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, 80 insertions, 0 deletions

diff --git a/include/uapi/misc/ocxl.h b/include/uapi/misc/ocxl.h
new file mode 100644
index 000000000..6d29a60a8
--- /dev/null
+++ b/include/uapi/misc/ocxl.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* Copyright 2017 IBM Corp. */
+#ifndef _UAPI_MISC_OCXL_H
+#define _UAPI_MISC_OCXL_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+enum ocxl_event_type {
+	OCXL_AFU_EVENT_XSL_FAULT_ERROR = 0,
+};
+
+#define OCXL_KERNEL_EVENT_FLAG_LAST 0x0001  /* This is the last event pending */
+
+struct ocxl_kernel_event_header {
+	__u16 type;
+	__u16 flags;
+	__u32 reserved;
+};
+
+struct ocxl_kernel_event_xsl_fault_error {
+	__u64 addr;
+	__u64 dsisr;
+	__u64 count;
+	__u64 reserved;
+};
+
+struct ocxl_ioctl_attach {
+	__u64 amr;
+	__u64 reserved1;
+	__u64 reserved2;
+	__u64 reserved3;
+};
+
+struct ocxl_ioctl_metadata {
+	__u16 version; /* struct version, always backwards compatible */
+
+	/* Version 0 fields */
+	__u8  afu_version_major;
+	__u8  afu_version_minor;
+	__u32 pasid;		/* PASID assigned to the current context */
+
+	__u64 pp_mmio_size;	/* Per PASID MMIO size */
+	__u64 global_mmio_size;
+
+	/* End version 0 fields */
+
+	__u64 reserved[13]; /* Total of 16*u64 */
+};
+
+struct ocxl_ioctl_p9_wait {
+	__u16 thread_id; /* The thread ID required to wake this thread */
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 reserved3[3];
+};
+
+#define OCXL_IOCTL_FEATURES_FLAGS0_P9_WAIT	0x01
+struct ocxl_ioctl_features {
+	__u64 flags[4];
+};
+
+struct ocxl_ioctl_irq_fd {
+	__u64 irq_offset;
+	__s32 eventfd;
+	__u32 reserved;
+};
+
+/* ioctl numbers */
+#define OCXL_MAGIC 0xCA
+/* AFU devices */
+#define OCXL_IOCTL_ATTACH	_IOW(OCXL_MAGIC, 0x10, struct ocxl_ioctl_attach)
+#define OCXL_IOCTL_IRQ_ALLOC	_IOR(OCXL_MAGIC, 0x11, __u64)
+#define OCXL_IOCTL_IRQ_FREE	_IOW(OCXL_MAGIC, 0x12, __u64)
+#define OCXL_IOCTL_IRQ_SET_FD	_IOW(OCXL_MAGIC, 0x13, struct ocxl_ioctl_irq_fd)
+#define OCXL_IOCTL_GET_METADATA _IOR(OCXL_MAGIC, 0x14, struct ocxl_ioctl_metadata)
+#define OCXL_IOCTL_ENABLE_P9_WAIT	_IOR(OCXL_MAGIC, 0x15, struct ocxl_ioctl_p9_wait)
+#define OCXL_IOCTL_GET_FEATURES _IOR(OCXL_MAGIC, 0x16, struct ocxl_ioctl_features)
+
+#endif /* _UAPI_MISC_OCXL_H */