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

1 files changed, 58 insertions, 0 deletions

diff --git a/fs/btrfs/tree-mod-log.h b/fs/btrfs/tree-mod-log.h
new file mode 100644
index 000000000..1c1256604
--- /dev/null
+++ b/fs/btrfs/tree-mod-log.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_TREE_MOD_LOG_H
+#define BTRFS_TREE_MOD_LOG_H
+
+#include <linux/list.h>
+
+struct extent_buffer;
+struct btrfs_fs_info;
+struct btrfs_path;
+struct btrfs_root;
+struct btrfs_seq_list;
+
+/* Represents a tree mod log user. */
+struct btrfs_seq_list {
+	struct list_head list;
+	u64 seq;
+};
+
+#define BTRFS_SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
+#define BTRFS_SEQ_LAST            ((u64)-1)
+
+enum btrfs_mod_log_op {
+	BTRFS_MOD_LOG_KEY_REPLACE,
+	BTRFS_MOD_LOG_KEY_ADD,
+	BTRFS_MOD_LOG_KEY_REMOVE,
+	BTRFS_MOD_LOG_KEY_REMOVE_WHILE_FREEING,
+	BTRFS_MOD_LOG_KEY_REMOVE_WHILE_MOVING,
+	BTRFS_MOD_LOG_MOVE_KEYS,
+	BTRFS_MOD_LOG_ROOT_REPLACE,
+};
+
+u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
+			   struct btrfs_seq_list *elem);
+void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
+			    struct btrfs_seq_list *elem);
+int btrfs_tree_mod_log_insert_root(struct extent_buffer *old_root,
+				   struct extent_buffer *new_root,
+				   bool log_removal);
+int btrfs_tree_mod_log_insert_key(const struct extent_buffer *eb, int slot,
+				  enum btrfs_mod_log_op op);
+int btrfs_tree_mod_log_free_eb(struct extent_buffer *eb);
+struct extent_buffer *btrfs_tree_mod_log_rewind(struct btrfs_fs_info *fs_info,
+						struct extent_buffer *eb,
+						u64 time_seq);
+struct extent_buffer *btrfs_get_old_root(struct btrfs_root *root, u64 time_seq);
+int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
+int btrfs_tree_mod_log_eb_copy(struct extent_buffer *dst,
+			       const struct extent_buffer *src,
+			       unsigned long dst_offset,
+			       unsigned long src_offset,
+			       int nr_items);
+int btrfs_tree_mod_log_insert_move(const struct extent_buffer *eb,
+				   int dst_slot, int src_slot,
+				   int nr_items);
+u64 btrfs_tree_mod_log_lowest_seq(struct btrfs_fs_info *fs_info);
+
+#endif