct path *path,
+			   const char *type, unsigned long flags, void *data)
+{
+	return tomoyo_mount_permission(dev_name, path, type, flags, data);
+}
+
+/**
+ * tomoyo_sb_umount - Target for security_sb_umount().
+ *
+ * @mnt:   Pointer to "struct vfsmount".
+ * @flags: Unmount options.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_sb_umount(struct vfsmount *mnt, int flags)
+{
+	struct path path = { .mnt = mnt, .dentry = mnt->mnt_root };
+
+	return tomoyo_path_perm(TOMOYO_TYPE_UMOUNT, &path, NULL);
+}
+
+/**
+ * tomoyo_sb_pivotroot - Target for security_sb_pivotroot().
+ *
+ * @old_path: Pointer to "struct path".
+ * @new_path: Pointer to "struct path".
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_sb_pivotroot(const struct path *old_path, const struct path *new_path)
+{
+	return tomoyo_path2_perm(TOMOYO_TYPE_PIVOT_ROOT, new_path, old_path);
+}
+
+/**
+ * tomoyo_socket_listen - Check permission for listen().
+ *
+ * @sock:    Pointer to "struct socket".
+ * @backlog: Backlog parameter.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_socket_listen(struct socket *sock, int backlog)
+{
+	return tomoyo_socket_listen_permission(sock);
+}
+
+/**
+ * tomoyo_socket_connect - Check permission for connect().
+ *
+ * @sock:     Pointer to "struct socket".
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_socket_connect(struct socket *sock, struct sockaddr *addr,
+				 int addr_len)
+{
+	return tomoyo_socket_connect_permission(sock, addr, addr_len);
+}
+
+/**
+ * tomoyo_socket_bind - Check permission for bind().
+ *
+ * @sock:     Pointer to "struct socket".
+ * @addr:     Pointer to "struct sockaddr".
+ * @addr_len: Size of @addr.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_socket_bind(struct socket *sock, struct sockaddr *addr,
+			      int addr_len)
+{
+	return tomoyo_socket_bind_permission(sock, addr, addr_len);
+}
+
+/**
+ * tomoyo_socket_sendmsg - Check permission for sendmsg().
+ *
+ * @sock: Pointer to "struct socket".
+ * @msg:  Pointer to "struct msghdr".
+ * @size: Size of message.
+ *
+ * Returns 0 on success, negative value otherwise.
+ */
+static int tomoyo_socket_sendmsg(struct socket *sock, struct msghdr *msg,
+				 int size)
+{
+	return tomoyo_socket_sendmsg_permission(sock, msg, size);
+}
+
+struct lsm_blob_sizes tomoyo_blob_sizes __ro_after_init = {
+	.lbs_task = sizeof(struct tomoyo_task),
+};
+
+/**
+ * tomoyo_task_alloc - Target for security_task_alloc().
+ *
+ * @task:        Pointer to "struct task_struct".
+ * @clone_flags: clone() flags.
+ *
+ * Returns 0.
+ */
+static int tomoyo_task_alloc(struct task_struct *task,
+			     u64 clone_flags)
+{
+	struct tomoyo_task *old = tomoyo_task(current);
+	struct tomoyo_task *new = tomoyo_task(task);
+
+	new->domain_info = old->domain_info;
+	atomic_inc(&new->domain_info->users);
+	new->old_domain_info = NULL;
+	return 0;
+}
+
+/**
+ * tomoyo_task_free - Target for security_task_free().
+ *
+ * @task: Pointer to "struct task_struct".
+ */
+static void tomoyo_task_free(struct task_struct *task)
+{
+	struct tomoyo_task *s = tomoyo_task(task);
+
+	if (s->domain_info) {
+		atomic_dec(&s->domain_info->users);
+		s->domain_info = NULL;
+	}
+	if (s->old_domain_info) {
+		atomic_dec(&s->old_domain_info->users);
+		s->old_domain_info = NULL;
+	}
+}
+
+static const struct lsm_id tomoyo_lsmid = {
+	.name = "tomoyo",
+	.id = LSM_ID_TOMOYO,
+};
+
+/* tomoyo_hooks is used for registering TOMOYO. */
+static struct security_hook_list tomoyo_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare),
+	LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds),
+	LSM_HOOK_INIT(task_alloc, tomoyo_task_alloc),
+	LSM_HOOK_INIT(task_free, tomoyo_task_free),
+#ifndef CONFIG_SECURITY_TOMOYO_OMIT_USERSPACE_LOADER
+	LSM_HOOK_INIT(bprm_creds_for_exec, tomoyo_bprm_creds_for_exec),
+#endif
+	LSM_HOOK_INIT(bprm_check_security, tomoyo_bprm_check_security),
+	LSM_HOOK_INIT(file_fcntl, tomoyo_file_fcntl),
+	LSM_HOOK_INIT(file_open, tomoyo_file_open),
+	LSM_HOOK_INIT(file_truncate, tomoyo_file_truncate),
+	LSM_HOOK_INIT(path_truncate, tomoyo_path_truncate),
+	LSM_HOOK_INIT(path_unlink, tomoyo_path_unlink),
+	LSM_HOOK_INIT(path_mkdir, tomoyo_path_mkdir),
+	LSM_HOOK_INIT(path_rmdir, tomoyo_path_rmdir),
+	LSM_HOOK_INIT(path_symlink, tomoyo_path_symlink),
+	LSM_HOOK_INIT(path_mknod, tomoyo_path_mknod),
+	LSM_HOOK_INIT(path_link, tomoyo_path_link),
+	LSM_HOOK_INIT(path_rename, tomoyo_path_rename),
+	LSM_HOOK_INIT(inode_getattr, tomoyo_inode_getattr),
+	LSM_HOOK_INIT(file_ioctl, tomoyo_file_ioctl),
+	LSM_HOOK_INIT(file_ioctl_compat, tomoyo_file_ioctl),
+	LSM_HOOK_INIT(path_chmod, tomoyo_path_chmod),
+	LSM_HOOK_INIT(path_chown, tomoyo_path_chown),
+	LSM_HOOK_INIT(path_chroot, tomoyo_path_chroot),
+	LSM_HOOK_INIT(sb_mount, tomoyo_sb_mount),
+	LSM_HOOK_INIT(sb_umount, tomoyo_sb_umount),
+	LSM_HOOK_INIT(sb_pivotroot, tomoyo_sb_pivotroot),
+	LSM_HOOK_INIT(socket_bind, tomoyo_socket_bind),
+	LSM_HOOK_INIT(socket_connect, tomoyo_socket_connect),
+	LSM_HOOK_INIT(socket_listen, tomoyo_socket_listen),
+	LSM_HOOK_INIT(socket_sendmsg, tomoyo_socket_sendmsg),
+};
+
+/* Lock for GC. */
+DEFINE_SRCU(tomoyo_ss);
+
+int tomoyo_enabled __ro_after_init = 1;
+
+/**
+ * tomoyo_init - Register TOMOYO Linux as a LSM module.
+ *
+ * Returns 0.
