diff options
| author | Jinke Han <jinkehan@didiglobal.com> | 2026-09-08 15:37:42 +0800 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-17 09:48:42 +0200 |
| commit | a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 (patch) | |
| tree | 73fef824f9a846cf935869d0dbc5070ef6e2f741 /drivers/nvme/target/auth.c | |
| download | linux-stable-a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255.tar.gz linux-stable-a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255.zip | |
x86/kprobes: Fix crash when probing CS CALL instructionsgrafted
When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.
The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:
<__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>: mov %r14,%rdi
<__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>: mov %eax,%r12d
<__hrtimer_run_queues+266>: xchg %ax,%ax
<__hrtimer_run_queues+268>: mov %r13,%rdi
Which triggers this crash:
BUG: unable to handle page fault for address: 00000000000f41c9
#PF: supervisor write access in kernel mode
#PF: error_code(0x0002) - not-present page
PGD 0 P4D 0
Oops: 0002 [#1] SMP NOPTI
CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
RIP: 0010:__hrtimer_run_queues+0x106/0x230
Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.
The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.
During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.
Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.
[ mingo: Refined the changelog ]
Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000
Diffstat (limited to 'drivers/nvme/target/auth.c')
| -rw-r--r-- | drivers/nvme/target/auth.c | 533 |
1 files changed, 533 insertions, 0 deletions
diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c new file mode 100644 index 000000000..a55319bcd --- /dev/null +++ b/drivers/nvme/target/auth.c @@ -0,0 +1,533 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NVMe over Fabrics DH-HMAC-CHAP authentication. + * Copyright (c) 2020 Hannes Reinecke, SUSE Software Solutions. + * All rights reserved. + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/crc32.h> +#include <linux/base64.h> +#include <linux/ctype.h> +#include <linux/random.h> +#include <linux/nvme-auth.h> +#include <linux/nvme-keyring.h> +#include <linux/unaligned.h> + +#include "nvmet.h" + +int nvmet_auth_set_key(struct nvmet_host *host, const char *secret, + bool set_ctrl) +{ + unsigned char key_hash; + char *dhchap_secret; + + if (!strlen(secret)) { + if (set_ctrl) { + kfree(host->dhchap_ctrl_secret); + host->dhchap_ctrl_secret = NULL; + host->dhchap_ctrl_key_hash = 0; + } else { + kfree(host->dhchap_secret); + host->dhchap_secret = NULL; + host->dhchap_key_hash = 0; + } + return 0; + } + if (sscanf(secret, "DHHC-1:%hhd:%*s", &key_hash) != 1) + return -EINVAL; + if (key_hash > 3) { + pr_warn("Invalid DH-HMAC-CHAP hash id %d\n", + key_hash); + return -EINVAL; + } + dhchap_secret = kstrdup(secret, GFP_KERNEL); + if (!dhchap_secret) + return -ENOMEM; + down_write(&nvmet_config_sem); + if (set_ctrl) { + kfree(host->dhchap_ctrl_secret); + host->dhchap_ctrl_secret = strim(dhchap_secret); + host->dhchap_ctrl_key_hash = key_hash; + } else { + kfree(host->dhchap_secret); + host->dhchap_secret = strim(dhchap_secret); + host->dhchap_key_hash = key_hash; + } + up_write(&nvmet_config_sem); + return 0; +} + +int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id) +{ + const char *dhgroup_kpp; + int ret = 0; + + pr_debug("%s: ctrl %d selecting dhgroup %d\n", + __func__, ctrl->cntlid, dhgroup_id); + + if (ctrl->dh_tfm) { + if (ctrl->dh_gid == dhgroup_id) { + pr_debug("%s: ctrl %d reuse existing DH group %d\n", + __func__, ctrl->cntlid, dhgroup_id); + return 0; + } + crypto_free_kpp(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } + + if (dhgroup_id == NVME_AUTH_DHGROUP_NULL) + return 0; + + dhgroup_kpp = nvme_auth_dhgroup_kpp(dhgroup_id); + if (!dhgroup_kpp) { + pr_debug("%s: ctrl %d invalid DH group %d\n", + __func__, ctrl->cntlid, dhgroup_id); + return -EINVAL; + } + ctrl->dh_tfm = crypto_alloc_kpp(dhgroup_kpp, 0, 0); + if (IS_ERR(ctrl->dh_tfm)) { + pr_debug("%s: ctrl %d failed to setup DH group %d, err %ld\n", + __func__, ctrl->cntlid, dhgroup_id, + PTR_ERR(ctrl->dh_tfm)); + ret = PTR_ERR(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } else { + ctrl->dh_gid = dhgroup_id; + pr_debug("%s: ctrl %d setup DH group %d\n", + __func__, ctrl->cntlid, ctrl->dh_gid); + ret = nvme_auth_gen_privkey(ctrl->dh_tfm, ctrl->dh_gid); + if (ret < 0) { + pr_debug("%s: ctrl %d failed to generate private key, err %d\n", + __func__, ctrl->cntlid, ret); + kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = NULL; + return ret; + } + ctrl->dh_keysize = crypto_kpp_maxsize(ctrl->dh_tfm); + kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = kzalloc(ctrl->dh_keysize, GFP_KERNEL); + if (!ctrl->dh_key) { + pr_warn("ctrl %d failed to allocate public key\n", + ctrl->cntlid); + return -ENOMEM; + } + ret = nvme_auth_gen_pubkey(ctrl->dh_tfm, ctrl->dh_key, + ctrl->dh_keysize); + if (ret < 0) { + pr_warn("ctrl %d failed to generate public key\n", + ctrl->cntlid); + kfree(ctrl->dh_key); + ctrl->dh_key = NULL; + } + } + + return ret; +} + +u8 nvmet_setup_auth(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq, bool reset) +{ + int ret = 0; + struct nvmet_host_link *p; + struct nvmet_host *host = NULL; + + down_read(&nvmet_config_sem); + if (nvmet_is_disc_subsys(ctrl->subsys)) + goto out_unlock; + + if (ctrl->subsys->allow_any_host) + goto out_unlock; + + list_for_each_entry(p, &ctrl->subsys->hosts, entry) { + if (strcmp(nvmet_host_name(p->host), ctrl->hostnqn)) + continue; + host = p->host; + break; + } + if (!host) { + pr_debug("host %s not found\n", ctrl->hostnqn); + ret = NVME_AUTH_DHCHAP_FAILURE_FAILED; + goto out_unlock; + } + + if (!reset && nvmet_queue_tls_keyid(sq)) { + pr_debug("host %s tls enabled\n", ctrl->hostnqn); + goto out_unlock; + } + + ret = nvmet_setup_dhgroup(ctrl, host->dhchap_dhgroup_id); + if (ret < 0) { + pr_warn("Failed to setup DH group"); + ret = NVME_AUTH_DHCHAP_FAILURE_DHGROUP_UNUSABLE; + goto out_unlock; + } + + if (!host->dhchap_secret) { + pr_debug("No authentication provided\n"); + goto out_unlock; + } + + if (host->dhchap_hash_id == ctrl->shash_id) { + pr_debug("Re-use existing hash ID %d\n", + ctrl->shash_id); + } else { + ctrl->shash_id = host->dhchap_hash_id; + } + + /* Skip the 