From 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d Mon Sep 17 00:00:00 2001 From: Zeng Chi 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 Cc: David Ballesteros Signed-off-by: Zeng Chi Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com [sean: split to separate patch] Signed-off-by: Sean Christopherson --- tools/include/uapi/README | 73 + tools/include/uapi/asm-generic/bitsperlong.h | 31 + tools/include/uapi/asm-generic/bpf_perf_event.h | 9 + tools/include/uapi/asm-generic/errno-base.h | 40 + tools/include/uapi/asm-generic/errno.h | 127 + tools/include/uapi/asm-generic/ioctls.h | 121 + tools/include/uapi/asm-generic/mman-common-tools.h | 23 + tools/include/uapi/asm-generic/mman-common.h | 94 + tools/include/uapi/asm-generic/mman.h | 26 + tools/include/uapi/asm-generic/socket.h | 175 + tools/include/uapi/asm-generic/unistd.h | 919 +++ tools/include/uapi/asm/bitsperlong.h | 18 + tools/include/uapi/asm/bpf_perf_event.h | 13 + tools/include/uapi/asm/errno.h | 16 + tools/include/uapi/linux/acct.h | 128 + tools/include/uapi/linux/bits.h | 14 + tools/include/uapi/linux/bpf.h | 7828 ++++++++++++++++++++ tools/include/uapi/linux/bpf_common.h | 57 + tools/include/uapi/linux/bpf_perf_event.h | 19 + tools/include/uapi/linux/btf.h | 215 + tools/include/uapi/linux/const.h | 71 + tools/include/uapi/linux/coredump.h | 104 + tools/include/uapi/linux/elf.h | 524 ++ tools/include/uapi/linux/erspan.h | 52 + tools/include/uapi/linux/fanotify.h | 274 + tools/include/uapi/linux/filter.h | 90 + tools/include/uapi/linux/fs.h | 570 ++ tools/include/uapi/linux/fscrypt.h | 198 + tools/include/uapi/linux/genetlink.h | 103 + tools/include/uapi/linux/hw_breakpoint.h | 25 + tools/include/uapi/linux/if_addr.h | 79 + tools/include/uapi/linux/if_link.h | 1982 +++++ tools/include/uapi/linux/if_tun.h | 118 + tools/include/uapi/linux/if_xdp.h | 185 + tools/include/uapi/linux/in.h | 337 + tools/include/uapi/linux/io_uring.h | 757 ++ tools/include/uapi/linux/kcmp.h | 28 + tools/include/uapi/linux/kvm.h | 1673 +++++ tools/include/uapi/linux/memfd.h | 39 + tools/include/uapi/linux/mman.h | 59 + tools/include/uapi/linux/module_signature.h | 41 + tools/include/uapi/linux/mount.h | 245 + tools/include/uapi/linux/neighbour.h | 229 + tools/include/uapi/linux/netdev.h | 253 + tools/include/uapi/linux/netfilter.h | 80 + tools/include/uapi/linux/netfilter_arp.h | 23 + tools/include/uapi/linux/netlink.h | 252 + tools/include/uapi/linux/nsfs.h | 128 + tools/include/uapi/linux/openat2.h | 43 + tools/include/uapi/linux/perf_event.h | 1528 ++++ tools/include/uapi/linux/pkt_cls.h | 565 ++ tools/include/uapi/linux/pkt_sched.h | 1055 +++ tools/include/uapi/linux/prctl.h | 377 + tools/include/uapi/linux/rtnetlink.h | 849 +++ tools/include/uapi/linux/seccomp.h | 157 + tools/include/uapi/linux/seg6.h | 55 + tools/include/uapi/linux/seg6_local.h | 80 + tools/include/uapi/linux/stat.h | 260 + tools/include/uapi/linux/stddef.h | 78 + tools/include/uapi/linux/taskstats.h | 291 + tools/include/uapi/linux/tc_act/tc_bpf.h | 30 + tools/include/uapi/linux/tcp.h | 357 + tools/include/uapi/linux/tls.h | 78 + tools/include/uapi/linux/types.h | 26 + tools/include/uapi/linux/userfaultfd.h | 432 ++ 65 files changed, 24726 insertions(+) create mode 100644 tools/include/uapi/README create mode 100644 tools/include/uapi/asm-generic/bitsperlong.h create mode 100644 tools/include/uapi/asm-generic/bpf_perf_event.h create mode 100644 tools/include/uapi/asm-generic/errno-base.h create mode 100644 tools/include/uapi/asm-generic/errno.h create mode 100644 tools/include/uapi/asm-generic/ioctls.h create mode 100644 tools/include/uapi/asm-generic/mman-common-tools.h create mode 100644 tools/include/uapi/asm-generic/mman-common.h create mode 100644 tools/include/uapi/asm-generic/mman.h create mode 100644 tools/include/uapi/asm-generic/socket.h create mode 100644 tools/include/uapi/asm-generic/unistd.h create mode 100644 tools/include/uapi/asm/bitsperlong.h create mode 100644 tools/include/uapi/asm/bpf_perf_event.h create mode 100644 tools/include/uapi/asm/errno.h create mode 100644 tools/include/uapi/linux/acct.h create mode 100644 tools/include/uapi/linux/bits.h create mode 100644 tools/include/uapi/linux/bpf.h create mode 100644 tools/include/uapi/linux/bpf_common.h create mode 100644 tools/include/uapi/linux/bpf_perf_event.h create mode 100644 tools/include/uapi/linux/btf.h create mode 100644 tools/include/uapi/linux/const.h create mode 100644 tools/include/uapi/linux/coredump.h create mode 100644 tools/include/uapi/linux/elf.h create mode 100644 tools/include/uapi/linux/erspan.h create mode 100644 tools/include/uapi/linux/fanotify.h create mode 100644 tools/include/uapi/linux/filter.h create mode 100644 tools/include/uapi/linux/fs.h create mode 100644 tools/include/uapi/linux/fscrypt.h create mode 100644 tools/include/uapi/linux/genetlink.h create mode 100644 tools/include/uapi/linux/hw_breakpoint.h create mode 100644 tools/include/uapi/linux/if_addr.h create mode 100644 tools/include/uapi/linux/if_link.h create mode 100644 tools/include/uapi/linux/if_tun.h create mode 100644 tools/include/uapi/linux/if_xdp.h create mode 100644 tools/include/uapi/linux/in.h create mode 100644 tools/include/uapi/linux/io_uring.h create mode 100644 tools/include/uapi/linux/kcmp.h create mode 100644 tools/include/uapi/linux/kvm.h create mode 100644 tools/include/uapi/linux/memfd.h create mode 100644 tools/include/uapi/linux/mman.h create mode 100644 tools/include/uapi/linux/module_signature.h create mode 100644 tools/include/uapi/linux/mount.h create mode 100644 tools/include/uapi/linux/neighbour.h create mode 100644 tools/include/uapi/linux/netdev.h create mode 100644 tools/include/uapi/linux/netfilter.h create mode 100644 tools/include/uapi/linux/netfilter_arp.h create mode 100644 tools/include/uapi/linux/netlink.h create mode 100644 tools/include/uapi/linux/nsfs.h create mode 100644 tools/include/uapi/linux/openat2.h create mode 100644 tools/include/uapi/linux/perf_event.h create mode 100644 tools/include/uapi/linux/pkt_cls.h create mode 100644 tools/include/uapi/linux/pkt_sched.h create mode 100644 tools/include/uapi/linux/prctl.h create mode 100644 tools/include/uapi/linux/rtnetlink.h create mode 100644 tools/include/uapi/linux/seccomp.h create mode 100644 tools/include/uapi/linux/seg6.h create mode 100644 tools/include/uapi/linux/seg6_local.h create mode 100644 tools/include/uapi/linux/stat.h create mode 100644 tools/include/uapi/linux/stddef.h create mode 100644 tools/include/uapi/linux/taskstats.h create mode 100644 tools/include/uapi/linux/tc_act/tc_bpf.h create mode 100644 tools/include/uapi/linux/tcp.h create mode 100644 tools/include/uapi/linux/tls.h create mode 100644 tools/include/uapi/linux/types.h create mode 100644 tools/include/uapi/linux/userfaultfd.h (limited to 'tools/include/uapi') diff --git a/tools/include/uapi/README b/tools/include/uapi/README new file mode 100644 index 000000000..7147b1b2c --- /dev/null +++ b/tools/include/uapi/README @@ -0,0 +1,73 @@ +Why we want a copy of kernel headers in tools? +============================================== + +There used to be no copies, with tools/ code using kernel headers +directly. From time to time tools/perf/ broke due to legitimate kernel +hacking. At some point Linus complained about such direct usage. Then we +adopted the current model. + +The way these headers are used in perf are not restricted to just +including them to compile something. + +There are sometimes used in scripts that convert defines into string +tables, etc, so some change may break one of these scripts, or new MSRs +may use some different #define pattern, etc. + +E.g.: + + $ ls -1 tools/perf/trace/beauty/*.sh | head -5 + tools/perf/trace/beauty/arch_errno_names.sh + tools/perf/trace/beauty/drm_ioctl.sh + tools/perf/trace/beauty/fadvise.sh + tools/perf/trace/beauty/fsconfig.sh + tools/perf/trace/beauty/fsmount.sh + $ + $ tools/perf/trace/beauty/fadvise.sh + static const char *fadvise_advices[] = { + [0] = "NORMAL", + [1] = "RANDOM", + [2] = "SEQUENTIAL", + [3] = "WILLNEED", + [4] = "DONTNEED", + [5] = "NOREUSE", + }; + $ + +The tools/perf/check-headers.sh script, part of the tools/ build +process, points out changes in the original files. + +So its important not to touch the copies in tools/ when doing changes in +the original kernel headers, that will be done later, when +check-headers.sh inform about the change to the perf tools hackers. + +Another explanation from Ingo Molnar: +It's better than all the alternatives we tried so far: + + - Symbolic links and direct #includes: this was the original approach but + was pushed back on from the kernel side, when tooling modified the + headers and broke them accidentally for kernel builds. + + - Duplicate self-defined ABI headers like glibc: double the maintenance + burden, double the chance for mistakes, plus there's no tech-driven + notification mechanism to look at new kernel side changes. + +What we are doing now is a third option: + + - A software-enforced copy-on-write mechanism of kernel headers to + tooling, driven by non-fatal warnings on the tooling side build when + kernel headers get modified: + + Warning: Kernel ABI header differences: + diff -u tools/include/uapi/drm/i915_drm.h include/uapi/drm/i915_drm.h + diff -u tools/include/uapi/linux/fs.h include/uapi/linux/fs.h + diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h + ... + + The tooling policy is to always pick up the kernel side headers as-is, + and integate them into the tooling build. The warnings above serve as a + notification to tooling maintainers that there's changes on the kernel + side. + +We've been using this for many years now, and it might seem hacky, but +works surprisingly well. + diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h new file mode 100644 index 000000000..fadb3f857 --- /dev/null +++ b/tools/include/uapi/asm-generic/bitsperlong.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG +#define _UAPI__ASM_GENERIC_BITS_PER_LONG + +#ifndef __BITS_PER_LONG +/* + * In order to keep safe and avoid regression, only unify uapi + * bitsperlong.h for some archs which are using newer toolchains + * that have the definitions of __CHAR_BIT__ and __SIZEOF_LONG__. + * See the following link for more info: + * https://lore.kernel.org/linux-arch/b9624545-2c80-49a1-ac3c-39264a591f7b@app.fastmail.com/ + */ +#if defined(__CHAR_BIT__) && defined(__SIZEOF_LONG__) +#define __BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__) +#else +/* + * There seems to be no way of detecting this automatically from user + * space, so 64 bit architectures should override this in their + * bitsperlong.h. In particular, an architecture that supports + * both 32 and 64 bit user space must not rely on CONFIG_64BIT + * to decide it, but rather check a compiler provided macro. + */ +#define __BITS_PER_LONG 32 +#endif +#endif + +#ifndef __BITS_PER_LONG_LONG +#define __BITS_PER_LONG_LONG 64 +#endif + +#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */ diff --git a/tools/include/uapi/asm-generic/bpf_perf_event.h b/tools/include/uapi/asm-generic/bpf_perf_event.h new file mode 100644 index 000000000..53815d2cd --- /dev/null +++ b/tools/include/uapi/asm-generic/bpf_perf_event.h @@ -0,0 +1,9 @@ +#ifndef _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ + +#include + +/* Export kernel pt_regs structure */ +typedef struct pt_regs bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_GENERIC_BPF_PERF_EVENT_H__ */ diff --git a/tools/include/uapi/asm-generic/errno-base.h b/tools/include/uapi/asm-generic/errno-base.h new file mode 100644 index 000000000..9653140bf --- /dev/null +++ b/tools/include/uapi/asm-generic/errno-base.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_GENERIC_ERRNO_BASE_H +#define _ASM_GENERIC_ERRNO_BASE_H + +#define EPERM 1 /* Operation not permitted */ +#define ENOENT 2 /* No such file or directory */ +#define ESRCH 3 /* No such process */ +#define EINTR 4 /* Interrupted system call */ +#define EIO 5 /* I/O error */ +#define ENXIO 6 /* No such device or address */ +#define E2BIG 7 /* Argument list too long */ +#define ENOEXEC 8 /* Exec format error */ +#define EBADF 9 /* Bad file number */ +#define ECHILD 10 /* No child processes */ +#define EAGAIN 11 /* Try again */ +#define ENOMEM 12 /* Out of memory */ +#define EACCES 13 /* Permission denied */ +#define EFAULT 14 /* Bad address */ +#define ENOTBLK 15 /* Block device required */ +#define EBUSY 16 /* Device or resource busy */ +#define EEXIST 17 /* File exists */ +#define EXDEV 18 /* Cross-device link */ +#define ENODEV 19 /* No such device */ +#define ENOTDIR 20 /* Not a directory */ +#define EISDIR 21 /* Is a directory */ +#define EINVAL 22 /* Invalid argument */ +#define ENFILE 23 /* File table overflow */ +#define EMFILE 24 /* Too many open files */ +#define ENOTTY 25 /* Not a typewriter */ +#define ETXTBSY 26 /* Text file busy */ +#define EFBIG 27 /* File too large */ +#define ENOSPC 28 /* No space left on device */ +#define ESPIPE 29 /* Illegal seek */ +#define EROFS 30 /* Read-only file system */ +#define EMLINK 31 /* Too many links */ +#define EPIPE 32 /* Broken pipe */ +#define EDOM 33 /* Math argument out of domain of func */ +#define ERANGE 34 /* Math result not representable */ + +#endif diff --git a/tools/include/uapi/asm-generic/errno.h b/tools/include/uapi/asm-generic/errno.h new file mode 100644 index 000000000..bd78e69e0 --- /dev/null +++ b/tools/include/uapi/asm-generic/errno.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_GENERIC_ERRNO_H +#define _ASM_GENERIC_ERRNO_H + +#include + +#define EDEADLK 35 /* Resource deadlock would occur */ +#define ENAMETOOLONG 36 /* File name too long */ +#define ENOLCK 37 /* No record locks available */ + +/* + * This error code is special: arch syscall entry code will return + * -ENOSYS if users try to call a syscall that doesn't exist. To keep + * failures of syscalls that really do exist distinguishable from + * failures due to attempts to use a nonexistent syscall, syscall + * implementations should refrain from returning -ENOSYS. + */ +#define ENOSYS 38 /* Invalid system call number */ + +#define ENOTEMPTY 39 /* Directory not empty */ +#define ELOOP 40 /* Too many symbolic links encountered */ +#define EWOULDBLOCK EAGAIN /* Operation would block */ +#define ENOMSG 42 /* No message of desired type */ +#define EIDRM 43 /* Identifier removed */ +#define ECHRNG 44 /* Channel number out of range */ +#define EL2NSYNC 45 /* Level 2 not synchronized */ +#define EL3HLT 46 /* Level 3 halted */ +#define EL3RST 47 /* Level 3 reset */ +#define ELNRNG 48 /* Link number out of range */ +#define EUNATCH 49 /* Protocol driver not attached */ +#define ENOCSI 50 /* No CSI structure available */ +#define EL2HLT 51 /* Level 2 halted */ +#define EBADE 52 /* Invalid exchange */ +#define EBADR 53 /* Invalid request descriptor */ +#define EXFULL 54 /* Exchange full */ +#define ENOANO 55 /* No anode */ +#define EBADRQC 56 /* Invalid request code */ +#define EBADSLT 57 /* Invalid slot */ + +#define EDEADLOCK EDEADLK + +#define EBFONT 59 /* Bad font file format */ +#define ENOSTR 60 /* Device not a stream */ +#define ENODATA 61 /* No data available */ +#define ETIME 62 /* Timer expired */ +#define ENOSR 63 /* Out of streams resources */ +#define ENONET 64 /* Machine is not on the network */ +#define ENOPKG 65 /* Package not installed */ +#define EREMOTE 66 /* Object is remote */ +#define ENOLINK 67 /* Link has been severed */ +#define EADV 68 /* Advertise error */ +#define ESRMNT 69 /* Srmount error */ +#define ECOMM 70 /* Communication error on send */ +#define EPROTO 71 /* Protocol error */ +#define EMULTIHOP 72 /* Multihop attempted */ +#define EDOTDOT 73 /* RFS specific error */ +#define EBADMSG 74 /* Not a data message */ +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EOVERFLOW 75 /* Value too large for defined data type */ +#define ENOTUNIQ 76 /* Name not unique on network */ +#define EBADFD 77 /* File descriptor in bad state */ +#define EREMCHG 78 /* Remote address changed */ +#define ELIBACC 79 /* Can not access a needed shared library */ +#define ELIBBAD 80 /* Accessing a corrupted shared library */ +#define ELIBSCN 81 /* .lib section in a.out corrupted */ +#define ELIBMAX 82 /* Attempting to link in too many shared libraries */ +#define ELIBEXEC 83 /* Cannot exec a shared library directly */ +#define EILSEQ 84 /* Illegal byte sequence */ +#define ERESTART 85 /* Interrupted system call should be restarted */ +#define ESTRPIPE 86 /* Streams pipe error */ +#define EUSERS 87 /* Too many users */ +#define ENOTSOCK 88 /* Socket operation on non-socket */ +#define EDESTADDRREQ 89 /* Destination address required */ +#define EMSGSIZE 90 /* Message too long */ +#define EPROTOTYPE 91 /* Protocol wrong type for socket */ +#define ENOPROTOOPT 92 /* Protocol not available */ +#define EPROTONOSUPPORT 93 /* Protocol not supported */ +#define ESOCKTNOSUPPORT 94 /* Socket type not supported */ +#define EOPNOTSUPP 95 /* Operation not supported on transport endpoint */ +#define EPFNOSUPPORT 96 /* Protocol family not supported */ +#define EAFNOSUPPORT 97 /* Address family not supported by protocol */ +#define EADDRINUSE 98 /* Address already in use */ +#define EADDRNOTAVAIL 99 /* Cannot assign requested address */ +#define ENETDOWN 100 /* Network is down */ +#define ENETUNREACH 101 /* Network is unreachable */ +#define ENETRESET 102 /* Network dropped connection because of reset */ +#define ECONNABORTED 103 /* Software caused connection abort */ +#define ECONNRESET 104 /* Connection reset by peer */ +#define ENOBUFS 105 /* No buffer space available */ +#define EISCONN 106 /* Transport endpoint is already connected */ +#define ENOTCONN 107 /* Transport endpoint is not connected */ +#define ESHUTDOWN 108 /* Cannot send after transport endpoint shutdown */ +#define ETOOMANYREFS 109 /* Too many references: cannot splice */ +#define ETIMEDOUT 110 /* Connection timed out */ +#define ECONNREFUSED 111 /* Connection refused */ +#define EHOSTDOWN 112 /* Host is down */ +#define EHOSTUNREACH 113 /* No route to host */ +#define EALREADY 114 /* Operation already in progress */ +#define EINPROGRESS 115 /* Operation now in progress */ +#define ESTALE 116 /* Stale file handle */ +#define EUCLEAN 117 /* Structure needs cleaning */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ +#define ENOTNAM 118 /* Not a XENIX named type file */ +#define ENAVAIL 119 /* No XENIX semaphores available */ +#define EISNAM 120 /* Is a named type file */ +#define EREMOTEIO 121 /* Remote I/O error */ +#define EDQUOT 122 /* Quota exceeded */ + +#define ENOMEDIUM 123 /* No medium found */ +#define EMEDIUMTYPE 124 /* Wrong medium type */ +#define ECANCELED 125 /* Operation Canceled */ +#define ENOKEY 126 /* Required key not available */ +#define EKEYEXPIRED 127 /* Key has expired */ +#define EKEYREVOKED 128 /* Key has been revoked */ +#define EKEYREJECTED 129 /* Key was rejected by service */ + +/* for robust mutexes */ +#define EOWNERDEAD 130 /* Owner died */ +#define ENOTRECOVERABLE 131 /* State not recoverable */ + +#define ERFKILL 132 /* Operation not possible due to RF-kill */ + +#define EHWPOISON 133 /* Memory page has hardware error */ + +#define EFTYPE 134 /* Wrong file type for the intended operation */ + +#endif diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h new file mode 100644 index 000000000..cdc9f4ca8 --- /dev/null +++ b/tools/include/uapi/asm-generic/ioctls.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_IOCTLS_H +#define __ASM_GENERIC_IOCTLS_H + +#include + +/* + * These are the most common definitions for tty ioctl numbers. + * Most of them do not use the recommended _IOC(), but there is + * probably some source code out there hardcoding the number, + * so we might as well use them for all new platforms. + * + * The architectures that use different values here typically + * try to be compatible with some Unix variants for the same + * architecture. + */ + +/* 0x54 is just a magic number to make these relatively unique ('T') */ + +#define TCGETS 0x5401 +#define TCSETS 0x5402 +#define TCSETSW 0x5403 +#define TCSETSF 0x5404 +#define TCGETA 0x5405 +#define TCSETA 0x5406 +#define TCSETAW 0x5407 +#define TCSETAF 0x5408 +#define TCSBRK 0x5409 +#define TCXONC 0x540A +#define TCFLSH 0x540B +#define TIOCEXCL 0x540C +#define TIOCNXCL 0x540D +#define TIOCSCTTY 0x540E +#define TIOCGPGRP 0x540F +#define TIOCSPGRP 0x5410 +#define TIOCOUTQ 0x5411 +#define TIOCSTI 0x5412 +#define TIOCGWINSZ 0x5413 +#define TIOCSWINSZ 0x5414 +#define TIOCMGET 0x5415 +#define TIOCMBIS 0x5416 +#define TIOCMBIC 0x5417 +#define TIOCMSET 0x5418 +#define TIOCGSOFTCAR 0x5419 +#define TIOCSSOFTCAR 0x541A +#define FIONREAD 0x541B +#define TIOCINQ FIONREAD +#define TIOCLINUX 0x541C +#define TIOCCONS 0x541D +#define TIOCGSERIAL 0x541E +#define TIOCSSERIAL 0x541F +#define TIOCPKT 0x5420 +#define FIONBIO 0x5421 +#define TIOCNOTTY 0x5422 +#define TIOCSETD 0x5423 +#define TIOCGETD 0x5424 +#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */ +#define TIOCSBRK 0x5427 /* BSD compatibility */ +#define TIOCCBRK 0x5428 /* BSD compatibility */ +#define TIOCGSID 0x5429 /* Return the session ID of FD */ +#define TCGETS2 _IOR('T', 0x2A, struct termios2) +#define TCSETS2 _IOW('T', 0x2B, struct termios2) +#define TCSETSW2 _IOW('T', 0x2C, struct termios2) +#define TCSETSF2 _IOW('T', 0x2D, struct termios2) +#define TIOCGRS485 0x542E +#ifndef TIOCSRS485 +#define TIOCSRS485 0x542F +#endif +#define TIOCGPTN _IOR('T', 0x30, unsigned int) /* Get Pty Number (of pty-mux device) */ +#define TIOCSPTLCK _IOW('T', 0x31, int) /* Lock/unlock Pty */ +#define TIOCGDEV _IOR('T', 0x32, unsigned int) /* Get primary device node of /dev/console */ +#define TCGETX 0x5432 /* SYS5 TCGETX compatibility */ +#define TCSETX 0x5433 +#define TCSETXF 0x5434 +#define TCSETXW 0x5435 +#define TIOCSIG _IOW('T', 0x36, int) /* pty: generate signal */ +#define TIOCVHANGUP 0x5437 +#define TIOCGPKT _IOR('T', 0x38, int) /* Get packet mode state */ +#define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ +#define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ +#define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) + +#define FIONCLEX 0x5450 +#define FIOCLEX 0x5451 +#define FIOASYNC 0x5452 +#define TIOCSERCONFIG 0x5453 +#define TIOCSERGWILD 0x5454 +#define TIOCSERSWILD 0x5455 +#define TIOCGLCKTRMIOS 0x5456 +#define TIOCSLCKTRMIOS 0x5457 +#define TIOCSERGSTRUCT 0x5458 /* For debugging only */ +#define TIOCSERGETLSR 0x5459 /* Get line status register */ +#define TIOCSERGETMULTI 0x545A /* Get multiport config */ +#define TIOCSERSETMULTI 0x545B /* Set multiport config */ + +#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */ +#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */ + +/* + * Some arches already define FIOQSIZE due to a historical + * conflict with a Hayes modem-specific ioctl value. + */ +#ifndef FIOQSIZE +# define FIOQSIZE 0x5460 +#endif + +/* Used for packet mode */ +#define TIOCPKT_DATA 0 +#define TIOCPKT_FLUSHREAD 1 +#define TIOCPKT_FLUSHWRITE 2 +#define TIOCPKT_STOP 4 +#define TIOCPKT_START 8 +#define TIOCPKT_NOSTOP 16 +#define TIOCPKT_DOSTOP 32 +#define TIOCPKT_IOCTL 64 + +#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */ + +#endif /* __ASM_GENERIC_IOCTLS_H */ diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h new file mode 100644 index 000000000..af7d0d3a3 --- /dev/null +++ b/tools/include/uapi/asm-generic/mman-common-tools.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H +#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H + +#include + +/* We need this because we need to have tools/include/uapi/ included in the tools + * header search path to get access to stuff that is not yet in the system's + * copy of the files in that directory, but since this cset: + * + * 746c9398f5ac ("arch: move common mmap flags to linux/mman.h") + * + * We end up making sys/mman.h, that is in the system headers, to not find the + * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy + * of asm-generic/mman-common.h. So we define them here and include this header + * from each of the per arch mman.h headers. + */ +#ifndef MAP_SHARED +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#endif +#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h new file mode 100644 index 000000000..ef1c27fa3 --- /dev/null +++ b/tools/include/uapi/asm-generic/mman-common.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_MMAN_COMMON_H +#define __ASM_GENERIC_MMAN_COMMON_H + +/* + Author: Michael S. Tsirkin , Mellanox Technologies Ltd. + Based on: asm-xxx/mman.h +*/ + +#define PROT_READ 0x1 /* page can be read */ +#define PROT_WRITE 0x2 /* page can be written */ +#define PROT_EXEC 0x4 /* page can be executed */ +#define PROT_SEM 0x8 /* page may be used for atomic ops */ +/* 0x10 reserved for arch-specific use */ +/* 0x20 reserved for arch-specific use */ +#define PROT_NONE 0x0 /* page can not be accessed */ +#define PROT_GROWSDOWN 0x01000000 /* mprotect flag: extend change to start of growsdown vma */ +#define PROT_GROWSUP 0x02000000 /* mprotect flag: extend change to end of growsup vma */ + +/* 0x01 - 0x03 are defined in linux/mman.h */ +#define MAP_TYPE 0x0f /* Mask for type of mapping */ +#define MAP_FIXED 0x10 /* Interpret addr exactly */ +#define MAP_ANONYMOUS 0x20 /* don't use a file */ + +/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */ +#define MAP_POPULATE 0x008000 /* populate (prefault) pagetables */ +#define MAP_NONBLOCK 0x010000 /* do not block on IO */ +#define MAP_STACK 0x020000 /* give out an address that is best suited for process/thread stacks */ +#define MAP_HUGETLB 0x040000 /* create a huge page mapping */ +#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */ +#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ + +#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be + * uninitialized */ + +/* + * Flags for mlock + */ +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ + +#define MS_ASYNC 1 /* sync memory asynchronously */ +#define MS_INVALIDATE 2 /* invalidate the caches */ +#define MS_SYNC 4 /* synchronous memory sync */ + +#define MADV_NORMAL 0 /* no further special treatment */ +#define MADV_RANDOM 1 /* expect random page references */ +#define MADV_SEQUENTIAL 2 /* expect sequential page references */ +#define MADV_WILLNEED 3 /* will need these pages */ +#define MADV_DONTNEED 4 /* don't need these pages */ + +/* common parameters: try to keep these consistent across architectures */ +#define MADV_FREE 8 /* free pages only if memory pressure */ +#define MADV_REMOVE 9 /* remove these pages & resources */ +#define MADV_DONTFORK 10 /* don't inherit across fork */ +#define MADV_DOFORK 11 /* do inherit across fork */ +#define MADV_HWPOISON 100 /* poison a page for testing */ +#define MADV_SOFT_OFFLINE 101 /* soft offline page for testing */ + +#define MADV_MERGEABLE 12 /* KSM may merge identical pages */ +#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */ + +#define MADV_HUGEPAGE 14 /* Worth backing with hugepages */ +#define MADV_NOHUGEPAGE 15 /* Not worth backing with hugepages */ + +#define MADV_DONTDUMP 16 /* Explicity exclude from the core dump, + overrides the coredump filter bits */ +#define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */ + +#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */ +#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */ + +#define MADV_COLD 20 /* deactivate these pages */ +#define MADV_PAGEOUT 21 /* reclaim these pages */ + +#define MADV_POPULATE_READ 22 /* populate (prefault) page tables readable */ +#define MADV_POPULATE_WRITE 23 /* populate (prefault) page tables writable */ + +#define MADV_DONTNEED_LOCKED 24 /* like DONTNEED, but drop locked pages too */ + +#define MADV_COLLAPSE 25 /* Synchronous hugepage collapse */ + +#define MADV_GUARD_INSTALL 102 /* fatal signal on access to range */ +#define MADV_GUARD_REMOVE 103 /* unguard range */ + +/* compatibility flags */ +#define MAP_FILE 0 + +#define PKEY_UNRESTRICTED 0x0 +#define PKEY_DISABLE_ACCESS 0x1 +#define PKEY_DISABLE_WRITE 0x2 +#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\ + PKEY_DISABLE_WRITE) + +#endif /* __ASM_GENERIC_MMAN_COMMON_H */ diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h new file mode 100644 index 000000000..51d2556af --- /dev/null +++ b/tools/include/uapi/asm-generic/mman.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_MMAN_H +#define __ASM_GENERIC_MMAN_H + +#include + +#define MAP_GROWSDOWN 0x0100 /* stack-like segment */ +#define MAP_DENYWRITE 0x0800 /* ETXTBSY */ +#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */ +#define MAP_LOCKED 0x2000 /* pages are locked */ +#define MAP_NORESERVE 0x4000 /* don't check for reservations */ + +/* + * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h + * for MAP_HUGETLB usage + */ + +#define MCL_CURRENT 1 /* lock all current mappings */ +#define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ + +#define SHADOW_STACK_SET_TOKEN (1ULL << 0) /* Set up a restore token in the shadow stack */ +#define SHADOW_STACK_SET_MARKER (1ULL << 1) /* Set up a top of stack marker in the shadow stack */ + + +#endif /* __ASM_GENERIC_MMAN_H */ diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h new file mode 100644 index 000000000..f333a0ac4 --- /dev/null +++ b/tools/include/uapi/asm-generic/socket.h @@ -0,0 +1,175 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_GENERIC_SOCKET_H +#define __ASM_GENERIC_SOCKET_H + +#include +#include + +/* For setsockopt(2) */ +#define SOL_SOCKET 1 + +#define SO_DEBUG 1 +#define SO_REUSEADDR 2 +#define SO_TYPE 3 +#define SO_ERROR 4 +#define SO_DONTROUTE 5 +#define SO_BROADCAST 6 +#define SO_SNDBUF 7 +#define SO_RCVBUF 8 +#define SO_SNDBUFFORCE 32 +#define SO_RCVBUFFORCE 33 +#define SO_KEEPALIVE 9 +#define SO_OOBINLINE 10 +#define SO_NO_CHECK 11 +#define SO_PRIORITY 12 +#define SO_LINGER 13 +#define SO_BSDCOMPAT 14 +#define SO_REUSEPORT 15 +#ifndef SO_PASSCRED /* powerpc only differs in these */ +#define SO_PASSCRED 16 +#define SO_PEERCRED 17 +#define SO_RCVLOWAT 18 +#define SO_SNDLOWAT 19 +#define SO_RCVTIMEO_OLD 20 +#define SO_SNDTIMEO_OLD 21 +#endif + +/* Security levels - as per NRL IPv6 - don't actually do anything */ +#define SO_SECURITY_AUTHENTICATION 22 +#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 +#define SO_SECURITY_ENCRYPTION_NETWORK 24 + +#define SO_BINDTODEVICE 25 + +/* Socket filtering */ +#define SO_ATTACH_FILTER 26 +#define SO_DETACH_FILTER 27 +#define SO_GET_FILTER SO_ATTACH_FILTER + +#define SO_PEERNAME 28 + +#define SO_ACCEPTCONN 30 + +#define SO_PEERSEC 31 +#define SO_PASSSEC 34 + +#define SO_MARK 36 + +#define SO_PROTOCOL 38 +#define SO_DOMAIN 39 + +#define SO_RXQ_OVFL 40 + +#define SO_WIFI_STATUS 41 +#define SCM_WIFI_STATUS SO_WIFI_STATUS +#define SO_PEEK_OFF 42 + +/* Instruct lower device to use last 4-bytes of skb data as FCS */ +#define SO_NOFCS 43 + +#define SO_LOCK_FILTER 44 + +#define SO_SELECT_ERR_QUEUE 45 + +#define SO_BUSY_POLL 46 + +#define SO_MAX_PACING_RATE 47 + +#define SO_BPF_EXTENSIONS 48 + +#define SO_INCOMING_CPU 49 + +#define SO_ATTACH_BPF 50 +#define SO_DETACH_BPF SO_DETACH_FILTER + +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + +#define SO_CNX_ADVICE 53 + +#define SCM_TIMESTAMPING_OPT_STATS 54 + +#define SO_MEMINFO 55 + +#define SO_INCOMING_NAPI_ID 56 + +#define SO_COOKIE 57 + +#define SCM_TIMESTAMPING_PKTINFO 58 + +#define SO_PEERGROUPS 59 + +#define SO_ZEROCOPY 60 + +#define SO_TXTIME 61 +#define SCM_TXTIME SO_TXTIME + +#define SO_BINDTOIFINDEX 62 + +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#define SO_DETACH_REUSEPORT_BPF 68 + +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + +#define SO_NETNS_COOKIE 71 + +#define SO_BUF_LOCK 72 + +#define SO_RESERVE_MEM 73 + +#define SO_TXREHASH 74 + +#define SO_RCVMARK 75 + +#define SO_PASSPIDFD 76 +#define SO_PEERPIDFD 77 + +#define SO_DEVMEM_LINEAR 78 +#define SCM_DEVMEM_LINEAR SO_DEVMEM_LINEAR +#define SO_DEVMEM_DMABUF 79 +#define SCM_DEVMEM_DMABUF SO_DEVMEM_DMABUF +#define SO_DEVMEM_DONTNEED 80 + +#define SCM_TS_OPT_ID 81 + +#define SO_RCVPRIORITY 82 + +#define SO_PASSRIGHTS 83 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +/* on 64-bit and x32, avoid the ?: operator */ +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + +#endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h new file mode 100644 index 000000000..5b7e77a7c --- /dev/null +++ b/tools/include/uapi/asm-generic/unistd.h @@ -0,0 +1,919 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#include + +/* + * This file contains the system call numbers, based on the + * layout of the x86-64 architecture, which embeds the + * pointer to the syscall in the table. + * + * As a basic principle, no duplication of functionality + * should be added, e.g. we don't use lseek when llseek + * is present. New architectures should use this file + * and implement the less feature-full calls in user space. + */ + +#ifndef __SYSCALL +#define __SYSCALL(x, y) +#endif + +#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT) +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32) +#else +#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64) +#endif + +#ifdef __SYSCALL_COMPAT +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp) +#else +#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys) +#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64) +#endif + +#define __NR_io_setup 0 +__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup) +#define __NR_io_destroy 1 +__SYSCALL(__NR_io_destroy, sys_io_destroy) +#define __NR_io_submit 2 +__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit) +#define __NR_io_cancel 3 +__SYSCALL(__NR_io_cancel, sys_io_cancel) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_io_getevents 4 +__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents) +#endif + +#define __NR_setxattr 5 +__SYSCALL(__NR_setxattr, sys_setxattr) +#define __NR_lsetxattr 6 +__SYSCALL(__NR_lsetxattr, sys_lsetxattr) +#define __NR_fsetxattr 7 +__SYSCALL(__NR_fsetxattr, sys_fsetxattr) +#define __NR_getxattr 8 +__SYSCALL(__NR_getxattr, sys_getxattr) +#define __NR_lgetxattr 9 +__SYSCALL(__NR_lgetxattr, sys_lgetxattr) +#define __NR_fgetxattr 10 +__SYSCALL(__NR_fgetxattr, sys_fgetxattr) +#define __NR_listxattr 11 +__SYSCALL(__NR_listxattr, sys_listxattr) +#define __NR_llistxattr 12 +__SYSCALL(__NR_llistxattr, sys_llistxattr) +#define __NR_flistxattr 13 +__SYSCALL(__NR_flistxattr, sys_flistxattr) +#define __NR_removexattr 14 +__SYSCALL(__NR_removexattr, sys_removexattr) +#define __NR_lremovexattr 15 +__SYSCALL(__NR_lremovexattr, sys_lremovexattr) +#define __NR_fremovexattr 16 +__SYSCALL(__NR_fremovexattr, sys_fremovexattr) +#define __NR_getcwd 17 +__SYSCALL(__NR_getcwd, sys_getcwd) +#define __NR_lookup_dcookie 18 +__SYSCALL(__NR_lookup_dcookie, sys_ni_syscall) +#define __NR_eventfd2 19 +__SYSCALL(__NR_eventfd2, sys_eventfd2) +#define __NR_epoll_create1 20 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) +#define __NR_epoll_ctl 21 +__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl) +#define __NR_epoll_pwait 22 +__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait) +#define __NR_dup 23 +__SYSCALL(__NR_dup, sys_dup) +#define __NR_dup3 24 +__SYSCALL(__NR_dup3, sys_dup3) +#define __NR3264_fcntl 25 +__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64) +#define __NR_inotify_init1 26 +__SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_inotify_add_watch 27 +__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch) +#define __NR_inotify_rm_watch 28 +__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch) +#define __NR_ioctl 29 +__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl) +#define __NR_ioprio_set 30 +__SYSCALL(__NR_ioprio_set, sys_ioprio_set) +#define __NR_ioprio_get 31 +__SYSCALL(__NR_ioprio_get, sys_ioprio_get) +#define __NR_flock 32 +__SYSCALL(__NR_flock, sys_flock) +#define __NR_mknodat 33 +__SYSCALL(__NR_mknodat, sys_mknodat) +#define __NR_mkdirat 34 +__SYSCALL(__NR_mkdirat, sys_mkdirat) +#define __NR_unlinkat 35 +__SYSCALL(__NR_unlinkat, sys_unlinkat) +#define __NR_symlinkat 36 +__SYSCALL(__NR_symlinkat, sys_symlinkat) +#define __NR_linkat 37 +__SYSCALL(__NR_linkat, sys_linkat) + +#ifdef __ARCH_WANT_RENAMEAT +/* renameat is superseded with flags by renameat2 */ +#define __NR_renameat 38 +__SYSCALL(__NR_renameat, sys_renameat) +#endif /* __ARCH_WANT_RENAMEAT */ + +#define __NR_umount2 39 +__SYSCALL(__NR_umount2, sys_umount) +#define __NR_mount 40 +__SYSCALL(__NR_mount, sys_mount) +#define __NR_pivot_root 41 +__SYSCALL(__NR_pivot_root, sys_pivot_root) +#define __NR_nfsservctl 42 +__SYSCALL(__NR_nfsservctl, sys_ni_syscall) +#define __NR3264_statfs 43 +__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \ + compat_sys_statfs64) +#define __NR3264_fstatfs 44 +__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \ + compat_sys_fstatfs64) +#define __NR3264_truncate 45 +__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \ + compat_sys_truncate64) +#define __NR3264_ftruncate 46 +__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \ + compat_sys_ftruncate64) +#define __NR_fallocate 47 +__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate) +#define __NR_faccessat 48 +__SYSCALL(__NR_faccessat, sys_faccessat) +#define __NR_chdir 49 +__SYSCALL(__NR_chdir, sys_chdir) +#define __NR_fchdir 50 +__SYSCALL(__NR_fchdir, sys_fchdir) +#define __NR_chroot 51 +__SYSCALL(__NR_chroot, sys_chroot) +#define __NR_fchmod 52 +__SYSCALL(__NR_fchmod, sys_fchmod) +#define __NR_fchmodat 53 +__SYSCALL(__NR_fchmodat, sys_fchmodat) +#define __NR_fchownat 54 +__SYSCALL(__NR_fchownat, sys_fchownat) +#define __NR_fchown 55 +__SYSCALL(__NR_fchown, sys_fchown) +#define __NR_openat 56 +__SYSCALL(__NR_openat, sys_openat) +#define __NR_close 57 +__SYSCALL(__NR_close, sys_close) +#define __NR_vhangup 58 +__SYSCALL(__NR_vhangup, sys_vhangup) +#define __NR_pipe2 59 +__SYSCALL(__NR_pipe2, sys_pipe2) +#define __NR_quotactl 60 +__SYSCALL(__NR_quotactl, sys_quotactl) +#define __NR_getdents64 61 +__SYSCALL(__NR_getdents64, sys_getdents64) +#define __NR3264_lseek 62 +__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek) +#define __NR_read 63 +__SYSCALL(__NR_read, sys_read) +#define __NR_write 64 +__SYSCALL(__NR_write, sys_write) +#define __NR_readv 65 +__SC_COMP(__NR_readv, sys_readv, sys_readv) +#define __NR_writev 66 +__SC_COMP(__NR_writev, sys_writev, sys_writev) +#define __NR_pread64 67 +__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64) +#define __NR_pwrite64 68 +__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64) +#define __NR_preadv 69 +__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv) +#define __NR_pwritev 70 +__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev) +#define __NR3264_sendfile 71 +__SYSCALL(__NR3264_sendfile, sys_sendfile64) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_pselect6 72 +__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32) +#define __NR_ppoll 73 +__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32) +#endif + +#define __NR_signalfd4 74 +__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4) +#define __NR_vmsplice 75 +__SYSCALL(__NR_vmsplice, sys_vmsplice) +#define __NR_splice 76 +__SYSCALL(__NR_splice, sys_splice) +#define __NR_tee 77 +__SYSCALL(__NR_tee, sys_tee) +#define __NR_readlinkat 78 +__SYSCALL(__NR_readlinkat, sys_readlinkat) + +#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64) +#define __NR3264_fstatat 79 +__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat) +#define __NR3264_fstat 80 +__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat) +#endif + +#define __NR_sync 81 +__SYSCALL(__NR_sync, sys_sync) +#define __NR_fsync 82 +__SYSCALL(__NR_fsync, sys_fsync) +#define __NR_fdatasync 83 +__SYSCALL(__NR_fdatasync, sys_fdatasync) + +#ifdef __ARCH_WANT_SYNC_FILE_RANGE2 +#define __NR_sync_file_range2 84 +__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \ + compat_sys_sync_file_range2) +#else +#define __NR_sync_file_range 84 +__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \ + compat_sys_sync_file_range) +#endif + +#define __NR_timerfd_create 85 +__SYSCALL(__NR_timerfd_create, sys_timerfd_create) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_timerfd_settime 86 +__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \ + sys_timerfd_settime) +#define __NR_timerfd_gettime 87 +__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \ + sys_timerfd_gettime) +#endif + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_utimensat 88 +__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat) +#endif + +#define __NR_acct 89 +__SYSCALL(__NR_acct, sys_acct) +#define __NR_capget 90 +__SYSCALL(__NR_capget, sys_capget) +#define __NR_capset 91 +__SYSCALL(__NR_capset, sys_capset) +#define __NR_personality 92 +__SYSCALL(__NR_personality, sys_personality) +#define __NR_exit 93 +__SYSCALL(__NR_exit, sys_exit) +#define __NR_exit_group 94 +__SYSCALL(__NR_exit_group, sys_exit_group) +#define __NR_waitid 95 +__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid) +#define __NR_set_tid_address 96 +__SYSCALL(__NR_set_tid_address, sys_set_tid_address) +#define __NR_unshare 97 +__SYSCALL(__NR_unshare, sys_unshare) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_futex 98 +__SC_3264(__NR_futex, sys_futex_time32, sys_futex) +#endif + +#define __NR_set_robust_list 99 +__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \ + compat_sys_set_robust_list) +#define __NR_get_robust_list 100 +__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \ + compat_sys_get_robust_list) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_nanosleep 101 +__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep) +#endif + +#define __NR_getitimer 102 +__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer) +#define __NR_setitimer 103 +__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer) +#define __NR_kexec_load 104 +__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load) +#define __NR_init_module 105 +__SYSCALL(__NR_init_module, sys_init_module) +#define __NR_delete_module 106 +__SYSCALL(__NR_delete_module, sys_delete_module) +#define __NR_timer_create 107 +__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_timer_gettime 108 +__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime) +#endif + +#define __NR_timer_getoverrun 109 +__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_timer_settime 110 +__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime) +#endif + +#define __NR_timer_delete 111 +__SYSCALL(__NR_timer_delete, sys_timer_delete) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_clock_settime 112 +__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime) +#define __NR_clock_gettime 113 +__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime) +#define __NR_clock_getres 114 +__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres) +#define __NR_clock_nanosleep 115 +__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \ + sys_clock_nanosleep) +#endif + +#define __NR_syslog 116 +__SYSCALL(__NR_syslog, sys_syslog) +#define __NR_ptrace 117 +__SC_COMP(__NR_ptrace, sys_ptrace, compat_sys_ptrace) +#define __NR_sched_setparam 118 +__SYSCALL(__NR_sched_setparam, sys_sched_setparam) +#define __NR_sched_setscheduler 119 +__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler) +#define __NR_sched_getscheduler 120 +__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler) +#define __NR_sched_getparam 121 +__SYSCALL(__NR_sched_getparam, sys_sched_getparam) +#define __NR_sched_setaffinity 122 +__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \ + compat_sys_sched_setaffinity) +#define __NR_sched_getaffinity 123 +__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \ + compat_sys_sched_getaffinity) +#define __NR_sched_yield 124 +__SYSCALL(__NR_sched_yield, sys_sched_yield) +#define __NR_sched_get_priority_max 125 +__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max) +#define __NR_sched_get_priority_min 126 +__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_sched_rr_get_interval 127 +__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \ + sys_sched_rr_get_interval) +#endif + +#define __NR_restart_syscall 128 +__SYSCALL(__NR_restart_syscall, sys_restart_syscall) +#define __NR_kill 129 +__SYSCALL(__NR_kill, sys_kill) +#define __NR_tkill 130 +__SYSCALL(__NR_tkill, sys_tkill) +#define __NR_tgkill 131 +__SYSCALL(__NR_tgkill, sys_tgkill) +#define __NR_sigaltstack 132 +__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack) +#define __NR_rt_sigsuspend 133 +__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend) +#define __NR_rt_sigaction 134 +__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction) +#define __NR_rt_sigprocmask 135 +__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask) +#define __NR_rt_sigpending 136 +__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_rt_sigtimedwait 137 +__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \ + sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32) +#endif + +#define __NR_rt_sigqueueinfo 138 +__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \ + compat_sys_rt_sigqueueinfo) +#define __NR_rt_sigreturn 139 +__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn) +#define __NR_setpriority 140 +__SYSCALL(__NR_setpriority, sys_setpriority) +#define __NR_getpriority 141 +__SYSCALL(__NR_getpriority, sys_getpriority) +#define __NR_reboot 142 +__SYSCALL(__NR_reboot, sys_reboot) +#define __NR_setregid 143 +__SYSCALL(__NR_setregid, sys_setregid) +#define __NR_setgid 144 +__SYSCALL(__NR_setgid, sys_setgid) +#define __NR_setreuid 145 +__SYSCALL(__NR_setreuid, sys_setreuid) +#define __NR_setuid 146 +__SYSCALL(__NR_setuid, sys_setuid) +#define __NR_setresuid 147 +__SYSCALL(__NR_setresuid, sys_setresuid) +#define __NR_getresuid 148 +__SYSCALL(__NR_getresuid, sys_getresuid) +#define __NR_setresgid 149 +__SYSCALL(__NR_setresgid, sys_setresgid) +#define __NR_getresgid 150 +__SYSCALL(__NR_getresgid, sys_getresgid) +#define __NR_setfsuid 151 +__SYSCALL(__NR_setfsuid, sys_setfsuid) +#define __NR_setfsgid 152 +__SYSCALL(__NR_setfsgid, sys_setfsgid) +#define __NR_times 153 +__SC_COMP(__NR_times, sys_times, compat_sys_times) +#define __NR_setpgid 154 +__SYSCALL(__NR_setpgid, sys_setpgid) +#define __NR_getpgid 155 +__SYSCALL(__NR_getpgid, sys_getpgid) +#define __NR_getsid 156 +__SYSCALL(__NR_getsid, sys_getsid) +#define __NR_setsid 157 +__SYSCALL(__NR_setsid, sys_setsid) +#define __NR_getgroups 158 +__SYSCALL(__NR_getgroups, sys_getgroups) +#define __NR_setgroups 159 +__SYSCALL(__NR_setgroups, sys_setgroups) +#define __NR_uname 160 +__SYSCALL(__NR_uname, sys_newuname) +#define __NR_sethostname 161 +__SYSCALL(__NR_sethostname, sys_sethostname) +#define __NR_setdomainname 162 +__SYSCALL(__NR_setdomainname, sys_setdomainname) + +#ifdef __ARCH_WANT_SET_GET_RLIMIT +/* getrlimit and setrlimit are superseded with prlimit64 */ +#define __NR_getrlimit 163 +__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit) +#define __NR_setrlimit 164 +__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit) +#endif + +#define __NR_getrusage 165 +__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage) +#define __NR_umask 166 +__SYSCALL(__NR_umask, sys_umask) +#define __NR_prctl 167 +__SYSCALL(__NR_prctl, sys_prctl) +#define __NR_getcpu 168 +__SYSCALL(__NR_getcpu, sys_getcpu) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_gettimeofday 169 +__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday) +#define __NR_settimeofday 170 +__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday) +#define __NR_adjtimex 171 +__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex) +#endif + +#define __NR_getpid 172 +__SYSCALL(__NR_getpid, sys_getpid) +#define __NR_getppid 173 +__SYSCALL(__NR_getppid, sys_getppid) +#define __NR_getuid 174 +__SYSCALL(__NR_getuid, sys_getuid) +#define __NR_geteuid 175 +__SYSCALL(__NR_geteuid, sys_geteuid) +#define __NR_getgid 176 +__SYSCALL(__NR_getgid, sys_getgid) +#define __NR_getegid 177 +__SYSCALL(__NR_getegid, sys_getegid) +#define __NR_gettid 178 +__SYSCALL(__NR_gettid, sys_gettid) +#define __NR_sysinfo 179 +__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo) +#define __NR_mq_open 180 +__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open) +#define __NR_mq_unlink 181 +__SYSCALL(__NR_mq_unlink, sys_mq_unlink) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_mq_timedsend 182 +__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend) +#define __NR_mq_timedreceive 183 +__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \ + sys_mq_timedreceive) +#endif + +#define __NR_mq_notify 184 +__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify) +#define __NR_mq_getsetattr 185 +__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr) +#define __NR_msgget 186 +__SYSCALL(__NR_msgget, sys_msgget) +#define __NR_msgctl 187 +__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl) +#define __NR_msgrcv 188 +__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv) +#define __NR_msgsnd 189 +__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd) +#define __NR_semget 190 +__SYSCALL(__NR_semget, sys_semget) +#define __NR_semctl 191 +__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_semtimedop 192 +__SC_3264(__NR_semtimedop, sys_semtimedop_time32, sys_semtimedop) +#endif + +#define __NR_semop 193 +__SYSCALL(__NR_semop, sys_semop) +#define __NR_shmget 194 +__SYSCALL(__NR_shmget, sys_shmget) +#define __NR_shmctl 195 +__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl) +#define __NR_shmat 196 +__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat) +#define __NR_shmdt 197 +__SYSCALL(__NR_shmdt, sys_shmdt) +#define __NR_socket 198 +__SYSCALL(__NR_socket, sys_socket) +#define __NR_socketpair 199 +__SYSCALL(__NR_socketpair, sys_socketpair) +#define __NR_bind 200 +__SYSCALL(__NR_bind, sys_bind) +#define __NR_listen 201 +__SYSCALL(__NR_listen, sys_listen) +#define __NR_accept 202 +__SYSCALL(__NR_accept, sys_accept) +#define __NR_connect 203 +__SYSCALL(__NR_connect, sys_connect) +#define __NR_getsockname 204 +__SYSCALL(__NR_getsockname, sys_getsockname) +#define __NR_getpeername 205 +__SYSCALL(__NR_getpeername, sys_getpeername) +#define __NR_sendto 206 +__SYSCALL(__NR_sendto, sys_sendto) +#define __NR_recvfrom 207 +__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom) +#define __NR_setsockopt 208 +__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt) +#define __NR_getsockopt 209 +__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt) +#define __NR_shutdown 210 +__SYSCALL(__NR_shutdown, sys_shutdown) +#define __NR_sendmsg 211 +__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg) +#define __NR_recvmsg 212 +__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg) +#define __NR_readahead 213 +__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead) +#define __NR_brk 214 +__SYSCALL(__NR_brk, sys_brk) +#define __NR_munmap 215 +__SYSCALL(__NR_munmap, sys_munmap) +#define __NR_mremap 216 +__SYSCALL(__NR_mremap, sys_mremap) +#define __NR_add_key 217 +__SYSCALL(__NR_add_key, sys_add_key) +#define __NR_request_key 218 +__SYSCALL(__NR_request_key, sys_request_key) +#define __NR_keyctl 219 +__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl) +#define __NR_clone 220 +__SYSCALL(__NR_clone, sys_clone) +#define __NR_execve 221 +__SC_COMP(__NR_execve, sys_execve, compat_sys_execve) +#define __NR3264_mmap 222 +__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap) +#define __NR3264_fadvise64 223 +__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64) + +/* CONFIG_MMU only */ +#ifndef __ARCH_NOMMU +#define __NR_swapon 224 +__SYSCALL(__NR_swapon, sys_swapon) +#define __NR_swapoff 225 +__SYSCALL(__NR_swapoff, sys_swapoff) +#define __NR_mprotect 226 +__SYSCALL(__NR_mprotect, sys_mprotect) +#define __NR_msync 227 +__SYSCALL(__NR_msync, sys_msync) +#define __NR_mlock 228 +__SYSCALL(__NR_mlock, sys_mlock) +#define __NR_munlock 229 +__SYSCALL(__NR_munlock, sys_munlock) +#define __NR_mlockall 230 +__SYSCALL(__NR_mlockall, sys_mlockall) +#define __NR_munlockall 231 +__SYSCALL(__NR_munlockall, sys_munlockall) +#define __NR_mincore 232 +__SYSCALL(__NR_mincore, sys_mincore) +#define __NR_madvise 233 +__SYSCALL(__NR_madvise, sys_madvise) +#define __NR_remap_file_pages 234 +__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages) +#define __NR_mbind 235 +__SYSCALL(__NR_mbind, sys_mbind) +#define __NR_get_mempolicy 236 +__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy) +#define __NR_set_mempolicy 237 +__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy) +#define __NR_migrate_pages 238 +__SYSCALL(__NR_migrate_pages, sys_migrate_pages) +#define __NR_move_pages 239 +__SYSCALL(__NR_move_pages, sys_move_pages) +#endif + +#define __NR_rt_tgsigqueueinfo 240 +__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \ + compat_sys_rt_tgsigqueueinfo) +#define __NR_perf_event_open 241 +__SYSCALL(__NR_perf_event_open, sys_perf_event_open) +#define __NR_accept4 242 +__SYSCALL(__NR_accept4, sys_accept4) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_recvmmsg 243 +__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32) +#endif + +/* + * Architectures may provide up to 16 syscalls of their own + * starting with this value. + */ +#define __NR_arch_specific_syscall 244 + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_wait4 260 +__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4) +#endif + +#define __NR_prlimit64 261 +__SYSCALL(__NR_prlimit64, sys_prlimit64) +#define __NR_fanotify_init 262 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 263 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_name_to_handle_at 264 +__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at) +#define __NR_open_by_handle_at 265 +__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_clock_adjtime 266 +__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime) +#endif + +#define __NR_syncfs 267 +__SYSCALL(__NR_syncfs, sys_syncfs) +#define __NR_setns 268 +__SYSCALL(__NR_setns, sys_setns) +#define __NR_sendmmsg 269 +__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg) +#define __NR_process_vm_readv 270 +__SYSCALL(__NR_process_vm_readv, sys_process_vm_readv) +#define __NR_process_vm_writev 271 +__SYSCALL(__NR_process_vm_writev, sys_process_vm_writev) +#define __NR_kcmp 272 +__SYSCALL(__NR_kcmp, sys_kcmp) +#define __NR_finit_module 273 +__SYSCALL(__NR_finit_module, sys_finit_module) +#define __NR_sched_setattr 274 +__SYSCALL(__NR_sched_setattr, sys_sched_setattr) +#define __NR_sched_getattr 275 +__SYSCALL(__NR_sched_getattr, sys_sched_getattr) +#define __NR_renameat2 276 +__SYSCALL(__NR_renameat2, sys_renameat2) +#define __NR_seccomp 277 +__SYSCALL(__NR_seccomp, sys_seccomp) +#define __NR_getrandom 278 +__SYSCALL(__NR_getrandom, sys_getrandom) +#define __NR_memfd_create 279 +__SYSCALL(__NR_memfd_create, sys_memfd_create) +#define __NR_bpf 280 +__SYSCALL(__NR_bpf, sys_bpf) +#define __NR_execveat 281 +__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) +#define __NR_userfaultfd 282 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 283 +__SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 284 +__SYSCALL(__NR_mlock2, sys_mlock2) +#define __NR_copy_file_range 285 +__SYSCALL(__NR_copy_file_range, sys_copy_file_range) +#define __NR_preadv2 286 +__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2) +#define __NR_pwritev2 287 +__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2) +#define __NR_pkey_mprotect 288 +__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect) +#define __NR_pkey_alloc 289 +__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc) +#define __NR_pkey_free 290 +__SYSCALL(__NR_pkey_free, sys_pkey_free) +#define __NR_statx 291 +__SYSCALL(__NR_statx, sys_statx) + +#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32 +#define __NR_io_pgetevents 292 +__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents) +#endif + +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) +#define __NR_kexec_file_load 294 +__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) + +/* 295 through 402 are unassigned to sync up with generic numbers, don't use */ + +#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32 +#define __NR_clock_gettime64 403 +__SYSCALL(__NR_clock_gettime64, sys_clock_gettime) +#define __NR_clock_settime64 404 +__SYSCALL(__NR_clock_settime64, sys_clock_settime) +#define __NR_clock_adjtime64 405 +__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime) +#define __NR_clock_getres_time64 406 +__SYSCALL(__NR_clock_getres_time64, sys_clock_getres) +#define __NR_clock_nanosleep_time64 407 +__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep) +#define __NR_timer_gettime64 408 +__SYSCALL(__NR_timer_gettime64, sys_timer_gettime) +#define __NR_timer_settime64 409 +__SYSCALL(__NR_timer_settime64, sys_timer_settime) +#define __NR_timerfd_gettime64 410 +__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime) +#define __NR_timerfd_settime64 411 +__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime) +#define __NR_utimensat_time64 412 +__SYSCALL(__NR_utimensat_time64, sys_utimensat) +#define __NR_pselect6_time64 413 +__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64) +#define __NR_ppoll_time64 414 +__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64) +#define __NR_io_pgetevents_time64 416 +__SC_COMP(__NR_io_pgetevents_time64, sys_io_pgetevents, compat_sys_io_pgetevents_time64) +#define __NR_recvmmsg_time64 417 +__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64) +#define __NR_mq_timedsend_time64 418 +__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend) +#define __NR_mq_timedreceive_time64 419 +__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive) +#define __NR_semtimedop_time64 420 +__SYSCALL(__NR_semtimedop_time64, sys_semtimedop) +#define __NR_rt_sigtimedwait_time64 421 +__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64) +#define __NR_futex_time64 422 +__SYSCALL(__NR_futex_time64, sys_futex) +#define __NR_sched_rr_get_interval_time64 423 +__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval) +#endif + +#define __NR_pidfd_send_signal 424 +__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal) +#define __NR_io_uring_setup 425 +__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup) +#define __NR_io_uring_enter 426 +__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter) +#define __NR_io_uring_register 427 +__SYSCALL(__NR_io_uring_register, sys_io_uring_register) +#define __NR_open_tree 428 +__SYSCALL(__NR_open_tree, sys_open_tree) +#define __NR_move_mount 429 +__SYSCALL(__NR_move_mount, sys_move_mount) +#define __NR_fsopen 430 +__SYSCALL(__NR_fsopen, sys_fsopen) +#define __NR_fsconfig 431 +__SYSCALL(__NR_fsconfig, sys_fsconfig) +#define __NR_fsmount 432 +__SYSCALL(__NR_fsmount, sys_fsmount) +#define __NR_fspick 433 +__SYSCALL(__NR_fspick, sys_fspick) +#define __NR_pidfd_open 434 +__SYSCALL(__NR_pidfd_open, sys_pidfd_open) +#define __NR_clone3 435 +__SYSCALL(__NR_clone3, sys_clone3) +#define __NR_close_range 436 +__SYSCALL(__NR_close_range, sys_close_range) +#define __NR_openat2 437 +__SYSCALL(__NR_openat2, sys_openat2) +#define __NR_pidfd_getfd 438 +__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd) +#define __NR_faccessat2 439 +__SYSCALL(__NR_faccessat2, sys_faccessat2) +#define __NR_process_madvise 440 +__SYSCALL(__NR_process_madvise, sys_process_madvise) +#define __NR_epoll_pwait2 441 +__SC_COMP(__NR_epoll_pwait2, sys_epoll_pwait2, compat_sys_epoll_pwait2) +#define __NR_mount_setattr 442 +__SYSCALL(__NR_mount_setattr, sys_mount_setattr) +#define __NR_quotactl_fd 443 +__SYSCALL(__NR_quotactl_fd, sys_quotactl_fd) +#define __NR_landlock_create_ruleset 444 +__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset) +#define __NR_landlock_add_rule 445 +__SYSCALL(__NR_landlock_add_rule, sys_landlock_add_rule) +#define __NR_landlock_restrict_self 446 +__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) + +#ifdef __ARCH_WANT_MEMFD_SECRET +#define __NR_memfd_secret 447 +__SYSCALL(__NR_memfd_secret, sys_memfd_secret) +#endif + +#define __NR_process_mrelease 448 +__SYSCALL(__NR_process_mrelease, sys_process_mrelease) +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) +#define __NR_cachestat 451 +__SYSCALL(__NR_cachestat, sys_cachestat) +#define __NR_fchmodat2 452 +__SYSCALL(__NR_fchmodat2, sys_fchmodat2) +#define __NR_map_shadow_stack 453 +__SYSCALL(__NR_map_shadow_stack, sys_map_shadow_stack) +#define __NR_futex_wake 454 +__SYSCALL(__NR_futex_wake, sys_futex_wake) +#define __NR_futex_wait 455 +__SYSCALL(__NR_futex_wait, sys_futex_wait) +#define __NR_futex_requeue 456 +__SYSCALL(__NR_futex_requeue, sys_futex_requeue) + +#define __NR_statmount 457 +__SYSCALL(__NR_statmount, sys_statmount) + +#define __NR_listmount 458 +__SYSCALL(__NR_listmount, sys_listmount) + +#define __NR_lsm_get_self_attr 459 +__SYSCALL(__NR_lsm_get_self_attr, sys_lsm_get_self_attr) +#define __NR_lsm_set_self_attr 460 +__SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr) +#define __NR_lsm_list_modules 461 +__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules) + +#define __NR_mseal 462 +__SYSCALL(__NR_mseal, sys_mseal) + +#define __NR_setxattrat 463 +__SYSCALL(__NR_setxattrat, sys_setxattrat) +#define __NR_getxattrat 464 +__SYSCALL(__NR_getxattrat, sys_getxattrat) +#define __NR_listxattrat 465 +__SYSCALL(__NR_listxattrat, sys_listxattrat) +#define __NR_removexattrat 466 +__SYSCALL(__NR_removexattrat, sys_removexattrat) +#define __NR_open_tree_attr 467 +__SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) + +/* fs/inode.c */ +#define __NR_file_getattr 468 +__SYSCALL(__NR_file_getattr, sys_file_getattr) +#define __NR_file_setattr 469 +__SYSCALL(__NR_file_setattr, sys_file_setattr) +#define __NR_listns 470 +__SYSCALL(__NR_listns, sys_listns) + +#define __NR_rseq_slice_yield 471 +__SYSCALL(__NR_rseq_slice_yield, sys_rseq_slice_yield) + +/* fs/open.c */ +#define __NR_fchroot 472 +__SYSCALL(__NR_fchroot, sys_fchroot) + +#undef __NR_syscalls +#define __NR_syscalls 473 + +/* + * 32 bit systems traditionally used different + * syscalls for off_t and loff_t arguments, while + * 64 bit systems only need the off_t version. + * For new 32 bit platforms, there is no need to + * implement the old 32 bit off_t syscalls, so + * they take different names. + * Here we map the numbers so that both versions + * use the same syscall table layout. + */ +#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT) +#define __NR_fcntl __NR3264_fcntl +#define __NR_statfs __NR3264_statfs +#define __NR_fstatfs __NR3264_fstatfs +#define __NR_truncate __NR3264_truncate +#define __NR_ftruncate __NR3264_ftruncate +#define __NR_lseek __NR3264_lseek +#define __NR_sendfile __NR3264_sendfile +#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64) +#define __NR_newfstatat __NR3264_fstatat +#define __NR_fstat __NR3264_fstat +#endif +#define __NR_mmap __NR3264_mmap +#define __NR_fadvise64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat __NR3264_stat +#define __NR_lstat __NR3264_lstat +#endif +#else +#define __NR_fcntl64 __NR3264_fcntl +#define __NR_statfs64 __NR3264_statfs +#define __NR_fstatfs64 __NR3264_fstatfs +#define __NR_truncate64 __NR3264_truncate +#define __NR_ftruncate64 __NR3264_ftruncate +#define __NR_llseek __NR3264_lseek +#define __NR_sendfile64 __NR3264_sendfile +#if defined(__ARCH_WANT_NEW_STAT) || defined(__ARCH_WANT_STAT64) +#define __NR_fstatat64 __NR3264_fstatat +#define __NR_fstat64 __NR3264_fstat +#endif +#define __NR_mmap2 __NR3264_mmap +#define __NR_fadvise64_64 __NR3264_fadvise64 +#ifdef __NR3264_stat +#define __NR_stat64 __NR3264_stat +#define __NR_lstat64 __NR3264_lstat +#endif +#endif diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000..c65267afc --- /dev/null +++ b/tools/include/uapi/asm/bitsperlong.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../../arch/x86/include/uapi/asm/bitsperlong.h" +#elif defined(__powerpc__) +#include "../../../arch/powerpc/include/uapi/asm/bitsperlong.h" +#elif defined(__s390__) +#include "../../../arch/s390/include/uapi/asm/bitsperlong.h" +#elif defined(__sparc__) +#include "../../../arch/sparc/include/uapi/asm/bitsperlong.h" +#elif defined(__mips__) +#include "../../../arch/mips/include/uapi/asm/bitsperlong.h" +#elif defined(__ia64__) +#include "../../../arch/ia64/include/uapi/asm/bitsperlong.h" +#elif defined(__alpha__) +#include "../../../arch/alpha/include/uapi/asm/bitsperlong.h" +#else +#include +#endif diff --git a/tools/include/uapi/asm/bpf_perf_event.h b/tools/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000..ff52668ab --- /dev/null +++ b/tools/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,13 @@ +#if defined(__aarch64__) +#include "../../arch/arm64/include/uapi/asm/bpf_perf_event.h" +#elif defined(__arc__) +#include "../../arch/arc/include/uapi/asm/bpf_perf_event.h" +#elif defined(__s390__) +#include "../../arch/s390/include/uapi/asm/bpf_perf_event.h" +#elif defined(__riscv) +#include "../../arch/riscv/include/uapi/asm/bpf_perf_event.h" +#elif defined(__loongarch__) +#include "../../arch/loongarch/include/uapi/asm/bpf_perf_event.h" +#else +#include +#endif diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h new file mode 100644 index 000000000..869379f91 --- /dev/null +++ b/tools/include/uapi/asm/errno.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if defined(__i386__) || defined(__x86_64__) +#include "../../../arch/x86/include/uapi/asm/errno.h" +#elif defined(__powerpc__) +#include "../../../arch/powerpc/include/uapi/asm/errno.h" +#elif defined(__sparc__) +#include "../../../arch/sparc/include/uapi/asm/errno.h" +#elif defined(__alpha__) +#include "../../../arch/alpha/include/uapi/asm/errno.h" +#elif defined(__mips__) +#include "../../../arch/mips/include/uapi/asm/errno.h" +#elif defined(__hppa__) +#include "../../../arch/parisc/include/uapi/asm/errno.h" +#else +#include +#endif diff --git a/tools/include/uapi/linux/acct.h b/tools/include/uapi/linux/acct.h new file mode 100644 index 000000000..1e2382ed4 --- /dev/null +++ b/tools/include/uapi/linux/acct.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * BSD Process Accounting for Linux - Definitions + * + * Author: Marco van Wieringen (mvw@planets.elm.net) + * + * This header file contains the definitions needed to implement + * BSD-style process accounting. The kernel accounting code and all + * user-level programs that try to do something useful with the + * process accounting log must include this file. + * + * Copyright (C) 1995 - 1997 Marco van Wieringen - ELM Consultancy B.V. + * + */ + +#ifndef _UAPI_LINUX_ACCT_H +#define _UAPI_LINUX_ACCT_H + +#include + +#include +#include + +/* + * comp_t is a 16-bit "floating" point number with a 3-bit base 8 + * exponent and a 13-bit fraction. + * comp2_t is 24-bit with 5-bit base 2 exponent and 20 bit fraction + * (leading 1 not stored). + * See linux/kernel/acct.c for the specific encoding systems used. + */ + +typedef __u16 comp_t; +typedef __u32 comp2_t; + +/* + * accounting file record + * + * This structure contains all of the information written out to the + * process accounting file whenever a process exits. + */ + +#define ACCT_COMM 16 + +struct acct +{ + char ac_flag; /* Flags */ + char ac_version; /* Always set to ACCT_VERSION */ + /* for binary compatibility back until 2.0 */ + __u16 ac_uid16; /* LSB of Real User ID */ + __u16 ac_gid16; /* LSB of Real Group ID */ + __u16 ac_tty; /* Control Terminal */ + /* __u32 range means times from 1970 to 2106 */ + __u32 ac_btime; /* Process Creation Time */ + comp_t ac_utime; /* User Time */ + comp_t ac_stime; /* System Time */ + comp_t ac_etime; /* Elapsed Time */ + comp_t ac_mem; /* Average Memory Usage */ + comp_t ac_io; /* Chars Transferred */ + comp_t ac_rw; /* Blocks Read or Written */ + comp_t ac_minflt; /* Minor Pagefaults */ + comp_t ac_majflt; /* Major Pagefaults */ + comp_t ac_swaps; /* Number of Swaps */ +/* m68k had no padding here. */ +#if !defined(CONFIG_M68K) || !defined(__KERNEL__) + __u16 ac_ahz; /* AHZ */ +#endif + __u32 ac_exitcode; /* Exitcode */ + char ac_comm[ACCT_COMM + 1]; /* Command Name */ + __u8 ac_etime_hi; /* Elapsed Time MSB */ + __u16 ac_etime_lo; /* Elapsed Time LSB */ + __u32 ac_uid; /* Real User ID */ + __u32 ac_gid; /* Real Group ID */ +}; + +struct acct_v3 +{ + char ac_flag; /* Flags */ + char ac_version; /* Always set to ACCT_VERSION */ + __u16 ac_tty; /* Control Terminal */ + __u32 ac_exitcode; /* Exitcode */ + __u32 ac_uid; /* Real User ID */ + __u32 ac_gid; /* Real Group ID */ + __u32 ac_pid; /* Process ID */ + __u32 ac_ppid; /* Parent Process ID */ + /* __u32 range means times from 1970 to 2106 */ + __u32 ac_btime; /* Process Creation Time */ +#ifdef __KERNEL__ + __u32 ac_etime; /* Elapsed Time */ +#else + float ac_etime; /* Elapsed Time */ +#endif + comp_t ac_utime; /* User Time */ + comp_t ac_stime; /* System Time */ + comp_t ac_mem; /* Average Memory Usage */ + comp_t ac_io; /* Chars Transferred */ + comp_t ac_rw; /* Blocks Read or Written */ + comp_t ac_minflt; /* Minor Pagefaults */ + comp_t ac_majflt; /* Major Pagefaults */ + comp_t ac_swaps; /* Number of Swaps */ + char ac_comm[ACCT_COMM]; /* Command Name */ +}; + +/* + * accounting flags + */ + /* bit set when the process/task ... */ +#define AFORK 0x01 /* ... executed fork, but did not exec */ +#define ASU 0x02 /* ... used super-user privileges */ +#define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */ +#define ACORE 0x08 /* ... dumped core */ +#define AXSIG 0x10 /* ... was killed by a signal */ +#define AGROUP 0x20 /* ... was the last task of the process (task group) */ + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) +#define ACCT_BYTEORDER 0x80 /* accounting file is big endian */ +#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) +#define ACCT_BYTEORDER 0x00 /* accounting file is little endian */ +#else +#error unspecified endianness +#endif + +#ifndef __KERNEL__ +#define ACCT_VERSION 2 +#define AHZ (HZ) +#endif /* __KERNEL */ + + +#endif /* _UAPI_LINUX_ACCT_H */ diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h new file mode 100644 index 000000000..a04afef9e --- /dev/null +++ b/tools/include/uapi/linux/bits.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* bits.h: Macros for dealing with bitmasks. */ + +#ifndef _UAPI_LINUX_BITS_H +#define _UAPI_LINUX_BITS_H + +#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) + +#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#define __GENMASK_U128(h, l) \ + ((_BIT128((h)) << 1) - (_BIT128(l))) + +#endif /* _UAPI_LINUX_BITS_H */ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h new file mode 100644 index 000000000..732b35cc0 --- /dev/null +++ b/tools/include/uapi/linux/bpf.h @@ -0,0 +1,7828 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ + +#include +#include + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_JMP32 0x06 /* jmp mode in word width */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word (64-bit) */ +#define BPF_MEMSX 0x80 /* load with sign extension */ +#define BPF_ATOMIC 0xc0 /* atomic memory ops - op type in immediate */ +#define BPF_XADD 0xc0 /* exclusive add - legacy name */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +/* jmp encodings */ +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ +#define BPF_JCOND 0xe0 /* conditional pseudo jumps: may_goto, goto_or_nop */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* atomic op type fields (stored in immediate) */ +#define BPF_FETCH 0x01 /* not an opcode on its own, used to build others */ +#define BPF_XCHG (0xe0 | BPF_FETCH) /* atomic exchange */ +#define BPF_CMPXCHG (0xf0 | BPF_FETCH) /* atomic compare-and-write */ + +#define BPF_LOAD_ACQ 0x100 /* load-acquire */ +#define BPF_STORE_REL 0x110 /* store-release */ + +enum bpf_cond_pseudo_jmp { + BPF_MAY_GOTO = 0, +}; + +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn { + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* Deprecated: use struct bpf_lpm_trie_key_u8 (when the "data" member is needed for + * byte access) or struct bpf_lpm_trie_key_hdr (when using an alternative type for + * the trailing flexible array member) instead. + */ +struct bpf_lpm_trie_key { + __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ + __u8 data[0]; /* Arbitrary size */ +}; + +/* Header for bpf_lpm_trie_key structs */ +struct bpf_lpm_trie_key_hdr { + __u32 prefixlen; +}; + +/* Key of an a BPF_MAP_TYPE_LPM_TRIE entry, with trailing byte array. */ +struct bpf_lpm_trie_key_u8 { + union { + struct bpf_lpm_trie_key_hdr hdr; + __u32 prefixlen; + }; + __u8 data[]; /* Arbitrary size */ +}; + +struct bpf_cgroup_storage_key { + __u64 cgroup_inode_id; /* cgroup inode id */ + __u32 attach_type; /* program attach type (enum bpf_attach_type) */ +}; + +enum bpf_cgroup_iter_order { + BPF_CGROUP_ITER_ORDER_UNSPEC = 0, + BPF_CGROUP_ITER_SELF_ONLY, /* process only a single object. */ + BPF_CGROUP_ITER_DESCENDANTS_PRE, /* walk descendants in pre-order. */ + BPF_CGROUP_ITER_DESCENDANTS_POST, /* walk descendants in post-order. */ + BPF_CGROUP_ITER_ANCESTORS_UP, /* walk ancestors upward. */ + /* + * Walks the immediate children of the specified parent + * cgroup_subsys_state. Unlike BPF_CGROUP_ITER_DESCENDANTS_PRE, + * BPF_CGROUP_ITER_DESCENDANTS_POST, and BPF_CGROUP_ITER_ANCESTORS_UP + * the iterator does not include the specified parent as one of the + * returned iterator elements. + */ + BPF_CGROUP_ITER_CHILDREN, +}; + +union bpf_iter_link_info { + struct { + __u32 map_fd; + } map; + struct { + enum bpf_cgroup_iter_order order; + + /* At most one of cgroup_fd and cgroup_id can be non-zero. If + * both are zero, the walk starts from the default cgroup v2 + * root. For walking v1 hierarchy, one should always explicitly + * specify cgroup_fd. + */ + __u32 cgroup_fd; + __u64 cgroup_id; + } cgroup; + /* Parameters of task iterators. */ + struct { + __u32 tid; + __u32 pid; + __u32 pid_fd; + } task; +}; + +/* BPF syscall commands, see bpf(2) man-page for more details. */ +/** + * DOC: eBPF Syscall Preamble + * + * The operation to be performed by the **bpf**\ () system call is determined + * by the *cmd* argument. Each operation takes an accompanying argument, + * provided via *attr*, which is a pointer to a union of type *bpf_attr* (see + * below). The size argument is the size of the union pointed to by *attr*. + */ +/** + * DOC: eBPF Syscall Commands + * + * BPF_MAP_CREATE + * Description + * Create a map and return a file descriptor that refers to the + * map. The close-on-exec file descriptor flag (see **fcntl**\ (2)) + * is automatically enabled for the new file descriptor. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_MAP_CREATE** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_LOOKUP_ELEM + * Description + * Look up an element with a given *key* in the map referred to + * by the file descriptor *map_fd*. + * + * The *flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_ELEM + * Description + * Create or update an element (key/value pair) in a specified map. + * + * The *flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create a new element or update an existing element. + * **BPF_NOEXIST** + * Create a new element only if it did not exist. + * **BPF_EXIST** + * Update an existing element. + * **BPF_F_LOCK** + * Update a spin_lock-ed map element. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, + * **E2BIG**, **EEXIST**, or **ENOENT**. + * + * **E2BIG** + * The number of elements in the map reached the + * *max_entries* limit specified at map creation time. + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_ELEM + * Description + * Look up and delete an element by key in a specified map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_GET_NEXT_KEY + * Description + * Look up an element by key in a specified map and return the key + * of the next element. Can be used to iterate over all elements + * in the map. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * The following cases can be used to iterate over all elements of + * the map: + * + * * If *key* is not found, the operation returns zero and sets + * the *next_key* pointer to the key of the first element. + * * If *key* is found, the operation returns zero and sets the + * *next_key* pointer to the key of the next element. + * * If *key* is the last element, returns -1 and *errno* is set + * to **ENOENT**. + * + * May set *errno* to **ENOMEM**, **EFAULT**, **EPERM**, or + * **EINVAL** on error. + * + * BPF_PROG_LOAD + * Description + * Verify and load an eBPF program, returning a new file + * descriptor associated with the program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_PROG_LOAD** will unload the eBPF program (but see NOTES). + * + * The close-on-exec file descriptor flag (see **fcntl**\ (2)) is + * automatically enabled for the new file descriptor. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_PIN + * Description + * Pin an eBPF program or map referred by the specified *bpf_fd* + * to the provided *pathname* on the filesystem. + * + * The *pathname* argument must not contain a dot ("."). + * + * On success, *pathname* retains a reference to the eBPF object, + * preventing deallocation of the object when the original + * *bpf_fd* is closed. This allow the eBPF object to live beyond + * **close**\ (\ *bpf_fd*\ ), and hence the lifetime of the parent + * process. + * + * Applying **unlink**\ (2) or similar calls to the *pathname* + * unpins the object from the filesystem, removing the reference. + * If no other file descriptors or filesystem nodes refer to the + * same object, it will be deallocated (see NOTES). + * + * The filesystem type for the parent directory of *pathname* must + * be **BPF_FS_MAGIC**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_OBJ_GET + * Description + * Open a file descriptor for the eBPF object pinned to the + * specified *pathname*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_PROG_ATTACH + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook. + * + * The *attach_type* specifies the eBPF attachment point to + * attach the program to, and must be one of *bpf_attach_type* + * (see below). + * + * The *attach_bpf_fd* must be a valid file descriptor for a + * loaded eBPF program of a cgroup, flow dissector, LIRC, sockmap + * or sock_ops type corresponding to the specified *attach_type*. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_TYPE_SK_SKB**, + * **BPF_PROG_TYPE_SK_MSG** + * + * eBPF map of socket type (eg **BPF_MAP_TYPE_SOCKHASH**). