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, 65 insertions, 0 deletions

diff --git a/arch/mips/boot/ecoff.h b/arch/mips/boot/ecoff.h
new file mode 100644
index 000000000..5be79ebfc
--- /dev/null
+++ b/arch/mips/boot/ecoff.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Some ECOFF definitions.
+ */
+
+#include <stdint.h>
+
+typedef struct filehdr {
+	uint16_t	f_magic;	/* magic number */
+	uint16_t	f_nscns;	/* number of sections */
+	int32_t		f_timdat;	/* time & date stamp */
+	int32_t		f_symptr;	/* file pointer to symbolic header */
+	int32_t		f_nsyms;	/* sizeof(symbolic hdr) */
+	uint16_t	f_opthdr;	/* sizeof(optional hdr) */
+	uint16_t	f_flags;	/* flags */
+} FILHDR;
+#define FILHSZ	sizeof(FILHDR)
+
+#define MIPSEBMAGIC	0x160
+#define MIPSELMAGIC	0x162
+
+typedef struct scnhdr {
+	char		s_name[8];	/* section name */
+	int32_t		s_paddr;	/* physical address, aliased s_nlib */
+	int32_t		s_vaddr;	/* virtual address */
+	int32_t		s_size;		/* section size */
+	int32_t		s_scnptr;	/* file ptr to raw data for section */
+	int32_t		s_relptr;	/* file ptr to relocation */
+	int32_t		s_lnnoptr;	/* file ptr to gp histogram */
+	uint16_t	s_nreloc;	/* number of relocation entries */
+	uint16_t	s_nlnno;	/* number of gp histogram entries */
+	int32_t		s_flags;	/* flags */
+} SCNHDR;
+#define SCNHSZ		sizeof(SCNHDR)
+#define SCNROUND	((int32_t)16)
+
+typedef struct aouthdr {
+	int16_t	magic;		/* see above				*/
+	int16_t	vstamp;		/* version stamp			*/
+	int32_t	tsize;		/* text size in bytes, padded to DW bdry*/
+	int32_t	dsize;		/* initialized data "  "		*/
+	int32_t	bsize;		/* uninitialized data "	  "		*/
+	int32_t	entry;		/* entry pt.				*/
+	int32_t	text_start;	/* base of text used for this file	*/
+	int32_t	data_start;	/* base of data used for this file	*/
+	int32_t	bss_start;	/* base of bss used for this file	*/
+	int32_t	gprmask;	/* general purpose register mask	*/
+	int32_t	cprmask[4];	/* co-processor register masks		*/
+	int32_t	gp_value;	/* the gp value used for this object	*/
+} AOUTHDR;
+#define AOUTHSZ sizeof(AOUTHDR)
+
+#define OMAGIC		0407
+#define NMAGIC		0410
+#define ZMAGIC		0413
+#define SMAGIC		0411
+#define LIBMAGIC	0443
+
+#define N_TXTOFF(f, a) \
+ ((a).magic == ZMAGIC || (a).magic == LIBMAGIC ? 0 : \
+  ((a).vstamp < 23 ? \
+   ((FILHSZ + AOUTHSZ + (f).f_nscns * SCNHSZ + 7) & 0xfffffff8) : \
+   ((FILHSZ + AOUTHSZ + (f).f_nscns * SCNHSZ + SCNROUND-1) & ~(SCNROUND-1)) ) )
+#define N_DATOFF(f, a) \
+  N_TXTOFF(f, a) + (a).tsize;