'DHHC-1:XX:' prefix */ + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = nvme_auth_extract_key(host->dhchap_secret + 10, + host->dhchap_key_hash); + if (IS_ERR(ctrl->host_key)) { + ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE; + ctrl->host_key = NULL; + goto out_free_hash; + } +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG + pr_debug("%s: using hash %s key %*ph\n", __func__, + ctrl->host_key->hash > 0 ? + nvme_auth_hmac_name(ctrl->host_key->hash) : "none", + (int)ctrl->host_key->len, ctrl->host_key->key); +#endif + nvme_auth_free_key(ctrl->ctrl_key); + if (!host->dhchap_ctrl_secret) { + ctrl->ctrl_key = NULL; + goto out_unlock; + } + + ctrl->ctrl_key = nvme_auth_extract_key(host->dhchap_ctrl_secret + 10, + host->dhchap_ctrl_key_hash); + if (IS_ERR(ctrl->ctrl_key)) { + ret = NVME_AUTH_DHCHAP_FAILURE_NOT_USABLE; + ctrl->ctrl_key = NULL; + goto out_free_hash; + } +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG + pr_debug("%s: using ctrl hash %s key %*ph\n", __func__, + ctrl->ctrl_key->hash > 0 ? + nvme_auth_hmac_name(ctrl->ctrl_key->hash) : "none", + (int)ctrl->ctrl_key->len, ctrl->ctrl_key->key); +#endif +out_free_hash: + if (ret) { + if (ctrl->host_key) { + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = NULL; + } + ctrl->shash_id = 0; + } +out_unlock: + up_read(&nvmet_config_sem); + + return ret; +} + +void nvmet_auth_sq_free(struct nvmet_sq *sq) +{ + cancel_delayed_work(&sq->auth_expired_work); + kfree(sq->dhchap_c1); + sq->dhchap_c1 = NULL; + kfree(sq->dhchap_c2); + sq->dhchap_c2 = NULL; + kfree(sq->dhchap_skey); + sq->dhchap_skey = NULL; +} + +void nvmet_auth_sq_destroy(struct nvmet_sq *sq) +{ + cancel_delayed_work_sync(&sq->auth_expired_work); + nvmet_auth_sq_free(sq); +} + +void nvmet_destroy_auth(struct nvmet_ctrl *ctrl) +{ + ctrl->shash_id = 0; + + if (ctrl->dh_tfm) { + crypto_free_kpp(ctrl->dh_tfm); + ctrl->dh_tfm = NULL; + ctrl->dh_gid = 0; + } + kfree_sensitive(ctrl->dh_key); + ctrl->dh_key = NULL; + + if (ctrl->host_key) { + nvme_auth_free_key(ctrl->host_key); + ctrl->host_key = NULL; + } + if (ctrl->ctrl_key) { + nvme_auth_free_key(ctrl->ctrl_key); + ctrl->ctrl_key = NULL; + } +#ifdef CONFIG_NVME_TARGET_TCP_TLS + if (ctrl->tls_key) { + key_put(ctrl->tls_key); + ctrl->tls_key = NULL; + } +#endif +} + +bool nvmet_check_auth_status(struct nvmet_req *req) +{ + if (req->sq->ctrl->host_key) { + if (req->sq->qid > 0) + return true; + if (!req->sq->authenticated) + return false; + } + return true; +} + +int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response, + unsigned int shash_len) +{ + struct nvme_auth_hmac_ctx hmac; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u8 *challenge = req->sq->dhchap_c1; + struct nvme_dhchap_key *transformed_key; + u8 buf[4]; + int ret; + + transformed_key = nvme_auth_transform_key(ctrl->host_key, + ctrl->hostnqn); + if (IS_ERR(transformed_key)) + return PTR_ERR(transformed_key); + + ret = nvme_auth_hmac_init(&hmac, ctrl->shash_id, transformed_key->key, + transformed_key->len); + if (ret) + goto out_free_response; + + if (shash_len != nvme_auth_hmac_hash_len(ctrl->shash_id)) { + pr_err("%s: hash len mismatch (len %u digest %zu)\n", __func__, + shash_len, nvme_auth_hmac_hash_len(ctrl->shash_id)); + ret = -EINVAL; + goto out_free_response; + } + + if (ctrl->dh_gid != NVME_AUTH_DHGROUP_NULL) { + challenge = kmalloc(shash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out_free_response; + } + ret = nvme_auth_augmented_challenge(ctrl->shash_id, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + req->sq->dhchap_c1, + challenge, shash_len); + if (ret) + goto out_free_challenge; + } + pr_debug("ctrl %d qid %d host response seq %u transaction %d\n", + ctrl->cntlid, req->sq->qid, req->sq->dhchap_s1, + req->sq->dhchap_tid); + + nvme_auth_hmac_update(&hmac, challenge, shash_len); + + put_unaligned_le32(req->sq->dhchap_s1, buf); + nvme_auth_hmac_update(&hmac, buf, 4); + + put_unaligned_le16(req->sq->dhchap_tid, buf); + nvme_auth_hmac_update(&hmac, buf, 2); + + *buf = req->sq->sc_c; + nvme_auth_hmac_update(&hmac, buf, 1); + nvme_auth_hmac_update(&hmac, "HostHost", 8); + memset(buf, 0, 4); + nvme_auth_hmac_update(&hmac, ctrl->hostnqn, strlen(ctrl->hostnqn)); + nvme_auth_hmac_update(&hmac, buf, 1); + nvme_auth_hmac_update(&hmac, ctrl->subsys->subsysnqn, + strlen(ctrl->subsys->subsysnqn)); + nvme_auth_hmac_final(&hmac, response); + ret = 0; +out_free_challenge: + if (challenge != req->sq->dhchap_c1) + kfree(challenge); +out_free_response: + memzero_explicit(&hmac, sizeof(hmac)); + nvme_auth_free_key(transformed_key); + return ret; +} + +int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response, + unsigned int shash_len) +{ + struct nvme_auth_hmac_ctx hmac; + struct nvmet_ctrl *ctrl = req->sq->ctrl; + u8 *challenge = req->sq->dhchap_c2; + struct nvme_dhchap_key *transformed_key; + u8 buf[4]; + int ret; + + transformed_key = nvme_auth_transform_key(ctrl->ctrl_key, + ctrl->subsys->subsysnqn); + if (IS_ERR(transformed_key)) + return PTR_ERR(transformed_key); + + ret = nvme_auth_hmac_init(&hmac, ctrl->shash_id, transformed_key->key, + transformed_key->len); + if (ret) + goto out_free_response; + + if (shash_len != nvme_auth_hmac_hash_len(ctrl->shash_id)) { + pr_err("%s: hash len mismatch (len %u digest %zu)\n", __func__, + shash_len, nvme_auth_hmac_hash_len(ctrl->shash_id)); + ret = -EINVAL; + goto out_free_response; + } + + if (ctrl->dh_gid != NVME_AUTH_DHGROUP_NULL) { + challenge = kmalloc(shash_len, GFP_KERNEL); + if (!challenge) { + ret = -ENOMEM; + goto out_free_response; + } + ret = nvme_auth_augmented_challenge(ctrl->shash_id, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + req->sq->dhchap_c2, + challenge, shash_len); + if (ret) + goto out_free_challenge; + } + + nvme_auth_hmac_update(&hmac, challenge, shash_len); + + put_unaligned_le32(req->sq->dhchap_s2, buf); + nvme_auth_hmac_update(&hmac, buf, 4); + + put_unaligned_le16(req->sq->dhchap_tid, buf); + nvme_auth_hmac_update(&hmac, buf, 2); + + *buf = req->sq->sc_c; + nvme_auth_hmac_update(&hmac, buf, 1); + nvme_auth_hmac_update(&hmac, "Controller", 10); + nvme_auth_hmac_update(&hmac, ctrl->subsys->subsysnqn, + strlen(ctrl->subsys->subsysnqn)); + memset(buf, 0, 4); + nvme_auth_hmac_update(&hmac, buf, 1); + nvme_auth_hmac_update(&hmac, ctrl->hostnqn, strlen(ctrl->hostnqn)); + nvme_auth_hmac_final(&hmac, response); + ret = 0; +out_free_challenge: + if (challenge != req->sq->dhchap_c2) + kfree(challenge); +out_free_response: + memzero_explicit(&hmac, sizeof(hmac)); + nvme_auth_free_key(transformed_key); + return ret; +} + +int nvmet_auth_ctrl_exponential(struct nvmet_req *req, + u8 *buf, int buf_size) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int ret = 0; + + if (!ctrl->dh_key) { + pr_warn("ctrl %d no DH public key!