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_DETACH + * Description + * Detach the eBPF program associated with the *target_fd* at the + * hook specified by *attach_type*. The program must have been + * previously attached using **BPF_PROG_ATTACH**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_TEST_RUN + * Description + * Run the eBPF program associated with the *prog_fd* a *repeat* + * number of times against a provided program context *ctx_in* and + * data *data_in*, and return the modified program context + * *ctx_out*, *data_out* (for example, packet data), result of the + * execution *retval*, and *duration* of the test run. + * + * The sizes of the buffers provided as input and output + * parameters *ctx_in*, *ctx_out*, *data_in*, and *data_out* must + * be provided in the corresponding variables *ctx_size_in*, + * *ctx_size_out*, *data_size_in*, and/or *data_size_out*. If any + * of these parameters are not provided (ie set to NULL), the + * corresponding size field must be zero. + * + * Some program types have particular requirements: + * + * **BPF_PROG_TYPE_SK_LOOKUP** + * *data_in* and *data_out* must be NULL. + * + * **BPF_PROG_TYPE_RAW_TRACEPOINT**, + * **BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE** + * + * *ctx_out*, *data_in* and *data_out* must be NULL. + * *repeat* must be zero. + * + * BPF_PROG_RUN is an alias for BPF_PROG_TEST_RUN. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * **ENOSPC** + * Either *data_size_out* or *ctx_size_out* is too small. + * **ENOTSUPP** + * This command is not supported by the program type of + * the program referred to by *prog_fd*. + * + * BPF_PROG_GET_NEXT_ID + * Description + * Fetch the next eBPF program currently loaded into the kernel. + * + * Looks for the eBPF program with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF programs + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_GET_NEXT_ID + * Description + * Fetch the next eBPF map currently loaded into the kernel. + * + * Looks for the eBPF map with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF maps + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_PROG_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF program corresponding to + * *prog_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_MAP_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF map corresponding to + * *map_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_OBJ_GET_INFO_BY_FD + * Description + * Obtain information about the eBPF object corresponding to + * *bpf_fd*. + * + * Populates up to *info_len* bytes of *info*, which will be in + * one of the following formats depending on the eBPF object type + * of *bpf_fd*: + * + * * **struct bpf_prog_info** + * * **struct bpf_map_info** + * * **struct bpf_btf_info** + * * **struct bpf_link_info** + * * **struct bpf_token_info** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_QUERY + * Description + * Obtain information about eBPF programs associated with the + * specified *attach_type* hook. + * + * The *target_fd* must be a valid file descriptor for a kernel + * object which depends on the attach type of *attach_bpf_fd*: + * + * **BPF_PROG_TYPE_CGROUP_DEVICE**, + * **BPF_PROG_TYPE_CGROUP_SKB**, + * **BPF_PROG_TYPE_CGROUP_SOCK**, + * **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + * **BPF_PROG_TYPE_CGROUP_SOCKOPT**, + * **BPF_PROG_TYPE_CGROUP_SYSCTL**, + * **BPF_PROG_TYPE_SOCK_OPS** + * + * Control Group v2 hierarchy with the eBPF controller + * enabled. Requires the kernel to be compiled with + * **CONFIG_CGROUP_BPF**. + * + * **BPF_PROG_TYPE_FLOW_DISSECTOR** + * + * Network namespace (eg /proc/self/ns/net). + * + * **BPF_PROG_TYPE_LIRC_MODE2** + * + * LIRC device path (eg /dev/lircN). Requires the kernel + * to be compiled with **CONFIG_BPF_LIRC_MODE2**. + * + * **BPF_PROG_QUERY** always fetches the number of programs + * attached and the *attach_flags* which were used to attach those + * programs. Additionally, if *prog_ids* is nonzero and the number + * of attached programs is less than *prog_cnt*, populates + * *prog_ids* with the eBPF program ids of the programs attached + * at *target_fd*. + * + * The following flags may alter the result: + * + * **BPF_F_QUERY_EFFECTIVE** + * Only return information regarding programs which are + * currently effective at the specified *target_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_RAW_TRACEPOINT_OPEN + * Description + * Attach an eBPF program to a tracepoint *name* to access kernel + * internal arguments of the tracepoint in their raw form. + * + * The *prog_fd* must be a valid file descriptor associated with + * a loaded eBPF program of type **BPF_PROG_TYPE_RAW_TRACEPOINT**. + * + * No ABI guarantees are made about the content of tracepoint + * arguments exposed to the corresponding eBPF program. + * + * Applying **close**\ (2) to the file descriptor returned by + * **BPF_RAW_TRACEPOINT_OPEN** will delete the map (but see NOTES). + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_LOAD + * Description + * Verify and load BPF Type Format (BTF) metadata into the kernel, + * returning a new file descriptor associated with the metadata. + * BTF is described in more detail at + * https://www.kernel.org/doc/html/latest/bpf/btf.html. + * + * The *btf* parameter must point to valid memory providing + * *btf_size* bytes of BTF binary metadata. + * + * The returned file descriptor can be passed to other **bpf**\ () + * subcommands such as **BPF_PROG_LOAD** or **BPF_MAP_CREATE** to + * associate the BTF with those objects. + * + * Similar to **BPF_PROG_LOAD**, **BPF_BTF_LOAD** has optional + * parameters to specify a *btf_log_buf*, *btf_log_size* and + * *btf_log_level* which allow the kernel to return freeform log + * output regarding the BTF verification process. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_BTF_GET_FD_BY_ID + * Description + * Open a file descriptor for the BPF Type Format (BTF) + * corresponding to *btf_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_TASK_FD_QUERY + * Description + * Obtain information about eBPF programs associated with the + * target process identified by *pid* and *fd*. + * + * If the *pid* and *fd* are associated with a tracepoint, kprobe + * or uprobe perf event, then the *prog_id* and *fd_type* will + * be populated with the eBPF program id and file descriptor type + * of type **bpf_task_fd_type**. If associated with a kprobe or + * uprobe, the *probe_offset* and *probe_addr* will also be + * populated. Optionally, if *buf* is provided, then up to + * *buf_len* bytes of *buf* will be populated with the name of + * the tracepoint, kprobe or uprobe. + * + * The resulting *prog_id* may be introspected in deeper detail + * using **BPF_PROG_GET_FD_BY_ID** and **BPF_OBJ_GET_INFO_BY_FD**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_LOOKUP_AND_DELETE_ELEM + * Description + * Look up an element with the given *key* in the map referred to + * by the file descriptor *fd*, and if found, delete the element. + * + * For **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map + * types, the *flags* argument needs to be set to 0, but for other + * map types, it may be specified as: + * + * **BPF_F_LOCK** + * Look up and delete the value of a spin-locked map + * without returning the lock. This must be specified if + * the elements contain a spinlock. + * + * The **BPF_MAP_TYPE_QUEUE** and **BPF_MAP_TYPE_STACK** map types + * implement this command as a "pop" operation, deleting the top + * element rather than one corresponding to *key*. + * The *key* and *key_len* parameters should be zeroed when + * issuing this operation for these map types. + * + * This command is only valid for the following map types: + * * **BPF_MAP_TYPE_QUEUE** + * * **BPF_MAP_TYPE_STACK** + * * **BPF_MAP_TYPE_HASH** + * * **BPF_MAP_TYPE_PERCPU_HASH** + * * **BPF_MAP_TYPE_LRU_HASH** + * * **BPF_MAP_TYPE_LRU_PERCPU_HASH** + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_FREEZE + * Description + * Freeze the permissions of the specified map. + * + * Write permissions may be frozen by passing zero *flags*. + * Upon success, no future syscall invocations may alter the + * map state of *map_fd*. Write operations from eBPF programs + * are still possible for a frozen map. + * + * Not supported for maps of type **BPF_MAP_TYPE_STRUCT_OPS**. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_BTF_GET_NEXT_ID + * Description + * Fetch the next BPF Type Format (BTF) object currently loaded + * into the kernel. + * + * Looks for the BTF object with an id greater than *start_id* + * and updates *next_id* on success. If no other BTF objects + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_MAP_LOOKUP_BATCH + * Description + * Iterate and fetch multiple elements in a map. + * + * Two opaque values are used to manage batch operations, + * *in_batch* and *out_batch*. Initially, *in_batch* must be set + * to NULL to begin the batched operation. After each subsequent + * **BPF_MAP_LOOKUP_BATCH**, the caller should pass the resultant + * *out_batch* as the *in_batch* for the next operation to + * continue iteration from the current point. Both *in_batch* and + * *out_batch* must point to memory large enough to hold a key, + * except for maps of type **BPF_MAP_TYPE_{HASH, PERCPU_HASH, + * LRU_HASH, LRU_PERCPU_HASH}**, for which batch parameters + * must be at least 4 bytes wide regardless of key size. + * + * The *keys* and *values* are output parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are copied into the + * user buffer, with the keys copied into *keys* and the values + * copied into the corresponding indices in *values*. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **ENOSPC** to indicate that *keys* or + * *values* is too small to dump an entire bucket during + * iteration of a hash-based map type. + * + * BPF_MAP_LOOKUP_AND_DELETE_BATCH + * Description + * Iterate and delete all elements in a map. + * + * This operation has the same behavior as + * **BPF_MAP_LOOKUP_BATCH** with two exceptions: + * + * * Every element that is successfully returned is also deleted + * from the map. This is at least *count* elements. Note that + * *count* is both an input and an output parameter. + * * Upon returning with *errno* set to **EFAULT**, up to + * *count* elements may be deleted without returning the keys + * and values of the deleted elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_MAP_UPDATE_BATCH + * Description + * Update multiple elements in a map by *key*. + * + * The *keys* and *values* are input parameters which must point + * to memory large enough to hold *count* items based on the key + * and value size of the map *map_fd*. The *keys* buffer must be + * of *key_size* * *count*. The *values* buffer must be of + * *value_size* * *count*. + * + * Each element specified in *keys* is sequentially updated to the + * value in the corresponding index in *values*. The *in_batch* + * and *out_batch* parameters are ignored and should be zeroed. + * + * The *elem_flags* argument should be specified as one of the + * following: + * + * **BPF_ANY** + * Create new elements or update a existing elements. + * **BPF_NOEXIST** + * Create new elements only if they do not exist. + * **BPF_EXIST** + * Update existing elements. + * **BPF_F_LOCK** + * Update spin_lock-ed map elements. This must be + * specified if the map value contains a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * May set *errno* to **EINVAL**, **EPERM**, **ENOMEM**, or + * **E2BIG**. **E2BIG** indicates that the number of elements in + * the map reached the *max_entries* limit specified at map + * creation time. + * + * May set *errno* to one of the following error codes under + * specific circumstances: + * + * **EEXIST** + * If *flags* specifies **BPF_NOEXIST** and the element + * with *key* already exists in the map. + * **ENOENT** + * If *flags* specifies **BPF_EXIST** and the element with + * *key* does not exist in the map. + * + * BPF_MAP_DELETE_BATCH + * Description + * Delete multiple elements in a map by *key*. + * + * The *keys* parameter is an input parameter which must point + * to memory large enough to hold *count* items based on the key + * size of the map *map_fd*, that is, *key_size* * *count*. + * + * Each element specified in *keys* is sequentially deleted. The + * *in_batch*, *out_batch*, and *values* parameters are ignored + * and should be zeroed. + * + * The *elem_flags* argument may be specified as one of the + * following: + * + * **BPF_F_LOCK** + * Look up the value of a spin-locked map without + * returning the lock. This must be specified if the + * elements contain a spinlock. + * + * On success, *count* elements from the map are updated. + * + * If an error is returned and *errno* is not **EFAULT**, *count* + * is set to the number of successfully processed elements. If + * *errno* is **EFAULT**, up to *count* elements may be been + * deleted. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_CREATE + * Description + * Attach an eBPF program to a *target_fd* at the specified + * *attach_type* hook and return a file descriptor handle for + * managing the link. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_UPDATE + * Description + * Update the eBPF program in the specified *link_fd* to + * *new_prog_fd*. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_LINK_GET_FD_BY_ID + * Description + * Open a file descriptor for the eBPF Link corresponding to + * *link_id*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_GET_NEXT_ID + * Description + * Fetch the next eBPF link currently loaded into the kernel. + * + * Looks for the eBPF link with an id greater than *start_id* + * and updates *next_id* on success. If no other eBPF links + * remain with ids higher than *start_id*, returns -1 and sets + * *errno* to **ENOENT**. + * + * Return + * Returns zero on success. On error, or when no id remains, -1 + * is returned and *errno* is set appropriately. + * + * BPF_ENABLE_STATS + * Description + * Enable eBPF runtime statistics gathering. + * + * Runtime statistics gathering for the eBPF runtime is disabled + * by default to minimize the corresponding performance overhead. + * This command enables statistics globally. + * + * Multiple programs may independently enable statistics. + * After gathering the desired statistics, eBPF runtime statistics + * may be disabled again by calling **close**\ (2) for the file + * descriptor returned by this function. Statistics will only be + * disabled system-wide when all outstanding file descriptors + * returned by prior calls for this subcommand are closed. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_ITER_CREATE + * Description + * Create an iterator on top of the specified *link_fd* (as + * previously created using **BPF_LINK_CREATE**) and return a + * file descriptor that can be used to trigger the iteration. + * + * If the resulting file descriptor is pinned to the filesystem + * using **BPF_OBJ_PIN**, then subsequent **read**\ (2) syscalls + * for that path will trigger the iterator to read kernel state + * using the eBPF program attached to *link_fd*. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_LINK_DETACH + * Description + * Forcefully detach the specified *link_fd* from its + * corresponding attachment point. + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_PROG_BIND_MAP + * Description + * Bind a map to the lifetime of an eBPF program. + * + * The map identified by *map_fd* is bound to the program + * identified by *prog_fd* and only released when *prog_fd* is + * released. This may be used in cases where metadata should be + * associated with a program which otherwise does not contain any + * references to the map (for example, embedded in the eBPF + * program instructions). + * + * Return + * Returns zero on success. On error, -1 is returned and *errno* + * is set appropriately. + * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_PROG_STREAM_READ_BY_FD + * Description + * Read data of a program's BPF stream. The program is identified + * by *prog_fd*, and the stream is identified by the *stream_id*. + * The data is copied to a buffer pointed to by *stream_buf*, and + * filled less than or equal to *stream_buf_len* bytes. + * + * Return + * Number of bytes read from the stream on success, or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * + * BPF_PROG_ASSOC_STRUCT_OPS + * Description + * Associate a BPF program with a struct_ops map. The struct_ops + * map is identified by *map_fd* and the BPF program is + * identified by *prog_fd*. + * + * Return + * 0 on success or -1 if an error occurred (in which case, + * *errno* is set appropriately). + * + * NOTES + * eBPF objects (maps and programs) can be shared between processes. + * + * * After **fork**\ (2), the child inherits file descriptors + * referring to the same eBPF objects. + * * File descriptors referring to eBPF objects can be transferred over + * **unix**\ (7) domain sockets. + * * File descriptors referring to eBPF objects can be duplicated in the + * usual way, using **dup**\ (2) and similar calls. + * * File descriptors referring to eBPF objects can be pinned to the + * filesystem using the **BPF_OBJ_PIN** command of **bpf**\ (2). + * + * An eBPF object is deallocated only after all file descriptors referring + * to the object have been closed and no references remain pinned to the + * filesystem or attached (for example, bound to a program or device). + */ +enum bpf_cmd { + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, + BPF_PROG_ATTACH, + BPF_PROG_DETACH, + BPF_PROG_TEST_RUN, + BPF_PROG_RUN = BPF_PROG_TEST_RUN, + BPF_PROG_GET_NEXT_ID, + BPF_MAP_GET_NEXT_ID, + BPF_PROG_GET_FD_BY_ID, + BPF_MAP_GET_FD_BY_ID, + BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, + BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, + BPF_BTF_GET_FD_BY_ID, + BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, + BPF_MAP_FREEZE, + BPF_BTF_GET_NEXT_ID, + BPF_MAP_LOOKUP_BATCH, + BPF_MAP_LOOKUP_AND_DELETE_BATCH, + BPF_MAP_UPDATE_BATCH, + BPF_MAP_DELETE_BATCH, + BPF_LINK_CREATE, + BPF_LINK_UPDATE, + BPF_LINK_GET_FD_BY_ID, + BPF_LINK_GET_NEXT_ID, + BPF_ENABLE_STATS, + BPF_ITER_CREATE, + BPF_LINK_DETACH, + BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + BPF_PROG_STREAM_READ_BY_FD, + BPF_PROG_ASSOC_STRUCT_OPS, + __MAX_BPF_CMD, + BPF_COMMON_ATTRS = 1 << 16, /* Indicate carrying syscall common attrs. */ +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, + BPF_MAP_TYPE_LRU_HASH, + BPF_MAP_TYPE_LRU_PERCPU_HASH, + BPF_MAP_TYPE_LPM_TRIE, + BPF_MAP_TYPE_ARRAY_OF_MAPS, + BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, + BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, + BPF_MAP_TYPE_SOCKHASH, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE is available to bpf programs + * attaching to a cgroup. The new mechanism (BPF_MAP_TYPE_CGRP_STORAGE + + * local percpu kptr) supports all BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * functionality and more. So mark * BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE + * deprecated. + */ + BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE = BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE_DEPRECATED, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, + BPF_MAP_TYPE_SK_STORAGE, + BPF_MAP_TYPE_DEVMAP_HASH, + BPF_MAP_TYPE_STRUCT_OPS, + BPF_MAP_TYPE_RINGBUF, + BPF_MAP_TYPE_INODE_STORAGE, + BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, + BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, + BPF_MAP_TYPE_ARENA, + BPF_MAP_TYPE_INSN_ARRAY, + BPF_MAP_TYPE_RHASH, + __MAX_BPF_MAP_TYPE +}; + +/* Note that tracing related programs such as + * BPF_PROG_TYPE_{KPROBE,TRACEPOINT,PERF_EVENT,RAW_TRACEPOINT} + * are not subject to a stable API since kernel internal data + * structures can change from release to release and may + * therefore break existing tracing BPF programs. Tracing BPF + * programs correspond to /a/ specific kernel which is to be + * analyzed, and not /a/ specific kernel /and/ all future ones. + */ +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, + BPF_PROG_TYPE_PERF_EVENT, + BPF_PROG_TYPE_CGROUP_SKB, + BPF_PROG_TYPE_CGROUP_SOCK, + BPF_PROG_TYPE_LWT_IN, + BPF_PROG_TYPE_LWT_OUT, + BPF_PROG_TYPE_LWT_XMIT, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_RAW_TRACEPOINT, + BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + BPF_PROG_TYPE_LWT_SEG6LOCAL, + BPF_PROG_TYPE_LIRC_MODE2, + BPF_PROG_TYPE_SK_REUSEPORT, + BPF_PROG_TYPE_FLOW_DISSECTOR, + BPF_PROG_TYPE_CGROUP_SYSCTL, + BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_PROG_TYPE_TRACING, + BPF_PROG_TYPE_STRUCT_OPS, + BPF_PROG_TYPE_EXT, + BPF_PROG_TYPE_LSM, + BPF_PROG_TYPE_SK_LOOKUP, + BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ + BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE +}; + +enum bpf_attach_type { + BPF_CGROUP_INET_INGRESS, + BPF_CGROUP_INET_EGRESS, + BPF_CGROUP_INET_SOCK_CREATE, + BPF_CGROUP_SOCK_OPS, + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, + BPF_SK_MSG_VERDICT, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_POST_BIND, + BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + BPF_LIRC_MODE2, + BPF_FLOW_DISSECTOR, + BPF_CGROUP_SYSCTL, + BPF_CGROUP_UDP4_RECVMSG, + BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, + BPF_TRACE_RAW_TP, + BPF_TRACE_FENTRY, + BPF_TRACE_FEXIT, + BPF_MODIFY_RETURN, + BPF_LSM_MAC, + BPF_TRACE_ITER, + BPF_CGROUP_INET4_GETPEERNAME, + BPF_CGROUP_INET6_GETPEERNAME, + BPF_CGROUP_INET4_GETSOCKNAME, + BPF_CGROUP_INET6_GETSOCKNAME, + BPF_XDP_DEVMAP, + BPF_CGROUP_INET_SOCK_RELEASE, + BPF_XDP_CPUMAP, + BPF_SK_LOOKUP, + BPF_XDP, + BPF_SK_SKB_VERDICT, + BPF_SK_REUSEPORT_SELECT, + BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, + BPF_PERF_EVENT, + BPF_TRACE_KPROBE_MULTI, + BPF_LSM_CGROUP, + BPF_STRUCT_OPS, + BPF_NETFILTER, + BPF_TCX_INGRESS, + BPF_TCX_EGRESS, + BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, + BPF_TRACE_KPROBE_SESSION, + BPF_TRACE_UPROBE_SESSION, + BPF_TRACE_FSESSION, + BPF_TRACE_FENTRY_MULTI, + BPF_TRACE_FEXIT_MULTI, + BPF_TRACE_FSESSION_MULTI, + __MAX_BPF_ATTACH_TYPE +}; + +#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE + +/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[] + * in sync with the definitions below. + */ +enum bpf_link_type { + BPF_LINK_TYPE_UNSPEC = 0, + BPF_LINK_TYPE_RAW_TRACEPOINT = 1, + BPF_LINK_TYPE_TRACING = 2, + BPF_LINK_TYPE_CGROUP = 3, + BPF_LINK_TYPE_ITER = 4, + BPF_LINK_TYPE_NETNS = 5, + BPF_LINK_TYPE_XDP = 6, + BPF_LINK_TYPE_PERF_EVENT = 7, + BPF_LINK_TYPE_KPROBE_MULTI = 8, + BPF_LINK_TYPE_STRUCT_OPS = 9, + BPF_LINK_TYPE_NETFILTER = 10, + BPF_LINK_TYPE_TCX = 11, + BPF_LINK_TYPE_UPROBE_MULTI = 12, + BPF_LINK_TYPE_NETKIT = 13, + BPF_LINK_TYPE_SOCKMAP = 14, + BPF_LINK_TYPE_TRACING_MULTI = 15, + __MAX_BPF_LINK_TYPE, +}; + +#define MAX_BPF_LINK_TYPE __MAX_BPF_LINK_TYPE + +enum bpf_perf_event_type { + BPF_PERF_EVENT_UNSPEC = 0, + BPF_PERF_EVENT_UPROBE = 1, + BPF_PERF_EVENT_URETPROBE = 2, + BPF_PERF_EVENT_KPROBE = 3, + BPF_PERF_EVENT_KRETPROBE = 4, + BPF_PERF_EVENT_TRACEPOINT = 5, + BPF_PERF_EVENT_EVENT = 6, +}; + +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * With BPF_F_ALLOW_MULTI a new program is added to the end of the list of + * programs for a cgroup. Though it's possible to replace an old program at + * any position by also specifying BPF_F_REPLACE flag and position itself in + * replace_bpf_fd attribute. Old program at this position will be released. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. + */ +#define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) +/* Generic attachment flags. */ +#define BPF_F_REPLACE (1U << 2) +#define BPF_F_BEFORE (1U << 3) +#define BPF_F_AFTER (1U << 4) +#define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) +#define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ + +/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will perform strict alignment checking as if the kernel + * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set, + * and NET_IP_ALIGN defined to 2. + */ +#define BPF_F_STRICT_ALIGNMENT (1U << 0) + +/* If BPF_F_ANY_ALIGNMENT is used in BPF_PROG_LOAD command, the + * verifier will allow any alignment whatsoever. On platforms + * with strict alignment requirements for loads ands stores (such + * as sparc and mips) the verifier validates that all loads and + * stores provably follow this requirement. This flag turns that + * checking and enforcement off. + * + * It is mostly used for testing when we want to validate the + * context and memory access aspects of the verifier, but because + * of an unaligned access the alignment check would trigger before + * the one we are interested in. + */ +#define BPF_F_ANY_ALIGNMENT (1U << 1) + +/* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ +#define BPF_F_TEST_RND_HI32 (1U << 2) + +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_STATE_FREQ (1U << 3) + +/* If BPF_F_SLEEPABLE is used in BPF_PROG_LOAD command, the verifier will + * restrict map and helper usage for such programs. Sleepable BPF programs can + * only be attached to hooks where kernel execution context allows sleeping. + * Such programs are allowed to use helpers that may sleep like + * bpf_copy_from_user(). + */ +#define BPF_F_SLEEPABLE (1U << 4) + +/* If BPF_F_XDP_HAS_FRAGS is used in BPF_PROG_LOAD command, the loaded program + * fully support xdp frags. + */ +#define BPF_F_XDP_HAS_FRAGS (1U << 5) + +/* If BPF_F_XDP_DEV_BOUND_ONLY is used in BPF_PROG_LOAD command, the loaded + * program becomes device-bound but can access XDP metadata. + */ +#define BPF_F_XDP_DEV_BOUND_ONLY (1U << 6) + +/* The verifier internal test flag. Behavior is undefined */ +#define BPF_F_TEST_REG_INVARIANTS (1U << 7) + +/* link_create.kprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_KPROBE_MULTI attach type to create return probe. + */ +enum { + BPF_F_KPROBE_MULTI_RETURN = (1U << 0) +}; + +/* link_create.uprobe_multi.flags used in LINK_CREATE command for + * BPF_TRACE_UPROBE_MULTI attach type to create return probe. + */ +enum { + /* Get return uprobe. */ + BPF_F_UPROBE_MULTI_RETURN = (1U << 0), + + /* Get path from provided path_fd. */ + BPF_F_UPROBE_MULTI_PATH_FD = (1U << 1), +}; + +/* link_create.netfilter.flags used in LINK_CREATE command for + * BPF_PROG_TYPE_NETFILTER to enable IP packet defragmentation. + */ +#define BPF_F_NETFILTER_IP_DEFRAG (1U << 0) + +/* When BPF ldimm64's insn[0].src_reg != 0 then this can have + * the following extensions: + * + * insn[0].src_reg: BPF_PSEUDO_MAP_[FD|IDX] + * insn[0].imm: map fd or fd_idx + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map + * verifier type: CONST_PTR_TO_MAP + */ +#define BPF_PSEUDO_MAP_FD 1 +#define BPF_PSEUDO_MAP_IDX 5 + +/* insn[0].src_reg: BPF_PSEUDO_MAP_[IDX_]VALUE + * insn[0].imm: map fd or fd_idx + * insn[1].imm: offset into value + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of map[0]+offset + * verifier type: PTR_TO_MAP_VALUE + */ +#define BPF_PSEUDO_MAP_VALUE 2 +#define BPF_PSEUDO_MAP_IDX_VALUE 6 + +/* insn[0].src_reg: BPF_PSEUDO_BTF_ID + * insn[0].imm: kernel btd id of VAR + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the kernel variable + * verifier type: PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var + * is struct/union. + */ +#define BPF_PSEUDO_BTF_ID 3 +/* insn[0].src_reg: BPF_PSEUDO_FUNC + * insn[0].imm: insn offset to the func + * insn[1].imm: 0 + * insn[0].off: 0 + * insn[1].off: 0 + * ldimm64 rewrite: address of the function + * verifier type: PTR_TO_FUNC. + */ +#define BPF_PSEUDO_FUNC 4 + +/* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative + * offset to another bpf function + */ +#define BPF_PSEUDO_CALL 1 +/* when bpf_call->src_reg == BPF_PSEUDO_KFUNC_CALL, + * bpf_call->imm == btf_id of a BTF_KIND_FUNC in the running kernel + */ +#define BPF_PSEUDO_KFUNC_CALL 2 + +enum bpf_addr_space_cast { + BPF_ADDR_SPACE_CAST = 1, +}; + +/* flags for BPF_MAP_UPDATE_ELEM command */ +enum { + BPF_ANY = 0, /* create new element or update existing */ + BPF_NOEXIST = 1, /* create new element if it didn't exist */ + BPF_EXIST = 2, /* update existing element */ + BPF_F_LOCK = 4, /* spin_lock-ed map_lookup/map_update */ + BPF_F_CPU = 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */ + BPF_F_ALL_CPUS = 16, /* update value across all CPUs for percpu maps */ +}; + +/* flags for BPF_MAP_CREATE command */ +enum { + BPF_F_NO_PREALLOC = (1U << 0), +/* Instead of having one common LRU list in the + * BPF_MAP_TYPE_LRU_[PERCPU_]HASH map, use a percpu LRU list + * which can scale and perform better. + * Note, the LRU nodes (including free nodes) cannot be moved + * across different LRU lists. + */ + BPF_F_NO_COMMON_LRU = (1U << 1), +/* Specify numa node during map creation */ + BPF_F_NUMA_NODE = (1U << 2), + +/* Flags for accessing BPF object from syscall side. */ + BPF_F_RDONLY = (1U << 3), + BPF_F_WRONLY = (1U << 4), + +/* Flag for stack_map, store build_id+offset instead of pointer */ + BPF_F_STACK_BUILD_ID = (1U << 5), + +/* Zero-initialize hash function seed. This should only be used for testing. */ + BPF_F_ZERO_SEED = (1U << 6), + +/* Flags for accessing BPF object from program side. */ + BPF_F_RDONLY_PROG = (1U << 7), + BPF_F_WRONLY_PROG = (1U << 8), + +/* Clone map from listener for newly accepted socket */ + BPF_F_CLONE = (1U << 9), + +/* Enable memory-mapping BPF map */ + BPF_F_MMAPABLE = (1U << 10), + +/* Share perf_event among processes */ + BPF_F_PRESERVE_ELEMS = (1U << 11), + +/* Create a map that is suitable to be an inner map with dynamic max entries */ + BPF_F_INNER_MAP = (1U << 12), + +/* Create a map that will be registered/unregesitered by the backed bpf_link */ + BPF_F_LINK = (1U << 13), + +/* Get path from provided FD in BPF_OBJ_PIN/BPF_OBJ_GET commands */ + BPF_F_PATH_FD = (1U << 14), + +/* Flag for value_type_btf_obj_fd, the fd is available */ + BPF_F_VTYPE_BTF_OBJ_FD = (1U << 15), + +/* BPF token FD is passed in a corresponding command's token_fd field */ + BPF_F_TOKEN_FD = (1U << 16), + +/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */ + BPF_F_SEGV_ON_FAULT = (1U << 17), + +/* Do not translate kernel bpf_arena pointers to user pointers */ + BPF_F_NO_USER_CONV = (1U << 18), + +/* Enable BPF ringbuf overwrite mode */ + BPF_F_RB_OVERWRITE = (1U << 19), +}; + +/* Flags for BPF_PROG_QUERY. */ + +/* Query effective (directly attached + inherited from ancestor cgroups) + * programs that will be executed for events within a cgroup. + * attach_flags with this flag are always returned 0. + */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + +/* Flags for BPF_PROG_TEST_RUN */ + +/* If set, run the test on the cpu specified by bpf_attr.test.cpu */ +#define BPF_F_TEST_RUN_ON_CPU (1U << 0) +/* If set, XDP frames will be transmitted after processing */ +#define BPF_F_TEST_XDP_LIVE_FRAMES (1U << 1) +/* If set, apply CHECKSUM_COMPLETE to skb and validate the checksum */ +#define BPF_F_TEST_SKB_CHECKSUM_COMPLETE (1U << 2) + +/* type for BPF_ENABLE_STATS */ +enum bpf_stats_type { + /* enabled run_time_ns and run_cnt */ + BPF_STATS_RUN_TIME = 0, +}; + +enum bpf_stack_build_id_status { + /* user space need an empty entry to identify end of a trace */ + BPF_STACK_BUILD_ID_EMPTY = 0, + /* with valid build_id and offset */ + BPF_STACK_BUILD_ID_VALID = 1, + /* couldn't get build_id, fallback to ip */ + BPF_STACK_BUILD_ID_IP = 2, +}; + +#define BPF_BUILD_ID_SIZE 20 +struct bpf_stack_build_id { + __s32 status; + unsigned char build_id[BPF_BUILD_ID_SIZE]; + union { + __u64 offset; + __u64 ip; + }; +}; + +struct bpf_common_attr { + __aligned_u64 log_buf; + __u32 log_size; + __u32 log_level; + __u32 log_true_size; +}; + +#define BPF_OBJ_NAME_LEN 16U + +enum { + BPF_STREAM_STDOUT = 1, + BPF_STREAM_STDERR = 2, +}; + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* BPF_MAP_CREATE related + * flags defined above. + */ + __u32 inner_map_fd; /* fd pointing to the inner map */ + __u32 numa_node; /* numa node (effective only if + * BPF_F_NUMA_NODE is set). + */ + char map_name[BPF_OBJ_NAME_LEN]; + __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_type_id; /* BTF type_id of the key */ + __u32 btf_value_type_id; /* BTF type_id of the value */ + __u32 btf_vmlinux_value_type_id;/* BTF type_id of a kernel- + * struct stored as the + * map value + */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + * + * BPF_MAP_TYPE_ARENA - contains the address where user space + * is going to mmap() the arena. It has to be page aligned. + * + * BPF_MAP_TYPE_RHASH - initial table size hint + * (nelem_hint). 0 = use rhashtable default. Must be + * <= min(max_entries, U16_MAX). Upper 32 bits reserved, + * must be zero. + */ + __u64 map_extra; + + __s32 value_type_btf_obj_fd; /* fd pointing to a BTF + * type data for + * btf_vmlinux_value_type_id. + */ + /* BPF token FD to use with BPF_MAP_CREATE operation. + * If provided, map_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 map_token_fd; + + /* Hash of the program that has exclusive access to the map. + */ + __aligned_u64 excl_prog_hash; + /* Size of the passed excl_prog_hash. */ + __u32 excl_prog_hash_size; + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM and BPF_MAP_FREEZE commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* struct used by BPF_MAP_*_BATCH commands */ + __aligned_u64 in_batch; /* start batch, + * NULL to start from beginning + */ + __aligned_u64 out_batch; /* output: next start batch */ + __aligned_u64 keys; + __aligned_u64 values; + __u32 count; /* input/output: + * input: # of key/value + * elements + * output: # of filled elements + */ + __u32 map_fd; + __u64 elem_flags; + __u64 flags; + } batch; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* not used */ + __u32 prog_flags; + char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_ifindex; /* ifindex of netdev to prep for */ + /* For some prog types expected attach type must be known at + * load time to verify attach type specific parts of prog + * (context accesses, allowed helpers, etc). + */ + __u32 expected_attach_type; + __u32 prog_btf_fd; /* fd pointing to BTF type data */ + __u32 func_info_rec_size; /* userspace bpf_func_info size */ + __aligned_u64 func_info; /* func info */ + __u32 func_info_cnt; /* number of bpf_func_info records */ + __u32 line_info_rec_size; /* userspace bpf_line_info size */ + __aligned_u64 line_info; /* line info */ + __u32 line_info_cnt; /* number of bpf_line_info records */ + __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; + __u32 core_relo_cnt; /* number of bpf_core_relo */ + __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 log_true_size; + /* BPF token FD to use with BPF_PROG_LOAD operation. + * If provided, prog_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 prog_token_fd; + /* The fd_array_cnt can be used to pass the length of the + * fd_array array. In this case all the [map] file descriptors + * passed in this array will be bound to the program, even if + * the maps are not referenced directly. The functionality is + * similar to the BPF_PROG_BIND_MAP syscall, but maps can be + * used by the verifier during the program load. If provided, + * then the fd_array[0,...,fd_array_cnt-1] is expected to be + * continuous. + */ + __u32 fd_array_cnt; + /* Pointer to a buffer containing the signature of the BPF + * program. + */ + __aligned_u64 signature; + /* Size of the signature buffer in bytes. */ + __u32 signature_size; + /* ID of the kernel keyring to be used for signature + * verification. + */ + __s32 keyring_id; + }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + __u32 file_flags; + /* Same as dirfd in openat() syscall; see openat(2) + * manpage for details of path FD and pathname semantics; + * path_fd should accompanied by BPF_F_PATH_FD flag set in + * file_flags field, otherwise it should be set to zero; + * if BPF_F_PATH_FD flag is not set, AT_FDCWD is assumed. + */ + __s32 path_fd; + }; + + struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_bpf_fd; + __u32 attach_type; + __u32 attach_flags; + __u32 replace_bpf_fd; + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + }; + + struct { /* anonymous struct used by BPF_PROG_TEST_RUN command */ + __u32 prog_fd; + __u32 retval; + __u32 data_size_in; /* input: len of data_in */ + __u32 data_size_out; /* input/output: len of data_out + * returns ENOSPC if data_out + * is too small. + */ + __aligned_u64 data_in; + __aligned_u64 data_out; + __u32 repeat; + __u32 duration; + __u32 ctx_size_in; /* input: len of ctx_in */ + __u32 ctx_size_out; /* input/output: len of ctx_out + * returns ENOSPC if ctx_out + * is too small. + */ + __aligned_u64 ctx_in; + __aligned_u64 ctx_out; + __u32 flags; + __u32 cpu; + __u32 batch_size; + } test; + + struct { /* anonymous struct used by BPF_*_GET_*_ID */ + union { + __u32 start_id; + __u32 prog_id; + __u32 map_id; + __u32 btf_id; + __u32 link_id; + }; + __u32 next_id; + __u32 open_flags; + __s32 fd_by_id_token_fd; + }; + + struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ + __u32 bpf_fd; + __u32 info_len; + __aligned_u64 info; + } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + union { + __u32 target_fd; /* target object to query or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + union { + __u32 prog_cnt; + __u32 count; + }; + __u32 :32; + /* output: per-program attach_flags. + * not allowed to be set during effective query. + */ + __aligned_u64 prog_attach_flags; + __aligned_u64 link_ids; + __aligned_u64 link_attach_flags; + __u64 revision; + } query; + + struct { /* anonymous struct used by BPF_RAW_TRACEPOINT_OPEN command */ + __u64 name; + __u32 prog_fd; + __u32 :32; + __aligned_u64 cookie; + } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + /* output: actual total log contents size (including termintaing zero). + * It could be both larger than original log_size (if log was + * truncated), or smaller (if log buffer wasn't filled completely). + */ + __u32 btf_log_true_size; + __u32 btf_flags; + /* BPF token FD to use with BPF_BTF_LOAD operation. + * If provided, btf_flags should have BPF_F_TOKEN_FD flag set. + */ + __s32 btf_token_fd; + }; + + struct { + __u32 pid; /* input: pid */ + __u32 fd; /* input: fd */ + __u32 flags; /* input: flags */ + __u32 buf_len; /* input/output: buf len */ + __aligned_u64 buf; /* input/output: + * tp_name for tracepoint + * symbol for kprobe + * filename for uprobe + */ + __u32 prog_id; /* output: prod_id */ + __u32 fd_type; /* output: BPF_FD_TYPE_* */ + __u64 probe_offset; /* output: probe_offset */ + __u64 probe_addr; /* output: probe_addr */ + } task_fd_query; + + struct { /* struct used by BPF_LINK_CREATE command */ + union { + __u32 prog_fd; /* eBPF program to attach */ + __u32 map_fd; /* struct_ops to attach */ + }; + union { + __u32 target_fd; /* target object to attach to or ... */ + __u32 target_ifindex; /* target ifindex */ + }; + __u32 attach_type; /* attach type */ + __u32 flags; /* extra flags */ + union { + __u32 target_btf_id; /* btf_id of target to attach to */ + struct { + __aligned_u64 iter_info; /* extra bpf_iter_link_info */ + __u32 iter_info_len; /* iter_info length */ + }; + struct { + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 bpf_cookie; + } perf_event; + struct { + __u32 flags; + __u32 cnt; + __aligned_u64 syms; + __aligned_u64 addrs; + __aligned_u64 cookies; + } kprobe_multi; + struct { + /* this is overlaid with the target_btf_id above. */ + __u32 target_btf_id; + /* black box user-provided value passed through + * to BPF program at the execution time and + * accessible through bpf_get_attach_cookie() BPF helper + */ + __u64 cookie; + } tracing; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } tcx; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 cnt; + __u32 flags; + __u32 pid; + __u32 path_fd; + } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } cgroup; + struct { + __aligned_u64 ids; + __aligned_u64 cookies; + __u32 cnt; + } tracing_multi; + }; + } link_create; + + struct { /* struct used by BPF_LINK_UPDATE command */ + __u32 link_fd; /* link fd */ + union { + /* new program fd to update link with */ + __u32 new_prog_fd; + /* new struct_ops map fd to update link with */ + __u32 new_map_fd; + }; + __u32 flags; /* extra flags */ + union { + /* expected link's program fd; is specified only if + * BPF_F_REPLACE flag is set in flags. + */ + __u32 old_prog_fd; + /* expected link's map fd; is specified only + * if BPF_F_REPLACE flag is set. + */ + __u32 old_map_fd; + }; + } link_update; + + struct { + __u32 link_fd; + } link_detach; + + struct { /* struct used by BPF_ENABLE_STATS command */ + __u32 type; + } enable_stats; + + struct { /* struct used by BPF_ITER_CREATE command */ + __u32 link_fd; + __u32 flags; + } iter_create; + + struct { /* struct used by BPF_PROG_BIND_MAP command */ + __u32 prog_fd; + __u32 map_fd; + __u32 flags; /* extra flags */ + } prog_bind_map; + + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + + struct { + __aligned_u64 stream_buf; + __u32 stream_buf_len; + __u32 stream_id; + __u32 prog_fd; + } prog_stream_read; + + struct { + __u32 map_fd; + __u32 prog_fd; + __u32 flags; + } prog_assoc_struct_ops; + +} __attribute__((aligned(8))); + +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_probe_read(void *dst, u32 size, const void *unsafe_ptr) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * kernel space address *unsafe_ptr* and store the data in *dst*. + * + * Generally, use **bpf_probe_read_user**\ () or + * **bpf_probe_read_kernel**\ () instead. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_ktime_get_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does not include time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_MONOTONIC**) + * Return + * Current *ktime*. + * + * long bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/tracing/trace* from TraceFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * Lines are discarded while *\/sys/kernel/tracing/trace* is + * open, use *\/sys/kernel/tracing/trace_pipe* to avoid this. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ```` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * block (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with migration disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * Attributes + * __bpf_fastcall + * + * long bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. The *flags* are a combination + * of the following values: + * + * **BPF_F_RECOMPUTE_CSUM** + * Automatically update *skb*\ **->csum** after storing the + * bytes. + * **BPF_F_INVALIDATE_HASH** + * Set *skb*\ **->hash**, *skb*\ **->swhash** and *skb*\ + * **->l4hash** to 0. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * that the modified header field is part of the pseudo-header. + * Flag **BPF_F_IPV6** should be set for IPv6 packets. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 33. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. Positive + * error indicates a potential drop or congestion in the target + * device. The particular positive error codes are not defined. + * + * u64 bpf_get_current_pid_tgid(void) + * Description + * Get the current pid and tgid. + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. + * + * u64 bpf_get_current_uid_gid(void) + * Description + * Get the current uid and gid. + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * long bpf_get_current_comm(void *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * long bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * **BPF_F_NO_TUNNEL_KEY** + * Add a flag to tunnel metadata indicating that no tunnel + * key should be set in the resulting tunnel header. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * long bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * identifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * long bpf_perf_event_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output.bpf.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_load_bytes(const void *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_get_stackid(void *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * long bpf_skb_get_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * long bpf_skb_set_tunnel_opt(struct sk_buff *skb, void *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. + * + * u64 bpf_get_current_task(void) + * Description + * Get the current task. + * Return + * A pointer to the current task struct. + * + * long bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 1, if current task belongs to the cgroup2. + * * 0, if current task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * long bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then all bytes in the linear part of *skb* will be made + * readable and writable. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * Return + * void. + * + * long bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * long bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_probe_read_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address + * *unsafe_ptr* to *dst*. See **bpf_probe_read_kernel_str**\ () for + * more details. + * + * Generally, use **bpf_probe_read_user_str**\ () or + * **bpf_probe_read_kernel_str**\ () instead. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a global socket + * identifier that can be assumed unique. + * Return + * A 8-byte long unique number on success, or 0 if the socket + * field is missing inside *skb*. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx) + * Description + * Equivalent to bpf_get_socket_cookie() helper that accepts + * *skb*, but gets socket from **struct bpf_sock_addr** context. + * Return + * A 8-byte long unique number. + * + * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *skb*, but gets socket from **struct bpf_sock_ops** context. + * Return + * A 8-byte long unique number. + * + * u64 bpf_get_socket_cookie(struct sock *sk) + * Description + * Equivalent to **bpf_get_socket_cookie**\ () helper that accepts + * *sk*, but gets socket from a BTF **struct sock**. This helper + * also works for sleepable programs. + * Return + * A 8-byte long unique number or 0 if *sk* is NULL. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Description + * Get the owner UID of the socked associated to *skb*. + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * long bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * long bpf_setsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, + * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * By default, the helper will reset any offloaded checksum + * indicator of the skb to CHECKSUM_NONE. This can be avoided + * by the following flag: + * + * * **BPF_F_ADJ_ROOM_NO_CSUM_RESET**: Do not reset offloaded + * checksum data of the skb to CHECKSUM_NONE. + * + * There are two supported modes at this time: + * + * * **BPF_ADJ_ROOM_MAC**: Adjust room at the mac layer + * (room space is added or removed between the layer 2 and + * layer 3 headers). + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed between the layer 3 and + * layer 4 headers). + * + * The following flags are supported at this time: + * + * * **BPF_F_ADJ_ROOM_FIXED_GSO**: Do not adjust gso_size. + * Adjusting mss in this way is not allowed for datagrams. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_ENCAP_L3_IPV6**: + * Any new space is reserved to hold a tunnel header. + * Configure skb offsets and other fields accordingly. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L4_GRE**, + * **BPF_F_ADJ_ROOM_ENCAP_L4_UDP**: + * Use with ENCAP_L3 flags to further specify the tunnel type. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2**\ (*len*): + * Use with ENCAP_L3/L4 flags to further specify the tunnel + * type; *len* is the length of the inner MAC header. + * + * * **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**: + * Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the + * L2 type as Ethernet. + * + * * **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**, + * **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**: + * Indicate the new IP header version after decapsulating the + * outer IP header. Used when the inner and outer IP versions + * are different. These flags only trigger a protocol change + * without clearing any tunnel-specific GSO flags. + * + * * **BPF_F_ADJ_ROOM_DECAP_L4_GRE**: + * Clear GRE tunnel GSO flags (SKB_GSO_GRE and SKB_GSO_GRE_CSUM) + * when decapsulating a GRE tunnel. + * + * * **BPF_F_ADJ_ROOM_DECAP_L4_UDP**: + * Clear UDP tunnel GSO flags (SKB_GSO_UDP_TUNNEL and + * SKB_GSO_UDP_TUNNEL_CSUM) when decapsulating a UDP tunnel. + * + * * **BPF_F_ADJ_ROOM_DECAP_IPXIP4**: + * Clear IPIP/SIT tunnel GSO flag (SKB_GSO_IPXIP4) when decapsulating + * a tunnel with an outer IPv4 header (IPv4-in-IPv4 or IPv6-in-IPv4). + * + * * **BPF_F_ADJ_ROOM_DECAP_IPXIP6**: + * Clear IPv6 encapsulation tunnel GSO flag (SKB_GSO_IPXIP6) when + * decapsulating a tunnel with an outer IPv6 header (IPv6-in-IPv6 + * or IPv4-in-IPv6). + * + * When using the decapsulation flags above, the skb->encapsulation + * flag is automatically cleared if all tunnel-specific GSO flags + * (SKB_GSO_UDP_TUNNEL, SKB_GSO_UDP_TUNNEL_CSUM, SKB_GSO_GRE, + * SKB_GSO_GRE_CSUM, SKB_GSO_IPXIP4, SKB_GSO_IPXIP6) have been + * removed from the packet. This handles cases where all tunnel + * layers have been decapsulated. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to **XDP_TX**, as chosen + * by the caller. The higher bits of *flags* can be set to + * BPF_F_BROADCAST or BPF_F_EXCLUDE_INGRESS as defined below. + * + * With BPF_F_BROADCAST the packet will be broadcasted to all the + * interfaces in the map, with BPF_F_EXCLUDE_INGRESS the ingress + * interface will be excluded when do broadcasting. + * + * See also **bpf_redirect**\ (), which only supports redirecting + * to an ifindex, but doesn't require a map to do so. + * Return + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the *flags* argument on error. + * + * long bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * long bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For an eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_getsockopt(void *bpf_socket, int level, int optname, void *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * *bpf_socket* should be one of the following: + * + * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_override_return(struct pt_regs *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * Return + * 0 + * + * long bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * *argval* is a flag array which can combine these flags: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) + * + * Therefore, this function can be used to clear a callback flag by + * setting the appropriate bit to zero. e.g. to disable the RTO + * callback: + * + * **bpf_sock_ops_cb_flags_set(bpf_sock,** + * **bpf_sock->bpf_sock_ops_cb_flags & ~BPF_SOCK_OPS_RTO_CB_FLAG)** + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * long bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * long bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * long bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * long bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). It's advised to pass zero port (**sin_port** + * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like + * behavior and lets the kernel efficiently pick up an unused + * port as long as 4-tuple is unique. Passing non-zero port might + * lead to degraded performance. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * possible to both shrink and grow the packet tail. + * Shrink done via *delta* being a negative integer. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_get_stack(void *ctx, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect (build_id, file_offset) instead of ips for user + * stack, only valid if **BPF_F_USER_STACK** is also + * specified. + * + * *file_offset* is an offset relative to the beginning + * of the executable or shared object file backing the vma + * which the *ip* falls in. It is *not* an offset relative + * to that object's base address. Accordingly, it must be + * adjusted by adding (sh_addr - sh_offset), where + * sh_{addr,offset} correspond to the executable section + * containing *file_offset* in the object, for comparisons + * to symbols' st_value to be valid. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. + * + * long bpf_skb_load_bytes_relative(const void *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_fib_lookup(void *ctx, struct bpf_fib_lookup *params, int plen, u32 flags) + * Description + * Do FIB lookup in kernel tables using parameters in *params*. + * If lookup is successful and result shows packet is to be + * forwarded, the neighbor tables are searched for the nexthop. + * If successful (ie., FIB lookup shows forwarding and nexthop + * is resolved), the nexthop address is returned in ipv4_dst + * or ipv6_dst based on family, smac is set to mac address of + * egress device, dmac is set to nexthop mac address, rt_metric + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. + * + * *plen* argument is the size of the passed in struct. + * *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_FIB_LOOKUP_DIRECT** + * Do a direct table lookup vs full lookup using FIB + * rules. + * **BPF_FIB_LOOKUP_TBID** + * Used with BPF_FIB_LOOKUP_DIRECT. + * Use the routing table ID present in *params*->tbid + * for the fib lookup. + * **BPF_FIB_LOOKUP_OUTPUT** + * Perform lookup from an egress perspective (default is + * ingress). + * **BPF_FIB_LOOKUP_SKIP_NEIGH** + * Skip the neighbour table lookup. *params*->dmac + * and *params*->smac will not be set as output. A common + * use case is to call **bpf_redirect_neigh**\ () after + * doing **bpf_fib_lookup**\ (). + * **BPF_FIB_LOOKUP_SRC** + * Derive and set source IP addr in *params*->ipv{4,6}_src + * for the nexthop. If the src addr cannot be derived, + * **BPF_FIB_LKUP_RET_NO_SRC_ADDR** is returned. In this + * case, *params*->dmac and *params*->smac are not set either. + * **BPF_FIB_LOOKUP_MARK** + * Use the mark present in *params*->mark for the fib lookup. + * This option should not be used with BPF_FIB_LOOKUP_DIRECT, + * as it only has meaning for full lookups. + * **BPF_FIB_LOOKUP_VLAN** + * If the fib lookup resolves to a VLAN device whose + * parent is a real (non-VLAN) device, set + * *params*->h_vlan_proto and *params*->h_vlan_TCI from + * the VLAN device and replace *params*->ifindex with the + * parent's ifindex. *params*->h_vlan_TCI carries the VID + * only, with PCP and DEI bits zero; a consumer wanting to + * set egress priority writes PCP itself. *params*->smac is + * the VLAN device's own address, which can differ from the + * parent's. Only the immediate parent is resolved; if it + * is itself a VLAN device (QinQ) or in another namespace, + * the egress cannot be reduced to a physical device plus + * one tag and the lookup returns + * **BPF_FIB_LKUP_RET_VLAN_FAILURE** with *params*->ifindex + * left at the input. To obtain the VLAN device's own + * ifindex, repeat the lookup without + * **BPF_FIB_LOOKUP_VLAN**, re-initializing *params* + * first: output fields overwrite the inputs they share + * storage with. The swap and the vlan fields + * are written only on success; other output fields keep + * the helper's existing behaviour, so a frag-needed result + * still reports the route mtu in *params*->mtu_result. + * This flag is only valid for XDP programs; tc programs + * receive -EINVAL since they can redirect to the VLAN + * device directly. + * **BPF_FIB_LOOKUP_VLAN_INPUT** + * Treat *params*->h_vlan_proto and *params*->h_vlan_TCI + * as an input VLAN tag and run the lookup as if ingress + * had happened on the VLAN subinterface carrying that tag + * on *params*->ifindex. The VID is the low 12 bits of + * *params*->h_vlan_TCI; *params*->h_vlan_proto must be + * ETH_P_8021Q or ETH_P_8021AD in network byte order, else + * **-EINVAL**. If *params*->ifindex is itself a VLAN + * device, its inner (QinQ) subinterface is matched; for a + * bond or team, pass the master's ifindex. An unmatched + * tag, a down device, or one in another namespace returns + * **BPF_FIB_LKUP_RET_NOT_FWDED**, mirroring real ingress. + * A VID of 0 is looked up literally, so do not set this + * flag for priority-tagged frames. Cannot be combined with + * **BPF_FIB_LOOKUP_TBID** or **BPF_FIB_LOOKUP_OUTPUT** + * (returns **-EINVAL**). + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** tc cls_act programs. + * Return + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * packet is not forwarded or needs assist from full stack + * + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU + * was exceeded and output params->mtu_result contains the MTU. + * + * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a sockhash *map* referencing sockets. + * The *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_msg_redirect_hash(struct sk_msg_buff *msg, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * long bpf_sk_redirect_hash(struct sk_buff *skb, struct bpf_map *map, void *key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * skb socket level. If the sk_buff *skb* is allowed to pass (i.e. + * if the verdict eBPF program returns **SK_PASS**), redirect it + * to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKHASH**) using hash *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * long bpf_lwt_push_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) + * Description + * Encapsulate the packet associated to *skb* within a Layer 3 + * protocol header. This header is provided in the buffer at + * address *hdr*, with *len* its size in bytes. *type* indicates + * the protocol of the header and can be one of: + * + * **BPF_LWT_ENCAP_SEG6** + * IPv6 encapsulation with Segment Routing Header + * (**struct ipv6_sr_hdr**). *hdr* only contains the SRH, + * the IPv6 header is computed by the kernel. + * **BPF_LWT_ENCAP_SEG6_INLINE** + * Only works if *skb* contains an IPv6 packet. Insert a + * Segment Routing Header (**struct ipv6_sr_hdr**) inside + * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to **LWT_BPF_MAX_HEADROOM** + * total bytes in all prepended headers. Please note that + * if **skb_is_gso**\ (*skb*) is true, no more than two + * headers can be prepended, and the inner header, if + * present, should be either GRE or UDP/GUE. + * + * **BPF_LWT_ENCAP_SEG6**\ \* types can be called by BPF programs + * of type **BPF_PROG_TYPE_LWT_IN**; **BPF_LWT_ENCAP_IP** type can + * be called by bpf programs of types **BPF_PROG_TYPE_LWT_IN** and + * **BPF_PROG_TYPE_LWT_XMIT**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_lwt_seg6_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. Only the flags, tag and TLVs + * inside the outermost IPv6 Segment Routing Header can be + * modified through this helper. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_lwt_seg6_adjust_srh(struct sk_buff *skb, u32 offset, s32 delta) + * Description + * Adjust the size allocated to TLVs in the outermost IPv6 + * Segment Routing Header contained in the packet associated to + * *skb*, at position *offset* by *delta* bytes. Only offsets + * after the segments are accepted. *delta* can be as well + * positive (growing) as negative (shrinking). + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_lwt_seg6_action(struct sk_buff *skb, u32 action, void *param, u32 param_len) + * Description + * Apply an IPv6 Segment Routing action of type *action* to the + * packet associated to *skb*. Each action takes a parameter + * contained at address *param*, and of length *param_len* bytes. + * *action* can be one of: + * + * **SEG6_LOCAL_ACTION_END_X** + * End.X action: Endpoint with Layer-3 cross-connect. + * Type of *param*: **struct in6_addr**. + * **SEG6_LOCAL_ACTION_END_T** + * End.T action: Endpoint with specific IPv6 table lookup. + * Type of *param*: **int**. + * **SEG6_LOCAL_ACTION_END_B6** + * End.B6 action: Endpoint bound to an SRv6 policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * **SEG6_LOCAL_ACTION_END_B6_ENCAP** + * End.B6.Encap action: Endpoint bound to an SRv6 + * encapsulation policy. + * Type of *param*: **struct ipv6_sr_hdr**. + * + * A call to this helper is susceptible to change the underlying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_rc_repeat(void *ctx) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded repeat key message. This delays + * the generation of a key up event for previously generated + * key down event. + * + * Some IR protocols like NEC have a special IR message for + * repeating last button, for when a button is held down. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * long bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded key press with *scancode*, + * *toggle* value in the given *protocol*. The scancode will be + * translated to a keycode using the rc keymap, and reported as + * an input key down event. After a period a key up event is + * generated. This period can be extended by calling either + * **bpf_rc_keydown**\ () again with the same values, or calling + * **bpf_rc_repeat**\ (). + * + * Some protocols include a toggle bit, in case the button was + * released and pressed again between consecutive scancodes. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * The *protocol* is the decoded protocol number (see + * **enum rc_proto** for some predefined values). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * u64 bpf_skb_cgroup_id(struct sk_buff *skb) + * Description + * Return the cgroup v2 id of the socket associated with the *skb*. + * This is roughly similar to the **bpf_get_cgroup_classid**\ () + * helper for cgroup v1 by providing a tag resp. identifier that + * can be matched on or used for map lookups e.g. to implement + * policy. The cgroup v2 id of a given path in the hierarchy is + * exposed in user space through the f_handle API in order to get + * to the same 64-bit id. + * + * This helper can be used on TC egress path, but not on ingress, + * and is available only if the kernel was compiled with the + * **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_get_current_cgroup_id(void) + * Description + * Get the current cgroup id based on the cgroup within which + * the current task is running. + * Return + * A 64-bit integer containing the current cgroup id based + * on the cgroup within which the current task is running. + * + * void *bpf_get_local_storage(void *map, u64 flags) + * Description + * Get the pointer to the local storage area. + * The type and the size of the local storage is defined + * by the *map* argument. + * The *flags* meaning is specific for each map type, + * and has to be 0 for cgroup local storage. + * + * Depending on the BPF program type, a local storage area + * can be shared between multiple instances of the BPF program, + * running simultaneously. + * + * A user should care about the synchronization by himself. + * For example, by using the **BPF_ATOMIC** instructions to alter + * the shared data. + * Return + * A pointer to the local storage area. + * + * long bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags) + * Description + * Select a **SO_REUSEPORT** socket from a + * **BPF_MAP_TYPE_REUSEPORT_SOCKARRAY** *map*. + * It checks the selected socket is matching the incoming + * request in the socket buffer. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *skb* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *skb*, then return value will be same as that + * of **bpf_skb_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *skb*. + * + * The format of returned id and helper limitations are same as in + * **bpf_skb_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for UDP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * The *ctx* should point to the context of the program, such as + * the skb or socket (depending on the hook in use). This is used + * to determine the base network namespace for the lookup. + * + * *tuple_size* must be one of: + * + * **sizeof**\ (*tuple*\ **->ipv4**) + * Look for an IPv4 socket. + * **sizeof**\ (*tuple*\ **->ipv6**) + * Look for an IPv6 socket. + * + * If the *netns* is a negative signed 32-bit integer, then the + * socket lookup table in the netns associated with the *ctx* + * will be used. For the TC hooks, this is the netns of the device + * in the skb. For socket hooks, this is the netns of the socket. + * If *netns* is any other signed 32-bit value greater than or + * equal to zero then it specifies the ID of the netns relative to + * the netns associated with the *ctx*. *netns* values beyond the + * range of 32-bit integers are reserved for future use. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * long bpf_sk_release(void *sock) + * Description + * Release the reference held by *sock*. *sock* must be a + * non-**NULL** pointer that was returned from + * **bpf_sk_lookup_xxx**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is + * removed to make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_msg_push_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * Description + * For socket policies, insert *len* bytes into *msg* at offset + * *start*. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it may want to insert metadata or options into the *msg*. + * This can later be read and used by any of the lower layer BPF + * hooks. + * + * This helper may fail if under memory pressure (a malloc + * fails) in these cases BPF programs will get an appropriate + * error and BPF programs will need to handle them. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_msg_pop_data(struct sk_msg_buff *msg, u32 start, u32 len, u64 flags) + * Description + * Will remove *len* bytes from a *msg* starting at byte *start*. + * This may result in **ENOMEM** errors under certain situations if + * an allocation and copy are required due to a full ring buffer. + * However, the helper will try to avoid doing the allocation + * if possible. Other errors can occur if input parameters are + * invalid either due to *start* byte not being valid part of *msg* + * payload and/or *pop* value being to large. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_rc_pointer_rel(void *ctx, s32 rel_x, s32 rel_y) + * Description + * This helper is used in programs implementing IR decoding, to + * report a successfully decoded pointer movement. + * + * The *ctx* should point to the lirc sample as passed into + * the program. + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_BPF_LIRC_MODE2** configuration option set to + * "**y**". + * Return + * 0 + * + * long bpf_spin_lock(struct bpf_spin_lock *lock) + * Description + * Acquire a spinlock represented by the pointer *lock*, which is + * stored as part of a value of a map. Taking the lock allows to + * safely update the rest of the fields in that value. The + * spinlock can (and must) later be released with a call to + * **bpf_spin_unlock**\ (\ *lock*\ ). + * + * Spinlocks in BPF programs come with a number of restrictions + * and constraints: + * + * * **bpf_spin_lock** objects are only allowed inside maps of + * types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this + * list could be extended in the future). + * * BTF description of the map is mandatory. + * * The BPF program can take ONE lock at a time, since taking two + * or more could cause dead locks. + * * Only one **struct bpf_spin_lock** is allowed per map element. + * * When the lock is taken, calls (either BPF to BPF or helpers) + * are not allowed. + * * The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not + * allowed inside a spinlock-ed region. + * * The BPF program MUST call **bpf_spin_unlock**\ () to release + * the lock, on all execution paths, before it returns. + * * The BPF program can access **struct bpf_spin_lock** only via + * the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ () + * helpers. Loading or storing data into the **struct + * bpf_spin_lock** *lock*\ **;** field of a map is not allowed. + * * To use the **bpf_spin_lock**\ () helper, the BTF description + * of the map value must be a struct and have **struct + * bpf_spin_lock** *anyname*\ **;** field at the top level. + * Nested lock inside another struct is not allowed. + * * The **struct bpf_spin_lock** *lock* field in a map value must + * be aligned on a multiple of 4 bytes in that value. + * * Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy + * the **bpf_spin_lock** field to user space. + * * Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from + * a BPF program, do not update the **bpf_spin_lock** field. + * * **bpf_spin_lock** cannot be on the stack or inside a + * networking packet (it can only be inside of a map values). + * * **bpf_spin_lock** is available to root only. + * * Tracing programs and socket filter programs cannot use + * **bpf_spin_lock**\ () due to insufficient preemption checks + * (but this may change in the future). + * * **bpf_spin_lock** is not allowed in inner maps of map-in-map. + * Return + * 0 + * + * long bpf_spin_unlock(struct bpf_spin_lock *lock) + * Description + * Release the *lock* previously locked by a call to + * **bpf_spin_lock**\ (\ *lock*\ ). + * Return + * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in this **bpf_sock** can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * Return + * A **struct bpf_tcp_sock** pointer on success, or **NULL** in + * case of failure. + * + * long bpf_skb_ecn_set_ce(struct sk_buff *skb) + * Description + * Set ECN (Explicit Congestion Notification) field of IP header + * to **CE** (Congestion Encountered) if current value is **ECT** + * (ECN Capable Transport). Otherwise, do nothing. Works with IPv6 + * and IPv4. + * Return + * 1 if the **CE** flag is set (either by the current helper call + * or because it was already present), 0 if it is not set. + * + * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk) + * Description + * Return a **struct bpf_sock** pointer in **TCP_LISTEN** state. + * **bpf_sk_release**\ () is unnecessary and not allowed. + * Return + * A **struct bpf_sock** pointer on success, or **NULL** in + * case of failure. + * + * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags) + * Description + * Look for TCP socket matching *tuple*, optionally in a child + * network namespace *netns*. The return value must be checked, + * and if non-**NULL**, released via **bpf_sk_release**\ (). + * + * This function is identical to **bpf_sk_lookup_tcp**\ (), except + * that it also returns timewait or request sockets. Use + * **bpf_sk_fullsock**\ () or **bpf_tcp_sock**\ () to access the + * full structure. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_NET** configuration option. + * Return + * Pointer to **struct bpf_sock**, or **NULL** in case of failure. + * For sockets with reuseport option, the **struct bpf_sock** + * result is from *reuse*\ **->socks**\ [] using the hash of the + * tuple. + * + * long bpf_tcp_check_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK for + * the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ipv6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK, or a negative + * error otherwise. + * + * long bpf_sysctl_get_name(struct bpf_sysctl *ctx, char *buf, size_t buf_len, u64 flags) + * Description + * Get name of sysctl in /proc/sys/ and copy it into provided by + * program buffer *buf* of size *buf_len*. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * + * If *flags* is zero, full name (e.g. "net/ipv4/tcp_mem") is + * copied. Use **BPF_F_SYSCTL_BASE_NAME** flag to copy base name + * only (e.g. "tcp_mem"). + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * long bpf_sysctl_get_current_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get current value of sysctl as it is presented in /proc/sys + * (incl. newline, etc), and copy it as a string into provided + * by program buffer *buf* of size *buf_len*. + * + * The whole value is copied, no matter what file position user + * space issued e.g. sys_read at. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if current value was unavailable, e.g. because + * sysctl is uninitialized and read returns -EIO for it. + * + * long bpf_sysctl_get_new_value(struct bpf_sysctl *ctx, char *buf, size_t buf_len) + * Description + * Get new value being written by user space to sysctl (before + * the actual write happens) and copy it as a string into + * provided by program buffer *buf* of size *buf_len*. + * + * User space may write new value at file position > 0. + * + * The buffer is always NUL terminated, unless it's zero-sized. + * Return + * Number of character copied (not including the trailing NUL). + * + * **-E2BIG** if the buffer wasn't big enough (*buf* will contain + * truncated name in this case). + * + * **-EINVAL** if sysctl is being read. + * + * long bpf_sysctl_set_new_value(struct bpf_sysctl *ctx, const char *buf, size_t buf_len) + * Description + * Override new value being written by user space to sysctl with + * value provided by program in buffer *buf* of size *buf_len*. + * + * *buf* should contain a string in same form as provided by user + * space on sysctl write. + * + * User space may write new value at file position > 0. To override + * the whole sysctl value file position should be set to zero. + * Return + * 0 on success. + * + * **-E2BIG** if the *buf_len* is too big. + * + * **-EINVAL** if sysctl is being read. + * + * long bpf_strtol(const char *buf, size_t buf_len, u64 flags, long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to a long integer according to the given base + * and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)) followed by a single + * optional '**-**' sign. + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtol**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * long bpf_strtoul(const char *buf, size_t buf_len, u64 flags, unsigned long *res) + * Description + * Convert the initial part of the string from buffer *buf* of + * size *buf_len* to an unsigned long integer according to the + * given base and save the result in *res*. + * + * The string may begin with an arbitrary amount of white space + * (as determined by **isspace**\ (3)). + * + * Five least significant bits of *flags* encode base, other bits + * are currently unused. + * + * Base must be either 8, 10, 16 or 0 to detect it automatically + * similar to user space **strtoul**\ (3). + * Return + * Number of characters consumed on success. Must be positive but + * no more than *buf_len*. + * + * **-EINVAL** if no valid digits were found or unsupported base + * was provided. + * + * **-ERANGE** if resulting value was out of range. + * + * void *bpf_sk_storage_get(struct bpf_map *map, void *sk, void *value, u64 flags) + * Description + * Get a bpf-local-storage from a *sk*. + * + * Logically, it could be thought of getting the value from + * a *map* with *sk* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *sk*) except this + * helper enforces the key must be a full socket and the map must + * be a **BPF_MAP_TYPE_SK_STORAGE** also. + * + * Underneath, the value is stored locally at *sk* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf-local-storages residing at *sk*. + * + * *sk* is a kernel **struct sock** pointer for LSM program. + * *sk* is a **struct bpf_sock** pointer for other program types. + * + * An optional *flags* (**BPF_SK_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf-local-storage will be + * created if one does not exist. *value* can be used + * together with **BPF_SK_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf-local-storage. If *value* is + * **NULL**, the new bpf-local-storage will be zero initialized. + * Return + * A bpf-local-storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf-local-storage. + * + * long bpf_sk_storage_delete(struct bpf_map *map, void *sk) + * Description + * Delete a bpf-local-storage from a *sk*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf-local-storage cannot be found. + * **-EINVAL** if sk is not a fullsock (e.g. a request_sock). + * + * long bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the process of the current task. + * The signal may be delivered to any of this process's threads. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * s64 bpf_tcp_gen_syncookie(void *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IP/TCP headers, *iph* and *th*, on the listening socket in *sk*. + * + * *iph* points to the start of the IPv4 or IPv6 header, while + * *iph_len* contains **sizeof**\ (**struct iphdr**) or + * **sizeof**\ (**struct ipv6hdr**). + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header with options (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** SYN cookie cannot be issued due to error + * + * **-ENOENT** SYN cookie should not be issued (no SYN flood) + * + * **-EOPNOTSUPP** kernel configuration does not enable SYN cookies + * + * **-EPROTONOSUPPORT** IP packet version is not 4 or 6 + * + * long bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct sk_buff. + * + * This helper is similar to **bpf_perf_event_output**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from user space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Safely attempt to read *size* bytes from kernel space address + * *unsafe_ptr* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe user address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, returns the number of bytes that were written, + * including the terminal NUL. This makes this helper useful in + * tracing programs for reading strings, and more importantly to + * get its length at runtime. See the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_user_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read_user**\ () helper here + * instead to read the string would require to estimate the length + * at compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the output string, + * including the trailing NUL character. On error, a negative + * value. + * + * long bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr) + * Description + * Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr* + * to *dst*. Same semantics as with **bpf_probe_read_user_str**\ () apply. + * Return + * On success, the strictly positive length of the string, including + * the trailing NUL character. On error, a negative value. + * + * long bpf_tcp_send_ack(void *tp, u32 rcv_nxt) + * Description + * Send out a tcp-ack. *tp* is the in-kernel struct **tcp_sock**. + * *rcv_nxt* is the ack_seq to be sent out. