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, 85 insertions, 0 deletions

diff --git a/fs/lockd/xdr.h b/fs/lockd/xdr.h
new file mode 100644
index 000000000..a1126cca9
--- /dev/null
+++ b/fs/lockd/xdr.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * XDR types for the NLM protocol
+ *
+ * Copyright (C) 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LOCKD_XDR_H
+#define _LOCKD_XDR_H
+
+#include <linux/fs.h>
+#include <linux/filelock.h>
+#include <linux/nfs.h>
+#include <linux/sunrpc/xdr.h>
+
+#define SM_MAXSTRLEN		1024
+#define SM_PRIV_SIZE		16
+
+struct nsm_private {
+	unsigned char		data[SM_PRIV_SIZE];
+};
+
+#define NLM_MAXCOOKIELEN    	32
+#define NLM_MAXSTRLEN		1024
+
+#define	nlm_granted		cpu_to_be32(NLM_LCK_GRANTED)
+#define	nlm_lck_denied		cpu_to_be32(NLM_LCK_DENIED)
+#define	nlm_lck_denied_nolocks	cpu_to_be32(NLM_LCK_DENIED_NOLOCKS)
+#define	nlm_lck_blocked		cpu_to_be32(NLM_LCK_BLOCKED)
+#define	nlm_lck_denied_grace_period	cpu_to_be32(NLM_LCK_DENIED_GRACE_PERIOD)
+
+/* Lock info passed via NLM */
+struct lockd_lock {
+	char *			caller;
+	unsigned int		len; 	/* length of "caller" */
+	struct nfs_fh		fh;
+	struct xdr_netobj	oh;
+	u32			svid;
+	u64			lock_start;
+	u64			lock_len;
+	struct file_lock	fl;
+};
+
+/*
+ *	NLM cookies. Technically they can be 1K, but Linux only uses 8 bytes.
+ *	FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to
+ *	32 bytes.
+ */
+
+struct lockd_cookie {
+	unsigned char data[NLM_MAXCOOKIELEN];
+	unsigned int len;
+};
+
+/*
+ * Generic lockd arguments for all but sm_notify
+ */
+struct lockd_args {
+	struct lockd_cookie	cookie;
+	struct lockd_lock	lock;
+	u32			block;
+	u32			reclaim;
+	u32			state;
+};
+
+/*
+ * Generic lockd result
+ */
+struct lockd_res {
+	struct lockd_cookie	cookie;
+	__be32			status;
+	struct lockd_lock	lock;
+};
+
+/*
+ * statd callback when client has rebooted
+ */
+struct lockd_reboot {
+	char			*mon;
+	unsigned int		len;
+	u32			state;
+	struct nsm_private	priv;
+};
+
+#endif /* _LOCKD_XDR_H */