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, 51 insertions, 0 deletions

diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
new file mode 100644
index 000000000..04c2f3175
--- /dev/null
+++ b/fs/btrfs/async-thread.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2007 Oracle.  All rights reserved.
+ * Copyright (C) 2014 Fujitsu.  All rights reserved.
+ */
+
+#ifndef BTRFS_ASYNC_THREAD_H
+#define BTRFS_ASYNC_THREAD_H
+
+#include <linux/compiler_types.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+
+struct btrfs_fs_info;
+struct btrfs_workqueue;
+struct btrfs_work;
+
+typedef void (*btrfs_func_t)(struct btrfs_work *arg);
+typedef void (*btrfs_ordered_func_t)(struct btrfs_work *arg, bool);
+
+struct btrfs_work {
+	btrfs_func_t func;
+	btrfs_ordered_func_t ordered_func;
+
+	/* Don't touch things below */
+	struct work_struct normal_work;
+	struct list_head ordered_list;
+	struct btrfs_workqueue *wq;
+	unsigned long flags;
+};
+
+struct btrfs_workqueue *btrfs_alloc_workqueue(struct btrfs_fs_info *fs_info,
+					      const char *name,
+					      unsigned int flags,
+					      int limit_active,
+					      int thresh);
+struct btrfs_workqueue *btrfs_alloc_ordered_workqueue(
+				struct btrfs_fs_info *fs_info, const char *name,
+				unsigned int flags);
+void btrfs_init_work(struct btrfs_work *work, btrfs_func_t func,
+		     btrfs_ordered_func_t ordered_func);
+void btrfs_queue_work(struct btrfs_workqueue *wq,
+		      struct btrfs_work *work);
+void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
+void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
+struct btrfs_fs_info * __pure btrfs_work_owner(const struct btrfs_work *work);
+struct btrfs_fs_info * __pure btrfs_workqueue_owner(const struct btrfs_workqueue *wq);
+bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq);
+void btrfs_flush_workqueue(struct btrfs_workqueue *wq);
+
+#endif