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_send_signal_thread(u32 sig) + * Description + * Send signal *sig* to the thread corresponding to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. + * + * u64 bpf_jiffies64(void) + * Description + * Obtain the 64bit jiffies + * Return + * The 64 bit jiffies + * + * long bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags) + * Description + * For an eBPF program attached to a perf event, retrieve the + * branch records (**struct perf_branch_entry**) associated to *ctx* + * and store it in the buffer pointed by *buf* up to size + * *size* bytes. + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to + * instead return the number of bytes required to store all the + * branch entries. If this flag is set, *buf* may be NULL. + * + * **-EINVAL** if arguments invalid or **size** not a multiple + * of **sizeof**\ (**struct perf_branch_entry**\ ). + * + * **-ENOENT** if architecture does not support branch records. + * + * long bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size) + * Description + * Returns 0 on success, values for *pid* and *tgid* as seen from the current + * *namespace* will be returned in *nsdata*. + * Return + * 0 on success, or one of the following in case of failure: + * + * **-EINVAL** if dev and inum supplied don't match dev_t and inode number + * with nsfs of current task, or if dev conversion to dev_t lost high bits. + * + * **-ENOENT** if pidns does not exists for the current task. + * + * long bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * *ctx* is a pointer to in-kernel struct xdp_buff. + * + * This helper is similar to **bpf_perf_eventoutput**\ () but + * restricted to raw_tracepoint bpf programs. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_get_netns_cookie(void *ctx) + * Description + * Retrieve the cookie (generated by the kernel) of the network + * namespace the input *ctx* is associated with. The network + * namespace cookie remains stable for its lifetime and provides + * a global identifier that can be assumed unique. If *ctx* is + * NULL, then the helper returns the cookie for the initial + * network namespace. The cookie itself is very similar to that + * of **bpf_get_socket_cookie**\ () helper, but for network + * namespaces instead of sockets. + * Return + * A 8-byte long opaque number. + * + * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of the cgroup associated + * with the current task at the *ancestor_level*. The root cgroup + * is at *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with the current task, then return value will be the + * same as that of **bpf_get_current_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with the current task. + * + * The format of returned id and helper limitations are same as in + * **bpf_get_current_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * long bpf_sk_assign(struct sk_buff *skb, void *sk, u64 flags) + * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SCHED_CLS** and + * **BPF_PROG_TYPE_SCHED_ACT** programs. + * + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative error in case of failure: + * + * **-EINVAL** if specified *flags* are not supported. + * + * **-ENOENT** if the socket is unavailable for assignment. + * + * **-ENETUNREACH** if the socket is unreachable (wrong netns). + * + * **-EOPNOTSUPP** if the operation is not supported, for example + * a call from outside of TC ingress. + * + * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags) + * Description + * Helper is overloaded depending on BPF program type. This + * description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs. + * + * Select the *sk* as a result of a socket lookup. + * + * For the operation to succeed passed socket must be compatible + * with the packet description provided by the *ctx* object. + * + * L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must + * be an exact match. While IP family (**AF_INET** or + * **AF_INET6**) must be compatible, that is IPv6 sockets + * that are not v6-only can be selected for IPv4 packets. + * + * Only TCP listeners and UDP unconnected sockets can be + * selected. *sk* can also be NULL to reset any previous + * selection. + * + * *flags* argument can combination of following values: + * + * * **BPF_SK_LOOKUP_F_REPLACE** to override the previous + * socket selection, potentially done by a BPF program + * that ran before us. + * + * * **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip + * load-balancing within reuseport group for the socket + * being selected. + * + * On success *ctx->sk* will point to the selected socket. + * + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EAFNOSUPPORT** if socket family (*sk->family*) is + * not compatible with packet family (*ctx->family*). + * + * * **-EEXIST** if socket has been already selected, + * potentially by another program, and + * **BPF_SK_LOOKUP_F_REPLACE** flag was not specified. + * + * * **-EINVAL** if unsupported flags were specified. + * + * * **-EPROTOTYPE** if socket L4 protocol + * (*sk->protocol*) doesn't match packet protocol + * (*ctx->protocol*). + * + * * **-ESOCKTNOSUPPORT** if socket is not in allowed + * state (TCP listening or UDP unconnected). + * + * u64 bpf_ktime_get_boot_ns(void) + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Does include the time the system was suspended. + * See: **clock_gettime**\ (**CLOCK_BOOTTIME**) + * Return + * Current *ktime*. + * + * long bpf_seq_printf(struct seq_file *m, const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * **bpf_seq_printf**\ () uses seq_file **seq_printf**\ () to print + * out the format string. + * The *m* represents the seq_file. The *fmt* and *fmt_size* are for + * the format string itself. The *data* and *data_len* are format string + * arguments. The *data* are a **u64** array and corresponding format string + * values are stored in the array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* array. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. + * + * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. + * Reading kernel memory may fail due to either invalid address or + * valid address but requiring a major memory fault. If reading kernel memory + * fails, the string for **%s** will be an empty string, and the ip + * address for **%p{i,I}{4,6}** will be 0. Not returning error to + * bpf program is consistent with what **bpf_trace_printk**\ () does for now. + * Return + * 0 on success, or a negative error in case of failure: + * + * **-EBUSY** if per-CPU memory copy buffer is busy, can try again + * by returning 1 from bpf program. + * + * **-EINVAL** if arguments are invalid, or if *fmt* is invalid/unsupported. + * + * **-E2BIG** if *fmt* contains too many format specifiers. + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * long bpf_seq_write(struct seq_file *m, const void *data, u32 len) + * Description + * **bpf_seq_write**\ () uses seq_file **seq_write**\ () to write the data. + * The *m* represents the seq_file. The *data* and *len* represent the + * data to write in bytes. + * Return + * 0 on success, or a negative error in case of failure: + * + * **-EOVERFLOW** if an overflow happened: The same object will be tried again. + * + * u64 bpf_sk_cgroup_id(void *sk) + * Description + * Return the cgroup v2 id of the socket *sk*. + * + * *sk* must be a non-**NULL** pointer to a socket, e.g. one + * returned from **bpf_sk_lookup_xxx**\ (), + * **bpf_sk_fullsock**\ (), etc. The format of returned id is + * same as in **bpf_skb_cgroup_id**\ (). + * + * This helper is available only if the kernel was compiled with + * the **CONFIG_SOCK_CGROUP_DATA** configuration option. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * u64 bpf_sk_ancestor_cgroup_id(void *sk, int ancestor_level) + * Description + * Return id of cgroup v2 that is ancestor of cgroup associated + * with the *sk* at the *ancestor_level*. The root cgroup is at + * *ancestor_level* zero and each step down the hierarchy + * increments the level. If *ancestor_level* == level of cgroup + * associated with *sk*, then return value will be same as that + * of **bpf_sk_cgroup_id**\ (). + * + * The helper is useful to implement policies based on cgroups + * that are upper in hierarchy than immediate cgroup associated + * with *sk*. + * + * The format of returned id and helper limitations are same as in + * **bpf_sk_cgroup_id**\ (). + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * long bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags) + * Description + * Copy *size* bytes from *data* into a ring buffer *ringbuf*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * An adaptive notification is a notification sent whenever the user-space + * process has caught up and consumed all available payloads. In case the user-space + * process is still processing a previous payload, then no notification is needed + * as it will process the newly added payload automatically. + * Return + * 0 on success, or a negative error in case of failure. + * + * void *bpf_ringbuf_reserve(void *ringbuf, u64 size, u64 flags) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf*. + * *flags* must be 0. + * Return + * Valid pointer with *size* bytes of memory available; NULL, + * otherwise. + * + * void bpf_ringbuf_submit(void *data, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard(void *data, u64 flags) + * Description + * Discard reserved ring buffer sample, pointed to by *data*. + * If **BPF_RB_NO_WAKEUP** is specified in *flags*, no notification + * of new data availability is sent. Discarded records remain in + * the ring buffer until consumed by user space, so a later submit + * using adaptive wakeup might not wake up the consumer. + * If **BPF_RB_FORCE_WAKEUP** is specified in *flags*, notification + * of new data availability is sent unconditionally. + * If **0** is specified in *flags*, an adaptive notification + * of new data availability is sent. + * + * See 'bpf_ringbuf_output()' for the definition of adaptive notification. + * Return + * Nothing. Always succeeds. + * + * u64 bpf_ringbuf_query(void *ringbuf, u64 flags) + * Description + * Query various characteristics of provided ring buffer. What + * exactly is queries is determined by *flags*: + * + * * **BPF_RB_AVAIL_DATA**: Amount of data not yet consumed. + * * **BPF_RB_RING_SIZE**: The size of ring buffer. + * * **BPF_RB_CONS_POS**: Consumer position (can wrap around). + * * **BPF_RB_PROD_POS**: Producer(s) position (can wrap around). + * * **BPF_RB_OVERWRITE_POS**: Overwrite position (can wrap around). + * + * Data returned is just a momentary snapshot of actual values + * and could be inaccurate, so this facility should be used to + * power heuristics and for reporting, not to make 100% correct + * calculation. + * Return + * Requested value, or 0, if *flags* are not recognized. + * + * long bpf_csum_level(struct sk_buff *skb, u64 level) + * Description + * Change the skbs checksum level by one layer up or down, or + * reset it entirely to none in order to have the stack perform + * checksum validation. The level is applicable to the following + * protocols: TCP, UDP, GRE, SCTP, FCOE. For example, a decap of + * | ETH | IP | UDP | GUE | IP | TCP | into | ETH | IP | TCP | + * through **bpf_skb_adjust_room**\ () helper with passing in + * **BPF_F_ADJ_ROOM_NO_CSUM_RESET** flag would require one call + * to **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_DEC** since + * the UDP header is removed. Similarly, an encap of the latter + * into the former could be accompanied by a helper call to + * **bpf_csum_level**\ () with **BPF_CSUM_LEVEL_INC** if the + * skb is still intended to be processed in higher layers of the + * stack instead of just egressing at tc. + * + * There are three supported level settings at this time: + * + * * **BPF_CSUM_LEVEL_INC**: Increases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_DEC**: Decreases skb->csum_level for skbs + * with CHECKSUM_UNNECESSARY. + * * **BPF_CSUM_LEVEL_RESET**: Resets skb->csum_level to 0 and + * sets CHECKSUM_NONE to force checksum validation by the stack. + * * **BPF_CSUM_LEVEL_QUERY**: No-op, returns the current + * skb->csum_level. + * Return + * 0 on success, or a negative error in case of failure. In the + * case of **BPF_CSUM_LEVEL_QUERY**, the current skb->csum_level + * is returned or the error code -EACCES in case the skb is not + * subject to CHECKSUM_UNNECESSARY. + * + * struct tcp6_sock *bpf_skc_to_tcp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp6_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * struct tcp_sock *bpf_skc_to_tcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * struct tcp_timewait_sock *bpf_skc_to_tcp_timewait_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_timewait_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * struct tcp_request_sock *bpf_skc_to_tcp_request_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *tcp_request_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * struct udp6_sock *bpf_skc_to_udp6_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *udp6_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_get_task_stack(struct task_struct *task, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * Note: the user stack will only be populated if the *task* is + * the current task; all other tasks will return -EOPNOTSUPP. + * To achieve this, the helper needs *task*, which is a valid + * pointer to **struct task_struct**. To store the stacktrace, the + * bpf program provides *buf* with a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * The *task* must be the current task. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_task_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack= + * Return + * The non-negative copied *buf* length equal to or less than + * *size* on success, or a negative error in case of failure. + * + * long bpf_load_hdr_opt(struct bpf_sock_ops *skops, void *searchby_res, u32 len, u64 flags) + * Description + * Load header option. Support reading a particular TCP header + * option for bpf program (**BPF_PROG_TYPE_SOCK_OPS**). + * + * If *flags* is 0, it will search the option from the + * *skops*\ **->skb_data**. The comment in **struct bpf_sock_ops** + * has details on what skb_data contains under different + * *skops*\ **->op**. + * + * The first byte of the *searchby_res* specifies the + * kind that it wants to search. + * + * If the searching kind is an experimental kind + * (i.e. 253 or 254 according to RFC6994). It also + * needs to specify the "magic" which is either + * 2 bytes or 4 bytes. It then also needs to + * specify the size of the magic by using + * the 2nd byte which is "kind-length" of a TCP + * header option and the "kind-length" also + * includes the first 2 bytes "kind" and "kind-length" + * itself as a normal TCP header option also does. + * + * For example, to search experimental kind 254 with + * 2 byte magic 0xeB9F, the searchby_res should be + * [ 254, 4, 0xeB, 0x9F, 0, 0, .... 0 ]. + * + * To search for the standard window scale option (3), + * the *searchby_res* should be [ 3, 0, 0, .... 0 ]. + * Note, kind-length must be 0 for regular option. + * + * Searching for No-Op (0) and End-of-Option-List (1) are + * not supported. + * + * *len* must be at least 2 bytes which is the minimal size + * of a header option. + * + * Supported flags: + * + * * **BPF_LOAD_HDR_OPT_TCP_SYN** to search from the + * saved_syn packet or the just-received syn packet. + * + * Return + * > 0 when found, the header option is copied to *searchby_res*. + * The return value is the total length copied. On failure, a + * negative error code is returned: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOMSG** if the option is not found. + * + * **-ENOENT** if no syn packet is available when + * **BPF_LOAD_HDR_OPT_TCP_SYN** is used. + * + * **-ENOSPC** if there is not enough space. Only *len* number of + * bytes are copied. + * + * **-EFAULT** on failure to parse the header options in the + * packet. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * long bpf_store_hdr_opt(struct bpf_sock_ops *skops, const void *from, u32 len, u64 flags) + * Description + * Store header option. The data will be copied + * from buffer *from* with length *len* to the TCP header. + * + * The buffer *from* should have the whole option that + * includes the kind, kind-length, and the actual + * option data. The *len* must be at least kind-length + * long. The kind-length does not have to be 4 byte + * aligned. The kernel will take care of the padding + * and setting the 4 bytes aligned value to th->doff. + * + * This helper will check for duplicated option + * by searching the same option in the outgoing skb. + * + * This helper can only be called during + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** If param is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * Nothing has been written + * + * **-EEXIST** if the option already exists. + * + * **-EFAULT** on failure to parse the existing header options. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * long bpf_reserve_hdr_opt(struct bpf_sock_ops *skops, u32 len, u64 flags) + * Description + * Reserve *len* bytes for the bpf header option. The + * space will be used by **bpf_store_hdr_opt**\ () later in + * **BPF_SOCK_OPS_WRITE_HDR_OPT_CB**. + * + * If **bpf_reserve_hdr_opt**\ () is called multiple times, + * the total number of bytes will be reserved. + * + * This helper can only be called during + * **BPF_SOCK_OPS_HDR_OPT_LEN_CB**. + * + * Return + * 0 on success, or negative error in case of failure: + * + * **-EINVAL** if a parameter is invalid. + * + * **-ENOSPC** if there is not enough space in the header. + * + * **-EPERM** if the helper cannot be used under the current + * *skops*\ **->op**. + * + * void *bpf_inode_storage_get(struct bpf_map *map, void *inode, void *value, u64 flags) + * Description + * Get a bpf_local_storage from an *inode*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *inode* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *inode*) except this + * helper enforces the key must be an inode and the map must also + * be a **BPF_MAP_TYPE_INODE_STORAGE**. + * + * Underneath, the value is stored locally at *inode* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *inode*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * int bpf_inode_storage_delete(struct bpf_map *map, void *inode) + * Description + * Delete a bpf_local_storage from an *inode*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * long bpf_d_path(const struct path *path, char *buf, u32 sz) + * Description + * Return full path for given **struct path** object, which + * needs to be the kernel BTF *path* object. The path is + * returned in the provided buffer *buf* of size *sz* and + * is zero terminated. + * + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * long bpf_copy_from_user(void *dst, u32 size, const void *user_ptr) + * Description + * Read *size* bytes from user space address *user_ptr* and store + * the data in *dst*. This is a wrapper of **copy_from_user**\ (). + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags) + * Description + * Use BTF to store a string representation of *ptr*->ptr in *str*, + * using *ptr*->type_id. This value should specify the type + * that *ptr*->ptr points to. LLVM __builtin_btf_type_id(type, 1) + * can be used to look up vmlinux BTF type ids. Traversing the + * data structure using BTF, the type information and values are + * stored in the first *str_size* - 1 bytes of *str*. Safe copy of + * the pointer data is carried out to avoid kernel crashes during + * operation. Smaller types can use string space on the stack; + * larger programs can use map data to store the string + * representation. + * + * The string can be subsequently shared with userspace via + * bpf_perf_event_output() or ring buffer interfaces. + * bpf_trace_printk() is to be avoided as it places too small + * a limit on string size to be useful. + * + * *flags* is a combination of + * + * **BTF_F_COMPACT** + * no formatting around type information + * **BTF_F_NONAME** + * no struct/union member names/types + * **BTF_F_PTR_RAW** + * show raw (unobfuscated) pointer values; + * equivalent to printk specifier %px. + * **BTF_F_ZERO** + * show zero-valued struct/union members; they + * are not displayed by default + * + * Return + * The number of bytes that were written (or would have been + * written if output had to be truncated due to string size), + * or a negative error in cases of failure. + * + * long bpf_seq_printf_btf(struct seq_file *m, struct btf_ptr *ptr, u32 ptr_size, u64 flags) + * Description + * Use BTF to write to seq_write a string representation of + * *ptr*->ptr, using *ptr*->type_id as per bpf_snprintf_btf(). + * *flags* are identical to those used for bpf_snprintf_btf. + * Return + * 0 on success or a negative error in case of failure. + * + * u64 bpf_skb_cgroup_classid(struct sk_buff *skb) + * Description + * See **bpf_get_cgroup_classid**\ () for the main description. + * This helper differs from **bpf_get_cgroup_classid**\ () in that + * the cgroup v1 net_cls class is retrieved only from the *skb*'s + * associated socket instead of the current process. + * Return + * The id is returned or 0 in case the id could not be retrieved. + * + * long bpf_redirect_neigh(u32 ifindex, struct bpf_redir_neigh *params, int plen, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex* + * and fill in L2 addresses from neighboring subsystem. This helper + * is somewhat similar to **bpf_redirect**\ (), except that it + * populates L2 addresses as well, meaning, internally, the helper + * relies on the neighbor lookup for the L2 address of the nexthop. + * + * The helper will perform a FIB lookup based on the skb's + * networking header to get the address of the next hop, unless + * this is supplied by the caller in the *params* argument. The + * *plen* argument indicates the len of *params* and should be set + * to 0 if *params* is NULL. + * + * The *flags* argument is reserved and must be 0. The helper is + * currently only supported for tc BPF program types, and enabled + * for IPv4 and IPv6 protocols. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + * + * void *bpf_per_cpu_ptr(const void *percpu_ptr, u32 cpu) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on *cpu*. A ksym is an + * extern variable decorated with '__ksym'. For ksym, there is a + * global var (either static or global) defined of the same name + * in the kernel. The ksym is percpu if the global var is percpu. + * The returned pointer points to the global percpu var on *cpu*. + * + * bpf_per_cpu_ptr() has the same semantic as per_cpu_ptr() in the + * kernel, except that bpf_per_cpu_ptr() may return NULL. This + * happens if *cpu* is larger than nr_cpu_ids. The caller of + * bpf_per_cpu_ptr() must check the returned value. + * Return + * A pointer pointing to the kernel percpu variable on *cpu*, or + * NULL, if *cpu* is invalid. + * + * void *bpf_this_cpu_ptr(const void *percpu_ptr) + * Description + * Take a pointer to a percpu ksym, *percpu_ptr*, and return a + * pointer to the percpu kernel variable on this cpu. See the + * description of 'ksym' in **bpf_per_cpu_ptr**\ (). + * + * bpf_this_cpu_ptr() has the same semantic as this_cpu_ptr() in + * the kernel. Different from **bpf_per_cpu_ptr**\ (), it would + * never return NULL. + * Return + * A pointer pointing to the kernel percpu variable on this cpu. + * + * long bpf_redirect_peer(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_redirect**\ (), except + * that the redirection happens to the *ifindex*' peer device. If + * *flags* is 0, the netns switch takes place from ingress to + * ingress without going through the CPU's backlog queue. If the + * **BPF_F_EGRESS** flag is provided then redirection happens in + * the egress direction of the peer device. + * + * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during + * the netns switch. + * + * If the *flags* argument is 0, the helper is currently only + * supported for tc BPF program types at the ingress hook and for + * veth and netkit target device types. The peer device must reside + * in a different network namespace. + * Return + * The helper returns **TC_ACT_REDIRECT** on success or + * **TC_ACT_SHOT** on error. + * + * void *bpf_task_storage_get(struct bpf_map *map, struct task_struct *task, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *task*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *task* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *task*) except this + * helper enforces the key must be a task_struct and the map must also + * be a **BPF_MAP_TYPE_TASK_STORAGE**. + * + * Underneath, the value is stored locally at *task* instead of + * the *map*. The *map* is used as the bpf-local-storage + * "type". The bpf-local-storage "type" (i.e. the *map*) is + * searched against all bpf_local_storage residing at *task*. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_task_storage_delete(struct bpf_map *map, struct task_struct *task) + * Description + * Delete a bpf_local_storage from a *task*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + * + * struct task_struct *bpf_get_current_task_btf(void) + * Description + * Return a BTF pointer to the "current" task. + * This pointer can also be used in helpers that accept an + * *ARG_PTR_TO_BTF_ID* of type *task_struct*. + * Return + * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's available). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUPP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. + * + * struct socket *bpf_sock_from_file(struct file *file) + * Description + * If the given file represents a socket, returns the associated + * socket. + * Return + * A pointer to a struct socket on success or NULL if the file is + * not a socket. + * + * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) + * Description + * Check packet size against exceeding MTU of net device (based + * on *ifindex*). This helper will likely be used in combination + * with helpers that adjust/change the packet size. + * + * The argument *len_diff* can be used for querying with a planned + * size change. This allows to check MTU prior to changing packet + * ctx. Providing a *len_diff* adjustment that is larger than the + * actual packet size (resulting in negative packet size) will in + * principle not exceed the MTU, which is why it is not considered + * a failure. Other BPF helpers are needed for performing the + * planned size change; therefore the responsibility for catching + * a negative packet size belongs in those helpers. + * + * Specifying *ifindex* zero means the MTU check is performed + * against the current net device. This is practical if this isn't + * used prior to redirect. + * + * On input *mtu_len* must be a valid pointer, else verifier will + * reject BPF program. If the value *mtu_len* is initialized to + * zero then the ctx packet size is use. When value *mtu_len* is + * provided as input this specify the L3 length that the MTU check + * is done against. Remember XDP and TC length operate at L2, but + * this value is L3 as this correlate to MTU and IP-header tot_len + * values which are L3 (similar behavior as bpf_fib_lookup). + * + * The Linux kernel route table can configure MTUs on a more + * specific per route level, which is not provided by this helper. + * For route level MTU checks use the **bpf_fib_lookup**\ () + * helper. + * + * *ctx* is either **struct xdp_md** for XDP programs or + * **struct sk_buff** for tc cls_act programs. + * + * The *flags* argument can be a combination of one or more of the + * following values: + * + * **BPF_MTU_CHK_SEGS** + * This flag will only works for *ctx* **struct sk_buff**. + * If packet context contains extra packet segment buffers + * (often knows as GSO skb), then MTU check is harder to + * check at this point, because in transmit path it is + * possible for the skb packet to get re-segmented + * (depending on net device features). This could still be + * a MTU violation, so this flag enables performing MTU + * check against segments, with a different violation + * return code to tell it apart. Check cannot use len_diff. + * + * On return *mtu_len* pointer contains the MTU value of the net + * device. Remember the net device configured MTU is the L3 size, + * which is returned here and XDP and TC length operate at L2. + * Helper take this into account for you, but remember when using + * MTU value in your BPF-code. + * + * Return + * * 0 on success, and populate MTU value in *mtu_len* pointer. + * + * * < 0 if any input argument is invalid (*mtu_len* not updated) + * + * MTU violations return positive values, but also populate MTU + * value in *mtu_len* pointer, as this can be needed for + * implementing PMTU handing: + * + * * **BPF_MTU_CHK_RET_FRAG_NEEDED** + * * **BPF_MTU_CHK_RET_SEGS_TOOBIG** + * + * long bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For each element in **map**, call **callback_fn** function with + * **map**, **callback_ctx** and other map-specific parameters. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. + * + * The following are a list of supported map types and their + * respective expected callback signatures: + * + * BPF_MAP_TYPE_HASH, BPF_MAP_TYPE_PERCPU_HASH, + * BPF_MAP_TYPE_LRU_HASH, BPF_MAP_TYPE_LRU_PERCPU_HASH, + * BPF_MAP_TYPE_ARRAY, BPF_MAP_TYPE_PERCPU_ARRAY + * + * long (\*callback_fn)(struct bpf_map \*map, const void \*key, void \*value, void \*ctx); + * + * For per_cpu maps, the map_value is the value on the cpu where the + * bpf_prog is running. + * + * If **callback_fn** return 0, the helper will continue to the next + * element. If return value is 1, the helper will skip the rest of + * elements and return. Other return values are not used now. + * + * Return + * The number of traversed map elements for success, **-EINVAL** for + * invalid **flags**. + * + * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len) + * Description + * Outputs a string into the **str** buffer of size **str_size** + * based on a format string stored in a read-only map pointed by + * **fmt**. + * + * Each format specifier in **fmt** corresponds to one u64 element + * in the **data** array. For strings and pointers where pointees + * are accessed, only the pointer values are stored in the *data* + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. + * + * Formats **%s** and **%p{i,I}{4,6}** require to read kernel + * memory. Reading kernel memory may fail due to either invalid + * address or valid address but requiring a major memory fault. If + * reading kernel memory fails, the string for **%s** will be an + * empty string, and the ip address for **%p{i,I}{4,6}** will be 0. + * Not returning error to bpf program is consistent with what + * **bpf_trace_printk**\ () does for now. + * + * Return + * The strictly positive length of the formatted string, including + * the trailing zero character. If the return value is greater than + * **str_size**, **str** contains a truncated string, guaranteed to + * be zero-terminated except when **str_size** is 0. + * + * Or **-EBUSY** if the per-CPU memory copy buffer is busy. + * + * long bpf_sys_bpf(u32 cmd, void *attr, u32 attr_size) + * Description + * Execute bpf syscall with given arguments. + * Return + * A syscall result. + * + * long bpf_btf_find_by_name_kind(char *name, int name_sz, u32 kind, int flags) + * Description + * Find BTF type with given name and kind in vmlinux BTF or in module's BTFs. + * Return + * Returns btf_id and btf_obj_fd in lower and upper 32 bits. + * + * long bpf_sys_close(u32 fd) + * Description + * Execute close syscall for given FD. + * Return + * A syscall result. + * + * long bpf_timer_init(struct bpf_timer *timer, struct bpf_map *map, u64 flags) + * Description + * Initialize the timer. + * First 4 bits of *flags* specify clockid. + * Only CLOCK_MONOTONIC, CLOCK_REALTIME, CLOCK_BOOTTIME are allowed. + * All other bits of *flags* are reserved. + * The verifier will reject the program if *timer* is not from + * the same *map*. + * Return + * 0 on success. + * **-EBUSY** if *timer* is already initialized. + * **-EINVAL** if invalid *flags* are passed. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn) + * Description + * Configure the timer to call *callback_fn* static function. + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EPERM** if *timer* is in a map that doesn't have any user references. + * The user space should either hold a file descriptor to a map with timers + * or pin such map in bpffs. When map is unpinned or file descriptor is + * closed all timers in the map will be cancelled and freed. + * + * long bpf_timer_start(struct bpf_timer *timer, u64 nsecs, u64 flags) + * Description + * Set timer expiration N nanoseconds from the current time. The + * configured callback will be invoked in soft irq context on some cpu + * and will not repeat unless another bpf_timer_start() is made. + * In such case the next invocation can migrate to a different cpu. + * Since struct bpf_timer is a field inside map element the map + * owns the timer. The bpf_timer_set_callback() will increment refcnt + * of BPF program to make sure that callback_fn code stays valid. + * When user space reference to a map reaches zero all timers + * in a map are cancelled and corresponding program's refcnts are + * decremented. This is done to make sure that Ctrl-C of a user + * process doesn't leave any timers running. If map is pinned in + * bpffs the callback_fn can re-arm itself indefinitely. + * bpf_map_update/delete_elem() helpers and user space sys_bpf commands + * cancel and free the timer in the given map element. + * The map can contain timers that invoke callback_fn-s from different + * programs. The same callback_fn can serve different timers from + * different maps if key/value layout matches across maps. + * Every bpf_timer_set_callback() can have different callback_fn. + * + * *flags* can be one of: + * + * **BPF_F_TIMER_ABS** + * Start the timer in absolute expire value instead of the + * default relative one. + * **BPF_F_TIMER_CPU_PIN** + * Timer will be pinned to the CPU of the caller. + * + * Return + * 0 on success. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier + * or invalid *flags* are passed. + * + * long bpf_timer_cancel(struct bpf_timer *timer) + * Description + * Cancel the timer and wait for callback_fn to finish if it was running. + * Return + * 0 if the timer was not active. + * 1 if the timer was active. + * **-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier. + * **-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its + * own timer which would have led to a deadlock otherwise. + * + * u64 bpf_get_func_ip(void *ctx) + * Description + * Get address of the traced function (for tracing and kprobe programs). + * + * When called for kprobe program attached as uprobe it returns + * probe address for both entry and return uprobe. + * + * Return + * Address of the traced function for kprobe. + * 0 for kprobes placed within the function (not at the entry). + * Address of the probe for uprobe and return uprobe. + * + * u64 bpf_get_attach_cookie(void *ctx) + * Description + * Get bpf_cookie value provided (optionally) during the program + * attachment. It might be different for each individual + * attachment, even if BPF program itself is the same. + * Expects BPF program context *ctx* as a first argument. + * + * Supported for the following program types: + * - kprobe/uprobe; + * - tracepoint; + * - perf_event. + * Return + * Value specified by user at BPF link creation/attachment time + * or 0, if it was not specified. + * + * long bpf_task_pt_regs(struct task_struct *task) + * Description + * Get the struct pt_regs associated with **task**. + * Return + * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u64 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument register (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= argument register count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of registers of the traced function (for tracing programs) where + * function arguments are stored in these registers. + * + * Return + * The number of argument registers of the traced function. + * + * int bpf_get_retval(void) + * Description + * Get the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * Return + * The BPF program's return value. + * + * int bpf_set_retval(int retval) + * Description + * Set the BPF program's return value that will be returned to the upper layers. + * + * This helper is currently supported by cgroup programs and only by the hooks + * where BPF program's return value is returned to the userspace via errno. + * + * Note that there is the following corner case where the program exports an error + * via bpf_set_retval but signals success via 'return 1': + * + * bpf_set_retval(-EPERM); + * return 1; + * + * In this case, the BPF program's return value will use helper's -EPERM. This + * still holds true for cgroup/bind{4,6} which supports extra 'return 3' success case. + * + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_xdp_get_buff_len(struct xdp_buff *xdp_md) + * Description + * Get the total size of a given xdp buff (linear and paged area) + * Return + * The total size of a given xdp buffer. + * + * long bpf_xdp_load_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * This helper is provided as an easy way to load data from a + * xdp buffer. It can be used to load *len* bytes from *offset* from + * the frame associated to *xdp_md*, into the buffer pointed by + * *buf*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_xdp_store_bytes(struct xdp_buff *xdp_md, u32 offset, void *buf, u32 len) + * Description + * Store *len* bytes from buffer *buf* into the frame + * associated to *xdp_md*, at *offset*. + * Return + * 0 on success, or a negative error in case of failure. + * + * long bpf_copy_from_user_task(void *dst, u32 size, const void *user_ptr, struct task_struct *tsk, u64 flags) + * Description + * Read *size* bytes from user space address *user_ptr* in *tsk*'s + * address space, and stores the data in *dst*. *flags* is not + * used yet and is provided for future extensibility. This helper + * can only be used by sleepable programs. + * Return + * 0 on success, or a negative error in case of failure. On error + * *dst* buffer is zeroed out. + * + * long bpf_skb_set_tstamp(struct sk_buff *skb, u64 tstamp, u32 tstamp_type) + * Description + * Change the __sk_buff->tstamp_type to *tstamp_type* + * and set *tstamp* to the __sk_buff->tstamp together. + * + * If there is no need to change the __sk_buff->tstamp_type, + * the tstamp value can be directly written to __sk_buff->tstamp + * instead. + * + * BPF_SKB_TSTAMP_DELIVERY_MONO is the only tstamp that + * will be kept during bpf_redirect_*(). A non zero + * *tstamp* must be used with the BPF_SKB_TSTAMP_DELIVERY_MONO + * *tstamp_type*. + * + * A BPF_SKB_TSTAMP_UNSPEC *tstamp_type* can only be used + * with a zero *tstamp*. + * + * Only IPv4 and IPv6 skb->protocol are supported. + * + * This function is most useful when it needs to set a + * mono delivery time to __sk_buff->tstamp and then + * bpf_redirect_*() to the egress of an iface. For example, + * changing the (rcv) timestamp in __sk_buff->tstamp at + * ingress to a mono delivery time and then bpf_redirect_*() + * to sch_fq@phy-dev. + * Return + * 0 on success. + * **-EINVAL** for invalid input + * **-EOPNOTSUPP** for unsupported protocol + * + * long bpf_ima_file_hash(struct file *file, void *dst, u32 size) + * Description + * Returns a calculated IMA hash of the *file*. + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUPP** if the hash calculation failed or **-EINVAL** if + * invalid arguments are passed. + * + * void *bpf_kptr_xchg(void *dst, void *ptr) + * Description + * Exchange kptr at pointer *dst* with *ptr*, and return the old value. + * *dst* can be map value or local kptr. *ptr* can be NULL, otherwise + * it must be a referenced pointer which will be released when this helper + * is called. + * Return + * The old value of kptr (which can be NULL). The returned pointer + * if not NULL, is a reference which must be released using its + * corresponding release function, or moved into a BPF map before + * program exit. + * + * void *bpf_map_lookup_percpu_elem(struct bpf_map *map, const void *key, u32 cpu) + * Description + * Perform a lookup in *percpu map* for an entry associated to + * *key* on *cpu*. + * Return + * Map value associated to *key* on *cpu*, or **NULL** if no entry + * was found or *cpu* is invalid. + * + * struct mptcp_sock *bpf_skc_to_mptcp_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *mptcp_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_dynptr_from_mem(void *data, u64 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Get a dynptr to local memory *data*. + * + * *data* must be a ptr to a map value. + * The maximum *size* supported is DYNPTR_MAX_SIZE. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE, + * -EINVAL if flags is not 0. + * + * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr) + * Description + * Reserve *size* bytes of payload in a ring buffer *ringbuf* + * through the dynptr interface. *flags* must be 0. + * + * Please note that a corresponding bpf_ringbuf_submit_dynptr or + * bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the + * reservation fails. This is enforced by the verifier. + * Return + * 0 on success, or a negative error in case of failure. + * + * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Submit reserved ring buffer sample, pointed to by *data*, + * through the dynptr interface. This is a no-op if the dynptr is + * invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_submit'. + * Return + * Nothing. Always succeeds. + * + * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags) + * Description + * Discard reserved ring buffer sample through the dynptr + * interface. This is a no-op if the dynptr is invalid/null. + * + * For more information on *flags*, please see + * 'bpf_ringbuf_discard'. + * Return + * Nothing. Always succeeds. + * + * long bpf_dynptr_read(void *dst, u64 len, const struct bpf_dynptr *src, u64 offset, u64 flags) + * Description + * Read *len* bytes from *src* into *dst*, starting from *offset* + * into *src*. + * *flags* is currently unused. + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if + * *flags* is not 0. + * + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u64 offset, void *src, u64 len, u64 flags) + * Description + * Write *len* bytes from *src* into *dst*, starting from *offset* + * into *dst*. + * + * *flags* must be 0 except for skb-type dynptrs. + * + * For skb-type dynptrs: + * * All data slices of the dynptr are automatically + * invalidated after **bpf_dynptr_write**\ (). This is + * because writing may pull the skb and change the + * underlying packet buffer. + * + * * For *flags*, please see the flags accepted by + * **bpf_skb_store_bytes**\ (). + * Return + * 0 on success, -E2BIG if *offset* + *len* exceeds the length + * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* + * is a read-only dynptr or if *flags* is not correct. For skb-type dynptrs, + * other errors correspond to errors returned by **bpf_skb_store_bytes**\ (). + * + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u64 offset, u64 len) + * Description + * Get a pointer to the underlying dynptr data. + * + * *len* must be a statically known value. The returned data slice + * is invalidated whenever the dynptr is invalidated. + * + * skb and xdp type dynptrs may not use bpf_dynptr_data. They should + * instead use bpf_dynptr_slice and bpf_dynptr_slice_rdwr. + * Return + * Pointer to the underlying dynptr data, NULL if the dynptr is + * read-only, if the dynptr is invalid, or if the offset and length + * is out of bounds. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv4/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * s64 bpf_tcp_raw_gen_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th, u32 th_len) + * Description + * Try to issue a SYN cookie for the packet with corresponding + * IPv6/TCP headers, *iph* and *th*, without depending on a + * listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the start of the TCP header, while *th_len* + * contains the length of the TCP header (at least + * **sizeof**\ (**struct tcphdr**)). + * Return + * On success, lower 32 bits hold the generated SYN cookie in + * followed by 16 bits which hold the MSS value for that cookie, + * and the top 16 bits are unused. + * + * On failure, the returned value is one of the following: + * + * **-EINVAL** if *th_len* is invalid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * long bpf_tcp_raw_check_syncookie_ipv4(struct iphdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv4 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * long bpf_tcp_raw_check_syncookie_ipv6(struct ipv6hdr *iph, struct tcphdr *th) + * Description + * Check whether *iph* and *th* contain a valid SYN cookie ACK + * without depending on a listening socket. + * + * *iph* points to the IPv6 header. + * + * *th* points to the TCP header. + * Return + * 0 if *iph* and *th* are a valid SYN cookie ACK. + * + * On failure, the returned value is one of the following: + * + * **-EACCES** if the SYN cookie is not valid. + * + * **-EPROTONOSUPPORT** if CONFIG_IPV6 is not builtin. + * + * u64 bpf_ktime_get_tai_ns(void) + * Description + * A nonsettable system-wide clock derived from wall-clock time but + * ignoring leap seconds. This clock does not experience + * discontinuities and backwards jumps caused by NTP inserting leap + * seconds as CLOCK_REALTIME does. + * + * See: **clock_gettime**\ (**CLOCK_TAI**) + * Return + * Current *ktime*. + * + * long bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void *ctx, u64 flags) + * Description + * Drain samples from the specified user ring buffer, and invoke + * the provided callback for each such sample: + * + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); + * + * If **callback_fn** returns 0, the helper will continue to try + * and drain the next sample, up to a maximum of + * BPF_MAX_USER_RINGBUF_SAMPLES samples. If the return value is 1, + * the helper will skip the rest of the samples and return. Other + * return values are not used now, and will be rejected by the + * verifier. + * Return + * The number of drained samples if no error was encountered while + * draining samples, or 0 if no samples were present in the ring + * buffer. If a user-space producer was epoll-waiting on this map, + * and at least one sample was drained, they will receive an event + * notification notifying them of available space in the ring + * buffer. If the BPF_RB_NO_WAKEUP flag is passed to this + * function, no wakeup notification will be sent. If the + * BPF_RB_FORCE_WAKEUP flag is passed, a wakeup notification will + * be sent even if no sample was drained. + * + * On failure, the returned value is one of the following: + * + * **-EBUSY** if the ring buffer is contended, and another calling + * context was concurrently draining the ring buffer. + * + * **-EINVAL** if user-space is not properly tracking the ring + * buffer due to the producer position not being aligned to 8 + * bytes, a sample not being aligned to 8 bytes, or the producer + * position not matching the advertised length of a sample. + * + * **-E2BIG** if user-space has tried to publish a sample which is + * larger than the size of the ring buffer, or which cannot fit + * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. + */ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ + /* This helper list is effectively frozen. If you are trying to \ + * add a new helper, you should add a kfunc instead which has \ + * less stability guarantees. See Documentation/bpf/kfuncs.rst \ + */ + +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, +enum bpf_func_id { + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) + __BPF_FUNC_MAX_ID, +}; +#undef __BPF_ENUM_FN + +/* All flags used by eBPF helper functions, placed here. */ + +/* BPF_FUNC_skb_store_bytes flags. */ +enum { + BPF_F_RECOMPUTE_CSUM = (1ULL << 0), + BPF_F_INVALIDATE_HASH = (1ULL << 1), +}; + +/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. + * First 4 bits are for passing the header field size. + */ +enum { + BPF_F_HDR_FIELD_MASK = 0xfULL, +}; + +/* BPF_FUNC_l4_csum_replace flags. */ +enum { + BPF_F_PSEUDO_HDR = (1ULL << 4), + BPF_F_MARK_MANGLED_0 = (1ULL << 5), + BPF_F_MARK_ENFORCE = (1ULL << 6), + BPF_F_IPV6 = (1ULL << 7), +}; + +/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ +enum { + BPF_F_TUNINFO_IPV6 = (1ULL << 0), +}; + +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ +enum { + BPF_F_SKIP_FIELD_MASK = 0xffULL, + BPF_F_USER_STACK = (1ULL << 8), +/* flags used by BPF_FUNC_get_stackid only. */ + BPF_F_FAST_STACK_CMP = (1ULL << 9), + BPF_F_REUSE_STACKID = (1ULL << 10), +/* flags used by BPF_FUNC_get_stack only. */ + BPF_F_USER_BUILD_ID = (1ULL << 11), +}; + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +enum { + BPF_F_ZERO_CSUM_TX = (1ULL << 1), + BPF_F_DONT_FRAGMENT = (1ULL << 2), + BPF_F_SEQ_NUMBER = (1ULL << 3), + BPF_F_NO_TUNNEL_KEY = (1ULL << 4), +}; + +/* BPF_FUNC_skb_get_tunnel_key flags. */ +enum { + BPF_F_TUNINFO_FLAGS = (1ULL << 4), +}; + +/* BPF_FUNC_perf_event_output, BPF_FUNC_perf_event_read and + * BPF_FUNC_perf_event_read_value flags. + */ +enum { + BPF_F_INDEX_MASK = 0xffffffffULL, + BPF_F_CURRENT_CPU = BPF_F_INDEX_MASK, +/* BPF_FUNC_perf_event_output for sk_buff input context. */ + BPF_F_CTXLEN_MASK = (0xfffffULL << 32), +}; + +/* Current network namespace */ +enum { + BPF_F_CURRENT_NETNS = (-1L), +}; + +/* BPF_FUNC_csum_level level values. */ +enum { + BPF_CSUM_LEVEL_QUERY, + BPF_CSUM_LEVEL_INC, + BPF_CSUM_LEVEL_DEC, + BPF_CSUM_LEVEL_RESET, +}; + +/* BPF_FUNC_skb_adjust_room flags. */ +enum bpf_adj_room_flags { + BPF_F_ADJ_ROOM_FIXED_GSO = (1ULL << 0), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 = (1ULL << 1), + BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 = (1ULL << 2), + BPF_F_ADJ_ROOM_ENCAP_L4_GRE = (1ULL << 3), + BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), + BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), + BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), + BPF_F_ADJ_ROOM_DECAP_L4_GRE = (1ULL << 9), + BPF_F_ADJ_ROOM_DECAP_L4_UDP = (1ULL << 10), + BPF_F_ADJ_ROOM_DECAP_IPXIP4 = (1ULL << 11), + BPF_F_ADJ_ROOM_DECAP_IPXIP6 = (1ULL << 12), +}; + +enum { + BPF_ADJ_ROOM_ENCAP_L2_MASK = 0xff, + BPF_ADJ_ROOM_ENCAP_L2_SHIFT = 56, +}; + +#define BPF_F_ADJ_ROOM_ENCAP_L2(len) (((__u64)len & \ + BPF_ADJ_ROOM_ENCAP_L2_MASK) \ + << BPF_ADJ_ROOM_ENCAP_L2_SHIFT) + +/* BPF_FUNC_sysctl_get_name flags. */ +enum { + BPF_F_SYSCTL_BASE_NAME = (1ULL << 0), +}; + +/* BPF_FUNC__storage_get flags */ +enum { + BPF_LOCAL_STORAGE_GET_F_CREATE = (1ULL << 0), + /* BPF_SK_STORAGE_GET_F_CREATE is only kept for backward compatibility + * and BPF_LOCAL_STORAGE_GET_F_CREATE must be used instead. + */ + BPF_SK_STORAGE_GET_F_CREATE = BPF_LOCAL_STORAGE_GET_F_CREATE, +}; + +/* BPF_FUNC_read_branch_records flags. */ +enum { + BPF_F_GET_BRANCH_RECORDS_SIZE = (1ULL << 0), +}; + +/* BPF_FUNC_bpf_ringbuf_commit, BPF_FUNC_bpf_ringbuf_discard, and + * BPF_FUNC_bpf_ringbuf_output flags. + */ +enum { + BPF_RB_NO_WAKEUP = (1ULL << 0), + BPF_RB_FORCE_WAKEUP = (1ULL << 1), +}; + +/* BPF_FUNC_bpf_ringbuf_query flags */ +enum { + BPF_RB_AVAIL_DATA = 0, + BPF_RB_RING_SIZE = 1, + BPF_RB_CONS_POS = 2, + BPF_RB_PROD_POS = 3, + BPF_RB_OVERWRITE_POS = 4, +}; + +/* BPF ring buffer constants */ +enum { + BPF_RINGBUF_BUSY_BIT = (1U << 31), + BPF_RINGBUF_DISCARD_BIT = (1U << 30), + BPF_RINGBUF_HDR_SZ = 8, +}; + +/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */ +enum { + BPF_SK_LOOKUP_F_REPLACE = (1ULL << 0), + BPF_SK_LOOKUP_F_NO_REUSEPORT = (1ULL << 1), +}; + +/* Mode for BPF_FUNC_skb_adjust_room helper. */ +enum bpf_adj_room_mode { + BPF_ADJ_ROOM_NET, + BPF_ADJ_ROOM_MAC, +}; + +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + +/* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ +enum bpf_lwt_encap_mode { + BPF_LWT_ENCAP_SEG6, + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, +}; + +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + +/* Flags for bpf_redirect and bpf_redirect_map helpers */ +enum { + BPF_F_INGRESS = (1ULL << 0), /* used for skb path */ + BPF_F_EGRESS = (1ULL << 1), /* used for skb path */ + BPF_F_BROADCAST = (1ULL << 3), /* used for XDP path */ + BPF_F_EXCLUDE_INGRESS = (1ULL << 4), /* used for XDP path */ +#define BPF_F_REDIRECT_FLAGS (BPF_F_INGRESS | BPF_F_EGRESS | BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS) +}; + +#define __bpf_md_ptr(type, name) \ +union { \ + type name; \ + __u64 :64; \ +} __attribute__((aligned(8))) + +/* The enum used in skb->tstamp_type. It specifies the clock type + * of the time stored in the skb->tstamp. + */ +enum { + BPF_SKB_TSTAMP_UNSPEC = 0, /* DEPRECATED */ + BPF_SKB_TSTAMP_DELIVERY_MONO = 1, /* DEPRECATED */ + BPF_SKB_CLOCK_REALTIME = 0, + BPF_SKB_CLOCK_MONOTONIC = 1, + BPF_SKB_CLOCK_TAI = 2, + /* For any future BPF_SKB_CLOCK_* that the bpf prog cannot handle, + * the bpf prog can try to deduce it by ingress/egress/skb->sk->sk_clockid. + */ +}; + +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; + __u32 napi_id; + + /* Accessed by BPF_PROG_TYPE_sk_skb types from here to ... */ + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + /* ... here. */ + + __u32 data_meta; + __bpf_md_ptr(struct bpf_flow_keys *, flow_keys); + __u64 tstamp; + __u32 wire_len; + __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); + __u32 gso_size; + __u8 tstamp_type; + __u32 :24; /* Padding, future use. */ + __u64 hwtstamp; +}; + +struct bpf_tunnel_key { + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + union { + __u16 tunnel_ext; /* compat */ + __be16 tunnel_flags; + }; + __u32 tunnel_label; + union { + __u32 local_ipv4; + __u32 local_ipv6[4]; + }; +}; + +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + __u16 ext; /* Padding, future use. */ + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + +/* Generic BPF return codes which all BPF program types may support. + * The values are binary compatible with their TC_ACT_* counter-part to + * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT + * programs. + * + * XDP is handled seprately, see XDP_*. + */ +enum bpf_ret_code { + BPF_OK = 0, + /* 1 reserved */ + BPF_DROP = 2, + /* 3-6 reserved */ + BPF_REDIRECT = 7, + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, + /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR + * to indicate that no custom dissection was performed, and + * fallback to standard dissector is requested. + */ + BPF_FLOW_DISSECTOR_CONTINUE = 129, +}; + +struct bpf_sock { + __u32 bound_dev_if; + __u32 family; + __u32 type; + __u32 protocol; + __u32 mark; + __u32 priority; + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __be16 dst_port; /* network byte order */ + __u16 :16; /* zero padding */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; + __s32 rx_queue_mapping; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. + */ + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. + */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ +}; + +struct bpf_sock_tuple { + union { + struct { + __be32 saddr; + __be32 daddr; + __be16 sport; + __be16 dport; + } ipv4; + struct { + __be32 saddr[4]; + __be32 daddr[4]; + __be16 sport; + __be16 dport; + } ipv6; + }; +}; + +/* (Simplified) user return codes for tcx prog type. + * A valid tcx program must return one of these defined values. All other + * return codes are reserved for future use. Must remain compatible with + * their TC_ACT_* counter-parts. For compatibility in behavior, unknown + * return codes are mapped to TCX_NEXT. + */ +enum tcx_action_base { + TCX_NEXT = -1, + TCX_PASS = 0, + TCX_DROP = 2, + TCX_REDIRECT = 7, +}; + +struct bpf_xdp_sock { + __u32 queue_id; +}; + +#define XDP_PACKET_HEADROOM 256 + +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will + * result in packet drops and a warning via bpf_warn_invalid_xdp_action(). + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, + XDP_REDIRECT, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; + __u32 data_meta; + /* Below access go through struct xdp_rxq_info */ + __u32 ingress_ifindex; /* rxq->dev->ifindex */ + __u32 rx_queue_index; /* rxq->queue_index */ + + __u32 egress_ifindex; /* txq->dev->ifindex */ +}; + +/* DEVMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_devmap_val { + __u32 ifindex; /* device index */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; +}; + +/* CPUMAP map-value layout + * + * The struct data-layout of map-value is a configuration interface. + * New members can only be added to the end of this structure. + */ +struct bpf_cpumap_val { + __u32 qsize; /* queue size to remote target CPU */ + union { + int fd; /* prog fd on map write */ + __u32 id; /* prog id on map read */ + } bpf_prog; +}; + +enum sk_action { + SK_DROP = 0, + SK_PASS, +}; + +/* user accessible metadata for SK_MSG packet hook, new fields must + * be added to the end of this structure + */ +struct sk_msg_md { + __bpf_md_ptr(void *, data); + __bpf_md_ptr(void *, data_end); + + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 size; /* Total size of sk_msg */ + + __bpf_md_ptr(struct bpf_sock *, sk); /* current socket */ +}; + +struct sk_reuseport_md { + /* + * Start of directly accessible data. It begins from + * the tcp/udp header. + */ + __bpf_md_ptr(void *, data); + /* End of directly accessible data */ + __bpf_md_ptr(void *, data_end); + /* + * Total length of packet (starting from the tcp/udp header). + * Note that the directly accessible bytes (data_end - data) + * could be less than this "len". Those bytes could be + * indirectly read by a helper "bpf_skb_load_bytes()". + */ + __u32 len; + /* + * Eth protocol in the mac header (network byte order). e.g. + * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD) + */ + __u32 eth_protocol; + __u32 ip_protocol; /* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */ + __u32 bind_inany; /* Is sock bound to an INANY address? */ + __u32 hash; /* A hash of the packet 4 tuples */ + /* When reuse->migrating_sk is NULL, it is selecting a sk for the + * new incoming connection request (e.g. selecting a listen sk for + * the received SYN in the TCP case). reuse->sk is one of the sk + * in the reuseport group. The bpf prog can use reuse->sk to learn + * the local listening ip/port without looking into the skb. + * + * When reuse->migrating_sk is not NULL, reuse->sk is closed and + * reuse->migrating_sk is the socket that needs to be migrated + * to another listening socket. migrating_sk could be a fullsock + * sk that is fully established or a reqsk that is in-the-middle + * of 3-way handshake. + */ + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(struct bpf_sock *, migrating_sk); +}; + +#define BPF_TAG_SIZE 8 + +struct bpf_prog_info { + __u32 type; + __u32 id; + __u8 tag[BPF_TAG_SIZE]; + __u32 jited_prog_len; + __u32 xlated_prog_len; + __aligned_u64 jited_prog_insns; + __aligned_u64 xlated_prog_insns; + __u64 load_time; /* ns since boottime */ + __u32 created_by_uid; + __u32 nr_map_ids; + __aligned_u64 map_ids; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ + __u64 netns_dev; + __u64 netns_ino; + __u32 nr_jited_ksyms; + __u32 nr_jited_func_lens; + __aligned_u64 jited_ksyms; + __aligned_u64 jited_func_lens; + __u32 btf_id; + __u32 func_info_rec_size; + __aligned_u64 func_info; + __u32 nr_func_info; + __u32 nr_line_info; + __aligned_u64 line_info; + __aligned_u64 jited_line_info; + __u32 nr_jited_line_info; + __u32 line_info_rec_size; + __u32 jited_line_info_rec_size; + __u32 nr_prog_tags; + __aligned_u64 prog_tags; + __u64 run_time_ns; + __u64 run_cnt; + __u64 recursion_misses; + __u32 verified_insns; + __u32 attach_btf_obj_id; + __u32 attach_btf_id; + __u32 :32; +} __attribute__((aligned(8))); + +struct bpf_map_info { + __u32 type; + __u32 id; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 map_flags; + char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 btf_vmlinux_value_type_id; + __u64 netns_dev; + __u64 netns_ino; + __u32 btf_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; + __u32 btf_vmlinux_id; + __u64 map_extra; + __aligned_u64 hash; + __u32 hash_size; + __u32 :32; +} __attribute__((aligned(8))); + +struct bpf_btf_info { + __aligned_u64 btf; + __u32 btf_size; + __u32 id; + __aligned_u64 name; + __u32 name_len; + __u32 kernel_btf; +} __attribute__((aligned(8))); + +struct bpf_link_info { + __u32 type; + __u32 id; + __u32 prog_id; + union { + struct { + __aligned_u64 tp_name; /* in/out: tp_name buffer ptr */ + __u32 tp_name_len; /* in/out: tp_name buffer len */ + __u32 :32; + __u64 cookie; + } raw_tracepoint; + struct { + __u32 attach_type; + __u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */ + __u32 target_btf_id; /* BTF type id inside the object */ + __u32 :32; + __u64 cookie; + } tracing; + struct { + __u64 cgroup_id; + __u32 attach_type; + } cgroup; + struct { + __aligned_u64 target_name; /* in/out: target_name buffer ptr */ + __u32 target_name_len; /* in/out: target_name buffer len */ + + /* If the iter specific field is 32 bits, it can be put + * in the first or second union. Otherwise it should be + * put in the second union. + */ + union { + struct { + __u32 map_id; + } map; + }; + union { + struct { + __u64 cgroup_id; + __u32 order; + } cgroup; + struct { + __u32 tid; + __u32 pid; + } task; + }; + } iter; + struct { + __u32 netns_ino; + __u32 attach_type; + } netns; + struct { + __u32 ifindex; + } xdp; + struct { + __u32 map_id; + } struct_ops; + struct { + __u32 pf; + __u32 hooknum; + __s32 priority; + __u32 flags; + } netfilter; + struct { + __aligned_u64 addrs; + __u32 count; /* in/out: kprobe_multi function count */ + __u32 flags; + __u64 missed; + __aligned_u64 cookies; + } kprobe_multi; + struct { + __aligned_u64 path; + __aligned_u64 offsets; + __aligned_u64 ref_ctr_offsets; + __aligned_u64 cookies; + __u32 path_size; /* in/out: real path size on success, including zero byte */ + __u32 count; /* in/out: uprobe_multi offsets/ref_ctr_offsets/cookies count */ + __u32 flags; + __u32 pid; + } uprobe_multi; + struct { + __u32 attach_type; + __u32 count; /* in/out: tracing_multi target count */ + __u32 btf_obj_id; + __u32 :32; + __aligned_u64 ids; + __aligned_u64 addrs; + __aligned_u64 cookies; + } tracing_multi; + struct { + __u32 type; /* enum bpf_perf_event_type */ + __u32 :32; + union { + struct { + __aligned_u64 file_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from file_name */ + __u64 cookie; + __u64 ref_ctr_offset; + } uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */ + struct { + __aligned_u64 func_name; /* in/out */ + __u32 name_len; + __u32 offset; /* offset from func_name */ + __u64 addr; + __u64 missed; + __u64 cookie; + } kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */ + struct { + __aligned_u64 tp_name; /* in/out */ + __u32 name_len; + __u32 :32; + __u64 cookie; + } tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */ + struct { + __u64 config; + __u32 type; + __u32 :32; + __u64 cookie; + } event; /* BPF_PERF_EVENT_EVENT */ + }; + } perf_event; + struct { + __u32 ifindex; + __u32 attach_type; + } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; + struct { + __u32 map_id; + __u32 attach_type; + } sockmap; + }; +} __attribute__((aligned(8))); + +struct bpf_token_info { + __u64 allowed_cmds; + __u64 allowed_maps; + __u64 allowed_progs; + __u64 allowed_attachs; +} __attribute__((aligned(8))); + +/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed + * by user and intended to be used by socket (e.g. to bind to, depends on + * attach type). + */ +struct bpf_sock_addr { + __u32 user_family; /* Allows 4-byte read, but no write. */ + __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. + * Stored in network byte order. + */ + __u32 user_port; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order + */ + __u32 family; /* Allows 4-byte read, but no write */ + __u32 type; /* Allows 4-byte read, but no write */ + __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. + * Stored in network byte order. + */ + __bpf_md_ptr(struct bpf_sock *, sk); +}; + +/* User bpf_sock_ops struct to access socket values and specify request ops + * and their replies. + * Some of this fields are in network (bigendian) byte order and may need + * to be converted before use (bpf_ntohl() defined in samples/bpf/bpf_endian.h). + * New fields can only be added at the end of this structure + */ +struct bpf_sock_ops { + __u32 op; + union { + __u32 args[4]; /* Optionally passed to bpf program */ + __u32 reply; /* Returned by bpf program */ + __u32 replylong[4]; /* Optionally returned by bpf prog */ + }; + __u32 family; + __u32 remote_ip4; /* Stored in network byte order */ + __u32 local_ip4; /* Stored in network byte order */ + __u32 remote_ip6[4]; /* Stored in network byte order */ + __u32 local_ip6[4]; /* Stored in network byte order */ + __u32 remote_port; /* Stored in network byte order */ + __u32 local_port; /* stored in host byte order */ + __u32 is_fullsock; /* Some TCP fields are only valid if + * there is a full socket. If not, the + * fields read as zero. + */ + __u32 snd_cwnd; + __u32 srtt_us; /* Averaged RTT << 3 in usecs */ + __u32 bpf_sock_ops_cb_flags; /* flags defined in uapi/linux/tcp.h */ + __u32 state; + __u32 rtt_min; + __u32 snd_ssthresh; + __u32 rcv_nxt; + __u32 snd_nxt; + __u32 snd_una; + __u32 mss_cache; + __u32 ecn_flags; + __u32 rate_delivered; + __u32 rate_interval_us; + __u32 packets_out; + __u32 retrans_out; + __u32 total_retrans; + __u32 segs_in; + __u32 data_segs_in; + __u32 segs_out; + __u32 data_segs_out; + __u32 lost_out; + __u32 sacked_out; + __u32 sk_txhash; + __u64 bytes_received; + __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); + /* [skb_data, skb_data_end) covers the whole TCP header. + * + * BPF_SOCK_OPS_PARSE_HDR_OPT_CB: The packet received + * BPF_SOCK_OPS_HDR_OPT_LEN_CB: Not useful because the + * header has not been written. + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB: The header and options have + * been written so far. + * BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: The SYNACK that concludes + * the 3WHS. + * BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: The ACK that concludes + * the 3WHS. + * + * bpf_load_hdr_opt() can also be used to read a particular option. + */ + __bpf_md_ptr(void *, skb_data); + __bpf_md_ptr(void *, skb_data_end); + __u32 skb_len; /* The total length of a packet. + * It includes the header, options, + * and payload. + */ + __u32 skb_tcp_flags; /* tcp_flags of the header. It provides + * an easy way to check for tcp_flags + * without parsing skb_data. + * + * In particular, the skb_tcp_flags + * will still be available in + * BPF_SOCK_OPS_HDR_OPT_LEN even though + * the outgoing header has not + * been written yet. + */ + __u64 skb_hwtstamp; +}; + +/* Definitions for bpf_sock_ops_cb_flags */ +enum { + BPF_SOCK_OPS_RTO_CB_FLAG = (1<<0), + BPF_SOCK_OPS_RETRANS_CB_FLAG = (1<<1), + BPF_SOCK_OPS_STATE_CB_FLAG = (1<<2), + BPF_SOCK_OPS_RTT_CB_FLAG = (1<<3), + /* Call bpf for all received TCP headers. The bpf prog will be + * called under sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + * + * It could be used at the client/active side (i.e. connect() side) + * when the server told it that the server was in syncookie + * mode and required the active side to resend the bpf-written + * options. The active side can keep writing the bpf-options until + * it received a valid packet from the server side to confirm + * the earlier packet (and options) has been received. The later + * example patch is using it like this at the active side when the + * server is in syncookie mode. + * + * The bpf prog will usually turn this off in the common cases. + */ + BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG = (1<<4), + /* Call bpf when kernel has received a header option that + * the kernel cannot handle. The bpf prog will be called under + * sock_ops->op == BPF_SOCK_OPS_PARSE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_PARSE_HDR_OPT_CB + * for the header option related helpers that will be useful + * to the bpf programs. + */ + BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG = (1<<5), + /* Call bpf when the kernel is writing header options for the + * outgoing packet. The bpf prog will first be called + * to reserve space in a skb under + * sock_ops->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB. Then + * the bpf prog will be called to write the header option(s) + * under sock_ops->op == BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * + * Please refer to the comment in BPF_SOCK_OPS_HDR_OPT_LEN_CB + * and BPF_SOCK_OPS_WRITE_HDR_OPT_CB for the header option + * related helpers that will be useful to the bpf programs. + * + * The kernel gets its chance to reserve space and write + * options first before the BPF program does. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG = (1<<6), +/* Mask of all currently supported cb flags */ + BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, +}; + +enum { + SK_BPF_CB_TX_TIMESTAMPING = 1<<0, + SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING - 1) | + SK_BPF_CB_TX_TIMESTAMPING +}; + +/* List of known BPF sock_ops operators. + * New entries can only be added at the end + */ +enum { + BPF_SOCK_OPS_VOID, + BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or + * -1 if default value should be used + */ + BPF_SOCK_OPS_RWND_INIT, /* Should return initial advertized + * window (in packets) or -1 if default + * value should be used + */ + BPF_SOCK_OPS_TCP_CONNECT_CB, /* Calls BPF program right before an + * active connection is initialized + */ + BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, /* Calls BPF program when an + * active connection is + * established + */ + BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, /* Calls BPF program when a + * passive connection is + * established + */ + BPF_SOCK_OPS_NEEDS_ECN, /* If connection's congestion control + * needs ECN + */ + BPF_SOCK_OPS_BASE_RTT, /* Get base RTT. The correct value is + * based on the path and may be + * dependent on the congestion control + * algorithm. In general it indicates + * a congestion threshold. RTTs above + * this indicate congestion + */ + BPF_SOCK_OPS_RTO_CB, /* Called when an RTO has triggered. + * Arg1: value of icsk_retransmits + * Arg2: value of icsk_rto + * Arg3: whether RTO has expired + */ + BPF_SOCK_OPS_RETRANS_CB, /* Called when skb is retransmitted. + * Arg1: sequence number of 1st byte + * Arg2: # segments + * Arg3: return value of + * tcp_transmit_skb (0 => success) + */ + BPF_SOCK_OPS_STATE_CB, /* Called when TCP changes state. + * Arg1: old_state + * Arg2: new_state + */ + BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after + * socket transition to LISTEN state. + */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + * Arg1: measured RTT input (mrtt) + * Arg2: updated srtt + */ + BPF_SOCK_OPS_PARSE_HDR_OPT_CB, /* Parse the header option. + * It will be called to handle + * the packets received at + * an already established + * connection. + * + * sock_ops->skb_data: + * Referring to the received skb. + * It covers the TCP header only. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option. + */ + BPF_SOCK_OPS_HDR_OPT_LEN_CB, /* Reserve space for writing the + * header option later in + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Not available because no header has + * been written yet. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the + * outgoing skb. (e.g. SYN, ACK, FIN). + * + * bpf_reserve_hdr_opt() should + * be used to reserve space. + */ + BPF_SOCK_OPS_WRITE_HDR_OPT_CB, /* Write the header options + * Arg1: bool want_cookie. (in + * writing SYNACK only) + * + * sock_ops->skb_data: + * Referring to the outgoing skb. + * It covers the TCP header + * that has already been written + * by the kernel and the + * earlier bpf-progs. + * + * sock_ops->skb_tcp_flags: + * The tcp_flags of the outgoing + * skb. (e.g. SYN, ACK, FIN). + * + * bpf_store_hdr_opt() should + * be used to write the + * option. + * + * bpf_load_hdr_opt() can also + * be used to search for a + * particular option that + * has already been written + * by the kernel or the + * earlier bpf-progs. + */ + BPF_SOCK_OPS_TSTAMP_SCHED_CB, /* Called when skb is passing + * through dev layer when + * SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_SW_CB, /* Called when skb is about to send + * to the nic when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SND_HW_CB, /* Called in hardware phase when + * SK_BPF_CB_TX_TIMESTAMPING feature + * is on. + */ + BPF_SOCK_OPS_TSTAMP_ACK_CB, /* Called when all the skbs in the + * same sendmsg call are acked + * when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ + BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall + * is triggered. It's used to correlate + * sendmsg timestamp with corresponding + * tskey. + */ +}; + +/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect + * changes between the TCP and BPF versions. Ideally this should never happen. + * If it does, we need to add code to convert them before calling + * the BPF sock_ops function. + */ +enum { + BPF_TCP_ESTABLISHED = 1, + BPF_TCP_SYN_SENT, + BPF_TCP_SYN_RECV, + BPF_TCP_FIN_WAIT1, + BPF_TCP_FIN_WAIT2, + BPF_TCP_TIME_WAIT, + BPF_TCP_CLOSE, + BPF_TCP_CLOSE_WAIT, + BPF_TCP_LAST_ACK, + BPF_TCP_LISTEN, + BPF_TCP_CLOSING, /* Now a valid state */ + BPF_TCP_NEW_SYN_RECV, + BPF_TCP_BOUND_INACTIVE, + + BPF_TCP_MAX_STATES /* Leave at the end! */ +}; + +enum { + TCP_BPF_IW = 1001, /* Set TCP initial congestion window */ + TCP_BPF_SNDCWND_CLAMP = 1002, /* Set sndcwnd_clamp */ + TCP_BPF_DELACK_MAX = 1003, /* Max delay ack in usecs */ + TCP_BPF_RTO_MIN = 1004, /* Min delay ack in usecs */ + /* Copy the SYN pkt to optval + * + * BPF_PROG_TYPE_SOCK_OPS only. It is similar to the + * bpf_getsockopt(TCP_SAVED_SYN) but it does not limit + * to only getting from the saved_syn. It can either get the + * syn packet from: + * + * 1. the just-received SYN packet (only available when writing the + * SYNACK). It will be useful when it is not necessary to + * save the SYN packet for latter use. It is also the only way + * to get the SYN during syncookie mode because the syn + * packet cannot be saved during syncookie. + * + * OR + * + * 2. the earlier saved syn which was done by + * bpf_setsockopt(TCP_SAVE_SYN). + * + * The bpf_getsockopt(TCP_BPF_SYN*) option will hide where the + * SYN packet is obtained. + * + * If the bpf-prog does not need the IP[46] header, the + * bpf-prog can avoid parsing the IP header by using + * TCP_BPF_SYN. Otherwise, the bpf-prog can get both + * IP[46] and TCP header by using TCP_BPF_SYN_IP. + * + * >0: Total number of bytes copied + * -ENOSPC: Not enough space in optval. Only optlen number of + * bytes is copied. + * -ENOENT: The SYN skb is not available now and the earlier SYN pkt + * is not saved by setsockopt(TCP_SAVE_SYN). + */ + TCP_BPF_SYN = 1005, /* Copy the TCP header */ + TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ + TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ + TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ + +}; + +enum { + BPF_LOAD_HDR_OPT_TCP_SYN = (1ULL << 0), +}; + +/* args[0] value during BPF_SOCK_OPS_HDR_OPT_LEN_CB and + * BPF_SOCK_OPS_WRITE_HDR_OPT_CB. + */ +enum { + BPF_WRITE_HDR_TCP_CURRENT_MSS = 1, /* Kernel is finding the + * total option spaces + * required for an established + * sk in order to calculate the + * MSS. No skb is actually + * sent. + */ + BPF_WRITE_HDR_TCP_SYNACK_COOKIE = 2, /* Kernel is in syncookie mode + * when sending a SYN. + */ +}; + +struct bpf_perf_event_value { + __u64 counter; + __u64 enabled; + __u64 running; +}; + +enum { + BPF_DEVCG_ACC_MKNOD = (1ULL << 0), + BPF_DEVCG_ACC_READ = (1ULL << 1), + BPF_DEVCG_ACC_WRITE = (1ULL << 2), +}; + +enum { + BPF_DEVCG_DEV_BLOCK = (1ULL << 0), + BPF_DEVCG_DEV_CHAR = (1ULL << 1), +}; + +struct bpf_cgroup_dev_ctx { + /* access_type encoded as (BPF_DEVCG_ACC_* << 16) | BPF_DEVCG_DEV_* */ + __u32 access_type; + __u32 major; + __u32 minor; +}; + +struct bpf_raw_tracepoint_args { + __u64 args[0]; +}; + +/* DIRECT: Skip the FIB rules and go to FIB table associated with device + * OUTPUT: Do lookup from egress perspective; default is ingress + */ +enum { + BPF_FIB_LOOKUP_DIRECT = (1U << 0), + BPF_FIB_LOOKUP_OUTPUT = (1U << 1), + BPF_FIB_LOOKUP_SKIP_NEIGH = (1U << 2), + BPF_FIB_LOOKUP_TBID = (1U << 3), + BPF_FIB_LOOKUP_SRC = (1U << 4), + BPF_FIB_LOOKUP_MARK = (1U << 5), + BPF_FIB_LOOKUP_VLAN = (1U << 6), + BPF_FIB_LOOKUP_VLAN_INPUT = (1U << 7), +}; + +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_FIB_LKUP_RET_NO_SRC_ADDR, /* failed to derive IP src addr */ + BPF_FIB_LKUP_RET_VLAN_FAILURE, /* VLAN egress, parent unresolvable */ +}; + +struct bpf_fib_lookup { + /* input: network family for lookup (AF_INET, AF_INET6) + * output: network family of egress nexthop + */ + __u8 family; + + /* set if lookup is to consider L4 data - e.g., FIB rules */ + __u8 l4_protocol; + __be16 sport; + __be16 dport; + + union { /* used for MTU check */ + /* input to lookup */ + __u16 tot_len; /* L3 length from network hdr (iph->tot_len) */ + + /* output: MTU value */ + __u16 mtu_result; + } __attribute__((packed, aligned(2))); + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; + + union { + /* inputs to lookup */ + __u8 tos; /* AF_INET */ + __be32 flowinfo; /* AF_INET6, flow_label + priority */ + + /* output: metric of fib result (IPv4/IPv6 only) */ + __u32 rt_metric; + }; + + /* input: source address to consider for lookup + * output: source address result from lookup + */ + union { + __be32 ipv4_src; + __u32 ipv6_src[4]; /* in6_addr; network order */ + }; + + /* input to bpf_fib_lookup, ipv{4,6}_dst is destination address in + * network header. output: bpf_fib_lookup sets to gateway address + * if FIB lookup returns gateway route + */ + union { + __be32 ipv4_dst; + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + + union { + struct { + /* + * output with BPF_FIB_LOOKUP_VLAN: set from the + * resolved egress VLAN device (see the flag); zeroed + * on other successful lookups. input with + * BPF_FIB_LOOKUP_VLAN_INPUT: the VLAN tag to scope + * the lookup by. + */ + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + }; + /* input: when accompanied with the + * 'BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_TBID` flags, a + * specific routing table to use for the fib lookup. + */ + __u32 tbid; + }; + + union { + /* input */ + struct { + __u32 mark; /* policy routing */ + /* 2 4-byte holes for input */ + }; + + /* output: source and dest mac */ + struct { + __u8 smac[6]; /* ETH_ALEN */ + __u8 dmac[6]; /* ETH_ALEN */ + }; + }; +}; + +struct bpf_redir_neigh { + /* network family for lookup (AF_INET, AF_INET6) */ + __u32 nh_family; + /* network address of nexthop; skips fib lookup to find gateway */ + union { + __be32 ipv4_nh; + __u32 ipv6_nh[4]; /* in6_addr; network order */ + }; +}; + +/* bpf_check_mtu flags*/ +enum bpf_check_mtu_flags { + BPF_MTU_CHK_SEGS = (1U << 0), +}; + +enum bpf_check_mtu_ret { + BPF_MTU_CHK_RET_SUCCESS, /* check and lookup successful */ + BPF_MTU_CHK_RET_FRAG_NEEDED, /* fragmentation required to fwd */ + BPF_MTU_CHK_RET_SEGS_TOOBIG, /* GSO re-segmentation needed to fwd */ +}; + +enum bpf_task_fd_type { + BPF_FD_TYPE_RAW_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_TRACEPOINT, /* tp name */ + BPF_FD_TYPE_KPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_KRETPROBE, /* (symbol + offset) or addr */ + BPF_FD_TYPE_UPROBE, /* filename + offset */ + BPF_FD_TYPE_URETPROBE, /* filename + offset */ +}; + +enum { + BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG = (1U << 0), + BPF_FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL = (1U << 1), + BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP = (1U << 2), +}; + +struct bpf_flow_keys { + __u16 nhoff; + __u16 thoff; + __u16 addr_proto; /* ETH_P_* of valid addrs */ + __u8 is_frag; + __u8 is_first_frag; + __u8 is_encap; + __u8 ip_proto; + __be16 n_proto; + __be16 sport; + __be16 dport; + union { + struct { + __be32 ipv4_src; + __be32 ipv4_dst; + }; + struct { + __u32 ipv6_src[4]; /* in6_addr; network order */ + __u32 ipv6_dst[4]; /* in6_addr; network order */ + }; + }; + __u32 flags; + __be32 flow_label; +}; + +struct bpf_func_info { + __u32 insn_off; + __u32 type_id; +}; + +#define BPF_LINE_INFO_LINE_NUM(line_col) ((line_col) >> 10) +#define BPF_LINE_INFO_LINE_COL(line_col) ((line_col) & 0x3ff) + +struct bpf_line_info { + __u32 insn_off; + __u32 file_name_off; + __u32 line_off; + __u32 line_col; +}; + +struct bpf_spin_lock { + __u32 val; +}; + +struct bpf_timer { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_task_work { + __u64 __opaque; +} __attribute__((aligned(8))); + +struct bpf_wq { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_dynptr { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_list_head { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_rb_root { + __u64 __opaque[2]; +} __attribute__((aligned(8))); + +struct bpf_rb_node { + __u64 __opaque[4]; +} __attribute__((aligned(8))); + +struct bpf_refcount { + __u32 __opaque[1]; +} __attribute__((aligned(4))); + +struct bpf_sysctl { + __u32 write; /* Sysctl is being read (= 0) or written (= 1). + * Allows 1,2,4-byte read, but no write. + */ + __u32 file_pos; /* Sysctl file position to read from, write to. + * Allows 1,2,4-byte read an 4-byte write. + */ +}; + +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + +struct bpf_pidns_info { + __u32 pid; + __u32 tgid; +}; + +/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */ +struct bpf_sk_lookup { + union { + __bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */ + __u64 cookie; /* Non-zero if socket was selected in PROG_TEST_RUN */ + }; + + __u32 family; /* Protocol family (AF_INET, AF_INET6) */ + __u32 protocol; /* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */ + __u32 remote_ip4; /* Network byte order */ + __u32 remote_ip6[4]; /* Network byte order */ + __be16 remote_port; /* Network byte order */ + __u16 :16; /* Zero padding */ + __u32 local_ip4; /* Network byte order */ + __u32 local_ip6[4]; /* Network byte order */ + __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ +}; + +/* + * struct btf_ptr is used for typed pointer representation; the + * type id is used to render the pointer data as the appropriate type + * via the bpf_snprintf_btf() helper described above. A flags field - + * potentially to specify additional details about the BTF pointer + * (rather than its mode of display) - is included for future use. + * Display flags - BTF_F_* - are passed to bpf_snprintf_btf separately. + */ +struct btf_ptr { + void *ptr; + __u32 type_id; + __u32 flags; /* BTF ptr flags; unused at present. */ +}; + +/* + * Flags to control bpf_snprintf_btf() behaviour. + * - BTF_F_COMPACT: no formatting around type information + * - BTF_F_NONAME: no struct/union member names/types + * - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values; + * equivalent to %px. + * - BTF_F_ZERO: show zero-valued struct/union members; they + * are not displayed by default + */ +enum { + BTF_F_COMPACT = (1ULL << 0), + BTF_F_NONAME = (1ULL << 1), + BTF_F_PTR_RAW = (1ULL << 2), + BTF_F_ZERO = (1ULL << 3), +}; + +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ + BPF_CORE_TYPE_MATCHES = 12, /* type match in target kernel */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + +/* + * Flags to control bpf_timer_start() behaviour. + * - BPF_F_TIMER_ABS: Timeout passed is absolute time, by default it is + * relative to current time. + * - BPF_F_TIMER_CPU_PIN: Timer will be pinned to the CPU of the caller. + */ +enum { + BPF_F_TIMER_ABS = (1ULL << 0), + BPF_F_TIMER_CPU_PIN = (1ULL << 1), +}; + +/* BPF numbers iterator state */ +struct bpf_iter_num { + /* opaque iterator state; having __u64 here allows to preserve correct + * alignment requirements in vmlinux.h, generated from BTF + */ + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +/* + * Flags to control BPF kfunc behaviour. + * - BPF_F_PAD_ZEROS: Pad destination buffer with zeros. (See the respective + * helper documentation for details.) + */ +enum bpf_kfunc_flags { + BPF_F_PAD_ZEROS = (1ULL << 0), +}; + +/* + * Values of a BPF_MAP_TYPE_INSN_ARRAY entry must be of this type. + * + * Before the map is used the orig_off field should point to an + * instruction inside the program being loaded. The other fields + * must be set to 0. + * + * After the program is loaded, the xlated_off will be adjusted + * by the verifier to point to the index of the original instruction + * in the xlated program. If the instruction is deleted, it will + * be set to (u32)-1. The jitted_off will be set to the corresponding + * offset in the jitted image of the program. + */ +struct bpf_insn_array_value { + __u32 orig_off; + __u32 xlated_off; + __u32 jitted_off; + __u32 :32; +}; + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h new file mode 100644 index 000000000..ee97668bd --- /dev/null +++ b/tools/include/uapi/linux/bpf_common.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_BPF_COMMON_H__ +#define _UAPI__LINUX_BPF_COMMON_H__ + +/* Instruction classes */ +#define BPF_CLASS(code) ((code) & 0x07) +#define BPF_LD 0x00 +#define BPF_LDX 0x01 +#define BPF_ST 0x02 +#define BPF_STX 0x03 +#define BPF_ALU 0x04 +#define BPF_JMP 0x05 +#define BPF_RET 0x06 +#define BPF_MISC 0x07 + +/* ld/ldx fields */ +#define BPF_SIZE(code) ((code) & 0x18) +#define BPF_W 0x00 /* 32-bit */ +#define BPF_H 0x08 /* 16-bit */ +#define BPF_B 0x10 /* 8-bit */ +/* eBPF BPF_DW 0x18 64-bit */ +#define BPF_MODE(code) ((code) & 0xe0) +#define BPF_IMM 0x00 +#define BPF_ABS 0x20 +#define BPF_IND 0x40 +#define BPF_MEM 0x60 +#define BPF_LEN 0x80 +#define BPF_MSH 0xa0 + +/* alu/jmp fields */ +#define BPF_OP(code) ((code) & 0xf0) +#define BPF_ADD 0x00 +#define BPF_SUB 0x10 +#define BPF_MUL 0x20 +#define BPF_DIV 0x30 +#define BPF_OR 0x40 +#define BPF_AND 0x50 +#define BPF_LSH 0x60 +#define BPF_RSH 0x70 +#define BPF_NEG 0x80 +#define BPF_MOD 0x90 +#define BPF_XOR 0xa0 + +#define BPF_JA 0x00 +#define BPF_JEQ 0x10 +#define BPF_JGT 0x20 +#define BPF_JGE 0x30 +#define BPF_JSET 0x40 +#define BPF_SRC(code) ((code) & 0x08) +#define BPF_K 0x00 +#define BPF_X 0x08 + +#ifndef BPF_MAXINSNS +#define BPF_MAXINSNS 4096 +#endif + +#endif /* _UAPI__LINUX_BPF_COMMON_H__ */ diff --git a/tools/include/uapi/linux/bpf_perf_event.h b/tools/include/uapi/linux/bpf_perf_event.h new file mode 100644 index 000000000..eb1b9d212 --- /dev/null +++ b/tools/include/uapi/linux/bpf_perf_event.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_PERF_EVENT_H__ +#define _UAPI__LINUX_BPF_PERF_EVENT_H__ + +#include + +struct bpf_perf_event_data { + bpf_user_pt_regs_t regs; + __u64 sample_period; + __u64 addr; +}; + +#endif /* _UAPI__LINUX_BPF_PERF_EVENT_H__ */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h new file mode 100644 index 000000000..618167cab --- /dev/null +++ b/tools/include/uapi/linux/btf.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +/* + * BTF layout section consists of a struct btf_layout for each known + * kind at BTF encoding time. + */ +struct btf_layout { + __u8 info_sz; /* size of singular element after btf_type */ + __u8 elem_sz; /* size of each of btf_vlen(t) elements */ + __u16 flags; /* currently unused */ +}; + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ + __u32 layout_off; /* offset of layout section */ + __u32 layout_len; /* length of layout section */ +}; + +enum btf_max { + /* Max possible kind */ + BTF_MAX_KIND = 0x0000007f, + /* Max # of type identifier */ + BTF_MAX_TYPE = 0x000fffff, + /* Max offset into the string section */ + BTF_MAX_NAME_OFFSET = 0x00ffffff, + /* Max # of struct/union/enum members or func args */ + BTF_MAX_VLEN = 0x00ffffff, +}; + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-23: vlen (e.g. # of struct's members) + * bits 24-30: kind (e.g. int, ptr, array...etc) + * bit 31: kind_flag, currently used by + * struct, union, enum, fwd, enum64, + * decl_tag and type_tag + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT, UNION, DATASEC and ENUM64. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x7f) +#define BTF_INFO_VLEN(info) ((info) & 0xffffff) +#define BTF_INFO_KFLAG(info) ((info) >> 31) + +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration up to 32-bit values */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL) & 0x00ff0000) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED (1 << 0) +#define BTF_INT_CHAR (1 << 1) +#define BTF_INT_BOOL (1 << 2) + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + /* If the type info kind_flag is set, the btf_member offset + * contains both member bitfield size and bit offset. The + * bitfield size is set for bitfield members. If the type + * info kind_flag is not set, the offset contains only bit + * offset. + */ + __u32 offset; +}; + +/* If the struct/union type info kind_flag is set, the + * following two macros are used to access bitfield_size + * and bit_offset from btf_member.offset. + */ +#define BTF_MEMBER_BITFIELD_SIZE(val) ((val) >> 24) +#define BTF_MEMBER_BIT_OFFSET(val) ((val) & 0xffffff) + +/* BTF_KIND_FUNC_PROTO is followed by multiple "struct btf_param". + * The exact number of btf_param is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_param { + __u32 name_off; + __u32 type; +}; + +enum { + BTF_VAR_STATIC = 0, + BTF_VAR_GLOBAL_ALLOCATED = 1, + BTF_VAR_GLOBAL_EXTERN = 2, +}; + +enum btf_func_linkage { + BTF_FUNC_STATIC = 0, + BTF_FUNC_GLOBAL = 1, + BTF_FUNC_EXTERN = 2, +}; + +/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe + * additional information related to the variable such as its linkage. + */ +struct btf_var { + __u32 linkage; +}; + +/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo" + * to describe all BTF_KIND_VAR types it contains along with it's + * in-section offset as well as size. + */ +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_decl_tag { + __s32 component_idx; +}; + +/* BTF_KIND_ENUM64 is followed by multiple "struct btf_enum64". + * The exact number of btf_enum64 is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/const.h b/tools/include/uapi/linux/const.h new file mode 100644 index 000000000..565f309b9 --- /dev/null +++ b/tools/include/uapi/linux/const.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* const.h: Macros for dealing with constants. */ + +#ifndef _UAPI_LINUX_CONST_H +#define _UAPI_LINUX_CONST_H + +/* Some constant macros are used in both assembler and + * C code. Therefore we cannot annotate them always with + * 'UL' and other type specifiers unilaterally. We + * use the following macros to deal with this. + * + * Similarly, _AT() will cast an expression with a type in C, but + * leave it unchanged in asm. + */ + +#ifdef __ASSEMBLY__ +#define _AC(X,Y) X +#define _AT(T,X) X +#else +#define __AC(X,Y) (X##Y) +#define _AC(X,Y) __AC(X,Y) +#define _AT(T,X) ((T)(X)) +#endif + +#define _UL(x) (_AC(x, UL)) +#define _ULL(x) (_AC(x, ULL)) + +#define _BITUL(x) (_UL(1) << (x)) +#define _BITULL(x) (_ULL(1) << (x)) + +#if !defined(__ASSEMBLY__) +/* + * Missing asm support + * + * __BIT128() would not work in the asm code, as it shifts an + * 'unsigned __int128' data type as direct representation of + * 128 bit constants is not supported in the gcc compiler, as + * they get silently truncated. + * + * TODO: Please revisit this implementation when gcc compiler + * starts representing 128 bit constants directly like long + * and unsigned long etc. Subsequently drop the comment for + * GENMASK_U128() which would then start supporting asm code. + */ +#define _BIT128(x) ((unsigned __int128)(1) << (x)) +#endif + +#define __ALIGN_KERNEL(x, a) __ALIGN_KERNEL_MASK(x, (__typeof__(x))(a) - 1) +#define __ALIGN_KERNEL_MASK(x, mask) (((x) + (mask)) & ~(mask)) + +#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) + +/* + * Divide positive or negative dividend by positive or negative divisor + * and round to closest integer. Result is undefined for negative + * divisors if the dividend variable type is unsigned and for negative + * dividends if the divisor variable type is unsigned. + */ +#define __KERNEL_DIV_ROUND_CLOSEST(x, divisor) \ +({ \ + __typeof__(x) __x = x; \ + __typeof__(divisor) __d = divisor; \ + \ + (((__typeof__(x))-1) > 0 || \ + ((__typeof__(divisor))-1) > 0 || \ + (((__x) > 0) == ((__d) > 0))) ? \ + (((__x) + ((__d) / 2)) / (__d)) : \ + (((__x) - ((__d) / 2)) / (__d)); \ +}) + +#endif /* _UAPI_LINUX_CONST_H */ diff --git a/tools/include/uapi/linux/coredump.h b/tools/include/uapi/linux/coredump.h new file mode 100644 index 000000000..dc3789b78 --- /dev/null +++ b/tools/include/uapi/linux/coredump.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_COREDUMP_H +#define _UAPI_LINUX_COREDUMP_H + +#include + +/** + * coredump_{req,ack} flags + * @COREDUMP_KERNEL: kernel writes coredump + * @COREDUMP_USERSPACE: userspace writes coredump + * @COREDUMP_REJECT: don't generate coredump + * @COREDUMP_WAIT: wait for coredump server + */ +enum { + COREDUMP_KERNEL = (1ULL << 0), + COREDUMP_USERSPACE = (1ULL << 1), + COREDUMP_REJECT = (1ULL << 2), + COREDUMP_WAIT = (1ULL << 3), +}; + +/** + * struct coredump_req - message kernel sends to userspace + * @size: size of struct coredump_req + * @size_ack: known size of struct coredump_ack on this kernel + * @mask: supported features + * + * When a coredump happens the kernel will connect to the coredump + * socket and send a coredump request to the coredump server. The @size + * member is set to the size of struct coredump_req and provides a hint + * to userspace how much data can be read. Userspace may use MSG_PEEK to + * peek the size of struct coredump_req and then choose to consume it in + * one go. Userspace may also simply read a COREDUMP_ACK_SIZE_VER0 + * request. If the size the kernel sends is larger userspace simply + * discards any remaining data. + * + * The coredump_req->mask member is set to the currently know features. + * Userspace may only set coredump_ack->mask to the bits raised by the + * kernel in coredump_req->mask. + * + * The coredump_req->size_ack member is set by the kernel to the size of + * struct coredump_ack the kernel knows. Userspace may only send up to + * coredump_req->size_ack bytes to the kernel and must set + * coredump_ack->size accordingly. + */ +struct coredump_req { + __u32 size; + __u32 size_ack; + __u64 mask; +}; + +enum { + COREDUMP_REQ_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * struct coredump_ack - message userspace sends to kernel + * @size: size of the struct + * @spare: unused + * @mask: features kernel is supposed to use + * + * The @size member must be set to the size of struct coredump_ack. It + * may never exceed what the kernel returned in coredump_req->size_ack + * but it may of course be smaller (>= COREDUMP_ACK_SIZE_VER0 and <= + * coredump_req->size_ack). + * + * The @mask member must be set to the features the coredump server + * wants the kernel to use. Only bits the kernel returned in + * coredump_req->mask may be set. + */ +struct coredump_ack { + __u32 size; + __u32 spare; + __u64 mask; +}; + +enum { + COREDUMP_ACK_SIZE_VER0 = 16U, /* size of first published struct */ +}; + +/** + * enum coredump_mark - Markers for the coredump socket + * + * The kernel will place a single byte on the coredump socket. The + * markers notify userspace whether the coredump ack succeeded or + * failed. + * + * @COREDUMP_MARK_MINSIZE: the provided coredump_ack size was too small + * @COREDUMP_MARK_MAXSIZE: the provided coredump_ack size was too big + * @COREDUMP_MARK_UNSUPPORTED: the provided coredump_ack mask was invalid + * @COREDUMP_MARK_CONFLICTING: the provided coredump_ack mask has conflicting options + * @COREDUMP_MARK_REQACK: the coredump request and ack was successful + * @__COREDUMP_MARK_MAX: the maximum coredump mark value + */ +enum coredump_mark { + COREDUMP_MARK_REQACK = 0U, + COREDUMP_MARK_MINSIZE = 1U, + COREDUMP_MARK_MAXSIZE = 2U, + COREDUMP_MARK_UNSUPPORTED = 3U, + COREDUMP_MARK_CONFLICTING = 4U, + __COREDUMP_MARK_MAX = (1U << 31), +}; + +#endif /* _UAPI_LINUX_COREDUMP_H */ diff --git a/tools/include/uapi/linux/elf.h b/tools/include/uapi/linux/elf.h new file mode 100644 index 000000000..5834b83d7 --- /dev/null +++ b/tools/include/uapi/linux/elf.h @@ -0,0 +1,524 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_ELF_H +#define _LINUX_ELF_H + +#include +#include + +/* 32-bit ELF base types. */ +typedef __u32 Elf32_Addr; +typedef __u16 Elf32_Half; +typedef __u32 Elf32_Off; +typedef __s32 Elf32_Sword; +typedef __u32 Elf32_Word; +typedef __u16 Elf32_Versym; + +/* 64-bit ELF base types. */ +typedef __u64 Elf64_Addr; +typedef __u16 Elf64_Half; +typedef __s16 Elf64_SHalf; +typedef __u64 Elf64_Off; +typedef __s32 Elf64_Sword; +typedef __u32 Elf64_Word; +typedef __u64 Elf64_Xword; +typedef __s64 Elf64_Sxword; +typedef __u16 Elf64_Versym; + +/* These constants are for the segment types stored in the image headers */ +#define PT_NULL 0 +#define PT_LOAD 1 +#define PT_DYNAMIC 2 +#define PT_INTERP 3 +#define PT_NOTE 4 +#define PT_SHLIB 5 +#define PT_PHDR 6 +#define PT_TLS 7 /* Thread local storage segment */ +#define PT_LOOS 0x60000000 /* OS-specific */ +#define PT_HIOS 0x6fffffff /* OS-specific */ +#define PT_LOPROC 0x70000000 +#define PT_HIPROC 0x7fffffff +#define PT_GNU_EH_FRAME (PT_LOOS + 0x474e550) +#define PT_GNU_STACK (PT_LOOS + 0x474e551) +#define PT_GNU_RELRO (PT_LOOS + 0x474e552) +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + + +/* ARM MTE memory tag segment type */ +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) + +/* + * Extended Numbering + * + * If the real number of program header table entries is larger than + * or equal to PN_XNUM(0xffff), it is set to sh_info field of the + * section header at index 0, and PN_XNUM is set to e_phnum + * field. Otherwise, the section header at index 0 is zero + * initialized, if it exists. + * + * Specifications are available in: + * + * - Oracle: Linker and Libraries. + * Part No: 817–1984–19, August 2011. + * https://docs.oracle.com/cd/E18752_01/pdf/817-1984.pdf + * + * - System V ABI AMD64 Architecture Processor Supplement + * Draft Version 0.99.4, + * January 13, 2010. + * http://www.cs.washington.edu/education/courses/cse351/12wi/supp-docs/abi.pdf + */ +#define PN_XNUM 0xffff + +/* These constants define the different elf file types */ +#define ET_NONE 0 +#define ET_REL 1 +#define ET_EXEC 2 +#define ET_DYN 3 +#define ET_CORE 4 +#define ET_LOPROC 0xff00 +#define ET_HIPROC 0xffff + +/* This is the info that is needed to parse the dynamic section of the file */ +#define DT_NULL 0 +#define DT_NEEDED 1 +#define DT_PLTRELSZ 2 +#define DT_PLTGOT 3 +#define DT_HASH 4 +#define DT_STRTAB 5 +#define DT_SYMTAB 6 +#define DT_RELA 7 +#define DT_RELASZ 8 +#define DT_RELAENT 9 +#define DT_STRSZ 10 +#define DT_SYMENT 11 +#define DT_INIT 12 +#define DT_FINI 13 +#define DT_SONAME 14 +#define DT_RPATH 15 +#define DT_SYMBOLIC 16 +#define DT_REL 17 +#define DT_RELSZ 18 +#define DT_RELENT 19 +#define DT_PLTREL 20 +#define DT_DEBUG 21 +#define DT_TEXTREL 22 +#define DT_JMPREL 23 +#define DT_ENCODING 32 +#define OLD_DT_LOOS 0x60000000 +#define DT_LOOS 0x6000000d +#define DT_HIOS 0x6ffff000 +#define DT_VALRNGLO 0x6ffffd00 +#define DT_VALRNGHI 0x6ffffdff +#define DT_ADDRRNGLO 0x6ffffe00 +#define DT_GNU_HASH 0x6ffffef5 +#define DT_ADDRRNGHI 0x6ffffeff +#define DT_VERSYM 0x6ffffff0 +#define DT_RELACOUNT 0x6ffffff9 +#define DT_RELCOUNT 0x6ffffffa +#define DT_FLAGS_1 0x6ffffffb +#define DT_VERDEF 0x6ffffffc +#define DT_VERDEFNUM 0x6ffffffd +#define DT_VERNEED 0x6ffffffe +#define DT_VERNEEDNUM 0x6fffffff +#define OLD_DT_HIOS 0x6fffffff +#define DT_LOPROC 0x70000000 +#define DT_HIPROC 0x7fffffff + +/* This info is needed when parsing the symbol table */ +#define STB_LOCAL 0 +#define STB_GLOBAL 1 +#define STB_WEAK 2 + +#define STN_UNDEF 0 + +#define STT_NOTYPE 0 +#define STT_OBJECT 1 +#define STT_FUNC 2 +#define STT_SECTION 3 +#define STT_FILE 4 +#define STT_COMMON 5 +#define STT_TLS 6 + +#define VER_FLG_BASE 0x1 +#define VER_FLG_WEAK 0x2 + +#define ELF_ST_BIND(x) ((x) >> 4) +#define ELF_ST_TYPE(x) ((x) & 0xf) +#define ELF32_ST_BIND(x) ELF_ST_BIND(x) +#define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) +#define ELF64_ST_BIND(x) ELF_ST_BIND(x) +#define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) + +typedef struct { + Elf32_Sword d_tag; + union { + Elf32_Sword d_val; + Elf32_Addr d_ptr; + } d_un; +} Elf32_Dyn; + +typedef struct { + Elf64_Sxword d_tag; /* entry tag value */ + union { + Elf64_Xword d_val; + Elf64_Addr d_ptr; + } d_un; +} Elf64_Dyn; + +/* The following are used with relocations */ +#define ELF32_R_SYM(x) ((x) >> 8) +#define ELF32_R_TYPE(x) ((x) & 0xff) + +#define ELF64_R_SYM(i) ((i) >> 32) +#define ELF64_R_TYPE(i) ((i) & 0xffffffff) + +typedef struct elf32_rel { + Elf32_Addr r_offset; + Elf32_Word r_info; +} Elf32_Rel; + +typedef struct elf64_rel { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ +} Elf64_Rel; + +typedef struct elf32_rela { + Elf32_Addr r_offset; + Elf32_Word r_info; + Elf32_Sword r_addend; +} Elf32_Rela; + +typedef struct elf64_rela { + Elf64_Addr r_offset; /* Location at which to apply the action */ + Elf64_Xword r_info; /* index and type of relocation */ + Elf64_Sxword r_addend; /* Constant addend used to compute value */ +} Elf64_Rela; + +typedef struct elf32_sym { + Elf32_Word st_name; + Elf32_Addr st_value; + Elf32_Word st_size; + unsigned char st_info; + unsigned char st_other; + Elf32_Half st_shndx; +} Elf32_Sym; + +typedef struct elf64_sym { + Elf64_Word st_name; /* Symbol name, index in string tbl */ + unsigned char st_info; /* Type and binding attributes */ + unsigned char st_other; /* No defined meaning, 0 */ + Elf64_Half st_shndx; /* Associated section index */ + Elf64_Addr st_value; /* Value of the symbol */ + Elf64_Xword st_size; /* Associated symbol size */ +} Elf64_Sym; + + +#define EI_NIDENT 16 + +typedef struct elf32_hdr { + unsigned char e_ident[EI_NIDENT]; + Elf32_Half e_type; + Elf32_Half e_machine; + Elf32_Word e_version; + Elf32_Addr e_entry; /* Entry point */ + Elf32_Off e_phoff; + Elf32_Off e_shoff; + Elf32_Word e_flags; + Elf32_Half e_ehsize; + Elf32_Half e_phentsize; + Elf32_Half e_phnum; + Elf32_Half e_shentsize; + Elf32_Half e_shnum; + Elf32_Half e_shstrndx; +} Elf32_Ehdr; + +typedef struct elf64_hdr { + unsigned char e_ident[EI_NIDENT]; /* ELF "magic number" */ + Elf64_Half e_type; + Elf64_Half e_machine; + Elf64_Word e_version; + Elf64_Addr e_entry; /* Entry point virtual address */ + Elf64_Off e_phoff; /* Program header table file offset */ + Elf64_Off e_shoff; /* Section header table file offset */ + Elf64_Word e_flags; + Elf64_Half e_ehsize; + Elf64_Half e_phentsize; + Elf64_Half e_phnum; + Elf64_Half e_shentsize; + Elf64_Half e_shnum; + Elf64_Half e_shstrndx; +} Elf64_Ehdr; + +/* These constants define the permissions on sections in the program + header, p_flags. */ +#define PF_R 0x4 +#define PF_W 0x2 +#define PF_X 0x1 + +typedef struct elf32_phdr { + Elf32_Word p_type; + Elf32_Off p_offset; + Elf32_Addr p_vaddr; + Elf32_Addr p_paddr; + Elf32_Word p_filesz; + Elf32_Word p_memsz; + Elf32_Word p_flags; + Elf32_Word p_align; +} Elf32_Phdr; + +typedef struct elf64_phdr { + Elf64_Word p_type; + Elf64_Word p_flags; + Elf64_Off p_offset; /* Segment file offset */ + Elf64_Addr p_vaddr; /* Segment virtual address */ + Elf64_Addr p_paddr; /* Segment physical address */ + Elf64_Xword p_filesz; /* Segment size in file */ + Elf64_Xword p_memsz; /* Segment size in memory */ + Elf64_Xword p_align; /* Segment alignment, file & memory */ +} Elf64_Phdr; + +/* sh_type */ +#define SHT_NULL 0 +#define SHT_PROGBITS 1 +#define SHT_SYMTAB 2 +#define SHT_STRTAB 3 +#define SHT_RELA 4 +#define SHT_HASH 5 +#define SHT_DYNAMIC 6 +#define SHT_NOTE 7 +#define SHT_NOBITS 8 +#define SHT_REL 9 +#define SHT_SHLIB 10 +#define SHT_DYNSYM 11 +#define SHT_NUM 12 +#define SHT_LOPROC 0x70000000 +#define SHT_HIPROC 0x7fffffff +#define SHT_LOUSER 0x80000000 +#define SHT_HIUSER 0xffffffff + +/* sh_flags */ +#define SHF_WRITE 0x1 +#define SHF_ALLOC 0x2 +#define SHF_EXECINSTR 0x4 +#define SHF_RELA_LIVEPATCH 0x00100000 +#define SHF_RO_AFTER_INIT 0x00200000 +#define SHF_MASKPROC 0xf0000000 + +/* special section indexes */ +#define SHN_UNDEF 0 +#define SHN_LORESERVE 0xff00 +#define SHN_LOPROC 0xff00 +#define SHN_HIPROC 0xff1f +#define SHN_LIVEPATCH 0xff20 +#define SHN_ABS 0xfff1 +#define SHN_COMMON 0xfff2 +#define SHN_HIRESERVE 0xffff + +typedef struct elf32_shdr { + Elf32_Word sh_name; + Elf32_Word sh_type; + Elf32_Word sh_flags; + Elf32_Addr sh_addr; + Elf32_Off sh_offset; + Elf32_Word sh_size; + Elf32_Word sh_link; + Elf32_Word sh_info; + Elf32_Word sh_addralign; + Elf32_Word sh_entsize; +} Elf32_Shdr; + +typedef struct elf64_shdr { + Elf64_Word sh_name; /* Section name, index in string tbl */ + Elf64_Word sh_type; /* Type of section */ + Elf64_Xword sh_flags; /* Miscellaneous section attributes */ + Elf64_Addr sh_addr; /* Section virtual addr at execution */ + Elf64_Off sh_offset; /* Section file offset */ + Elf64_Xword sh_size; /* Size of section in bytes */ + Elf64_Word sh_link; /* Index of another section */ + Elf64_Word sh_info; /* Additional section information */ + Elf64_Xword sh_addralign; /* Section alignment */ + Elf64_Xword sh_entsize; /* Entry size if section holds table */ +} Elf64_Shdr; + +#define EI_MAG0 0 /* e_ident[] indexes */ +#define EI_MAG1 1 +#define EI_MAG2 2 +#define EI_MAG3 3 +#define EI_CLASS 4 +#define EI_DATA 5 +#define EI_VERSION 6 +#define EI_OSABI 7 +#define EI_PAD 8 + +#define ELFMAG0 0x7f /* EI_MAG */ +#define ELFMAG1 'E' +#define ELFMAG2 'L' +#define ELFMAG3 'F' +#define ELFMAG "\177ELF" +#define SELFMAG 4 + +#define ELFCLASSNONE 0 /* EI_CLASS */ +#define ELFCLASS32 1 +#define ELFCLASS64 2 +#define ELFCLASSNUM 3 + +#define ELFDATANONE 0 /* e_ident[EI_DATA] */ +#define ELFDATA2LSB 1 +#define ELFDATA2MSB 2 + +#define EV_NONE 0 /* e_version, EI_VERSION */ +#define EV_CURRENT 1 +#define EV_NUM 2 + +#define ELFOSABI_NONE 0 +#define ELFOSABI_LINUX 3 + +#ifndef ELF_OSABI +#define ELF_OSABI ELFOSABI_NONE +#endif + +/* + * Notes used in ET_CORE. Architectures export some of the arch register sets + * using the corresponding note types via the PTRACE_GETREGSET and + * PTRACE_SETREGSET requests. + * The note name for these types is "LINUX", except NT_PRFPREG that is named + * "CORE". + */ +#define NT_PRSTATUS 1 +#define NT_PRFPREG 2 +#define NT_PRPSINFO 3 +#define NT_TASKSTRUCT 4 +#define NT_AUXV 6 +/* + * Note to userspace developers: size of NT_SIGINFO note may increase + * in the future to accomodate more fields, don't assume it is fixed! + */ +#define NT_SIGINFO 0x53494749 +#define NT_FILE 0x46494c45 +#define NT_PRXFPREG 0x46e62b7f /* copied from gdb5.1/include/elf/common.h */ +#define NT_PPC_VMX 0x100 /* PowerPC Altivec/VMX registers */ +#define NT_PPC_SPE 0x101 /* PowerPC SPE/EVR registers */ +#define NT_PPC_VSX 0x102 /* PowerPC VSX registers */ +#define NT_PPC_TAR 0x103 /* Target Address Register */ +#define NT_PPC_PPR 0x104 /* Program Priority Register */ +#define NT_PPC_DSCR 0x105 /* Data Stream Control Register */ +#define NT_PPC_EBB 0x106 /* Event Based Branch Registers */ +#define NT_PPC_PMU 0x107 /* Performance Monitor Registers */ +#define NT_PPC_TM_CGPR 0x108 /* TM checkpointed GPR Registers */ +#define NT_PPC_TM_CFPR 0x109 /* TM checkpointed FPR Registers */ +#define NT_PPC_TM_CVMX 0x10a /* TM checkpointed VMX Registers */ +#define NT_PPC_TM_CVSX 0x10b /* TM checkpointed VSX Registers */ +#define NT_PPC_TM_SPR 0x10c /* TM Special Purpose Registers */ +#define NT_PPC_TM_CTAR 0x10d /* TM checkpointed Target Address Register */ +#define NT_PPC_TM_CPPR 0x10e /* TM checkpointed Program Priority Register */ +#define NT_PPC_TM_CDSCR 0x10f /* TM checkpointed Data Stream Control Register */ +#define NT_PPC_PKEY 0x110 /* Memory Protection Keys registers */ +#define NT_PPC_DEXCR 0x111 /* PowerPC DEXCR registers */ +#define NT_PPC_HASHKEYR 0x112 /* PowerPC HASHKEYR register */ +#define NT_386_TLS 0x200 /* i386 TLS slots (struct user_desc) */ +#define NT_386_IOPERM 0x201 /* x86 io permission bitmap (1=deny) */ +#define NT_X86_XSTATE 0x202 /* x86 extended state using xsave */ +/* Old binutils treats 0x203 as a CET state */ +#define NT_X86_SHSTK 0x204 /* x86 SHSTK state */ +#define NT_X86_XSAVE_LAYOUT 0x205 /* XSAVE layout description */ +#define NT_S390_HIGH_GPRS 0x300 /* s390 upper register halves */ +#define NT_S390_TIMER 0x301 /* s390 timer register */ +#define NT_S390_TODCMP 0x302 /* s390 TOD clock comparator register */ +#define NT_S390_TODPREG 0x303 /* s390 TOD programmable register */ +#define NT_S390_CTRS 0x304 /* s390 control registers */ +#define NT_S390_PREFIX 0x305 /* s390 prefix register */ +#define NT_S390_LAST_BREAK 0x306 /* s390 breaking event address */ +#define NT_S390_SYSTEM_CALL 0x307 /* s390 system call restart data */ +#define NT_S390_TDB 0x308 /* s390 transaction diagnostic block */ +#define NT_S390_VXRS_LOW 0x309 /* s390 vector registers 0-15 upper half */ +#define NT_S390_VXRS_HIGH 0x30a /* s390 vector registers 16-31 */ +#define NT_S390_GS_CB 0x30b /* s390 guarded storage registers */ +#define NT_S390_GS_BC 0x30c /* s390 guarded storage broadcast control block */ +#define NT_S390_RI_CB 0x30d /* s390 runtime instrumentation */ +#define NT_S390_PV_CPU_DATA 0x30e /* s390 protvirt cpu dump data */ +#define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ +#define NT_ARM_TLS 0x401 /* ARM TLS register */ +#define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ +#define NT_ARM_HW_WATCH 0x403 /* ARM hardware watchpoint registers */ +#define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ +#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ +#define NT_ARM_PAC_MASK 0x406 /* ARM pointer authentication code masks */ +#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */ +#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ +#define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ +#define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ +#define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ +#define NT_ARM_POE 0x40f /* ARM POE registers */ +#define NT_ARM_GCS 0x410 /* ARM GCS state */ +#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ +#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ +#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ +#define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ +#define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_RISCV_CSR 0x900 /* RISC-V Control and Status Registers */ +#define NT_RISCV_VECTOR 0x901 /* RISC-V vector registers */ +#define NT_RISCV_TAGGED_ADDR_CTRL 0x902 /* RISC-V tagged address control (prctl()) */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ +#define NT_LOONGARCH_HW_BREAK 0xa05 /* LoongArch hardware breakpoint registers */ +#define NT_LOONGARCH_HW_WATCH 0xa06 /* LoongArch hardware watchpoint registers */ + +/* Note types with note name "GNU" */ +#define NT_GNU_PROPERTY_TYPE_0 5 + +/* Note header in a PT_NOTE section */ +typedef struct elf32_note { + Elf32_Word n_namesz; /* Name size */ + Elf32_Word n_descsz; /* Content size */ + Elf32_Word n_type; /* Content type */ +} Elf32_Nhdr; + +/* Note header in a PT_NOTE section */ +typedef struct elf64_note { + Elf64_Word n_namesz; /* Name size */ + Elf64_Word n_descsz; /* Content size */ + Elf64_Word n_type; /* Content type */ +} Elf64_Nhdr; + +/* .note.gnu.property types for EM_AARCH64: */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000 + +/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */ +#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0) + +typedef struct { + Elf32_Half vd_version; + Elf32_Half vd_flags; + Elf32_Half vd_ndx; + Elf32_Half vd_cnt; + Elf32_Word vd_hash; + Elf32_Word vd_aux; + Elf32_Word vd_next; +} Elf32_Verdef; + +typedef struct { + Elf64_Half vd_version; + Elf64_Half vd_flags; + Elf64_Half vd_ndx; + Elf64_Half vd_cnt; + Elf64_Word vd_hash; + Elf64_Word vd_aux; + Elf64_Word vd_next; +} Elf64_Verdef; + +typedef struct { + Elf32_Word vda_name; + Elf32_Word vda_next; +} Elf32_Verdaux; + +typedef struct { + Elf64_Word vda_name; + Elf64_Word vda_next; +} Elf64_Verdaux; + +#endif /* _LINUX_ELF_H */ diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h new file mode 100644 index 000000000..841573019 --- /dev/null +++ b/tools/include/uapi/linux/erspan.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ERSPAN Tunnel Metadata + * + * Copyright (c) 2018 VMware + * + * 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. + * + * Userspace API for metadata mode ERSPAN tunnel + */ +#ifndef _UAPI_ERSPAN_H +#define _UAPI_ERSPAN_H + +#include /* For __beXX in userspace */ +#include + +/* ERSPAN version 2 metadata header */ +struct erspan_md2 { + __be32 timestamp; + __be16 sgt; /* security group tag */ +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hwid_upper:2, + ft:5, + p:1; + __u8 o:1, + gra:2, + dir:1, + hwid:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 p:1, + ft:5, + hwid_upper:2; + __u8 hwid:4, + dir:1, + gra:2, + o:1; +#else +#error "Please fix " +#endif +}; + +struct erspan_metadata { + int version; + union { + __be32 index; /* Version 1 (type II)*/ + struct erspan_md2 md2; /* Version 2 (type III) */ + } u; +}; + +#endif /* _UAPI_ERSPAN_H */ diff --git a/tools/include/uapi/linux/fanotify.h b/tools/include/uapi/linux/fanotify.h new file mode 100644 index 000000000..e710967c7 --- /dev/null +++ b/tools/include/uapi/linux/fanotify.h @@ -0,0 +1,274 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_FANOTIFY_H +#define _UAPI_LINUX_FANOTIFY_H + +#include + +/* the following events that user-space can register for */ +#define FAN_ACCESS 0x00000001 /* File was accessed */ +#define FAN_MODIFY 0x00000002 /* File was modified */ +#define FAN_ATTRIB 0x00000004 /* Metadata changed */ +#define FAN_CLOSE_WRITE 0x00000008 /* Writable file closed */ +#define FAN_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ +#define FAN_OPEN 0x00000020 /* File was opened */ +#define FAN_MOVED_FROM 0x00000040 /* File was moved from X */ +#define FAN_MOVED_TO 0x00000080 /* File was moved to Y */ +#define FAN_CREATE 0x00000100 /* Subfile was created */ +#define FAN_DELETE 0x00000200 /* Subfile was deleted */ +#define FAN_DELETE_SELF 0x00000400 /* Self was deleted */ +#define FAN_MOVE_SELF 0x00000800 /* Self was moved */ +#define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ + +#define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ + +#define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ +#define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ +#define FAN_OPEN_EXEC_PERM 0x00040000 /* File open/exec in perm check */ +/* #define FAN_DIR_MODIFY 0x00080000 */ /* Deprecated (reserved) */ + +#define FAN_PRE_ACCESS 0x00100000 /* Pre-content access hook */ +#define FAN_MNT_ATTACH 0x01000000 /* Mount was attached */ +#define FAN_MNT_DETACH 0x02000000 /* Mount was detached */ + +#define FAN_EVENT_ON_CHILD 0x08000000 /* Interested in child events */ + +#define FAN_RENAME 0x10000000 /* File was renamed */ + +#define FAN_ONDIR 0x40000000 /* Event occurred against dir */ + +/* helper events */ +#define FAN_CLOSE (FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */ +#define FAN_MOVE (FAN_MOVED_FROM | FAN_MOVED_TO) /* moves */ + +/* flags used for fanotify_init() */ +#define FAN_CLOEXEC 0x00000001 +#define FAN_NONBLOCK 0x00000002 + +/* These are NOT bitwise flags. Both bits are used together. */ +#define FAN_CLASS_NOTIF 0x00000000 +#define FAN_CLASS_CONTENT 0x00000004 +#define FAN_CLASS_PRE_CONTENT 0x00000008 + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_CLASS_BITS (FAN_CLASS_NOTIF | FAN_CLASS_CONTENT | \ + FAN_CLASS_PRE_CONTENT) + +#define FAN_UNLIMITED_QUEUE 0x00000010 +#define FAN_UNLIMITED_MARKS 0x00000020 +#define FAN_ENABLE_AUDIT 0x00000040 + +/* Flags to determine fanotify event format */ +#define FAN_REPORT_PIDFD 0x00000080 /* Report pidfd for event->pid */ +#define FAN_REPORT_TID 0x00000100 /* event->pid is thread id */ +#define FAN_REPORT_FID 0x00000200 /* Report unique file id */ +#define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ +#define FAN_REPORT_NAME 0x00000800 /* Report events with name */ +#define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ +#define FAN_REPORT_FD_ERROR 0x00002000 /* event->fd can report error */ +#define FAN_REPORT_MNT 0x00004000 /* Report mount events */ + +/* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ +#define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) +/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */ +#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \ + FAN_REPORT_FID | FAN_REPORT_TARGET_FID) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ + FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\ + FAN_UNLIMITED_MARKS) + +/* flags used for fanotify_modify_mark() */ +#define FAN_MARK_ADD 0x00000001 +#define FAN_MARK_REMOVE 0x00000002 +#define FAN_MARK_DONT_FOLLOW 0x00000004 +#define FAN_MARK_ONLYDIR 0x00000008 +/* FAN_MARK_MOUNT is 0x00000010 */ +#define FAN_MARK_IGNORED_MASK 0x00000020 +#define FAN_MARK_IGNORED_SURV_MODIFY 0x00000040 +#define FAN_MARK_FLUSH 0x00000080 +/* FAN_MARK_FILESYSTEM is 0x00000100 */ +#define FAN_MARK_EVICTABLE 0x00000200 +/* This bit is mutually exclusive with FAN_MARK_IGNORED_MASK bit */ +#define FAN_MARK_IGNORE 0x00000400 + +/* These are NOT bitwise flags. Both bits can be used togther. */ +#define FAN_MARK_INODE 0x00000000 +#define FAN_MARK_MOUNT 0x00000010 +#define FAN_MARK_FILESYSTEM 0x00000100 +#define FAN_MARK_MNTNS 0x00000110 + +/* + * Convenience macro - FAN_MARK_IGNORE requires FAN_MARK_IGNORED_SURV_MODIFY + * for non-inode mark types. + */ +#define FAN_MARK_IGNORE_SURV (FAN_MARK_IGNORE | FAN_MARK_IGNORED_SURV_MODIFY) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_MARK_FLAGS (FAN_MARK_ADD |\ + FAN_MARK_REMOVE |\ + FAN_MARK_DONT_FOLLOW |\ + FAN_MARK_ONLYDIR |\ + FAN_MARK_MOUNT |\ + FAN_MARK_IGNORED_MASK |\ + FAN_MARK_IGNORED_SURV_MODIFY |\ + FAN_MARK_FLUSH) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_EVENTS (FAN_ACCESS |\ + FAN_MODIFY |\ + FAN_CLOSE |\ + FAN_OPEN) + +/* + * All events which require a permission response from userspace + */ +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_PERM_EVENTS (FAN_OPEN_PERM |\ + FAN_ACCESS_PERM) + +/* Deprecated - do not use this in programs and do not add new flags here! */ +#define FAN_ALL_OUTGOING_EVENTS (FAN_ALL_EVENTS |\ + FAN_ALL_PERM_EVENTS |\ + FAN_Q_OVERFLOW) + +#define FANOTIFY_METADATA_VERSION 3 + +struct fanotify_event_metadata { + __u32 event_len; + __u8 vers; + __u8 reserved; + __u16 metadata_len; + __aligned_u64 mask; + __s32 fd; + __s32 pid; +}; + +#define FAN_EVENT_INFO_TYPE_FID 1 +#define FAN_EVENT_INFO_TYPE_DFID_NAME 2 +#define FAN_EVENT_INFO_TYPE_DFID 3 +#define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 +#define FAN_EVENT_INFO_TYPE_RANGE 6 +#define FAN_EVENT_INFO_TYPE_MNT 7 + +/* Special info types for FAN_RENAME */ +#define FAN_EVENT_INFO_TYPE_OLD_DFID_NAME 10 +/* Reserved for FAN_EVENT_INFO_TYPE_OLD_DFID 11 */ +#define FAN_EVENT_INFO_TYPE_NEW_DFID_NAME 12 +/* Reserved for FAN_EVENT_INFO_TYPE_NEW_DFID 13 */ + +/* Variable length info record following event metadata */ +struct fanotify_event_info_header { + __u8 info_type; + __u8 pad; + __u16 len; +}; + +/* + * Unique file identifier info record. + * This structure is used for records of types FAN_EVENT_INFO_TYPE_FID, + * FAN_EVENT_INFO_TYPE_DFID and FAN_EVENT_INFO_TYPE_DFID_NAME. + * For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null terminated + * name immediately after the file handle. + */ +struct fanotify_event_info_fid { + struct fanotify_event_info_header hdr; + __kernel_fsid_t fsid; + /* + * Following is an opaque struct file_handle that can be passed as + * an argument to open_by_handle_at(2). + */ + unsigned char handle[]; +}; + +/* + * This structure is used for info records of type FAN_EVENT_INFO_TYPE_PIDFD. + * It holds a pidfd for the pid that was responsible for generating an event. + */ +struct fanotify_event_info_pidfd { + struct fanotify_event_info_header hdr; + __s32 pidfd; +}; + +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + +struct fanotify_event_info_range { + struct fanotify_event_info_header hdr; + __u32 pad; + __u64 offset; + __u64 count; +}; + +struct fanotify_event_info_mnt { + struct fanotify_event_info_header hdr; + __u64 mnt_id; +}; + +/* + * User space may need to record additional information about its decision. + * The extra information type records what kind of information is included. + * The default is none. We also define an extra information buffer whose + * size is determined by the extra information type. + * + * If the information type is Audit Rule, then the information following + * is the rule number that triggered the user space decision that + * requires auditing. + */ + +#define FAN_RESPONSE_INFO_NONE 0 +#define FAN_RESPONSE_INFO_AUDIT_RULE 1 + +struct fanotify_response { + __s32 fd; + __u32 response; +}; + +struct fanotify_response_info_header { + __u8 type; + __u8 pad; + __u16 len; +}; + +struct fanotify_response_info_audit_rule { + struct fanotify_response_info_header hdr; + __u32 rule_number; + __u32 subj_trust; + __u32 obj_trust; +}; + +/* Legit userspace responses to a _PERM event */ +#define FAN_ALLOW 0x01 +#define FAN_DENY 0x02 +/* errno other than EPERM can specified in upper byte of deny response */ +#define FAN_ERRNO_BITS 8 +#define FAN_ERRNO_SHIFT (32 - FAN_ERRNO_BITS) +#define FAN_ERRNO_MASK ((1 << FAN_ERRNO_BITS) - 1) +#define FAN_DENY_ERRNO(err) \ + (FAN_DENY | ((((__u32)(err)) & FAN_ERRNO_MASK) << FAN_ERRNO_SHIFT)) + +#define FAN_AUDIT 0x10 /* Bitmask to create audit record for result */ +#define FAN_INFO 0x20 /* Bitmask to indicate additional information */ + +/* No fd set in event */ +#define FAN_NOFD -1 +#define FAN_NOPIDFD FAN_NOFD +#define FAN_EPIDFD -2 + +/* Helper functions to deal with fanotify_event_metadata buffers */ +#define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata)) + +#define FAN_EVENT_NEXT(meta, len) ((len) -= (meta)->event_len, \ + (struct fanotify_event_metadata*)(((char *)(meta)) + \ + (meta)->event_len)) + +#define FAN_EVENT_OK(meta, len) ((long)(len) >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len >= (long)FAN_EVENT_METADATA_LEN && \ + (long)(meta)->event_len <= (long)(len)) + +#endif /* _UAPI_LINUX_FANOTIFY_H */ diff --git a/tools/include/uapi/linux/filter.h b/tools/include/uapi/linux/filter.h new file mode 100644 index 000000000..eaef459e7 --- /dev/null +++ b/tools/include/uapi/linux/filter.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Linux Socket Filter Data Structures + */ + +#ifndef __LINUX_FILTER_H__ +#define __LINUX_FILTER_H__ + + +#include +#include + +/* + * Current version of the filter code architecture. + */ +#define BPF_MAJOR_VERSION 1 +#define BPF_MINOR_VERSION 1 + +/* + * Try and keep these values and structures similar to BSD, especially + * the BPF code definitions which need to match so you can share filters + */ + +struct sock_filter { /* Filter block */ + __u16 code; /* Actual filter code */ + __u8 jt; /* Jump true */ + __u8 jf; /* Jump false */ + __u32 k; /* Generic multiuse field */ +}; + +struct sock_fprog { /* Required for SO_ATTACH_FILTER. */ + unsigned short len; /* Number of filter blocks */ + struct sock_filter *filter; +}; + +/* ret - BPF_K and BPF_X also apply */ +#define BPF_RVAL(code) ((code) & 0x18) +#define BPF_A 0x10 + +/* misc */ +#define BPF_MISCOP(code) ((code) & 0xf8) +#define BPF_TAX 0x00 +#define BPF_TXA 0x80 + +/* + * Macros for filter block array initializers. + */ +#ifndef BPF_STMT +#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k } +#endif +#ifndef BPF_JUMP +#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k } +#endif + +/* + * Number of scratch memory words for: BPF_ST and BPF_STX + */ +#define BPF_MEMWORDS 16 + +/* RATIONALE. Negative offsets are invalid in BPF. + We use them to reference ancillary data. + Unlike introduction new instructions, it does not break + existing compilers/optimizers. + */ +#define SKF_AD_OFF (-0x1000) +#define SKF_AD_PROTOCOL 0 +#define SKF_AD_PKTTYPE 4 +#define SKF_AD_IFINDEX 8 +#define SKF_AD_NLATTR 12 +#define SKF_AD_NLATTR_NEST 16 +#define SKF_AD_MARK 20 +#define SKF_AD_QUEUE 24 +#define SKF_AD_HATYPE 28 +#define SKF_AD_RXHASH 32 +#define SKF_AD_CPU 36 +#define SKF_AD_ALU_XOR_X 40 +#define SKF_AD_VLAN_TAG 44 +#define SKF_AD_VLAN_TAG_PRESENT 48 +#define SKF_AD_PAY_OFFSET 52 +#define SKF_AD_RANDOM 56 +#define SKF_AD_VLAN_TPID 60 +#define SKF_AD_MAX 64 + +#define SKF_NET_OFF (-0x100000) +#define SKF_LL_OFF (-0x200000) + +#define BPF_NET_OFF SKF_NET_OFF +#define BPF_LL_OFF SKF_LL_OFF + +#endif /* __LINUX_FILTER_H__ */ diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h new file mode 100644 index 000000000..f0a26309b --- /dev/null +++ b/tools/include/uapi/linux/fs.h @@ -0,0 +1,570 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_FS_H +#define _UAPI_LINUX_FS_H + +/* + * This file has definitions for some important file table structures + * and constants and structures used by various generic file system + * ioctl's. Please do not make any changes in this file before + * sending patches for review to linux-fsdevel@vger.kernel.org and + * linux-api@vger.kernel.org. + */ + +#include +#include +#include +#ifndef __KERNEL__ +#include +#endif + +/* Use of MS_* flags within the kernel is restricted to core mount(2) code. */ +#if !defined(__KERNEL__) +#include +#endif + +/* + * It's silly to have NR_OPEN bigger than NR_FILE, but you can change + * the file limit at runtime and only root can increase the per-process + * nr_file rlimit, so it's safe to set up a ridiculously high absolute + * upper limit on files-per-process. + * + * Some programs (notably those using select()) may have to be + * recompiled to take full advantage of the new limits.. + */ + +/* Fixed constants first: */ +#undef NR_OPEN +#define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ +#define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ + +#define BLOCK_SIZE_BITS 10 +#define BLOCK_SIZE (1</maps ioctl */ +#define PROCMAP_QUERY _IOWR(PROCFS_IOCTL_MAGIC, 17, struct procmap_query) + +enum procmap_query_flags { + /* + * VMA permission flags. + * + * Can be used as part of procmap_query.query_flags field to look up + * only VMAs satisfying specified subset of permissions. E.g., specifying + * PROCMAP_QUERY_VMA_READABLE only will return both readable and read/write VMAs, + * while having PROCMAP_QUERY_VMA_READABLE | PROCMAP_QUERY_VMA_WRITABLE will only + * return read/write VMAs, though both executable/non-executable and + * private/shared will be ignored. + * + * PROCMAP_QUERY_VMA_* flags are also returned in procmap_query.vma_flags + * field to specify actual VMA permissions. + */ + PROCMAP_QUERY_VMA_READABLE = 0x01, + PROCMAP_QUERY_VMA_WRITABLE = 0x02, + PROCMAP_QUERY_VMA_EXECUTABLE = 0x04, + PROCMAP_QUERY_VMA_SHARED = 0x08, + /* + * Query modifier flags. + * + * By default VMA that covers provided address is returned, or -ENOENT + * is returned. With PROCMAP_QUERY_COVERING_OR_NEXT_VMA flag set, closest + * VMA with vma_start > addr will be returned if no covering VMA is + * found. + * + * PROCMAP_QUERY_FILE_BACKED_VMA instructs query to consider only VMAs that + * have file backing. Can be combined with PROCMAP_QUERY_COVERING_OR_NEXT_VMA + * to iterate all VMAs with file backing. + */ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA = 0x10, + PROCMAP_QUERY_FILE_BACKED_VMA = 0x20, +}; + +/* + * Input/output argument structured passed into ioctl() call. It can be used + * to query a set of VMAs (Virtual Memory Areas) of a process. + * + * Each field can be one of three kinds, marked in a short comment to the + * right of the field: + * - "in", input argument, user has to provide this value, kernel doesn't modify it; + * - "out", output argument, kernel sets this field with VMA data; + * - "in/out", input and output argument; user provides initial value (used + * to specify maximum allowable buffer size), and kernel sets it to actual + * amount of data written (or zero, if there is no data). + * + * If matching VMA is found (according to criterias specified by + * query_addr/query_flags, all the out fields are filled out, and ioctl() + * returns 0. If there is no matching VMA, -ENOENT will be returned. + * In case of any other error, negative error code other than -ENOENT is + * returned. + * + * Most of the data is similar to the one returned as text in /proc//maps + * file, but procmap_query provides more querying flexibility. There are no + * consistency guarantees between subsequent ioctl() calls, but data returned + * for matched VMA is self-consistent. + */ +struct procmap_query { + /* Query struct size, for backwards/forward compatibility */ + __u64 size; + /* + * Query flags, a combination of enum procmap_query_flags values. + * Defines query filtering and behavior, see enum procmap_query_flags. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_flags; /* in */ + /* + * Query address. By default, VMA that covers this address will + * be looked up. PROCMAP_QUERY_* flags above modify this default + * behavior further. + * + * Input argument, provided by user. Kernel doesn't modify it. + */ + __u64 query_addr; /* in */ + /* VMA starting (inclusive) and ending (exclusive) address, if VMA is found. */ + __u64 vma_start; /* out */ + __u64 vma_end; /* out */ + /* VMA permissions flags. A combination of PROCMAP_QUERY_VMA_* flags. */ + __u64 vma_flags; /* out */ + /* VMA backing page size granularity. */ + __u64 vma_page_size; /* out */ + /* + * VMA file offset. If VMA has file backing, this specifies offset + * within the file that VMA's start address corresponds to. + * Is set to zero if VMA has no backing file. + */ + __u64 vma_offset; /* out */ + /* Backing file's inode number, or zero, if VMA has no backing file. */ + __u64 inode; /* out */ + /* Backing file's device major/minor number, or zero, if VMA has no backing file. */ + __u32 dev_major; /* out */ + __u32 dev_minor; /* out */ + /* + * If set to non-zero value, signals the request to return VMA name + * (i.e., VMA's backing file's absolute path, with " (deleted)" suffix + * appended, if file was unlinked from FS) for matched VMA. VMA name + * can also be some special name (e.g., "[heap]", "[stack]") or could + * be even user-supplied with prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME). + * + * Kernel will set this field to zero, if VMA has no associated name. + * Otherwise kernel will return actual amount of bytes filled in + * user-supplied buffer (see vma_name_addr field below), including the + * terminating zero. + * + * If VMA name is longer that user-supplied maximum buffer size, + * -E2BIG error is returned. + * + * If this field is set to non-zero value, vma_name_addr should point + * to valid user space memory buffer of at least vma_name_size bytes. + * If set to zero, vma_name_addr should be set to zero as well + */ + __u32 vma_name_size; /* in/out */ + /* + * If set to non-zero value, signals the request to extract and return + * VMA's backing file's build ID, if the backing file is an ELF file + * and it contains embedded build ID. + * + * Kernel will set this field to zero, if VMA has no backing file, + * backing file is not an ELF file, or ELF file has no build ID + * embedded. + * + * Build ID is a binary value (not a string). Kernel will set + * build_id_size field to exact number of bytes used for build ID. + * If build ID is requested and present, but needs more bytes than + * user-supplied maximum buffer size (see build_id_addr field below), + * -E2BIG error will be returned. + * + * If this field is set to non-zero value, build_id_addr should point + * to valid user space memory buffer of at least build_id_size bytes. + * If set to zero, build_id_addr should be set to zero as well + */ + __u32 build_id_size; /* in/out */ + /* + * User-supplied address of a buffer of at least vma_name_size bytes + * for kernel to fill with matched VMA's name (see vma_name_size field + * description above for details). + * + * Should be set to zero if VMA name should not be returned. + */ + __u64 vma_name_addr; /* in */ + /* + * User-supplied address of a buffer of at least build_id_size bytes + * for kernel to fill with matched VMA's ELF build ID, if available + * (see build_id_size field description above for details). + * + * Should be set to zero if build ID should not be returned. + */ + __u64 build_id_addr; /* in */ +}; + +#endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h new file mode 100644 index 000000000..84507280b --- /dev/null +++ b/tools/include/uapi/linux/fscrypt.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * fscrypt user API + * + * These ioctls can be used on filesystems that support fscrypt. See the + * "User API" section of Documentation/filesystems/fscrypt.rst. + */ +#ifndef _UAPI_LINUX_FSCRYPT_H +#define _UAPI_LINUX_FSCRYPT_H + +#include +#include + +/* Encryption policy flags */ +#define FSCRYPT_POLICY_FLAGS_PAD_4 0x00 +#define FSCRYPT_POLICY_FLAGS_PAD_8 0x01 +#define FSCRYPT_POLICY_FLAGS_PAD_16 0x02 +#define FSCRYPT_POLICY_FLAGS_PAD_32 0x03 +#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03 +#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08 +#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10 + +/* Encryption algorithms */ +#define FSCRYPT_MODE_AES_256_XTS 1 +#define FSCRYPT_MODE_AES_256_CTS 4 +#define FSCRYPT_MODE_AES_128_CBC 5 +#define FSCRYPT_MODE_AES_128_CTS 6 +#define FSCRYPT_MODE_SM4_XTS 7 +#define FSCRYPT_MODE_SM4_CTS 8 +#define FSCRYPT_MODE_ADIANTUM 9 +#define FSCRYPT_MODE_AES_256_HCTR2 10 + +/* + * Legacy policy version; ad-hoc KDF and no key verification. + * For new encrypted directories, use fscrypt_policy_v2 instead. + * + * Careful: the .version field for this is actually 0, not 1. + */ +#define FSCRYPT_POLICY_V1 0 +#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8 +struct fscrypt_policy_v1 { + __u8 version; + __u8 contents_encryption_mode; + __u8 filenames_encryption_mode; + __u8 flags; + __u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; +}; + +/* + * Process-subscribed "logon" key description prefix and payload format. + * Deprecated; prefer FS_IOC_ADD_ENCRYPTION_KEY instead. + */ +#define FSCRYPT_KEY_DESC_PREFIX "fscrypt:" +#define FSCRYPT_KEY_DESC_PREFIX_SIZE 8 +#define FSCRYPT_MAX_KEY_SIZE 64 +struct fscrypt_key { + __u32 mode; + __u8 raw[FSCRYPT_MAX_KEY_SIZE]; + __u32 size; +}; + +/* + * New policy version with HKDF and key verification (recommended). + */ +#define FSCRYPT_POLICY_V2 2 +#define FSCRYPT_KEY_IDENTIFIER_SIZE 16 +struct fscrypt_policy_v2 { + __u8 version; + __u8 contents_encryption_mode; + __u8 filenames_encryption_mode; + __u8 flags; + __u8 log2_data_unit_size; + __u8 __reserved[3]; + __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; +}; + +/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */ +struct fscrypt_get_policy_ex_arg { + __u64 policy_size; /* input/output */ + union { + __u8 version; + struct fscrypt_policy_v1 v1; + struct fscrypt_policy_v2 v2; + } policy; /* output */ +}; + +/* + * v1 policy keys are specified by an arbitrary 8-byte key "descriptor", + * matching fscrypt_policy_v1::master_key_descriptor. + */ +#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1 + +/* + * v2 policy keys are specified by a 16-byte key "identifier" which the kernel + * calculates as a cryptographic hash of the key itself, + * matching fscrypt_policy_v2::master_key_identifier. + */ +#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2 + +/* + * Specifies a key, either for v1 or v2 policies. This doesn't contain the + * actual key itself; this is just the "name" of the key. + */ +struct fscrypt_key_specifier { + __u32 type; /* one of FSCRYPT_KEY_SPEC_TYPE_* */ + __u32 __reserved; + union { + __u8 __reserved[32]; /* reserve some extra space */ + __u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE]; + __u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]; + } u; +}; + +/* + * Payload of Linux keyring key of type "fscrypt-provisioning", referenced by + * fscrypt_add_key_arg::key_id as an alternative to fscrypt_add_key_arg::raw. + */ +struct fscrypt_provisioning_key_payload { + __u32 type; + __u32 flags; + __u8 raw[]; +}; + +/* Struct passed to FS_IOC_ADD_ENCRYPTION_KEY */ +struct fscrypt_add_key_arg { + struct fscrypt_key_specifier key_spec; + __u32 raw_size; + __u32 key_id; +#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; + __u8 raw[]; +}; + +/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */ +struct fscrypt_remove_key_arg { + struct fscrypt_key_specifier key_spec; +#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_FILES_BUSY 0x00000001 +#define FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS 0x00000002 + __u32 removal_status_flags; /* output */ + __u32 __reserved[5]; +}; + +/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */ +struct fscrypt_get_key_status_arg { + /* input */ + struct fscrypt_key_specifier key_spec; + __u32 __reserved[6]; + + /* output */ +#define FSCRYPT_KEY_STATUS_ABSENT 1 +#define FSCRYPT_KEY_STATUS_PRESENT 2 +#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3 + __u32 status; +#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001 + __u32 status_flags; + __u32 user_count; + __u32 __out_reserved[13]; +}; + +#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy_v1) +#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16]) +#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy_v1) +#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */ +#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg) +#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOWR('f', 24, struct fscrypt_remove_key_arg) +#define FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS _IOWR('f', 25, struct fscrypt_remove_key_arg) +#define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 26, struct fscrypt_get_key_status_arg) +#define FS_IOC_GET_ENCRYPTION_NONCE _IOR('f', 27, __u8[16]) + +/**********************************************************************/ + +/* old names; don't add anything new here! */ +#ifndef __KERNEL__ +#define fscrypt_policy fscrypt_policy_v1 +#define FS_KEY_DESCRIPTOR_SIZE FSCRYPT_KEY_DESCRIPTOR_SIZE +#define FS_POLICY_FLAGS_PAD_4 FSCRYPT_POLICY_FLAGS_PAD_4 +#define FS_POLICY_FLAGS_PAD_8 FSCRYPT_POLICY_FLAGS_PAD_8 +#define FS_POLICY_FLAGS_PAD_16 FSCRYPT_POLICY_FLAGS_PAD_16 +#define FS_POLICY_FLAGS_PAD_32 FSCRYPT_POLICY_FLAGS_PAD_32 +#define FS_POLICY_FLAGS_PAD_MASK FSCRYPT_POLICY_FLAGS_PAD_MASK +#define FS_POLICY_FLAG_DIRECT_KEY FSCRYPT_POLICY_FLAG_DIRECT_KEY +#define FS_POLICY_FLAGS_VALID 0x07 /* contains old flags only */ +#define FS_ENCRYPTION_MODE_INVALID 0 /* never used */ +#define FS_ENCRYPTION_MODE_AES_256_XTS FSCRYPT_MODE_AES_256_XTS +#define FS_ENCRYPTION_MODE_AES_256_GCM 2 /* never used */ +#define FS_ENCRYPTION_MODE_AES_256_CBC 3 /* never used */ +#define FS_ENCRYPTION_MODE_AES_256_CTS FSCRYPT_MODE_AES_256_CTS +#define FS_ENCRYPTION_MODE_AES_128_CBC FSCRYPT_MODE_AES_128_CBC +#define FS_ENCRYPTION_MODE_AES_128_CTS FSCRYPT_MODE_AES_128_CTS +#define FS_ENCRYPTION_MODE_ADIANTUM FSCRYPT_MODE_ADIANTUM +#define FS_KEY_DESC_PREFIX FSCRYPT_KEY_DESC_PREFIX +#define FS_KEY_DESC_PREFIX_SIZE FSCRYPT_KEY_DESC_PREFIX_SIZE +#define FS_MAX_KEY_SIZE FSCRYPT_MAX_KEY_SIZE +#endif /* !__KERNEL__ */ + +#endif /* _UAPI_LINUX_FSCRYPT_H */ diff --git a/tools/include/uapi/linux/genetlink.h b/tools/include/uapi/linux/genetlink.h new file mode 100644 index 000000000..ddba3ca01 --- /dev/null +++ b/tools/include/uapi/linux/genetlink.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_GENERIC_NETLINK_H +#define _UAPI__LINUX_GENERIC_NETLINK_H + +#include +#include + +#define GENL_NAMSIZ 16 /* length of family name */ + +#define GENL_MIN_ID NLMSG_MIN_TYPE +#define GENL_MAX_ID 1023 + +struct genlmsghdr { + __u8 cmd; + __u8 version; + __u16 reserved; +}; + +#define GENL_HDRLEN NLMSG_ALIGN(sizeof(struct genlmsghdr)) + +#define GENL_ADMIN_PERM 0x01 +#define GENL_CMD_CAP_DO 0x02 +#define GENL_CMD_CAP_DUMP 0x04 +#define GENL_CMD_CAP_HASPOL 0x08 +#define GENL_UNS_ADMIN_PERM 0x10 + +/* + * List of reserved static generic netlink identifiers: + */ +#define GENL_ID_CTRL NLMSG_MIN_TYPE +#define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1) +#define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2) +/* must be last reserved + 1 */ +#define GENL_START_ALLOC (NLMSG_MIN_TYPE + 3) + +/************************************************************************** + * Controller + **************************************************************************/ + +enum { + CTRL_CMD_UNSPEC, + CTRL_CMD_NEWFAMILY, + CTRL_CMD_DELFAMILY, + CTRL_CMD_GETFAMILY, + CTRL_CMD_NEWOPS, + CTRL_CMD_DELOPS, + CTRL_CMD_GETOPS, + CTRL_CMD_NEWMCAST_GRP, + CTRL_CMD_DELMCAST_GRP, + CTRL_CMD_GETMCAST_GRP, /* unused */ + CTRL_CMD_GETPOLICY, + __CTRL_CMD_MAX, +}; + +#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1) + +enum { + CTRL_ATTR_UNSPEC, + CTRL_ATTR_FAMILY_ID, + CTRL_ATTR_FAMILY_NAME, + CTRL_ATTR_VERSION, + CTRL_ATTR_HDRSIZE, + CTRL_ATTR_MAXATTR, + CTRL_ATTR_OPS, + CTRL_ATTR_MCAST_GROUPS, + CTRL_ATTR_POLICY, + CTRL_ATTR_OP_POLICY, + CTRL_ATTR_OP, + __CTRL_ATTR_MAX, +}; + +#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1) + +enum { + CTRL_ATTR_OP_UNSPEC, + CTRL_ATTR_OP_ID, + CTRL_ATTR_OP_FLAGS, + __CTRL_ATTR_OP_MAX, +}; + +#define CTRL_ATTR_OP_MAX (__CTRL_ATTR_OP_MAX - 1) + +enum { + CTRL_ATTR_MCAST_GRP_UNSPEC, + CTRL_ATTR_MCAST_GRP_NAME, + CTRL_ATTR_MCAST_GRP_ID, + __CTRL_ATTR_MCAST_GRP_MAX, +}; + +#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1) + +enum { + CTRL_ATTR_POLICY_UNSPEC, + CTRL_ATTR_POLICY_DO, + CTRL_ATTR_POLICY_DUMP, + + __CTRL_ATTR_POLICY_DUMP_MAX, + CTRL_ATTR_POLICY_DUMP_MAX = __CTRL_ATTR_POLICY_DUMP_MAX - 1 +}; + +#define CTRL_ATTR_POLICY_MAX (__CTRL_ATTR_POLICY_DUMP_MAX - 1) + +#endif /* _UAPI__LINUX_GENERIC_NETLINK_H */ diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h new file mode 100644 index 000000000..1575d3ca6 --- /dev/null +++ b/tools/include/uapi/linux/hw_breakpoint.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_HW_BREAKPOINT_H +#define _UAPI_LINUX_HW_BREAKPOINT_H + +enum { + HW_BREAKPOINT_LEN_1 = 1, + HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_3 = 3, + HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_5 = 5, + HW_BREAKPOINT_LEN_6 = 6, + HW_BREAKPOINT_LEN_7 = 7, + HW_BREAKPOINT_LEN_8 = 8, +}; + +enum { + HW_BREAKPOINT_EMPTY = 0, + HW_BREAKPOINT_R = 1, + HW_BREAKPOINT_W = 2, + HW_BREAKPOINT_RW = HW_BREAKPOINT_R | HW_BREAKPOINT_W, + HW_BREAKPOINT_X = 4, + HW_BREAKPOINT_INVALID = HW_BREAKPOINT_RW | HW_BREAKPOINT_X, +}; + +#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */ diff --git a/tools/include/uapi/linux/if_addr.h b/tools/include/uapi/linux/if_addr.h new file mode 100644 index 000000000..aa7958b4e --- /dev/null +++ b/tools/include/uapi/linux/if_addr.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_IF_ADDR_H +#define _UAPI__LINUX_IF_ADDR_H + +#include +#include + +struct ifaddrmsg { + __u8 ifa_family; + __u8 ifa_prefixlen; /* The prefix length */ + __u8 ifa_flags; /* Flags */ + __u8 ifa_scope; /* Address scope */ + __u32 ifa_index; /* Link index */ +}; + +/* + * Important comment: + * IFA_ADDRESS is prefix address, rather than local interface address. + * It makes no difference for normally configured broadcast interfaces, + * but for point-to-point IFA_ADDRESS is DESTINATION address, + * local address is supplied in IFA_LOCAL attribute. + * + * IFA_FLAGS is a u32 attribute that extends the u8 field ifa_flags. + * If present, the value from struct ifaddrmsg will be ignored. + */ +enum { + IFA_UNSPEC, + IFA_ADDRESS, + IFA_LOCAL, + IFA_LABEL, + IFA_BROADCAST, + IFA_ANYCAST, + IFA_CACHEINFO, + IFA_MULTICAST, + IFA_FLAGS, + IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_TARGET_NETNSID, + IFA_PROTO, /* u8, address protocol */ + __IFA_MAX, +}; + +#define IFA_MAX (__IFA_MAX - 1) + +/* ifa_flags */ +#define IFA_F_SECONDARY 0x01 +#define IFA_F_TEMPORARY IFA_F_SECONDARY + +#define IFA_F_NODAD 0x02 +#define IFA_F_OPTIMISTIC 0x04 +#define IFA_F_DADFAILED 0x08 +#define IFA_F_HOMEADDRESS 0x10 +#define IFA_F_DEPRECATED 0x20 +#define IFA_F_TENTATIVE 0x40 +#define IFA_F_PERMANENT 0x80 +#define IFA_F_MANAGETEMPADDR 0x100 +#define IFA_F_NOPREFIXROUTE 0x200 +#define IFA_F_MCAUTOJOIN 0x400 +#define IFA_F_STABLE_PRIVACY 0x800 + +struct ifa_cacheinfo { + __u32 ifa_prefered; + __u32 ifa_valid; + __u32 cstamp; /* created timestamp, hundredths of seconds */ + __u32 tstamp; /* updated timestamp, hundredths of seconds */ +}; + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifaddrmsg)))) +#define IFA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifaddrmsg)) +#endif + +/* ifa_proto */ +#define IFAPROT_UNSPEC 0 +#define IFAPROT_KERNEL_LO 1 /* loopback */ +#define IFAPROT_KERNEL_RA 2 /* set by kernel from router announcement */ +#define IFAPROT_KERNEL_LL 3 /* link-local set by kernel */ + +#endif diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h new file mode 100644 index 000000000..757ce5e94 --- /dev/null +++ b/tools/include/uapi/linux/if_link.h @@ -0,0 +1,1982 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_IF_LINK_H +#define _UAPI_LINUX_IF_LINK_H + +#include +#include + +/* This struct should be in sync with struct rtnl_link_stats64 */ +struct rtnl_link_stats { + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; + __u32 collisions; + /* detailed rx_errors: */ + __u32 rx_length_errors; + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; + + /* detailed tx_errors */ + __u32 tx_aborted_errors; + __u32 tx_carrier_errors; + __u32 tx_fifo_errors; + __u32 tx_heartbeat_errors; + __u32 tx_window_errors; + + /* for cslip etc */ + __u32 rx_compressed; + __u32 tx_compressed; + + __u32 rx_nohandler; +}; + +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + * + * @rx_otherhost_dropped: Number of packets dropped due to mismatch + * in destination MAC address. + */ +struct rtnl_link_stats64 { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; + __u64 collisions; + + /* detailed rx_errors: */ + __u64 rx_length_errors; + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; + + /* detailed tx_errors */ + __u64 tx_aborted_errors; + __u64 tx_carrier_errors; + __u64 tx_fifo_errors; + __u64 tx_heartbeat_errors; + __u64 tx_window_errors; + + /* for cslip etc */ + __u64 rx_compressed; + __u64 tx_compressed; + __u64 rx_nohandler; + + __u64 rx_otherhost_dropped; +}; + +/* Subset of link stats useful for in-HW collection. Meaning of the fields is as + * for struct rtnl_link_stats64. + */ +struct rtnl_hw_stats64 { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; +}; + +/* The struct should be in sync with struct ifmap */ +struct rtnl_link_ifmap { + __u64 mem_start; + __u64 mem_end; + __u64 base_addr; + __u16 irq; + __u8 dma; + __u8 port; +}; + +/* + * IFLA_AF_SPEC + * Contains nested attributes for address family specific attributes. + * Each address family may create a attribute with the address family + * number as type and create its own attribute structure in it. + * + * Example: + * [IFLA_AF_SPEC] = { + * [AF_INET] = { + * [IFLA_INET_CONF] = ..., + * }, + * [AF_INET6] = { + * [IFLA_INET6_FLAGS] = ..., + * [IFLA_INET6_CONF] = ..., + * } + * } + */ + +enum { + IFLA_UNSPEC, + IFLA_ADDRESS, + IFLA_BROADCAST, + IFLA_IFNAME, + IFLA_MTU, + IFLA_LINK, + IFLA_QDISC, + IFLA_STATS, + IFLA_COST, +#define IFLA_COST IFLA_COST + IFLA_PRIORITY, +#define IFLA_PRIORITY IFLA_PRIORITY + IFLA_MASTER, +#define IFLA_MASTER IFLA_MASTER + IFLA_WIRELESS, /* Wireless Extension event - see wireless.h */ +#define IFLA_WIRELESS IFLA_WIRELESS + IFLA_PROTINFO, /* Protocol specific information for a link */ +#define IFLA_PROTINFO IFLA_PROTINFO + IFLA_TXQLEN, +#define IFLA_TXQLEN IFLA_TXQLEN + IFLA_MAP, +#define IFLA_MAP IFLA_MAP + IFLA_WEIGHT, +#define IFLA_WEIGHT IFLA_WEIGHT + IFLA_OPERSTATE, + IFLA_LINKMODE, + IFLA_LINKINFO, +#define IFLA_LINKINFO IFLA_LINKINFO + IFLA_NET_NS_PID, + IFLA_IFALIAS, + IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ + IFLA_VFINFO_LIST, + IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, + IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ + IFLA_NET_NS_FD, + IFLA_EXT_MASK, /* Extended info mask, VFs, etc */ + IFLA_PROMISCUITY, /* Promiscuity count: > 0 means acts PROMISC */ +#define IFLA_PROMISCUITY IFLA_PROMISCUITY + IFLA_NUM_TX_QUEUES, + IFLA_NUM_RX_QUEUES, + IFLA_CARRIER, + IFLA_PHYS_PORT_ID, + IFLA_CARRIER_CHANGES, + IFLA_PHYS_SWITCH_ID, + IFLA_LINK_NETNSID, + IFLA_PHYS_PORT_NAME, + IFLA_PROTO_DOWN, + IFLA_GSO_MAX_SEGS, + IFLA_GSO_MAX_SIZE, + IFLA_PAD, + IFLA_XDP, + IFLA_EVENT, + IFLA_NEW_NETNSID, + IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ + IFLA_CARRIER_UP_COUNT, + IFLA_CARRIER_DOWN_COUNT, + IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, + IFLA_PROP_LIST, + IFLA_ALT_IFNAME, /* Alternative ifname */ + IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, + IFLA_TSO_MAX_SIZE, + IFLA_TSO_MAX_SEGS, + IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */ + + IFLA_DEVLINK_PORT, + + IFLA_GSO_IPV4_MAX_SIZE, + IFLA_GRO_IPV4_MAX_SIZE, + IFLA_DPLL_PIN, + IFLA_MAX_PACING_OFFLOAD_HORIZON, + __IFLA_MAX +}; + + +#define IFLA_MAX (__IFLA_MAX - 1) + +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + +/* backwards compatibility for userspace */ +#ifndef __KERNEL__ +#define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) +#define IFLA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ifinfomsg)) +#endif + +enum { + IFLA_INET_UNSPEC, + IFLA_INET_CONF, + __IFLA_INET_MAX, +}; + +#define IFLA_INET_MAX (__IFLA_INET_MAX - 1) + +/* ifi_flags. + + IFF_* flags. + + The only change is: + IFF_LOOPBACK, IFF_BROADCAST and IFF_POINTOPOINT are + more not changeable by user. They describe link media + characteristics and set by device driver. + + Comments: + - Combination IFF_BROADCAST|IFF_POINTOPOINT is invalid + - If neither of these three flags are set; + the interface is NBMA. + + - IFF_MULTICAST does not mean anything special: + multicasts can be used on all not-NBMA links. + IFF_MULTICAST means that this media uses special encapsulation + for multicast frames. Apparently, all IFF_POINTOPOINT and + IFF_BROADCAST devices are able to use multicasts too. + */ + +/* IFLA_LINK. + For usual devices it is equal ifi_index. + If it is a "virtual interface" (f.e. tunnel), ifi_link + can point to real physical interface (f.e. for bandwidth calculations), + or maybe 0, what means, that real media is unknown (usual + for IPIP tunnels, when route to endpoint is allowed to change) + */ + +/* Subtype attributes for IFLA_PROTINFO */ +enum { + IFLA_INET6_UNSPEC, + IFLA_INET6_FLAGS, /* link flags */ + IFLA_INET6_CONF, /* sysctl parameters */ + IFLA_INET6_STATS, /* statistics */ + IFLA_INET6_MCAST, /* MC things. What of them? */ + IFLA_INET6_CACHEINFO, /* time values and max reasm size */ + IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ + IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ + IFLA_INET6_RA_MTU, /* mtu carried in the RA message */ + __IFLA_INET6_MAX +}; + +#define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) + +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, + IN6_ADDR_GEN_MODE_STABLE_PRIVACY, + IN6_ADDR_GEN_MODE_RANDOM, +}; + +/* Bridge section */ + +/** + * DOC: Bridge enum definition + * + * Please *note* that the timer values in the following section are expected + * in clock_t format, which is seconds multiplied by USER_HZ (generally + * defined as 100). + * + * @IFLA_BR_FORWARD_DELAY + * The bridge forwarding delay is the time spent in LISTENING state + * (before moving to LEARNING) and in LEARNING state (before moving + * to FORWARDING). Only relevant if STP is enabled. + * + * The valid values are between (2 * USER_HZ) and (30 * USER_HZ). + * The default value is (15 * USER_HZ). + * + * @IFLA_BR_HELLO_TIME + * The time between hello packets sent by the bridge, when it is a root + * bridge or a designated bridge. Only relevant if STP is enabled. + * + * The valid values are between (1 * USER_HZ) and (10 * USER_HZ). + * The default value is (2 * USER_HZ). + * + * @IFLA_BR_MAX_AGE + * The hello packet timeout is the time until another bridge in the + * spanning tree is assumed to be dead, after reception of its last hello + * message. Only relevant if STP is enabled. + * + * The valid values are between (6 * USER_HZ) and (40 * USER_HZ). + * The default value is (20 * USER_HZ). + * + * @IFLA_BR_AGEING_TIME + * Configure the bridge's FDB entries aging time. It is the time a MAC + * address will be kept in the FDB after a packet has been received from + * that address. After this time has passed, entries are cleaned up. + * Allow values outside the 802.1 standard specification for special cases: + * + * * 0 - entry never ages (all permanent) + * * 1 - entry disappears (no persistence) + * + * The default value is (300 * USER_HZ). + * + * @IFLA_BR_STP_STATE + * Turn spanning tree protocol on (*IFLA_BR_STP_STATE* > 0) or off + * (*IFLA_BR_STP_STATE* == 0) for this bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_PRIORITY + * Set this bridge's spanning tree priority, used during STP root bridge + * election. + * + * The valid values are between 0 and 65535. + * + * @IFLA_BR_VLAN_FILTERING + * Turn VLAN filtering on (*IFLA_BR_VLAN_FILTERING* > 0) or off + * (*IFLA_BR_VLAN_FILTERING* == 0). When disabled, the bridge will not + * consider the VLAN tag when handling packets. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_PROTOCOL + * Set the protocol used for VLAN filtering. + * + * The valid values are 0x8100(802.1Q) or 0x88A8(802.1AD). The default value + * is 0x8100(802.1Q). + * + * @IFLA_BR_GROUP_FWD_MASK + * The group forwarding mask. This is the bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses (of the form 01:80:C2:00:00:0X). + * + * The default value is 0, which means the bridge does not forward any + * link-local frames coming on this port. + * + * @IFLA_BR_ROOT_ID + * The bridge root id, read only. + * + * @IFLA_BR_BRIDGE_ID + * The bridge id, read only. + * + * @IFLA_BR_ROOT_PORT + * The bridge root port, read only. + * + * @IFLA_BR_ROOT_PATH_COST + * The bridge root path cost, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE + * The bridge topology change, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_DETECTED + * The bridge topology change detected, read only. + * + * @IFLA_BR_HELLO_TIMER + * The bridge hello timer, read only. + * + * @IFLA_BR_TCN_TIMER + * The bridge tcn timer, read only. + * + * @IFLA_BR_TOPOLOGY_CHANGE_TIMER + * The bridge topology change timer, read only. + * + * @IFLA_BR_GC_TIMER + * The bridge gc timer, read only. + * + * @IFLA_BR_GROUP_ADDR + * Set the MAC address of the multicast group this bridge uses for STP. + * The address must be a link-local address in standard Ethernet MAC address + * format. It is an address of the form 01:80:C2:00:00:0X, with X in [0, 4..f]. + * + * The default value is 0. + * + * @IFLA_BR_FDB_FLUSH + * Flush bridge's fdb dynamic entries. + * + * @IFLA_BR_MCAST_ROUTER + * Set bridge's multicast router if IGMP snooping is enabled. + * The valid values are: + * + * * 0 - disabled. + * * 1 - automatic (queried). + * * 2 - permanently enabled. + * + * The default value is 1. + * + * @IFLA_BR_MCAST_SNOOPING + * Turn multicast snooping on (*IFLA_BR_MCAST_SNOOPING* > 0) or off + * (*IFLA_BR_MCAST_SNOOPING* == 0). + * + * The default value is 1. + * + * @IFLA_BR_MCAST_QUERY_USE_IFADDR + * If enabled use the bridge's own IP address as source address for IGMP + * queries (*IFLA_BR_MCAST_QUERY_USE_IFADDR* > 0) or the default of 0.0.0.0 + * (*IFLA_BR_MCAST_QUERY_USE_IFADDR* == 0). + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_QUERIER + * Enable (*IFLA_BR_MULTICAST_QUERIER* > 0) or disable + * (*IFLA_BR_MULTICAST_QUERIER* == 0) IGMP querier, ie sending of multicast + * queries by the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_HASH_ELASTICITY + * Set multicast database hash elasticity, It is the maximum chain length in + * the multicast hash table. This attribute is *deprecated* and the value + * is always 16. + * + * @IFLA_BR_MCAST_HASH_MAX + * Set maximum size of the multicast hash table + * + * The default value is 4096, the value must be a power of 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_CNT + * The Last Member Query Count is the number of Group-Specific Queries + * sent before the router assumes there are no local members. The Last + * Member Query Count is also the number of Group-and-Source-Specific + * Queries sent before the router assumes there are no listeners for a + * particular source. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_STARTUP_QUERY_CNT + * The Startup Query Count is the number of Queries sent out on startup, + * separated by the Startup Query Interval. + * + * The default value is 2. + * + * @IFLA_BR_MCAST_LAST_MEMBER_INTVL + * The Last Member Query Interval is the Max Response Time inserted into + * Group-Specific Queries sent in response to Leave Group messages, and + * is also the amount of time between Group-Specific Query messages. + * + * The default value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_MEMBERSHIP_INTVL + * The interval after which the bridge will leave a group, if no membership + * reports for this group are received. + * + * The default value is (260 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERIER_INTVL + * The interval between queries sent by other routers. if no queries are + * seen after this delay has passed, the bridge will start to send its own + * queries (as if *IFLA_BR_MCAST_QUERIER_INTVL* was enabled). + * + * The default value is (255 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_INTVL + * The Query Interval is the interval between General Queries sent by + * the Querier. + * + * The default value is (125 * USER_HZ). The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_MCAST_QUERY_RESPONSE_INTVL + * The Max Response Time used to calculate the Max Resp Code inserted + * into the periodic General Queries. + * + * The default value is (10 * USER_HZ). + * + * @IFLA_BR_MCAST_STARTUP_QUERY_INTVL + * The interval between queries in the startup phase. + * + * The default value is (125 * USER_HZ) / 4. The minimum value is (1 * USER_HZ). + * + * @IFLA_BR_NF_CALL_IPTABLES + * Enable (*NF_CALL_IPTABLES* > 0) or disable (*NF_CALL_IPTABLES* == 0) + * iptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_IP6TABLES + * Enable (*NF_CALL_IP6TABLES* > 0) or disable (*NF_CALL_IP6TABLES* == 0) + * ip6tables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_NF_CALL_ARPTABLES + * Enable (*NF_CALL_ARPTABLES* > 0) or disable (*NF_CALL_ARPTABLES* == 0) + * arptables hooks on the bridge. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_VLAN_DEFAULT_PVID + * VLAN ID applied to untagged and priority-tagged incoming packets. + * + * The default value is 1. Setting to the special value 0 makes all ports of + * this bridge not have a PVID by default, which means that they will + * not accept VLAN-untagged traffic. + * + * @IFLA_BR_PAD + * Bridge attribute padding type for netlink message. + * + * @IFLA_BR_VLAN_STATS_ENABLED + * Enable (*IFLA_BR_VLAN_STATS_ENABLED* == 1) or disable + * (*IFLA_BR_VLAN_STATS_ENABLED* == 0) per-VLAN stats accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_STATS_ENABLED + * Enable (*IFLA_BR_MCAST_STATS_ENABLED* > 0) or disable + * (*IFLA_BR_MCAST_STATS_ENABLED* == 0) multicast (IGMP/MLD) stats + * accounting. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MCAST_IGMP_VERSION + * Set the IGMP version. + * + * The valid values are 2 and 3. The default value is 2. + * + * @IFLA_BR_MCAST_MLD_VERSION + * Set the MLD version. + * + * The valid values are 1 and 2. The default value is 1. + * + * @IFLA_BR_VLAN_STATS_PER_PORT + * Enable (*IFLA_BR_VLAN_STATS_PER_PORT* == 1) or disable + * (*IFLA_BR_VLAN_STATS_PER_PORT* == 0) per-VLAN per-port stats accounting. + * Can be changed only when there are no port VLANs configured. + * + * The default value is 0 (disabled). + * + * @IFLA_BR_MULTI_BOOLOPT + * The multi_boolopt is used to control new boolean options to avoid adding + * new netlink attributes. You can look at ``enum br_boolopt_id`` for those + * options. + * + * @IFLA_BR_MCAST_QUERIER_STATE + * Bridge mcast querier states, read only. + * + * @IFLA_BR_FDB_N_LEARNED + * The number of dynamically learned FDB entries for the current bridge, + * read only. + * + * @IFLA_BR_FDB_MAX_LEARNED + * Set the number of max dynamically learned FDB entries for the current + * bridge. + */ +enum { + IFLA_BR_UNSPEC, + IFLA_BR_FORWARD_DELAY, + IFLA_BR_HELLO_TIME, + IFLA_BR_MAX_AGE, + IFLA_BR_AGEING_TIME, + IFLA_BR_STP_STATE, + IFLA_BR_PRIORITY, + IFLA_BR_VLAN_FILTERING, + IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, + IFLA_BR_PAD, + IFLA_BR_VLAN_STATS_ENABLED, + IFLA_BR_MCAST_STATS_ENABLED, + IFLA_BR_MCAST_IGMP_VERSION, + IFLA_BR_MCAST_MLD_VERSION, + IFLA_BR_VLAN_STATS_PER_PORT, + IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, + IFLA_BR_FDB_N_LEARNED, + IFLA_BR_FDB_MAX_LEARNED, + __IFLA_BR_MAX, +}; + +#define IFLA_BR_MAX (__IFLA_BR_MAX - 1) + +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + +/** + * DOC: Bridge mode enum definition + * + * @BRIDGE_MODE_HAIRPIN + * Controls whether traffic may be sent back out of the port on which it + * was received. This option is also called reflective relay mode, and is + * used to support basic VEPA (Virtual Ethernet Port Aggregator) + * capabilities. By default, this flag is turned off and the bridge will + * not forward traffic back out of the receiving port. + */ +enum { + BRIDGE_MODE_UNSPEC, + BRIDGE_MODE_HAIRPIN, +}; + +/** + * DOC: Bridge port enum definition + * + * @IFLA_BRPORT_STATE + * The operation state of the port. Here are the valid values. + * + * * 0 - port is in STP *DISABLED* state. Make this port completely + * inactive for STP. This is also called BPDU filter and could be used + * to disable STP on an untrusted port, like a leaf virtual device. + * The traffic forwarding is also stopped on this port. + * * 1 - port is in STP *LISTENING* state. Only valid if STP is enabled + * on the bridge. In this state the port listens for STP BPDUs and + * drops all other traffic frames. + * * 2 - port is in STP *LEARNING* state. Only valid if STP is enabled on + * the bridge. In this state the port will accept traffic only for the + * purpose of updating MAC address tables. + * * 3 - port is in STP *FORWARDING* state. Port is fully active. + * * 4 - port is in STP *BLOCKING* state. Only valid if STP is enabled on + * the bridge. This state is used during the STP election process. + * In this state, port will only process STP BPDUs. + * + * @IFLA_BRPORT_PRIORITY + * The STP port priority. The valid values are between 0 and 255. + * + * @IFLA_BRPORT_COST + * The STP path cost of the port. The valid values are between 1 and 65535. + * + * @IFLA_BRPORT_MODE + * Set the bridge port mode. See *BRIDGE_MODE_HAIRPIN* for more details. + * + * @IFLA_BRPORT_GUARD + * Controls whether STP BPDUs will be processed by the bridge port. By + * default, the flag is turned off to allow BPDU processing. Turning this + * flag on will disable the bridge port if a STP BPDU packet is received. + * + * If the bridge has Spanning Tree enabled, hostile devices on the network + * may send BPDU on a port and cause network failure. Setting *guard on* + * will detect and stop this by disabling the port. The port will be + * restarted if the link is brought down, or removed and reattached. + * + * @IFLA_BRPORT_PROTECT + * Controls whether a given port is allowed to become a root port or not. + * Only used when STP is enabled on the bridge. By default the flag is off. + * + * This feature is also called root port guard. If BPDU is received from a + * leaf (edge) port, it should not be elected as root port. This could + * be used if using STP on a bridge and the downstream bridges are not fully + * trusted; this prevents a hostile guest from rerouting traffic. + * + * @IFLA_BRPORT_FAST_LEAVE + * This flag allows the bridge to immediately stop multicast traffic + * forwarding on a port that receives an IGMP Leave message. It is only used + * when IGMP snooping is enabled on the bridge. By default the flag is off. + * + * @IFLA_BRPORT_LEARNING + * Controls whether a given port will learn *source* MAC addresses from + * received traffic or not. Also controls whether dynamic FDB entries + * (which can also be added by software) will be refreshed by incoming + * traffic. By default this flag is on. + * + * @IFLA_BRPORT_UNICAST_FLOOD + * Controls whether unicast traffic for which there is no FDB entry will + * be flooded towards this port. By default this flag is on. + * + * @IFLA_BRPORT_PROXYARP + * Enable proxy ARP on this port. + * + * @IFLA_BRPORT_LEARNING_SYNC + * Controls whether a given port will sync MAC addresses learned on device + * port to bridge FDB. + * + * @IFLA_BRPORT_PROXYARP_WIFI + * Enable proxy ARP on this port which meets extended requirements by + * IEEE 802.11 and Hotspot 2.0 specifications. + * + * @IFLA_BRPORT_ROOT_ID + * + * @IFLA_BRPORT_BRIDGE_ID + * + * @IFLA_BRPORT_DESIGNATED_PORT + * + * @IFLA_BRPORT_DESIGNATED_COST + * + * @IFLA_BRPORT_ID + * + * @IFLA_BRPORT_NO + * + * @IFLA_BRPORT_TOPOLOGY_CHANGE_ACK + * + * @IFLA_BRPORT_CONFIG_PENDING + * + * @IFLA_BRPORT_MESSAGE_AGE_TIMER + * + * @IFLA_BRPORT_FORWARD_DELAY_TIMER + * + * @IFLA_BRPORT_HOLD_TIMER + * + * @IFLA_BRPORT_FLUSH + * Flush bridge ports' fdb dynamic entries. + * + * @IFLA_BRPORT_MULTICAST_ROUTER + * Configure the port's multicast router presence. A port with + * a multicast router will receive all multicast traffic. + * The valid values are: + * + * * 0 disable multicast routers on this port + * * 1 let the system detect the presence of routers (default) + * * 2 permanently enable multicast traffic forwarding on this port + * * 3 enable multicast routers temporarily on this port, not depending + * on incoming queries. + * + * @IFLA_BRPORT_PAD + * + * @IFLA_BRPORT_MCAST_FLOOD + * Controls whether a given port will flood multicast traffic for which + * there is no MDB entry. By default this flag is on. + * + * @IFLA_BRPORT_MCAST_TO_UCAST + * Controls whether a given port will replicate packets using unicast + * instead of multicast. By default this flag is off. + * + * This is done by copying the packet per host and changing the multicast + * destination MAC to a unicast one accordingly. + * + * *mcast_to_unicast* works on top of the multicast snooping feature of the + * bridge. Which means unicast copies are only delivered to hosts which + * are interested in unicast and signaled this via IGMP/MLD reports previously. + * + * This feature is intended for interface types which have a more reliable + * and/or efficient way to deliver unicast packets than broadcast ones + * (e.g. WiFi). + * + * However, it should only be enabled on interfaces where no IGMPv2/MLDv1 + * report suppression takes place. IGMP/MLD report suppression issue is + * usually overcome by the network daemon (supplicant) enabling AP isolation + * and by that separating all STAs. + * + * Delivery of STA-to-STA IP multicast is made possible again by enabling + * and utilizing the bridge hairpin mode, which considers the incoming port + * as a potential outgoing port, too (see *BRIDGE_MODE_HAIRPIN* option). + * Hairpin mode is performed after multicast snooping, therefore leading + * to only deliver reports to STAs running a multicast router. + * + * @IFLA_BRPORT_VLAN_TUNNEL + * Controls whether vlan to tunnel mapping is enabled on the port. + * By default this flag is off. + * + * @IFLA_BRPORT_BCAST_FLOOD + * Controls flooding of broadcast traffic on the given port. By default + * this flag is on. + * + * @IFLA_BRPORT_GROUP_FWD_MASK + * Set the group forward mask. This is a bitmask that is applied to + * decide whether to forward incoming frames destined to link-local + * addresses. The addresses of the form are 01:80:C2:00:00:0X (defaults + * to 0, which means the bridge does not forward any link-local frames + * coming on this port). + * + * @IFLA_BRPORT_NEIGH_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression + * is enabled on the port. By default this flag is off. + * + * @IFLA_BRPORT_ISOLATED + * Controls whether a given port will be isolated, which means it will be + * able to communicate with non-isolated ports only. By default this + * flag is off. + * + * @IFLA_BRPORT_BACKUP_PORT + * Set a backup port. If the port loses carrier all traffic will be + * redirected to the configured backup port. Set the value to 0 to disable + * it. + * + * @IFLA_BRPORT_MRP_RING_OPEN + * + * @IFLA_BRPORT_MRP_IN_OPEN + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + * The number of per-port EHT hosts limit. The default value is 512. + * Setting to 0 is not allowed. + * + * @IFLA_BRPORT_MCAST_EHT_HOSTS_CNT + * The current number of tracked hosts, read only. + * + * @IFLA_BRPORT_LOCKED + * Controls whether a port will be locked, meaning that hosts behind the + * port will not be able to communicate through the port unless an FDB + * entry with the unit's MAC address is in the FDB. The common use case is + * that hosts are allowed access through authentication with the IEEE 802.1X + * protocol or based on whitelists. By default this flag is off. + * + * Please note that secure 802.1X deployments should always use the + * *BR_BOOLOPT_NO_LL_LEARN* flag, to not permit the bridge to populate its + * FDB based on link-local (EAPOL) traffic received on the port. + * + * @IFLA_BRPORT_MAB + * Controls whether a port will use MAC Authentication Bypass (MAB), a + * technique through which select MAC addresses may be allowed on a locked + * port, without using 802.1X authentication. Packets with an unknown source + * MAC address generates a "locked" FDB entry on the incoming bridge port. + * The common use case is for user space to react to these bridge FDB + * notifications and optionally replace the locked FDB entry with a normal + * one, allowing traffic to pass for whitelisted MAC addresses. + * + * Setting this flag also requires *IFLA_BRPORT_LOCKED* and + * *IFLA_BRPORT_LEARNING*. *IFLA_BRPORT_LOCKED* ensures that unauthorized + * data packets are dropped, and *IFLA_BRPORT_LEARNING* allows the dynamic + * FDB entries installed by user space (as replacements for the locked FDB + * entries) to be refreshed and/or aged out. + * + * @IFLA_BRPORT_MCAST_N_GROUPS + * + * @IFLA_BRPORT_MCAST_MAX_GROUPS + * Sets the maximum number of MDB entries that can be registered for a + * given port. Attempts to register more MDB entries at the port than this + * limit allows will be rejected, whether they are done through netlink + * (e.g. the bridge tool), or IGMP or MLD membership reports. Setting a + * limit of 0 disables the limit. The default value is 0. + * + * @IFLA_BRPORT_NEIGH_VLAN_SUPPRESS + * Controls whether neighbor discovery (arp and nd) proxy and suppression is + * enabled for a given port. By default this flag is off. + * + * Note that this option only takes effect when *IFLA_BRPORT_NEIGH_SUPPRESS* + * is enabled for a given port. + * + * @IFLA_BRPORT_BACKUP_NHID + * The FDB nexthop object ID to attach to packets being redirected to a + * backup port that has VLAN tunnel mapping enabled (via the + * *IFLA_BRPORT_VLAN_TUNNEL* option). Setting a value of 0 (default) has + * the effect of not attaching any ID. + */ +enum { + IFLA_BRPORT_UNSPEC, + IFLA_BRPORT_STATE, /* Spanning tree state */ + IFLA_BRPORT_PRIORITY, /* " priority */ + IFLA_BRPORT_COST, /* " cost */ + IFLA_BRPORT_MODE, /* mode (hairpin) */ + IFLA_BRPORT_GUARD, /* bpdu guard */ + IFLA_BRPORT_PROTECT, /* root port protection */ + IFLA_BRPORT_FAST_LEAVE, /* multicast fast leave */ + IFLA_BRPORT_LEARNING, /* mac learning */ + IFLA_BRPORT_UNICAST_FLOOD, /* flood unicast traffic */ + IFLA_BRPORT_PROXYARP, /* proxy ARP */ + IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ + IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, + IFLA_BRPORT_PAD, + IFLA_BRPORT_MCAST_FLOOD, + IFLA_BRPORT_MCAST_TO_UCAST, + IFLA_BRPORT_VLAN_TUNNEL, + IFLA_BRPORT_BCAST_FLOOD, + IFLA_BRPORT_GROUP_FWD_MASK, + IFLA_BRPORT_NEIGH_SUPPRESS, + IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, + IFLA_BRPORT_MRP_RING_OPEN, + IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + IFLA_BRPORT_LOCKED, + IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, + IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, + IFLA_BRPORT_BACKUP_NHID, + __IFLA_BRPORT_MAX +}; +#define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) + +struct ifla_cacheinfo { + __u32 max_reasm_len; + __u32 tstamp; /* ipv6InterfaceTable updated timestamp */ + __u32 reachable_time; + __u32 retrans_time; +}; + +enum { + IFLA_INFO_UNSPEC, + IFLA_INFO_KIND, + IFLA_INFO_DATA, + IFLA_INFO_XSTATS, + IFLA_INFO_SLAVE_KIND, + IFLA_INFO_SLAVE_DATA, + __IFLA_INFO_MAX, +}; + +#define IFLA_INFO_MAX (__IFLA_INFO_MAX - 1) + +/* VLAN section */ + +enum { + IFLA_VLAN_UNSPEC, + IFLA_VLAN_ID, + IFLA_VLAN_FLAGS, + IFLA_VLAN_EGRESS_QOS, + IFLA_VLAN_INGRESS_QOS, + IFLA_VLAN_PROTOCOL, + __IFLA_VLAN_MAX, +}; + +#define IFLA_VLAN_MAX (__IFLA_VLAN_MAX - 1) + +struct ifla_vlan_flags { + __u32 flags; + __u32 mask; +}; + +enum { + IFLA_VLAN_QOS_UNSPEC, + IFLA_VLAN_QOS_MAPPING, + __IFLA_VLAN_QOS_MAX +}; + +#define IFLA_VLAN_QOS_MAX (__IFLA_VLAN_QOS_MAX - 1) + +struct ifla_vlan_qos_mapping { + __u32 from; + __u32 to; +}; + +/* MACVLAN section */ +enum { + IFLA_MACVLAN_UNSPEC, + IFLA_MACVLAN_MODE, + IFLA_MACVLAN_FLAGS, + IFLA_MACVLAN_MACADDR_MODE, + IFLA_MACVLAN_MACADDR, + IFLA_MACVLAN_MACADDR_DATA, + IFLA_MACVLAN_MACADDR_COUNT, + IFLA_MACVLAN_BC_QUEUE_LEN, + IFLA_MACVLAN_BC_QUEUE_LEN_USED, + IFLA_MACVLAN_BC_CUTOFF, + __IFLA_MACVLAN_MAX, +}; + +#define IFLA_MACVLAN_MAX (__IFLA_MACVLAN_MAX - 1) + +enum macvlan_mode { + MACVLAN_MODE_PRIVATE = 1, /* don't talk to other macvlans */ + MACVLAN_MODE_VEPA = 2, /* talk to other ports through ext bridge */ + MACVLAN_MODE_BRIDGE = 4, /* talk to bridge ports directly */ + MACVLAN_MODE_PASSTHRU = 8,/* take over the underlying device */ + MACVLAN_MODE_SOURCE = 16,/* use source MAC address list to assign */ +}; + +enum macvlan_macaddr_mode { + MACVLAN_MACADDR_ADD, + MACVLAN_MACADDR_DEL, + MACVLAN_MACADDR_FLUSH, + MACVLAN_MACADDR_SET, +}; + +#define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ + +/* VRF section */ +enum { + IFLA_VRF_UNSPEC, + IFLA_VRF_TABLE, + __IFLA_VRF_MAX +}; + +#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1) + +enum { + IFLA_VRF_PORT_UNSPEC, + IFLA_VRF_PORT_TABLE, + __IFLA_VRF_PORT_MAX +}; + +#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1) + +/* MACSEC section */ +enum { + IFLA_MACSEC_UNSPEC, + IFLA_MACSEC_SCI, + IFLA_MACSEC_PORT, + IFLA_MACSEC_ICV_LEN, + IFLA_MACSEC_CIPHER_SUITE, + IFLA_MACSEC_WINDOW, + IFLA_MACSEC_ENCODING_SA, + IFLA_MACSEC_ENCRYPT, + IFLA_MACSEC_PROTECT, + IFLA_MACSEC_INC_SCI, + IFLA_MACSEC_ES, + IFLA_MACSEC_SCB, + IFLA_MACSEC_REPLAY_PROTECT, + IFLA_MACSEC_VALIDATION, + IFLA_MACSEC_PAD, + IFLA_MACSEC_OFFLOAD, + __IFLA_MACSEC_MAX, +}; + +#define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) + +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + IFLA_XFRM_COLLECT_METADATA, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + +enum macsec_validation_type { + MACSEC_VALIDATE_DISABLED = 0, + MACSEC_VALIDATE_CHECK = 1, + MACSEC_VALIDATE_STRICT = 2, + __MACSEC_VALIDATE_END, + MACSEC_VALIDATE_MAX = __MACSEC_VALIDATE_END - 1, +}; + +enum macsec_offload { + MACSEC_OFFLOAD_OFF = 0, + MACSEC_OFFLOAD_PHY = 1, + MACSEC_OFFLOAD_MAC = 2, + __MACSEC_OFFLOAD_END, + MACSEC_OFFLOAD_MAX = __MACSEC_OFFLOAD_END - 1, +}; + +/* IPVLAN section */ +enum { + IFLA_IPVLAN_UNSPEC, + IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, + __IFLA_IPVLAN_MAX +}; + +#define IFLA_IPVLAN_MAX (__IFLA_IPVLAN_MAX - 1) + +enum ipvlan_mode { + IPVLAN_MODE_L2 = 0, + IPVLAN_MODE_L3, + IPVLAN_MODE_L3S, + IPVLAN_MODE_MAX +}; + +#define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 + +/* Tunnel RTM header */ +struct tunnel_msg { + __u8 family; + __u8 flags; + __u16 reserved2; + __u32 ifindex; +}; + +/* netkit section */ +enum netkit_action { + NETKIT_NEXT = -1, + NETKIT_PASS = 0, + NETKIT_DROP = 2, + NETKIT_REDIRECT = 7, +}; + +enum netkit_mode { + NETKIT_L2, + NETKIT_L3, +}; + +/* NETKIT_SCRUB_NONE leaves clearing skb->{mark,priority} up to + * the BPF program if attached. This also means the latter can + * consume the two fields if they were populated earlier. + * + * NETKIT_SCRUB_DEFAULT zeroes skb->{mark,priority} fields before + * invoking the attached BPF program when the peer device resides + * in a different network namespace. This is the default behavior. + */ +enum netkit_scrub { + NETKIT_SCRUB_NONE, + NETKIT_SCRUB_DEFAULT, +}; + +enum { + IFLA_NETKIT_UNSPEC, + IFLA_NETKIT_PEER_INFO, + IFLA_NETKIT_PRIMARY, + IFLA_NETKIT_POLICY, + IFLA_NETKIT_PEER_POLICY, + IFLA_NETKIT_MODE, + IFLA_NETKIT_SCRUB, + IFLA_NETKIT_PEER_SCRUB, + IFLA_NETKIT_HEADROOM, + IFLA_NETKIT_TAILROOM, + __IFLA_NETKIT_MAX, +}; +#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) + +/* VXLAN section */ + +/* include statistics in the dump */ +#define TUNNEL_MSG_FLAG_STATS 0x01 + +#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS + +/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */ +enum { + VNIFILTER_ENTRY_STATS_UNSPEC, + VNIFILTER_ENTRY_STATS_RX_BYTES, + VNIFILTER_ENTRY_STATS_RX_PKTS, + VNIFILTER_ENTRY_STATS_RX_DROPS, + VNIFILTER_ENTRY_STATS_RX_ERRORS, + VNIFILTER_ENTRY_STATS_TX_BYTES, + VNIFILTER_ENTRY_STATS_TX_PKTS, + VNIFILTER_ENTRY_STATS_TX_DROPS, + VNIFILTER_ENTRY_STATS_TX_ERRORS, + VNIFILTER_ENTRY_STATS_PAD, + __VNIFILTER_ENTRY_STATS_MAX +}; +#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1) + +enum { + VXLAN_VNIFILTER_ENTRY_UNSPEC, + VXLAN_VNIFILTER_ENTRY_START, + VXLAN_VNIFILTER_ENTRY_END, + VXLAN_VNIFILTER_ENTRY_GROUP, + VXLAN_VNIFILTER_ENTRY_GROUP6, + VXLAN_VNIFILTER_ENTRY_STATS, + __VXLAN_VNIFILTER_ENTRY_MAX +}; +#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) + +enum { + VXLAN_VNIFILTER_UNSPEC, + VXLAN_VNIFILTER_ENTRY, + __VXLAN_VNIFILTER_MAX +}; +#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1) + +enum { + IFLA_VXLAN_UNSPEC, + IFLA_VXLAN_ID, + IFLA_VXLAN_GROUP, /* group or remote address */ + IFLA_VXLAN_LINK, + IFLA_VXLAN_LOCAL, + IFLA_VXLAN_TTL, + IFLA_VXLAN_TOS, + IFLA_VXLAN_LEARNING, + IFLA_VXLAN_AGEING, + IFLA_VXLAN_LIMIT, + IFLA_VXLAN_PORT_RANGE, /* source port */ + IFLA_VXLAN_PROXY, + IFLA_VXLAN_RSC, + IFLA_VXLAN_L2MISS, + IFLA_VXLAN_L3MISS, + IFLA_VXLAN_PORT, /* destination port */ + IFLA_VXLAN_GROUP6, + IFLA_VXLAN_LOCAL6, + IFLA_VXLAN_UDP_CSUM, + IFLA_VXLAN_UDP_ZERO_CSUM6_TX, + IFLA_VXLAN_UDP_ZERO_CSUM6_RX, + IFLA_VXLAN_REMCSUM_TX, + IFLA_VXLAN_REMCSUM_RX, + IFLA_VXLAN_GBP, + IFLA_VXLAN_REMCSUM_NOPARTIAL, + IFLA_VXLAN_COLLECT_METADATA, + IFLA_VXLAN_LABEL, + IFLA_VXLAN_GPE, + IFLA_VXLAN_TTL_INHERIT, + IFLA_VXLAN_DF, + IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ + IFLA_VXLAN_LOCALBYPASS, + IFLA_VXLAN_LABEL_POLICY, /* IPv6 flow label policy; ifla_vxlan_label_policy */ + __IFLA_VXLAN_MAX +}; +#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) + +struct ifla_vxlan_port_range { + __be16 low; + __be16 high; +}; + +enum ifla_vxlan_df { + VXLAN_DF_UNSET = 0, + VXLAN_DF_SET, + VXLAN_DF_INHERIT, + __VXLAN_DF_END, + VXLAN_DF_MAX = __VXLAN_DF_END - 1, +}; + +enum ifla_vxlan_label_policy { + VXLAN_LABEL_FIXED = 0, + VXLAN_LABEL_INHERIT = 1, + __VXLAN_LABEL_END, + VXLAN_LABEL_MAX = __VXLAN_LABEL_END - 1, +}; + +/* GENEVE section */ +enum { + IFLA_GENEVE_UNSPEC, + IFLA_GENEVE_ID, + IFLA_GENEVE_REMOTE, + IFLA_GENEVE_TTL, + IFLA_GENEVE_TOS, + IFLA_GENEVE_PORT, /* destination port */ + IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, + IFLA_GENEVE_UDP_CSUM, + IFLA_GENEVE_UDP_ZERO_CSUM6_TX, + IFLA_GENEVE_UDP_ZERO_CSUM6_RX, + IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, + IFLA_GENEVE_DF, + IFLA_GENEVE_INNER_PROTO_INHERIT, + __IFLA_GENEVE_MAX +}; +#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) + +enum ifla_geneve_df { + GENEVE_DF_UNSET = 0, + GENEVE_DF_SET, + GENEVE_DF_INHERIT, + __GENEVE_DF_END, + GENEVE_DF_MAX = __GENEVE_DF_END - 1, +}; + +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + +/* PPP section */ +enum { + IFLA_PPP_UNSPEC, + IFLA_PPP_DEV_FD, + __IFLA_PPP_MAX +}; +#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1) + +/* GTP section */ + +enum ifla_gtp_role { + GTP_ROLE_GGSN = 0, + GTP_ROLE_SGSN, +}; + +enum { + IFLA_GTP_UNSPEC, + IFLA_GTP_FD0, + IFLA_GTP_FD1, + IFLA_GTP_PDP_HASHSIZE, + IFLA_GTP_ROLE, + IFLA_GTP_CREATE_SOCKETS, + IFLA_GTP_RESTART_COUNT, + IFLA_GTP_LOCAL, + IFLA_GTP_LOCAL6, + __IFLA_GTP_MAX, +}; +#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) + +/* Bonding section */ + +enum { + IFLA_BOND_UNSPEC, + IFLA_BOND_MODE, + IFLA_BOND_ACTIVE_SLAVE, + IFLA_BOND_MIIMON, + IFLA_BOND_UPDELAY, + IFLA_BOND_DOWNDELAY, + IFLA_BOND_USE_CARRIER, + IFLA_BOND_ARP_INTERVAL, + IFLA_BOND_ARP_IP_TARGET, + IFLA_BOND_ARP_VALIDATE, + IFLA_BOND_ARP_ALL_TARGETS, + IFLA_BOND_PRIMARY, + IFLA_BOND_PRIMARY_RESELECT, + IFLA_BOND_FAIL_OVER_MAC, + IFLA_BOND_XMIT_HASH_POLICY, + IFLA_BOND_RESEND_IGMP, + IFLA_BOND_NUM_PEER_NOTIF, + IFLA_BOND_ALL_SLAVES_ACTIVE, + IFLA_BOND_MIN_LINKS, + IFLA_BOND_LP_INTERVAL, + IFLA_BOND_PACKETS_PER_SLAVE, + IFLA_BOND_AD_LACP_RATE, + IFLA_BOND_AD_SELECT, + IFLA_BOND_AD_INFO, + IFLA_BOND_AD_ACTOR_SYS_PRIO, + IFLA_BOND_AD_USER_PORT_KEY, + IFLA_BOND_AD_ACTOR_SYSTEM, + IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, + IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, + IFLA_BOND_NS_IP6_TARGET, + IFLA_BOND_COUPLED_CONTROL, + IFLA_BOND_BROADCAST_NEIGH, + IFLA_BOND_LACP_STRICT, + __IFLA_BOND_MAX, +}; + +#define IFLA_BOND_MAX (__IFLA_BOND_MAX - 1) + +enum { + IFLA_BOND_AD_INFO_UNSPEC, + IFLA_BOND_AD_INFO_AGGREGATOR, + IFLA_BOND_AD_INFO_NUM_PORTS, + IFLA_BOND_AD_INFO_ACTOR_KEY, + IFLA_BOND_AD_INFO_PARTNER_KEY, + IFLA_BOND_AD_INFO_PARTNER_MAC, + __IFLA_BOND_AD_INFO_MAX, +}; + +#define IFLA_BOND_AD_INFO_MAX (__IFLA_BOND_AD_INFO_MAX - 1) + +enum { + IFLA_BOND_SLAVE_UNSPEC, + IFLA_BOND_SLAVE_STATE, + IFLA_BOND_SLAVE_MII_STATUS, + IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, + IFLA_BOND_SLAVE_PERM_HWADDR, + IFLA_BOND_SLAVE_QUEUE_ID, + IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, + IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, + IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, + IFLA_BOND_SLAVE_PRIO, + __IFLA_BOND_SLAVE_MAX, +}; + +#define IFLA_BOND_SLAVE_MAX (__IFLA_BOND_SLAVE_MAX - 1) + +/* SR-IOV virtual function management section */ + +enum { + IFLA_VF_INFO_UNSPEC, + IFLA_VF_INFO, + __IFLA_VF_INFO_MAX, +}; + +#define IFLA_VF_INFO_MAX (__IFLA_VF_INFO_MAX - 1) + +enum { + IFLA_VF_UNSPEC, + IFLA_VF_MAC, /* Hardware queue specific attributes */ + IFLA_VF_VLAN, /* VLAN ID and QoS */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ + IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ + IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ + IFLA_VF_RSS_QUERY_EN, /* RSS Redirection Table and Hash Key query + * on/off switch + */ + IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ + IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */ + IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */ + IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */ + IFLA_VF_BROADCAST, /* VF broadcast */ + __IFLA_VF_MAX, +}; + +#define IFLA_VF_MAX (__IFLA_VF_MAX - 1) + +struct ifla_vf_mac { + __u32 vf; + __u8 mac[32]; /* MAX_ADDR_LEN */ +}; + +struct ifla_vf_broadcast { + __u8 broadcast[32]; +}; + +struct ifla_vf_vlan { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; +}; + +enum { + IFLA_VF_VLAN_INFO_UNSPEC, + IFLA_VF_VLAN_INFO, /* VLAN ID, QoS and VLAN protocol */ + __IFLA_VF_VLAN_INFO_MAX, +}; + +#define IFLA_VF_VLAN_INFO_MAX (__IFLA_VF_VLAN_INFO_MAX - 1) +#define MAX_VLAN_LIST_LEN 1 + +struct ifla_vf_vlan_info { + __u32 vf; + __u32 vlan; /* 0 - 4095, 0 disables VLAN filter */ + __u32 qos; + __be16 vlan_proto; /* VLAN protocol either 802.1Q or 802.1ad */ +}; + +struct ifla_vf_tx_rate { + __u32 vf; + __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ +}; + +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + +struct ifla_vf_spoofchk { + __u32 vf; + __u32 setting; +}; + +struct ifla_vf_guid { + __u32 vf; + __u64 guid; +}; + +enum { + IFLA_VF_LINK_STATE_AUTO, /* link state of the uplink */ + IFLA_VF_LINK_STATE_ENABLE, /* link always up */ + IFLA_VF_LINK_STATE_DISABLE, /* link always down */ + __IFLA_VF_LINK_STATE_MAX, +}; + +struct ifla_vf_link_state { + __u32 vf; + __u32 link_state; +}; + +struct ifla_vf_rss_query_en { + __u32 vf; + __u32 setting; +}; + +enum { + IFLA_VF_STATS_RX_PACKETS, + IFLA_VF_STATS_TX_PACKETS, + IFLA_VF_STATS_RX_BYTES, + IFLA_VF_STATS_TX_BYTES, + IFLA_VF_STATS_BROADCAST, + IFLA_VF_STATS_MULTICAST, + IFLA_VF_STATS_PAD, + IFLA_VF_STATS_RX_DROPPED, + IFLA_VF_STATS_TX_DROPPED, + __IFLA_VF_STATS_MAX, +}; + +#define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) + +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + + +/* IPoIB section */ + +enum { + IFLA_IPOIB_UNSPEC, + IFLA_IPOIB_PKEY, + IFLA_IPOIB_MODE, + IFLA_IPOIB_UMCAST, + __IFLA_IPOIB_MAX +}; + +enum { + IPOIB_MODE_DATAGRAM = 0, /* using unreliable datagram QPs */ + IPOIB_MODE_CONNECTED = 1, /* using connected QPs */ +}; + +#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) + + +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; + +enum { + IFLA_HSR_UNSPEC, + IFLA_HSR_SLAVE1, + IFLA_HSR_SLAVE2, + IFLA_HSR_MULTICAST_SPEC, /* Last byte of supervision addr */ + IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ + IFLA_HSR_SEQ_NR, + IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ + IFLA_HSR_INTERLINK, /* HSR interlink network device */ + __IFLA_HSR_MAX, +}; + +#define IFLA_HSR_MAX (__IFLA_HSR_MAX - 1) + +/* STATS section */ + +struct if_stats_msg { + __u8 family; + __u8 pad1; + __u16 pad2; + __u32 ifindex; + __u32 filter_mask; +}; + +/* A stats attribute can be netdev specific or a global stat. + * For netdev stats, lets use the prefix IFLA_STATS_LINK_* + */ +enum { + IFLA_STATS_UNSPEC, /* also used as 64bit pad attribute */ + IFLA_STATS_LINK_64, + IFLA_STATS_LINK_XSTATS, + IFLA_STATS_LINK_XSTATS_SLAVE, + IFLA_STATS_LINK_OFFLOAD_XSTATS, + IFLA_STATS_AF_SPEC, + __IFLA_STATS_MAX, +}; + +#define IFLA_STATS_MAX (__IFLA_STATS_MAX - 1) + +#define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) + +enum { + IFLA_STATS_GETSET_UNSPEC, + IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with + * a filter mask for the corresponding group. + */ + IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */ + __IFLA_STATS_GETSET_MAX, +}; + +#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1) + +/* These are embedded into IFLA_STATS_LINK_XSTATS: + * [IFLA_STATS_LINK_XSTATS] + * -> [LINK_XSTATS_TYPE_xxx] + * -> [rtnl link type specific attributes] + */ +enum { + LINK_XSTATS_TYPE_UNSPEC, + LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, + __LINK_XSTATS_TYPE_MAX +}; +#define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) + +/* These are stats embedded into IFLA_STATS_LINK_OFFLOAD_XSTATS */ +enum { + IFLA_OFFLOAD_XSTATS_UNSPEC, + IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */ + IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */ + __IFLA_OFFLOAD_XSTATS_MAX +}; +#define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) + +enum { + IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC, + IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */ + __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX, +}; +#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \ + (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1) + +/* XDP section */ + +#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) +#define XDP_FLAGS_SKB_MODE (1U << 1) +#define XDP_FLAGS_DRV_MODE (1U << 2) +#define XDP_FLAGS_HW_MODE (1U << 3) +#define XDP_FLAGS_REPLACE (1U << 4) +#define XDP_FLAGS_MODES (XDP_FLAGS_SKB_MODE | \ + XDP_FLAGS_DRV_MODE | \ + XDP_FLAGS_HW_MODE) +#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \ + XDP_FLAGS_MODES | XDP_FLAGS_REPLACE) + +/* These are stored into IFLA_XDP_ATTACHED on dump. */ +enum { + XDP_ATTACHED_NONE = 0, + XDP_ATTACHED_DRV, + XDP_ATTACHED_SKB, + XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, +}; + +enum { + IFLA_XDP_UNSPEC, + IFLA_XDP_FD, + IFLA_XDP_ATTACHED, + IFLA_XDP_FLAGS, + IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, + IFLA_XDP_EXPECTED_FD, + __IFLA_XDP_MAX, +}; + +#define IFLA_XDP_MAX (__IFLA_XDP_MAX - 1) + +enum { + IFLA_EVENT_NONE, + IFLA_EVENT_REBOOT, /* internal reset / reboot */ + IFLA_EVENT_FEATURES, /* change in offload features */ + IFLA_EVENT_BONDING_FAILOVER, /* change in active slave */ + IFLA_EVENT_NOTIFY_PEERS, /* re-sent grat. arp/ndisc */ + IFLA_EVENT_IGMP_RESEND, /* re-sent IGMP JOIN */ + IFLA_EVENT_BONDING_OPTIONS, /* change in bonding options */ +}; + +/* tun section */ + +enum { + IFLA_TUN_UNSPEC, + IFLA_TUN_OWNER, + IFLA_TUN_GROUP, + IFLA_TUN_TYPE, + IFLA_TUN_PI, + IFLA_TUN_VNET_HDR, + IFLA_TUN_PERSIST, + IFLA_TUN_MULTI_QUEUE, + IFLA_TUN_NUM_QUEUES, + IFLA_TUN_NUM_DISABLED_QUEUES, + __IFLA_TUN_MAX, +}; + +#define IFLA_TUN_MAX (__IFLA_TUN_MAX - 1) + +/* rmnet section */ + +#define RMNET_FLAGS_INGRESS_DEAGGREGATION (1U << 0) +#define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) + +enum { + IFLA_RMNET_UNSPEC, + IFLA_RMNET_MUX_ID, + IFLA_RMNET_FLAGS, + __IFLA_RMNET_MAX, +}; + +#define IFLA_RMNET_MAX (__IFLA_RMNET_MAX - 1) + +struct ifla_rmnet_flags { + __u32 flags; + __u32 mask; +}; + +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + +/* DSA section */ + +enum { + IFLA_DSA_UNSPEC, + IFLA_DSA_CONDUIT, + /* Deprecated, use IFLA_DSA_CONDUIT instead */ + IFLA_DSA_MASTER = IFLA_DSA_CONDUIT, + __IFLA_DSA_MAX, +}; + +#define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1) + +#endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/include/uapi/linux/if_tun.h b/tools/include/uapi/linux/if_tun.h new file mode 100644 index 000000000..2c8552570 --- /dev/null +++ b/tools/include/uapi/linux/if_tun.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Universal TUN/TAP device driver. + * Copyright (C) 1999-2000 Maxim Krasnyansky + * + * 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; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _UAPI__IF_TUN_H +#define _UAPI__IF_TUN_H + +#include +#include +#include + +/* Read queue size */ +#define TUN_READQ_SIZE 500 +/* TUN device type flags: deprecated. Use IFF_TUN/IFF_TAP instead. */ +#define TUN_TUN_DEV IFF_TUN +#define TUN_TAP_DEV IFF_TAP +#define TUN_TYPE_MASK 0x000f + +/* Ioctl defines */ +#define TUNSETNOCSUM _IOW('T', 200, int) +#define TUNSETDEBUG _IOW('T', 201, int) +#define TUNSETIFF _IOW('T', 202, int) +#define TUNSETPERSIST _IOW('T', 203, int) +#define TUNSETOWNER _IOW('T', 204, int) +#define TUNSETLINK _IOW('T', 205, int) +#define TUNSETGROUP _IOW('T', 206, int) +#define TUNGETFEATURES _IOR('T', 207, unsigned int) +#define TUNSETOFFLOAD _IOW('T', 208, unsigned int) +#define TUNSETTXFILTER _IOW('T', 209, unsigned int) +#define TUNGETIFF _IOR('T', 210, unsigned int) +#define TUNGETSNDBUF _IOR('T', 211, int) +#define TUNSETSNDBUF _IOW('T', 212, int) +#define TUNATTACHFILTER _IOW('T', 213, struct sock_fprog) +#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog) +#define TUNGETVNETHDRSZ _IOR('T', 215, int) +#define TUNSETVNETHDRSZ _IOW('T', 216, int) +#define TUNSETQUEUE _IOW('T', 217, int) +#define TUNSETIFINDEX _IOW('T', 218, unsigned int) +#define TUNGETFILTER _IOR('T', 219, struct sock_fprog) +#define TUNSETVNETLE _IOW('T', 220, int) +#define TUNGETVNETLE _IOR('T', 221, int) +/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on + * little-endian hosts. Not all kernel configurations support them, but all + * configurations that support SET also support GET. + */ +#define TUNSETVNETBE _IOW('T', 222, int) +#define TUNGETVNETBE _IOR('T', 223, int) +#define TUNSETSTEERINGEBPF _IOR('T', 224, int) +#define TUNSETFILTEREBPF _IOR('T', 225, int) +#define TUNSETCARRIER _IOW('T', 226, int) +#define TUNGETDEVNETNS _IO('T', 227) + +/* TUNSETIFF ifr flags */ +#define IFF_TUN 0x0001 +#define IFF_TAP 0x0002 +#define IFF_NAPI 0x0010 +#define IFF_NAPI_FRAGS 0x0020 +/* Stop the queue instead of dropping when the internal ring is full, so an + * attached qdisc applies backpressure instead of being bypassed. + */ +#define IFF_BACKPRESSURE 0x0080 +#define IFF_NO_PI 0x1000 +/* This flag has no real effect */ +#define IFF_ONE_QUEUE 0x2000 +#define IFF_VNET_HDR 0x4000 +#define IFF_TUN_EXCL 0x8000 +#define IFF_MULTI_QUEUE 0x0100 +#define IFF_ATTACH_QUEUE 0x0200 +#define IFF_DETACH_QUEUE 0x0400 +/* read-only flag */ +#define IFF_PERSIST 0x0800 +#define IFF_NOFILTER 0x1000 + +/* Socket options */ +#define TUN_TX_TIMESTAMP 1 + +/* Features for GSO (TUNSETOFFLOAD). */ +#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */ +#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */ +#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */ +#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */ +#define TUN_F_UFO 0x10 /* I can handle UFO packets */ + +/* Protocol info prepended to the packets (when IFF_NO_PI is not set) */ +#define TUN_PKT_STRIP 0x0001 +struct tun_pi { + __u16 flags; + __be16 proto; +}; + +/* + * Filter spec (used for SETXXFILTER ioctls) + * This stuff is applicable only to the TAP (Ethernet) devices. + * If the count is zero the filter is disabled and the driver accepts + * all packets (promisc mode). + * If the filter is enabled in order to accept broadcast packets + * broadcast addr must be explicitly included in the addr list. + */ +#define TUN_FLT_ALLMULTI 0x0001 /* Accept all multicast packets */ +struct tun_filter { + __u16 flags; /* TUN_FLT_ flags see above */ + __u16 count; /* Number of addresses */ + __u8 addr[][ETH_ALEN]; +}; + +#endif /* _UAPI__IF_TUN_H */ diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h new file mode 100644 index 000000000..50d67df78 --- /dev/null +++ b/tools/include/uapi/linux/if_xdp.h @@ -0,0 +1,185 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * if_xdp: XDP socket user-space interface + * Copyright(c) 2018 Intel Corporation. + * + * Author(s): Björn Töpel + * Magnus Karlsson + */ + +#ifndef _UAPI_LINUX_IF_XDP_H +#define _UAPI_LINUX_IF_XDP_H + +#include + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM (1 << 0) +#define XDP_COPY (1 << 1) /* Force copy-mode */ +#define XDP_ZEROCOPY (1 << 2) /* Force zero-copy mode */ +/* If this option is set, the driver might go sleep and in that case + * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be + * set. If it is set, the application need to explicitly wake up the + * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are + * running the driver and the application on the same core, you should + * use this option so that the kernel will yield to the user space + * application. + */ +#define XDP_USE_NEED_WAKEUP (1 << 3) +/* By setting this option, userspace application indicates that it can + * handle multiple descriptors per packet thus enabling AF_XDP to split + * multi-buffer XDP frames into multiple Rx descriptors. Without this set + * such frames will be dropped. + */ +#define XDP_USE_SG (1 << 4) + +/* Flags for xsk_umem_config flags */ +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +/* Force checksum calculation in software. Can be used for testing or + * working around potential HW issues. This option causes performance + * degradation and only works in XDP_COPY mode. + */ +#define XDP_UMEM_TX_SW_CSUM (1 << 1) + +/* Request to reserve tx_metadata_len bytes of per-chunk metadata. + */ +#define XDP_UMEM_TX_METADATA_LEN (1 << 2) + +struct sockaddr_xdp { + __u16 sxdp_family; + __u16 sxdp_flags; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; +}; + +/* XDP_RING flags */ +#define XDP_RING_NEED_WAKEUP (1 << 0) + +struct xdp_ring_offset { + __u64 producer; + __u64 consumer; + __u64 desc; + __u64 flags; +}; + +struct xdp_mmap_offsets { + struct xdp_ring_offset rx; + struct xdp_ring_offset tx; + struct xdp_ring_offset fr; /* Fill */ + struct xdp_ring_offset cr; /* Completion */ +}; + +/* XDP socket options */ +#define XDP_MMAP_OFFSETS 1 +#define XDP_RX_RING 2 +#define XDP_TX_RING 3 +#define XDP_UMEM_REG 4 +#define XDP_UMEM_FILL_RING 5 +#define XDP_UMEM_COMPLETION_RING 6 +#define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 +#define XDP_MAX_TX_SKB_BUDGET 9 + +struct xdp_umem_reg { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 chunk_size; + __u32 headroom; + __u32 flags; + __u32 tx_metadata_len; +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for other reasons */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 rx_ring_full; /* Dropped due to rx ring being full */ + __u64 rx_fill_ring_empty_descs; /* Failed to retrieve item from fill ring */ + __u64 tx_ring_empty_descs; /* Failed to retrieve item from tx ring */ +}; + +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000ULL +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000ULL + +/* Masks for unaligned chunks mode */ +#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48 +#define XSK_UNALIGNED_BUF_ADDR_MASK \ + ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) + +/* Request transmit timestamp. Upon completion, put it into tx_timestamp + * field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) + +/* Request transmit checksum offload. Checksum start position and offset + * are communicated via csum_start and csum_offset fields of struct + * xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) + +/* Request launch time hardware offload. The device will schedule the packet for + * transmission at a pre-determined time called launch time. The value of + * launch time is communicated via launch_time field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_LAUNCH_TIME (1 << 2) + +/* AF_XDP offloads request. 'request' union member is consumed by the driver + * when the packet is being transmitted. 'completion' union member is + * filled by the driver when the transmit completion arrives. + */ +struct xsk_tx_metadata { + __u64 flags; + + union { + struct { + /* XDP_TXMD_FLAGS_CHECKSUM */ + + /* Offset from desc->addr where checksumming should start. */ + __u16 csum_start; + /* Offset from csum_start where checksum should be stored. */ + __u16 csum_offset; + __u32 reserved; + + /* XDP_TXMD_FLAGS_LAUNCH_TIME */ + /* Launch time in nanosecond against the PTP HW Clock */ + __u64 launch_time; + } request; + + struct { + /* XDP_TXMD_FLAGS_TIMESTAMP */ + __u64 tx_timestamp; + } completion; + }; +}; + +/* Rx/Tx descriptor */ +struct xdp_desc { + __u64 addr; + __u32 len; + __u32 options; +}; + +/* UMEM descriptor is __u64 */ + +/* Flag indicating that the packet continues with the buffer pointed out by the + * next frame in the ring. The end of the packet is signalled by setting this + * bit to zero. For single buffer packets, every descriptor has 'options' set + * to 0 and this maintains backward compatibility. + */ +#define XDP_PKT_CONTD (1 << 0) + +/* TX packet carries valid metadata. */ +#define XDP_TX_METADATA (1 << 1) + +#endif /* _UAPI_LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h new file mode 100644 index 000000000..ced0fc3c3 --- /dev/null +++ b/tools/include/uapi/linux/in.h @@ -0,0 +1,337 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions of the Internet Protocol. + * + * Version: @(#)in.h 1.0.1 04/21/93 + * + * Authors: Original taken from the GNU Project file. + * Fred N. van Kempen, + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_IN_H +#define _UAPI_LINUX_IN_H + +#include +#include +#include +#include + +#if __UAPI_DEF_IN_IPPROTO +/* Standard well-defined IP protocols. */ +enum { + IPPROTO_IP = 0, /* Dummy protocol for TCP */ +#define IPPROTO_IP IPPROTO_IP + IPPROTO_ICMP = 1, /* Internet Control Message Protocol */ +#define IPPROTO_ICMP IPPROTO_ICMP + IPPROTO_IGMP = 2, /* Internet Group Management Protocol */ +#define IPPROTO_IGMP IPPROTO_IGMP + IPPROTO_IPIP = 4, /* IPIP tunnels (older KA9Q tunnels use 94) */ +#define IPPROTO_IPIP IPPROTO_IPIP + IPPROTO_TCP = 6, /* Transmission Control Protocol */ +#define IPPROTO_TCP IPPROTO_TCP + IPPROTO_EGP = 8, /* Exterior Gateway Protocol */ +#define IPPROTO_EGP IPPROTO_EGP + IPPROTO_PUP = 12, /* PUP protocol */ +#define IPPROTO_PUP IPPROTO_PUP + IPPROTO_UDP = 17, /* User Datagram Protocol */ +#define IPPROTO_UDP IPPROTO_UDP + IPPROTO_IDP = 22, /* XNS IDP protocol */ +#define IPPROTO_IDP IPPROTO_IDP + IPPROTO_TP = 29, /* SO Transport Protocol Class 4 */ +#define IPPROTO_TP IPPROTO_TP + IPPROTO_DCCP = 33, /* Datagram Congestion Control Protocol */ +#define IPPROTO_DCCP IPPROTO_DCCP + IPPROTO_IPV6 = 41, /* IPv6-in-IPv4 tunnelling */ +#define IPPROTO_IPV6 IPPROTO_IPV6 + IPPROTO_RSVP = 46, /* RSVP Protocol */ +#define IPPROTO_RSVP IPPROTO_RSVP + IPPROTO_GRE = 47, /* Cisco GRE tunnels (rfc 1701,1702) */ +#define IPPROTO_GRE IPPROTO_GRE + IPPROTO_ESP = 50, /* Encapsulation Security Payload protocol */ +#define IPPROTO_ESP IPPROTO_ESP + IPPROTO_AH = 51, /* Authentication Header protocol */ +#define IPPROTO_AH IPPROTO_AH + IPPROTO_MTP = 92, /* Multicast Transport Protocol */ +#define IPPROTO_MTP IPPROTO_MTP + IPPROTO_BEETPH = 94, /* IP option pseudo header for BEET */ +#define IPPROTO_BEETPH IPPROTO_BEETPH + IPPROTO_ENCAP = 98, /* Encapsulation Header */ +#define IPPROTO_ENCAP IPPROTO_ENCAP + IPPROTO_PIM = 103, /* Protocol Independent Multicast */ +#define IPPROTO_PIM IPPROTO_PIM + IPPROTO_COMP = 108, /* Compression Header Protocol */ +#define IPPROTO_COMP IPPROTO_COMP + IPPROTO_L2TP = 115, /* Layer 2 Tunnelling Protocol */ +#define IPPROTO_L2TP IPPROTO_L2TP + IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */ +#define IPPROTO_SCTP IPPROTO_SCTP + IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */ +#define IPPROTO_UDPLITE IPPROTO_UDPLITE + IPPROTO_MPLS = 137, /* MPLS in IP (RFC 4023) */ +#define IPPROTO_MPLS IPPROTO_MPLS + IPPROTO_ETHERNET = 143, /* Ethernet-within-IPv6 Encapsulation */ +#define IPPROTO_ETHERNET IPPROTO_ETHERNET + IPPROTO_AGGFRAG = 144, /* AGGFRAG in ESP (RFC 9347) */ +#define IPPROTO_AGGFRAG IPPROTO_AGGFRAG + IPPROTO_RAW = 255, /* Raw IP packets */ +#define IPPROTO_RAW IPPROTO_RAW + IPPROTO_SMC = 256, /* Shared Memory Communications */ +#define IPPROTO_SMC IPPROTO_SMC + IPPROTO_MPTCP = 262, /* Multipath TCP connection */ +#define IPPROTO_MPTCP IPPROTO_MPTCP + IPPROTO_MAX +}; +#endif + +#if __UAPI_DEF_IN_ADDR +/* Internet address. */ +struct in_addr { + __be32 s_addr; +}; +#endif + +#define IP_TOS 1 +#define IP_TTL 2 +#define IP_HDRINCL 3 +#define IP_OPTIONS 4 +#define IP_ROUTER_ALERT 5 +#define IP_RECVOPTS 6 +#define IP_RETOPTS 7 +#define IP_PKTINFO 8 +#define IP_PKTOPTIONS 9 +#define IP_MTU_DISCOVER 10 +#define IP_RECVERR 11 +#define IP_RECVTTL 12 +#define IP_RECVTOS 13 +#define IP_MTU 14 +#define IP_FREEBIND 15 +#define IP_IPSEC_POLICY 16 +#define IP_XFRM_POLICY 17 +#define IP_PASSSEC 18 +#define IP_TRANSPARENT 19 + +/* BSD compatibility */ +#define IP_RECVRETOPTS IP_RETOPTS + +/* TProxy original addresses */ +#define IP_ORIGDSTADDR 20 +#define IP_RECVORIGDSTADDR IP_ORIGDSTADDR + +#define IP_MINTTL 21 +#define IP_NODEFRAG 22 +#define IP_CHECKSUM 23 +#define IP_BIND_ADDRESS_NO_PORT 24 +#define IP_RECVFRAGSIZE 25 +#define IP_RECVERR_RFC4884 26 + +/* IP_MTU_DISCOVER values */ +#define IP_PMTUDISC_DONT 0 /* Never send DF frames */ +#define IP_PMTUDISC_WANT 1 /* Use per route hints */ +#define IP_PMTUDISC_DO 2 /* Always DF */ +#define IP_PMTUDISC_PROBE 3 /* Ignore dst pmtu */ +/* Always use interface mtu (ignores dst pmtu) but don't set DF flag. + * Also incoming ICMP frag_needed notifications will be ignored on + * this socket to prevent accepting spoofed ones. + */ +#define IP_PMTUDISC_INTERFACE 4 +/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get + * fragmented if they exceed the interface mtu + */ +#define IP_PMTUDISC_OMIT 5 + +#define IP_MULTICAST_IF 32 +#define IP_MULTICAST_TTL 33 +#define IP_MULTICAST_LOOP 34 +#define IP_ADD_MEMBERSHIP 35 +#define IP_DROP_MEMBERSHIP 36 +#define IP_UNBLOCK_SOURCE 37 +#define IP_BLOCK_SOURCE 38 +#define IP_ADD_SOURCE_MEMBERSHIP 39 +#define IP_DROP_SOURCE_MEMBERSHIP 40 +#define IP_MSFILTER 41 +#define MCAST_JOIN_GROUP 42 +#define MCAST_BLOCK_SOURCE 43 +#define MCAST_UNBLOCK_SOURCE 44 +#define MCAST_LEAVE_GROUP 45 +#define MCAST_JOIN_SOURCE_GROUP 46 +#define MCAST_LEAVE_SOURCE_GROUP 47 +#define MCAST_MSFILTER 48 +#define IP_MULTICAST_ALL 49 +#define IP_UNICAST_IF 50 +#define IP_LOCAL_PORT_RANGE 51 +#define IP_PROTOCOL 52 + +#define MCAST_EXCLUDE 0 +#define MCAST_INCLUDE 1 + +/* These need to appear somewhere around here */ +#define IP_DEFAULT_MULTICAST_TTL 1 +#define IP_DEFAULT_MULTICAST_LOOP 1 + +/* Request struct for multicast socket ops */ + +#if __UAPI_DEF_IP_MREQ +struct ip_mreq { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_interface; /* local IP address of interface */ +}; + +struct ip_mreqn { + struct in_addr imr_multiaddr; /* IP multicast address of group */ + struct in_addr imr_address; /* local IP address of interface */ + int imr_ifindex; /* Interface index */ +}; + +struct ip_mreq_source { + __be32 imr_multiaddr; + __be32 imr_interface; + __be32 imr_sourceaddr; +}; + +struct ip_msfilter { + __be32 imsf_multiaddr; + __be32 imsf_interface; + __u32 imsf_fmode; + __u32 imsf_numsrc; + union { + __be32 imsf_slist[1]; + __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex); + }; +}; + +#define IP_MSFILTER_SIZE(numsrc) \ + (sizeof(struct ip_msfilter) - sizeof(__u32) \ + + (numsrc) * sizeof(__u32)) + +struct group_req { + __u32 gr_interface; /* interface index */ + struct __kernel_sockaddr_storage gr_group; /* group address */ +}; + +struct group_source_req { + __u32 gsr_interface; /* interface index */ + struct __kernel_sockaddr_storage gsr_group; /* group address */ + struct __kernel_sockaddr_storage gsr_source; /* source address */ +}; + +struct group_filter { + union { + struct { + __u32 gf_interface_aux; /* interface index */ + struct __kernel_sockaddr_storage gf_group_aux; /* multicast address */ + __u32 gf_fmode_aux; /* filter mode */ + __u32 gf_numsrc_aux; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist[1]; /* interface index */ + }; + struct { + __u32 gf_interface; /* interface index */ + struct __kernel_sockaddr_storage gf_group; /* multicast address */ + __u32 gf_fmode; /* filter mode */ + __u32 gf_numsrc; /* number of sources */ + struct __kernel_sockaddr_storage gf_slist_flex[]; /* interface index */ + }; + }; +}; + +#define GROUP_FILTER_SIZE(numsrc) \ + (sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \ + + (numsrc) * sizeof(struct __kernel_sockaddr_storage)) +#endif + +#if __UAPI_DEF_IN_PKTINFO +struct in_pktinfo { + int ipi_ifindex; + struct in_addr ipi_spec_dst; + struct in_addr ipi_addr; +}; +#endif + +/* Structure describing an Internet (IP) socket address. */ +#if __UAPI_DEF_SOCKADDR_IN +#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */ +struct sockaddr_in { + __kernel_sa_family_t sin_family; /* Address family */ + __be16 sin_port; /* Port number */ + struct in_addr sin_addr; /* Internet address */ + + /* Pad to size of `struct sockaddr'. */ + unsigned char __pad[__SOCK_SIZE__ - sizeof(short int) - + sizeof(unsigned short int) - sizeof(struct in_addr)]; +}; +#define sin_zero __pad /* for BSD UNIX comp. -FvK */ +#endif + +#if __UAPI_DEF_IN_CLASS +/* + * Definitions of the bits in an Internet address integer. + * On subnets, host and network parts are found according + * to the subnet mask, not these masks. + */ +#define IN_CLASSA(a) ((((long int) (a)) & 0x80000000) == 0) +#define IN_CLASSA_NET 0xff000000 +#define IN_CLASSA_NSHIFT 24 +#define IN_CLASSA_HOST (0xffffffff & ~IN_CLASSA_NET) +#define IN_CLASSA_MAX 128 + +#define IN_CLASSB(a) ((((long int) (a)) & 0xc0000000) == 0x80000000) +#define IN_CLASSB_NET 0xffff0000 +#define IN_CLASSB_NSHIFT 16 +#define IN_CLASSB_HOST (0xffffffff & ~IN_CLASSB_NET) +#define IN_CLASSB_MAX 65536 + +#define IN_CLASSC(a) ((((long int) (a)) & 0xe0000000) == 0xc0000000) +#define IN_CLASSC_NET 0xffffff00 +#define IN_CLASSC_NSHIFT 8 +#define IN_CLASSC_HOST (0xffffffff & ~IN_CLASSC_NET) + +#define IN_CLASSD(a) ((((long int) (a)) & 0xf0000000) == 0xe0000000) +#define IN_MULTICAST(a) IN_CLASSD(a) +#define IN_MULTICAST_NET 0xe0000000 + +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) +#define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) + +#define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) +#define IN_CLASSE_NET 0xffffffff +#define IN_CLASSE_NSHIFT 0 + +/* Address to accept any incoming messages. */ +#define INADDR_ANY ((unsigned long int) 0x00000000) + +/* Address to send to all hosts. */ +#define INADDR_BROADCAST ((unsigned long int) 0xffffffff) + +/* Address indicating an error return. */ +#define INADDR_NONE ((unsigned long int) 0xffffffff) + +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + +/* Network number for local host loopback. */ +#define IN_LOOPBACKNET 127 + +/* Address to loopback in software to local host. */ +#define INADDR_LOOPBACK 0x7f000001 /* 127.0.0.1 */ +#define IN_LOOPBACK(a) ((((long int) (a)) & 0xff000000) == 0x7f000000) + +/* Defines for Multicast INADDR */ +#define INADDR_UNSPEC_GROUP 0xe0000000U /* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U /* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U /* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU /* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU /* 224.0.0.255 */ +#endif + +/* contains the htonl type stuff.. */ +#include + + +#endif /* _UAPI_LINUX_IN_H */ diff --git a/tools/include/uapi/linux/io_uring.h b/tools/include/uapi/linux/io_uring.h new file mode 100644 index 000000000..f1c16f817 --- /dev/null +++ b/tools/include/uapi/linux/io_uring.h @@ -0,0 +1,757 @@ +/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */ +/* + * Header file for the io_uring interface. + * + * Copyright (C) 2019 Jens Axboe + * Copyright (C) 2019 Christoph Hellwig + */ +#ifndef LINUX_IO_URING_H +#define LINUX_IO_URING_H + +#include +#include +/* + * this file is shared with liburing and that has to autodetect + * if linux/time_types.h is available or not, it can + * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H + * if linux/time_types.h is not available + */ +#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H +#include +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +/* + * IO submission data structure (Submission Queue Entry) + */ +struct io_uring_sqe { + __u8 opcode; /* type of operation for this sqe */ + __u8 flags; /* IOSQE_ flags */ + __u16 ioprio; /* ioprio for the request */ + __s32 fd; /* file descriptor to do IO on */ + union { + __u64 off; /* offset into file */ + __u64 addr2; + struct { + __u32 cmd_op; + __u32 __pad1; + }; + }; + union { + __u64 addr; /* pointer to buffer or iovecs */ + __u64 splice_off_in; + struct { + __u32 level; + __u32 optname; + }; + }; + __u32 len; /* buffer size or number of iovecs */ + union { + __kernel_rwf_t rw_flags; + __u32 fsync_flags; + __u16 poll_events; /* compatibility */ + __u32 poll32_events; /* word-reversed for BE */ + __u32 sync_range_flags; + __u32 msg_flags; + __u32 timeout_flags; + __u32 accept_flags; + __u32 cancel_flags; + __u32 open_flags; + __u32 statx_flags; + __u32 fadvise_advice; + __u32 splice_flags; + __u32 rename_flags; + __u32 unlink_flags; + __u32 hardlink_flags; + __u32 xattr_flags; + __u32 msg_ring_flags; + __u32 uring_cmd_flags; + __u32 waitid_flags; + __u32 futex_flags; + }; + __u64 user_data; /* data to be passed back at completion time */ + /* pack this to avoid bogus arm OABI complaints */ + union { + /* index into fixed buffers, if used */ + __u16 buf_index; + /* for grouped buffer selection */ + __u16 buf_group; + } __attribute__((packed)); + /* personality to use, if used */ + __u16 personality; + union { + __s32 splice_fd_in; + __u32 file_index; + __u32 optlen; + struct { + __u16 addr_len; + __u16 __pad3[1]; + }; + }; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + __u64 optval; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; +}; + +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + +enum { + IOSQE_FIXED_FILE_BIT, + IOSQE_IO_DRAIN_BIT, + IOSQE_IO_LINK_BIT, + IOSQE_IO_HARDLINK_BIT, + IOSQE_ASYNC_BIT, + IOSQE_BUFFER_SELECT_BIT, + IOSQE_CQE_SKIP_SUCCESS_BIT, +}; + +/* + * sqe->flags + */ +/* use fixed fileset */ +#define IOSQE_FIXED_FILE (1U << IOSQE_FIXED_FILE_BIT) +/* issue after inflight IO */ +#define IOSQE_IO_DRAIN (1U << IOSQE_IO_DRAIN_BIT) +/* links next sqe */ +#define IOSQE_IO_LINK (1U << IOSQE_IO_LINK_BIT) +/* like LINK, but stronger */ +#define IOSQE_IO_HARDLINK (1U << IOSQE_IO_HARDLINK_BIT) +/* always go async */ +#define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT) +/* select buffer from sqe->buf_group */ +#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT) +/* don't post CQE if request succeeded */ +#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT) + +/* + * io_uring_setup() flags + */ +#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */ +#define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */ +#define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */ +#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */ +#define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ +#define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ +#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ +#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ +/* + * Only one task is allowed to submit requests + */ +#define IORING_SETUP_SINGLE_ISSUER (1U << 12) + +/* + * Defer running task work to get events. + * Rather than running bits of task work whenever the task transitions + * try to do it just before it is needed. + */ +#define IORING_SETUP_DEFER_TASKRUN (1U << 13) + +/* + * Application provides the memory for the rings + */ +#define IORING_SETUP_NO_MMAP (1U << 14) + +/* + * Register the ring fd in itself for use with + * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather + * than an fd. + */ +#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15) + +/* + * Removes indirection through the SQ index array. + */ +#define IORING_SETUP_NO_SQARRAY (1U << 16) + +enum io_uring_op { + IORING_OP_NOP, + IORING_OP_READV, + IORING_OP_WRITEV, + IORING_OP_FSYNC, + IORING_OP_READ_FIXED, + IORING_OP_WRITE_FIXED, + IORING_OP_POLL_ADD, + IORING_OP_POLL_REMOVE, + IORING_OP_SYNC_FILE_RANGE, + IORING_OP_SENDMSG, + IORING_OP_RECVMSG, + IORING_OP_TIMEOUT, + IORING_OP_TIMEOUT_REMOVE, + IORING_OP_ACCEPT, + IORING_OP_ASYNC_CANCEL, + IORING_OP_LINK_TIMEOUT, + IORING_OP_CONNECT, + IORING_OP_FALLOCATE, + IORING_OP_OPENAT, + IORING_OP_CLOSE, + IORING_OP_FILES_UPDATE, + IORING_OP_STATX, + IORING_OP_READ, + IORING_OP_WRITE, + IORING_OP_FADVISE, + IORING_OP_MADVISE, + IORING_OP_SEND, + IORING_OP_RECV, + IORING_OP_OPENAT2, + IORING_OP_EPOLL_CTL, + IORING_OP_SPLICE, + IORING_OP_PROVIDE_BUFFERS, + IORING_OP_REMOVE_BUFFERS, + IORING_OP_TEE, + IORING_OP_SHUTDOWN, + IORING_OP_RENAMEAT, + IORING_OP_UNLINKAT, + IORING_OP_MKDIRAT, + IORING_OP_SYMLINKAT, + IORING_OP_LINKAT, + IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, + IORING_OP_SOCKET, + IORING_OP_URING_CMD, + IORING_OP_SEND_ZC, + IORING_OP_SENDMSG_ZC, + IORING_OP_READ_MULTISHOT, + IORING_OP_WAITID, + IORING_OP_FUTEX_WAIT, + IORING_OP_FUTEX_WAKE, + IORING_OP_FUTEX_WAITV, + + /* this goes last, obviously */ + IORING_OP_LAST, +}; + +/* + * sqe->uring_cmd_flags top 8bits aren't available for userspace + * IORING_URING_CMD_FIXED use registered buffer; pass this flag + * along with setting sqe->buf_index. + */ +#define IORING_URING_CMD_FIXED (1U << 0) +#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED + + +/* + * sqe->fsync_flags + */ +#define IORING_FSYNC_DATASYNC (1U << 0) + +/* + * sqe->timeout_flags + */ +#define IORING_TIMEOUT_ABS (1U << 0) +#define IORING_TIMEOUT_UPDATE (1U << 1) +#define IORING_TIMEOUT_BOOTTIME (1U << 2) +#define IORING_TIMEOUT_REALTIME (1U << 3) +#define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) +#define IORING_TIMEOUT_MULTISHOT (1U << 6) +#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) +#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) +/* + * sqe->splice_flags + * extends splice(2) flags + */ +#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */ + +/* + * POLL_ADD flags. Note that since sqe->poll_events is the flag space, the + * command flags for POLL_ADD are stored in sqe->len. + * + * IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if + * the poll handler will continue to report + * CQEs on behalf of the same SQE. + * + * IORING_POLL_UPDATE Update existing poll request, matching + * sqe->addr as the old user_data field. + * + * IORING_POLL_LEVEL Level triggered poll. + */ +#define IORING_POLL_ADD_MULTI (1U << 0) +#define IORING_POLL_UPDATE_EVENTS (1U << 1) +#define IORING_POLL_UPDATE_USER_DATA (1U << 2) +#define IORING_POLL_ADD_LEVEL (1U << 3) + +/* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request + * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor + * IORING_ASYNC_CANCEL_USERDATA Match on user_data, default for no other key + * IORING_ASYNC_CANCEL_OP Match request based on opcode + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) +#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3) +#define IORING_ASYNC_CANCEL_USERDATA (1U << 4) +#define IORING_ASYNC_CANCEL_OP (1U << 5) + +/* + * send/sendmsg and recv/recvmsg flags (sqe->ioprio) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + * + * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if + * the handler will continue to report + * CQEs on behalf of the same SQE. + * + * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in + * the buf_index field. + * + * IORING_SEND_ZC_REPORT_USAGE + * If set, SEND[MSG]_ZC should report + * the zerocopy usage in cqe.res + * for the IORING_CQE_F_NOTIF cqe. + * 0 is reported if zerocopy was actually possible. + * IORING_NOTIF_USAGE_ZC_COPIED if data was copied + * (at least partially). + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) +#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECVSEND_FIXED_BUF (1U << 2) +#define IORING_SEND_ZC_REPORT_USAGE (1U << 3) + +/* + * cqe.res for IORING_CQE_F_NOTIF if + * IORING_SEND_ZC_REPORT_USAGE was requested + * + * It should be treated as a flag, all other + * bits of cqe.res should be treated as reserved! + */ +#define IORING_NOTIF_USAGE_ZC_COPIED (1U << 31) + +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* + * IORING_OP_MSG_RING command types, stored in sqe->addr + */ +enum { + IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ + IORING_MSG_SEND_FD, /* send a registered fd to another ring */ +}; + +/* + * IORING_OP_MSG_RING flags (sqe->msg_ring_flags) + * + * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not + * applicable for IORING_MSG_DATA, obviously. + */ +#define IORING_MSG_RING_CQE_SKIP (1U << 0) +/* Pass through the flags from sqe->file_index to cqe->flags */ +#define IORING_MSG_RING_FLAGS_PASS (1U << 1) + +/* + * IO completion data structure (Completion Queue Entry) + */ +struct io_uring_cqe { + __u64 user_data; /* sqe->data submission passed back */ + __s32 res; /* result code for this event */ + __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; +}; + +/* + * cqe->flags + * + * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID + * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv + * IORING_CQE_F_NOTIF Set for notification CQEs. Can be used to distinct + * them from sends. + */ +#define IORING_CQE_F_BUFFER (1U << 0) +#define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) +#define IORING_CQE_F_NOTIF (1U << 3) + +enum { + IORING_CQE_BUFFER_SHIFT = 16, +}; + +/* + * Magic offsets for the application to mmap the data it needs + */ +#define IORING_OFF_SQ_RING 0ULL +#define IORING_OFF_CQ_RING 0x8000000ULL +#define IORING_OFF_SQES 0x10000000ULL +#define IORING_OFF_PBUF_RING 0x80000000ULL +#define IORING_OFF_PBUF_SHIFT 16 +#define IORING_OFF_MMAP_MASK 0xf8000000ULL + +/* + * Filled with the offset for mmap(2) + */ +struct io_sqring_offsets { + __u32 head; + __u32 tail; + __u32 ring_mask; + __u32 ring_entries; + __u32 flags; + __u32 dropped; + __u32 array; + __u32 resv1; + __u64 user_addr; +}; + +/* + * sq_ring->flags + */ +#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ +#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ + +struct io_cqring_offsets { + __u32 head; + __u32 tail; + __u32 ring_mask; + __u32 ring_entries; + __u32 overflow; + __u32 cqes; + __u32 flags; + __u32 resv1; + __u64 user_addr; +}; + +/* + * cq_ring->flags + */ + +/* disable eventfd notifications */ +#define IORING_CQ_EVENTFD_DISABLED (1U << 0) + +/* + * io_uring_enter(2) flags + */ +#define IORING_ENTER_GETEVENTS (1U << 0) +#define IORING_ENTER_SQ_WAKEUP (1U << 1) +#define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_REGISTERED_RING (1U << 4) + +/* + * Passed in for io_uring_setup(2). Copied back with updated info on success + */ +struct io_uring_params { + __u32 sq_entries; + __u32 cq_entries; + __u32 flags; + __u32 sq_thread_cpu; + __u32 sq_thread_idle; + __u32 features; + __u32 wq_fd; + __u32 resv[3]; + struct io_sqring_offsets sq_off; + struct io_cqring_offsets cq_off; +}; + +/* + * io_uring_params->features flags + */ +#define IORING_FEAT_SINGLE_MMAP (1U << 0) +#define IORING_FEAT_NODROP (1U << 1) +#define IORING_FEAT_SUBMIT_STABLE (1U << 2) +#define IORING_FEAT_RW_CUR_POS (1U << 3) +#define IORING_FEAT_CUR_PERSONALITY (1U << 4) +#define IORING_FEAT_FAST_POLL (1U << 5) +#define IORING_FEAT_POLL_32BITS (1U << 6) +#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7) +#define IORING_FEAT_EXT_ARG (1U << 8) +#define IORING_FEAT_NATIVE_WORKERS (1U << 9) +#define IORING_FEAT_RSRC_TAGS (1U << 10) +#define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) +#define IORING_FEAT_REG_REG_RING (1U << 13) + +/* + * io_uring_register(2) opcodes and arguments + */ +enum { + IORING_REGISTER_BUFFERS = 0, + IORING_UNREGISTER_BUFFERS = 1, + IORING_REGISTER_FILES = 2, + IORING_UNREGISTER_FILES = 3, + IORING_REGISTER_EVENTFD = 4, + IORING_UNREGISTER_EVENTFD = 5, + IORING_REGISTER_FILES_UPDATE = 6, + IORING_REGISTER_EVENTFD_ASYNC = 7, + IORING_REGISTER_PROBE = 8, + IORING_REGISTER_PERSONALITY = 9, + IORING_UNREGISTER_PERSONALITY = 10, + IORING_REGISTER_RESTRICTIONS = 11, + IORING_REGISTER_ENABLE_RINGS = 12, + + /* extended with tagging */ + IORING_REGISTER_FILES2 = 13, + IORING_REGISTER_FILES_UPDATE2 = 14, + IORING_REGISTER_BUFFERS2 = 15, + IORING_REGISTER_BUFFERS_UPDATE = 16, + + /* set/clear io-wq thread affinities */ + IORING_REGISTER_IOWQ_AFF = 17, + IORING_UNREGISTER_IOWQ_AFF = 18, + + /* set/get max number of io-wq workers */ + IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + + /* register/unregister io_uring fd with the ring */ + IORING_REGISTER_RING_FDS = 20, + IORING_UNREGISTER_RING_FDS = 21, + + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + + /* sync cancelation API */ + IORING_REGISTER_SYNC_CANCEL = 24, + + /* register a range of fixed file slots for automatic slot allocation */ + IORING_REGISTER_FILE_ALLOC_RANGE = 25, + + /* this goes last */ + IORING_REGISTER_LAST, + + /* flag added to the opcode to use a registered ring fd */ + IORING_REGISTER_USE_REGISTERED_RING = 1U << 31 +}; + +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + +/* deprecated, see struct io_uring_rsrc_update */ +struct io_uring_files_update { + __u32 offset; + __u32 resv; + __aligned_u64 /* __s32 * */ fds; +}; + +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + +struct io_uring_rsrc_register { + __u32 nr; + __u32 flags; + __u64 resv2; + __aligned_u64 data; + __aligned_u64 tags; +}; + +struct io_uring_rsrc_update { + __u32 offset; + __u32 resv; + __aligned_u64 data; +}; + +struct io_uring_rsrc_update2 { + __u32 offset; + __u32 resv; + __aligned_u64 data; + __aligned_u64 tags; + __u32 nr; + __u32 resv2; +}; + +/* Skip updating fd indexes set to this value in the fd table */ +#define IORING_REGISTER_FILES_SKIP (-2) + +#define IO_URING_OP_SUPPORTED (1U << 0) + +struct io_uring_probe_op { + __u8 op; + __u8 resv; + __u16 flags; /* IO_URING_OP_* flags */ + __u32 resv2; +}; + +struct io_uring_probe { + __u8 last_op; /* last opcode supported */ + __u8 ops_len; /* length of ops[] array below */ + __u16 resv; + __u32 resv2[3]; + struct io_uring_probe_op ops[]; +}; + +struct io_uring_restriction { + __u16 opcode; + union { + __u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */ + __u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */ + __u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */ + }; + __u8 resv; + __u32 resv2[3]; +}; + +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + __DECLARE_FLEX_ARRAY(struct io_uring_buf, bufs); + }; +}; + +/* + * Flags for IORING_REGISTER_PBUF_RING. + * + * IOU_PBUF_RING_MMAP: If set, kernel will allocate the memory for the ring. + * The application must not set a ring_addr in struct + * io_uring_buf_reg, instead it must subsequently call + * mmap(2) with the offset set as: + * IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT) + * to get a virtual mapping for the ring. + */ +enum { + IOU_PBUF_RING_MMAP = 1, +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 flags; + __u64 resv[3]; +}; + +/* + * io_uring_restriction->opcode values + */ +enum { + /* Allow an io_uring_register(2) opcode */ + IORING_RESTRICTION_REGISTER_OP = 0, + + /* Allow an sqe opcode */ + IORING_RESTRICTION_SQE_OP = 1, + + /* Allow sqe flags */ + IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2, + + /* Require sqe flags (these flags must be set on each submission) */ + IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3, + + IORING_RESTRICTION_LAST +}; + +struct io_uring_getevents_arg { + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad; + __u64 ts; +}; + +/* + * Argument for IORING_REGISTER_SYNC_CANCEL + */ +struct io_uring_sync_cancel_reg { + __u64 addr; + __s32 fd; + __u32 flags; + struct __kernel_timespec timeout; + __u8 opcode; + __u8 pad[7]; + __u64 pad2[3]; +}; + +/* + * Argument for IORING_REGISTER_FILE_ALLOC_RANGE + * The range is specified as [off, off + len) + */ +struct io_uring_file_index_range { + __u32 off; + __u32 len; + __u64 resv; +}; + +struct io_uring_recvmsg_out { + __u32 namelen; + __u32 controllen; + __u32 payloadlen; + __u32 flags; +}; + +/* + * Argument for IORING_OP_URING_CMD when file is a socket + */ +enum { + SOCKET_URING_OP_SIOCINQ = 0, + SOCKET_URING_OP_SIOCOUTQ, + SOCKET_URING_OP_GETSOCKOPT, + SOCKET_URING_OP_SETSOCKOPT, +}; + +#ifdef __cplusplus +} +#endif + +#endif diff --git a/tools/include/uapi/linux/kcmp.h b/tools/include/uapi/linux/kcmp.h new file mode 100644 index 000000000..ef1305010 --- /dev/null +++ b/tools/include/uapi/linux/kcmp.