+ */
+static int __init tomoyo_init(void)
+{
+	struct tomoyo_task *s = tomoyo_task(current);
+
+	/* register ourselves with the security framework */
+	security_add_hooks(tomoyo_hooks, ARRAY_SIZE(tomoyo_hooks),
+			   &tomoyo_lsmid);
+	pr_info("TOMOYO Linux initialized\n");
+	s->domain_info = &tomoyo_kernel_domain;
+	atomic_inc(&tomoyo_kernel_domain.users);
+	s->old_domain_info = NULL;
+	tomoyo_mm_init();
+
+	return 0;
+}
+
+DEFINE_LSM(tomoyo) = {
+	.id = &tomoyo_lsmid,
+	.enabled = &tomoyo_enabled,
+	.flags = LSM_FLAG_LEGACY_MAJOR,
+	.blobs = &tomoyo_blob_sizes,
+	.init = tomoyo_init,
+	.initcall_fs = tomoyo_interface_init,
+};
diff --git a/security/tomoyo/util.c b/security/tomoyo/util.c
new file mode 100644
index 000000000..6799b1122
--- /dev/null
+++ b/security/tomoyo/util.c
@@ -0,0 +1,1106 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * security/tomoyo/util.c
+ *
+ * Copyright (C) 2005-2011  NTT DATA CORPORATION
+ */
+
+#include <linux/slab.h>
+#include <linux/rculist.h>
+
+#include "common.h"
+
+/* Lock for protecting policy. */
+DEFINE_MUTEX(tomoyo_policy_lock);
+
+/* Has /sbin/init started? */
+bool tomoyo_policy_loaded;
+
+/*
+ * Mapping table from "enum tomoyo_mac_index" to
+ * "enum tomoyo_mac_category_index".
+ */
+const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = {
+	/* CONFIG::file group */
+	[TOMOYO_MAC_FILE_EXECUTE]    = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_OPEN]       = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_CREATE]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_UNLINK]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_GETATTR]    = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MKDIR]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_RMDIR]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MKFIFO]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MKSOCK]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_TRUNCATE]   = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_SYMLINK]    = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MKBLOCK]    = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MKCHAR]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_LINK]       = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_RENAME]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_CHMOD]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_CHOWN]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_CHGRP]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_IOCTL]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_CHROOT]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_MOUNT]      = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_UMOUNT]     = TOMOYO_MAC_CATEGORY_FILE,
+	[TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE,
+	/* CONFIG::network group */
+	[TOMOYO_MAC_NETWORK_INET_STREAM_BIND]       =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN]     =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT]    =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_DGRAM_BIND]        =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_DGRAM_SEND]        =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_RAW_BIND]          =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_INET_RAW_SEND]          =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND]       =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN]     =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT]    =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND]        =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND]        =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND]    =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN]  =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	[TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] =
+	TOMOYO_MAC_CATEGORY_NETWORK,
+	/* CONFIG::misc group */
+	[TOMOYO_MAC_ENVIRON]         = TOMOYO_MAC_CATEGORY_MISC,
+};
+
+/**
+ * tomoyo_convert_time - Convert time_t to YYYY/MM/DD hh/mm/ss.
+ *
+ * @time64: Seconds since 1970/01/01 00:00:00.
+ * @stamp:  Pointer to "struct tomoyo_time".
+ *
+ * Returns nothing.
+ */
+void tomoyo_convert_time(time64_t time64, struct tomoyo_time *stamp)
+{
+	struct tm tm;
+
+	time64_to_tm(time64, 0, &tm);
+	stamp->sec = tm.tm_sec;
+	stamp->min = tm.tm_min;
+	stamp->hour = tm.tm_hour;
+	stamp->day = tm.tm_mday;
+	stamp->month = tm.tm_mon + 1;
+	stamp->year = tm.tm_year + 1900;
+}
+
+/**
+ * tomoyo_permstr - Find permission keywords.
+ *
+ * @string: String representation for permissions in foo/bar/buz format.
+ * @keyword: Keyword to find from @string/
+ *
+ * Returns true if @keyword was found in @string, false otherwise.
+ *
+ * This function assumes that strncmp(w1, w2, strlen(w1)) != 0 if w1 != w2.
+ */
+bool tomoyo_permstr(const char *string, const char *keyword)
+{
+	const char *cp = strstr(string, keyword);
+
+	if (cp)
+		return cp == string || *(cp - 1) == '/';
+	return false;
+}
+
+/**
+ * tomoyo_read_token - Read a word from a line.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns a word on success, "" otherwise.
+ *
+ * To allow the caller to skip NULL check, this function returns "" rather than
+ * NULL if there is no more words to read.
+ */
+char *tomoyo_read_token(struct tomoyo_acl_param *param)
+{
+	char *pos = param->data;
+	char *del = strchr(pos, ' ');
+
+	if (del)
+		*del++ = '\0';
+	else
+		del = pos + strlen(pos);
+	param->data = del;
+	return pos;
+}
+
+static bool tomoyo_correct_path2(const char *filename, const size_t len);
+
+/**
+ * tomoyo_get_domainname - Read a domainname from a line.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ *
+ * Returns a domainname on success, NULL otherwise.
+ */
+const struct tomoyo_path_info *tomoyo_get_domainname
+(struct tomoyo_acl_param *param)
+{
+	char *start = param->data;
+	char *pos = start;
+
+	while (*pos) {
+		if (*pos++ != ' ' ||
+		    tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos))
+			continue;
+		*(pos - 1) = '\0';
+		break;
+	}
+	param->data = pos;
+	if (tomoyo_correct_domain(start))
+		return tomoyo_get_name(start);
+	return NULL;
+}
+
+/**
+ * tomoyo_parse_ulong - Parse an "unsigned long" value.
+ *
+ * @result: Pointer to "unsigned long".
+ * @str:    Pointer to string to parse.
+ *
+ * Returns one of values in "enum tomoyo_value_type".
+ *
+ * The @src is updated to point the first character after the value
+ * on success.
+ */
+u8 tomoyo_parse_ulong(unsigned long *result, char **str)
+{
+	const char *cp = *str;
+	char *ep;
+	int base = 10;
+
+	if (*cp == '0') {
+		char c = *(cp + 1);
+
+		if (c == 'x' || c == 'X') {
+			base = 16;
+			cp += 2;
+		} else if (c >= '0' && c <= '7') {
+			base = 8;
+			cp++;
+		}
+	}
+	*result = simple_strtoul(cp, &ep, base);
+	if (cp == ep)
+		return TOMOYO_VALUE_TYPE_INVALID;
+	*str = ep;
+	switch (base) {
+	case 16:
+		return TOMOYO_VALUE_TYPE_HEXADECIMAL;
+	case 8:
+		return TOMOYO_VALUE_TYPE_OCTAL;
+	default:
+		return TOMOYO_VALUE_TYPE_DECIMAL;
+	}
+}
+
+/**
+ * tomoyo_print_ulong - Print an "unsigned long" value.
+ *
+ * @buffer:     Pointer to buffer.
+ * @buffer_len: Size of @buffer.
