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/tracefs/internal.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 fs/tracefs/internal.h (limited to 'fs/tracefs/internal.h') diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h new file mode 100644 index 000000000..c61481d04 --- /dev/null +++ b/fs/tracefs/internal.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TRACEFS_INTERNAL_H +#define _TRACEFS_INTERNAL_H + +enum { + TRACEFS_EVENT_INODE = BIT(1), + TRACEFS_GID_PERM_SET = BIT(2), + TRACEFS_UID_PERM_SET = BIT(3), + TRACEFS_INSTANCE_INODE = BIT(4), +}; + +struct tracefs_inode { + struct inode vfs_inode; + /* The below gets initialized with memset_after(ti, 0, vfs_inode) */ + struct list_head list; + unsigned long flags; + void *private; +}; + +/* + * struct eventfs_attr - cache the mode and ownership of a eventfs entry + * @mode: saved mode plus flags of what is saved + * @uid: saved uid if changed + * @gid: saved gid if changed + */ +struct eventfs_attr { + int mode; + kuid_t uid; + kgid_t gid; +}; + +/* + * struct eventfs_inode - hold the properties of the eventfs directories. + * @list: link list into the parent directory + * @rcu: Union with @list for freeing + * @children: link list into the child eventfs_inode + * @entries: the array of entries representing the files in the directory + * @name: the name of the directory to create + * @entry_attrs: Saved mode and ownership of the @d_children + * @data: The private data to pass to the callbacks + * @attr: Saved mode and ownership of eventfs_inode itself + * @is_freed: Flag set if the eventfs is on its way to be freed + * Note if is_freed is set, then dentry is corrupted. + * @is_events: Flag set for only the top level "events" directory + * @nr_entries: The number of items in @entries + * @ino: The saved inode number + */ +struct eventfs_inode { + struct list_head list; + union { + struct list_head children; + struct rcu_head rcu; + }; + const struct eventfs_entry *entries; + const char *name; + struct eventfs_attr *entry_attrs; + void *data; + struct eventfs_attr attr; + struct kref kref; + unsigned int is_freed:1; + unsigned int is_events:1; + unsigned int nr_entries:30; + unsigned int ino; +}; + +static inline struct tracefs_inode *get_tracefs(const struct inode *inode) +{ + return container_of(inode, struct tracefs_inode, vfs_inode); +} + +struct dentry *tracefs_start_creating(const char *name, struct dentry *parent); +struct dentry *tracefs_end_creating(struct dentry *dentry); +struct dentry *tracefs_failed_creating(struct dentry *dentry); +struct inode *tracefs_get_inode(struct super_block *sb); + +void eventfs_remount(struct tracefs_inode *ti, bool update_uid, bool update_gid); +void eventfs_d_release(struct dentry *dentry); + +int eventfs_remount_lock(void); +void eventfs_remount_unlock(int srcu_idx); + +#endif /* _TRACEFS_INTERNAL_H */ -- cgit v1.3.1