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, 82 insertions, 0 deletions

diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
new file mode 100644
index 000000000..37d658887
--- /dev/null
+++ b/include/xen/interface/version.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: MIT */
+/******************************************************************************
+ * version.h
+ *
+ * Xen version, type, and compile information.
+ *
+ * Copyright (c) 2005, Nguyen Anh Quynh <aquynh@gmail.com>
+ * Copyright (c) 2005, Keir Fraser <keir@xensource.com>
+ */
+
+#ifndef __XEN_PUBLIC_VERSION_H__
+#define __XEN_PUBLIC_VERSION_H__
+
+/* NB. All ops return zero on success, except XENVER_version. */
+
+/* arg == NULL; returns major:minor (16:16). */
+#define XENVER_version      0
+
+/* arg == xen_extraversion_t. */
+#define XENVER_extraversion 1
+struct xen_extraversion {
+    char extraversion[16];
+};
+#define XEN_EXTRAVERSION_LEN (sizeof(struct xen_extraversion))
+
+/* arg == xen_compile_info_t. */
+#define XENVER_compile_info 2
+struct xen_compile_info {
+    char compiler[64];
+    char compile_by[16];
+    char compile_domain[32];
+    char compile_date[32];
+};
+
+#define XENVER_capabilities 3
+struct xen_capabilities_info {
+    char info[1024];
+};
+#define XEN_CAPABILITIES_INFO_LEN (sizeof(struct xen_capabilities_info))
+
+#define XENVER_changeset 4
+struct xen_changeset_info {
+    char info[64];
+};
+#define XEN_CHANGESET_INFO_LEN (sizeof(struct xen_changeset_info))
+
+#define XENVER_platform_parameters 5
+struct xen_platform_parameters {
+    xen_ulong_t virt_start;
+};
+
+#define XENVER_get_features 6
+struct xen_feature_info {
+    unsigned int submap_idx;    /* IN: which 32-bit submap to return */
+    uint32_t     submap;        /* OUT: 32-bit submap */
+};
+
+/* Declares the features reported by XENVER_get_features. */
+#include <xen/interface/features.h>
+
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
+/* arg == xen_domain_handle_t. */
+#define XENVER_guest_handle 8
+
+#define XENVER_commandline 9
+struct xen_commandline {
+	char buf[1024];
+};
+
+/*
+ * Return value is the number of bytes written, or XEN_Exx on error.
+ * Calling with empty parameter returns the size of build_id.
+ */
+#define XENVER_build_id 10
+struct xen_build_id {
+	uint32_t	len; /* IN: size of buf[]. */
+	unsigned char	buf[];
+};
+
+#endif /* __XEN_PUBLIC_VERSION_H__ */