+ * @value:      An "unsigned long" value.
+ * @type:       Type of @value.
+ *
+ * Returns nothing.
+ */
+void tomoyo_print_ulong(char *buffer, const int buffer_len,
+			const unsigned long value, const u8 type)
+{
+	if (type == TOMOYO_VALUE_TYPE_DECIMAL)
+		snprintf(buffer, buffer_len, "%lu", value);
+	else if (type == TOMOYO_VALUE_TYPE_OCTAL)
+		snprintf(buffer, buffer_len, "0%lo", value);
+	else if (type == TOMOYO_VALUE_TYPE_HEXADECIMAL)
+		snprintf(buffer, buffer_len, "0x%lX", value);
+	else
+		snprintf(buffer, buffer_len, "type(%u)", type);
+}
+
+/**
+ * tomoyo_parse_name_union - Parse a tomoyo_name_union.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @ptr:   Pointer to "struct tomoyo_name_union".
+ *
+ * Returns true on success, false otherwise.
+ */
+bool tomoyo_parse_name_union(struct tomoyo_acl_param *param,
+			     struct tomoyo_name_union *ptr)
+{
+	char *filename;
+
+	if (param->data[0] == '@') {
+		param->data++;
+		ptr->group = tomoyo_get_group(param, TOMOYO_PATH_GROUP);
+		return ptr->group != NULL;
+	}
+	filename = tomoyo_read_token(param);
+	if (!tomoyo_correct_word(filename))
+		return false;
+	ptr->filename = tomoyo_get_name(filename);
+	return ptr->filename != NULL;
+}
+
+/**
+ * tomoyo_parse_number_union - Parse a tomoyo_number_union.
+ *
+ * @param: Pointer to "struct tomoyo_acl_param".
+ * @ptr:   Pointer to "struct tomoyo_number_union".
+ *
+ * Returns true on success, false otherwise.
+ */
+bool tomoyo_parse_number_union(struct tomoyo_acl_param *param,
+			       struct tomoyo_number_union *ptr)
+{
+	char *data;
+	u8 type;
+	unsigned long v;
+
+	memset(ptr, 0, sizeof(*ptr));
+	if (param->data[0] == '@') {
+		param->data++;
+		ptr->group = tomoyo_get_group(param, TOMOYO_NUMBER_GROUP);
+		return ptr->group != NULL;
+	}
+	data = tomoyo_read_token(param);
+	type = tomoyo_parse_ulong(&v, &data);
+	if (type == TOMOYO_VALUE_TYPE_INVALID)
+		return false;
+	ptr->values[0] = v;
+	ptr->value_type[0] = type;
+	if (!*data) {
+		ptr->values[1] = v;
+		ptr->value_type[1] = type;
+		return true;
+	}
+	if (*data++ != '-')
+		return false;
+	type = tomoyo_parse_ulong(&v, &data);
+	if (type == TOMOYO_VALUE_TYPE_INVALID || *data || ptr->values[0] > v)
+		return false;
+	ptr->values[1] = v;
+	ptr->value_type[1] = type;
+	return true;
+}
+
+/**
+ * tomoyo_byte_range - Check whether the string is a \ooo style octal value.
+ *
+ * @str: Pointer to the string.
+ *
+ * Returns true if @str is a \ooo style octal value, false otherwise.
+ *
+ * TOMOYO uses \ooo style representation for 0x01 - 0x20 and 0x7F - 0xFF.
+ * This function verifies that \ooo is in valid range.
+ */
+static inline bool tomoyo_byte_range(const char *str)
+{
+	return *str >= '0' && *str++ <= '3' &&
+		*str >= '0' && *str++ <= '7' &&
+		*str >= '0' && *str <= '7';
+}
+
+/**
+ * tomoyo_alphabet_char - Check whether the character is an alphabet.
+ *
+ * @c: The character to check.
+ *
+ * Returns true if @c is an alphabet character, false otherwise.
+ */
+static inline bool tomoyo_alphabet_char(const char c)
+{
+	return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z');
+}
+
+/**
+ * tomoyo_make_byte - Make byte value from three octal characters.
+ *
+ * @c1: The first character.
+ * @c2: The second character.
+ * @c3: The third character.
+ *
+ * Returns byte value.
+ */
+static inline u8 tomoyo_make_byte(const u8 c1, const u8 c2, const u8 c3)
+{
+	return ((c1 - '0') << 6) + ((c2 - '0') << 3) + (c3 - '0');
+}
+
+/**
+ * tomoyo_valid - Check whether the character is a valid char.
+ *
+ * @c: The character to check.
+ *
+ * Returns true if @c is a valid character, false otherwise.
+ */
+static inline bool tomoyo_valid(const unsigned char c)
+{
+	return c > ' ' && c < 127;
+}
+
+/**
+ * tomoyo_invalid - Check whether the character is an invalid char.
+ *
+ * @c: The character to check.
+ *
+ * Returns true if @c is an invalid character, false otherwise.
+ */
+static inline bool tomoyo_invalid(const unsigned char c)
+{
+	return c && (c <= ' ' || c >= 127);
+}
+
+/**
+ * tomoyo_str_starts - Check whether the given string starts with the given keyword.
+ *
+ * @src:  Pointer to pointer to the string.
+ * @find: Pointer to the keyword.
+ *
+ * Returns true if @src starts with @find, false otherwise.
+ *
+ * The @src is updated to point the first character after the @find
+ * if @src starts with @find.
+ */
+bool tomoyo_str_starts(char **src, const char *find)
+{
+	const int len = strlen(find);
+	char *tmp = *src;
+
+	if (strncmp(tmp, find, len))
+		return false;
+	tmp += len;
+	*src = tmp;
+	return true;
+}
+
+/**
+ * tomoyo_normalize_line - Format string.
+ *
+ * @buffer: The line to normalize.
+ *
+ * Leading and trailing whitespaces are removed.
+ * Multiple whitespaces are packed into single space.
+ *
+ * Returns nothing.
+ */
+void tomoyo_normalize_line(unsigned char *buffer)
+{
+	unsigned char *sp = buffer;
+	unsigned char *dp = buffer;
+	bool first = true;
+
+	while (tomoyo_invalid(*sp))
+		sp++;
+	while (*sp) {
+		if (!first)
+			*dp++ = ' ';
+		first = false;
+		while (tomoyo_valid(*sp))
+			*dp++ = *sp++;
+		while (tomoyo_invalid(*sp))
+			sp++;
+	}
+	*dp = '\0';
+}
+
+/**
+ * tomoyo_correct_word2 - Validate a string.
+ *
+ * @string: The string to check. Maybe non-'\0'-terminated.
+ * @len:    Length of @string.
+ *
+ * Check whether the given string follows the naming rules.
+ * Returns true if @string follows the naming rules, false otherwise.
