From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- fs/gfs2/util.h | 199 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 199 insertions(+) create mode 100644 fs/gfs2/util.h (limited to 'fs/gfs2/util.h') diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h new file mode 100644 index 000000000..ffcc47d6b --- /dev/null +++ b/fs/gfs2/util.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. + */ + +#ifndef __UTIL_DOT_H__ +#define __UTIL_DOT_H__ + +#ifdef pr_fmt +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#endif + +#include + +#include "incore.h" + +#define fs_emerg(fs, fmt, ...) \ + pr_emerg("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__) +#define fs_warn(fs, fmt, ...) \ + pr_warn("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__) +#define fs_err(fs, fmt, ...) \ + pr_err("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__) +#define fs_info(fs, fmt, ...) \ + pr_info("fsid=%s: " fmt, (fs)->sd_fsname, ##__VA_ARGS__) + +void gfs2_assert_i(struct gfs2_sbd *sdp); + +#define gfs2_assert(sdp, assertion) \ +do { \ + if (unlikely(!(assertion))) { \ + gfs2_assert_i(sdp); \ + BUG(); \ + } \ +} while (0) + + +void gfs2_assert_withdraw_i(struct gfs2_sbd *sdp, char *assertion, + const char *function, char *file, unsigned int line); + +#define gfs2_assert_withdraw(sdp, assertion) \ + ({ \ + bool _bool = (assertion); \ + if (unlikely(!_bool)) \ + gfs2_assert_withdraw_i((sdp), #assertion, \ + __func__, __FILE__, __LINE__); \ + !_bool; \ + }) + +void gfs2_assert_warn_i(struct gfs2_sbd *sdp, char *assertion, + const char *function, char *file, unsigned int line); + +#define gfs2_assert_warn(sdp, assertion) \ + ({ \ + bool _bool = (assertion); \ + if (unlikely(!_bool)) \ + gfs2_assert_warn_i((sdp), #assertion, \ + __func__, __FILE__, __LINE__); \ + !_bool; \ + }) + +void gfs2_consist_i(struct gfs2_sbd *sdp, + const char *function, char *file, unsigned int line); + +#define gfs2_consist(sdp) \ +gfs2_consist_i((sdp), __func__, __FILE__, __LINE__) + + +void gfs2_consist_inode_i(struct gfs2_inode *ip, + const char *function, char *file, unsigned int line); + +#define gfs2_consist_inode(ip) \ +gfs2_consist_inode_i((ip), __func__, __FILE__, __LINE__) + + +void gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, + const char *function, char *file, unsigned int line); + +#define gfs2_consist_rgrpd(rgd) \ +gfs2_consist_rgrpd_i((rgd), __func__, __FILE__, __LINE__) + + +void gfs2_meta_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh, + const char *function, + char *file, unsigned int line); + +static inline int gfs2_meta_check(struct gfs2_sbd *sdp, + struct buffer_head *bh) +{ + struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data; + u32 magic = be32_to_cpu(mh->mh_magic); + if (unlikely(magic != GFS2_MAGIC)) { + fs_err(sdp, "Magic number missing at %llu\n", + (unsigned long long)bh->b_blocknr); + return -EIO; + } + return 0; +} + +void gfs2_metatype_check_ii(struct gfs2_sbd *sdp, struct buffer_head *bh, + u16 type, u16 t, + const char *function, + char *file, unsigned int line); + +static inline int gfs2_metatype_check_i(struct gfs2_sbd *sdp, + struct buffer_head *bh, + u16 type, + const char *function, + char *file, unsigned int line) +{ + struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data; + u32 magic = be32_to_cpu(mh->mh_magic); + u16 t = be32_to_cpu(mh->mh_type); + if (unlikely(magic != GFS2_MAGIC)) { + gfs2_meta_check_ii(sdp, bh, function, + file, line); + return -EIO; + } + if (unlikely(t != type)) { + gfs2_metatype_check_ii(sdp, bh, type, t, function, + file, line); + return -EIO; + } + return 0; +} + +#define gfs2_metatype_check(sdp, bh, type) \ +gfs2_metatype_check_i((sdp), (bh), (type), __func__, __FILE__, __LINE__) + +static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type, + u16 format) +{ + struct gfs2_meta_header *mh; + mh = (struct gfs2_meta_header *)bh->b_data; + mh->mh_type = cpu_to_be32(type); + mh->mh_format = cpu_to_be32(format); +} + + +void gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, + char *file, unsigned int line); + +int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, + bool verbose); +int gfs2_freeze_lock_shared(struct gfs2_sbd *sdp); +void gfs2_freeze_unlock(struct gfs2_sbd *sdp); + +#define gfs2_io_error(sdp) \ +gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__) + + +void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh, + const char *function, char *file, unsigned int line); + +#define gfs2_io_error_bh(sdp, bh) \ +gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__) + + +extern struct kmem_cache *gfs2_glock_cachep; +extern struct kmem_cache *gfs2_glock_aspace_cachep; +extern struct kmem_cache *gfs2_inode_cachep; +extern struct kmem_cache *gfs2_bufdata_cachep; +extern struct kmem_cache *gfs2_rgrpd_cachep; +extern struct kmem_cache *gfs2_quotad_cachep; +extern struct kmem_cache *gfs2_qadata_cachep; +extern struct kmem_cache *gfs2_trans_cachep; +extern mempool_t *gfs2_page_pool; +extern struct workqueue_struct *gfs2_control_wq; + +static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, + unsigned int *p) +{ + unsigned int x; + spin_lock(>->gt_spin); + x = *p; + spin_unlock(>->gt_spin); + return x; +} + +/** + * gfs2_withdrawn - test whether the file system is withdrawn + * @sdp: the superblock + */ +static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp) +{ + return unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)); +} + +#define gfs2_tune_get(sdp, field) \ +gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field) + +__printf(2, 3) +void gfs2_lm(struct gfs2_sbd *sdp, const char *fmt, ...); + +void gfs2_withdraw_func(struct work_struct *work); +void gfs2_withdraw(struct gfs2_sbd *sdp); + +#endif /* __UTIL_DOT_H__ */ -- cgit v1.3.1