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, 56 insertions, 0 deletions

diff --git a/fs/lockd/nlm.h b/fs/lockd/nlm.h
new file mode 100644
index 000000000..47be65d01
--- /dev/null
+++ b/fs/lockd/nlm.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Declarations for the Network Lock Manager protocol.
+ *
+ * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LOCKD_NLM_H
+#define _LOCKD_NLM_H
+
+
+/* Maximum file offset in file_lock.fl_end */
+# define NLM_OFFSET_MAX		((s32) 0x7fffffff)
+# define NLM4_OFFSET_MAX	((s64) ((~(u64)0) >> 1))
+
+/* Return states for NLM */
+enum {
+	NLM_LCK_GRANTED			= 0,
+	NLM_LCK_DENIED			= 1,
+	NLM_LCK_DENIED_NOLOCKS		= 2,
+	NLM_LCK_BLOCKED			= 3,
+	NLM_LCK_DENIED_GRACE_PERIOD	= 4,
+#ifdef CONFIG_LOCKD_V4
+	NLM_DEADLCK			= 5,
+	NLM_ROFS			= 6,
+	NLM_STALE_FH			= 7,
+	NLM_FBIG			= 8,
+	NLM_FAILED			= 9,
+#endif
+};
+
+#define NLM_PROGRAM		100021
+
+#define NLMPROC_NULL		0
+#define NLMPROC_TEST		1
+#define NLMPROC_LOCK		2
+#define NLMPROC_CANCEL		3
+#define NLMPROC_UNLOCK		4
+#define NLMPROC_GRANTED		5
+#define NLMPROC_TEST_MSG	6
+#define NLMPROC_LOCK_MSG	7
+#define NLMPROC_CANCEL_MSG	8
+#define NLMPROC_UNLOCK_MSG	9
+#define NLMPROC_GRANTED_MSG	10
+#define NLMPROC_TEST_RES	11
+#define NLMPROC_LOCK_RES	12
+#define NLMPROC_CANCEL_RES	13
+#define NLMPROC_UNLOCK_RES	14
+#define NLMPROC_GRANTED_RES	15
+#define NLMPROC_NSM_NOTIFY	16		/* statd callback */
+#define NLMPROC_SHARE		20
+#define NLMPROC_UNSHARE		21
+#define NLMPROC_NM_LOCK		22
+#define NLMPROC_FREE_ALL	23
+
+#endif /* _LOCKD_NLM_H */