+ */
+static bool tomoyo_correct_word2(const char *string, size_t len)
+{
+	u8 recursion = 20;
+	const char *const start = string;
+	bool in_repetition = false;
+
+	if (!len)
+		goto out;
+	while (len--) {
+		unsigned char c = *string++;
+
+		if (c == '\\') {
+			if (!len--)
+				goto out;
+			c = *string++;
+			if (c >= '0' && c <= '3') {
+				unsigned char d;
+				unsigned char e;
+
+				if (!len-- || !len--)
+					goto out;
+				d = *string++;
+				e = *string++;
+				if (d < '0' || d > '7' || e < '0' || e > '7')
+					goto out;
+				c = tomoyo_make_byte(c, d, e);
+				if (c <= ' ' || c >= 127)
+					continue;
+				goto out;
+			}
+			switch (c) {
+			case '\\':  /* "\\" */
+			case '+':   /* "\+" */
+			case '?':   /* "\?" */
+			case 'x':   /* "\x" */
+			case 'a':   /* "\a" */
+			case '-':   /* "\-" */
+				continue;
+			}
+			if (!recursion--)
+				goto out;
+			switch (c) {
+			case '*':   /* "\*" */
+			case '@':   /* "\@" */
+			case '$':   /* "\$" */
+			case 'X':   /* "\X" */
+			case 'A':   /* "\A" */
+				continue;
+			case '{':   /* "/\{" */
+				if (string - 3 < start || *(string - 3) != '/')
+					goto out;
+				in_repetition = true;
+				continue;
+			case '}':   /* "\}/" */
+				if (*string != '/')
+					goto out;
+				if (!in_repetition)
+					goto out;
+				in_repetition = false;
+				continue;
+			}
+			goto out;
+		} else if (in_repetition && c == '/') {
+			goto out;
+		} else if (c <= ' ' || c >= 127) {
+			goto out;
+		}
+	}
+	if (in_repetition)
+		goto out;
+	return true;
+ out:
+	return false;
+}
+
+/**
+ * tomoyo_correct_word - Validate a string.
+ *
+ * @string: The string to check.
+ *
+ * Check whether the given string follows the naming rules.
+ * Returns true if @string follows the naming rules, false otherwise.
+ */
+bool tomoyo_correct_word(const char *string)
+{
+	return tomoyo_correct_word2(string, strlen(string));
+}
+
+/**
+ * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules.
+ *
+ * @filename: The pathname to check.
+ * @len:      Length of @filename.
+ *
+ * Returns true if @filename follows the naming rules, false otherwise.
+ */
+static bool tomoyo_correct_path2(const char *filename, const size_t len)
+{
+	const char *cp1 = memchr(filename, '/', len);
+	const char *cp2 = memchr(filename, '.', len);
+
+	return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len);
+}
+
+/**
+ * tomoyo_correct_path - Validate a pathname.
+ *
+ * @filename: The pathname to check.
+ *
+ * Check whether the given pathname follows the naming rules.
+ * Returns true if @filename follows the naming rules, false otherwise.
+ */
+bool tomoyo_correct_path(const char *filename)
+{
+	return tomoyo_correct_path2(filename, strlen(filename));
+}
+
+/**
+ * tomoyo_correct_domain - Check whether the given domainname follows the naming rules.
+ *
+ * @domainname: The domainname to check.
+ *
+ * Returns true if @domainname follows the naming rules, false otherwise.
+ */
+bool tomoyo_correct_domain(const unsigned char *domainname)
+{
+	if (!domainname || !tomoyo_domain_def(domainname))
+		return false;
+	domainname = strchr(domainname, ' ');
+	if (!domainname++)
+		return true;
+	while (1) {
+		const unsigned char *cp = strchr(domainname, ' ');
+
+		if (!cp)
+			break;
+		if (!tomoyo_correct_path2(domainname, cp - domainname))
+			return false;
+		domainname = cp + 1;
+	}
+	return tomoyo_correct_path(domainname);
+}
+
+/**
+ * tomoyo_domain_def - Check whether the given token can be a domainname.
+ *
+ * @buffer: The token to check.
+ *
+ * Returns true if @buffer possibly be a domainname, false otherwise.
+ */
+bool tomoyo_domain_def(const unsigned char *buffer)
+{
+	const unsigned char *cp;
+	int len;
+
+	if (*buffer != '<')
+		return false;
+	cp = strchr(buffer, ' ');
+	if (!cp)
+		len = strlen(buffer);
+	else
+		len = cp - buffer;
+	if (buffer[len - 1] != '>' ||
+	    !tomoyo_correct_word2(buffer + 1, len - 2))
+		return false;
+	return true;
+}
+
+/**
+ * tomoyo_find_domain - Find a domain by the given name.
+ *
+ * @domainname: The domainname to find.
+ *
+ * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname)
+{
+	struct tomoyo_domain_info *domain;
+	struct tomoyo_path_info name;
+
+	name.name = domainname;
+	tomoyo_fill_path_info(&name);
+	list_for_each_entry_rcu(domain, &tomoyo_domain_list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		if (!domain->is_deleted &&
+		    !tomoyo_pathcmp(&name, domain->domainname))
+			return domain;
+	}
+	return NULL;
+}
+
+/**
+ * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token.
+ *
+ * @filename: The string to evaluate.
+ *
+ * Returns the initial length without a pattern in @filename.
+ */
+static int tomoyo_const_part_length(const char *filename)
+{
+	char c;
+	int len = 0;
+
+	if (!filename)
+		return 0;
+	while ((c = *filename++) != '\0') {
+		if (c != '\\') {
+			len++;
+			continue;
+		}
+		c = *filename++;
+		switch (c) {
+		case '\\':  /* "\\" */
+			len += 2;
+			continue;
+		case '0':   /* "\ooo" */
+		case '1':
+		case '2':
+		case '3':
+			c = *filename++;
+			if (c < '0' || c > '7')
+				break;
+			c = *filename++;
+			if (c < '0' || c > '7')
+				break;
+			len += 4;
+			continue;
+		}
+		break;
+	}
+	return len;
+}
+
+/**
+ * tomoyo_fill_path_info - Fill in "struct tomoyo_path_info" members.
+ *
+ * @ptr: Pointer to "struct tomoyo_path_info" to fill in.
+ *
+ * The caller sets "struct tomoyo_path_info"->name.
+ */
+void tomoyo_fill_path_info(struct tomoyo_path_info *ptr)
+{
+	const char *name = ptr->name;
+	const int len = strlen(name);
+
+	ptr->const_len = tomoyo_const_part_length(name);
+	ptr->is_dir = len && (name[len - 1] == '/');
+	ptr->is_patterned = (ptr->const_len < len);
+	ptr->hash = full_name_hash(NULL, name, len);
+}
+
+/**
+ * tomoyo_file_matches_pattern2 - Pattern matching without '/' character and "\-" pattern.
+ *
+ * @filename:     The start of string to check.
+ * @filename_end: The end of string to check.
+ * @pattern:      The start of pattern to compare.
+ * @pattern_end:  The end of pattern to compare.
+ *
+ * Returns true if @filename matches @pattern, false otherwise.
