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, 54 insertions, 0 deletions

diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
new file mode 100644
index 000000000..079284120
--- /dev/null
+++ b/fs/pstore/internal.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PSTORE_INTERNAL_H__
+#define __PSTORE_INTERNAL_H__
+
+#include <linux/types.h>
+#include <linux/time.h>
+#include <linux/pstore.h>
+
+extern unsigned int kmsg_bytes;
+
+#ifdef CONFIG_PSTORE_FTRACE
+extern unsigned long decode_ip(unsigned long ip);
+extern void pstore_register_ftrace(void);
+extern void pstore_unregister_ftrace(void);
+ssize_t pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size,
+				  const char *src_log, size_t src_log_size);
+#else
+static inline void pstore_register_ftrace(void) {}
+static inline void pstore_unregister_ftrace(void) {}
+static inline unsigned long decode_ip(unsigned long ip) { return ip; }
+static inline ssize_t
+pstore_ftrace_combine_log(char **dest_log, size_t *dest_log_size,
+			  const char *src_log, size_t src_log_size)
+{
+	*dest_log_size = 0;
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_PSTORE_PMSG
+extern void pstore_register_pmsg(void);
+extern void pstore_unregister_pmsg(void);
+#else
+static inline void pstore_register_pmsg(void) {}
+static inline void pstore_unregister_pmsg(void) {}
+#endif
+
+extern struct pstore_info *psinfo;
+
+extern void	pstore_set_kmsg_bytes(unsigned int bytes);
+extern void	pstore_get_records(int);
+extern void	pstore_get_backend_records(struct pstore_info *psi,
+					   struct dentry *root, int quiet);
+extern int	pstore_put_backend_records(struct pstore_info *psi);
+extern int	pstore_mkfile(struct dentry *root,
+			      struct pstore_record *record);
+extern void	pstore_record_init(struct pstore_record *record,
+				   struct pstore_info *psi);
+
+/* Called during pstore init/exit. */
+int __init	pstore_init_fs(void);
+void __exit	pstore_exit_fs(void);
+
+#endif