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_KCMP_H +#define _UAPI_LINUX_KCMP_H + +#include + +/* Comparison type */ +enum kcmp_type { + KCMP_FILE, + KCMP_VM, + KCMP_FILES, + KCMP_FS, + KCMP_SIGHAND, + KCMP_IO, + KCMP_SYSVSEM, + KCMP_EPOLL_TFD, + + KCMP_TYPES, +}; + +/* Slot for KCMP_EPOLL_TFD */ +struct kcmp_epoll_slot { + __u32 efd; /* epoll file descriptor */ + __u32 tfd; /* target file number */ + __u32 toff; /* target offset within same numbered sequence */ +}; + +#endif /* _UAPI_LINUX_KCMP_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h new file mode 100644 index 000000000..419011097 --- /dev/null +++ b/tools/include/uapi/linux/kvm.h @@ -0,0 +1,1673 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_KVM_H +#define __LINUX_KVM_H + +/* + * Userspace interface for /dev/kvm - kernel based virtual machine + * + * Note: you must update KVM_API_VERSION if you change this interface. + */ + +#include +#include +#include +#include +#include +#include + +#ifdef __KERNEL__ +#include +#endif + +#define KVM_API_VERSION 12 + +/* + * Backwards-compatible definitions. + */ +#define __KVM_HAVE_GUEST_DEBUG + +/* for KVM_SET_USER_MEMORY_REGION */ +struct kvm_userspace_memory_region { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; /* start of the userspace allocated memory */ +}; + +/* for KVM_SET_USER_MEMORY_REGION2 */ +struct kvm_userspace_memory_region2 { + __u32 slot; + __u32 flags; + __u64 guest_phys_addr; + __u64 memory_size; + __u64 userspace_addr; + __u64 guest_memfd_offset; + __u32 guest_memfd; + __u32 pad1; + __u64 pad2[14]; +}; + +/* + * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for + * userspace, other bits are reserved for kvm internal use which are defined + * in include/linux/kvm_host.h. + */ +#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) +#define KVM_MEM_READONLY (1UL << 1) +#define KVM_MEM_GUEST_MEMFD (1UL << 2) + +/* for KVM_IRQ_LINE */ +struct kvm_irq_level { + /* + * ACPI gsi notion of irq. + * For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47.. + * For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23.. + * For ARM: See Documentation/virt/kvm/api.rst + */ + union { + __u32 irq; + __s32 status; + }; + __u32 level; +}; + + +struct kvm_irqchip { + __u32 chip_id; + __u32 pad; + union { + char dummy[512]; /* reserving space */ +#ifdef __KVM_HAVE_PIT + struct kvm_pic_state pic; +#endif +#ifdef __KVM_HAVE_IOAPIC + struct kvm_ioapic_state ioapic; +#endif + } chip; +}; + +/* for KVM_CREATE_PIT2 */ +struct kvm_pit_config { + __u32 flags; + __u32 pad[15]; +}; + +#define KVM_PIT_SPEAKER_DUMMY 1 + +struct kvm_hyperv_exit { +#define KVM_EXIT_HYPERV_SYNIC 1 +#define KVM_EXIT_HYPERV_HCALL 2 +#define KVM_EXIT_HYPERV_SYNDBG 3 + __u32 type; + __u32 pad1; + union { + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 evt_page; + __u64 msg_page; + } synic; + struct { + __u64 input; + __u64 result; + __u64 params[2]; + } hcall; + struct { + __u32 msr; + __u32 pad2; + __u64 control; + __u64 status; + __u64 send_page; + __u64 recv_page; + __u64 pending_page; + } syndbg; + } u; +}; + +struct kvm_xen_exit { +#define KVM_EXIT_XEN_HCALL 1 + __u32 type; + union { + struct { + __u32 longmode; + __u32 cpl; + __u64 input; + __u64 result; + __u64 params[6]; + } hcall; + } u; +}; + +struct kvm_exit_snp_req_certs { + __u64 gpa; + __u64 npages; + __u64 ret; +}; + +#define KVM_S390_GET_SKEYS_NONE 1 +#define KVM_S390_SKEYS_MAX 1048576 + +#define KVM_EXIT_UNKNOWN 0 +#define KVM_EXIT_EXCEPTION 1 +#define KVM_EXIT_IO 2 +#define KVM_EXIT_HYPERCALL 3 +#define KVM_EXIT_DEBUG 4 +#define KVM_EXIT_HLT 5 +#define KVM_EXIT_MMIO 6 +#define KVM_EXIT_IRQ_WINDOW_OPEN 7 +#define KVM_EXIT_SHUTDOWN 8 +#define KVM_EXIT_FAIL_ENTRY 9 +#define KVM_EXIT_INTR 10 +#define KVM_EXIT_SET_TPR 11 +#define KVM_EXIT_TPR_ACCESS 12 +#define KVM_EXIT_S390_SIEIC 13 +#define KVM_EXIT_S390_RESET 14 +#define KVM_EXIT_DCR 15 /* deprecated */ +#define KVM_EXIT_NMI 16 +#define KVM_EXIT_INTERNAL_ERROR 17 +#define KVM_EXIT_OSI 18 +#define KVM_EXIT_PAPR_HCALL 19 +#define KVM_EXIT_S390_UCONTROL 20 +#define KVM_EXIT_WATCHDOG 21 +#define KVM_EXIT_S390_TSCH 22 +#define KVM_EXIT_EPR 23 +#define KVM_EXIT_SYSTEM_EVENT 24 +#define KVM_EXIT_S390_STSI 25 +#define KVM_EXIT_IOAPIC_EOI 26 +#define KVM_EXIT_HYPERV 27 +#define KVM_EXIT_ARM_NISV 28 +#define KVM_EXIT_X86_RDMSR 29 +#define KVM_EXIT_X86_WRMSR 30 +#define KVM_EXIT_DIRTY_RING_FULL 31 +#define KVM_EXIT_AP_RESET_HOLD 32 +#define KVM_EXIT_X86_BUS_LOCK 33 +#define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 +#define KVM_EXIT_RISCV_CSR 36 +#define KVM_EXIT_NOTIFY 37 +#define KVM_EXIT_LOONGARCH_IOCSR 38 +#define KVM_EXIT_MEMORY_FAULT 39 +#define KVM_EXIT_TDX 40 +#define KVM_EXIT_ARM_SEA 41 +#define KVM_EXIT_ARM_LDST64B 42 +#define KVM_EXIT_SNP_REQ_CERTS 43 + +/* For KVM_EXIT_INTERNAL_ERROR */ +/* Emulate instruction failed. */ +#define KVM_INTERNAL_ERROR_EMULATION 1 +/* Encounter unexpected simultaneous exceptions. */ +#define KVM_INTERNAL_ERROR_SIMUL_EX 2 +/* Encounter unexpected vm-exit due to delivery event. */ +#define KVM_INTERNAL_ERROR_DELIVERY_EV 3 +/* Encounter unexpected vm-exit reason */ +#define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 + +/* Flags that describe what fields in emulation_failure hold valid data. */ +#define KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES (1ULL << 0) + +/* + * struct kvm_run can be modified by userspace at any time, so KVM must be + * careful to avoid TOCTOU bugs. In order to protect KVM, HINT_UNSAFE_IN_KVM() + * renames fields in struct kvm_run from to __unsafe when + * compiled into the kernel, ensuring that any use within KVM is obvious and + * gets extra scrutiny. + */ +#ifdef __KERNEL__ +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol##__unsafe +#else +#define HINT_UNSAFE_IN_KVM(_symbol) _symbol +#endif + +/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ +struct kvm_run { + /* in */ + __u8 request_interrupt_window; + __u8 HINT_UNSAFE_IN_KVM(immediate_exit); + __u8 padding1[6]; + + /* out */ + __u32 exit_reason; + __u8 ready_for_interrupt_injection; + __u8 if_flag; + __u16 flags; + + /* in (pre_kvm_run), out (post_kvm_run) */ + __u64 cr8; + __u64 apic_base; + +#ifdef __KVM_S390 + /* the processor status word for s390 */ + __u64 psw_mask; /* psw upper half */ + __u64 psw_addr; /* psw lower half */ +#endif + union { + /* KVM_EXIT_UNKNOWN */ + struct { + __u64 hardware_exit_reason; + } hw; + /* KVM_EXIT_FAIL_ENTRY */ + struct { + __u64 hardware_entry_failure_reason; + __u32 cpu; + } fail_entry; + /* KVM_EXIT_EXCEPTION */ + struct { + __u32 exception; + __u32 error_code; + } ex; + /* KVM_EXIT_IO */ + struct { +#define KVM_EXIT_IO_IN 0 +#define KVM_EXIT_IO_OUT 1 + __u8 direction; + __u8 size; /* bytes */ + __u16 port; + __u32 count; + __u64 data_offset; /* relative to kvm_run start */ + } io; + /* KVM_EXIT_DEBUG */ + struct { + struct kvm_debug_exit_arch arch; + } debug; + /* KVM_EXIT_MMIO */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } mmio; + /* KVM_EXIT_LOONGARCH_IOCSR */ + struct { + __u64 phys_addr; + __u8 data[8]; + __u32 len; + __u8 is_write; + } iocsr_io; + /* KVM_EXIT_HYPERCALL */ + struct { + __u64 nr; + __u64 args[6]; + __u64 ret; + + union { +#ifndef __KERNEL__ + __u32 longmode; +#endif + __u64 flags; + }; + } hypercall; + /* KVM_EXIT_TPR_ACCESS */ + struct { + __u64 rip; + __u32 is_write; + __u32 pad; + } tpr_access; + /* KVM_EXIT_S390_SIEIC */ + struct { + __u8 icptcode; + __u16 ipa; + __u32 ipb; + } s390_sieic; + /* KVM_EXIT_S390_RESET */ + __u64 s390_reset_flags; + /* KVM_EXIT_S390_UCONTROL */ + struct { + __u64 trans_exc_code; + __u32 pgm_code; + } s390_ucontrol; + /* KVM_EXIT_DCR (deprecated) */ + struct { + __u32 dcrn; + __u32 data; + __u8 is_write; + } dcr; + /* KVM_EXIT_INTERNAL_ERROR */ + struct { + __u32 suberror; + /* Available with KVM_CAP_INTERNAL_ERROR_DATA: */ + __u32 ndata; + __u64 data[16]; + } internal; + /* + * KVM_INTERNAL_ERROR_EMULATION + * + * "struct emulation_failure" is an overlay of "struct internal" + * that is used for the KVM_INTERNAL_ERROR_EMULATION sub-type of + * KVM_EXIT_INTERNAL_ERROR. Note, unlike other internal error + * sub-types, this struct is ABI! It also needs to be backwards + * compatible with "struct internal". Take special care that + * "ndata" is correct, that new fields are enumerated in "flags", + * and that each flag enumerates fields that are 64-bit aligned + * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! + */ + struct { + __u32 suberror; + __u32 ndata; + __u64 flags; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; + /* Arbitrary debug data may follow. */ + } emulation_failure; + /* KVM_EXIT_OSI */ + struct { + __u64 gprs[32]; + } osi; + /* KVM_EXIT_PAPR_HCALL */ + struct { + __u64 nr; + __u64 ret; + __u64 args[9]; + } papr_hcall; + /* KVM_EXIT_S390_TSCH */ + struct { + __u16 subchannel_id; + __u16 subchannel_nr; + __u32 io_int_parm; + __u32 io_int_word; + __u32 ipb; + __u8 dequeued; + } s390_tsch; + /* KVM_EXIT_EPR */ + struct { + __u32 epr; + } epr; + /* KVM_EXIT_SYSTEM_EVENT */ + struct { +#define KVM_SYSTEM_EVENT_SHUTDOWN 1 +#define KVM_SYSTEM_EVENT_RESET 2 +#define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 +#define KVM_SYSTEM_EVENT_SEV_TERM 6 +#define KVM_SYSTEM_EVENT_TDX_FATAL 7 + __u32 type; + __u32 ndata; + union { +#ifndef __KERNEL__ + __u64 flags; +#endif + __u64 data[16]; + }; + } system_event; + /* KVM_EXIT_S390_STSI */ + struct { + __u64 addr; + __u8 ar; + __u8 reserved; + __u8 fc; + __u8 sel1; + __u16 sel2; + } s390_stsi; + /* KVM_EXIT_IOAPIC_EOI */ + struct { + __u8 vector; + } eoi; + /* KVM_EXIT_HYPERV */ + struct kvm_hyperv_exit hyperv; + /* KVM_EXIT_ARM_NISV / KVM_EXIT_ARM_LDST64B */ + struct { + __u64 esr_iss; + __u64 fault_ipa; + } arm_nisv; + /* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */ + struct { + __u8 error; /* user -> kernel */ + __u8 pad[7]; +#define KVM_MSR_EXIT_REASON_INVAL (1 << 0) +#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1) +#define KVM_MSR_EXIT_REASON_FILTER (1 << 2) +#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \ + KVM_MSR_EXIT_REASON_UNKNOWN | \ + KVM_MSR_EXIT_REASON_FILTER) + __u32 reason; /* kernel -> user */ + __u32 index; /* kernel -> user */ + __u64 data; /* kernel <-> user */ + } msr; + /* KVM_EXIT_XEN */ + struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; + /* KVM_EXIT_RISCV_CSR */ + struct { + unsigned long csr_num; + unsigned long new_value; + unsigned long write_mask; + unsigned long ret_value; + } riscv_csr; + /* KVM_EXIT_NOTIFY */ + struct { +#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) + __u32 flags; + } notify; + /* KVM_EXIT_MEMORY_FAULT */ + struct { +#define KVM_MEMORY_EXIT_FLAG_PRIVATE (1ULL << 3) + __u64 flags; + __u64 gpa; + __u64 size; + } memory_fault; + /* KVM_EXIT_TDX */ + struct { + __u64 flags; + __u64 nr; + union { + struct { + __u64 ret; + __u64 data[5]; + } unknown; + struct { + __u64 ret; + __u64 gpa; + __u64 size; + } get_quote; + struct { + __u64 ret; + __u64 leaf; + __u64 r11, r12, r13, r14; + } get_tdvmcall_info; + struct { + __u64 ret; + __u64 vector; + } setup_event_notify; + }; + } tdx; + /* KVM_EXIT_ARM_SEA */ + struct { +#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID (1ULL << 0) + __u64 flags; + __u64 esr; + __u64 gva; + __u64 gpa; + } arm_sea; + /* KVM_EXIT_SNP_REQ_CERTS */ + struct kvm_exit_snp_req_certs snp_req_certs; + /* Fix the size of the union. */ + char padding[256]; + }; + + /* 2048 is the size of the char array used to bound/pad the size + * of the union that holds sync regs. + */ + #define SYNC_REGS_SIZE_BYTES 2048 + /* + * shared registers between kvm and userspace. + * kvm_valid_regs specifies the register classes set by the host + * kvm_dirty_regs specified the register classes dirtied by userspace + * struct kvm_sync_regs is architecture specific, as well as the + * bits for kvm_valid_regs and kvm_dirty_regs + */ + __u64 kvm_valid_regs; + __u64 kvm_dirty_regs; + union { + struct kvm_sync_regs regs; + char padding[SYNC_REGS_SIZE_BYTES]; + } s; +}; + +/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */ + +struct kvm_coalesced_mmio_zone { + __u64 addr; + __u32 size; + union { + __u32 pad; + __u32 pio; + }; +}; + +struct kvm_coalesced_mmio { + __u64 phys_addr; + __u32 len; + union { + __u32 pad; + __u32 pio; + }; + __u8 data[8]; +}; + +struct kvm_coalesced_mmio_ring { + __u32 first, last; + __DECLARE_FLEX_ARRAY(struct kvm_coalesced_mmio, coalesced_mmio); +}; + +#define KVM_COALESCED_MMIO_MAX \ + ((PAGE_SIZE - sizeof(struct kvm_coalesced_mmio_ring)) / \ + sizeof(struct kvm_coalesced_mmio)) + +/* for KVM_TRANSLATE */ +struct kvm_translation { + /* in */ + __u64 linear_address; + + /* out */ + __u64 physical_address; + __u8 valid; + __u8 writeable; + __u8 usermode; + __u8 pad[5]; +}; + +/* for KVM_INTERRUPT */ +struct kvm_interrupt { + /* in */ + __u32 irq; +}; + +/* for KVM_GET_DIRTY_LOG */ +struct kvm_dirty_log { + __u32 slot; + __u32 padding1; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +/* for KVM_CLEAR_DIRTY_LOG */ +struct kvm_clear_dirty_log { + __u32 slot; + __u32 num_pages; + __u64 first_page; + union { + void __user *dirty_bitmap; /* one bit per page */ + __u64 padding2; + }; +}; + +/* for KVM_SET_SIGNAL_MASK */ +struct kvm_signal_mask { + __u32 len; + __DECLARE_FLEX_ARRAY(__u8, sigset); +}; + +/* for KVM_TPR_ACCESS_REPORTING */ +struct kvm_tpr_access_ctl { + __u32 enabled; + __u32 flags; + __u32 reserved[8]; +}; + +/* for KVM_SET_VAPIC_ADDR */ +struct kvm_vapic_addr { + __u64 vapic_addr; +}; + +/* for KVM_SET_MP_STATE */ + +/* not all states are valid on all architectures */ +#define KVM_MP_STATE_RUNNABLE 0 +#define KVM_MP_STATE_UNINITIALIZED 1 +#define KVM_MP_STATE_INIT_RECEIVED 2 +#define KVM_MP_STATE_HALTED 3 +#define KVM_MP_STATE_SIPI_RECEIVED 4 +#define KVM_MP_STATE_STOPPED 5 +#define KVM_MP_STATE_CHECK_STOP 6 +#define KVM_MP_STATE_OPERATING 7 +#define KVM_MP_STATE_LOAD 8 +#define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 + +struct kvm_mp_state { + __u32 mp_state; +}; + +/* for KVM_SET_GUEST_DEBUG */ + +#define KVM_GUESTDBG_ENABLE 0x00000001 +#define KVM_GUESTDBG_SINGLESTEP 0x00000002 + +struct kvm_guest_debug { + __u32 control; + __u32 pad; + struct kvm_guest_debug_arch arch; +}; + +enum { + kvm_ioeventfd_flag_nr_datamatch, + kvm_ioeventfd_flag_nr_pio, + kvm_ioeventfd_flag_nr_deassign, + kvm_ioeventfd_flag_nr_virtio_ccw_notify, + kvm_ioeventfd_flag_nr_fast_mmio, + kvm_ioeventfd_flag_nr_max, +}; + +#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch) +#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio) +#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign) +#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \ + (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify) + +#define KVM_IOEVENTFD_VALID_FLAG_MASK ((1 << kvm_ioeventfd_flag_nr_max) - 1) + +struct kvm_ioeventfd { + __u64 datamatch; + __u64 addr; /* legal pio/mmio address */ + __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */ + __s32 fd; + __u32 flags; + __u8 pad[36]; +}; + +#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) +#define KVM_X86_DISABLE_EXITS_HLT (1 << 1) +#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) +#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3) +#define KVM_X86_DISABLE_EXITS_APERFMPERF (1 << 4) + +/* for KVM_ENABLE_CAP */ +struct kvm_enable_cap { + /* in */ + __u32 cap; + __u32 flags; + __u64 args[4]; + __u8 pad[64]; +}; + +#define KVMIO 0xAE + +/* machine type bits, to be used as argument to KVM_CREATE_VM */ +#define KVM_VM_S390_UCONTROL 1 + +/* on ppc, 0 indicate default, 1 should force HV and 2 PR */ +#define KVM_VM_PPC_HV 1 +#define KVM_VM_PPC_PR 2 + +/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */ +#define KVM_VM_MIPS_AUTO 0 +#define KVM_VM_MIPS_VZ 1 +#define KVM_VM_MIPS_TE 2 + +#define KVM_S390_SIE_PAGE_OFFSET 1 + +/* + * On arm64, machine type can be used to request the physical + * address size for the VM. Bits[7-0] are reserved for the guest + * PA size shift (i.e, log2(PA_Size)). For backward compatibility, + * value 0 implies the default IPA size, 40bits. + */ +#define KVM_VM_TYPE_ARM_IPA_SIZE_MASK 0xffULL +#define KVM_VM_TYPE_ARM_IPA_SIZE(x) \ + ((x) & KVM_VM_TYPE_ARM_IPA_SIZE_MASK) + +#define KVM_VM_TYPE_ARM_PROTECTED (1UL << 31) +#define KVM_VM_TYPE_ARM_MASK (KVM_VM_TYPE_ARM_IPA_SIZE_MASK | \ + KVM_VM_TYPE_ARM_PROTECTED) + +/* + * ioctls for /dev/kvm fds: + */ +#define KVM_GET_API_VERSION _IO(KVMIO, 0x00) +#define KVM_CREATE_VM _IO(KVMIO, 0x01) /* returns a VM fd */ +#define KVM_GET_MSR_INDEX_LIST _IOWR(KVMIO, 0x02, struct kvm_msr_list) + +#define KVM_S390_ENABLE_SIE _IO(KVMIO, 0x06) +/* + * Check if a kvm extension is available. Argument is extension number, + * return is 1 (yes) or 0 (no, sorry). + */ +#define KVM_CHECK_EXTENSION _IO(KVMIO, 0x03) +/* + * Get size for mmap(vcpu_fd) + */ +#define KVM_GET_VCPU_MMAP_SIZE _IO(KVMIO, 0x04) /* in bytes */ +#define KVM_GET_SUPPORTED_CPUID _IOWR(KVMIO, 0x05, struct kvm_cpuid2) +#define KVM_GET_EMULATED_CPUID _IOWR(KVMIO, 0x09, struct kvm_cpuid2) +#define KVM_GET_MSR_FEATURE_INDEX_LIST _IOWR(KVMIO, 0x0a, struct kvm_msr_list) + +/* + * Extension capability list. + */ +#define KVM_CAP_IRQCHIP 0 +#define KVM_CAP_HLT 1 +#define KVM_CAP_MMU_SHADOW_CACHE_CONTROL 2 +#define KVM_CAP_USER_MEMORY 3 +#define KVM_CAP_SET_TSS_ADDR 4 +#define KVM_CAP_VAPIC 6 +#define KVM_CAP_EXT_CPUID 7 +#define KVM_CAP_CLOCKSOURCE 8 +#define KVM_CAP_NR_VCPUS 9 /* returns recommended max vcpus per vm */ +#define KVM_CAP_NR_MEMSLOTS 10 /* returns max memory slots per vm */ +#define KVM_CAP_PIT 11 +#define KVM_CAP_NOP_IO_DELAY 12 +#define KVM_CAP_PV_MMU 13 +#define KVM_CAP_MP_STATE 14 +#define KVM_CAP_COALESCED_MMIO 15 +#define KVM_CAP_SYNC_MMU 16 /* Changes to host mmap are reflected in guest */ +#define KVM_CAP_IOMMU 18 +/* Bug in KVM_SET_USER_MEMORY_REGION fixed: */ +#define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21 +#define KVM_CAP_USER_NMI 22 +#define KVM_CAP_SET_GUEST_DEBUG 23 +#ifdef __KVM_HAVE_PIT +#define KVM_CAP_REINJECT_CONTROL 24 +#endif +#define KVM_CAP_IRQ_ROUTING 25 +#define KVM_CAP_IRQ_INJECT_STATUS 26 +#define KVM_CAP_ASSIGN_DEV_IRQ 29 +/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */ +#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30 +#ifdef __KVM_HAVE_MCE +#define KVM_CAP_MCE 31 +#endif +#define KVM_CAP_IRQFD 32 +#ifdef __KVM_HAVE_PIT +#define KVM_CAP_PIT2 33 +#endif +#define KVM_CAP_SET_BOOT_CPU_ID 34 +#ifdef __KVM_HAVE_PIT_STATE2 +#define KVM_CAP_PIT_STATE2 35 +#endif +#define KVM_CAP_IOEVENTFD 36 +#define KVM_CAP_SET_IDENTITY_MAP_ADDR 37 +#ifdef __KVM_HAVE_XEN_HVM +#define KVM_CAP_XEN_HVM 38 +#endif +#define KVM_CAP_ADJUST_CLOCK 39 +#define KVM_CAP_INTERNAL_ERROR_DATA 40 +#ifdef __KVM_HAVE_VCPU_EVENTS +#define KVM_CAP_VCPU_EVENTS 41 +#endif +#define KVM_CAP_S390_PSW 42 +#define KVM_CAP_PPC_SEGSTATE 43 +#define KVM_CAP_HYPERV 44 +#define KVM_CAP_HYPERV_VAPIC 45 +#define KVM_CAP_HYPERV_SPIN 46 +#define KVM_CAP_PCI_SEGMENT 47 +#define KVM_CAP_PPC_PAIRED_SINGLES 48 +#define KVM_CAP_INTR_SHADOW 49 +#ifdef __KVM_HAVE_DEBUGREGS +#define KVM_CAP_DEBUGREGS 50 +#endif +#define KVM_CAP_X86_ROBUST_SINGLESTEP 51 +#define KVM_CAP_PPC_OSI 52 +#define KVM_CAP_PPC_UNSET_IRQ 53 +#define KVM_CAP_ENABLE_CAP 54 +#ifdef __KVM_HAVE_XSAVE +#define KVM_CAP_XSAVE 55 +#endif +#ifdef __KVM_HAVE_XCRS +#define KVM_CAP_XCRS 56 +#endif +#define KVM_CAP_PPC_GET_PVINFO 57 +#define KVM_CAP_PPC_IRQ_LEVEL 58 +#define KVM_CAP_ASYNC_PF 59 +#define KVM_CAP_TSC_CONTROL 60 +#define KVM_CAP_GET_TSC_KHZ 61 +#define KVM_CAP_PPC_BOOKE_SREGS 62 +#define KVM_CAP_SPAPR_TCE 63 +#define KVM_CAP_PPC_SMT 64 +#define KVM_CAP_PPC_RMA 65 +#define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ +#define KVM_CAP_PPC_HIOR 67 +#define KVM_CAP_PPC_PAPR 68 +#define KVM_CAP_SW_TLB 69 +#define KVM_CAP_ONE_REG 70 +#define KVM_CAP_S390_GMAP 71 +#define KVM_CAP_TSC_DEADLINE_TIMER 72 +#define KVM_CAP_S390_UCONTROL 73 +#define KVM_CAP_SYNC_REGS 74 +#define KVM_CAP_PCI_2_3 75 +#define KVM_CAP_KVMCLOCK_CTRL 76 +#define KVM_CAP_SIGNAL_MSI 77 +#define KVM_CAP_PPC_GET_SMMU_INFO 78 +#define KVM_CAP_S390_COW 79 +#define KVM_CAP_PPC_ALLOC_HTAB 80 +#define KVM_CAP_READONLY_MEM 81 +#define KVM_CAP_IRQFD_RESAMPLE 82 +#define KVM_CAP_PPC_BOOKE_WATCHDOG 83 +#define KVM_CAP_PPC_HTAB_FD 84 +#define KVM_CAP_S390_CSS_SUPPORT 85 +#define KVM_CAP_PPC_EPR 86 +#define KVM_CAP_ARM_PSCI 87 +#define KVM_CAP_ARM_SET_DEVICE_ADDR 88 +#define KVM_CAP_DEVICE_CTRL 89 +#define KVM_CAP_IRQ_MPIC 90 +#define KVM_CAP_PPC_RTAS 91 +#define KVM_CAP_IRQ_XICS 92 +#define KVM_CAP_ARM_EL1_32BIT 93 +#define KVM_CAP_SPAPR_MULTITCE 94 +#define KVM_CAP_EXT_EMUL_CPUID 95 +#define KVM_CAP_HYPERV_TIME 96 +#define KVM_CAP_IOAPIC_POLARITY_IGNORED 97 +#define KVM_CAP_ENABLE_CAP_VM 98 +#define KVM_CAP_S390_IRQCHIP 99 +#define KVM_CAP_IOEVENTFD_NO_LENGTH 100 +#define KVM_CAP_VM_ATTRIBUTES 101 +#define KVM_CAP_ARM_PSCI_0_2 102 +#define KVM_CAP_PPC_FIXUP_HCALL 103 +#define KVM_CAP_PPC_ENABLE_HCALL 104 +#define KVM_CAP_CHECK_EXTENSION_VM 105 +#define KVM_CAP_S390_USER_SIGP 106 +#define KVM_CAP_S390_VECTOR_REGISTERS 107 +#define KVM_CAP_S390_MEM_OP 108 +#define KVM_CAP_S390_USER_STSI 109 +#define KVM_CAP_S390_SKEYS 110 +#define KVM_CAP_MIPS_FPU 111 +#define KVM_CAP_MIPS_MSA 112 +#define KVM_CAP_S390_INJECT_IRQ 113 +#define KVM_CAP_S390_IRQ_STATE 114 +#define KVM_CAP_PPC_HWRNG 115 +#define KVM_CAP_DISABLE_QUIRKS 116 +#define KVM_CAP_X86_SMM 117 +#define KVM_CAP_MULTI_ADDRESS_SPACE 118 +#define KVM_CAP_GUEST_DEBUG_HW_BPS 119 +#define KVM_CAP_GUEST_DEBUG_HW_WPS 120 +#define KVM_CAP_SPLIT_IRQCHIP 121 +#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122 +#define KVM_CAP_HYPERV_SYNIC 123 +#define KVM_CAP_S390_RI 124 +#define KVM_CAP_SPAPR_TCE_64 125 +#define KVM_CAP_ARM_PMU_V3 126 +#define KVM_CAP_VCPU_ATTRIBUTES 127 +#define KVM_CAP_MAX_VCPU_ID 128 +#define KVM_CAP_X2APIC_API 129 +#define KVM_CAP_S390_USER_INSTR0 130 +#define KVM_CAP_MSI_DEVID 131 +#define KVM_CAP_PPC_HTM 132 +#define KVM_CAP_SPAPR_RESIZE_HPT 133 +#define KVM_CAP_PPC_MMU_RADIX 134 +#define KVM_CAP_PPC_MMU_HASH_V3 135 +#define KVM_CAP_IMMEDIATE_EXIT 136 +#define KVM_CAP_MIPS_VZ 137 +#define KVM_CAP_MIPS_TE 138 +#define KVM_CAP_MIPS_64BIT 139 +#define KVM_CAP_S390_GS 140 +#define KVM_CAP_S390_AIS 141 +#define KVM_CAP_SPAPR_TCE_VFIO 142 +#define KVM_CAP_X86_DISABLE_EXITS 143 +#define KVM_CAP_ARM_USER_IRQ 144 +#define KVM_CAP_S390_CMMA_MIGRATION 145 +#define KVM_CAP_PPC_FWNMI 146 +#define KVM_CAP_PPC_SMT_POSSIBLE 147 +#define KVM_CAP_HYPERV_SYNIC2 148 +#define KVM_CAP_HYPERV_VP_INDEX 149 +#define KVM_CAP_S390_AIS_MIGRATION 150 +#define KVM_CAP_PPC_GET_CPU_CHAR 151 +#define KVM_CAP_S390_BPB 152 +#define KVM_CAP_GET_MSR_FEATURES 153 +#define KVM_CAP_HYPERV_EVENTFD 154 +#define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 +#define KVM_CAP_NESTED_STATE 157 +#define KVM_CAP_ARM_INJECT_SERROR_ESR 158 +#define KVM_CAP_MSR_PLATFORM_INFO 159 +#define KVM_CAP_PPC_NESTED_HV 160 +#define KVM_CAP_HYPERV_SEND_IPI 161 +#define KVM_CAP_COALESCED_PIO 162 +#define KVM_CAP_HYPERV_ENLIGHTENED_VMCS 163 +#define KVM_CAP_EXCEPTION_PAYLOAD 164 +#define KVM_CAP_ARM_VM_IPA_SIZE 165 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT 166 /* Obsolete */ +#define KVM_CAP_HYPERV_CPUID 167 +#define KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 168 +#define KVM_CAP_PPC_IRQ_XIVE 169 +#define KVM_CAP_ARM_SVE 170 +#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171 +#define KVM_CAP_ARM_PTRAUTH_GENERIC 172 +#define KVM_CAP_PMU_EVENT_FILTER 173 +#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174 +#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 +#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176 +#define KVM_CAP_ARM_NISV_TO_USER 177 +#define KVM_CAP_ARM_INJECT_EXT_DABT 178 +#define KVM_CAP_S390_VCPU_RESETS 179 +#define KVM_CAP_S390_PROTECTED 180 +#define KVM_CAP_PPC_SECURE_GUEST 181 +#define KVM_CAP_HALT_POLL 182 +#define KVM_CAP_ASYNC_PF_INT 183 +#define KVM_CAP_LAST_CPU 184 +#define KVM_CAP_SMALLER_MAXPHYADDR 185 +#define KVM_CAP_S390_DIAG318 186 +#define KVM_CAP_STEAL_TIME 187 +#define KVM_CAP_X86_USER_SPACE_MSR 188 +#define KVM_CAP_X86_MSR_FILTER 189 +#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190 +#define KVM_CAP_SYS_HYPERV_CPUID 191 +#define KVM_CAP_DIRTY_LOG_RING 192 +#define KVM_CAP_X86_BUS_LOCK_EXIT 193 +#define KVM_CAP_PPC_DAWR1 194 +#define KVM_CAP_SET_GUEST_DEBUG2 195 +#define KVM_CAP_SGX_ATTRIBUTE 196 +#define KVM_CAP_VM_COPY_ENC_CONTEXT_FROM 197 +#define KVM_CAP_PTP_KVM 198 +#define KVM_CAP_HYPERV_ENFORCE_CPUID 199 +#define KVM_CAP_SREGS2 200 +#define KVM_CAP_EXIT_HYPERCALL 201 +#define KVM_CAP_PPC_RPT_INVALIDATE 202 +#define KVM_CAP_BINARY_STATS_FD 203 +#define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 +#define KVM_CAP_ARM_MTE 205 +#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 +#define KVM_CAP_VM_GPA_BITS 207 +#define KVM_CAP_XSAVE2 208 +#define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 +#define KVM_CAP_S390_MEM_OP_EXTENSION 211 +#define KVM_CAP_PMU_CAPABILITY 212 +#define KVM_CAP_DISABLE_QUIRKS2 213 +#define KVM_CAP_VM_TSC_CONTROL 214 +#define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_PROTECTED_DUMP 217 +#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218 +#define KVM_CAP_X86_NOTIFY_VMEXIT 219 +#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 +#define KVM_CAP_S390_ZPCI_OP 221 +#define KVM_CAP_S390_CPU_TOPOLOGY 222 +#define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 +#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 +#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 +#define KVM_CAP_COUNTER_OFFSET 227 +#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228 +#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 +#define KVM_CAP_ARM_SUPPORTED_REG_MASK_RANGES 230 +#define KVM_CAP_USER_MEMORY2 231 +#define KVM_CAP_MEMORY_FAULT_INFO 232 +#define KVM_CAP_MEMORY_ATTRIBUTES 233 +#define KVM_CAP_GUEST_MEMFD 234 +#define KVM_CAP_VM_TYPES 235 +#define KVM_CAP_PRE_FAULT_MEMORY 236 +#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237 +#define KVM_CAP_X86_GUEST_MODE 238 +#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239 +#define KVM_CAP_ARM_EL2 240 +#define KVM_CAP_ARM_EL2_E2H0 241 +#define KVM_CAP_RISCV_MP_STATE_RESET 242 +#define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 +#define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_ARM_SEA_TO_USER 245 +#define KVM_CAP_S390_USER_OPEREXEC 246 +#define KVM_CAP_S390_KEYOP 247 +#define KVM_CAP_S390_VSIE_ESAMODE 248 +#define KVM_CAP_S390_HPAGE_2G 249 + +struct kvm_irq_routing_irqchip { + __u32 irqchip; + __u32 pin; +}; + +struct kvm_irq_routing_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + union { + __u32 pad; + __u32 devid; + }; +}; + +struct kvm_irq_routing_s390_adapter { + __u64 ind_addr; + __u64 summary_addr; + __u64 ind_offset; + __u32 summary_offset; + __u32 adapter_id; +}; + +struct kvm_irq_routing_hv_sint { + __u32 vcpu; + __u32 sint; +}; + +struct kvm_irq_routing_xen_evtchn { + __u32 port; + __u32 vcpu; + __u32 priority; +}; + +#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1)) + +/* gsi routing entry types */ +#define KVM_IRQ_ROUTING_IRQCHIP 1 +#define KVM_IRQ_ROUTING_MSI 2 +#define KVM_IRQ_ROUTING_S390_ADAPTER 3 +#define KVM_IRQ_ROUTING_HV_SINT 4 +#define KVM_IRQ_ROUTING_XEN_EVTCHN 5 + +struct kvm_irq_routing_entry { + __u32 gsi; + __u32 type; + __u32 flags; + __u32 pad; + union { + struct kvm_irq_routing_irqchip irqchip; + struct kvm_irq_routing_msi msi; + struct kvm_irq_routing_s390_adapter adapter; + struct kvm_irq_routing_hv_sint hv_sint; + struct kvm_irq_routing_xen_evtchn xen_evtchn; + __u32 pad[8]; + } u; +}; + +struct kvm_irq_routing { + __u32 nr; + __u32 flags; + __DECLARE_FLEX_ARRAY(struct kvm_irq_routing_entry, entries); +}; + +#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0) +/* + * Available with KVM_CAP_IRQFD_RESAMPLE + * + * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies + * the irqfd to operate in resampling mode for level triggered interrupt + * emulation. See Documentation/virt/kvm/api.rst. + */ +#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) + +struct kvm_irqfd { + __u32 fd; + __u32 gsi; + __u32 flags; + __u32 resamplefd; + __u8 pad[16]; +}; + +/* For KVM_CAP_ADJUST_CLOCK */ + +/* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ +#define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) + +struct kvm_clock_data { + __u64 clock; + __u32 flags; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; +}; + +/* For KVM_CAP_SW_TLB */ + +#define KVM_MMU_FSL_BOOKE_NOHV 0 +#define KVM_MMU_FSL_BOOKE_HV 1 + +struct kvm_config_tlb { + __u64 params; + __u64 array; + __u32 mmu_type; + __u32 array_len; +}; + +struct kvm_dirty_tlb { + __u64 bitmap; + __u32 num_dirty; +}; + +/* Available with KVM_CAP_ONE_REG */ + +#define KVM_REG_ARCH_MASK 0xff00000000000000ULL +#define KVM_REG_GENERIC 0x0000000000000000ULL + +/* + * Architecture specific registers are to be defined in arch headers and + * ORed with the arch identifier. + */ +#define KVM_REG_PPC 0x1000000000000000ULL +#define KVM_REG_X86 0x2000000000000000ULL +#define KVM_REG_IA64 0x3000000000000000ULL +#define KVM_REG_ARM 0x4000000000000000ULL +#define KVM_REG_S390 0x5000000000000000ULL +#define KVM_REG_ARM64 0x6000000000000000ULL +#define KVM_REG_MIPS 0x7000000000000000ULL +#define KVM_REG_RISCV 0x8000000000000000ULL +#define KVM_REG_LOONGARCH 0x9000000000000000ULL + +#define KVM_REG_SIZE_SHIFT 52 +#define KVM_REG_SIZE_MASK 0x00f0000000000000ULL + +#define KVM_REG_SIZE(id) \ + (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) + +#define KVM_REG_SIZE_U8 0x0000000000000000ULL +#define KVM_REG_SIZE_U16 0x0010000000000000ULL +#define KVM_REG_SIZE_U32 0x0020000000000000ULL +#define KVM_REG_SIZE_U64 0x0030000000000000ULL +#define KVM_REG_SIZE_U128 0x0040000000000000ULL +#define KVM_REG_SIZE_U256 0x0050000000000000ULL +#define KVM_REG_SIZE_U512 0x0060000000000000ULL +#define KVM_REG_SIZE_U1024 0x0070000000000000ULL +#define KVM_REG_SIZE_U2048 0x0080000000000000ULL + +struct kvm_reg_list { + __u64 n; /* number of regs */ + __DECLARE_FLEX_ARRAY(__u64, reg); +}; + +struct kvm_one_reg { + __u64 id; + __u64 addr; +}; + +#define KVM_MSI_VALID_DEVID (1U << 0) +struct kvm_msi { + __u32 address_lo; + __u32 address_hi; + __u32 data; + __u32 flags; + __u32 devid; + __u8 pad[12]; +}; + +struct kvm_arm_device_addr { + __u64 id; + __u64 addr; +}; + +/* + * Device control API, available with KVM_CAP_DEVICE_CTRL + */ +#define KVM_CREATE_DEVICE_TEST 1 + +struct kvm_create_device { + __u32 type; /* in: KVM_DEV_TYPE_xxx */ + __u32 fd; /* out: device handle */ + __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */ +}; + +struct kvm_device_attr { + __u32 flags; /* no flags currently defined */ + __u32 group; /* device-defined */ + __u64 attr; /* group-defined */ + __u64 addr; /* userspace address of attr data */ +}; + +#define KVM_DEV_VFIO_FILE 1 + +#define KVM_DEV_VFIO_FILE_ADD 1 +#define KVM_DEV_VFIO_FILE_DEL 2 + +/* KVM_DEV_VFIO_GROUP aliases are for compile time uapi compatibility */ +#define KVM_DEV_VFIO_GROUP KVM_DEV_VFIO_FILE + +#define KVM_DEV_VFIO_GROUP_ADD KVM_DEV_VFIO_FILE_ADD +#define KVM_DEV_VFIO_GROUP_DEL KVM_DEV_VFIO_FILE_DEL +#define KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE 3 + +enum kvm_device_type { + KVM_DEV_TYPE_FSL_MPIC_20 = 1, +#define KVM_DEV_TYPE_FSL_MPIC_20 KVM_DEV_TYPE_FSL_MPIC_20 + KVM_DEV_TYPE_FSL_MPIC_42, +#define KVM_DEV_TYPE_FSL_MPIC_42 KVM_DEV_TYPE_FSL_MPIC_42 + KVM_DEV_TYPE_XICS, +#define KVM_DEV_TYPE_XICS KVM_DEV_TYPE_XICS + KVM_DEV_TYPE_VFIO, +#define KVM_DEV_TYPE_VFIO KVM_DEV_TYPE_VFIO + KVM_DEV_TYPE_ARM_VGIC_V2, +#define KVM_DEV_TYPE_ARM_VGIC_V2 KVM_DEV_TYPE_ARM_VGIC_V2 + KVM_DEV_TYPE_FLIC, +#define KVM_DEV_TYPE_FLIC KVM_DEV_TYPE_FLIC + KVM_DEV_TYPE_ARM_VGIC_V3, +#define KVM_DEV_TYPE_ARM_VGIC_V3 KVM_DEV_TYPE_ARM_VGIC_V3 + KVM_DEV_TYPE_ARM_VGIC_ITS, +#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS + KVM_DEV_TYPE_XIVE, +#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE + KVM_DEV_TYPE_ARM_PV_TIME, +#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME + KVM_DEV_TYPE_RISCV_AIA, +#define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA + KVM_DEV_TYPE_LOONGARCH_IPI, +#define KVM_DEV_TYPE_LOONGARCH_IPI KVM_DEV_TYPE_LOONGARCH_IPI + KVM_DEV_TYPE_LOONGARCH_EIOINTC, +#define KVM_DEV_TYPE_LOONGARCH_EIOINTC KVM_DEV_TYPE_LOONGARCH_EIOINTC + KVM_DEV_TYPE_LOONGARCH_PCHPIC, +#define KVM_DEV_TYPE_LOONGARCH_PCHPIC KVM_DEV_TYPE_LOONGARCH_PCHPIC + KVM_DEV_TYPE_LOONGARCH_DMSINTC, +#define KVM_DEV_TYPE_LOONGARCH_DMSINTC KVM_DEV_TYPE_LOONGARCH_DMSINTC + KVM_DEV_TYPE_ARM_VGIC_V5, +#define KVM_DEV_TYPE_ARM_VGIC_V5 KVM_DEV_TYPE_ARM_VGIC_V5 + + KVM_DEV_TYPE_MAX, + +}; + +struct kvm_vfio_spapr_tce { + __s32 groupfd; + __s32 tablefd; +}; + +#define KVM_S390_KEYOP_ISKE 0x01 +#define KVM_S390_KEYOP_RRBE 0x02 +#define KVM_S390_KEYOP_SSKE 0x03 +struct kvm_s390_keyop { + __u64 guest_addr; + __u8 key; + __u8 operation; + __u8 pad[6]; +}; + +/* + * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns + * a vcpu fd. + */ +#define KVM_CREATE_VCPU _IO(KVMIO, 0x41) +#define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) +#define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) +#define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) /* deprecated */ +#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ + struct kvm_userspace_memory_region) +#define KVM_SET_TSS_ADDR _IO(KVMIO, 0x47) +#define KVM_SET_IDENTITY_MAP_ADDR _IOW(KVMIO, 0x48, __u64) +#define KVM_SET_USER_MEMORY_REGION2 _IOW(KVMIO, 0x49, \ + struct kvm_userspace_memory_region2) + +/* enable ucontrol for s390 */ +#define KVM_S390_UCAS_MAP _IOW(KVMIO, 0x50, struct kvm_s390_ucas_mapping) +#define KVM_S390_UCAS_UNMAP _IOW(KVMIO, 0x51, struct kvm_s390_ucas_mapping) +#define KVM_S390_VCPU_FAULT _IOW(KVMIO, 0x52, unsigned long) +#define KVM_S390_KEYOP _IOWR(KVMIO, 0x53, struct kvm_s390_keyop) + +/* Device model IOC */ +#define KVM_CREATE_IRQCHIP _IO(KVMIO, 0x60) +#define KVM_IRQ_LINE _IOW(KVMIO, 0x61, struct kvm_irq_level) +#define KVM_GET_IRQCHIP _IOWR(KVMIO, 0x62, struct kvm_irqchip) +#define KVM_SET_IRQCHIP _IOR(KVMIO, 0x63, struct kvm_irqchip) +#define KVM_CREATE_PIT _IO(KVMIO, 0x64) +#define KVM_GET_PIT _IOWR(KVMIO, 0x65, struct kvm_pit_state) +#define KVM_SET_PIT _IOR(KVMIO, 0x66, struct kvm_pit_state) +#define KVM_IRQ_LINE_STATUS _IOWR(KVMIO, 0x67, struct kvm_irq_level) +#define KVM_REGISTER_COALESCED_MMIO \ + _IOW(KVMIO, 0x67, struct kvm_coalesced_mmio_zone) +#define KVM_UNREGISTER_COALESCED_MMIO \ + _IOW(KVMIO, 0x68, struct kvm_coalesced_mmio_zone) +#define KVM_SET_GSI_ROUTING _IOW(KVMIO, 0x6a, struct kvm_irq_routing) +#define KVM_REINJECT_CONTROL _IO(KVMIO, 0x71) +#define KVM_IRQFD _IOW(KVMIO, 0x76, struct kvm_irqfd) +#define KVM_CREATE_PIT2 _IOW(KVMIO, 0x77, struct kvm_pit_config) +#define KVM_SET_BOOT_CPU_ID _IO(KVMIO, 0x78) +#define KVM_IOEVENTFD _IOW(KVMIO, 0x79, struct kvm_ioeventfd) +#define KVM_XEN_HVM_CONFIG _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config) +#define KVM_SET_CLOCK _IOW(KVMIO, 0x7b, struct kvm_clock_data) +#define KVM_GET_CLOCK _IOR(KVMIO, 0x7c, struct kvm_clock_data) +/* Available with KVM_CAP_PIT_STATE2 */ +#define KVM_GET_PIT2 _IOR(KVMIO, 0x9f, struct kvm_pit_state2) +#define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) +/* Available with KVM_CAP_PPC_GET_PVINFO */ +#define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) +/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with +* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ +#define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) +#define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) +/* Available with KVM_CAP_SIGNAL_MSI */ +#define KVM_SIGNAL_MSI _IOW(KVMIO, 0xa5, struct kvm_msi) +/* Available with KVM_CAP_PPC_GET_SMMU_INFO */ +#define KVM_PPC_GET_SMMU_INFO _IOR(KVMIO, 0xa6, struct kvm_ppc_smmu_info) +/* Available with KVM_CAP_PPC_ALLOC_HTAB */ +#define KVM_PPC_ALLOCATE_HTAB _IOWR(KVMIO, 0xa7, __u32) +#define KVM_CREATE_SPAPR_TCE _IOW(KVMIO, 0xa8, struct kvm_create_spapr_tce) +#define KVM_CREATE_SPAPR_TCE_64 _IOW(KVMIO, 0xa8, \ + struct kvm_create_spapr_tce_64) +/* Available with KVM_CAP_RMA */ +#define KVM_ALLOCATE_RMA _IOR(KVMIO, 0xa9, struct kvm_allocate_rma) +/* Available with KVM_CAP_PPC_HTAB_FD */ +#define KVM_PPC_GET_HTAB_FD _IOW(KVMIO, 0xaa, struct kvm_get_htab_fd) +/* Available with KVM_CAP_ARM_SET_DEVICE_ADDR */ +#define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) +/* Available with KVM_CAP_PPC_RTAS */ +#define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args) +/* Available with KVM_CAP_SPAPR_RESIZE_HPT */ +#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) +#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) +/* Available with KVM_CAP_PPC_MMU_RADIX or KVM_CAP_PPC_MMU_HASH_V3 */ +#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) +/* Available with KVM_CAP_PPC_MMU_RADIX */ +#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) +/* Available with KVM_CAP_PPC_GET_CPU_CHAR */ +#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char) +/* Available with KVM_CAP_PMU_EVENT_FILTER */ +#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter) +#define KVM_PPC_SVM_OFF _IO(KVMIO, 0xb3) +#define KVM_ARM_MTE_COPY_TAGS _IOR(KVMIO, 0xb4, struct kvm_arm_copy_mte_tags) +/* Available with KVM_CAP_COUNTER_OFFSET */ +#define KVM_ARM_SET_COUNTER_OFFSET _IOW(KVMIO, 0xb5, struct kvm_arm_counter_offset) +#define KVM_ARM_GET_REG_WRITABLE_MASKS _IOR(KVMIO, 0xb6, struct reg_mask_range) + +/* ioctl for vm fd */ +#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) + +/* ioctls for fds returned by KVM_CREATE_DEVICE */ +#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xe1, struct kvm_device_attr) +#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xe2, struct kvm_device_attr) +#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xe3, struct kvm_device_attr) + +/* + * ioctls for vcpu fds + */ +#define KVM_RUN _IO(KVMIO, 0x80) +#define KVM_GET_REGS _IOR(KVMIO, 0x81, struct kvm_regs) +#define KVM_SET_REGS _IOW(KVMIO, 0x82, struct kvm_regs) +#define KVM_GET_SREGS _IOR(KVMIO, 0x83, struct kvm_sregs) +#define KVM_SET_SREGS _IOW(KVMIO, 0x84, struct kvm_sregs) +#define KVM_TRANSLATE _IOWR(KVMIO, 0x85, struct kvm_translation) +#define KVM_INTERRUPT _IOW(KVMIO, 0x86, struct kvm_interrupt) +#define KVM_GET_MSRS _IOWR(KVMIO, 0x88, struct kvm_msrs) +#define KVM_SET_MSRS _IOW(KVMIO, 0x89, struct kvm_msrs) +#define KVM_SET_CPUID _IOW(KVMIO, 0x8a, struct kvm_cpuid) +#define KVM_SET_SIGNAL_MASK _IOW(KVMIO, 0x8b, struct kvm_signal_mask) +#define KVM_GET_FPU _IOR(KVMIO, 0x8c, struct kvm_fpu) +#define KVM_SET_FPU _IOW(KVMIO, 0x8d, struct kvm_fpu) +#define KVM_GET_LAPIC _IOR(KVMIO, 0x8e, struct kvm_lapic_state) +#define KVM_SET_LAPIC _IOW(KVMIO, 0x8f, struct kvm_lapic_state) +#define KVM_SET_CPUID2 _IOW(KVMIO, 0x90, struct kvm_cpuid2) +#define KVM_GET_CPUID2 _IOWR(KVMIO, 0x91, struct kvm_cpuid2) +/* Available with KVM_CAP_VAPIC */ +#define KVM_TPR_ACCESS_REPORTING _IOWR(KVMIO, 0x92, struct kvm_tpr_access_ctl) +/* Available with KVM_CAP_VAPIC */ +#define KVM_SET_VAPIC_ADDR _IOW(KVMIO, 0x93, struct kvm_vapic_addr) +/* valid for virtual machine (for floating interrupt)_and_ vcpu */ +#define KVM_S390_INTERRUPT _IOW(KVMIO, 0x94, struct kvm_s390_interrupt) +/* store status for s390 */ +#define KVM_S390_STORE_STATUS_NOADDR (-1ul) +#define KVM_S390_STORE_STATUS_PREFIXED (-2ul) +#define KVM_S390_STORE_STATUS _IOW(KVMIO, 0x95, unsigned long) +/* initial ipl psw for s390 */ +#define KVM_S390_SET_INITIAL_PSW _IOW(KVMIO, 0x96, struct kvm_s390_psw) +/* initial reset for s390 */ +#define KVM_S390_INITIAL_RESET _IO(KVMIO, 0x97) +#define KVM_GET_MP_STATE _IOR(KVMIO, 0x98, struct kvm_mp_state) +#define KVM_SET_MP_STATE _IOW(KVMIO, 0x99, struct kvm_mp_state) +/* Available with KVM_CAP_USER_NMI */ +#define KVM_NMI _IO(KVMIO, 0x9a) +/* Available with KVM_CAP_SET_GUEST_DEBUG */ +#define KVM_SET_GUEST_DEBUG _IOW(KVMIO, 0x9b, struct kvm_guest_debug) +/* MCE for x86 */ +#define KVM_X86_SETUP_MCE _IOW(KVMIO, 0x9c, __u64) +#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO, 0x9d, __u64) +#define KVM_X86_SET_MCE _IOW(KVMIO, 0x9e, struct kvm_x86_mce) +/* Available with KVM_CAP_VCPU_EVENTS */ +#define KVM_GET_VCPU_EVENTS _IOR(KVMIO, 0x9f, struct kvm_vcpu_events) +#define KVM_SET_VCPU_EVENTS _IOW(KVMIO, 0xa0, struct kvm_vcpu_events) +/* Available with KVM_CAP_DEBUGREGS */ +#define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) +#define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) +/* + * vcpu version available with KVM_CAP_ENABLE_CAP + * vm version available with KVM_CAP_ENABLE_CAP_VM + */ +#define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) +/* Available with KVM_CAP_XSAVE */ +#define KVM_GET_XSAVE _IOR(KVMIO, 0xa4, struct kvm_xsave) +#define KVM_SET_XSAVE _IOW(KVMIO, 0xa5, struct kvm_xsave) +/* Available with KVM_CAP_XCRS */ +#define KVM_GET_XCRS _IOR(KVMIO, 0xa6, struct kvm_xcrs) +#define KVM_SET_XCRS _IOW(KVMIO, 0xa7, struct kvm_xcrs) +/* Available with KVM_CAP_SW_TLB */ +#define KVM_DIRTY_TLB _IOW(KVMIO, 0xaa, struct kvm_dirty_tlb) +/* Available with KVM_CAP_ONE_REG */ +#define KVM_GET_ONE_REG _IOW(KVMIO, 0xab, struct kvm_one_reg) +#define KVM_SET_ONE_REG _IOW(KVMIO, 0xac, struct kvm_one_reg) +/* VM is being stopped by host */ +#define KVM_KVMCLOCK_CTRL _IO(KVMIO, 0xad) +#define KVM_ARM_VCPU_INIT _IOW(KVMIO, 0xae, struct kvm_vcpu_init) +#define KVM_ARM_PREFERRED_TARGET _IOR(KVMIO, 0xaf, struct kvm_vcpu_init) +#define KVM_GET_REG_LIST _IOWR(KVMIO, 0xb0, struct kvm_reg_list) +/* Available with KVM_CAP_S390_MEM_OP */ +#define KVM_S390_MEM_OP _IOW(KVMIO, 0xb1, struct kvm_s390_mem_op) +/* Available with KVM_CAP_S390_SKEYS */ +#define KVM_S390_GET_SKEYS _IOW(KVMIO, 0xb2, struct kvm_s390_skeys) +#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys) +/* Available with KVM_CAP_S390_INJECT_IRQ */ +#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq) +/* Available with KVM_CAP_S390_IRQ_STATE */ +#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state) +#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state) +/* Available with KVM_CAP_X86_SMM */ +#define KVM_SMI _IO(KVMIO, 0xb7) +/* Available with KVM_CAP_S390_CMMA_MIGRATION */ +#define KVM_S390_GET_CMMA_BITS _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log) +#define KVM_S390_SET_CMMA_BITS _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log) +/* Memory Encryption Commands */ +#define KVM_MEMORY_ENCRYPT_OP _IOWR(KVMIO, 0xba, unsigned long) + +struct kvm_enc_region { + __u64 addr; + __u64 size; +}; + +#define KVM_MEMORY_ENCRYPT_REG_REGION _IOR(KVMIO, 0xbb, struct kvm_enc_region) +#define KVM_MEMORY_ENCRYPT_UNREG_REGION _IOR(KVMIO, 0xbc, struct kvm_enc_region) + +/* Available with KVM_CAP_HYPERV_EVENTFD */ +#define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd) + +/* Available with KVM_CAP_NESTED_STATE */ +#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) +#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) + +/* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */ +#define KVM_CLEAR_DIRTY_LOG _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log) + +/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */ +#define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2) + +/* Available with KVM_CAP_ARM_SVE */ +#define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) + +/* Available with KVM_CAP_S390_VCPU_RESETS */ +#define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) +#define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) + +/* Available with KVM_CAP_S390_PROTECTED */ +#define KVM_S390_PV_COMMAND _IOWR(KVMIO, 0xc5, struct kvm_pv_cmd) + +/* Available with KVM_CAP_X86_MSR_FILTER */ +#define KVM_X86_SET_MSR_FILTER _IOW(KVMIO, 0xc6, struct kvm_msr_filter) + +/* Available with KVM_CAP_DIRTY_LOG_RING */ +#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7) + +/* Per-VM Xen attributes */ +#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr) +#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr) + +/* Per-vCPU Xen attributes */ +#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) +#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn) + +#define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) +#define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) + +#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) +#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) + +/* + * Arch needs to define the macro after implementing the dirty ring + * feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the + * starting page offset of the dirty ring structures. + */ +#ifndef KVM_DIRTY_LOG_PAGE_OFFSET +#define KVM_DIRTY_LOG_PAGE_OFFSET 0 +#endif + +/* + * KVM dirty GFN flags, defined as: + * + * |---------------+---------------+--------------| + * | bit 1 (reset) | bit 0 (dirty) | Status | + * |---------------+---------------+--------------| + * | 0 | 0 | Invalid GFN | + * | 0 | 1 | Dirty GFN | + * | 1 | X | GFN to reset | + * |---------------+---------------+--------------| + * + * Lifecycle of a dirty GFN goes like: + * + * dirtied harvested reset + * 00 -----------> 01 -------------> 1X -------+ + * ^ | + * | | + * +------------------------------------------+ + * + * The userspace program is only responsible for the 01->1X state + * conversion after harvesting an entry. Also, it must not skip any + * dirty bits, so that dirty bits are always harvested in sequence. + */ +#define KVM_DIRTY_GFN_F_DIRTY _BITUL(0) +#define KVM_DIRTY_GFN_F_RESET _BITUL(1) +#define KVM_DIRTY_GFN_F_MASK 0x3 + +/* + * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of + * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn. The + * size of the gfn buffer is decided by the first argument when + * enabling KVM_CAP_DIRTY_LOG_RING. + */ +struct kvm_dirty_gfn { + __u32 flags; + __u32 slot; + __u64 offset; +}; + +#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0) +#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1) + +#define KVM_PMU_CAP_DISABLE (1 << 0) + +/** + * struct kvm_stats_header - Header of per vm/vcpu binary statistics data. + * @flags: Some extra information for header, always 0 for now. + * @name_size: The size in bytes of the memory which contains statistics + * name string including trailing '\0'. The memory is allocated + * at the send of statistics descriptor. + * @num_desc: The number of statistics the vm or vcpu has. + * @id_offset: The offset of the vm/vcpu stats' id string in the file pointed + * by vm/vcpu stats fd. + * @desc_offset: The offset of the vm/vcpu stats' descriptor block in the file + * pointd by vm/vcpu stats fd. + * @data_offset: The offset of the vm/vcpu stats' data block in the file + * pointed by vm/vcpu stats fd. + * + * This is the header userspace needs to read from stats fd before any other + * readings. It is used by userspace to discover all the information about the + * vm/vcpu's binary statistics. + * Userspace reads this header from the start of the vm/vcpu's stats fd. + */ +struct kvm_stats_header { + __u32 flags; + __u32 name_size; + __u32 num_desc; + __u32 id_offset; + __u32 desc_offset; + __u32 data_offset; +}; + +#define KVM_STATS_TYPE_SHIFT 0 +#define KVM_STATS_TYPE_MASK (0xF << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_CUMULATIVE (0x0 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_INSTANT (0x1 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_PEAK (0x2 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_LINEAR_HIST (0x3 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_LOG_HIST (0x4 << KVM_STATS_TYPE_SHIFT) +#define KVM_STATS_TYPE_MAX KVM_STATS_TYPE_LOG_HIST + +#define KVM_STATS_UNIT_SHIFT 4 +#define KVM_STATS_UNIT_MASK (0xF << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_NONE (0x0 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BYTES (0x1 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN + +#define KVM_STATS_BASE_SHIFT 8 +#define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW10 (0x0 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_POW2 (0x1 << KVM_STATS_BASE_SHIFT) +#define KVM_STATS_BASE_MAX KVM_STATS_BASE_POW2 + +/** + * struct kvm_stats_desc - Descriptor of a KVM statistics. + * @flags: Annotations of the stats, like type, unit, etc. + * @exponent: Used together with @flags to determine the unit. + * @size: The number of data items for this stats. + * Every data item is of type __u64. + * @offset: The offset of the stats to the start of stat structure in + * structure kvm or kvm_vcpu. + * @bucket_size: A parameter value used for histogram stats. It is only used + * for linear histogram stats, specifying the size of the bucket; + * @name: The name string for the stats. Its size is indicated by the + * &kvm_stats_header->name_size. + */ +struct kvm_stats_desc { + __u32 flags; + __s16 exponent; + __u16 size; + __u32 offset; + __u32 bucket_size; +#ifdef __KERNEL__ + char name[KVM_STATS_NAME_SIZE]; +#else + __DECLARE_FLEX_ARRAY(char, name); +#endif +}; + +#define KVM_GET_STATS_FD _IO(KVMIO, 0xce) + +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + +/* Available with KVM_CAP_S390_PROTECTED_DUMP */ +#define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd) + +/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */ +#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0) +#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1) + +/* Available with KVM_CAP_S390_ZPCI_OP */ +#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) + +/* Available with KVM_CAP_MEMORY_ATTRIBUTES */ +#define KVM_SET_MEMORY_ATTRIBUTES _IOW(KVMIO, 0xd2, struct kvm_memory_attributes) + +struct kvm_memory_attributes { + __u64 address; + __u64 size; + __u64 attributes; + __u64 flags; +}; + +#define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +#define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) +#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) + +struct kvm_create_guest_memfd { + __u64 size; + __u64 flags; + __u64 reserved[6]; +}; + +#define KVM_PRE_FAULT_MEMORY _IOWR(KVMIO, 0xd5, struct kvm_pre_fault_memory) + +struct kvm_pre_fault_memory { + __u64 gpa; + __u64 size; + __u64 flags; + __u64 padding[5]; +}; + +#endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/memfd.h b/tools/include/uapi/linux/memfd.h new file mode 100644 index 000000000..01c0324e7 --- /dev/null +++ b/tools/include/uapi/linux/memfd.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_MEMFD_H +#define _LINUX_MEMFD_H + +#include + +/* flags for memfd_create(2) (unsigned int) */ +#define MFD_CLOEXEC 0x0001U +#define MFD_ALLOW_SEALING 0x0002U +#define MFD_HUGETLB 0x0004U +/* not executable and sealed to prevent changing to executable. */ +#define MFD_NOEXEC_SEAL 0x0008U +/* executable */ +#define MFD_EXEC 0x0010U + +/* + * Huge page size encoding when MFD_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MFD_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MFD_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MFD_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MFD_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MFD_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB +#define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB +#define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + +#endif /* _LINUX_MEMFD_H */ diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h new file mode 100644 index 000000000..e89d00528 --- /dev/null +++ b/tools/include/uapi/linux/mman.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_MMAN_H +#define _UAPI_LINUX_MMAN_H + +#include +#include +#include + +#define MREMAP_MAYMOVE 1 +#define MREMAP_FIXED 2 +#define MREMAP_DONTUNMAP 4 + +#define OVERCOMMIT_GUESS 0 +#define OVERCOMMIT_ALWAYS 1 +#define OVERCOMMIT_NEVER 2 + +#define MAP_SHARED 0x01 /* Share changes */ +#define MAP_PRIVATE 0x02 /* Changes are private */ +#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */ +#define MAP_DROPPABLE 0x08 /* Zero memory under memory pressure. */ + +/* + * Huge page size encoding when MAP_HUGETLB is specified, and a huge page + * size other than the default is desired. See hugetlb_encode.h. + * All known huge page size encodings are provided here. It is the + * responsibility of the application to know which sizes are supported on + * the running system. See mmap(2) man page for details. + */ +#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT +#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK + +#define MAP_HUGE_16KB HUGETLB_FLAG_ENCODE_16KB +#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB +#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB +#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB +#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB +#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB +#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB +#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB +#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB +#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB +#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB + +struct cachestat_range { + __u64 off; + __u64 len; +}; + +struct cachestat { + __u64 nr_cache; + __u64 nr_dirty; + __u64 nr_writeback; + __u64 nr_evicted; + __u64 nr_recently_evicted; +}; + +#endif /* _UAPI_LINUX_MMAN_H */ diff --git a/tools/include/uapi/linux/module_signature.h b/tools/include/uapi/linux/module_signature.h new file mode 100644 index 000000000..634c9f1c8 --- /dev/null +++ b/tools/include/uapi/linux/module_signature.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Module signature handling. + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifndef _UAPI_LINUX_MODULE_SIGNATURE_H +#define _UAPI_LINUX_MODULE_SIGNATURE_H + +#include + +/* In stripped ARM and x86-64 modules, ~ is surprisingly rare. */ +#define MODULE_SIGNATURE_MARKER "~Module signature appended~\n" + +enum module_signature_type { + MODULE_SIGNATURE_TYPE_PKCS7 = 2, /* Signature in PKCS#7 message */ +}; + +/* + * Module signature information block. + * + * The constituents of the signature section are, in order: + * + * - Signer's name + * - Key identifier + * - Signature data + * - Information block + */ +struct module_signature { + __u8 algo; /* Public-key crypto algorithm [0] */ + __u8 hash; /* Digest algorithm [0] */ + __u8 id_type; /* Key identifier type [enum module_signature_type] */ + __u8 signer_len; /* Length of signer's name [0] */ + __u8 key_id_len; /* Length of key identifier [0] */ + __u8 __pad[3]; + __be32 sig_len; /* Length of signature data */ +}; + +#endif /* _UAPI_LINUX_MODULE_SIGNATURE_H */ diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h new file mode 100644 index 000000000..2204708db --- /dev/null +++ b/tools/include/uapi/linux/mount.h @@ -0,0 +1,245 @@ +#ifndef _UAPI_LINUX_MOUNT_H +#define _UAPI_LINUX_MOUNT_H + +#include + +/* + * These are the fs-independent mount-flags: up to 32 flags are supported + * + * Usage of these is restricted within the kernel to core mount(2) code and + * callers of sys_mount() only. Filesystems should be using the SB_* + * equivalent instead. + */ +#define MS_RDONLY 1 /* Mount read-only */ +#define MS_NOSUID 2 /* Ignore suid and sgid bits */ +#define MS_NODEV 4 /* Disallow access to device special files */ +#define MS_NOEXEC 8 /* Disallow program execution */ +#define MS_SYNCHRONOUS 16 /* Writes are synced at once */ +#define MS_REMOUNT 32 /* Alter flags of a mounted FS */ +#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ +#define MS_NOATIME 1024 /* Do not update access times. */ +#define MS_NODIRATIME 2048 /* Do not update directory access times */ +#define MS_BIND 4096 +#define MS_MOVE 8192 +#define MS_REC 16384 +#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence. + MS_VERBOSE is deprecated. */ +#define MS_SILENT 32768 +#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define MS_UNBINDABLE (1<<17) /* change to unbindable */ +#define MS_PRIVATE (1<<18) /* change to private */ +#define MS_SLAVE (1<<19) /* change to slave */ +#define MS_SHARED (1<<20) /* change to shared */ +#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */ +#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define MS_I_VERSION (1<<23) /* Update inode I_version field */ +#define MS_STRICTATIME (1<<24) /* Always perform atime updates */ +#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define MS_SUBMOUNT (1<<26) +#define MS_NOREMOTELOCK (1<<27) +#define MS_NOSEC (1<<28) +#define MS_BORN (1<<29) +#define MS_ACTIVE (1<<30) +#define MS_NOUSER (1<<31) + +/* + * Superblock flags that can be altered by MS_REMOUNT + */ +#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\ + MS_LAZYTIME) + +/* + * Old magic mount flag and mask + */ +#define MS_MGC_VAL 0xC0ED0000 +#define MS_MGC_MSK 0xffff0000 + +/* + * open_tree() flags. + */ +#define OPEN_TREE_CLONE (1 << 0) /* Clone the target tree and attach the clone */ +#define OPEN_TREE_NAMESPACE (1 << 1) /* Clone the target tree into a new mount namespace */ +#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */ + +/* + * move_mount() flags. + */ +#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */ +#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */ +#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ +#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */ +#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ +#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ +#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 + +/* + * fsopen() flags. + */ +#define FSOPEN_CLOEXEC 0x00000001 + +/* + * fspick() flags. + */ +#define FSPICK_CLOEXEC 0x00000001 +#define FSPICK_SYMLINK_NOFOLLOW 0x00000002 +#define FSPICK_NO_AUTOMOUNT 0x00000004 +#define FSPICK_EMPTY_PATH 0x00000008 + +/* + * The type of fsconfig() call made. + */ +enum fsconfig_command { + FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */ + FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */ + FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */ + FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */ + FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */ + FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */ + FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */ + FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */ + FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */ +}; + +/* + * fsmount() flags. + */ +#define FSMOUNT_CLOEXEC 0x00000001 +#define FSMOUNT_NAMESPACE 0x00000002 /* Create the mount in a new mount namespace */ + +/* + * Mount attributes. + */ +#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */ +#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */ +#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */ +#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */ +#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */ +#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ +#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */ +#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */ +#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */ +#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */ +#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */ + +/* + * mount_setattr() + */ +struct mount_attr { + __u64 attr_set; + __u64 attr_clr; + __u64 propagation; + __u64 userns_fd; +}; + +/* List of all mount_attr versions. */ +#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */ + + +/* + * Structure for getting mount/superblock/filesystem info with statmount(2). + * + * The interface is similar to statx(2): individual fields or groups can be + * selected with the @mask argument of statmount(). Kernel will set the @mask + * field according to the supported fields. + * + * If string fields are selected, then the caller needs to pass a buffer that + * has space after the fixed part of the structure. Nul terminated strings are + * copied there and offsets relative to @str are stored in the relevant fields. + * If the buffer is too small, then EOVERFLOW is returned. The actually used + * size is returned in @size. + */ +struct statmount { + __u32 size; /* Total size, including strings */ + __u32 mnt_opts; /* [str] Options (comma separated, escaped) */ + __u64 mask; /* What results were written */ + __u32 sb_dev_major; /* Device ID */ + __u32 sb_dev_minor; + __u64 sb_magic; /* ..._SUPER_MAGIC */ + __u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */ + __u32 fs_type; /* [str] Filesystem type */ + __u64 mnt_id; /* Unique ID of mount */ + __u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */ + __u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */ + __u32 mnt_parent_id_old; + __u64 mnt_attr; /* MOUNT_ATTR_... */ + __u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */ + __u64 mnt_peer_group; /* ID of shared peer group */ + __u64 mnt_master; /* Mount receives propagation from this ID */ + __u64 propagate_from; /* Propagation from in current namespace */ + __u32 mnt_root; /* [str] Root of mount relative to root of fs */ + __u32 mnt_point; /* [str] Mountpoint relative to current root */ + __u64 mnt_ns_id; /* ID of the mount namespace */ + __u32 fs_subtype; /* [str] Subtype of fs_type (if any) */ + __u32 sb_source; /* [str] Source string of the mount */ + __u32 opt_num; /* Number of fs options */ + __u32 opt_array; /* [str] Array of nul terminated fs options */ + __u32 opt_sec_num; /* Number of security options */ + __u32 opt_sec_array; /* [str] Array of nul terminated security options */ + __u64 supported_mask; /* Mask flags that this kernel supports */ + __u32 mnt_uidmap_num; /* Number of uid mappings */ + __u32 mnt_uidmap; /* [str] Array of uid mappings (as seen from callers namespace) */ + __u32 mnt_gidmap_num; /* Number of gid mappings */ + __u32 mnt_gidmap; /* [str] Array of gid mappings (as seen from callers namespace) */ + __u64 __spare2[43]; + char str[]; /* Variable size part containing strings */ +}; + +/* + * Structure for passing mount ID and miscellaneous parameters to statmount(2) + * and listmount(2). + * + * For statmount(2) @param represents the request mask. + * For listmount(2) @param represents the last listed mount id (or zero). + */ +struct mnt_id_req { + __u32 size; + union { + __u32 mnt_ns_fd; + __u32 mnt_fd; + }; + __u64 mnt_id; + __u64 param; + __u64 mnt_ns_id; +}; + +/* List of all mnt_id_req versions. */ +#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */ +#define MNT_ID_REQ_SIZE_VER1 32 /* sizeof second published struct */ + +/* + * @mask bits for statmount(2) + */ +#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */ +#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */ +#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */ +#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */ +#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */ +#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */ +#define STATMOUNT_MNT_NS_ID 0x00000040U /* Want/got mnt_ns_id */ +#define STATMOUNT_MNT_OPTS 0x00000080U /* Want/got mnt_opts */ +#define STATMOUNT_FS_SUBTYPE 0x00000100U /* Want/got fs_subtype */ +#define STATMOUNT_SB_SOURCE 0x00000200U /* Want/got sb_source */ +#define STATMOUNT_OPT_ARRAY 0x00000400U /* Want/got opt_... */ +#define STATMOUNT_OPT_SEC_ARRAY 0x00000800U /* Want/got opt_sec... */ +#define STATMOUNT_SUPPORTED_MASK 0x00001000U /* Want/got supported mask flags */ +#define STATMOUNT_MNT_UIDMAP 0x00002000U /* Want/got uidmap... */ +#define STATMOUNT_MNT_GIDMAP 0x00004000U /* Want/got gidmap... */ + +/* + * Special @mnt_id values that can be passed to listmount + */ +#define LSMT_ROOT 0xffffffffffffffff /* root mount */ +#define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ + +/* + * @flag bits for statmount(2) + */ +#define STATMOUNT_BY_FD 0x00000001U /* want mountinfo for given fd */ + +#endif /* _UAPI_LINUX_MOUNT_H */ diff --git a/tools/include/uapi/linux/neighbour.h b/tools/include/uapi/linux/neighbour.h new file mode 100644 index 000000000..c34a81245 --- /dev/null +++ b/tools/include/uapi/linux/neighbour.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NEIGHBOUR_H +#define _UAPI__LINUX_NEIGHBOUR_H + +#include +#include + +struct ndmsg { + __u8 ndm_family; + __u8 ndm_pad1; + __u16 ndm_pad2; + __s32 ndm_ifindex; + __u16 ndm_state; + __u8 ndm_flags; + __u8 ndm_type; +}; + +enum { + NDA_UNSPEC, + NDA_DST, + NDA_LLADDR, + NDA_CACHEINFO, + NDA_PROBES, + NDA_VLAN, + NDA_PORT, + NDA_VNI, + NDA_IFINDEX, + NDA_MASTER, + NDA_LINK_NETNSID, + NDA_SRC_VNI, + NDA_PROTOCOL, /* Originator of entry */ + NDA_NH_ID, + NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, + NDA_NDM_STATE_MASK, + NDA_NDM_FLAGS_MASK, + __NDA_MAX +}; + +#define NDA_MAX (__NDA_MAX - 1) + +/* + * Neighbor Cache Entry Flags + */ + +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_LOCKED (1 << 1) +#define NTF_EXT_EXT_VALIDATED (1 << 2) + +/* + * Neighbor Cache Entry States. + */ + +#define NUD_INCOMPLETE 0x01 +#define NUD_REACHABLE 0x02 +#define NUD_STALE 0x04 +#define NUD_DELAY 0x08 +#define NUD_PROBE 0x10 +#define NUD_FAILED 0x20 + +/* Dummy states */ +#define NUD_NOARP 0x40 +#define NUD_PERMANENT 0x80 +#define NUD_NONE 0x00 + +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * + * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry + * states don't make sense and thus are ignored. Such entries don't age and + * can roam. + * + * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf + * of a user space control plane, and automatically refreshed so that (if + * possible) they remain in NUD_REACHABLE state. + * + * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the + * bridge in response to a host trying to communicate via a locked bridge port + * with MAB enabled. Their purpose is to notify user space that a host requires + * authentication. + * + * NTF_EXT_EXT_VALIDATED flagged neighbor entries were externally validated by + * a user space control plane. The kernel will not remove or invalidate them, + * but it can probe them and notify user space when they become reachable. + */ + +struct nda_cacheinfo { + __u32 ndm_confirmed; + __u32 ndm_used; + __u32 ndm_updated; + __u32 ndm_refcnt; +}; + +/***************************************************************** + * Neighbour tables specific messages. + * + * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the + * NLM_F_DUMP flag set. Every neighbour table configuration is + * spread over multiple messages to avoid running into message + * size limits on systems with many interfaces. The first message + * in the sequence transports all not device specific data such as + * statistics, configuration, and the default parameter set. + * This message is followed by 0..n messages carrying device + * specific parameter sets. + * Although the ordering should be sufficient, NDTA_NAME can be + * used to identify sequences. The initial message can be identified + * by checking for NDTA_CONFIG. The device specific messages do + * not contain this TLV but have NDTPA_IFINDEX set to the + * corresponding interface index. + * + * To change neighbour table attributes, send RTM_SETNEIGHTBL + * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], + * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked + * otherwise. Device specific parameter sets can be changed by + * setting NDTPA_IFINDEX to the interface index of the corresponding + * device. + ****/ + +struct ndt_stats { + __u64 ndts_allocs; + __u64 ndts_destroys; + __u64 ndts_hash_grows; + __u64 ndts_res_failed; + __u64 ndts_lookups; + __u64 ndts_hits; + __u64 ndts_rcv_probes_mcast; + __u64 ndts_rcv_probes_ucast; + __u64 ndts_periodic_gc_runs; + __u64 ndts_forced_gc_runs; + __u64 ndts_table_fulls; +}; + +enum { + NDTPA_UNSPEC, + NDTPA_IFINDEX, /* u32, unchangeable */ + NDTPA_REFCNT, /* u32, read-only */ + NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ + NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ + NDTPA_RETRANS_TIME, /* u64, msecs */ + NDTPA_GC_STALETIME, /* u64, msecs */ + NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ + NDTPA_QUEUE_LEN, /* u32 */ + NDTPA_APP_PROBES, /* u32 */ + NDTPA_UCAST_PROBES, /* u32 */ + NDTPA_MCAST_PROBES, /* u32 */ + NDTPA_ANYCAST_DELAY, /* u64, msecs */ + NDTPA_PROXY_DELAY, /* u64, msecs */ + NDTPA_PROXY_QLEN, /* u32 */ + NDTPA_LOCKTIME, /* u64, msecs */ + NDTPA_QUEUE_LENBYTES, /* u32 */ + NDTPA_MCAST_REPROBES, /* u32 */ + NDTPA_PAD, + NDTPA_INTERVAL_PROBE_TIME_MS, /* u64, msecs */ + __NDTPA_MAX +}; +#define NDTPA_MAX (__NDTPA_MAX - 1) + +struct ndtmsg { + __u8 ndtm_family; + __u8 ndtm_pad1; + __u16 ndtm_pad2; +}; + +struct ndt_config { + __u16 ndtc_key_len; + __u16 ndtc_entry_size; + __u32 ndtc_entries; + __u32 ndtc_last_flush; /* delta to now in msecs */ + __u32 ndtc_last_rand; /* delta to now in msecs */ + __u32 ndtc_hash_rnd; + __u32 ndtc_hash_mask; + __u32 ndtc_hash_chain_gc; + __u32 ndtc_proxy_qlen; +}; + +enum { + NDTA_UNSPEC, + NDTA_NAME, /* char *, unchangeable */ + NDTA_THRESH1, /* u32 */ + NDTA_THRESH2, /* u32 */ + NDTA_THRESH3, /* u32 */ + NDTA_CONFIG, /* struct ndt_config, read-only */ + NDTA_PARMS, /* nested TLV NDTPA_* */ + NDTA_STATS, /* struct ndt_stats, read-only */ + NDTA_GC_INTERVAL, /* u64, msecs */ + NDTA_PAD, + __NDTA_MAX +}; +#define NDTA_MAX (__NDTA_MAX - 1) + + /* FDB activity notification bits used in NFEA_ACTIVITY_NOTIFY: + * - FDB_NOTIFY_BIT - notify on activity/expire for any entry + * - FDB_NOTIFY_INACTIVE_BIT - mark as inactive to avoid multiple notifications + */ +enum { + FDB_NOTIFY_BIT = (1 << 0), + FDB_NOTIFY_INACTIVE_BIT = (1 << 1) +}; + +/* embedded into NDA_FDB_EXT_ATTRS: + * [NDA_FDB_EXT_ATTRS] = { + * [NFEA_ACTIVITY_NOTIFY] + * ... + * } + */ +enum { + NFEA_UNSPEC, + NFEA_ACTIVITY_NOTIFY, + NFEA_DONT_REFRESH, + __NFEA_MAX +}; +#define NFEA_MAX (__NFEA_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h new file mode 100644 index 000000000..35ff08322 --- /dev/null +++ b/tools/include/uapi/linux/netdev.h @@ -0,0 +1,253 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ +/* To regenerate run: tools/net/ynl/ynl-regen.sh */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP features set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * offloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, + + /* private: */ + NETDEV_XDP_ACT_MASK = 127, +}; + +/** + * enum netdev_xdp_rx_metadata + * @NETDEV_XDP_RX_METADATA_TIMESTAMP: Device is capable of exposing receive HW + * timestamp via bpf_xdp_metadata_rx_timestamp(). + * @NETDEV_XDP_RX_METADATA_HASH: Device is capable of exposing receive packet + * hash via bpf_xdp_metadata_rx_hash(). + * @NETDEV_XDP_RX_METADATA_VLAN_TAG: Device is capable of exposing receive + * packet VLAN tag via bpf_xdp_metadata_rx_vlan_tag(). + */ +enum netdev_xdp_rx_metadata { + NETDEV_XDP_RX_METADATA_TIMESTAMP = 1, + NETDEV_XDP_RX_METADATA_HASH = 2, + NETDEV_XDP_RX_METADATA_VLAN_TAG = 4, +}; + +/** + * enum netdev_xsk_flags + * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported + * by the driver. + * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the + * driver. + * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported + * by the driver. + */ +enum netdev_xsk_flags { + NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, + NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4, +}; + +enum netdev_queue_type { + NETDEV_QUEUE_TYPE_RX, + NETDEV_QUEUE_TYPE_TX, +}; + +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + +enum netdev_napi_threaded { + NETDEV_NAPI_THREADED_DISABLED, + NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + NETDEV_A_DEV_XDP_ZC_MAX_SEGS, + NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, + NETDEV_A_DEV_XSK_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_A_IO_URING_PROVIDER_INFO_RX_BUF_LEN = 1, + + __NETDEV_A_IO_URING_PROVIDER_INFO_MAX, + NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1) +}; + +enum { + NETDEV_A_PAGE_POOL_ID = 1, + NETDEV_A_PAGE_POOL_IFINDEX, + NETDEV_A_PAGE_POOL_NAPI_ID, + NETDEV_A_PAGE_POOL_INFLIGHT, + NETDEV_A_PAGE_POOL_INFLIGHT_MEM, + NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, + NETDEV_A_PAGE_POOL_IO_URING, + + __NETDEV_A_PAGE_POOL_MAX, + NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) +}; + +enum { + NETDEV_A_PAGE_POOL_STATS_INFO = 1, + NETDEV_A_PAGE_POOL_STATS_ALLOC_FAST = 8, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW, + NETDEV_A_PAGE_POOL_STATS_ALLOC_SLOW_HIGH_ORDER, + NETDEV_A_PAGE_POOL_STATS_ALLOC_EMPTY, + NETDEV_A_PAGE_POOL_STATS_ALLOC_REFILL, + NETDEV_A_PAGE_POOL_STATS_ALLOC_WAIVE, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHED, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_CACHE_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RING_FULL, + NETDEV_A_PAGE_POOL_STATS_RECYCLE_RELEASED_REFCNT, + + __NETDEV_A_PAGE_POOL_STATS_MAX, + NETDEV_A_PAGE_POOL_STATS_MAX = (__NETDEV_A_PAGE_POOL_STATS_MAX - 1) +}; + +enum { + NETDEV_A_NAPI_IFINDEX = 1, + NETDEV_A_NAPI_ID, + NETDEV_A_NAPI_IRQ, + NETDEV_A_NAPI_PID, + NETDEV_A_NAPI_DEFER_HARD_IRQS, + NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, + NETDEV_A_NAPI_THREADED, + + __NETDEV_A_NAPI_MAX, + NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) +}; + +enum { + __NETDEV_A_XSK_INFO_MAX, + NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) +}; + +enum { + NETDEV_A_QUEUE_ID = 1, + NETDEV_A_QUEUE_IFINDEX, + NETDEV_A_QUEUE_TYPE, + NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, + NETDEV_A_QUEUE_IO_URING, + NETDEV_A_QUEUE_XSK, + NETDEV_A_QUEUE_LEASE, + + __NETDEV_A_QUEUE_MAX, + NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) +}; + +enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, + NETDEV_A_QSTATS_RX_HW_DROPS, + NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, + NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, + NETDEV_A_QSTATS_RX_CSUM_NONE, + NETDEV_A_QSTATS_RX_CSUM_BAD, + NETDEV_A_QSTATS_RX_HW_GRO_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_BYTES, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_PACKETS, + NETDEV_A_QSTATS_RX_HW_GRO_WIRE_BYTES, + NETDEV_A_QSTATS_RX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_HW_DROPS, + NETDEV_A_QSTATS_TX_HW_DROP_ERRORS, + NETDEV_A_QSTATS_TX_CSUM_NONE, + NETDEV_A_QSTATS_TX_NEEDS_CSUM, + NETDEV_A_QSTATS_TX_HW_GSO_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_BYTES, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_PACKETS, + NETDEV_A_QSTATS_TX_HW_GSO_WIRE_BYTES, + NETDEV_A_QSTATS_TX_HW_DROP_RATELIMITS, + NETDEV_A_QSTATS_TX_STOP, + NETDEV_A_QSTATS_TX_WAKE, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + +enum { + NETDEV_A_LEASE_IFINDEX = 1, + NETDEV_A_LEASE_QUEUE, + NETDEV_A_LEASE_NETNS_ID, + + __NETDEV_A_LEASE_MAX, + NETDEV_A_LEASE_MAX = (__NETDEV_A_LEASE_MAX - 1) +}; + +enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + NETDEV_A_DMABUF_RX_PAGE_SIZE, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_GET, + NETDEV_CMD_PAGE_POOL_ADD_NTF, + NETDEV_CMD_PAGE_POOL_DEL_NTF, + NETDEV_CMD_PAGE_POOL_CHANGE_NTF, + NETDEV_CMD_PAGE_POOL_STATS_GET, + NETDEV_CMD_QUEUE_GET, + NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, + NETDEV_CMD_NAPI_SET, + NETDEV_CMD_BIND_TX, + NETDEV_CMD_QUEUE_CREATE, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" +#define NETDEV_MCGRP_PAGE_POOL "page-pool" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/tools/include/uapi/linux/netfilter.h b/tools/include/uapi/linux/netfilter.h new file mode 100644 index 000000000..5a79ccb76 --- /dev/null +++ b/tools/include/uapi/linux/netfilter.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETFILTER_H +#define _UAPI__LINUX_NETFILTER_H + +#include +#include +#include +#include + +/* Responses from hook functions. */ +#define NF_DROP 0 +#define NF_ACCEPT 1 +#define NF_STOLEN 2 +#define NF_QUEUE 3 +#define NF_REPEAT 4 +#define NF_STOP 5 /* Deprecated, for userspace nf_queue compatibility. */ +#define NF_MAX_VERDICT NF_STOP + +/* we overload the higher bits for encoding auxiliary data such as the queue + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 + +/* queue number (NF_QUEUE) or errno (NF_DROP) */ +#define NF_VERDICT_QMASK 0xffff0000 +#define NF_VERDICT_QBITS 16 + +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) + +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) + +/* only for userspace compatibility */ +#ifndef __KERNEL__ + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 +#endif + +enum nf_inet_hooks { + NF_INET_PRE_ROUTING, + NF_INET_LOCAL_IN, + NF_INET_FORWARD, + NF_INET_LOCAL_OUT, + NF_INET_POST_ROUTING, + NF_INET_NUMHOOKS, + NF_INET_INGRESS = NF_INET_NUMHOOKS, +}; + +enum nf_dev_hooks { + NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, + NF_NETDEV_NUMHOOKS +}; + +enum { + NFPROTO_UNSPEC = 0, + NFPROTO_INET = 1, + NFPROTO_IPV4 = 2, + NFPROTO_ARP = 3, + NFPROTO_NETDEV = 5, + NFPROTO_BRIDGE = 7, + NFPROTO_IPV6 = 10, +#ifndef __KERNEL__ /* no longer supported by kernel */ + NFPROTO_DECNET = 12, +#endif + NFPROTO_NUMPROTO, +}; + +union nf_inet_addr { + __u32 all[4]; + __be32 ip; + __be32 ip6[4]; + struct in_addr in; + struct in6_addr in6; +}; + +#endif /* _UAPI__LINUX_NETFILTER_H */ diff --git a/tools/include/uapi/linux/netfilter_arp.h b/tools/include/uapi/linux/netfilter_arp.h new file mode 100644 index 000000000..791dfc5ae --- /dev/null +++ b/tools/include/uapi/linux/netfilter_arp.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ +#ifndef __LINUX_ARP_NETFILTER_H +#define __LINUX_ARP_NETFILTER_H + +/* ARP-specific defines for netfilter. + * (C)2002 Rusty Russell IBM -- This code is GPL. + */ + +#include + +/* There is no PF_ARP. */ +#define NF_ARP 0 + +/* ARP Hooks */ +#define NF_ARP_IN 0 +#define NF_ARP_OUT 1 +#define NF_ARP_FORWARD 2 + +#ifndef __KERNEL__ +#define NF_ARP_NUMHOOKS 3 +#endif + +#endif /* __LINUX_ARP_NETFILTER_H */ diff --git a/tools/include/uapi/linux/netlink.h b/tools/include/uapi/linux/netlink.h new file mode 100644 index 000000000..0a4d73317 --- /dev/null +++ b/tools/include/uapi/linux/netlink.h @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_NETLINK_H +#define _UAPI__LINUX_NETLINK_H + +#include +#include /* for __kernel_sa_family_t */ +#include + +#define NETLINK_ROUTE 0 /* Routing/device hook */ +#define NETLINK_UNUSED 1 /* Unused number */ +#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ +#define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */ +#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ +#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ +#define NETLINK_XFRM 6 /* ipsec */ +#define NETLINK_SELINUX 7 /* SELinux event notifications */ +#define NETLINK_ISCSI 8 /* Open-iSCSI */ +#define NETLINK_AUDIT 9 /* auditing */ +#define NETLINK_FIB_LOOKUP 10 +#define NETLINK_CONNECTOR 11 +#define NETLINK_NETFILTER 12 /* netfilter subsystem */ +#define NETLINK_IP6_FW 13 +#define NETLINK_DNRTMSG 14 /* DECnet routing messages */ +#define NETLINK_KOBJECT_UEVENT 15 /* Kernel messages to userspace */ +#define NETLINK_GENERIC 16 +/* leave room for NETLINK_DM (DM Events) */ +#define NETLINK_SCSITRANSPORT 18 /* SCSI Transports */ +#define NETLINK_ECRYPTFS 19 +#define NETLINK_RDMA 20 +#define NETLINK_CRYPTO 21 /* Crypto layer */ +#define NETLINK_SMC 22 /* SMC monitoring */ + +#define NETLINK_INET_DIAG NETLINK_SOCK_DIAG + +#define MAX_LINKS 32 + +struct sockaddr_nl { + __kernel_sa_family_t nl_family; /* AF_NETLINK */ + unsigned short nl_pad; /* zero */ + __u32 nl_pid; /* port ID */ + __u32 nl_groups; /* multicast groups mask */ +}; + +struct nlmsghdr { + __u32 nlmsg_len; /* Length of message including header */ + __u16 nlmsg_type; /* Message content */ + __u16 nlmsg_flags; /* Additional flags */ + __u32 nlmsg_seq; /* Sequence number */ + __u32 nlmsg_pid; /* Sending process port ID */ +}; + +/* Flags values */ + +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ + +/* Modifiers to GET request */ +#define NLM_F_ROOT 0x100 /* specify tree root */ +#define NLM_F_MATCH 0x200 /* return all matching */ +#define NLM_F_ATOMIC 0x400 /* atomic GET */ +#define NLM_F_DUMP (NLM_F_ROOT|NLM_F_MATCH) + +/* Modifiers to NEW request */ +#define NLM_F_REPLACE 0x100 /* Override existing */ +#define NLM_F_EXCL 0x200 /* Do not touch, if it exists */ +#define NLM_F_CREATE 0x400 /* Create, if it does not exist */ +#define NLM_F_APPEND 0x800 /* Add to end of list */ + +/* Modifiers to DELETE request */ +#define NLM_F_NONREC 0x100 /* Do not delete recursively */ + +/* Flags for ACK message */ +#define NLM_F_CAPPED 0x100 /* request was capped */ +#define NLM_F_ACK_TLVS 0x200 /* extended ACK TVLs were included */ + +/* + 4.4BSD ADD NLM_F_CREATE|NLM_F_EXCL + 4.4BSD CHANGE NLM_F_REPLACE + + True CHANGE NLM_F_CREATE|NLM_F_REPLACE + Append NLM_F_CREATE + Check NLM_F_EXCL + */ + +#define NLMSG_ALIGNTO 4U +#define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) ) +#define NLMSG_HDRLEN ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr))) +#define NLMSG_LENGTH(len) ((len) + NLMSG_HDRLEN) +#define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len)) +#define NLMSG_DATA(nlh) ((void*)(((char*)nlh) + NLMSG_LENGTH(0))) +#define NLMSG_NEXT(nlh,len) ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \ + (struct nlmsghdr*)(((char*)(nlh)) + NLMSG_ALIGN((nlh)->nlmsg_len))) +#define NLMSG_OK(nlh,len) ((len) >= (int)sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len >= sizeof(struct nlmsghdr) && \ + (nlh)->nlmsg_len <= (len)) +#define NLMSG_PAYLOAD(nlh,len) ((nlh)->nlmsg_len - NLMSG_SPACE((len))) + +#define NLMSG_NOOP 0x1 /* Nothing. */ +#define NLMSG_ERROR 0x2 /* Error */ +#define NLMSG_DONE 0x3 /* End of a dump */ +#define NLMSG_OVERRUN 0x4 /* Data lost */ + +#define NLMSG_MIN_TYPE 0x10 /* < 0x10: reserved control messages */ + +struct nlmsgerr { + int error; + struct nlmsghdr msg; + /* + * followed by the message contents unless NETLINK_CAP_ACK was set + * or the ACK indicates success (error == 0) + * message length is aligned with NLMSG_ALIGN() + */ + /* + * followed by TLVs defined in enum nlmsgerr_attrs + * if NETLINK_EXT_ACK was set + */ +}; + +/** + * enum nlmsgerr_attrs - nlmsgerr attributes + * @NLMSGERR_ATTR_UNUSED: unused + * @NLMSGERR_ATTR_MSG: error message string (string) + * @NLMSGERR_ATTR_OFFS: offset of the invalid attribute in the original + * message, counting from the beginning of the header (u32) + * @NLMSGERR_ATTR_COOKIE: arbitrary subsystem specific cookie to + * be used - in the success case - to identify a created + * object or operation or similar (binary) + * @__NLMSGERR_ATTR_MAX: number of attributes + * @NLMSGERR_ATTR_MAX: highest attribute number + */ +enum nlmsgerr_attrs { + NLMSGERR_ATTR_UNUSED, + NLMSGERR_ATTR_MSG, + NLMSGERR_ATTR_OFFS, + NLMSGERR_ATTR_COOKIE, + + __NLMSGERR_ATTR_MAX, + NLMSGERR_ATTR_MAX = __NLMSGERR_ATTR_MAX - 1 +}; + +#define NETLINK_ADD_MEMBERSHIP 1 +#define NETLINK_DROP_MEMBERSHIP 2 +#define NETLINK_PKTINFO 3 +#define NETLINK_BROADCAST_ERROR 4 +#define NETLINK_NO_ENOBUFS 5 +#ifndef __KERNEL__ +#define NETLINK_RX_RING 6 +#define NETLINK_TX_RING 7 +#endif +#define NETLINK_LISTEN_ALL_NSID 8 +#define NETLINK_LIST_MEMBERSHIPS 9 +#define NETLINK_CAP_ACK 10 +#define NETLINK_EXT_ACK 11 +#define NETLINK_GET_STRICT_CHK 12 + +struct nl_pktinfo { + __u32 group; +}; + +struct nl_mmap_req { + unsigned int nm_block_size; + unsigned int nm_block_nr; + unsigned int nm_frame_size; + unsigned int nm_frame_nr; +}; + +struct nl_mmap_hdr { + unsigned int nm_status; + unsigned int nm_len; + __u32 nm_group; + /* credentials */ + __u32 nm_pid; + __u32 nm_uid; + __u32 nm_gid; +}; + +#ifndef __KERNEL__ +enum nl_mmap_status { + NL_MMAP_STATUS_UNUSED, + NL_MMAP_STATUS_RESERVED, + NL_MMAP_STATUS_VALID, + NL_MMAP_STATUS_COPY, + NL_MMAP_STATUS_SKIP, +}; + +#define NL_MMAP_MSG_ALIGNMENT NLMSG_ALIGNTO +#define NL_MMAP_MSG_ALIGN(sz) __ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT) +#define NL_MMAP_HDRLEN NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr)) +#endif + +#define NET_MAJOR 36 /* Major 36 is reserved for networking */ + +enum { + NETLINK_UNCONNECTED = 0, + NETLINK_CONNECTED, +}; + +/* + * <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)--> + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * | Header | Pad | Payload | Pad | + * | (struct nlattr) | ing | | ing | + * +---------------------+- - -+- - - - - - - - - -+- - -+ + * <-------------- nlattr->nla_len --------------> + */ + +struct nlattr { + __u16 nla_len; + __u16 nla_type; +}; + +/* + * nla_type (16 bits) + * +---+---+-------------------------------+ + * | N | O | Attribute Type | + * +---+---+-------------------------------+ + * N := Carries nested attributes + * O := Payload stored in network byte order + * + * Note: The N and O flag are mutually exclusive. + */ +#define NLA_F_NESTED (1 << 15) +#define NLA_F_NET_BYTEORDER (1 << 14) +#define NLA_TYPE_MASK ~(NLA_F_NESTED | NLA_F_NET_BYTEORDER) + +#define NLA_ALIGNTO 4 +#define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) +#define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) + +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; + +#endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/tools/include/uapi/linux/nsfs.h b/tools/include/uapi/linux/nsfs.h new file mode 100644 index 000000000..a25e38d1c --- /dev/null +++ b/tools/include/uapi/linux/nsfs.