+ */
+static bool tomoyo_file_matches_pattern2(const char *filename,
+					 const char *filename_end,
+					 const char *pattern,
+					 const char *pattern_end)
+{
+	while (filename < filename_end && pattern < pattern_end) {
+		char c;
+		int i;
+		int j;
+
+		if (*pattern != '\\') {
+			if (*filename++ != *pattern++)
+				return false;
+			continue;
+		}
+		c = *filename;
+		pattern++;
+		switch (*pattern) {
+		case '?':
+			if (c == '/') {
+				return false;
+			} else if (c == '\\') {
+				if (filename[1] == '\\')
+					filename++;
+				else if (tomoyo_byte_range(filename + 1))
+					filename += 3;
+				else
+					return false;
+			}
+			break;
+		case '\\':
+			if (c != '\\')
+				return false;
+			if (*++filename != '\\')
+				return false;
+			break;
+		case '+':
+			if (!isdigit(c))
+				return false;
+			break;
+		case 'x':
+			if (!isxdigit(c))
+				return false;
+			break;
+		case 'a':
+			if (!tomoyo_alphabet_char(c))
+				return false;
+			break;
+		case '0':
+		case '1':
+		case '2':
+		case '3':
+			if (c == '\\' && tomoyo_byte_range(filename + 1)
+			    && strncmp(filename + 1, pattern, 3) == 0) {
+				filename += 3;
+				pattern += 2;
+				break;
+			}
+			return false; /* Not matched. */
+		case '*':
+		case '@':
+			for (i = 0; i <= filename_end - filename; i++) {
+				if (tomoyo_file_matches_pattern2(
+						    filename + i, filename_end,
+						    pattern + 1, pattern_end))
+					return true;
+				c = filename[i];
+				if (c == '.' && *pattern == '@')
+					break;
+				if (c != '\\')
+					continue;
+				if (filename[i + 1] == '\\')
+					i++;
+				else if (tomoyo_byte_range(filename + i + 1))
+					i += 3;
+				else
+					break; /* Bad pattern. */
+			}
+			return false; /* Not matched. */
+		default:
+			j = 0;
+			c = *pattern;
+			if (c == '$') {
+				while (isdigit(filename[j]))
+					j++;
+			} else if (c == 'X') {
+				while (isxdigit(filename[j]))
+					j++;
+			} else if (c == 'A') {
+				while (tomoyo_alphabet_char(filename[j]))
+					j++;
+			}
+			for (i = 1; i <= j; i++) {
+				if (tomoyo_file_matches_pattern2(
+						    filename + i, filename_end,
+						    pattern + 1, pattern_end))
+					return true;
+			}
+			return false; /* Not matched or bad pattern. */
+		}
+		filename++;
+		pattern++;
+	}
+	while (*pattern == '\\' &&
+	       (*(pattern + 1) == '*' || *(pattern + 1) == '@'))
+		pattern += 2;
+	return filename == filename_end && pattern == pattern_end;
+}
+
+/**
+ * tomoyo_file_matches_pattern - Pattern matching without '/' character.
+ *
+ * @filename:     The start of string to check.
+ * @filename_end: The end of string to check.
+ * @pattern:      The start of pattern to compare.
+ * @pattern_end:  The end of pattern to compare.
+ *
+ * Returns true if @filename matches @pattern, false otherwise.
+ */
+static bool tomoyo_file_matches_pattern(const char *filename,
+					const char *filename_end,
+					const char *pattern,
+					const char *pattern_end)
+{
+	const char *pattern_start = pattern;
+	bool first = true;
+	bool result;
+
+	while (pattern < pattern_end - 1) {
+		/* Split at "\-" pattern. */
+		if (*pattern++ != '\\' || *pattern++ != '-')
+			continue;
+		result = tomoyo_file_matches_pattern2(filename,
+						      filename_end,
+						      pattern_start,
+						      pattern - 2);
+		if (first)
+			result = !result;
+		if (result)
+			return false;
+		first = false;
+		pattern_start = pattern;
+	}
+	result = tomoyo_file_matches_pattern2(filename, filename_end,
+					      pattern_start, pattern_end);
+	return first ? result : !result;
+}
+
+/**
+ * tomoyo_path_matches_pattern2 - Do pathname pattern matching.
+ *
+ * @f: The start of string to check.
+ * @p: The start of pattern to compare.
+ *
+ * Returns true if @f matches @p, false otherwise.
+ */
+static bool tomoyo_path_matches_pattern2(const char *f, const char *p)
+{
+	const char *f_delimiter;
+	const char *p_delimiter;
+
+	while (*f && *p) {
+		f_delimiter = strchr(f, '/');
+		if (!f_delimiter)
+			f_delimiter = f + strlen(f);
+		p_delimiter = strchr(p, '/');
+		if (!p_delimiter)
+			p_delimiter = p + strlen(p);
+		if (*p == '\\' && *(p + 1) == '{')
+			goto recursive;
+		if (!tomoyo_file_matches_pattern(f, f_delimiter, p,
+						 p_delimiter))
+			return false;
+		f = f_delimiter;
+		if (*f)
+			f++;
+		p = p_delimiter;
+		if (*p)
+			p++;
+	}
+	/* Ignore trailing "\*" and "\@" in @pattern. */
+	while (*p == '\\' &&
+	       (*(p + 1) == '*' || *(p + 1) == '@'))
+		p += 2;
+	return !*f && !*p;
+ recursive:
+	/*
+	 * The "\{" pattern is permitted only after '/' character.
+	 * This guarantees that below "*(p - 1)" is safe.
+	 * Also, the "\}" pattern is permitted only before '/' character
+	 * so that "\{" + "\}" pair will not break the "\-" operator.
+	 */
+	if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' ||
+	    *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\')
+		return false; /* Bad pattern. */
+	do {
+		/* Compare current component with pattern. */
+		if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2,
+						 p_delimiter - 2))
+			break;
+		/* Proceed to next component. */
+		f = f_delimiter;
+		if (!*f)
+			break;
+		f++;
+		/* Continue comparison. */
+		if (tomoyo_path_matches_pattern2(f, p_delimiter + 1))
+			return true;
+		f_delimiter = strchr(f, '/');
+	} while (f_delimiter);
+	return false; /* Not matched. */
+}
+
+/**
+ * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern.
+ *
+ * @filename: The filename to check.
+ * @pattern:  The pattern to compare.
+ *
+ * Returns true if matches, false otherwise.
+ *
+ * The following patterns are available.
+ *   \\     \ itself.
+ *   \ooo   Octal representation of a byte.
+ *   \*     Zero or more repetitions of characters other than '/'.
+ *   \@     Zero or more repetitions of characters other than '/' or '.'.
+ *   \?     1 byte character other than '/'.
+ *   \$     One or more repetitions of decimal digits.
+ *   \+     1 decimal digit.
+ *   \X     One or more repetitions of hexadecimal digits.
+ *   \x     1 hexadecimal digit.
+ *   \A     One or more repetitions of alphabet characters.
+ *   \a     1 alphabet character.
+ *
+ *   \-     Subtraction operator.
+ *
+ *   /\{dir\}/   '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/
+ *               /dir/dir/dir/ ).