\n", ctrl->cntlid); + return -ENOKEY; + } + if (buf_size != ctrl->dh_keysize) { + pr_warn("ctrl %d DH public key size mismatch, need %zu is %d\n", + ctrl->cntlid, ctrl->dh_keysize, buf_size); + ret = -EINVAL; + } else { + memcpy(buf, ctrl->dh_key, buf_size); +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG + pr_debug("%s: ctrl %d public key %*ph\n", __func__, + ctrl->cntlid, (int)buf_size, buf); +#endif + } + + return ret; +} + +int nvmet_auth_ctrl_sesskey(struct nvmet_req *req, + const u8 *pkey, int pkey_size) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + int ret; + + req->sq->dhchap_skey_len = nvme_auth_hmac_hash_len(ctrl->shash_id); + req->sq->dhchap_skey = kzalloc(req->sq->dhchap_skey_len, GFP_KERNEL); + if (!req->sq->dhchap_skey) + return -ENOMEM; + ret = nvme_auth_gen_session_key(ctrl->dh_tfm, + pkey, pkey_size, + req->sq->dhchap_skey, + req->sq->dhchap_skey_len, + ctrl->shash_id); + if (ret) + pr_debug("failed to compute session key, err %d\n", ret); +#ifdef CONFIG_NVME_TARGET_AUTH_DEBUG + else + pr_debug("%s: session key %*ph\n", __func__, + (int)req->sq->dhchap_skey_len, + req->sq->dhchap_skey); +#endif + return ret; +} + +void nvmet_auth_insert_psk(struct nvmet_sq *sq) +{ + int hash_len = nvme_auth_hmac_hash_len(sq->ctrl->shash_id); + u8 *psk, *tls_psk; + char *digest; + size_t psk_len; + int ret; +#ifdef CONFIG_NVME_TARGET_TCP_TLS + struct key *tls_key = NULL; +#endif + + ret = nvme_auth_generate_psk(sq->ctrl->shash_id, + sq->dhchap_skey, + sq->dhchap_skey_len, + sq->dhchap_c1, sq->dhchap_c2, + hash_len, &psk, &psk_len); + if (ret) { + pr_warn("%s: ctrl %d qid %d failed to generate PSK, error %d\n", + __func__, sq->ctrl->cntlid, sq->qid, ret); + return; + } + ret = nvme_auth_generate_digest(sq->ctrl->shash_id, psk, psk_len, + sq->ctrl->subsys->subsysnqn, + sq->ctrl->hostnqn, &digest); + if (ret) { + pr_warn("%s: ctrl %d qid %d failed to generate digest, error %d\n", + __func__, sq->ctrl->cntlid, sq->qid, ret); + goto out_free_psk; + } + ret = nvme_auth_derive_tls_psk(sq->ctrl->shash_id, psk, psk_len, + digest, &tls_psk); + if (ret) { + pr_warn("%s: ctrl %d qid %d failed to derive TLS PSK, error %d\n", + __func__, sq->ctrl->cntlid, sq->qid, ret); + goto out_free_digest; + } +#ifdef CONFIG_NVME_TARGET_TCP_TLS + tls_key = nvme_tls_psk_refresh(NULL, sq->ctrl->hostnqn, + sq->ctrl->subsys->subsysnqn, + sq->ctrl->shash_id, tls_psk, psk_len, + digest); + if (IS_ERR(tls_key)) { + pr_warn("%s: ctrl %d qid %d failed to refresh key, error %ld\n", + __func__, sq->ctrl->cntlid, sq->qid, PTR_ERR(tls_key)); + tls_key = NULL; + } + if (sq->ctrl->tls_key) + key_put(sq->ctrl->tls_key); + sq->ctrl->tls_key = tls_key; +#endif + kfree_sensitive(tls_psk); +out_free_digest: + kfree_sensitive(digest); +out_free_psk: + kfree_sensitive(psk); +} |