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_NSFS_H +#define __LINUX_NSFS_H + +#include +#include + +#define NSIO 0xb7 + +/* Returns a file descriptor that refers to an owning user namespace */ +#define NS_GET_USERNS _IO(NSIO, 0x1) +/* Returns a file descriptor that refers to a parent namespace */ +#define NS_GET_PARENT _IO(NSIO, 0x2) +/* Returns the type of namespace (CLONE_NEW* value) referred to by + file descriptor */ +#define NS_GET_NSTYPE _IO(NSIO, 0x3) +/* Get owner UID (in the caller's user namespace) for a user namespace */ +#define NS_GET_OWNER_UID _IO(NSIO, 0x4) +/* Translate pid from target pid namespace into the caller's pid namespace. */ +#define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) +/* Return thread-group leader id of pid in the callers pid namespace. */ +#define NS_GET_TGID_FROM_PIDNS _IOR(NSIO, 0x7, int) +/* Translate pid from caller's pid namespace into a target pid namespace. */ +#define NS_GET_PID_IN_PIDNS _IOR(NSIO, 0x8, int) +/* Return thread-group leader id of pid in the target pid namespace. */ +#define NS_GET_TGID_IN_PIDNS _IOR(NSIO, 0x9, int) + +struct mnt_ns_info { + __u32 size; + __u32 nr_mounts; + __u64 mnt_ns_id; +}; + +#define MNT_NS_INFO_SIZE_VER0 16 /* size of first published struct */ + +/* Get information about namespace. */ +#define NS_MNT_GET_INFO _IOR(NSIO, 10, struct mnt_ns_info) +/* Get next namespace. */ +#define NS_MNT_GET_NEXT _IOR(NSIO, 11, struct mnt_ns_info) +/* Get previous namespace. */ +#define NS_MNT_GET_PREV _IOR(NSIO, 12, struct mnt_ns_info) + +/* Retrieve namespace identifiers. */ +#define NS_GET_MNTNS_ID _IOR(NSIO, 5, __u64) +#define NS_GET_ID _IOR(NSIO, 13, __u64) + +enum init_ns_ino { + IPC_NS_INIT_INO = 0xEFFFFFFFU, + UTS_NS_INIT_INO = 0xEFFFFFFEU, + USER_NS_INIT_INO = 0xEFFFFFFDU, + PID_NS_INIT_INO = 0xEFFFFFFCU, + CGROUP_NS_INIT_INO = 0xEFFFFFFBU, + TIME_NS_INIT_INO = 0xEFFFFFFAU, + NET_NS_INIT_INO = 0xEFFFFFF9U, + MNT_NS_INIT_INO = 0xEFFFFFF8U, +#ifdef __KERNEL__ + MNT_NS_ANON_INO = 0xEFFFFFF7U, +#endif +}; + +struct nsfs_file_handle { + __u64 ns_id; + __u32 ns_type; + __u32 ns_inum; +}; + +#define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ +#define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ + +enum init_ns_id { + IPC_NS_INIT_ID = 1ULL, + UTS_NS_INIT_ID = 2ULL, + USER_NS_INIT_ID = 3ULL, + PID_NS_INIT_ID = 4ULL, + CGROUP_NS_INIT_ID = 5ULL, + TIME_NS_INIT_ID = 6ULL, + NET_NS_INIT_ID = 7ULL, + MNT_NS_INIT_ID = 8ULL, +#ifdef __KERNEL__ + NS_LAST_INIT_ID = MNT_NS_INIT_ID, +#endif +}; + +enum ns_type { + TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */ + MNT_NS = (1ULL << 17), /* CLONE_NEWNS */ + CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */ + UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */ + IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */ + USER_NS = (1ULL << 28), /* CLONE_NEWUSER */ + PID_NS = (1ULL << 29), /* CLONE_NEWPID */ + NET_NS = (1ULL << 30), /* CLONE_NEWNET */ +}; + +/** + * struct ns_id_req - namespace ID request structure + * @size: size of this structure + * @spare: reserved for future use + * @filter: filter mask + * @ns_id: last namespace id + * @user_ns_id: owning user namespace ID + * + * Structure for passing namespace ID and miscellaneous parameters to + * statns(2) and listns(2). + * + * For statns(2) @param represents the request mask. + * For listns(2) @param represents the last listed mount id (or zero). + */ +struct ns_id_req { + __u32 size; + __u32 spare; + __u64 ns_id; + struct /* listns */ { + __u32 ns_type; + __u32 spare2; + __u64 user_ns_id; + }; +}; + +/* + * Special @user_ns_id value that can be passed to listns() + */ +#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */ + +/* List of all ns_id_req versions. */ +#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */ + +#endif /* __LINUX_NSFS_H */ diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h new file mode 100644 index 000000000..4759c4716 --- /dev/null +++ b/tools/include/uapi/linux/openat2.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_OPENAT2_H +#define _LINUX_OPENAT2_H + +#include + +/* + * Arguments for how openat2(2) should open the target path. If only @flags and + * @mode are non-zero, then openat2(2) operates very similarly to openat(2). + * + * However, unlike openat(2), unknown or invalid bits in @flags result in + * -EINVAL rather than being silently ignored. @mode must be zero unless one of + * {O_CREAT, O_TMPFILE} are set. + * + * @flags: O_* flags. + * @mode: O_CREAT/O_TMPFILE file mode. + * @resolve: RESOLVE_* flags. + */ +struct open_how { + __u64 flags; + __u64 mode; + __u64 resolve; +}; + +/* how->resolve flags for openat2(2). */ +#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings + (includes bind-mounts). */ +#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style + "magic-links". */ +#define RESOLVE_NO_SYMLINKS 0x04 /* Block traversal through all symlinks + (implies OEXT_NO_MAGICLINKS) */ +#define RESOLVE_BENEATH 0x08 /* Block "lexical" trickery like + "..", symlinks, and absolute + paths which escape the dirfd. */ +#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".." + be scoped inside the dirfd + (similar to chroot(2)). */ +#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be + completed through cached lookup. May + return -EAGAIN if that's not + possible. */ + +#endif /* _LINUX_OPENAT2_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h new file mode 100644 index 000000000..fd10aa8d6 --- /dev/null +++ b/tools/include/uapi/linux/perf_event.h @@ -0,0 +1,1528 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Performance events: + * + * Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner + * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra + * + * Data type definitions, declarations, prototypes. + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * For licencing details see kernel-base/COPYING + */ +#ifndef _UAPI_LINUX_PERF_EVENT_H +#define _UAPI_LINUX_PERF_EVENT_H + +#include +#include +#include + +/* + * User-space ABI bits: + */ + +/* + * attr.type + */ +enum perf_type_id { + PERF_TYPE_HARDWARE = 0, + PERF_TYPE_SOFTWARE = 1, + PERF_TYPE_TRACEPOINT = 2, + PERF_TYPE_HW_CACHE = 3, + PERF_TYPE_RAW = 4, + PERF_TYPE_BREAKPOINT = 5, + + PERF_TYPE_MAX, /* non-ABI */ +}; + +/* + * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * + * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA + * AA: hardware event ID + * EEEEEEEE: PMU type ID + * + * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB + * BB: hardware cache ID + * CC: hardware cache op ID + * DD: hardware cache op result ID + * EEEEEEEE: PMU type ID + * + * If the PMU type ID is 0, PERF_TYPE_RAW will be applied. + */ +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff + +/* + * Generalized performance event event_id types, used by the + * attr.event_id parameter of the sys_perf_event_open() + * syscall: + */ +enum perf_hw_id { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_HW_CPU_CYCLES = 0, + PERF_COUNT_HW_INSTRUCTIONS = 1, + PERF_COUNT_HW_CACHE_REFERENCES = 2, + PERF_COUNT_HW_CACHE_MISSES = 3, + PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_HW_BRANCH_MISSES = 5, + PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, + PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, + PERF_COUNT_HW_REF_CPU_CYCLES = 9, + + PERF_COUNT_HW_MAX, /* non-ABI */ +}; + +/* + * Generalized hardware cache events: + * + * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x + * { read, write, prefetch } x + * { accesses, misses } + */ +enum perf_hw_cache_id { + PERF_COUNT_HW_CACHE_L1D = 0, + PERF_COUNT_HW_CACHE_L1I = 1, + PERF_COUNT_HW_CACHE_LL = 2, + PERF_COUNT_HW_CACHE_DTLB = 3, + PERF_COUNT_HW_CACHE_ITLB = 4, + PERF_COUNT_HW_CACHE_BPU = 5, + PERF_COUNT_HW_CACHE_NODE = 6, + + PERF_COUNT_HW_CACHE_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_id { + PERF_COUNT_HW_CACHE_OP_READ = 0, + PERF_COUNT_HW_CACHE_OP_WRITE = 1, + PERF_COUNT_HW_CACHE_OP_PREFETCH = 2, + + PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_result_id { + PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0, + PERF_COUNT_HW_CACHE_RESULT_MISS = 1, + + PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */ +}; + +/* + * Special "software" events provided by the kernel, even if the hardware + * does not support performance events. These events measure various + * physical and SW events of the kernel (and allow the profiling of them as + * well): + */ +enum perf_sw_ids { + PERF_COUNT_SW_CPU_CLOCK = 0, + PERF_COUNT_SW_TASK_CLOCK = 1, + PERF_COUNT_SW_PAGE_FAULTS = 2, + PERF_COUNT_SW_CONTEXT_SWITCHES = 3, + PERF_COUNT_SW_CPU_MIGRATIONS = 4, + PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, + PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, + PERF_COUNT_SW_EMULATION_FAULTS = 8, + PERF_COUNT_SW_DUMMY = 9, + PERF_COUNT_SW_BPF_OUTPUT = 10, + PERF_COUNT_SW_CGROUP_SWITCHES = 11, + + PERF_COUNT_SW_MAX, /* non-ABI */ +}; + +/* + * Bits that can be set in attr.sample_type to request information + * in the overflow packets. + */ +enum perf_event_sample_format { + PERF_SAMPLE_IP = 1U << 0, + PERF_SAMPLE_TID = 1U << 1, + PERF_SAMPLE_TIME = 1U << 2, + PERF_SAMPLE_ADDR = 1U << 3, + PERF_SAMPLE_READ = 1U << 4, + PERF_SAMPLE_CALLCHAIN = 1U << 5, + PERF_SAMPLE_ID = 1U << 6, + PERF_SAMPLE_CPU = 1U << 7, + PERF_SAMPLE_PERIOD = 1U << 8, + PERF_SAMPLE_STREAM_ID = 1U << 9, + PERF_SAMPLE_RAW = 1U << 10, + PERF_SAMPLE_BRANCH_STACK = 1U << 11, + PERF_SAMPLE_REGS_USER = 1U << 12, + PERF_SAMPLE_STACK_USER = 1U << 13, + PERF_SAMPLE_WEIGHT = 1U << 14, + PERF_SAMPLE_DATA_SRC = 1U << 15, + PERF_SAMPLE_IDENTIFIER = 1U << 16, + PERF_SAMPLE_TRANSACTION = 1U << 17, + PERF_SAMPLE_REGS_INTR = 1U << 18, + PERF_SAMPLE_PHYS_ADDR = 1U << 19, + PERF_SAMPLE_AUX = 1U << 20, + PERF_SAMPLE_CGROUP = 1U << 21, + PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22, + PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23, + PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, + + PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ +}; + +#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) + +/* + * Values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set. + * + * If the user does not pass priv level information via branch_sample_type, + * the kernel uses the event's priv level. Branch and event priv levels do + * not have to match. Branch priv level is checked for permissions. + * + * The branch types can be combined, however BRANCH_ANY covers all types + * of branches and therefore it supersedes all the other types. + */ +enum perf_branch_sample_type_shift { + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ + + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* CALL/RET stack */ + PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ + PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ + + PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ + PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + + PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT = 16, /* save branch type */ + + PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT = 17, /* save low level index of raw branch records */ + + PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT = 18, /* save privilege mode */ + + PERF_SAMPLE_BRANCH_COUNTERS_SHIFT = 19, /* save occurrences of events on a branch */ + + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ +}; + +enum perf_branch_sample_type { + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + + PERF_SAMPLE_BRANCH_TYPE_SAVE = 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + + PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, +}; + +/* + * Common control flow change classifications: + */ +enum { + PERF_BR_UNKNOWN = 0, /* Unknown */ + PERF_BR_COND = 1, /* Conditional */ + PERF_BR_UNCOND = 2, /* Unconditional */ + PERF_BR_IND = 3, /* Indirect */ + PERF_BR_CALL = 4, /* Function call */ + PERF_BR_IND_CALL = 5, /* Indirect function call */ + PERF_BR_RET = 6, /* Function return */ + PERF_BR_SYSCALL = 7, /* Syscall */ + PERF_BR_SYSRET = 8, /* Syscall return */ + PERF_BR_COND_CALL = 9, /* Conditional function call */ + PERF_BR_COND_RET = 10, /* Conditional function return */ + PERF_BR_ERET = 11, /* Exception return */ + PERF_BR_IRQ = 12, /* IRQ */ + PERF_BR_SERROR = 13, /* System error */ + PERF_BR_NO_TX = 14, /* Not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* Extend ABI */ + PERF_BR_MAX, +}; + +/* + * Common branch speculation outcome classifications: + */ +enum { + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_MAX, +}; + +enum { + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_MAX, +}; + +enum { + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, +}; + +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 + +#define PERF_SAMPLE_BRANCH_PLM_ALL \ + (PERF_SAMPLE_BRANCH_USER|\ + PERF_SAMPLE_BRANCH_KERNEL|\ + PERF_SAMPLE_BRANCH_HV) + +/* + * Values to determine ABI of the registers dump. + */ +enum perf_sample_regs_abi { + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, +}; + +/* + * Values for the memory transaction event qualifier, mostly for + * abort events. Multiple bits can be set. + */ +enum { + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction is not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + + PERF_TXN_MAX = (1 << 8), /* non-ABI */ + + /* Bits 32..63 are reserved for the abort code */ + + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, +}; + +/* + * The format of the data returned by read() on a perf event fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * { u64 lost; } && PERF_FORMAT_LOST + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; + */ +enum perf_event_read_format { + PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, + PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, + PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, + PERF_FORMAT_LOST = 1U << 4, + + PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ +}; + +#define PERF_ATTR_SIZE_VER0 64 /* Size of first published 'struct perf_event_attr' */ +#define PERF_ATTR_SIZE_VER1 72 /* Add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* Add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* Add: sample_regs_user */ + /* Add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* Add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* Add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ +#define PERF_ATTR_SIZE_VER9 144 /* add: config4 */ + +/* + * 'struct perf_event_attr' contains various attributes that define + * a performance event - most of them hardware related configuration + * details, but also a lot of behavioral switches and values implemented + * by the kernel. + */ +struct perf_event_attr { + + /* + * Major type: hardware/software/tracepoint/etc. + */ + __u32 type; + + /* + * Size of the attr structure, for forward/backwards compatibility. + */ + __u32 size; + + /* + * Type specific configuration information. + */ + __u64 config; + + union { + __u64 sample_period; + __u64 sample_freq; + }; + + __u64 sample_type; + __u64 read_format; + + __u64 disabled : 1, /* off by default */ + inherit : 1, /* children inherit it */ + pinned : 1, /* must always be on PMU */ + exclusive : 1, /* only group on PMU */ + exclude_user : 1, /* don't count user */ + exclude_kernel : 1, /* ditto kernel */ + exclude_hv : 1, /* ditto hypervisor */ + exclude_idle : 1, /* don't count when idle */ + mmap : 1, /* include mmap data */ + comm : 1, /* include comm data */ + freq : 1, /* use freq, not period */ + inherit_stat : 1, /* per task counts */ + enable_on_exec : 1, /* next exec enables */ + task : 1, /* trace fork/exit */ + watermark : 1, /* wakeup_watermark */ + /* + * precise_ip: + * + * 0 - SAMPLE_IP can have arbitrary skid + * 1 - SAMPLE_IP must have constant skid + * 2 - SAMPLE_IP requested to have 0 skid + * 3 - SAMPLE_IP must have 0 skid + * + * See also PERF_RECORD_MISC_EXACT_IP + */ + precise_ip : 2, /* skid constraint */ + mmap_data : 1, /* non-exec mmap data */ + sample_id_all : 1, /* sample_type all events */ + + exclude_host : 1, /* don't count in host */ + exclude_guest : 1, /* don't count in guest */ + + exclude_callchain_kernel : 1, /* exclude kernel callchains */ + exclude_callchain_user : 1, /* exclude user callchains */ + mmap2 : 1, /* include mmap with inode data */ + comm_exec : 1, /* flag comm events that are due to an exec */ + use_clockid : 1, /* use @clockid for time fields */ + context_switch : 1, /* context switch data */ + write_backward : 1, /* write ring buffer from end to beginning */ + namespaces : 1, /* include namespaces data */ + ksymbol : 1, /* include ksymbol events */ + bpf_event : 1, /* include BPF events */ + aux_output : 1, /* generate AUX records instead of events */ + cgroup : 1, /* include cgroup events */ + text_poke : 1, /* include text poke events */ + build_id : 1, /* use build ID in mmap2 events */ + inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ + remove_on_exec : 1, /* event is removed from task on exec */ + sigtrap : 1, /* send synchronous SIGTRAP on event */ + defer_callchain: 1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */ + defer_output : 1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */ + __reserved_1 : 24; + + union { + __u32 wakeup_events; /* wake up every n events */ + __u32 wakeup_watermark; /* bytes before wakeup */ + }; + + __u32 bp_type; + union { + __u64 bp_addr; + __u64 kprobe_func; /* for perf_kprobe */ + __u64 uprobe_path; /* for perf_uprobe */ + __u64 config1; /* extension of config */ + }; + union { + __u64 bp_len; + __u64 kprobe_addr; /* when kprobe_func == NULL */ + __u64 probe_offset; /* for perf_[k,u]probe */ + __u64 config2; /* extension of config1 */ + }; + __u64 branch_sample_type; /* enum perf_branch_sample_type */ + + /* + * Defines set of user regs to dump on samples. + * See asm/perf_regs.h for details. + */ + __u64 sample_regs_user; + + /* + * Defines size of the user stack to dump on samples. + */ + __u32 sample_stack_user; + + __s32 clockid; + /* + * Defines set of regs to dump for each sample + * state captured on: + * - precise = 0: PMU interrupt + * - precise > 0: sampled instruction + * + * See asm/perf_regs.h for details. + */ + __u64 sample_regs_intr; + + /* + * Wakeup watermark for AUX area + */ + __u32 aux_watermark; + + /* + * Max number of frame pointers in a callchain, should be + * lower than /proc/sys/kernel/perf_event_max_stack. + * + * Max number of entries of branch stack should be lower + * than the hardware limit. + */ + __u16 sample_max_stack; + + __u16 __reserved_2; + __u32 aux_sample_size; + + union { + __u32 aux_action; + struct { + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 29; + }; + }; + + /* + * User provided data if sigtrap=1, passed back to user via + * siginfo_t::si_perf_data, e.g. to permit user to identify the event. + * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be + * truncated accordingly on 32 bit architectures. + */ + __u64 sig_data; + + __u64 config3; /* extension of config2 */ + __u64 config4; /* extension of config3 */ +}; + +/* + * Structure used by below PERF_EVENT_IOC_QUERY_BPF command + * to query BPF programs attached to the same perf tracepoint + * as the given perf event. + */ +struct perf_event_query_bpf { + /* + * The below ids array length + */ + __u32 ids_len; + /* + * Set by the kernel to indicate the number of + * available programs + */ + __u32 prog_cnt; + /* + * User provided buffer to store program ids + */ + __u32 ids[]; +}; + +/* + * Ioctls that can be done on a perf event fd: + */ +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW ('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW ('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR ('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW ('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW ('$', 9, __u32) +#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) +#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW ('$', 11, struct perf_event_attr *) + +enum perf_event_ioc_flags { + PERF_IOC_FLAG_GROUP = 1U << 0, +}; + +/* + * Structure of the page that can be mapped via mmap + */ +struct perf_event_mmap_page { + __u32 version; /* version number of this structure */ + __u32 compat_version; /* lowest version this is compat with */ + + /* + * Bits needed to read the HW events in user-space. + * + * u32 seq, time_mult, time_shift, index, width; + * u64 count, enabled, running; + * u64 cyc, time_offset; + * s64 pmc = 0; + * + * do { + * seq = pc->lock; + * barrier() + * + * enabled = pc->time_enabled; + * running = pc->time_running; + * + * if (pc->cap_usr_time && enabled != running) { + * cyc = rdtsc(); + * time_offset = pc->time_offset; + * time_mult = pc->time_mult; + * time_shift = pc->time_shift; + * } + * + * index = pc->index; + * count = pc->offset; + * if (pc->cap_user_rdpmc && index) { + * width = pc->pmc_width; + * pmc = rdpmc(index - 1); + * } + * + * barrier(); + * } while (pc->lock != seq); + * + * NOTE: for obvious reason this only works on self-monitoring + * processes. + */ + __u32 lock; /* seqlock for synchronization */ + __u32 index; /* hardware event identifier */ + __s64 offset; /* add to hardware event value */ + __u64 time_enabled; /* time event active */ + __u64 time_running; /* time event on CPU */ + union { + __u64 capabilities; + struct { + __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */ + cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ + + cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ + cap_user_time : 1, /* The time_{shift,mult,offset} fields are used */ + cap_user_time_zero : 1, /* The time_zero field is used */ + cap_user_time_short : 1, /* the time_{cycle,mask} fields are used */ + cap_____res : 58; + }; + }; + + /* + * If cap_user_rdpmc this field provides the bit-width of the value + * read using the rdpmc() or equivalent instruction. This can be used + * to sign extend the result like: + * + * pmc <<= 64 - width; + * pmc >>= 64 - width; // signed shift right + * count += pmc; + */ + __u16 pmc_width; + + /* + * If cap_usr_time the below fields can be used to compute the time + * delta since time_enabled (in ns) using RDTSC or similar. + * + * u64 quot, rem; + * u64 delta; + * + * quot = (cyc >> time_shift); + * rem = cyc & (((u64)1 << time_shift) - 1); + * delta = time_offset + quot * time_mult + + * ((rem * time_mult) >> time_shift); + * + * Where time_offset,time_mult,time_shift and cyc are read in the + * seqcount loop described above. This delta can then be added to + * enabled and possible running (if index), improving the scaling: + * + * enabled += delta; + * if (index) + * running += delta; + * + * quot = count / running; + * rem = count % running; + * count = quot * enabled + (rem * enabled) / running; + */ + __u16 time_shift; + __u32 time_mult; + __u64 time_offset; + /* + * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated + * from sample timestamps. + * + * time = timestamp - time_zero; + * quot = time / time_mult; + * rem = time % time_mult; + * cyc = (quot << time_shift) + (rem << time_shift) / time_mult; + * + * And vice versa: + * + * quot = cyc >> time_shift; + * rem = cyc & (((u64)1 << time_shift) - 1); + * timestamp = time_zero + quot * time_mult + + * ((rem * time_mult) >> time_shift); + */ + __u64 time_zero; + + __u32 size; /* Header size up to __reserved[] fields. */ + __u32 __reserved_1; + + /* + * If cap_usr_time_short, the hardware clock is less than 64bit wide + * and we must compute the 'cyc' value, as used by cap_usr_time, as: + * + * cyc = time_cycles + ((cyc - time_cycles) & time_mask) + * + * NOTE: this form is explicitly chosen such that cap_usr_time_short + * is a correction on top of cap_usr_time, and code that doesn't + * know about cap_usr_time_short still works under the assumption + * the counter doesn't wrap. + */ + __u64 time_cycles; + __u64 time_mask; + + /* + * Hole for extension of the self monitor capabilities + */ + + __u8 __reserved[116*8]; /* align to 1k. */ + + /* + * Control data for the mmap() data buffer. + * + * User-space reading the @data_head value should issue an smp_rmb(), + * after reading this value. + * + * When the mapping is PROT_WRITE the @data_tail value should be + * written by user-space to reflect the last read data, after issuing + * an smp_mb() to separate the data read from the ->data_tail store. + * In this case the kernel will not over-write unread data. + * + * See perf_output_put_handle() for the data ordering. + * + * data_{offset,size} indicate the location and size of the perf record + * buffer within the mmapped area. + */ + __u64 data_head; /* head in the data section */ + __u64 data_tail; /* user-space written tail */ + __u64 data_offset; /* where the buffer starts */ + __u64 data_size; /* data buffer size */ + + /* + * AUX area is defined by aux_{offset,size} fields that should be set + * by the user-space, so that + * + * aux_offset >= data_offset + data_size + * + * prior to mmap()ing it. Size of the mmap()ed area should be aux_size. + * + * Ring buffer pointers aux_{head,tail} have the same semantics as + * data_{head,tail} and same ordering rules apply. + */ + __u64 aux_head; + __u64 aux_tail; + __u64 aux_offset; + __u64 aux_size; +}; + +/* + * The current state of perf_event_header::misc bits usage: + * ('|' used bit, '-' unused bit) + * + * 012 CDEF + * |||---------|||| + * + * Where: + * 0-2 CPUMODE_MASK + * + * C PROC_MAP_PARSE_TIMEOUT + * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT + * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT + * F (reserved) + */ + +#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) +#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) +#define PERF_RECORD_MISC_KERNEL (1 << 0) +#define PERF_RECORD_MISC_USER (2 << 0) +#define PERF_RECORD_MISC_HYPERVISOR (3 << 0) +#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) +#define PERF_RECORD_MISC_GUEST_USER (5 << 0) + +/* + * Indicates that /proc/PID/maps parsing are truncated by time out. + */ +#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12) +/* + * Following PERF_RECORD_MISC_* are used on different + * events, so can reuse the same bit position: + * + * PERF_RECORD_MISC_MMAP_DATA - PERF_RECORD_MMAP* events + * PERF_RECORD_MISC_COMM_EXEC - PERF_RECORD_COMM event + * PERF_RECORD_MISC_FORK_EXEC - PERF_RECORD_FORK event (perf internal) + * PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events + */ +#define PERF_RECORD_MISC_MMAP_DATA (1 << 13) +#define PERF_RECORD_MISC_COMM_EXEC (1 << 13) +#define PERF_RECORD_MISC_FORK_EXEC (1 << 13) +#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13) +/* + * These PERF_RECORD_MISC_* flags below are safely reused + * for the following events: + * + * PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events + * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event + * + * + * PERF_RECORD_MISC_EXACT_IP: + * Indicates that the content of PERF_SAMPLE_IP points to + * the actual instruction that triggered the event. See also + * perf_event_attr::precise_ip. + * + * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT: + * Indicates that thread was preempted in TASK_RUNNING state. + * + * PERF_RECORD_MISC_MMAP_BUILD_ID: + * Indicates that mmap2 event carries build ID data. + */ +#define PERF_RECORD_MISC_EXACT_IP (1 << 14) +#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) +#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14) +/* + * Reserve the last bit to indicate some extended misc field + */ +#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) + +struct perf_event_header { + __u32 type; + __u16 misc; + __u16 size; +}; + +struct perf_ns_link_info { + __u64 dev; + __u64 ino; +}; + +enum { + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ +}; + +enum perf_event_type { + + /* + * If perf_event_attr.sample_id_all is set then all event types will + * have the sample_type selected fields related to where/when + * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU, + * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed + * just after the perf_event_header and the fields already present for + * the existing fields, i.e. at the end of the payload. That way a newer + * perf.data file will be supported by older perf tools, with these new + * optional fields being ignored. + * + * struct sample_id { + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 id; } && PERF_SAMPLE_IDENTIFIER + * } && perf_event_attr::sample_id_all + * + * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The + * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed + * relative to header.size. + */ + + /* + * The MMAP events record the PROT_EXEC mappings so that we can + * correlate user-space IPs to code. They have the following structure: + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * char filename[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_MMAP = 1, + + /* + * struct { + * struct perf_event_header header; + * u64 id; + * u64 lost; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_LOST = 2, + + /* + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * char comm[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_COMM = 3, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * u64 time; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_EXIT = 4, + + /* + * struct { + * struct perf_event_header header; + * u64 time; + * u64 id; + * u64 stream_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_THROTTLE = 5, + PERF_RECORD_UNTHROTTLE = 6, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * u64 time; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_FORK = 7, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, tid; + * + * struct read_format values; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_READ = 8, + + /* + * struct { + * struct perf_event_header header; + * + * # + * # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. + * # The advantage of PERF_SAMPLE_IDENTIFIER is that its position + * # is fixed relative to header. + * # + * + * { u64 id; } && PERF_SAMPLE_IDENTIFIER + * { u64 ip; } && PERF_SAMPLE_IP + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 addr; } && PERF_SAMPLE_ADDR + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 period; } && PERF_SAMPLE_PERIOD + * + * { struct read_format values; } && PERF_SAMPLE_READ + * + * { u64 nr, + * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * + * { u32 size; + * char data[size];}&& PERF_SAMPLE_RAW + * + * { u64 nr; + * { u64 hw_idx; } && PERF_SAMPLE_BRANCH_HW_INDEX + * { u64 from, to, flags } lbr[nr]; + * # + * # The format of the counters is decided by the + * # "branch_counter_nr" and "branch_counter_width", + * # which are defined in the ABI. + * # + * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS + * } && PERF_SAMPLE_BRANCH_STACK + * + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * + * { union perf_sample_weight + * { + * u64 full; && PERF_SAMPLE_WEIGHT + * #if defined(__LITTLE_ENDIAN_BITFIELD) + * struct { + * u32 var1_dw; + * u16 var2_w; + * u16 var3_w; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #elif defined(__BIG_ENDIAN_BITFIELD) + * struct { + * u16 var3_w; + * u16 var2_w; + * u32 var1_dw; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #endif + * } + * } + * { u64 data_src; } && PERF_SAMPLE_DATA_SRC + * { u64 transaction; } && PERF_SAMPLE_TRANSACTION + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR + * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR + * { u64 cgroup;} && PERF_SAMPLE_CGROUP + * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE + * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX + * }; + */ + PERF_RECORD_SAMPLE = 9, + + /* + * The MMAP2 records are an augmented version of MMAP, they add + * maj, min, ino numbers to be used to uniquely identify each mapping + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * union { + * struct { + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * }; + * struct { + * u8 build_id_size; + * u8 __reserved_1; + * u16 __reserved_2; + * u8 build_id[20]; + * }; + * }; + * u32 prot, flags; + * char filename[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_MMAP2 = 10, + + /* + * Records that new data landed in the AUX buffer part. + * + * struct { + * struct perf_event_header header; + * + * u64 aux_offset; + * u64 aux_size; + * u64 flags; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX = 11, + + /* + * Indicates that instruction trace has started + * + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_ITRACE_START = 12, + + /* + * Records the dropped/lost sample number. + * + * struct { + * struct perf_event_header header; + * + * u64 lost; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_LOST_SAMPLES = 13, + + /* + * Records a context switch in or out (flagged by + * PERF_RECORD_MISC_SWITCH_OUT). See also + * PERF_RECORD_SWITCH_CPU_WIDE. + * + * struct { + * struct perf_event_header header; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH = 14, + + /* + * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and + * next_prev_tid that are the next (switching out) or previous + * (switching in) pid/tid. + * + * struct { + * struct perf_event_header header; + * u32 next_prev_pid; + * u32 next_prev_tid; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH_CPU_WIDE = 15, + + /* + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * u64 nr_namespaces; + * { u64 dev, inode; } [nr_namespaces]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_NAMESPACES = 16, + + /* + * Record ksymbol register/unregister events: + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u32 len; + * u16 ksym_type; + * u16 flags; + * char name[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_KSYMBOL = 17, + + /* + * Record BPF events: + * enum perf_bpf_event_type { + * PERF_BPF_EVENT_UNKNOWN = 0, + * PERF_BPF_EVENT_PROG_LOAD = 1, + * PERF_BPF_EVENT_PROG_UNLOAD = 2, + * }; + * + * struct { + * struct perf_event_header header; + * u16 type; + * u16 flags; + * u32 id; + * u8 tag[BPF_TAG_SIZE]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_BPF_EVENT = 18, + + /* + * struct { + * struct perf_event_header header; + * u64 id; + * char path[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CGROUP = 19, + + /* + * Records changes to kernel text i.e. self-modified code. 'old_len' is + * the number of old bytes, 'new_len' is the number of new bytes. Either + * 'old_len' or 'new_len' may be zero to indicate, for example, the + * addition or removal of a trampoline. 'bytes' contains the old bytes + * followed immediately by the new bytes. + * + * struct { + * struct perf_event_header header; + * u64 addr; + * u16 old_len; + * u16 new_len; + * u8 bytes[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_TEXT_POKE = 20, + + /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + + /* + * This user callchain capture was deferred until shortly before + * returning to user space. Previous samples would have kernel + * callchains only and they need to be stitched with this to make full + * callchains. + * + * struct { + * struct perf_event_header header; + * u64 cookie; + * u64 nr; + * u64 ips[nr]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CALLCHAIN_DEFERRED = 22, + + PERF_RECORD_MAX, /* non-ABI */ +}; + +enum perf_record_ksymbol_type { + PERF_RECORD_KSYMBOL_TYPE_UNKNOWN = 0, + PERF_RECORD_KSYMBOL_TYPE_BPF = 1, + /* + * Out of line code such as kprobe-replaced instructions or optimized + * kprobes or ftrace trampolines. + */ + PERF_RECORD_KSYMBOL_TYPE_OOL = 2, + PERF_RECORD_KSYMBOL_TYPE_MAX /* non-ABI */ +}; + +#define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) + +enum perf_bpf_event_type { + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ +}; + +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 + +enum perf_callchain_context { + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_USER_DEFERRED = (__u64)-640, + + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, + + PERF_CONTEXT_MAX = (__u64)-4095, +}; + +/** + * PERF_RECORD_AUX::flags bits + */ +#define PERF_AUX_FLAG_TRUNCATED 0x0001 /* Record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x0002 /* Snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x0004 /* Record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x0008 /* Sample collided with another */ +#define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ + +/* CoreSight PMU AUX buffer formats */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ + +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup ID, per-CPU mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ + +#if defined(__LITTLE_ENDIAN_BITFIELD) +union perf_mem_data_src { + __u64 val; + struct { + __u64 mem_op : 5, /* Type of opcode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_snoop : 5, /* Snoop mode */ + mem_lock : 2, /* Lock instr */ + mem_dtlb : 7, /* TLB access */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_remote : 1, /* Remote */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_blk : 3, /* Access blocked */ + mem_hops : 3, /* Hop level */ + mem_region : 5, /* cache/memory regions */ + mem_rsvd : 13; + }; +}; +#elif defined(__BIG_ENDIAN_BITFIELD) +union perf_mem_data_src { + __u64 val; + struct { + __u64 mem_rsvd : 13, + mem_region : 5, /* cache/memory regions */ + mem_hops : 3, /* Hop level */ + mem_blk : 3, /* Access blocked */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_remote : 1, /* Remote */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_dtlb : 7, /* TLB access */ + mem_lock : 2, /* Lock instr */ + mem_snoop : 5, /* Snoop mode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_op : 5; /* Type of opcode */ + }; +}; +#else +# error "Unknown endianness" +#endif + +/* Type of memory opcode: */ +#define PERF_MEM_OP_NA 0x0001 /* Not available */ +#define PERF_MEM_OP_LOAD 0x0002 /* Load instruction */ +#define PERF_MEM_OP_STORE 0x0004 /* Store instruction */ +#define PERF_MEM_OP_PFETCH 0x0008 /* Prefetch */ +#define PERF_MEM_OP_EXEC 0x0010 /* Code (execution) */ +#define PERF_MEM_OP_SHIFT 0 + +/* + * The PERF_MEM_LVL_* namespace is being deprecated to some extent in + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * We support this namespace in order to not break defined ABIs. + * + * Memory hierarchy (memory level, hit or miss) + */ +#define PERF_MEM_LVL_NA 0x0001 /* Not available */ +#define PERF_MEM_LVL_HIT 0x0002 /* Hit level */ +#define PERF_MEM_LVL_MISS 0x0004 /* Miss level */ +#define PERF_MEM_LVL_L1 0x0008 /* L1 */ +#define PERF_MEM_LVL_LFB 0x0010 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x0020 /* L2 */ +#define PERF_MEM_LVL_L3 0x0040 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x0080 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x0100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x0200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x0400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x0800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +#define PERF_MEM_REMOTE_REMOTE 0x0001 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x0001 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x0002 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x0003 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ +#define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ +#define PERF_MEM_LVLNUM_L0 0x0007 /* L0 */ +#define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x000b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x000c /* LFB / L1 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_RAM 0x000d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x000e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x000f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + +/* Snoop mode */ +#define PERF_MEM_SNOOP_NA 0x0001 /* Not available */ +#define PERF_MEM_SNOOP_NONE 0x0002 /* No snoop */ +#define PERF_MEM_SNOOP_HIT 0x0004 /* Snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x0008 /* Snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x0010 /* Snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +#define PERF_MEM_SNOOPX_FWD 0x0001 /* Forward */ +#define PERF_MEM_SNOOPX_PEER 0x0002 /* Transfer from peer */ +#define PERF_MEM_SNOOPX_SHIFT 38 + +/* Locked instruction */ +#define PERF_MEM_LOCK_NA 0x0001 /* Not available */ +#define PERF_MEM_LOCK_LOCKED 0x0002 /* Locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 + +/* TLB access */ +#define PERF_MEM_TLB_NA 0x0001 /* Not available */ +#define PERF_MEM_TLB_HIT 0x0002 /* Hit level */ +#define PERF_MEM_TLB_MISS 0x0004 /* Miss level */ +#define PERF_MEM_TLB_L1 0x0008 /* L1 */ +#define PERF_MEM_TLB_L2 0x0010 /* L2 */ +#define PERF_MEM_TLB_WK 0x0020 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x0040 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 + +/* Access blocked */ +#define PERF_MEM_BLK_NA 0x0001 /* Not available */ +#define PERF_MEM_BLK_DATA 0x0002 /* Data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x0004 /* Address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + +/* Hop level */ +#define PERF_MEM_HOPS_0 0x0001 /* Remote core, same node */ +#define PERF_MEM_HOPS_1 0x0002 /* Remote node, same socket */ +#define PERF_MEM_HOPS_2 0x0003 /* Remote socket, same board */ +#define PERF_MEM_HOPS_3 0x0004 /* Remote board */ +/* 5-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + +/* Cache/Memory region */ +#define PERF_MEM_REGION_NA 0x0 /* Invalid */ +#define PERF_MEM_REGION_RSVD 0x01 /* Reserved */ +#define PERF_MEM_REGION_L_SHARE 0x02 /* Local CA shared cache */ +#define PERF_MEM_REGION_L_NON_SHARE 0x03 /* Local CA non-shared cache */ +#define PERF_MEM_REGION_O_IO 0x04 /* Other CA IO agent */ +#define PERF_MEM_REGION_O_SHARE 0x05 /* Other CA shared cache */ +#define PERF_MEM_REGION_O_NON_SHARE 0x06 /* Other CA non-shared cache */ +#define PERF_MEM_REGION_MMIO 0x07 /* MMIO */ +#define PERF_MEM_REGION_MEM0 0x08 /* Memory region 0 */ +#define PERF_MEM_REGION_MEM1 0x09 /* Memory region 1 */ +#define PERF_MEM_REGION_MEM2 0x0a /* Memory region 2 */ +#define PERF_MEM_REGION_MEM3 0x0b /* Memory region 3 */ +#define PERF_MEM_REGION_MEM4 0x0c /* Memory region 4 */ +#define PERF_MEM_REGION_MEM5 0x0d /* Memory region 5 */ +#define PERF_MEM_REGION_MEM6 0x0e /* Memory region 6 */ +#define PERF_MEM_REGION_MEM7 0x0f /* Memory region 7 */ +#define PERF_MEM_REGION_SHIFT 46 + +#define PERF_MEM_S(a, s) \ + (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) + +/* + * Layout of single taken branch records: + * + * from: source instruction (may not always be a branch insn) + * to: branch target + * mispred: branch target was mispredicted + * predicted: branch target was predicted + * + * support for mispred, predicted is optional. In case it + * is not supported mispred = predicted = 0. + * + * in_tx: running in a hardware transaction + * abort: aborting a hardware transaction + * cycles: cycles from last branch (or 0 if not supported) + * type: branch type + * spec: branch speculation info (or 0 if not supported) + */ +struct perf_branch_entry { + __u64 from; + __u64 to; + __u64 mispred : 1, /* target mispredicted */ + predicted : 1, /* target predicted */ + in_tx : 1, /* in transaction */ + abort : 1, /* transaction abort */ + cycles : 16, /* cycle count to last branch */ + type : 4, /* branch type */ + spec : 2, /* branch speculation info */ + new_type : 4, /* additional branch type */ + priv : 3, /* privilege level */ + reserved : 31; +}; + +/* Size of used info bits in struct perf_branch_entry */ +#define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 + +union perf_sample_weight { + __u64 full; +#if defined(__LITTLE_ENDIAN_BITFIELD) + struct { + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; + }; +#elif defined(__BIG_ENDIAN_BITFIELD) + struct { + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; + }; +#else +# error "Unknown endianness" +#endif +}; + +#endif /* _UAPI_LINUX_PERF_EVENT_H */ diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h new file mode 100644 index 000000000..bd4b227ab --- /dev/null +++ b/tools/include/uapi/linux/pkt_cls.h @@ -0,0 +1,565 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_CLS_H +#define __LINUX_PKT_CLS_H + +#include +#include + +#define TC_COOKIE_MAX_SIZE 16 + +/* Action attributes */ +enum { + TCA_ACT_UNSPEC, + TCA_ACT_KIND, + TCA_ACT_OPTIONS, + TCA_ACT_INDEX, + TCA_ACT_STATS, + TCA_ACT_PAD, + TCA_ACT_COOKIE, + __TCA_ACT_MAX +}; + +#define TCA_ACT_MAX __TCA_ACT_MAX +#define TCA_OLD_COMPAT (TCA_ACT_MAX+1) +#define TCA_ACT_MAX_PRIO 32 +#define TCA_ACT_BIND 1 +#define TCA_ACT_NOBIND 0 +#define TCA_ACT_UNBIND 1 +#define TCA_ACT_NOUNBIND 0 +#define TCA_ACT_REPLACE 1 +#define TCA_ACT_NOREPLACE 0 + +#define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 +#define TC_ACT_RECLASSIFY 1 +#define TC_ACT_SHOT 2 +#define TC_ACT_PIPE 3 +#define TC_ACT_STOLEN 4 +#define TC_ACT_QUEUED 5 +#define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu" + * and don't further process the frame + * in hardware. For sw path, this is + * equivalent of TC_ACT_STOLEN - drop + * the skb and act like everything + * is alright. + */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP + +/* There is a special kind of actions called "extended actions", + * which need a value parameter. These have a local opcode located in + * the highest nibble, starting from 1. The rest of the bits + * are used to carry the value. These two parts together make + * a combined opcode. + */ +#define __TC_ACT_EXT_SHIFT 28 +#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) +#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) + +#define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN + +/* Action type identifiers*/ +enum { + TCA_ID_UNSPEC=0, + TCA_ID_POLICE=1, + /* other actions go here */ + __TCA_ID_MAX=255 +}; + +#define TCA_ID_MAX __TCA_ID_MAX + +struct tc_police { + __u32 index; + int action; +#define TC_POLICE_UNSPEC TC_ACT_UNSPEC +#define TC_POLICE_OK TC_ACT_OK +#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY +#define TC_POLICE_SHOT TC_ACT_SHOT +#define TC_POLICE_PIPE TC_ACT_PIPE + + __u32 limit; + __u32 burst; + __u32 mtu; + struct tc_ratespec rate; + struct tc_ratespec peakrate; + int refcnt; + int bindcnt; + __u32 capab; +}; + +struct tcf_t { + __u64 install; + __u64 lastuse; + __u64 expires; + __u64 firstuse; +}; + +struct tc_cnt { + int refcnt; + int bindcnt; +}; + +#define tc_gen \ + __u32 index; \ + __u32 capab; \ + int action; \ + int refcnt; \ + int bindcnt + +enum { + TCA_POLICE_UNSPEC, + TCA_POLICE_TBF, + TCA_POLICE_RATE, + TCA_POLICE_PEAKRATE, + TCA_POLICE_AVRATE, + TCA_POLICE_RESULT, + TCA_POLICE_TM, + TCA_POLICE_PAD, + __TCA_POLICE_MAX +#define TCA_POLICE_RESULT TCA_POLICE_RESULT +}; + +#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1) + +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */ +#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */ +#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */ +#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */ +#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */ + +/* U32 filters */ + +#define TC_U32_HTID(h) ((h)&0xFFF00000) +#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20) +#define TC_U32_HASH(h) (((h)>>12)&0xFF) +#define TC_U32_NODE(h) ((h)&0xFFF) +#define TC_U32_KEY(h) ((h)&0xFFFFF) +#define TC_U32_UNSPEC 0 +#define TC_U32_ROOT (0xFFF00000) + +enum { + TCA_U32_UNSPEC, + TCA_U32_CLASSID, + TCA_U32_HASH, + TCA_U32_LINK, + TCA_U32_DIVISOR, + TCA_U32_SEL, + TCA_U32_POLICE, + TCA_U32_ACT, + TCA_U32_INDEV, + TCA_U32_PCNT, + TCA_U32_MARK, + TCA_U32_FLAGS, + TCA_U32_PAD, + __TCA_U32_MAX +}; + +#define TCA_U32_MAX (__TCA_U32_MAX - 1) + +struct tc_u32_key { + __be32 mask; + __be32 val; + int off; + int offmask; +}; + +struct tc_u32_sel { + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + struct tc_u32_key keys[]; +}; + +struct tc_u32_mark { + __u32 val; + __u32 mask; + __u32 success; +}; + +struct tc_u32_pcnt { + __u64 rcnt; + __u64 rhit; + __u64 kcnts[]; +}; + +/* Flags */ + +#define TC_U32_TERMINAL 1 +#define TC_U32_OFFSET 2 +#define TC_U32_VAROFFSET 4 +#define TC_U32_EAT 8 + +#define TC_U32_MAXDEPTH 8 + +/* ROUTE filter */ + +enum { + TCA_ROUTE4_UNSPEC, + TCA_ROUTE4_CLASSID, + TCA_ROUTE4_TO, + TCA_ROUTE4_FROM, + TCA_ROUTE4_IIF, + TCA_ROUTE4_POLICE, + TCA_ROUTE4_ACT, + __TCA_ROUTE4_MAX +}; + +#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1) + + +/* FW filter */ + +enum { + TCA_FW_UNSPEC, + TCA_FW_CLASSID, + TCA_FW_POLICE, + TCA_FW_INDEV, + TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ + TCA_FW_MASK, + __TCA_FW_MAX +}; + +#define TCA_FW_MAX (__TCA_FW_MAX - 1) + +/* Flow filter */ + +enum { + FLOW_KEY_SRC, + FLOW_KEY_DST, + FLOW_KEY_PROTO, + FLOW_KEY_PROTO_SRC, + FLOW_KEY_PROTO_DST, + FLOW_KEY_IIF, + FLOW_KEY_PRIORITY, + FLOW_KEY_MARK, + FLOW_KEY_NFCT, + FLOW_KEY_NFCT_SRC, + FLOW_KEY_NFCT_DST, + FLOW_KEY_NFCT_PROTO_SRC, + FLOW_KEY_NFCT_PROTO_DST, + FLOW_KEY_RTCLASSID, + FLOW_KEY_SKUID, + FLOW_KEY_SKGID, + FLOW_KEY_VLAN_TAG, + FLOW_KEY_RXHASH, + __FLOW_KEY_MAX, +}; + +#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1) + +enum { + FLOW_MODE_MAP, + FLOW_MODE_HASH, +}; + +enum { + TCA_FLOW_UNSPEC, + TCA_FLOW_KEYS, + TCA_FLOW_MODE, + TCA_FLOW_BASECLASS, + TCA_FLOW_RSHIFT, + TCA_FLOW_ADDEND, + TCA_FLOW_MASK, + TCA_FLOW_XOR, + TCA_FLOW_DIVISOR, + TCA_FLOW_ACT, + TCA_FLOW_POLICE, + TCA_FLOW_EMATCHES, + TCA_FLOW_PERTURB, + __TCA_FLOW_MAX +}; + +#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1) + +/* Basic filter */ + +enum { + TCA_BASIC_UNSPEC, + TCA_BASIC_CLASSID, + TCA_BASIC_EMATCHES, + TCA_BASIC_ACT, + TCA_BASIC_POLICE, + __TCA_BASIC_MAX +}; + +#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1) + + +/* Cgroup classifier */ + +enum { + TCA_CGROUP_UNSPEC, + TCA_CGROUP_ACT, + TCA_CGROUP_POLICE, + TCA_CGROUP_EMATCHES, + __TCA_CGROUP_MAX, +}; + +#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1) + +/* BPF classifier */ + +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + +enum { + TCA_BPF_UNSPEC, + TCA_BPF_ACT, + TCA_BPF_POLICE, + TCA_BPF_CLASSID, + TCA_BPF_OPS_LEN, + TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, + TCA_BPF_FLAGS, + TCA_BPF_FLAGS_GEN, + TCA_BPF_TAG, + TCA_BPF_ID, + __TCA_BPF_MAX, +}; + +#define TCA_BPF_MAX (__TCA_BPF_MAX - 1) + +/* Flower classifier */ + +enum { + TCA_FLOWER_UNSPEC, + TCA_FLOWER_CLASSID, + TCA_FLOWER_INDEV, + TCA_FLOWER_ACT, + TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_TYPE, /* be16 */ + TCA_FLOWER_KEY_IP_PROTO, /* u8 */ + TCA_FLOWER_KEY_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_TCP_SRC, /* be16 */ + TCA_FLOWER_KEY_TCP_DST, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC, /* be16 */ + TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, + TCA_FLOWER_KEY_VLAN_ID, /* be16 */ + TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + + TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */ + + TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST, /* be16 */ + + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ + + TCA_FLOWER_KEY_FLAGS, /* be32 */ + TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ + + TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + + TCA_FLOWER_KEY_ARP_SIP, /* be32 */ + TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_OP, /* u8 */ + TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */ + TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */ + + TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */ + TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */ + TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */ + TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */ + + TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */ + TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */ + + TCA_FLOWER_KEY_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_CVLAN_ID, /* be16 */ + TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + + TCA_FLOWER_IN_HW_COUNT, + + __TCA_FLOWER_MAX, +}; + +#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, + TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ + * attributes + */ + __TCA_FLOWER_KEY_ENC_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1) + +enum { + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), +}; + +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + +/* Extended Matches */ + +struct tcf_ematch_tree_hdr { + __u16 nmatches; + __u16 progid; +}; + +enum { + TCA_EMATCH_TREE_UNSPEC, + TCA_EMATCH_TREE_HDR, + TCA_EMATCH_TREE_LIST, + __TCA_EMATCH_TREE_MAX +}; +#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1) + +struct tcf_ematch_hdr { + __u16 matchid; + __u16 kind; + __u16 flags; + __u16 pad; /* currently unused */ +}; + +/* 0 1 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 + * +-----------------------+-+-+---+ + * | Unused |S|I| R | + * +-----------------------+-+-+---+ + * + * R(2) ::= relation to next ematch + * where: 0 0 END (last ematch) + * 0 1 AND + * 1 0 OR + * 1 1 Unused (invalid) + * I(1) ::= invert result + * S(1) ::= simple payload + */ +#define TCF_EM_REL_END 0 +#define TCF_EM_REL_AND (1<<0) +#define TCF_EM_REL_OR (1<<1) +#define TCF_EM_INVERT (1<<2) +#define TCF_EM_SIMPLE (1<<3) + +#define TCF_EM_REL_MASK 3 +#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK) + +enum { + TCF_LAYER_LINK, + TCF_LAYER_NETWORK, + TCF_LAYER_TRANSPORT, + __TCF_LAYER_MAX +}; +#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1) + +/* Ematch type assignments + * 1..32767 Reserved for ematches inside kernel tree + * 32768..65535 Free to use, not reliable + */ +#define TCF_EM_CONTAINER 0 +#define TCF_EM_CMP 1 +#define TCF_EM_NBYTE 2 +#define TCF_EM_U32 3 +#define TCF_EM_META 4 +#define TCF_EM_TEXT 5 +#define TCF_EM_VLAN 6 +#define TCF_EM_CANID 7 +#define TCF_EM_IPSET 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 + +enum { + TCF_EM_PROG_TC +}; + +enum { + TCF_EM_OPND_EQ, + TCF_EM_OPND_GT, + TCF_EM_OPND_LT +}; + +#endif diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h new file mode 100644 index 000000000..587481a19 --- /dev/null +++ b/tools/include/uapi/linux/pkt_sched.h @@ -0,0 +1,1055 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_SCHED_H +#define __LINUX_PKT_SCHED_H + +#include + +/* Logical priority bands not depending on specific packet scheduler. + Every scheduler will map them to real traffic classes, if it has + no more precise mechanism to classify packets. + + These numbers have no special meaning, though their coincidence + with obsolete IPv6 values is not occasional :-). New IPv6 drafts + preferred full anarchy inspired by diffserv group. + + Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy + class, actually, as rule it will be handled with more care than + filler or even bulk. + */ + +#define TC_PRIO_BESTEFFORT 0 +#define TC_PRIO_FILLER 1 +#define TC_PRIO_BULK 2 +#define TC_PRIO_INTERACTIVE_BULK 4 +#define TC_PRIO_INTERACTIVE 6 +#define TC_PRIO_CONTROL 7 + +#define TC_PRIO_MAX 15 + +/* Generic queue statistics, available for all the elements. + Particular schedulers may have also their private records. + */ + +struct tc_stats { + __u64 bytes; /* Number of enqueued bytes */ + __u32 packets; /* Number of enqueued packets */ + __u32 drops; /* Packets dropped because of lack of resources */ + __u32 overlimits; /* Number of throttle events when this + * flow goes out of allocated bandwidth */ + __u32 bps; /* Current flow byte rate */ + __u32 pps; /* Current flow packet rate */ + __u32 qlen; + __u32 backlog; +}; + +struct tc_estimator { + signed char interval; + unsigned char ewma_log; +}; + +/* "Handles" + --------- + + All the traffic control objects have 32bit identifiers, or "handles". + + They can be considered as opaque numbers from user API viewpoint, + but actually they always consist of two fields: major and + minor numbers, which are interpreted by kernel specially, + that may be used by applications, though not recommended. + + F.e. qdisc handles always have minor number equal to zero, + classes (or flows) have major equal to parent qdisc major, and + minor uniquely identifying class inside qdisc. + + Macros to manipulate handles: + */ + +#define TC_H_MAJ_MASK (0xFFFF0000U) +#define TC_H_MIN_MASK (0x0000FFFFU) +#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK) +#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK) +#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK)) + +#define TC_H_UNSPEC (0U) +#define TC_H_ROOT (0xFFFFFFFFU) +#define TC_H_INGRESS (0xFFFFFFF1U) +#define TC_H_CLSACT TC_H_INGRESS + +#define TC_H_MIN_PRIORITY 0xFFE0U +#define TC_H_MIN_INGRESS 0xFFF2U +#define TC_H_MIN_EGRESS 0xFFF3U + +/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */ +enum tc_link_layer { + TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */ + TC_LINKLAYER_ETHERNET, + TC_LINKLAYER_ATM, +}; +#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */ + +struct tc_ratespec { + unsigned char cell_log; + __u8 linklayer; /* lower 4 bits */ + unsigned short overhead; + short cell_align; + unsigned short mpu; + __u32 rate; +}; + +#define TC_RTAB_SIZE 1024 + +struct tc_sizespec { + unsigned char cell_log; + unsigned char size_log; + short cell_align; + int overhead; + unsigned int linklayer; + unsigned int mpu; + unsigned int mtu; + unsigned int tsize; +}; + +enum { + TCA_STAB_UNSPEC, + TCA_STAB_BASE, + TCA_STAB_DATA, + __TCA_STAB_MAX +}; + +#define TCA_STAB_MAX (__TCA_STAB_MAX - 1) + +/* FIFO section */ + +struct tc_fifo_qopt { + __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */ +}; + +/* SKBPRIO section */ + +/* + * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1). + * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able + * to map one to one the DS field of IPV4 and IPV6 headers. + * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY. + */ + +#define SKBPRIO_MAX_PRIORITY 64 + +struct tc_skbprio_qopt { + __u32 limit; /* Queue length in packets. */ +}; + +/* PRIO section */ + +#define TCQ_PRIO_BANDS 16 +#define TCQ_MIN_PRIO_BANDS 2 + +struct tc_prio_qopt { + int bands; /* Number of bands */ + __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */ +}; + +/* MULTIQ section */ + +struct tc_multiq_qopt { + __u16 bands; /* Number of bands */ + __u16 max_bands; /* Maximum number of queues */ +}; + +/* PLUG section */ + +#define TCQ_PLUG_BUFFER 0 +#define TCQ_PLUG_RELEASE_ONE 1 +#define TCQ_PLUG_RELEASE_INDEFINITE 2 +#define TCQ_PLUG_LIMIT 3 + +struct tc_plug_qopt { + /* TCQ_PLUG_BUFFER: Inset a plug into the queue and + * buffer any incoming packets + * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head + * to beginning of the next plug. + * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue. + * Stop buffering packets until the next TCQ_PLUG_BUFFER + * command is received (just act as a pass-thru queue). + * TCQ_PLUG_LIMIT: Increase/decrease queue size + */ + int action; + __u32 limit; +}; + +/* TBF section */ + +struct tc_tbf_qopt { + struct tc_ratespec rate; + struct tc_ratespec peakrate; + __u32 limit; + __u32 buffer; + __u32 mtu; +}; + +enum { + TCA_TBF_UNSPEC, + TCA_TBF_PARMS, + TCA_TBF_RTAB, + TCA_TBF_PTAB, + TCA_TBF_RATE64, + TCA_TBF_PRATE64, + TCA_TBF_BURST, + TCA_TBF_PBURST, + TCA_TBF_PAD, + __TCA_TBF_MAX, +}; + +#define TCA_TBF_MAX (__TCA_TBF_MAX - 1) + + +/* TEQL section */ + +/* TEQL does not require any parameters */ + +/* SFQ section */ + +struct tc_sfq_qopt { + unsigned quantum; /* Bytes per round allocated to flow */ + int perturb_period; /* Period of hash perturbation */ + __u32 limit; /* Maximal packets in queue */ + unsigned divisor; /* Hash divisor */ + unsigned flows; /* Maximal number of flows */ +}; + +struct tc_sfqred_stats { + __u32 prob_drop; /* Early drops, below max threshold */ + __u32 forced_drop; /* Early drops, after max threshold */ + __u32 prob_mark; /* Marked packets, below max threshold */ + __u32 forced_mark; /* Marked packets, after max threshold */ + __u32 prob_mark_head; /* Marked packets, below max threshold */ + __u32 forced_mark_head;/* Marked packets, after max threshold */ +}; + +struct tc_sfq_qopt_v1 { + struct tc_sfq_qopt v0; + unsigned int depth; /* max number of packets per flow */ + unsigned int headdrop; +/* SFQRED parameters */ + __u32 limit; /* HARD maximal flow queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; + __u32 max_P; /* probability, high resolution */ +/* SFQRED stats */ + struct tc_sfqred_stats stats; +}; + + +struct tc_sfq_xstats { + __s32 allot; +}; + +/* RED section */ + +enum { + TCA_RED_UNSPEC, + TCA_RED_PARMS, + TCA_RED_STAB, + TCA_RED_MAX_P, + __TCA_RED_MAX, +}; + +#define TCA_RED_MAX (__TCA_RED_MAX - 1) + +struct tc_red_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; +#define TC_RED_ECN 1 +#define TC_RED_HARDDROP 2 +#define TC_RED_ADAPTATIVE 4 +}; + +struct tc_red_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ +}; + +/* GRED section */ + +#define MAX_DPs 16 + +enum { + TCA_GRED_UNSPEC, + TCA_GRED_PARMS, + TCA_GRED_STAB, + TCA_GRED_DPS, + TCA_GRED_MAX_P, + TCA_GRED_LIMIT, + TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */ + __TCA_GRED_MAX, +}; + +#define TCA_GRED_MAX (__TCA_GRED_MAX - 1) + +enum { + TCA_GRED_VQ_ENTRY_UNSPEC, + TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */ + __TCA_GRED_VQ_ENTRY_MAX, +}; +#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1) + +enum { + TCA_GRED_VQ_UNSPEC, + TCA_GRED_VQ_PAD, + TCA_GRED_VQ_DP, /* u32 */ + TCA_GRED_VQ_STAT_BYTES, /* u64 */ + TCA_GRED_VQ_STAT_PACKETS, /* u32 */ + TCA_GRED_VQ_STAT_BACKLOG, /* u32 */ + TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */ + TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */ + TCA_GRED_VQ_STAT_PDROP, /* u32 */ + TCA_GRED_VQ_STAT_OTHER, /* u32 */ + TCA_GRED_VQ_FLAGS, /* u32 */ + __TCA_GRED_VQ_MAX +}; + +#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1) + +struct tc_gred_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + __u32 DP; /* up to 2^32 DPs */ + __u32 backlog; + __u32 qave; + __u32 forced; + __u32 early; + __u32 other; + __u32 pdrop; + __u8 Wlog; /* log(W) */ + __u8 Plog; /* log(P_max/(qth_max-qth_min)) */ + __u8 Scell_log; /* cell size for idle damping */ + __u8 prio; /* prio of this VQ */ + __u32 packets; + __u32 bytesin; +}; + +/* gred setup */ +struct tc_gred_sopt { + __u32 DPs; + __u32 def_DP; + __u8 grio; + __u8 flags; + __u16 pad1; +}; + +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + TCA_CHOKE_MAX_P, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + +/* HTB section */ +#define TC_HTB_NUMPRIO 8 +#define TC_HTB_MAXDEPTH 8 +#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */ + +struct tc_htb_opt { + struct tc_ratespec rate; + struct tc_ratespec ceil; + __u32 buffer; + __u32 cbuffer; + __u32 quantum; + __u32 level; /* out only */ + __u32 prio; +}; +struct tc_htb_glob { + __u32 version; /* to match HTB/TC */ + __u32 rate2quantum; /* bps->quantum divisor */ + __u32 defcls; /* default class number */ + __u32 debug; /* debug flags */ + + /* stats */ + __u32 direct_pkts; /* count of non shaped packets */ +}; +enum { + TCA_HTB_UNSPEC, + TCA_HTB_PARMS, + TCA_HTB_INIT, + TCA_HTB_CTAB, + TCA_HTB_RTAB, + TCA_HTB_DIRECT_QLEN, + TCA_HTB_RATE64, + TCA_HTB_CEIL64, + TCA_HTB_PAD, + TCA_HTB_OFFLOAD, + __TCA_HTB_MAX, +}; + +#define TCA_HTB_MAX (__TCA_HTB_MAX - 1) + +struct tc_htb_xstats { + __u32 lends; + __u32 borrows; + __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */ + __s32 tokens; + __s32 ctokens; +}; + +/* HFSC section */ + +struct tc_hfsc_qopt { + __u16 defcls; /* default class */ +}; + +struct tc_service_curve { + __u32 m1; /* slope of the first segment in bps */ + __u32 d; /* x-projection of the first segment in us */ + __u32 m2; /* slope of the second segment in bps */ +}; + +struct tc_hfsc_stats { + __u64 work; /* total work done */ + __u64 rtwork; /* work done by real-time criteria */ + __u32 period; /* current period */ + __u32 level; /* class level in hierarchy */ +}; + +enum { + TCA_HFSC_UNSPEC, + TCA_HFSC_RSC, + TCA_HFSC_FSC, + TCA_HFSC_USC, + __TCA_HFSC_MAX, +}; + +#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1) + +/* Network emulator */ + +enum { + TCA_NETEM_UNSPEC, + TCA_NETEM_CORR, + TCA_NETEM_DELAY_DIST, + TCA_NETEM_REORDER, + TCA_NETEM_CORRUPT, + TCA_NETEM_LOSS, + TCA_NETEM_RATE, + TCA_NETEM_ECN, + TCA_NETEM_RATE64, + TCA_NETEM_PAD, + TCA_NETEM_LATENCY64, + TCA_NETEM_JITTER64, + TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, + __TCA_NETEM_MAX, +}; + +#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1) + +struct tc_netem_qopt { + __u32 latency; /* added delay (us) */ + __u32 limit; /* fifo limit (packets) */ + __u32 loss; /* random packet loss (0=none ~0=100%) */ + __u32 gap; /* re-ordering gap (0 for none) */ + __u32 duplicate; /* random packet dup (0=none ~0=100%) */ + __u32 jitter; /* random jitter in latency (us) */ +}; + +struct tc_netem_corr { + __u32 delay_corr; /* delay correlation */ + __u32 loss_corr; /* packet loss correlation */ + __u32 dup_corr; /* duplicate correlation */ +}; + +struct tc_netem_reorder { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_corrupt { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_rate { + __u32 rate; /* byte/s */ + __s32 packet_overhead; + __u32 cell_size; + __s32 cell_overhead; +}; + +struct tc_netem_slot { + __s64 min_delay; /* nsec */ + __s64 max_delay; + __s32 max_packets; + __s32 max_bytes; + __s64 dist_delay; /* nsec */ + __s64 dist_jitter; /* nsec */ +}; + +enum { + NETEM_LOSS_UNSPEC, + NETEM_LOSS_GI, /* General Intuitive - 4 state model */ + NETEM_LOSS_GE, /* Gilbert Elliot models */ + __NETEM_LOSS_MAX +}; +#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) + +/* State transition probabilities for 4 state model */ +struct tc_netem_gimodel { + __u32 p13; + __u32 p31; + __u32 p32; + __u32 p14; + __u32 p23; +}; + +/* Gilbert-Elliot models */ +struct tc_netem_gemodel { + __u32 p; + __u32 r; + __u32 h; + __u32 k1; +}; + +#define NETEM_DIST_SCALE 8192 +#define NETEM_DIST_MAX 16384 + +/* DRR */ + +enum { + TCA_DRR_UNSPEC, + TCA_DRR_QUANTUM, + __TCA_DRR_MAX +}; + +#define TCA_DRR_MAX (__TCA_DRR_MAX - 1) + +struct tc_drr_stats { + __u32 deficit; +}; + +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +enum { + TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */ + TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */ + __TC_MQPRIO_HW_OFFLOAD_MAX +}; + +#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) + +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + +/* SFB */ + +enum { + TCA_SFB_UNSPEC, + TCA_SFB_PARMS, + __TCA_SFB_MAX, +}; + +#define TCA_SFB_MAX (__TCA_SFB_MAX - 1) + +/* + * Note: increment, decrement are Q0.16 fixed-point values. + */ +struct tc_sfb_qopt { + __u32 rehash_interval; /* delay between hash move, in ms */ + __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */ + __u32 max; /* max len of qlen_min */ + __u32 bin_size; /* maximum queue length per bin */ + __u32 increment; /* probability increment, (d1 in Blue) */ + __u32 decrement; /* probability decrement, (d2 in Blue) */ + __u32 limit; /* max SFB queue length */ + __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */ + __u32 penalty_burst; +}; + +struct tc_sfb_xstats { + __u32 earlydrop; + __u32 penaltydrop; + __u32 bucketdrop; + __u32 queuedrop; + __u32 childdrop; /* drops in child qdisc */ + __u32 marked; + __u32 maxqlen; + __u32 maxprob; + __u32 avgprob; +}; + +#define SFB_MAX_PROB 0xFFFF + +/* QFQ */ +enum { + TCA_QFQ_UNSPEC, + TCA_QFQ_WEIGHT, + TCA_QFQ_LMAX, + __TCA_QFQ_MAX +}; + +#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1) + +struct tc_qfq_stats { + __u32 weight; + __u32 lmax; +}; + +/* CODEL */ + +enum { + TCA_CODEL_UNSPEC, + TCA_CODEL_TARGET, + TCA_CODEL_LIMIT, + TCA_CODEL_INTERVAL, + TCA_CODEL_ECN, + TCA_CODEL_CE_THRESHOLD, + __TCA_CODEL_MAX +}; + +#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1) + +struct tc_codel_xstats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 count; /* how many drops we've done since the last time we + * entered dropping state + */ + __u32 lastcount; /* count at entry to dropping state */ + __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */ + __s32 drop_next; /* time to drop next packet */ + __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */ + __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */ + __u32 dropping; /* are we in dropping state ? */ + __u32 ce_mark; /* number of CE marked packets because of ce_threshold */ +}; + +/* FQ_CODEL */ + +enum { + TCA_FQ_CODEL_UNSPEC, + TCA_FQ_CODEL_TARGET, + TCA_FQ_CODEL_LIMIT, + TCA_FQ_CODEL_INTERVAL, + TCA_FQ_CODEL_ECN, + TCA_FQ_CODEL_FLOWS, + TCA_FQ_CODEL_QUANTUM, + TCA_FQ_CODEL_CE_THRESHOLD, + TCA_FQ_CODEL_DROP_BATCH_SIZE, + TCA_FQ_CODEL_MEMORY_LIMIT, + __TCA_FQ_CODEL_MAX +}; + +#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1) + +enum { + TCA_FQ_CODEL_XSTATS_QDISC, + TCA_FQ_CODEL_XSTATS_CLASS, +}; + +struct tc_fq_codel_qd_stats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 drop_overlimit; /* number of time max qdisc + * packet limit was hit + */ + __u32 ecn_mark; /* number of packets we ECN marked + * instead of being dropped + */ + __u32 new_flow_count; /* number of time packets + * created a 'new flow' + */ + __u32 new_flows_len; /* count of flows in new list */ + __u32 old_flows_len; /* count of flows in old list */ + __u32 ce_mark; /* packets above ce_threshold */ + __u32 memory_usage; /* in bytes */ + __u32 drop_overmemory; +}; + +struct tc_fq_codel_cl_stats { + __s32 deficit; + __u32 ldelay; /* in-queue delay seen by most recently + * dequeued packet + */ + __u32 count; + __u32 lastcount; + __u32 dropping; + __s32 drop_next; +}; + +struct tc_fq_codel_xstats { + __u32 type; + union { + struct tc_fq_codel_qd_stats qdisc_stats; + struct tc_fq_codel_cl_stats class_stats; + }; +}; + +/* FQ */ + +enum { + TCA_FQ_UNSPEC, + + TCA_FQ_PLIMIT, /* limit of total number of packets in queue */ + + TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */ + + TCA_FQ_QUANTUM, /* RR quantum */ + + TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */ + + TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */ + + TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */ + + TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */ + + TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */ + + TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */ + + TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */ + + TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */ + + TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */ + + __TCA_FQ_MAX +}; + +#define TCA_FQ_MAX (__TCA_FQ_MAX - 1) + +struct tc_fq_qd_stats { + __u64 gc_flows; + __u64 highprio_packets; + __u64 tcp_retrans; + __u64 throttled; + __u64 flows_plimit; + __u64 pkts_too_long; + __u64 allocation_errors; + __s64 time_next_delayed_flow; + __u32 flows; + __u32 inactive_flows; + __u32 throttled_flows; + __u32 unthrottle_latency_ns; + __u64 ce_mark; /* packets above ce_threshold */ +}; + +/* Heavy-Hitter Filter */ + +enum { + TCA_HHF_UNSPEC, + TCA_HHF_BACKLOG_LIMIT, + TCA_HHF_QUANTUM, + TCA_HHF_HH_FLOWS_LIMIT, + TCA_HHF_RESET_TIMEOUT, + TCA_HHF_ADMIT_BYTES, + TCA_HHF_EVICT_TIMEOUT, + TCA_HHF_NON_HH_WEIGHT, + __TCA_HHF_MAX +}; + +#define TCA_HHF_MAX (__TCA_HHF_MAX - 1) + +struct tc_hhf_xstats { + __u32 drop_overlimit; /* number of times max qdisc packet limit + * was hit + */ + __u32 hh_overlimit; /* number of times max heavy-hitters was hit */ + __u32 hh_tot_count; /* number of captured heavy-hitters so far */ + __u32 hh_cur_count; /* number of current heavy-hitters */ +}; + +/* PIE */ +enum { + TCA_PIE_UNSPEC, + TCA_PIE_TARGET, + TCA_PIE_LIMIT, + TCA_PIE_TUPDATE, + TCA_PIE_ALPHA, + TCA_PIE_BETA, + TCA_PIE_ECN, + TCA_PIE_BYTEMODE, + __TCA_PIE_MAX +}; +#define TCA_PIE_MAX (__TCA_PIE_MAX - 1) + +struct tc_pie_xstats { + __u32 prob; /* current probability */ + __u32 delay; /* current delay in ms */ + __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */ + __u32 packets_in; /* total number of packets enqueued */ + __u32 dropped; /* packets dropped due to pie_action */ + __u32 overlimit; /* dropped due to lack of space in queue */ + __u32 maxq; /* maximum queue size */ + __u32 ecn_mark; /* packets marked with ecn*/ +}; + +/* CBS */ +struct tc_cbs_qopt { + __u8 offload; + __u8 _pad[3]; + __s32 hicredit; + __s32 locredit; + __s32 idleslope; + __s32 sendslope; +}; + +enum { + TCA_CBS_UNSPEC, + TCA_CBS_PARMS, + __TCA_CBS_MAX, +}; + +#define TCA_CBS_MAX (__TCA_CBS_MAX - 1) + + +/* ETF */ +struct tc_etf_qopt { + __s32 delta; + __s32 clockid; + __u32 flags; +#define TC_ETF_DEADLINE_MODE_ON BIT(0) +#define TC_ETF_OFFLOAD_ON BIT(1) +}; + +enum { + TCA_ETF_UNSPEC, + TCA_ETF_PARMS, + __TCA_ETF_MAX, +}; + +#define TCA_ETF_MAX (__TCA_ETF_MAX - 1) + + +/* CAKE */ +enum { + TCA_CAKE_UNSPEC, + TCA_CAKE_PAD, + TCA_CAKE_BASE_RATE64, + TCA_CAKE_DIFFSERV_MODE, + TCA_CAKE_ATM, + TCA_CAKE_FLOW_MODE, + TCA_CAKE_OVERHEAD, + TCA_CAKE_RTT, + TCA_CAKE_TARGET, + TCA_CAKE_AUTORATE, + TCA_CAKE_MEMORY, + TCA_CAKE_NAT, + TCA_CAKE_RAW, + TCA_CAKE_WASH, + TCA_CAKE_MPU, + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, + __TCA_CAKE_MAX +}; +#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) + +enum { + __TCA_CAKE_STATS_INVALID, + TCA_CAKE_STATS_PAD, + TCA_CAKE_STATS_CAPACITY_ESTIMATE64, + TCA_CAKE_STATS_MEMORY_LIMIT, + TCA_CAKE_STATS_MEMORY_USED, + TCA_CAKE_STATS_AVG_NETOFF, + TCA_CAKE_STATS_MIN_NETLEN, + TCA_CAKE_STATS_MAX_NETLEN, + TCA_CAKE_STATS_MIN_ADJLEN, + TCA_CAKE_STATS_MAX_ADJLEN, + TCA_CAKE_STATS_TIN_STATS, + TCA_CAKE_STATS_DEFICIT, + TCA_CAKE_STATS_COBALT_COUNT, + TCA_CAKE_STATS_DROPPING, + TCA_CAKE_STATS_DROP_NEXT_US, + TCA_CAKE_STATS_P_DROP, + TCA_CAKE_STATS_BLUE_TIMER_US, + __TCA_CAKE_STATS_MAX +}; +#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) + +enum { + __TCA_CAKE_TIN_STATS_INVALID, + TCA_CAKE_TIN_STATS_PAD, + TCA_CAKE_TIN_STATS_SENT_PACKETS, + TCA_CAKE_TIN_STATS_SENT_BYTES64, + TCA_CAKE_TIN_STATS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS, + TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64, + TCA_CAKE_TIN_STATS_BACKLOG_PACKETS, + TCA_CAKE_TIN_STATS_BACKLOG_BYTES, + TCA_CAKE_TIN_STATS_THRESHOLD_RATE64, + TCA_CAKE_TIN_STATS_TARGET_US, + TCA_CAKE_TIN_STATS_INTERVAL_US, + TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS, + TCA_CAKE_TIN_STATS_WAY_MISSES, + TCA_CAKE_TIN_STATS_WAY_COLLISIONS, + TCA_CAKE_TIN_STATS_PEAK_DELAY_US, + TCA_CAKE_TIN_STATS_AVG_DELAY_US, + TCA_CAKE_TIN_STATS_BASE_DELAY_US, + TCA_CAKE_TIN_STATS_SPARSE_FLOWS, + TCA_CAKE_TIN_STATS_BULK_FLOWS, + TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS, + TCA_CAKE_TIN_STATS_MAX_SKBLEN, + TCA_CAKE_TIN_STATS_FLOW_QUANTUM, + __TCA_CAKE_TIN_STATS_MAX +}; +#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1) +#define TC_CAKE_MAX_TINS (8) + +enum { + CAKE_FLOW_NONE = 0, + CAKE_FLOW_SRC_IP, + CAKE_FLOW_DST_IP, + CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */ + CAKE_FLOW_FLOWS, + CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */ + CAKE_FLOW_MAX, +}; + +enum { + CAKE_DIFFSERV_DIFFSERV3 = 0, + CAKE_DIFFSERV_DIFFSERV4, + CAKE_DIFFSERV_DIFFSERV8, + CAKE_DIFFSERV_BESTEFFORT, + CAKE_DIFFSERV_PRECEDENCE, + CAKE_DIFFSERV_MAX +}; + +enum { + CAKE_ACK_NONE = 0, + CAKE_ACK_FILTER, + CAKE_ACK_AGGRESSIVE, + CAKE_ACK_MAX +}; + +enum { + CAKE_ATM_NONE = 0, + CAKE_ATM_ATM, + CAKE_ATM_PTM, + CAKE_ATM_MAX +}; + + +/* TAPRIO */ +enum { + TC_TAPRIO_CMD_SET_GATES = 0x00, + TC_TAPRIO_CMD_SET_AND_HOLD = 0x01, + TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02, +}; + +enum { + TCA_TAPRIO_SCHED_ENTRY_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */ + TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */ + __TCA_TAPRIO_SCHED_ENTRY_MAX, +}; +#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1) + +/* The format for schedule entry list is: + * [TCA_TAPRIO_SCHED_ENTRY_LIST] + * [TCA_TAPRIO_SCHED_ENTRY] + * [TCA_TAPRIO_SCHED_ENTRY_CMD] + * [TCA_TAPRIO_SCHED_ENTRY_GATES] + * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] + */ +enum { + TCA_TAPRIO_SCHED_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY, + __TCA_TAPRIO_SCHED_MAX, +}; + +#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1) + +enum { + TCA_TAPRIO_ATTR_UNSPEC, + TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ + TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */ + TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ + TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ + TCA_TAPRIO_PAD, + __TCA_TAPRIO_ATTR_MAX, +}; + +#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h new file mode 100644 index 000000000..475fc8ca4 --- /dev/null +++ b/tools/include/uapi/linux/prctl.h @@ -0,0 +1,377 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_PRCTL_H +#define _LINUX_PRCTL_H + +#include + +/* Values to pass as first argument to prctl() */ + +#define PR_SET_PDEATHSIG 1 /* Second arg is a signal */ +#define PR_GET_PDEATHSIG 2 /* Second arg is a ptr to return the signal */ + +/* Get/set current->mm->dumpable */ +#define PR_GET_DUMPABLE 3 +#define PR_SET_DUMPABLE 4 + +/* Get/set unaligned access control bits (if meaningful) */ +#define PR_GET_UNALIGN 5 +#define PR_SET_UNALIGN 6 +# define PR_UNALIGN_NOPRINT 1 /* silently fix up unaligned user accesses */ +# define PR_UNALIGN_SIGBUS 2 /* generate SIGBUS on unaligned user access */ + +/* Get/set whether or not to drop capabilities on setuid() away from + * uid 0 (as per security/commoncap.c) */ +#define PR_GET_KEEPCAPS 7 +#define PR_SET_KEEPCAPS 8 + +/* Get/set floating-point emulation control bits (if meaningful) */ +#define PR_GET_FPEMU 9 +#define PR_SET_FPEMU 10 +# define PR_FPEMU_NOPRINT 1 /* silently emulate fp operations accesses */ +# define PR_FPEMU_SIGFPE 2 /* don't emulate fp operations, send SIGFPE instead */ + +/* Get/set floating-point exception mode (if meaningful) */ +#define PR_GET_FPEXC 11 +#define PR_SET_FPEXC 12 +# define PR_FP_EXC_SW_ENABLE 0x80 /* Use FPEXC for FP exception enables */ +# define PR_FP_EXC_DIV 0x010000 /* floating point divide by zero */ +# define PR_FP_EXC_OVF 0x020000 /* floating point overflow */ +# define PR_FP_EXC_UND 0x040000 /* floating point underflow */ +# define PR_FP_EXC_RES 0x080000 /* floating point inexact result */ +# define PR_FP_EXC_INV 0x100000 /* floating point invalid operation */ +# define PR_FP_EXC_DISABLED 0 /* FP exceptions disabled */ +# define PR_FP_EXC_NONRECOV 1 /* async non-recoverable exc. mode */ +# define PR_FP_EXC_ASYNC 2 /* async recoverable exception mode */ +# define PR_FP_EXC_PRECISE 3 /* precise exception mode */ + +/* Get/set whether we use statistical process timing or accurate timestamp + * based process timing */ +#define PR_GET_TIMING 13 +#define PR_SET_TIMING 14 +# define PR_TIMING_STATISTICAL 0 /* Normal, traditional, + statistical process timing */ +# define PR_TIMING_TIMESTAMP 1 /* Accurate timestamp based + process timing */ + +#define PR_SET_NAME 15 /* Set process name */ +#define PR_GET_NAME 16 /* Get process name */ + +/* Get/set process endian */ +#define PR_GET_ENDIAN 19 +#define PR_SET_ENDIAN 20 +# define PR_ENDIAN_BIG 0 +# define PR_ENDIAN_LITTLE 1 /* True little endian mode */ +# define PR_ENDIAN_PPC_LITTLE 2 /* "PowerPC" pseudo little endian */ + +/* Get/set process seccomp mode */ +#define PR_GET_SECCOMP 21 +#define PR_SET_SECCOMP 22 + +/* Get/set the capability bounding set (as per security/commoncap.c) */ +#define PR_CAPBSET_READ 23 +#define PR_CAPBSET_DROP 24 + +/* Get/set the process' ability to use the timestamp counter instruction */ +#define PR_GET_TSC 25 +#define PR_SET_TSC 26 +# define PR_TSC_ENABLE 1 /* allow the use of the timestamp counter */ +# define PR_TSC_SIGSEGV 2 /* throw a SIGSEGV instead of reading the TSC */ + +/* Get/set securebits (as per security/commoncap.c) */ +#define PR_GET_SECUREBITS 27 +#define PR_SET_SECUREBITS 28 + +/* + * Get/set the timerslack as used by poll/select/nanosleep + * A value of 0 means "use default" + */ +#define PR_SET_TIMERSLACK 29 +#define PR_GET_TIMERSLACK 30 + +#define PR_TASK_PERF_EVENTS_DISABLE 31 +#define PR_TASK_PERF_EVENTS_ENABLE 32 + +/* + * Set early/late kill mode for hwpoison memory corruption. + * This influences when the process gets killed on a memory corruption. + */ +#define PR_MCE_KILL 33 +# define PR_MCE_KILL_CLEAR 0 +# define PR_MCE_KILL_SET 1 + +# define PR_MCE_KILL_LATE 0 +# define PR_MCE_KILL_EARLY 1 +# define PR_MCE_KILL_DEFAULT 2 + +#define PR_MCE_KILL_GET 34 + +/* + * Tune up process memory map specifics. + */ +#define PR_SET_MM 35 +# define PR_SET_MM_START_CODE 1 +# define PR_SET_MM_END_CODE 2 +# define PR_SET_MM_START_DATA 