+ */
+bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename,
+				 const struct tomoyo_path_info *pattern)
+{
+	const char *f = filename->name;
+	const char *p = pattern->name;
+	const int len = pattern->const_len;
+
+	/* If @pattern doesn't contain pattern, I can use strcmp(). */
+	if (!pattern->is_patterned)
+		return !tomoyo_pathcmp(filename, pattern);
+	/* Don't compare directory and non-directory. */
+	if (filename->is_dir != pattern->is_dir)
+		return false;
+	/* Compare the initial length without patterns. */
+	if (strncmp(f, p, len))
+		return false;
+	f += len;
+	p += len;
+	return tomoyo_path_matches_pattern2(f, p);
+}
+
+/**
+ * tomoyo_get_exe - Get tomoyo_realpath() of current process.
+ *
+ * Returns the tomoyo_realpath() of current process on success, NULL otherwise.
+ *
+ * This function uses kzalloc(), so the caller must call kfree()
+ * if this function didn't return NULL.
+ */
+const char *tomoyo_get_exe(void)
+{
+	struct file *exe_file;
+	const char *cp;
+	struct mm_struct *mm = current->mm;
+
+	if (!mm)
+		return NULL;
+	exe_file = get_mm_exe_file(mm);
+	if (!exe_file)
+		return NULL;
+
+	cp = tomoyo_realpath_from_path(&exe_file->f_path);
+	fput(exe_file);
+	return cp;
+}
+
+/**
+ * tomoyo_get_mode - Get MAC mode.
+ *
+ * @ns:      Pointer to "struct tomoyo_policy_namespace".
+ * @profile: Profile number.
+ * @index:   Index number of functionality.
+ *
+ * Returns mode.
+ */
+int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile,
+		    const u8 index)
+{
+	u8 mode;
+	struct tomoyo_profile *p;
+
+	if (!tomoyo_policy_loaded)
+		return TOMOYO_CONFIG_DISABLED;
+	p = tomoyo_profile(ns, profile);
+	mode = p->config[index];
+	if (mode == TOMOYO_CONFIG_USE_DEFAULT)
+		mode = p->config[tomoyo_index2category[index]
+				 + TOMOYO_MAX_MAC_INDEX];
+	if (mode == TOMOYO_CONFIG_USE_DEFAULT)
+		mode = p->default_config;
+	return mode & 3;
+}
+
+/**
+ * tomoyo_init_request_info - Initialize "struct tomoyo_request_info" members.
+ *
+ * @r:      Pointer to "struct tomoyo_request_info" to initialize.
+ * @domain: Pointer to "struct tomoyo_domain_info". NULL for tomoyo_domain().
+ * @index:  Index number of functionality.
+ *
+ * Returns mode.
+ */
+int tomoyo_init_request_info(struct tomoyo_request_info *r,
+			     struct tomoyo_domain_info *domain, const u8 index)
+{
+	u8 profile;
+
+	memset(r, 0, sizeof(*r));
+	if (!domain)
+		domain = tomoyo_domain();
+	r->domain = domain;
+	profile = domain->profile;
+	r->profile = profile;
+	r->type = index;
+	r->mode = tomoyo_get_mode(domain->ns, profile, index);
+	return r->mode;
+}
+
+/**
+ * tomoyo_domain_quota_is_ok - Check for domain's quota.
+ *
+ * @r: Pointer to "struct tomoyo_request_info".
+ *
+ * Returns true if the domain is not exceeded quota, false otherwise.
+ *
+ * Caller holds tomoyo_read_lock().
+ */
+bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r)
+{
+	unsigned int count = 0;
+	struct tomoyo_domain_info *domain = r->domain;
+	struct tomoyo_acl_info *ptr;
+
+	if (r->mode != TOMOYO_CONFIG_LEARNING)
+		return false;
+	if (!domain)
+		return true;
+	if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED]))
+		return false;
+	list_for_each_entry_rcu(ptr, &domain->acl_info_list, list,
+				srcu_read_lock_held(&tomoyo_ss)) {
+		u16 perm;
+
+		if (ptr->is_deleted)
+			continue;
+		/*
+		 * Reading perm bitmap might race with tomoyo_merge_*() because
+		 * caller does not hold tomoyo_policy_lock mutex. But exceeding
+		 * max_learning_entry parameter by a few entries does not harm.
+		 */
+		switch (ptr->type) {
+		case TOMOYO_TYPE_PATH_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm);
+			break;
+		case TOMOYO_TYPE_PATH2_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm);
+			break;
+		case TOMOYO_TYPE_PATH_NUMBER_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head)
+				  ->perm);
+			break;
+		case TOMOYO_TYPE_MKDEV_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm);
+			break;
+		case TOMOYO_TYPE_INET_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm);
+			break;
+		case TOMOYO_TYPE_UNIX_ACL:
+			perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm);
+			break;
+		case TOMOYO_TYPE_MANUAL_TASK_ACL:
+			perm = 0;
+			break;
+		default:
+			perm = 1;
+		}
+		count += hweight16(perm);
+	}
+	if (count < tomoyo_profile(domain->ns, domain->profile)->
+	    pref[TOMOYO_PREF_MAX_LEARNING_ENTRY])
+		return true;
+	WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true);
+	/* r->granted = false; */
+	tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]);
+#ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING
+	pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n",
+		domain->domainname->name);
+#endif
+	return false;
+}
diff --git a/security/yama/Kconfig b/security/yama/Kconfig
new file mode 100644
index 000000000..a81030412
--- /dev/null
+++ b/security/yama/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config SECURITY_YAMA
+	bool "Yama support"
+	depends on SECURITY
+	default n
+	help
+	  This selects Yama, which extends DAC support with additional
+	  system-wide security settings beyond regular Linux discretionary
+	  access controls. Currently available is ptrace scope restriction.
+	  Like capabilities, this security module stacks with other LSMs.
+	  Further information can be found in
+	  Documentation/admin-guide/LSM/Yama.rst.
+
+	  If you are unsure how to answer this question, answer N.
diff --git a/security/yama/Makefile b/security/yama/Makefile
new file mode 100644
index 000000000..0fa5d0fe2
--- /dev/null
+++ b/security/yama/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SECURITY_YAMA) := yama.o
+
+yama-y := yama_lsm.o
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
new file mode 100644
index 000000000..cef3776cf
--- /dev/null
+++ b/security/yama/yama_lsm.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Yama Linux Security Module
+ *
+ * Author: Kees Cook <keescook@chromium.org>
+ *
+ * Copyright (C) 2010 Canonical, Ltd.
+ * Copyright (C) 2011 The Chromium OS Authors.
