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, 61 insertions, 0 deletions

diff --git a/include/uapi/video/uvesafb.h b/include/uapi/video/uvesafb.h
new file mode 100644
index 000000000..a0d5c9213
--- /dev/null
+++ b/include/uapi/video/uvesafb.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_UVESAFB_H
+#define _UAPI_UVESAFB_H
+
+#include <linux/types.h>
+
+struct v86_regs {
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 esi;
+	__u32 edi;
+	__u32 ebp;
+	__u32 eax;
+	__u32 eip;
+	__u32 eflags;
+	__u32 esp;
+	__u16 cs;
+	__u16 ss;
+	__u16 es;
+	__u16 ds;
+	__u16 fs;
+	__u16 gs;
+};
+
+/* Task flags */
+#define TF_VBEIB	0x01
+#define TF_BUF_ESDI	0x02
+#define TF_BUF_ESBX	0x04
+#define TF_BUF_RET	0x08
+#define TF_EXIT		0x10
+
+struct uvesafb_task {
+	__u8 flags;
+	int buf_len;
+	struct v86_regs regs;
+};
+
+/* Constants for the capabilities field
+ * in vbe_ib */
+#define VBE_CAP_CAN_SWITCH_DAC	0x01
+#define VBE_CAP_VGACOMPAT	0x02
+
+/* The VBE Info Block */
+struct vbe_ib {
+	char  vbe_signature[4];
+	__u16 vbe_version;
+	__u32 oem_string_ptr;
+	__u32 capabilities;
+	__u32 mode_list_ptr;
+	__u16 total_memory;
+	__u16 oem_software_rev;
+	__u32 oem_vendor_name_ptr;
+	__u32 oem_product_name_ptr;
+	__u32 oem_product_rev_ptr;
+	__u8  reserved[222];
+	char  oem_data[256];
+	char  misc_data[512];
+} __attribute__ ((packed));
+
+#endif /* _UAPI_UVESAFB_H */