3 +# define PR_SET_MM_END_DATA 4 +# define PR_SET_MM_START_STACK 5 +# define PR_SET_MM_START_BRK 6 +# define PR_SET_MM_BRK 7 +# define PR_SET_MM_ARG_START 8 +# define PR_SET_MM_ARG_END 9 +# define PR_SET_MM_ENV_START 10 +# define PR_SET_MM_ENV_END 11 +# define PR_SET_MM_AUXV 12 +# define PR_SET_MM_EXE_FILE 13 +# define PR_SET_MM_MAP 14 +# define PR_SET_MM_MAP_SIZE 15 + +/* + * This structure provides new memory descriptor + * map which mostly modifies /proc/pid/stat[m] + * output for a task. This mostly done in a + * sake of checkpoint/restore functionality. + */ +struct prctl_mm_map { + __u64 start_code; /* code section bounds */ + __u64 end_code; + __u64 start_data; /* data section bounds */ + __u64 end_data; + __u64 start_brk; /* heap for brk() syscall */ + __u64 brk; + __u64 start_stack; /* stack starts at */ + __u64 arg_start; /* command line arguments bounds */ + __u64 arg_end; + __u64 env_start; /* environment variables bounds */ + __u64 env_end; + __u64 *auxv; /* auxiliary vector */ + __u32 auxv_size; /* vector size */ + __u32 exe_fd; /* /proc/$pid/exe link file */ +}; + +/* + * Set specific pid that is allowed to ptrace the current task. + * A value of 0 mean "no process". + */ +#define PR_SET_PTRACER 0x59616d61 +# define PR_SET_PTRACER_ANY ((unsigned long)-1) + +#define PR_SET_CHILD_SUBREAPER 36 +#define PR_GET_CHILD_SUBREAPER 37 + +/* + * If no_new_privs is set, then operations that grant new privileges (i.e. + * execve) will either fail or not grant them. This affects suid/sgid, + * file capabilities, and LSMs. + * + * Operations that merely manipulate or drop existing privileges (setresuid, + * capset, etc.) will still work. Drop those privileges if you want them gone. + * + * Changing LSM security domain is considered a new privilege. So, for example, + * asking selinux for a specific new context (e.g. with runcon) will result + * in execve returning -EPERM. + * + * See Documentation/userspace-api/no_new_privs.rst for more details. + */ +#define PR_SET_NO_NEW_PRIVS 38 +#define PR_GET_NO_NEW_PRIVS 39 + +#define PR_GET_TID_ADDRESS 40 + +#define PR_SET_THP_DISABLE 41 +#define PR_GET_THP_DISABLE 42 + +/* + * No longer implemented, but left here to ensure the numbers stay reserved: + */ +#define PR_MPX_ENABLE_MANAGEMENT 43 +#define PR_MPX_DISABLE_MANAGEMENT 44 + +#define PR_SET_FP_MODE 45 +#define PR_GET_FP_MODE 46 +# define PR_FP_MODE_FR (1 << 0) /* 64b FP registers */ +# define PR_FP_MODE_FRE (1 << 1) /* 32b compatibility */ + +/* Control the ambient capability set */ +#define PR_CAP_AMBIENT 47 +# define PR_CAP_AMBIENT_IS_SET 1 +# define PR_CAP_AMBIENT_RAISE 2 +# define PR_CAP_AMBIENT_LOWER 3 +# define PR_CAP_AMBIENT_CLEAR_ALL 4 + +/* arm64 Scalable Vector Extension controls */ +/* Flag values must be kept in sync with ptrace NT_ARM_SVE interface */ +#define PR_SVE_SET_VL 50 /* set task vector length */ +# define PR_SVE_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SVE_GET_VL 51 /* get task vector length */ +/* Bits common to PR_SVE_SET_VL and PR_SVE_GET_VL */ +# define PR_SVE_VL_LEN_MASK 0xffff +# define PR_SVE_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Per task speculation control */ +#define PR_GET_SPECULATION_CTRL 52 +#define PR_SET_SPECULATION_CTRL 53 +/* Speculation control variants */ +# define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 +# define PR_SPEC_L1D_FLUSH 2 +/* Return and control values for PR_SET/GET_SPECULATION_CTRL */ +# define PR_SPEC_NOT_AFFECTED 0 +# define PR_SPEC_PRCTL (1UL << 0) +# define PR_SPEC_ENABLE (1UL << 1) +# define PR_SPEC_DISABLE (1UL << 2) +# define PR_SPEC_FORCE_DISABLE (1UL << 3) +# define PR_SPEC_DISABLE_NOEXEC (1UL << 4) + +/* Reset arm64 pointer authentication keys */ +#define PR_PAC_RESET_KEYS 54 +# define PR_PAC_APIAKEY (1UL << 0) +# define PR_PAC_APIBKEY (1UL << 1) +# define PR_PAC_APDAKEY (1UL << 2) +# define PR_PAC_APDBKEY (1UL << 3) +# define PR_PAC_APGAKEY (1UL << 4) + +/* Tagged user address controls for arm64 and RISC-V */ +#define PR_SET_TAGGED_ADDR_CTRL 55 +#define PR_GET_TAGGED_ADDR_CTRL 56 +# define PR_TAGGED_ADDR_ENABLE (1UL << 0) +/* MTE tag check fault modes */ +# define PR_MTE_TCF_NONE 0UL +# define PR_MTE_TCF_SYNC (1UL << 1) +# define PR_MTE_TCF_ASYNC (1UL << 2) +# define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) +/* MTE tag inclusion mask */ +# define PR_MTE_TAG_SHIFT 3 +# define PR_MTE_TAG_MASK (0xffffUL << PR_MTE_TAG_SHIFT) +/* Unused; kept only for source compatibility */ +# define PR_MTE_TCF_SHIFT 1 +/* RISC-V pointer masking tag length */ +# define PR_PMLEN_SHIFT 24 +# define PR_PMLEN_MASK (0x7fUL << PR_PMLEN_SHIFT) + +/* Control reclaim behavior when allocating memory */ +#define PR_SET_IO_FLUSHER 57 +#define PR_GET_IO_FLUSHER 58 + +/* Dispatch syscalls to a userspace handler */ +#define PR_SET_SYSCALL_USER_DISPATCH 59 +# define PR_SYS_DISPATCH_OFF 0 +/* Enable dispatch except for the specified range */ +# define PR_SYS_DISPATCH_EXCLUSIVE_ON 1 +/* Enable dispatch for the specified range */ +# define PR_SYS_DISPATCH_INCLUSIVE_ON 2 +/* Legacy name for backwards compatibility */ +# define PR_SYS_DISPATCH_ON PR_SYS_DISPATCH_EXCLUSIVE_ON +/* The control values for the user space selector when dispatch is enabled */ +# define SYSCALL_DISPATCH_FILTER_ALLOW 0 +# define SYSCALL_DISPATCH_FILTER_BLOCK 1 + +/* Set/get enabled arm64 pointer authentication keys */ +#define PR_PAC_SET_ENABLED_KEYS 60 +#define PR_PAC_GET_ENABLED_KEYS 61 + +/* Request the scheduler to share a core */ +#define PR_SCHED_CORE 62 +# define PR_SCHED_CORE_GET 0 +# define PR_SCHED_CORE_CREATE 1 /* create unique core_sched cookie */ +# define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ +# define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ +# define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 + +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + +/* Memory deny write / execute */ +#define PR_SET_MDWE 65 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) + +#define PR_GET_MDWE 66 + +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + +#define PR_GET_AUXV 0x41555856 + +#define PR_SET_MEMORY_MERGE 67 +#define PR_GET_MEMORY_MERGE 68 + +#define PR_RISCV_V_SET_CONTROL 69 +#define PR_RISCV_V_GET_CONTROL 70 +# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0 +# define PR_RISCV_V_VSTATE_CTRL_OFF 1 +# define PR_RISCV_V_VSTATE_CTRL_ON 2 +# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4) +# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3 +# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc +# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f + +#define PR_RISCV_SET_ICACHE_FLUSH_CTX 71 +# define PR_RISCV_CTX_SW_FENCEI_ON 0 +# define PR_RISCV_CTX_SW_FENCEI_OFF 1 +# define PR_RISCV_SCOPE_PER_PROCESS 0 +# define PR_RISCV_SCOPE_PER_THREAD 1 + +/* PowerPC Dynamic Execution Control Register (DEXCR) controls */ +#define PR_PPC_GET_DEXCR 72 +#define PR_PPC_SET_DEXCR 73 +/* DEXCR aspect to act on */ +# define PR_PPC_DEXCR_SBHE 0 /* Speculative branch hint enable */ +# define PR_PPC_DEXCR_IBRTPD 1 /* Indirect branch recurrent target prediction disable */ +# define PR_PPC_DEXCR_SRAPD 2 /* Subroutine return address prediction disable */ +# define PR_PPC_DEXCR_NPHIE 3 /* Non-privileged hash instruction enable */ +/* Action to apply / return */ +# define PR_PPC_DEXCR_CTRL_EDITABLE 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */ +# define PR_PPC_DEXCR_CTRL_SET 0x2 /* Set the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_CLEAR 0x4 /* Clear the aspect for this process */ +# define PR_PPC_DEXCR_CTRL_SET_ONEXEC 0x8 /* Set the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC 0x10 /* Clear the aspect on exec */ +# define PR_PPC_DEXCR_CTRL_MASK 0x1f + +/* + * Get the current shadow stack configuration for the current thread, + * this will be the value configured via PR_SET_SHADOW_STACK_STATUS. + */ +#define PR_GET_SHADOW_STACK_STATUS 74 + +/* + * Set the current shadow stack configuration. Enabling the shadow + * stack will cause a shadow stack to be allocated for the thread. + */ +#define PR_SET_SHADOW_STACK_STATUS 75 +# define PR_SHADOW_STACK_ENABLE (1UL << 0) +# define PR_SHADOW_STACK_WRITE (1UL << 1) +# define PR_SHADOW_STACK_PUSH (1UL << 2) + +/* + * Prevent further changes to the specified shadow stack + * configuration. All bits may be locked via this call, including + * undefined bits. + */ +#define PR_LOCK_SHADOW_STACK_STATUS 76 + +/* + * Controls the mode of timer_create() for CRIU restore operations. + * Enabling this allows CRIU to restore timers with explicit IDs. + * + * Don't use for normal operations as the result might be undefined. + */ +#define PR_TIMER_CREATE_RESTORE_IDS 77 +# define PR_TIMER_CREATE_RESTORE_IDS_OFF 0 +# define PR_TIMER_CREATE_RESTORE_IDS_ON 1 +# define PR_TIMER_CREATE_RESTORE_IDS_GET 2 + +/* FUTEX hash management */ +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define PR_FUTEX_HASH_GET_SLOTS 2 + +#endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/rtnetlink.h b/tools/include/uapi/linux/rtnetlink.h new file mode 100644 index 000000000..27265fd31 --- /dev/null +++ b/tools/include/uapi/linux/rtnetlink.h @@ -0,0 +1,849 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__LINUX_RTNETLINK_H +#define _UAPI__LINUX_RTNETLINK_H + +#include +#include +#include +#include +#include + +/* rtnetlink families. Values up to 127 are reserved for real address + * families, values above 128 may be used arbitrarily. + */ +#define RTNL_FAMILY_IPMR 128 +#define RTNL_FAMILY_IP6MR 129 +#define RTNL_FAMILY_MAX 129 + +/**** + * Routing/neighbour discovery messages. + ****/ + +/* Types of messages */ + +enum { + RTM_BASE = 16, +#define RTM_BASE RTM_BASE + + RTM_NEWLINK = 16, +#define RTM_NEWLINK RTM_NEWLINK + RTM_DELLINK, +#define RTM_DELLINK RTM_DELLINK + RTM_GETLINK, +#define RTM_GETLINK RTM_GETLINK + RTM_SETLINK, +#define RTM_SETLINK RTM_SETLINK + + RTM_NEWADDR = 20, +#define RTM_NEWADDR RTM_NEWADDR + RTM_DELADDR, +#define RTM_DELADDR RTM_DELADDR + RTM_GETADDR, +#define RTM_GETADDR RTM_GETADDR + + RTM_NEWROUTE = 24, +#define RTM_NEWROUTE RTM_NEWROUTE + RTM_DELROUTE, +#define RTM_DELROUTE RTM_DELROUTE + RTM_GETROUTE, +#define RTM_GETROUTE RTM_GETROUTE + + RTM_NEWNEIGH = 28, +#define RTM_NEWNEIGH RTM_NEWNEIGH + RTM_DELNEIGH, +#define RTM_DELNEIGH RTM_DELNEIGH + RTM_GETNEIGH, +#define RTM_GETNEIGH RTM_GETNEIGH + + RTM_NEWRULE = 32, +#define RTM_NEWRULE RTM_NEWRULE + RTM_DELRULE, +#define RTM_DELRULE RTM_DELRULE + RTM_GETRULE, +#define RTM_GETRULE RTM_GETRULE + + RTM_NEWQDISC = 36, +#define RTM_NEWQDISC RTM_NEWQDISC + RTM_DELQDISC, +#define RTM_DELQDISC RTM_DELQDISC + RTM_GETQDISC, +#define RTM_GETQDISC RTM_GETQDISC + + RTM_NEWTCLASS = 40, +#define RTM_NEWTCLASS RTM_NEWTCLASS + RTM_DELTCLASS, +#define RTM_DELTCLASS RTM_DELTCLASS + RTM_GETTCLASS, +#define RTM_GETTCLASS RTM_GETTCLASS + + RTM_NEWTFILTER = 44, +#define RTM_NEWTFILTER RTM_NEWTFILTER + RTM_DELTFILTER, +#define RTM_DELTFILTER RTM_DELTFILTER + RTM_GETTFILTER, +#define RTM_GETTFILTER RTM_GETTFILTER + + RTM_NEWACTION = 48, +#define RTM_NEWACTION RTM_NEWACTION + RTM_DELACTION, +#define RTM_DELACTION RTM_DELACTION + RTM_GETACTION, +#define RTM_GETACTION RTM_GETACTION + + RTM_NEWPREFIX = 52, +#define RTM_NEWPREFIX RTM_NEWPREFIX + + RTM_NEWMULTICAST = 56, +#define RTM_NEWMULTICAST RTM_NEWMULTICAST + RTM_DELMULTICAST, +#define RTM_DELMULTICAST RTM_DELMULTICAST + RTM_GETMULTICAST, +#define RTM_GETMULTICAST RTM_GETMULTICAST + + RTM_NEWANYCAST = 60, +#define RTM_NEWANYCAST RTM_NEWANYCAST + RTM_DELANYCAST, +#define RTM_DELANYCAST RTM_DELANYCAST + RTM_GETANYCAST, +#define RTM_GETANYCAST RTM_GETANYCAST + + RTM_NEWNEIGHTBL = 64, +#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL + RTM_GETNEIGHTBL = 66, +#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL + RTM_SETNEIGHTBL, +#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL + + RTM_NEWNDUSEROPT = 68, +#define RTM_NEWNDUSEROPT RTM_NEWNDUSEROPT + + RTM_NEWADDRLABEL = 72, +#define RTM_NEWADDRLABEL RTM_NEWADDRLABEL + RTM_DELADDRLABEL, +#define RTM_DELADDRLABEL RTM_DELADDRLABEL + RTM_GETADDRLABEL, +#define RTM_GETADDRLABEL RTM_GETADDRLABEL + + RTM_GETDCB = 78, +#define RTM_GETDCB RTM_GETDCB + RTM_SETDCB, +#define RTM_SETDCB RTM_SETDCB + + RTM_NEWNETCONF = 80, +#define RTM_NEWNETCONF RTM_NEWNETCONF + RTM_DELNETCONF, +#define RTM_DELNETCONF RTM_DELNETCONF + RTM_GETNETCONF = 82, +#define RTM_GETNETCONF RTM_GETNETCONF + + RTM_NEWMDB = 84, +#define RTM_NEWMDB RTM_NEWMDB + RTM_DELMDB = 85, +#define RTM_DELMDB RTM_DELMDB + RTM_GETMDB = 86, +#define RTM_GETMDB RTM_GETMDB + + RTM_NEWNSID = 88, +#define RTM_NEWNSID RTM_NEWNSID + RTM_DELNSID = 89, +#define RTM_DELNSID RTM_DELNSID + RTM_GETNSID = 90, +#define RTM_GETNSID RTM_GETNSID + + RTM_NEWSTATS = 92, +#define RTM_NEWSTATS RTM_NEWSTATS + RTM_GETSTATS = 94, +#define RTM_GETSTATS RTM_GETSTATS + RTM_SETSTATS, +#define RTM_SETSTATS RTM_SETSTATS + + RTM_NEWCACHEREPORT = 96, +#define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT + + RTM_NEWCHAIN = 100, +#define RTM_NEWCHAIN RTM_NEWCHAIN + RTM_DELCHAIN, +#define RTM_DELCHAIN RTM_DELCHAIN + RTM_GETCHAIN, +#define RTM_GETCHAIN RTM_GETCHAIN + + RTM_NEWNEXTHOP = 104, +#define RTM_NEWNEXTHOP RTM_NEWNEXTHOP + RTM_DELNEXTHOP, +#define RTM_DELNEXTHOP RTM_DELNEXTHOP + RTM_GETNEXTHOP, +#define RTM_GETNEXTHOP RTM_GETNEXTHOP + + RTM_NEWLINKPROP = 108, +#define RTM_NEWLINKPROP RTM_NEWLINKPROP + RTM_DELLINKPROP, +#define RTM_DELLINKPROP RTM_DELLINKPROP + RTM_GETLINKPROP, +#define RTM_GETLINKPROP RTM_GETLINKPROP + + RTM_NEWVLAN = 112, +#define RTM_NEWVLAN RTM_NEWVLAN + RTM_DELVLAN, +#define RTM_DELVLAN RTM_DELVLAN + RTM_GETVLAN, +#define RTM_GETVLAN RTM_GETVLAN + + RTM_NEWNEXTHOPBUCKET = 116, +#define RTM_NEWNEXTHOPBUCKET RTM_NEWNEXTHOPBUCKET + RTM_DELNEXTHOPBUCKET, +#define RTM_DELNEXTHOPBUCKET RTM_DELNEXTHOPBUCKET + RTM_GETNEXTHOPBUCKET, +#define RTM_GETNEXTHOPBUCKET RTM_GETNEXTHOPBUCKET + + RTM_NEWTUNNEL = 120, +#define RTM_NEWTUNNEL RTM_NEWTUNNEL + RTM_DELTUNNEL, +#define RTM_DELTUNNEL RTM_DELTUNNEL + RTM_GETTUNNEL, +#define RTM_GETTUNNEL RTM_GETTUNNEL + + __RTM_MAX, +#define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) +}; + +#define RTM_NR_MSGTYPES (RTM_MAX + 1 - RTM_BASE) +#define RTM_NR_FAMILIES (RTM_NR_MSGTYPES >> 2) +#define RTM_FAM(cmd) (((cmd) - RTM_BASE) >> 2) + +/* + Generic structure for encapsulation of optional route information. + It is reminiscent of sockaddr, but with sa_family replaced + with attribute type. + */ + +struct rtattr { + unsigned short rta_len; + unsigned short rta_type; +}; + +/* Macros to handle rtattributes */ + +#define RTA_ALIGNTO 4U +#define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) ) +#define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \ + (rta)->rta_len >= sizeof(struct rtattr) && \ + (rta)->rta_len <= (len)) +#define RTA_NEXT(rta,attrlen) ((attrlen) -= RTA_ALIGN((rta)->rta_len), \ + (struct rtattr*)(((char*)(rta)) + RTA_ALIGN((rta)->rta_len))) +#define RTA_LENGTH(len) (RTA_ALIGN(sizeof(struct rtattr)) + (len)) +#define RTA_SPACE(len) RTA_ALIGN(RTA_LENGTH(len)) +#define RTA_DATA(rta) ((void*)(((char*)(rta)) + RTA_LENGTH(0))) +#define RTA_PAYLOAD(rta) ((int)((rta)->rta_len) - RTA_LENGTH(0)) + + + + +/****************************************************************************** + * Definitions used in routing table administration. + ****/ + +struct rtmsg { + unsigned char rtm_family; + unsigned char rtm_dst_len; + unsigned char rtm_src_len; + unsigned char rtm_tos; + + unsigned char rtm_table; /* Routing table id */ + unsigned char rtm_protocol; /* Routing protocol; see below */ + unsigned char rtm_scope; /* See below */ + unsigned char rtm_type; /* See below */ + + unsigned rtm_flags; +}; + +/* rtm_type */ + +enum { + RTN_UNSPEC, + RTN_UNICAST, /* Gateway or direct route */ + RTN_LOCAL, /* Accept locally */ + RTN_BROADCAST, /* Accept locally as broadcast, + send as broadcast */ + RTN_ANYCAST, /* Accept locally as broadcast, + but send as unicast */ + RTN_MULTICAST, /* Multicast route */ + RTN_BLACKHOLE, /* Drop */ + RTN_UNREACHABLE, /* Destination is unreachable */ + RTN_PROHIBIT, /* Administratively prohibited */ + RTN_THROW, /* Not in this table */ + RTN_NAT, /* Translate this address */ + RTN_XRESOLVE, /* Use external resolver */ + __RTN_MAX +}; + +#define RTN_MAX (__RTN_MAX - 1) + + +/* rtm_protocol */ + +#define RTPROT_UNSPEC 0 +#define RTPROT_REDIRECT 1 /* Route installed by ICMP redirects; + not used by current IPv4 */ +#define RTPROT_KERNEL 2 /* Route installed by kernel */ +#define RTPROT_BOOT 3 /* Route installed during boot */ +#define RTPROT_STATIC 4 /* Route installed by administrator */ + +/* Values of protocol >= RTPROT_STATIC are not interpreted by kernel; + they are just passed from user and back as is. + It will be used by hypothetical multiple routing daemons. + Note that protocol values should be standardized in order to + avoid conflicts. + */ + +#define RTPROT_GATED 8 /* Apparently, GateD */ +#define RTPROT_RA 9 /* RDISC/ND router advertisements */ +#define RTPROT_MRT 10 /* Merit MRT */ +#define RTPROT_ZEBRA 11 /* Zebra */ +#define RTPROT_BIRD 12 /* BIRD */ +#define RTPROT_DNROUTED 13 /* DECnet routing daemon */ +#define RTPROT_XORP 14 /* XORP */ +#define RTPROT_NTK 15 /* Netsukuku */ +#define RTPROT_DHCP 16 /* DHCP client */ +#define RTPROT_MROUTED 17 /* Multicast daemon */ +#define RTPROT_KEEPALIVED 18 /* Keepalived daemon */ +#define RTPROT_BABEL 42 /* Babel daemon */ +#define RTPROT_OVN 84 /* OVN daemon */ +#define RTPROT_OPENR 99 /* Open Routing (Open/R) Routes */ +#define RTPROT_BGP 186 /* BGP Routes */ +#define RTPROT_ISIS 187 /* ISIS Routes */ +#define RTPROT_OSPF 188 /* OSPF Routes */ +#define RTPROT_RIP 189 /* RIP Routes */ +#define RTPROT_EIGRP 192 /* EIGRP Routes */ + +/* rtm_scope + + Really it is not scope, but sort of distance to the destination. + NOWHERE are reserved for not existing destinations, HOST is our + local addresses, LINK are destinations, located on directly attached + link and UNIVERSE is everywhere in the Universe. + + Intermediate values are also possible f.e. interior routes + could be assigned a value between UNIVERSE and LINK. +*/ + +enum rt_scope_t { + RT_SCOPE_UNIVERSE=0, +/* User defined values */ + RT_SCOPE_SITE=200, + RT_SCOPE_LINK=253, + RT_SCOPE_HOST=254, + RT_SCOPE_NOWHERE=255 +}; + +/* rtm_flags */ + +#define RTM_F_NOTIFY 0x100 /* Notify user of route change */ +#define RTM_F_CLONED 0x200 /* This route is cloned */ +#define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */ +#define RTM_F_PREFIX 0x800 /* Prefix addresses */ +#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */ +#define RTM_F_FIB_MATCH 0x2000 /* return full fib lookup match */ +#define RTM_F_OFFLOAD 0x4000 /* route is offloaded */ +#define RTM_F_TRAP 0x8000 /* route is trapping packets */ +#define RTM_F_OFFLOAD_FAILED 0x20000000 /* route offload failed, this value + * is chosen to avoid conflicts with + * other flags defined in + * include/uapi/linux/ipv6_route.h + */ + +/* Reserved table identifiers */ + +enum rt_class_t { + RT_TABLE_UNSPEC=0, +/* User defined values */ + RT_TABLE_COMPAT=252, + RT_TABLE_DEFAULT=253, + RT_TABLE_MAIN=254, + RT_TABLE_LOCAL=255, + RT_TABLE_MAX=0xFFFFFFFF +}; + + +/* Routing message attributes */ + +enum rtattr_type_t { + RTA_UNSPEC, + RTA_DST, + RTA_SRC, + RTA_IIF, + RTA_OIF, + RTA_GATEWAY, + RTA_PRIORITY, + RTA_PREFSRC, + RTA_METRICS, + RTA_MULTIPATH, + RTA_PROTOINFO, /* no longer used */ + RTA_FLOW, + RTA_CACHEINFO, + RTA_SESSION, /* no longer used */ + RTA_MP_ALGO, /* no longer used */ + RTA_TABLE, + RTA_MARK, + RTA_MFC_STATS, + RTA_VIA, + RTA_NEWDST, + RTA_PREF, + RTA_ENCAP_TYPE, + RTA_ENCAP, + RTA_EXPIRES, + RTA_PAD, + RTA_UID, + RTA_TTL_PROPAGATE, + RTA_IP_PROTO, + RTA_SPORT, + RTA_DPORT, + RTA_NH_ID, + RTA_FLOWLABEL, + __RTA_MAX +}; + +#define RTA_MAX (__RTA_MAX - 1) + +#define RTM_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct rtmsg)))) +#define RTM_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct rtmsg)) + +/* RTM_MULTIPATH --- array of struct rtnexthop. + * + * "struct rtnexthop" describes all necessary nexthop information, + * i.e. parameters of path to a destination via this nexthop. + * + * At the moment it is impossible to set different prefsrc, mtu, window + * and rtt for different paths from multipath. + */ + +struct rtnexthop { + unsigned short rtnh_len; + unsigned char rtnh_flags; + unsigned char rtnh_hops; + int rtnh_ifindex; +}; + +/* rtnh_flags */ + +#define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ +#define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ +#define RTNH_F_ONLINK 4 /* Gateway is forced on link */ +#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */ +#define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ +#define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */ +#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */ + +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \ + RTNH_F_OFFLOAD | RTNH_F_TRAP) + +/* Macros to handle hexthops */ + +#define RTNH_ALIGNTO 4 +#define RTNH_ALIGN(len) ( ((len)+RTNH_ALIGNTO-1) & ~(RTNH_ALIGNTO-1) ) +#define RTNH_OK(rtnh,len) ((rtnh)->rtnh_len >= sizeof(struct rtnexthop) && \ + ((int)(rtnh)->rtnh_len) <= (len)) +#define RTNH_NEXT(rtnh) ((struct rtnexthop*)(((char*)(rtnh)) + RTNH_ALIGN((rtnh)->rtnh_len))) +#define RTNH_LENGTH(len) (RTNH_ALIGN(sizeof(struct rtnexthop)) + (len)) +#define RTNH_SPACE(len) RTNH_ALIGN(RTNH_LENGTH(len)) +#define RTNH_DATA(rtnh) ((struct rtattr*)(((char*)(rtnh)) + RTNH_LENGTH(0))) + +/* RTA_VIA */ +struct rtvia { + __kernel_sa_family_t rtvia_family; + __u8 rtvia_addr[]; +}; + +/* RTM_CACHEINFO */ + +struct rta_cacheinfo { + __u32 rta_clntref; + __u32 rta_lastuse; + __s32 rta_expires; + __u32 rta_error; + __u32 rta_used; + +#define RTNETLINK_HAVE_PEERINFO 1 + __u32 rta_id; + __u32 rta_ts; + __u32 rta_tsage; +}; + +/* RTM_METRICS --- array of struct rtattr with types of RTAX_* */ + +enum { + RTAX_UNSPEC, +#define RTAX_UNSPEC RTAX_UNSPEC + RTAX_LOCK, +#define RTAX_LOCK RTAX_LOCK + RTAX_MTU, +#define RTAX_MTU RTAX_MTU + RTAX_WINDOW, +#define RTAX_WINDOW RTAX_WINDOW + RTAX_RTT, +#define RTAX_RTT RTAX_RTT + RTAX_RTTVAR, +#define RTAX_RTTVAR RTAX_RTTVAR + RTAX_SSTHRESH, +#define RTAX_SSTHRESH RTAX_SSTHRESH + RTAX_CWND, +#define RTAX_CWND RTAX_CWND + RTAX_ADVMSS, +#define RTAX_ADVMSS RTAX_ADVMSS + RTAX_REORDERING, +#define RTAX_REORDERING RTAX_REORDERING + RTAX_HOPLIMIT, +#define RTAX_HOPLIMIT RTAX_HOPLIMIT + RTAX_INITCWND, +#define RTAX_INITCWND RTAX_INITCWND + RTAX_FEATURES, +#define RTAX_FEATURES RTAX_FEATURES + RTAX_RTO_MIN, +#define RTAX_RTO_MIN RTAX_RTO_MIN + RTAX_INITRWND, +#define RTAX_INITRWND RTAX_INITRWND + RTAX_QUICKACK, +#define RTAX_QUICKACK RTAX_QUICKACK + RTAX_CC_ALGO, +#define RTAX_CC_ALGO RTAX_CC_ALGO + RTAX_FASTOPEN_NO_COOKIE, +#define RTAX_FASTOPEN_NO_COOKIE RTAX_FASTOPEN_NO_COOKIE + __RTAX_MAX +}; + +#define RTAX_MAX (__RTAX_MAX - 1) + +#define RTAX_FEATURE_ECN (1 << 0) +#define RTAX_FEATURE_SACK (1 << 1) /* unused */ +#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */ +#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */ +#define RTAX_FEATURE_TCP_USEC_TS (1 << 4) + +#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \ + RTAX_FEATURE_SACK | \ + RTAX_FEATURE_TIMESTAMP | \ + RTAX_FEATURE_ALLFRAG | \ + RTAX_FEATURE_TCP_USEC_TS) + +struct rta_session { + __u8 proto; + __u8 pad1; + __u16 pad2; + + union { + struct { + __u16 sport; + __u16 dport; + } ports; + + struct { + __u8 type; + __u8 code; + __u16 ident; + } icmpt; + + __u32 spi; + } u; +}; + +struct rta_mfc_stats { + __u64 mfcs_packets; + __u64 mfcs_bytes; + __u64 mfcs_wrong_if; +}; + +/**** + * General form of address family dependent message. + ****/ + +struct rtgenmsg { + unsigned char rtgen_family; +}; + +/***************************************************************** + * Link layer specific messages. + ****/ + +/* struct ifinfomsg + * passes link level specific information, not dependent + * on network protocol. + */ + +struct ifinfomsg { + unsigned char ifi_family; + unsigned char __ifi_pad; + unsigned short ifi_type; /* ARPHRD_* */ + int ifi_index; /* Link index */ + unsigned ifi_flags; /* IFF_* flags */ + unsigned ifi_change; /* IFF_* change mask */ +}; + +/******************************************************************** + * prefix information + ****/ + +struct prefixmsg { + unsigned char prefix_family; + unsigned char prefix_pad1; + unsigned short prefix_pad2; + int prefix_ifindex; + unsigned char prefix_type; + unsigned char prefix_len; + unsigned char prefix_flags; + unsigned char prefix_pad3; +}; + +enum +{ + PREFIX_UNSPEC, + PREFIX_ADDRESS, + PREFIX_CACHEINFO, + __PREFIX_MAX +}; + +#define PREFIX_MAX (__PREFIX_MAX - 1) + +struct prefix_cacheinfo { + __u32 preferred_time; + __u32 valid_time; +}; + + +/***************************************************************** + * Traffic control messages. + ****/ + +struct tcmsg { + unsigned char tcm_family; + unsigned char tcm__pad1; + unsigned short tcm__pad2; + int tcm_ifindex; + __u32 tcm_handle; + __u32 tcm_parent; +/* tcm_block_index is used instead of tcm_parent + * in case tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK + */ +#define tcm_block_index tcm_parent + __u32 tcm_info; +}; + +/* For manipulation of filters in shared block, tcm_ifindex is set to + * TCM_IFINDEX_MAGIC_BLOCK, and tcm_parent is aliased to tcm_block_index + * which is the block index. + */ +#define TCM_IFINDEX_MAGIC_BLOCK (0xFFFFFFFFU) + +enum { + TCA_UNSPEC, + TCA_KIND, + TCA_OPTIONS, + TCA_STATS, + TCA_XSTATS, + TCA_RATE, + TCA_FCNT, + TCA_STATS2, + TCA_STAB, + TCA_PAD, + TCA_DUMP_INVISIBLE, + TCA_CHAIN, + TCA_HW_OFFLOAD, + TCA_INGRESS_BLOCK, + TCA_EGRESS_BLOCK, + TCA_DUMP_FLAGS, + TCA_EXT_WARN_MSG, + __TCA_MAX +}; + +#define TCA_MAX (__TCA_MAX - 1) + +#define TCA_DUMP_FLAGS_TERSE (1 << 0) /* Means that in dump user gets only basic + * data necessary to identify the objects + * (handle, cookie, etc.) and stats. + */ + +#define TCA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcmsg)))) +#define TCA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcmsg)) + +/******************************************************************** + * Neighbor Discovery userland options + ****/ + +struct nduseroptmsg { + unsigned char nduseropt_family; + unsigned char nduseropt_pad1; + unsigned short nduseropt_opts_len; /* Total length of options */ + int nduseropt_ifindex; + __u8 nduseropt_icmp_type; + __u8 nduseropt_icmp_code; + unsigned short nduseropt_pad2; + unsigned int nduseropt_pad3; + /* Followed by one or more ND options */ +}; + +enum { + NDUSEROPT_UNSPEC, + NDUSEROPT_SRCADDR, + __NDUSEROPT_MAX +}; + +#define NDUSEROPT_MAX (__NDUSEROPT_MAX - 1) + +#ifndef __KERNEL__ +/* RTnetlink multicast groups - backwards compatibility for userspace */ +#define RTMGRP_LINK 1 +#define RTMGRP_NOTIFY 2 +#define RTMGRP_NEIGH 4 +#define RTMGRP_TC 8 + +#define RTMGRP_IPV4_IFADDR 0x10 +#define RTMGRP_IPV4_MROUTE 0x20 +#define RTMGRP_IPV4_ROUTE 0x40 +#define RTMGRP_IPV4_RULE 0x80 + +#define RTMGRP_IPV6_IFADDR 0x100 +#define RTMGRP_IPV6_MROUTE 0x200 +#define RTMGRP_IPV6_ROUTE 0x400 +#define RTMGRP_IPV6_IFINFO 0x800 + +#define RTMGRP_DECnet_IFADDR 0x1000 +#define RTMGRP_DECnet_ROUTE 0x4000 + +#define RTMGRP_IPV6_PREFIX 0x20000 +#endif + +/* RTnetlink multicast groups */ +enum rtnetlink_groups { + RTNLGRP_NONE, +#define RTNLGRP_NONE RTNLGRP_NONE + RTNLGRP_LINK, +#define RTNLGRP_LINK RTNLGRP_LINK + RTNLGRP_NOTIFY, +#define RTNLGRP_NOTIFY RTNLGRP_NOTIFY + RTNLGRP_NEIGH, +#define RTNLGRP_NEIGH RTNLGRP_NEIGH + RTNLGRP_TC, +#define RTNLGRP_TC RTNLGRP_TC + RTNLGRP_IPV4_IFADDR, +#define RTNLGRP_IPV4_IFADDR RTNLGRP_IPV4_IFADDR + RTNLGRP_IPV4_MROUTE, +#define RTNLGRP_IPV4_MROUTE RTNLGRP_IPV4_MROUTE + RTNLGRP_IPV4_ROUTE, +#define RTNLGRP_IPV4_ROUTE RTNLGRP_IPV4_ROUTE + RTNLGRP_IPV4_RULE, +#define RTNLGRP_IPV4_RULE RTNLGRP_IPV4_RULE + RTNLGRP_IPV6_IFADDR, +#define RTNLGRP_IPV6_IFADDR RTNLGRP_IPV6_IFADDR + RTNLGRP_IPV6_MROUTE, +#define RTNLGRP_IPV6_MROUTE RTNLGRP_IPV6_MROUTE + RTNLGRP_IPV6_ROUTE, +#define RTNLGRP_IPV6_ROUTE RTNLGRP_IPV6_ROUTE + RTNLGRP_IPV6_IFINFO, +#define RTNLGRP_IPV6_IFINFO RTNLGRP_IPV6_IFINFO + RTNLGRP_DECnet_IFADDR, +#define RTNLGRP_DECnet_IFADDR RTNLGRP_DECnet_IFADDR + RTNLGRP_NOP2, + RTNLGRP_DECnet_ROUTE, +#define RTNLGRP_DECnet_ROUTE RTNLGRP_DECnet_ROUTE + RTNLGRP_DECnet_RULE, +#define RTNLGRP_DECnet_RULE RTNLGRP_DECnet_RULE + RTNLGRP_NOP4, + RTNLGRP_IPV6_PREFIX, +#define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + RTNLGRP_IPV6_RULE, +#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE + RTNLGRP_ND_USEROPT, +#define RTNLGRP_ND_USEROPT RTNLGRP_ND_USEROPT + RTNLGRP_PHONET_IFADDR, +#define RTNLGRP_PHONET_IFADDR RTNLGRP_PHONET_IFADDR + RTNLGRP_PHONET_ROUTE, +#define RTNLGRP_PHONET_ROUTE RTNLGRP_PHONET_ROUTE + RTNLGRP_DCB, +#define RTNLGRP_DCB RTNLGRP_DCB + RTNLGRP_IPV4_NETCONF, +#define RTNLGRP_IPV4_NETCONF RTNLGRP_IPV4_NETCONF + RTNLGRP_IPV6_NETCONF, +#define RTNLGRP_IPV6_NETCONF RTNLGRP_IPV6_NETCONF + RTNLGRP_MDB, +#define RTNLGRP_MDB RTNLGRP_MDB + RTNLGRP_MPLS_ROUTE, +#define RTNLGRP_MPLS_ROUTE RTNLGRP_MPLS_ROUTE + RTNLGRP_NSID, +#define RTNLGRP_NSID RTNLGRP_NSID + RTNLGRP_MPLS_NETCONF, +#define RTNLGRP_MPLS_NETCONF RTNLGRP_MPLS_NETCONF + RTNLGRP_IPV4_MROUTE_R, +#define RTNLGRP_IPV4_MROUTE_R RTNLGRP_IPV4_MROUTE_R + RTNLGRP_IPV6_MROUTE_R, +#define RTNLGRP_IPV6_MROUTE_R RTNLGRP_IPV6_MROUTE_R + RTNLGRP_NEXTHOP, +#define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP + RTNLGRP_BRVLAN, +#define RTNLGRP_BRVLAN RTNLGRP_BRVLAN + RTNLGRP_MCTP_IFADDR, +#define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR + RTNLGRP_TUNNEL, +#define RTNLGRP_TUNNEL RTNLGRP_TUNNEL + RTNLGRP_STATS, +#define RTNLGRP_STATS RTNLGRP_STATS + RTNLGRP_IPV4_MCADDR, +#define RTNLGRP_IPV4_MCADDR RTNLGRP_IPV4_MCADDR + RTNLGRP_IPV6_MCADDR, +#define RTNLGRP_IPV6_MCADDR RTNLGRP_IPV6_MCADDR + RTNLGRP_IPV6_ACADDR, +#define RTNLGRP_IPV6_ACADDR RTNLGRP_IPV6_ACADDR + __RTNLGRP_MAX +}; +#define RTNLGRP_MAX (__RTNLGRP_MAX - 1) + +/* TC action piece */ +struct tcamsg { + unsigned char tca_family; + unsigned char tca__pad1; + unsigned short tca__pad2; +}; + +enum { + TCA_ROOT_UNSPEC, + TCA_ROOT_TAB, +#define TCA_ACT_TAB TCA_ROOT_TAB +#define TCAA_MAX TCA_ROOT_TAB + TCA_ROOT_FLAGS, + TCA_ROOT_COUNT, + TCA_ROOT_TIME_DELTA, /* in msecs */ + TCA_ROOT_EXT_WARN_MSG, + __TCA_ROOT_MAX, +#define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) +}; + +#define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg)))) +#define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg)) +/* tcamsg flags stored in attribute TCA_ROOT_FLAGS + * + * TCA_ACT_FLAG_LARGE_DUMP_ON user->kernel to request for larger than + * TCA_ACT_MAX_PRIO actions in a dump. All dump responses will contain the + * number of actions being dumped stored in for user app's consumption in + * TCA_ROOT_COUNT + * + * TCA_ACT_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only + * includes essential action info (kind, index, etc.) + * + */ +#define TCA_FLAG_LARGE_DUMP_ON (1 << 0) +#define TCA_ACT_FLAG_LARGE_DUMP_ON TCA_FLAG_LARGE_DUMP_ON +#define TCA_ACT_FLAG_TERSE_DUMP (1 << 1) + +/* New extended info filters for IFLA_EXT_MASK */ +#define RTEXT_FILTER_VF (1 << 0) +#define RTEXT_FILTER_BRVLAN (1 << 1) +#define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) +#define RTEXT_FILTER_SKIP_STATS (1 << 3) +#define RTEXT_FILTER_MRP (1 << 4) +#define RTEXT_FILTER_CFM_CONFIG (1 << 5) +#define RTEXT_FILTER_CFM_STATUS (1 << 6) +#define RTEXT_FILTER_MST (1 << 7) +#define RTEXT_FILTER_NAME_ONLY (1 << 8) + +/* End of information exported to user level */ + + + +#endif /* _UAPI__LINUX_RTNETLINK_H */ diff --git a/tools/include/uapi/linux/seccomp.h b/tools/include/uapi/linux/seccomp.h new file mode 100644 index 000000000..dbfc9b37f --- /dev/null +++ b/tools/include/uapi/linux/seccomp.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_SECCOMP_H +#define _UAPI_LINUX_SECCOMP_H + +#include +#include + + +/* Valid values for seccomp.mode and prctl(PR_SET_SECCOMP, ) */ +#define SECCOMP_MODE_DISABLED 0 /* seccomp is not in use. */ +#define SECCOMP_MODE_STRICT 1 /* uses hard-coded filter. */ +#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */ + +/* Valid operations for seccomp syscall. */ +#define SECCOMP_SET_MODE_STRICT 0 +#define SECCOMP_SET_MODE_FILTER 1 +#define SECCOMP_GET_ACTION_AVAIL 2 +#define SECCOMP_GET_NOTIF_SIZES 3 + +/* Valid flags for SECCOMP_SET_MODE_FILTER */ +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) +#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) + +/* + * All BPF programs must return a 32-bit value. + * The bottom 16-bits are for optional return data. + * The upper 16-bits are ordered from least permissive values to most, + * as a signed value (so 0x8000000 is negative). + * + * The ordering ensures that a min_t() over composed return values always + * selects the least permissive choice. + */ +#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */ +#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */ +#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD +#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */ +#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */ +#define SECCOMP_RET_USER_NOTIF 0x7fc00000U /* notifies userspace */ +#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */ +#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */ +#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */ + +/* Masks for the return value sections. */ +#define SECCOMP_RET_ACTION_FULL 0xffff0000U +#define SECCOMP_RET_ACTION 0x7fff0000U +#define SECCOMP_RET_DATA 0x0000ffffU + +/** + * struct seccomp_data - the format the BPF program executes over. + * @nr: the system call number + * @arch: indicates system call convention as an AUDIT_ARCH_* value + * as defined in . + * @instruction_pointer: at the time of the system call. + * @args: up to 6 system call arguments always stored as 64-bit values + * regardless of the architecture. + */ +struct seccomp_data { + int nr; + __u32 arch; + __u64 instruction_pointer; + __u64 args[6]; +}; + +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +/* + * Valid flags for struct seccomp_notif_resp + * + * Note, the SECCOMP_USER_NOTIF_FLAG_CONTINUE flag must be used with caution! + * If set by the process supervising the syscalls of another process the + * syscall will continue. This is problematic because of an inherent TOCTOU. + * An attacker can exploit the time while the supervised process is waiting on + * a response from the supervising process to rewrite syscall arguments which + * are passed as pointers of the intercepted syscall. + * It should be absolutely clear that this means that the seccomp notifier + * _cannot_ be used to implement a security policy! It should only ever be used + * in scenarios where a more privileged process supervises the syscalls of a + * lesser privileged process to get around kernel-enforced security + * restrictions when the privileged process deems this safe. In other words, + * in order to continue a syscall the supervising process should be sure that + * another security mechanism or the kernel itself will sufficiently block + * syscalls if arguments are rewritten to something unsafe. + * + * Similar precautions should be applied when stacking SECCOMP_RET_USER_NOTIF + * or SECCOMP_RET_TRACE. For SECCOMP_RET_USER_NOTIF filters acting on the + * same syscall, the most recently added filter takes precedence. This means + * that the new SECCOMP_RET_USER_NOTIF filter can override any + * SECCOMP_IOCTL_NOTIF_SEND from earlier filters, essentially allowing all + * such filtered syscalls to be executed by sending the response + * SECCOMP_USER_NOTIF_FLAG_CONTINUE. Note that SECCOMP_RET_TRACE can equally + * be overriden by SECCOMP_USER_NOTIF_FLAG_CONTINUE. + */ +#define SECCOMP_USER_NOTIF_FLAG_CONTINUE (1UL << 0) + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0) + +/* valid flags for seccomp_notif_addfd */ +#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */ +#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */ + +/** + * struct seccomp_notif_addfd + * @id: The ID of the seccomp notification + * @flags: SECCOMP_ADDFD_FLAG_* + * @srcfd: The local fd number + * @newfd: Optional remote FD number if SETFD option is set, otherwise 0. + * @newfd_flags: The O_* flags the remote FD should have applied + */ +struct seccomp_notif_addfd { + __u64 id; + __u32 flags; + __u32 srcfd; + __u32 newfd; + __u32 newfd_flags; +}; + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64) +/* On success, the return value is the remote process's added fd number */ +#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \ + struct seccomp_notif_addfd) + +#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64) + +#endif /* _UAPI_LINUX_SECCOMP_H */ diff --git a/tools/include/uapi/linux/seg6.h b/tools/include/uapi/linux/seg6.h new file mode 100644 index 000000000..f94baf154 --- /dev/null +++ b/tools/include/uapi/linux/seg6.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_H +#define _UAPI_LINUX_SEG6_H + +#include +#include /* For struct in6_addr. */ + +/* + * SRH + */ +struct ipv6_sr_hdr { + __u8 nexthdr; + __u8 hdrlen; + __u8 type; + __u8 segments_left; + __u8 first_segment; /* Represents the last_entry field of SRH */ + __u8 flags; + __u16 tag; + + struct in6_addr segments[]; +}; + +#define SR6_FLAG1_PROTECTED (1 << 6) +#define SR6_FLAG1_OAM (1 << 5) +#define SR6_FLAG1_ALERT (1 << 4) +#define SR6_FLAG1_HMAC (1 << 3) + +#define SR6_TLV_INGRESS 1 +#define SR6_TLV_EGRESS 2 +#define SR6_TLV_OPAQUE 3 +#define SR6_TLV_PADDING 4 +#define SR6_TLV_HMAC 5 + +#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC) + +struct sr6_tlv { + __u8 type; + __u8 len; + __u8 data[]; +}; + +#endif diff --git a/tools/include/uapi/linux/seg6_local.h b/tools/include/uapi/linux/seg6_local.h new file mode 100644 index 000000000..edc138bdc --- /dev/null +++ b/tools/include/uapi/linux/seg6_local.h @@ -0,0 +1,80 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun + * + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_LOCAL_H +#define _UAPI_LINUX_SEG6_LOCAL_H + +#include + +enum { + SEG6_LOCAL_UNSPEC, + SEG6_LOCAL_ACTION, + SEG6_LOCAL_SRH, + SEG6_LOCAL_TABLE, + SEG6_LOCAL_NH4, + SEG6_LOCAL_NH6, + SEG6_LOCAL_IIF, + SEG6_LOCAL_OIF, + SEG6_LOCAL_BPF, + __SEG6_LOCAL_MAX, +}; +#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) + +enum { + SEG6_LOCAL_ACTION_UNSPEC = 0, + /* node segment */ + SEG6_LOCAL_ACTION_END = 1, + /* adjacency segment (IPv6 cross-connect) */ + SEG6_LOCAL_ACTION_END_X = 2, + /* lookup of next seg NH in table */ + SEG6_LOCAL_ACTION_END_T = 3, + /* decap and L2 cross-connect */ + SEG6_LOCAL_ACTION_END_DX2 = 4, + /* decap and IPv6 cross-connect */ + SEG6_LOCAL_ACTION_END_DX6 = 5, + /* decap and IPv4 cross-connect */ + SEG6_LOCAL_ACTION_END_DX4 = 6, + /* decap and lookup of DA in v6 table */ + SEG6_LOCAL_ACTION_END_DT6 = 7, + /* decap and lookup of DA in v4 table */ + SEG6_LOCAL_ACTION_END_DT4 = 8, + /* binding segment with insertion */ + SEG6_LOCAL_ACTION_END_B6 = 9, + /* binding segment with encapsulation */ + SEG6_LOCAL_ACTION_END_B6_ENCAP = 10, + /* binding segment with MPLS encap */ + SEG6_LOCAL_ACTION_END_BM = 11, + /* lookup last seg in table */ + SEG6_LOCAL_ACTION_END_S = 12, + /* forward to SR-unaware VNF with static proxy */ + SEG6_LOCAL_ACTION_END_AS = 13, + /* forward to SR-unaware VNF with masquerading */ + SEG6_LOCAL_ACTION_END_AM = 14, + /* custom BPF action */ + SEG6_LOCAL_ACTION_END_BPF = 15, + + __SEG6_LOCAL_ACTION_MAX, +}; + +#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1) + +enum { + SEG6_LOCAL_BPF_PROG_UNSPEC, + SEG6_LOCAL_BPF_PROG, + SEG6_LOCAL_BPF_PROG_NAME, + __SEG6_LOCAL_BPF_PROG_MAX, +}; + +#define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h new file mode 100644 index 000000000..1686861aa --- /dev/null +++ b/tools/include/uapi/linux/stat.h @@ -0,0 +1,260 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_STAT_H +#define _UAPI_LINUX_STAT_H + +#include + +#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2) + +#define S_IFMT 00170000 +#define S_IFSOCK 0140000 +#define S_IFLNK 0120000 +#define S_IFREG 0100000 +#define S_IFBLK 0060000 +#define S_IFDIR 0040000 +#define S_IFCHR 0020000 +#define S_IFIFO 0010000 +#define S_ISUID 0004000 +#define S_ISGID 0002000 +#define S_ISVTX 0001000 + +#define S_ISLNK(m) (((m) & S_IFMT) == S_IFLNK) +#define S_ISREG(m) (((m) & S_IFMT) == S_IFREG) +#define S_ISDIR(m) (((m) & S_IFMT) == S_IFDIR) +#define S_ISCHR(m) (((m) & S_IFMT) == S_IFCHR) +#define S_ISBLK(m) (((m) & S_IFMT) == S_IFBLK) +#define S_ISFIFO(m) (((m) & S_IFMT) == S_IFIFO) +#define S_ISSOCK(m) (((m) & S_IFMT) == S_IFSOCK) + +#define S_IRWXU 00700 +#define S_IRUSR 00400 +#define S_IWUSR 00200 +#define S_IXUSR 00100 + +#define S_IRWXG 00070 +#define S_IRGRP 00040 +#define S_IWGRP 00020 +#define S_IXGRP 00010 + +#define S_IRWXO 00007 +#define S_IROTH 00004 +#define S_IWOTH 00002 +#define S_IXOTH 00001 + +#endif + +/* + * Timestamp structure for the timestamps in struct statx. + * + * tv_sec holds the number of seconds before (negative) or after (positive) + * 00:00:00 1st January 1970 UTC. + * + * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time. + * + * __reserved is held in case we need a yet finer resolution. + */ +struct statx_timestamp { + __s64 tv_sec; + __u32 tv_nsec; + __s32 __reserved; +}; + +/* + * Structures for the extended file attribute retrieval system call + * (statx()). + * + * The caller passes a mask of what they're specifically interested in as a + * parameter to statx(). What statx() actually got will be indicated in + * st_mask upon return. + * + * For each bit in the mask argument: + * + * - if the datum is not supported: + * + * - the bit will be cleared, and + * + * - the datum will be set to an appropriate fabricated value if one is + * available (eg. CIFS can take a default uid and gid), otherwise + * + * - the field will be cleared; + * + * - otherwise, if explicitly requested: + * + * - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is + * set or if the datum is considered out of date, and + * + * - the field will be filled in and the bit will be set; + * + * - otherwise, if not requested, but available in approximate form without any + * effort, it will be filled in anyway, and the bit will be set upon return + * (it might not be up to date, however, and no attempt will be made to + * synchronise the internal state first); + * + * - otherwise the field and the bit will be cleared before returning. + * + * Items in STATX_BASIC_STATS may be marked unavailable on return, but they + * will have values installed for compatibility purposes so that stat() and + * co. can be emulated in userspace. + */ +struct statx { + /* 0x00 */ + /* What results were written [uncond] */ + __u32 stx_mask; + + /* Preferred general I/O size [uncond] */ + __u32 stx_blksize; + + /* Flags conveying information about the file [uncond] */ + __u64 stx_attributes; + + /* 0x10 */ + /* Number of hard links */ + __u32 stx_nlink; + + /* User ID of owner */ + __u32 stx_uid; + + /* Group ID of owner */ + __u32 stx_gid; + + /* File mode */ + __u16 stx_mode; + __u16 __spare0[1]; + + /* 0x20 */ + /* Inode number */ + __u64 stx_ino; + + /* File size */ + __u64 stx_size; + + /* Number of 512-byte blocks allocated */ + __u64 stx_blocks; + + /* Mask to show what's supported in stx_attributes */ + __u64 stx_attributes_mask; + + /* 0x40 */ + /* Last access time */ + struct statx_timestamp stx_atime; + + /* File creation time */ + struct statx_timestamp stx_btime; + + /* Last attribute change time */ + struct statx_timestamp stx_ctime; + + /* Last data modification time */ + struct statx_timestamp stx_mtime; + + /* 0x80 */ + /* Device ID of special file [if bdev/cdev] */ + __u32 stx_rdev_major; + __u32 stx_rdev_minor; + + /* ID of device containing file [uncond] */ + __u32 stx_dev_major; + __u32 stx_dev_minor; + + /* 0x90 */ + __u64 stx_mnt_id; + + /* Memory buffer alignment for direct I/O */ + __u32 stx_dio_mem_align; + + /* File offset alignment for direct I/O */ + __u32 stx_dio_offset_align; + + /* 0xa0 */ + /* Subvolume identifier */ + __u64 stx_subvol; + + /* Min atomic write unit in bytes */ + __u32 stx_atomic_write_unit_min; + + /* Max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max; + + /* 0xb0 */ + /* Max atomic write segment count */ + __u32 stx_atomic_write_segments_max; + + /* File offset alignment for direct I/O reads */ + __u32 stx_dio_read_offset_align; + + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ + + /* 0x100 */ +}; + +/* + * Flags to be stx_mask + * + * Query request/result mask for statx() and struct statx::stx_mask. + * + * These bits should be set in the mask argument of statx() to request + * particular items when calling statx(). + */ +#define STATX_TYPE 0x00000001U /* Want/got stx_mode & S_IFMT */ +#define STATX_MODE 0x00000002U /* Want/got stx_mode & ~S_IFMT */ +#define STATX_NLINK 0x00000004U /* Want/got stx_nlink */ +#define STATX_UID 0x00000008U /* Want/got stx_uid */ +#define STATX_GID 0x00000010U /* Want/got stx_gid */ +#define STATX_ATIME 0x00000020U /* Want/got stx_atime */ +#define STATX_MTIME 0x00000040U /* Want/got stx_mtime */ +#define STATX_CTIME 0x00000080U /* Want/got stx_ctime */ +#define STATX_INO 0x00000100U /* Want/got stx_ino */ +#define STATX_SIZE 0x00000200U /* Want/got stx_size */ +#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */ +#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */ +#define STATX_BTIME 0x00000800U /* Want/got stx_btime */ +#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */ +#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */ +#define STATX_MNT_ID_UNIQUE 0x00004000U /* Want/got extended stx_mount_id */ +#define STATX_SUBVOL 0x00008000U /* Want/got stx_subvol */ +#define STATX_WRITE_ATOMIC 0x00010000U /* Want/got atomic_write_* fields */ +#define STATX_DIO_READ_ALIGN 0x00020000U /* Want/got dio read alignment info */ + +#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */ + +#ifndef __KERNEL__ +/* + * This is deprecated, and shall remain the same value in the future. To avoid + * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME) + * instead. + */ +#define STATX_ALL 0x00000fffU +#endif + +/* + * Attributes to be found in stx_attributes and masked in stx_attributes_mask. + * + * These give information about the features or the state of a file that might + * be of use to ordinary userspace programs such as GUIs or ls rather than + * specialised tools. + * + * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags + * semantically. Where possible, the numerical value is picked to correspond + * also. Note that the DAX attribute indicates that the file is in the CPU + * direct access state. It does not correspond to the per-inode flag that + * some filesystems support. + * + */ +#define STATX_ATTR_COMPRESSED 0x00000004 /* [I] File is compressed by the fs */ +#define STATX_ATTR_IMMUTABLE 0x00000010 /* [I] File is marked immutable */ +#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */ +#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */ +#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */ +#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */ +#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */ +#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */ +#define STATX_ATTR_DAX 0x00200000 /* File is currently in DAX state */ +#define STATX_ATTR_WRITE_ATOMIC 0x00400000 /* File supports atomic write operations */ + + +#endif /* _UAPI_LINUX_STAT_H */ diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h new file mode 100644 index 000000000..457498259 --- /dev/null +++ b/tools/include/uapi/linux/stddef.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_STDDEF_H +#define _LINUX_STDDEF_H + + +#ifndef __always_inline +#define __always_inline __inline__ +#endif + +/* Not all C++ standards support type declarations inside an anonymous union */ +#ifndef __cplusplus +#define __struct_group_tag(TAG) TAG +#else +#define __struct_group_tag(TAG) +#endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse (C only), + * as well as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct __struct_group_tag(TAG) { MEMBERS } ATTRS NAME; \ + } ATTRS + +#ifdef __cplusplus +/* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ +#define __DECLARE_FLEX_ARRAY(T, member) \ + T member[0] +#else +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } +#endif + +#ifndef __counted_by +#define __counted_by(m) +#endif + +#ifndef __counted_by_le +#define __counted_by_le(m) +#endif + +#ifndef __counted_by_be +#define __counted_by_be(m) +#endif + +#ifndef __counted_by_ptr +#define __counted_by_ptr(m) +#endif + +#define __kernel_nonstring + +#endif /* _LINUX_STDDEF_H */ diff --git a/tools/include/uapi/linux/taskstats.h b/tools/include/uapi/linux/taskstats.h new file mode 100644 index 000000000..3ae25f3ce --- /dev/null +++ b/tools/include/uapi/linux/taskstats.h @@ -0,0 +1,291 @@ +/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */ +/* taskstats.h - exporting per-task statistics + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2006 + * (C) Balbir Singh, IBM Corp. 2006 + * (C) Jay Lan, SGI, 2006 + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2.1 of the GNU Lesser General Public License + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + */ + +#ifndef _LINUX_TASKSTATS_H +#define _LINUX_TASKSTATS_H + +#include +#include + +/* Format for per-task data returned to userland when + * - a task exits + * - listener requests stats for a task + * + * The struct is versioned. Newer versions should only add fields to + * the bottom of the struct to maintain backward compatibility. + * + * + * To add new fields + * a) bump up TASKSTATS_VERSION + * b) add comment indicating new version number at end of struct + * c) add new fields after version comment; maintain 64-bit alignment + */ + + +#define TASKSTATS_VERSION 17 +#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN + * in linux/sched.h */ + +struct taskstats { + + /* The version number of this struct. This field is always set to + * TAKSTATS_VERSION, which is defined in . + * Each time the struct is changed, the value should be incremented. + */ + __u16 version; + __u32 ac_exitcode; /* Exit status */ + + /* The accounting flags of a task as defined in + * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP. + * (AGROUP since version 12). + */ + __u8 ac_flag; /* Record flags */ + __u8 ac_nice; /* task_nice */ + + /* Delay accounting fields start + * + * All values, until comment "Delay accounting fields end" are + * available only if delay accounting is enabled, even though the last + * few fields are not delays + * + * xxx_count is the number of delay values recorded + * xxx_delay_total is the corresponding cumulative delay in nanoseconds + * + * xxx_delay_total wraps around to zero on overflow + * xxx_count incremented regardless of overflow + */ + + /* Delay waiting for cpu, while runnable + * count, delay_total NOT updated atomically + */ + __u64 cpu_count __attribute__((aligned(8))); + __u64 cpu_delay_total; + + /* Following four fields atomically updated using task->delays->lock */ + + /* Delay waiting for synchronous block I/O to complete + * does not account for delays in I/O submission + */ + __u64 blkio_count; + __u64 blkio_delay_total; + + /* Delay waiting for page fault I/O (swap in only) */ + __u64 swapin_count; + __u64 swapin_delay_total; + + /* cpu "wall-clock" running time + * On some architectures, value will adjust for cpu time stolen + * from the kernel in involuntary waits due to virtualization. + * Value is cumulative, in nanoseconds, without a corresponding count + * and wraps around to zero silently on overflow + */ + __u64 cpu_run_real_total; + + /* cpu "virtual" running time + * Uses time intervals seen by the kernel i.e. no adjustment + * for kernel's involuntary waits due to virtualization. + * Value is cumulative, in nanoseconds, without a corresponding count + * and wraps around to zero silently on overflow + */ + __u64 cpu_run_virtual_total; + /* Delay accounting fields end */ + /* version 1 ends here */ + + /* Basic Accounting Fields start */ + char ac_comm[TS_COMM_LEN]; /* Command name */ + __u8 ac_sched __attribute__((aligned(8))); + /* Scheduling discipline */ + __u8 ac_pad[3]; + __u32 ac_uid __attribute__((aligned(8))); + /* User ID */ + __u32 ac_gid; /* Group ID */ + __u32 ac_pid; /* Process ID */ + __u32 ac_ppid; /* Parent process ID */ + /* __u32 range means times from 1970 to 2106 */ + __u32 ac_btime; /* Begin time [sec since 1970] */ + __u64 ac_etime __attribute__((aligned(8))); + /* Elapsed time [usec] */ + __u64 ac_utime; /* User CPU time [usec] */ + __u64 ac_stime; /* SYstem CPU time [usec] */ + __u64 ac_minflt; /* Minor Page Fault Count */ + __u64 ac_majflt; /* Major Page Fault Count */ + /* Basic Accounting Fields end */ + + /* Extended accounting fields start */ + /* Accumulated RSS usage in duration of a task, in MBytes-usecs. + * The current rss usage is added to this counter every time + * a tick is charged to a task's system time. So, at the end we + * will have memory usage multiplied by system time. Thus an + * average usage per system time unit can be calculated. + */ + __u64 coremem; /* accumulated RSS usage in MB-usec */ + /* Accumulated virtual memory usage in duration of a task. + * Same as acct_rss_mem1 above except that we keep track of VM usage. + */ + __u64 virtmem; /* accumulated VM usage in MB-usec */ + + /* High watermark of RSS and virtual memory usage in duration of + * a task, in KBytes. + */ + __u64 hiwater_rss; /* High-watermark of RSS usage, in KB */ + __u64 hiwater_vm; /* High-water VM usage, in KB */ + + /* The following four fields are I/O statistics of a task. */ + __u64 read_char; /* bytes read */ + __u64 write_char; /* bytes written */ + __u64 read_syscalls; /* read syscalls */ + __u64 write_syscalls; /* write syscalls */ + /* Extended accounting fields end */ + +#define TASKSTATS_HAS_IO_ACCOUNTING + /* Per-task storage I/O accounting starts */ + __u64 read_bytes; /* bytes of read I/O */ + __u64 write_bytes; /* bytes of write I/O */ + __u64 cancelled_write_bytes; /* bytes of cancelled write I/O */ + + __u64 nvcsw; /* voluntary_ctxt_switches */ + __u64 nivcsw; /* nonvoluntary_ctxt_switches */ + + /* time accounting for SMT machines */ + __u64 ac_utimescaled; /* utime scaled on frequency etc */ + __u64 ac_stimescaled; /* stime scaled on frequency etc */ + __u64 cpu_scaled_run_real_total; /* scaled cpu_run_real_total */ + + /* Delay waiting for memory reclaim */ + __u64 freepages_count; + __u64 freepages_delay_total; + + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; + + /* v10: 64-bit btime to avoid overflow */ + __u64 ac_btime64; /* 64-bit begin time */ + + /* v11: Delay waiting for memory compact */ + __u64 compact_count; + __u64 compact_delay_total; + + /* v12 begin */ + __u32 ac_tgid; /* thread group ID */ + /* Thread group walltime up to now. This is total process walltime if + * AGROUP flag is set. + */ + __u64 ac_tgetime __attribute__((aligned(8))); + /* Lightweight information to identify process binary files. + * This leaves userspace to match this to a file system path, using + * MAJOR() and MINOR() macros to identify a device and mount point, + * the inode to identify the executable file. This is /proc/self/exe + * at the end, so matching the most recent exec(). Values are zero + * for kernel threads. + */ + __u64 ac_exe_dev; /* program binary device ID */ + __u64 ac_exe_inode; /* program binary inode number */ + /* v12 end */ + + /* v13: Delay waiting for write-protect copy */ + __u64 wpcopy_count; + __u64 wpcopy_delay_total; + + /* v14: Delay waiting for IRQ/SOFTIRQ */ + __u64 irq_count; + __u64 irq_delay_total; + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; + + /*v17: delay max timestamp record*/ + struct __kernel_timespec cpu_delay_max_ts; + struct __kernel_timespec blkio_delay_max_ts; + struct __kernel_timespec swapin_delay_max_ts; + struct __kernel_timespec freepages_delay_max_ts; + struct __kernel_timespec thrashing_delay_max_ts; + struct __kernel_timespec compact_delay_max_ts; + struct __kernel_timespec wpcopy_delay_max_ts; + struct __kernel_timespec irq_delay_max_ts; +}; + + +/* + * Commands sent from userspace + * Not versioned. New commands should only be inserted at the enum's end + * prior to __TASKSTATS_CMD_MAX + */ + +enum { + TASKSTATS_CMD_UNSPEC = 0, /* Reserved */ + TASKSTATS_CMD_GET, /* user->kernel request/get-response */ + TASKSTATS_CMD_NEW, /* kernel->user event */ + __TASKSTATS_CMD_MAX, +}; + +#define TASKSTATS_CMD_MAX (__TASKSTATS_CMD_MAX - 1) + +enum { + TASKSTATS_TYPE_UNSPEC = 0, /* Reserved */ + TASKSTATS_TYPE_PID, /* Process id */ + TASKSTATS_TYPE_TGID, /* Thread group id */ + TASKSTATS_TYPE_STATS, /* taskstats structure */ + TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */ + TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */ + TASKSTATS_TYPE_NULL, /* contains nothing */ + __TASKSTATS_TYPE_MAX, +}; + +#define TASKSTATS_TYPE_MAX (__TASKSTATS_TYPE_MAX - 1) + +enum { + TASKSTATS_CMD_ATTR_UNSPEC = 0, + TASKSTATS_CMD_ATTR_PID, + TASKSTATS_CMD_ATTR_TGID, + TASKSTATS_CMD_ATTR_REGISTER_CPUMASK, + TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK, + __TASKSTATS_CMD_ATTR_MAX, +}; + +#define TASKSTATS_CMD_ATTR_MAX (__TASKSTATS_CMD_ATTR_MAX - 1) + +/* NETLINK_GENERIC related info */ + +#define TASKSTATS_GENL_NAME "TASKSTATS" +#define TASKSTATS_GENL_VERSION 0x1 + +#endif /* _LINUX_TASKSTATS_H */ diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h new file mode 100644 index 000000000..fe6c8f8f3 --- /dev/null +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (c) 2015 Jiri Pirko + */ + +#ifndef __LINUX_TC_BPF_H +#define __LINUX_TC_BPF_H + +#include + +struct tc_act_bpf { + tc_gen; +}; + +enum { + TCA_ACT_BPF_UNSPEC, + TCA_ACT_BPF_TM, + TCA_ACT_BPF_PARMS, + TCA_ACT_BPF_OPS_LEN, + TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, + TCA_ACT_BPF_PAD, + TCA_ACT_BPF_TAG, + TCA_ACT_BPF_ID, + __TCA_ACT_BPF_MAX, +}; +#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/tcp.h b/tools/include/uapi/linux/tcp.h new file mode 100644 index 000000000..13ceeb395 --- /dev/null +++ b/tools/include/uapi/linux/tcp.h @@ -0,0 +1,357 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * INET An implementation of the TCP/IP protocol suite for the LINUX + * operating system. INET is implemented using the BSD Socket + * interface as the means of communication with the user level. + * + * Definitions for the TCP protocol. + * + * Version: @(#)tcp.h 1.0.2 04/28/93 + * + * Author: Fred N. van Kempen, + * + * 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; either version + * 2 of the License, or (at your option) any later version. + */ +#ifndef _UAPI_LINUX_TCP_H +#define _UAPI_LINUX_TCP_H + +#include +#include +#include + +struct tcphdr { + __be16 source; + __be16 dest; + __be32 seq; + __be32 ack_seq; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u16 res1:4, + doff:4, + fin:1, + syn:1, + rst:1, + psh:1, + ack:1, + urg:1, + ece:1, + cwr:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u16 doff:4, + res1:4, + cwr:1, + ece:1, + urg:1, + ack:1, + psh:1, + rst:1, + syn:1, + fin:1; +#else +#error "Adjust your defines" +#endif + __be16 window; + __sum16 check; + __be16 urg_ptr; +}; + +/* + * The union cast uses a gcc extension to avoid aliasing problems + * (union is compatible to any of its members) + * This means this part of the code is -fstrict-aliasing safe now. + */ +union tcp_word_hdr { + struct tcphdr hdr; + __be32 words[5]; +}; + +#define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) + +enum { + TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), + TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), + TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), + TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000), + TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000), + TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), + TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), + TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), + TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), + TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) +}; + +/* + * TCP general constants + */ +#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */ +#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */ + +/* TCP socket options */ +#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */ +#define TCP_MAXSEG 2 /* Limit MSS */ +#define TCP_CORK 3 /* Never send partially complete segments */ +#define TCP_KEEPIDLE 4 /* Start keeplives after this period */ +#define TCP_KEEPINTVL 5 /* Interval between keepalives */ +#define TCP_KEEPCNT 6 /* Number of keepalives before death */ +#define TCP_SYNCNT 7 /* Number of SYN retransmits */ +#define TCP_LINGER2 8 /* Life time of orphaned FIN-WAIT-2 state */ +#define TCP_DEFER_ACCEPT 9 /* Wake up listener only when data arrive */ +#define TCP_WINDOW_CLAMP 10 /* Bound advertised window */ +#define TCP_INFO 11 /* Information about this connection. */ +#define TCP_QUICKACK 12 /* Block/reenable quick acks */ +#define TCP_CONGESTION 13 /* Congestion control algorithm */ +#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */ +#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/ +#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */ +#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */ +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ +#define TCP_REPAIR_QUEUE 20 +#define TCP_QUEUE_SEQ 21 +#define TCP_REPAIR_OPTIONS 22 +#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ +#define TCP_TIMESTAMP 24 +#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ +#define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ +#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ +#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ +#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */ +#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */ +#define TCP_ULP 31 /* Attach a ULP to a TCP connection */ +#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ +#define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ +#define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ +#define TCP_ZEROCOPY_RECEIVE 35 +#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */ + +#define TCP_CM_INQ TCP_INQ + +#define TCP_TX_DELAY 37 /* delay outgoing packets by XX usec */ + + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF 0 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + +struct tcp_repair_opt { + __u32 opt_code; + __u32 opt_val; +}; + +struct tcp_repair_window { + __u32 snd_wl1; + __u32 snd_wnd; + __u32 max_window; + + __u32 rcv_wnd; + __u32 rcv_wup; +}; + +enum { + TCP_NO_QUEUE, + TCP_RECV_QUEUE, + TCP_SEND_QUEUE, + TCP_QUEUES_NR, +}; + +/* why fastopen failed from client perspective */ +enum tcp_fastopen_client_fail { + TFO_STATUS_UNSPEC, /* catch-all */ + TFO_COOKIE_UNAVAILABLE, /* if not in TFO_CLIENT_NO_COOKIE mode */ + TFO_DATA_NOT_ACKED, /* SYN-ACK did not ack SYN data */ + TFO_SYN_RETRANSMITTED, /* SYN-ACK did not ack SYN data after timeout */ +}; + +/* for TCP_INFO socket option */ +#define TCPI_OPT_TIMESTAMPS 1 +#define TCPI_OPT_SACK 2 +#define TCPI_OPT_WSCALE 4 +#define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ +#define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ +#define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ + +/* + * Sender's congestion state indicating normal or abnormal situations + * in the last round of packets sent. The state is driven by the ACK + * information and timer events. + */ +enum tcp_ca_state { + /* + * Nothing bad has been observed recently. + * No apparent reordering, packet loss, or ECN marks. + */ + TCP_CA_Open = 0, +#define TCPF_CA_Open (1< + +/* TLS socket options */ +#define TLS_TX 1 /* Set transmit parameters */ +#define TLS_RX 2 /* Set receive parameters */ + +/* Supported versions */ +#define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) +#define TLS_VERSION_MAJOR(ver) (((ver) >> 8) & 0xFF) + +#define TLS_VERSION_NUMBER(id) ((((id##_VERSION_MAJOR) & 0xFF) << 8) | \ + ((id##_VERSION_MINOR) & 0xFF)) + +#define TLS_1_2_VERSION_MAJOR 0x3 +#define TLS_1_2_VERSION_MINOR 0x3 +#define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2) + +/* Supported ciphers */ +#define TLS_CIPHER_AES_GCM_128 51 +#define TLS_CIPHER_AES_GCM_128_IV_SIZE 8 +#define TLS_CIPHER_AES_GCM_128_KEY_SIZE 16 +#define TLS_CIPHER_AES_GCM_128_SALT_SIZE 4 +#define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16 +#define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8 + +#define TLS_SET_RECORD_TYPE 1 +#define TLS_GET_RECORD_TYPE 2 + +struct tls_crypto_info { + __u16 version; + __u16 cipher_type; +}; + +struct tls12_crypto_info_aes_gcm_128 { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_AES_GCM_128_IV_SIZE]; + unsigned char key[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_AES_GCM_128_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE]; +}; + +#endif /* _UAPI_LINUX_TLS_H */ diff --git a/tools/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h new file mode 100644 index 000000000..85aa32724 --- /dev/null +++ b/tools/include/uapi/linux/types.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _UAPI_LINUX_TYPES_H +#define _UAPI_LINUX_TYPES_H + +#include + +#ifndef __ASSEMBLER__ + +/* copied from linux:include/uapi/linux/types.h */ +#define __bitwise +typedef __u16 __bitwise __le16; +typedef __u16 __bitwise __be16; +typedef __u32 __bitwise __le32; +typedef __u32 __bitwise __be32; +typedef __u64 __bitwise __le64; +typedef __u64 __bitwise __be64; + +typedef __u16 __bitwise __sum16; +typedef __u32 __bitwise __wsum; + +#define __aligned_u64 __u64 __attribute__((aligned(8))) +#define __aligned_be64 __be64 __attribute__((aligned(8))) +#define __aligned_le64 __le64 __attribute__((aligned(8))) + +#endif /* __ASSEMBLER__ */ +#endif /* _UAPI_LINUX_TYPES_H */ diff --git a/tools/include/uapi/linux/userfaultfd.h b/tools/include/uapi/linux/userfaultfd.h new file mode 100644 index 000000000..c8e99df95 --- /dev/null +++ b/tools/include/uapi/linux/userfaultfd.h @@ -0,0 +1,432 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * include/linux/userfaultfd.h + * + * Copyright (C) 2007 Davide Libenzi + * Copyright (C) 2015 Red Hat, Inc. + * + */ + +#ifndef _LINUX_USERFAULTFD_H +#define _LINUX_USERFAULTFD_H + +#include + +/* ioctls for /dev/userfaultfd */ +#define USERFAULTFD_IOC 0xAA +#define USERFAULTFD_IOC_NEW _IO(USERFAULTFD_IOC, 0x00) + +/* + * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and + * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In + * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ + * means the userland is reading). + */ +#define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR | \ + UFFDIO_REGISTER_MODE_RWP) +#define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ + UFFD_FEATURE_EVENT_FORK | \ + UFFD_FEATURE_EVENT_REMAP | \ + UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_UNMAP | \ + UFFD_FEATURE_MISSING_HUGETLBFS | \ + UFFD_FEATURE_MISSING_SHMEM | \ + UFFD_FEATURE_SIGBUS | \ + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS | \ + UFFD_FEATURE_MINOR_SHMEM | \ + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM | \ + UFFD_FEATURE_WP_UNPOPULATED | \ + UFFD_FEATURE_POISON | \ + UFFD_FEATURE_WP_ASYNC | \ + UFFD_FEATURE_MOVE | \ + UFFD_FEATURE_RWP | \ + UFFD_FEATURE_RWP_ASYNC) +#define UFFD_API_IOCTLS \ + ((__u64)1 << _UFFDIO_REGISTER | \ + (__u64)1 << _UFFDIO_UNREGISTER | \ + (__u64)1 << _UFFDIO_SET_MODE | \ + (__u64)1 << _UFFDIO_API) +#define UFFD_API_RANGE_IOCTLS \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_ZEROPAGE | \ + (__u64)1 << _UFFDIO_MOVE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON | \ + (__u64)1 << _UFFDIO_RWPROTECT) +#define UFFD_API_RANGE_IOCTLS_BASIC \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_POISON | \ + (__u64)1 << _UFFDIO_RWPROTECT) + +/* + * Valid ioctl command number range with this API is from 0x00 to + * 0x3F. UFFDIO_API is the fixed number, everything else can be + * changed by implementing a different UFFD_API. If sticking to the + * same UFFD_API more ioctl can be added and userland will be aware of + * which ioctl the running kernel implements through the ioctl command + * bitmask written by the UFFDIO_API. + */ +#define _UFFDIO_REGISTER (0x00) +#define _UFFDIO_UNREGISTER (0x01) +#define _UFFDIO_WAKE (0x02) +#define _UFFDIO_COPY (0x03) +#define _UFFDIO_ZEROPAGE (0x04) +#define _UFFDIO_MOVE (0x05) +#define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) +#define _UFFDIO_POISON (0x08) +#define _UFFDIO_RWPROTECT (0x09) +#define _UFFDIO_SET_MODE (0x0A) +#define _UFFDIO_API (0x3F) + +/* userfaultfd ioctl ids */ +#define UFFDIO 0xAA +#define UFFDIO_API _IOWR(UFFDIO, _UFFDIO_API, \ + struct uffdio_api) +#define UFFDIO_REGISTER _IOWR(UFFDIO, _UFFDIO_REGISTER, \ + struct uffdio_register) +#define UFFDIO_UNREGISTER _IOR(UFFDIO, _UFFDIO_UNREGISTER, \ + struct uffdio_range) +#define UFFDIO_WAKE _IOR(UFFDIO, _UFFDIO_WAKE, \ + struct uffdio_range) +#define UFFDIO_COPY _IOWR(UFFDIO, _UFFDIO_COPY, \ + struct uffdio_copy) +#define UFFDIO_ZEROPAGE _IOWR(UFFDIO, _UFFDIO_ZEROPAGE, \ + struct uffdio_zeropage) +#define UFFDIO_MOVE _IOWR(UFFDIO, _UFFDIO_MOVE, \ + struct uffdio_move) +#define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ + struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOWR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) +#define UFFDIO_POISON _IOWR(UFFDIO, _UFFDIO_POISON, \ + struct uffdio_poison) +#define UFFDIO_RWPROTECT _IOWR(UFFDIO, _UFFDIO_RWPROTECT, \ + struct uffdio_rwprotect) +#define UFFDIO_SET_MODE _IOW(UFFDIO, _UFFDIO_SET_MODE, \ + struct uffdio_set_mode) + +/* read() structure */ +struct uffd_msg { + __u8 event; + + __u8 reserved1; + __u16 reserved2; + __u32 reserved3; + + union { + struct { + __u64 flags; + __u64 address; + union { + __u32 ptid; + } feat; + } pagefault; + + struct { + __u32 ufd; + } fork; + + struct { + __u64 from; + __u64 to; + __u64 len; + } remap; + + struct { + __u64 start; + __u64 end; + } remove; + + struct { + /* unused reserved fields */ + __u64 reserved1; + __u64 reserved2; + __u64 reserved3; + } reserved; + } arg; +} __attribute__((packed)); + +/* + * Start at 0x12 and not at 0 to be more strict against bugs. + */ +#define UFFD_EVENT_PAGEFAULT 0x12 +#define UFFD_EVENT_FORK 0x13 +#define UFFD_EVENT_REMAP 0x14 +#define UFFD_EVENT_REMOVE 0x15 +#define UFFD_EVENT_UNMAP 0x16 + +/* flags for UFFD_EVENT_PAGEFAULT */ +#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ +#define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ +#define UFFD_PAGEFAULT_FLAG_RWP (1<<3) /* If reason is VM_UFFD_RWP */ + +struct uffdio_api { + /* userland asks for an API number and the features to enable */ + __u64 api; + /* + * Kernel answers below with the all available features for + * the API, this notifies userland of which events and/or + * which flags for each event are enabled in the current + * kernel. + * + * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE + * are to be considered implicitly always enabled in all kernels as + * long as the uffdio_api.api requested matches UFFD_API. + * + * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER + * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on + * hugetlbfs virtual memory ranges. Adding or not adding + * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has + * no real functional effect after UFFDIO_API returns, but + * it's only useful for an initial feature set probe at + * UFFDIO_API time. There are two ways to use it: + * + * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the + * uffdio_api.features before calling UFFDIO_API, an error + * will be returned by UFFDIO_API on a kernel without + * hugetlbfs missing support + * + * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in + * uffdio_api.features and instead it will be set by the + * kernel in the uffdio_api.features if the kernel supports + * it, so userland can later check if the feature flag is + * present in uffdio_api.features after UFFDIO_API + * succeeded. + * + * UFFD_FEATURE_MISSING_SHMEM works the same as + * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem + * (i.e. tmpfs and other shmem based APIs). + * + * UFFD_FEATURE_SIGBUS feature means no page-fault + * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead + * a SIGBUS signal will be sent to the faulting process. + * + * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will + * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. + * + * UFFD_FEATURE_MINOR_SHMEM indicates the same support as + * UFFD_FEATURE_MINOR_HUGETLBFS, but for shmem-backed pages instead. + * + * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page + * faults would be provided and the offset within the page would not be + * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. + * + * UFFD_FEATURE_WP_UNPOPULATED indicates that userfaultfd + * write-protection mode will always apply to unpopulated pages + * (i.e. empty ptes). This will be the default behavior for shmem + * & hugetlbfs, so this flag only affects anonymous memory behavior + * when userfault write-protection mode is registered. + * + * UFFD_FEATURE_WP_ASYNC indicates that userfaultfd write-protection + * asynchronous mode is supported in which the write fault is + * automatically resolved and write-protection is un-set. + * It implies UFFD_FEATURE_WP_UNPOPULATED. + * + * UFFD_FEATURE_MOVE indicates that the kernel supports moving an + * existing page contents from userspace. + * + * UFFD_FEATURE_RWP indicates that the kernel supports + * UFFDIO_REGISTER_MODE_RWP for read-write protection tracking. + * Pages are made inaccessible via UFFDIO_RWPROTECT and faults + * are delivered when the pages are re-accessed. + * + * UFFD_FEATURE_RWP_ASYNC indicates asynchronous mode for + * UFFDIO_REGISTER_MODE_RWP. When set, faults on read-write + * protected pages are auto-resolved by the kernel (PTE + * permissions restored immediately) without delivering a message + * to the userfaultfd handler. Use PAGEMAP_SCAN with inverted + * PAGE_IS_ACCESSED to find pages that were not re-accessed. + */ +#define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) +#define UFFD_FEATURE_EVENT_FORK (1<<1) +#define UFFD_FEATURE_EVENT_REMAP (1<<2) +#define UFFD_FEATURE_EVENT_REMOVE (1<<3) +#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) +#define UFFD_FEATURE_MISSING_SHMEM (1<<5) +#define UFFD_FEATURE_EVENT_UNMAP (1<<6) +#define UFFD_FEATURE_SIGBUS (1<<7) +#define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) +#define UFFD_FEATURE_MINOR_SHMEM (1<<10) +#define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) +#define UFFD_FEATURE_WP_UNPOPULATED (1<<13) +#define UFFD_FEATURE_POISON (1<<14) +#define UFFD_FEATURE_WP_ASYNC (1<<15) +#define UFFD_FEATURE_MOVE (1<<16) +#define UFFD_FEATURE_RWP (1<<17) +#define UFFD_FEATURE_RWP_ASYNC (1<<18) + __u64 features; + + __u64 ioctls; +}; + +struct uffdio_range { + __u64 start; + __u64 len; +}; + +struct uffdio_register { + struct uffdio_range range; +#define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) +#define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) +#define UFFDIO_REGISTER_MODE_RWP ((__u64)1<<3) + __u64 mode; + + /* + * kernel answers which ioctl commands are available for the + * range, keep at the end as the last 8 bytes aren't read. + */ + __u64 ioctls; +}; + +struct uffdio_copy { + __u64 dst; + __u64 src; + __u64 len; +#define UFFDIO_COPY_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_COPY_MODE_WP will map the page write protected on + * the fly. UFFDIO_COPY_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_COPY_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * "copy" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 copy; +}; + +struct uffdio_zeropage { + struct uffdio_range range; +#define UFFDIO_ZEROPAGE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * "zeropage" is written by the ioctl and must be at the end: + * the copy_from_user will not read the last 8 bytes. + */ + __s64 zeropage; +}; + +struct uffdio_writeprotect { + struct uffdio_range range; +/* + * UFFDIO_WRITEPROTECT_MODE_WP: set the flag to write protect a range, + * unset the flag to undo protection of a range which was previously + * write protected. + * + * UFFDIO_WRITEPROTECT_MODE_DONTWAKE: set the flag to avoid waking up + * any wait thread after the operation succeeds. + * + * NOTE: Write protecting a region (WP=1) is unrelated to page faults, + * therefore DONTWAKE flag is meaningless with WP=1. Removing write + * protection (WP=0) in response to a page fault wakes the faulting + * task unless DONTWAKE is set. + */ +#define UFFDIO_WRITEPROTECT_MODE_WP ((__u64)1<<0) +#define UFFDIO_WRITEPROTECT_MODE_DONTWAKE ((__u64)1<<1) + __u64 mode; +}; + +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + /* + * UFFDIO_CONTINUE_MODE_WP will map the page write protected on + * the fly. UFFDIO_CONTINUE_MODE_WP is available only if the + * write protected ioctl is implemented for the range + * according to the uffdio_register.ioctls. + */ +#define UFFDIO_CONTINUE_MODE_WP ((__u64)1<<1) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + +struct uffdio_poison { + struct uffdio_range range; +#define UFFDIO_POISON_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 updated; +}; + +struct uffdio_rwprotect { + struct uffdio_range range; + /* !RWP means undo RWP-protection */ +#define UFFDIO_RWPROTECT_MODE_RWP ((__u64)1<<0) +#define UFFDIO_RWPROTECT_MODE_DONTWAKE ((__u64)1<<1) + __u64 mode; +}; + +struct uffdio_move { + __u64 dst; + __u64 src; + __u64 len; + /* + * Especially if used to atomically remove memory from the + * address space the wake on the dst range is not needed. + */ +#define UFFDIO_MOVE_MODE_DONTWAKE ((__u64)1<<0) +#define UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES ((__u64)1<<1) + __u64 mode; + /* + * "move" is written by the ioctl and must be at the end: the + * copy_from_user will not read the last 8 bytes. + */ + __s64 move; +}; + +struct uffdio_set_mode { + /* + * Toggle async mode for features at runtime. + * Supported: UFFD_FEATURE_RWP_ASYNC. + * Setting a bit in both enable and disable is invalid. + */ + __u64 enable; + __u64 disable; +}; + +/* + * Flags for the userfaultfd(2) system call itself. + */ + +/* + * Create a userfaultfd that can handle page faults only in user mode. + */ +#define UFFD_USER_MODE_ONLY 1 + +#endif /* _LINUX_USERFAULTFD_H */ -- cgit v1.3.1