+ */
+
+#include <linux/lsm_hooks.h>
+#include <linux/sysctl.h>
+#include <linux/ptrace.h>
+#include <linux/prctl.h>
+#include <linux/ratelimit.h>
+#include <linux/workqueue.h>
+#include <linux/string_helpers.h>
+#include <linux/task_work.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <uapi/linux/lsm.h>
+
+#define YAMA_SCOPE_DISABLED	0
+#define YAMA_SCOPE_RELATIONAL	1
+#define YAMA_SCOPE_CAPABILITY	2
+#define YAMA_SCOPE_NO_ATTACH	3
+
+static int ptrace_scope = YAMA_SCOPE_RELATIONAL;
+
+/* describe a ptrace relationship for potential exception */
+struct ptrace_relation {
+	struct task_struct *tracer;
+	struct task_struct *tracee;
+	bool invalid;
+	struct list_head node;
+	struct rcu_head rcu;
+};
+
+static LIST_HEAD(ptracer_relations);
+static DEFINE_SPINLOCK(ptracer_relations_lock);
+
+static void yama_relation_cleanup(struct work_struct *work);
+static DECLARE_WORK(yama_relation_work, yama_relation_cleanup);
+
+struct access_report_info {
+	struct callback_head work;
+	const char *access;
+	struct task_struct *target;
+	struct task_struct *agent;
+};
+
+static void __report_access(struct callback_head *work)
+{
+	struct access_report_info *info =
+		container_of(work, struct access_report_info, work);
+	char *target_cmd, *agent_cmd;
+
+	target_cmd = kstrdup_quotable_cmdline(info->target, GFP_KERNEL);
+	agent_cmd = kstrdup_quotable_cmdline(info->agent, GFP_KERNEL);
+
+	pr_notice_ratelimited(
+		"ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n",
+		info->access, target_cmd, info->target->pid, agent_cmd,
+		info->agent->pid);
+
+	kfree(agent_cmd);
+	kfree(target_cmd);
+
+	put_task_struct(info->agent);
+	put_task_struct(info->target);
+	kfree(info);
+}
+
+/* defers execution because cmdline access can sleep */
+static void report_access(const char *access, struct task_struct *target,
+				struct task_struct *agent)
+{
+	struct access_report_info *info;
+
+	assert_spin_locked(&target->alloc_lock); /* for target->comm */
+
+	if (current->flags & PF_KTHREAD) {
+		/* I don't think kthreads call task_work_run() before exiting.
+		 * Imagine angry ranting about procfs here.
+		 */
+		pr_notice_ratelimited(
+		    "ptrace %s of \"%s\"[%d] was attempted by \"%s\"[%d]\n",
+		    access, target->comm, target->pid, agent->comm, agent->pid);
+		return;
+	}
+
+	info = kmalloc_obj(*info, GFP_ATOMIC);
+	if (!info)
+		return;
+	init_task_work(&info->work, __report_access);
+	get_task_struct(target);
+	get_task_struct(agent);
+	info->access = access;
+	info->target = target;
+	info->agent = agent;
+	if (task_work_add(current, &info->work, TWA_RESUME) == 0)
+		return; /* success */
+
+	WARN(1, "report_access called from exiting task");
+	put_task_struct(target);
+	put_task_struct(agent);
+	kfree(info);
+}
+
+/**
+ * yama_relation_cleanup - remove invalid entries from the relation list
+ * @work: unused
+ *
+ */
+static void yama_relation_cleanup(struct work_struct *work)
+{
+	struct ptrace_relation *relation;
+
+	spin_lock(&ptracer_relations_lock);
+	rcu_read_lock();
+	list_for_each_entry_rcu(relation, &ptracer_relations, node) {
+		if (relation->invalid) {
+			list_del_rcu(&relation->node);
+			kfree_rcu(relation, rcu);
+		}
+	}
+	rcu_read_unlock();
+	spin_unlock(&ptracer_relations_lock);
+}
+
+/**
+ * yama_ptracer_add - add/replace an exception for this tracer/tracee pair
+ * @tracer: the task_struct of the process doing the ptrace
+ * @tracee: the task_struct of the process to be ptraced
+ *
+ * Each tracee can have, at most, one tracer registered. Each time this
+ * is called, the prior registered tracer will be replaced for the tracee.
+ *
+ * Returns 0 if relationship was added, -ve on error.
+ */
+static int yama_ptracer_add(struct task_struct *tracer,
+			    struct task_struct *tracee)
+{
+	struct ptrace_relation *relation, *added;
+
+	added = kmalloc_obj(*added);
+	if (!added)
+		return -ENOMEM;
+
+	added->tracee = tracee;
+	added->tracer = tracer;
+	added->invalid = false;
+
+	spin_lock(&ptracer_relations_lock);
+	rcu_read_lock();
+	list_for_each_entry_rcu(relation, &ptracer_relations, node) {
+		if (relation->invalid)
+			continue;
+		if (relation->tracee == tracee) {
+			list_replace_rcu(&relation->node, &added->node);
+			kfree_rcu(relation, rcu);
+			goto out;
+		}
+	}
+
+	list_add_rcu(&added->node, &ptracer_relations);
+
+out:
+	rcu_read_unlock();
+	spin_unlock(&ptracer_relations_lock);
+	return 0;
+}
+
+/**
+ * yama_ptracer_del - remove exceptions related to the given tasks
+ * @tracer: remove any relation where tracer task matches
+ * @tracee: remove any relation where tracee task matches
+ */
+static void yama_ptracer_del(struct task_struct *tracer,
+			     struct task_struct *tracee)
+{
+	struct ptrace_relation *relation;
+	bool marked = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(relation, &ptracer_relations, node) {
+		if (relation->invalid)
+			continue;
+		if (relation->tracee == tracee ||
+		    (tracer && relation->tracer == tracer)) {
+			relation->invalid = true;
+			marked = true;
+		}
+	}
+	rcu_read_unlock();
+
+	if (marked)
+		schedule_work(&yama_relation_work);
+}
+
+/**
+ * yama_task_free - check for task_pid to remove from exception list
+ * @task: task being removed
+ */
+static void yama_task_free(struct task_struct *task)
+{
+	yama_ptracer_del(task, task);
+}
+
+/**
+ * yama_task_prctl - check for Yama-specific prctl operations
+ * @option: operation
+ * @arg2: argument
+ * @arg3: argument
+ * @arg4: argument
+ * @arg5: argument
+ *
+ * Return 0 on success, -ve on error.  -ENOSYS is returned when Yama
+ * does not handle the given option.
+ */
+static int yama_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, unsigned long arg5)
+{
+	int rc = -ENOSYS;
+	struct task_struct *myself;
+
+	switch (option) {
+	case PR_SET_PTRACER:
+		/* Since a thread can call prctl(), find the group leader
+		 * before calling _add() or _del() on it, since we want
+		 * process-level granularity of control. The tracer group
+		 * leader checking is handled later when walking the ancestry
+		 * at the time of PTRACE_ATTACH check.
+		 */
+		myself = current->group_leader;
+
+		if (arg2 == 0) {
+			yama_ptracer_del(NULL, myself);
+			rc = 0;
+		} else if (arg2 == PR_SET_PTRACER_ANY || (int)arg2 == -1) {
+			rc = yama_ptracer_add(NULL, myself);
+		} else {
+			struct task_struct *tracer;
+
+			tracer = find_get_task_by_vpid(arg2);
+			if (!tracer) {
+				rc = -EINVAL;
+			} else {
+				rc = yama_ptracer_add(tracer, myself);
+				put_task_struct(tracer);
+			}
+		}
+
+		break;
+	}
+
+	return rc;
+}
+
+/**
+ * task_is_descendant - walk up a process family tree looking for a match
+ * @parent: the process to compare against while walking up from child
+ * @child: the process to start from while looking upwards for parent
+ *
+ * Returns 1 if child is a descendant of parent, 0 if not.
