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, 49 insertions, 0 deletions

diff --git a/io_uring/cancel.h b/io_uring/cancel.h
new file mode 100644
index 000000000..1b201a094
--- /dev/null
+++ b/io_uring/cancel.h
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IORING_CANCEL_H
+#define IORING_CANCEL_H
+
+#include <linux/io_uring_types.h>
+
+struct io_cancel_data {
+	struct io_ring_ctx *ctx;
+	u64 data;
+	struct file *file;
+	u8 opcode;
+	u32 flags;
+	int seq;
+};
+
+int io_async_cancel_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_try_cancel(struct io_uring_task *tctx, struct io_cancel_data *cd,
+		  unsigned int issue_flags);
+
+int io_sync_cancel(struct io_ring_ctx *ctx, void __user *arg);
+bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd);
+bool io_match_task_safe(struct io_kiocb *head, struct io_uring_task *tctx,
+			bool cancel_all);
+
+bool io_cancel_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+			  struct hlist_head *list, bool cancel_all,
+			  bool (*cancel)(struct io_kiocb *));
+int io_cancel_remove(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		     unsigned int issue_flags, struct hlist_head *list,
+		     bool (*cancel)(struct io_kiocb *));
+__cold bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
+					 struct io_uring_task *tctx,
+					 bool cancel_all, bool is_sqpoll_thread);
+__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
+__cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data);
+
+static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence)
+{
+	if (req->cancel_seq_set && sequence == req->work.cancel_seq)
+		return true;
+
+	req->cancel_seq_set = true;
+	req->work.cancel_seq = sequence;
+	return false;
+}
+
+#endif