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, 71 insertions, 0 deletions

diff --git a/lib/lzo/lzodefs.h b/lib/lzo/lzodefs.h
new file mode 100644
index 000000000..b60851fcf
--- /dev/null
+++ b/lib/lzo/lzodefs.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  lzodefs.h -- architecture, OS and compiler specific defines
+ *
+ *  Copyright (C) 1996-2012 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for Linux kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+
+/* Version
+ * 0: original lzo version
+ * 1: lzo with support for RLE
+ */
+#define LZO_VERSION 1
+
+#define COPY4(dst, src)	\
+		put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst))
+#if defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
+#define COPY8(dst, src)	\
+		put_unaligned(get_unaligned((const u64 *)(src)), (u64 *)(dst))
+#else
+#define COPY8(dst, src)	\
+		COPY4(dst, src); COPY4((dst) + 4, (src) + 4)
+#endif
+
+#if defined(__BIG_ENDIAN) && defined(__LITTLE_ENDIAN)
+#error "conflicting endian definitions"
+#elif defined(CONFIG_X86_64) || defined(CONFIG_ARM64)
+#define LZO_USE_CTZ64	1
+#define LZO_USE_CTZ32	1
+#define LZO_FAST_64BIT_MEMORY_ACCESS
+#elif defined(CONFIG_X86) || defined(CONFIG_PPC)
+#define LZO_USE_CTZ32	1
+#elif defined(CONFIG_ARM) && (__LINUX_ARM_ARCH__ >= 5)
+#define LZO_USE_CTZ32	1
+#endif
+
+#define M1_MAX_OFFSET	0x0400
+#define M2_MAX_OFFSET	0x0800
+#define M3_MAX_OFFSET	0x4000
+#define M4_MAX_OFFSET_V0	0xbfff
+#define M4_MAX_OFFSET_V1	0xbffe
+
+#define M1_MIN_LEN	2
+#define M1_MAX_LEN	2
+#define M2_MIN_LEN	3
+#define M2_MAX_LEN	8
+#define M3_MIN_LEN	3
+#define M3_MAX_LEN	33
+#define M4_MIN_LEN	3
+#define M4_MAX_LEN	9
+
+#define M1_MARKER	0
+#define M2_MARKER	64
+#define M3_MARKER	32
+#define M4_MARKER	16
+
+#define MIN_ZERO_RUN_LENGTH	4
+#define MAX_ZERO_RUN_LENGTH	(2047 + MIN_ZERO_RUN_LENGTH)
+
+#define lzo_dict_t      unsigned short
+#define D_BITS		13
+#define D_SIZE		(1u << D_BITS)
+#define D_MASK		(D_SIZE - 1)
+#define D_HIGH		((D_MASK >> 1) + 1)