+ */
+static int task_is_descendant(struct task_struct *parent,
+			      struct task_struct *child)
+{
+	int rc = 0;
+	struct task_struct *walker = child;
+
+	if (!parent || !child)
+		return 0;
+
+	rcu_read_lock();
+	if (!thread_group_leader(parent))
+		parent = rcu_dereference(parent->group_leader);
+	while (walker->pid > 0) {
+		if (!thread_group_leader(walker))
+			walker = rcu_dereference(walker->group_leader);
+		if (walker == parent) {
+			rc = 1;
+			break;
+		}
+		walker = rcu_dereference(walker->real_parent);
+	}
+	rcu_read_unlock();
+
+	return rc;
+}
+
+/**
+ * ptracer_exception_found - tracer registered as exception for this tracee
+ * @tracer: the task_struct of the process attempting ptrace
+ * @tracee: the task_struct of the process to be ptraced
+ *
+ * Returns 1 if tracer has a ptracer exception ancestor for tracee.
+ */
+static int ptracer_exception_found(struct task_struct *tracer,
+				   struct task_struct *tracee)
+{
+	int rc = 0;
+	struct ptrace_relation *relation;
+	struct task_struct *parent = NULL;
+	bool found = false;
+
+	rcu_read_lock();
+
+	/*
+	 * If there's already an active tracing relationship, then make an
+	 * exception for the sake of other accesses, like process_vm_rw().
+	 */
+	parent = ptrace_parent(tracee);
+	if (parent != NULL && same_thread_group(parent, tracer)) {
+		rc = 1;
+		goto unlock;
+	}
+
+	/* Look for a PR_SET_PTRACER relationship. */
+	if (!thread_group_leader(tracee))
+		tracee = rcu_dereference(tracee->group_leader);
+	list_for_each_entry_rcu(relation, &ptracer_relations, node) {
+		if (relation->invalid)
+			continue;
+		if (relation->tracee == tracee) {
+			parent = relation->tracer;
+			found = true;
+			break;
+		}
+	}
+
+	if (found && (parent == NULL || task_is_descendant(parent, tracer)))
+		rc = 1;
+
+unlock:
+	rcu_read_unlock();
+
+	return rc;
+}
+
+/**
+ * yama_ptrace_access_check - validate PTRACE_ATTACH calls
+ * @child: task that current task is attempting to ptrace
+ * @mode: ptrace attach mode
+ *
+ * Returns 0 if following the ptrace is allowed, -ve on error.
+ */
+static int yama_ptrace_access_check(struct task_struct *child,
+				    unsigned int mode)
+{
+	int rc = 0;
+
+	/* require ptrace target be a child of ptracer on attach */
+	if (mode & PTRACE_MODE_ATTACH) {
+		switch (ptrace_scope) {
+		case YAMA_SCOPE_DISABLED:
+			/* No additional restrictions. */
+			break;
+		case YAMA_SCOPE_RELATIONAL:
+			rcu_read_lock();
+			if (!pid_alive(child))
+				rc = -EPERM;
+			if (!rc && !task_is_descendant(current, child) &&
+			    !ptracer_exception_found(current, child) &&
+			    !ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
+				rc = -EPERM;
+			rcu_read_unlock();
+			break;
+		case YAMA_SCOPE_CAPABILITY:
+			rcu_read_lock();
+			if (!ns_capable(__task_cred(child)->user_ns, CAP_SYS_PTRACE))
+				rc = -EPERM;
+			rcu_read_unlock();
+			break;
+		case YAMA_SCOPE_NO_ATTACH:
+		default:
+			rc = -EPERM;
+			break;
+		}
+	}
+
+	if (rc && (mode & PTRACE_MODE_NOAUDIT) == 0)
+		report_access("attach", child, current);
+
+	return rc;
+}
+
+/**
+ * yama_ptrace_traceme - validate PTRACE_TRACEME calls
+ * @parent: task that will become the ptracer of the current task
+ *
+ * Returns 0 if following the ptrace is allowed, -ve on error.
+ */
+static int yama_ptrace_traceme(struct task_struct *parent)
+{
+	int rc = 0;
+
+	/* Only disallow PTRACE_TRACEME on more aggressive settings. */
+	switch (ptrace_scope) {
+	case YAMA_SCOPE_CAPABILITY:
+		if (!has_ns_capability(parent, current_user_ns(), CAP_SYS_PTRACE))
+			rc = -EPERM;
+		break;
+	case YAMA_SCOPE_NO_ATTACH:
+		rc = -EPERM;
+		break;
+	}
+
+	if (rc) {
+		task_lock(current);
+		report_access("traceme", current, parent);
+		task_unlock(current);
+	}
+
+	return rc;
+}
+
+static const struct lsm_id yama_lsmid = {
+	.name = "yama",
+	.id = LSM_ID_YAMA,
+};
+
+static struct security_hook_list yama_hooks[] __ro_after_init = {
+	LSM_HOOK_INIT(ptrace_access_check, yama_ptrace_access_check),
+	LSM_HOOK_INIT(ptrace_traceme, yama_ptrace_traceme),
+	LSM_HOOK_INIT(task_prctl, yama_task_prctl),
+	LSM_HOOK_INIT(task_free, yama_task_free),
+};
+
+#ifdef CONFIG_SYSCTL
+static int yama_dointvec_minmax(const struct ctl_table *table, int write,
+				void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table table_copy;
+
+	if (write && !capable(CAP_SYS_PTRACE))
+		return -EPERM;
+
+	/* Lock the max value if it ever gets set. */
+	table_copy = *table;
+	if (*(int *)table_copy.data == *(int *)table_copy.extra2)
+		table_copy.extra1 = table_copy.extra2;
+
+	return proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos);
+}
+
+static int max_scope = YAMA_SCOPE_NO_ATTACH;
+
+static const struct ctl_table yama_sysctl_table[] = {
+	{
+		.procname       = "ptrace_scope",
+		.data           = &ptrace_scope,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = yama_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = &max_scope,
+	},
+};
+static void __init yama_init_sysctl(void)
+{
+	if (!register_sysctl("kernel/yama", yama_sysctl_table))
+		panic("Yama: sysctl registration failed.\n");
+}
+#else
+static inline void yama_init_sysctl(void) { }
+#endif /* CONFIG_SYSCTL */
+
+static int __init yama_init(void)
+{
+	pr_info("Yama: becoming mindful.\n");
+	security_add_hooks(yama_hooks, ARRAY_SIZE(yama_hooks), &yama_lsmid);
+	yama_init_sysctl();
+	return 0;
+}
+
+DEFINE_LSM(yama) = {
+	.id = &yama_lsmid,
+	.init = yama_init,
+};
-- 
cgit v1.3.1