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, 53 insertions, 0 deletions

diff --git a/io_uring/rw.h b/io_uring/rw.h
new file mode 100644
index 000000000..1179506f9
--- /dev/null
+++ b/io_uring/rw.h
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/io_uring_types.h>
+#include <linux/pagemap.h>
+#include <linux/uio.h>
+
+struct io_meta_state {
+	u32			seed;
+	struct iov_iter_state	iter_meta;
+};
+
+struct io_async_rw {
+	struct iou_vec			vec;
+	size_t				bytes_done;
+
+	struct_group(clear,
+		struct iov_iter			iter;
+		struct iov_iter_state		iter_state;
+		struct iovec			fast_iov;
+		unsigned			buf_group;
+
+		/*
+		 * wpq is for buffered io, while meta fields are used with
+		 * direct io
+		 */
+		union {
+			struct wait_page_queue		wpq;
+			struct {
+				struct uio_meta			meta;
+				struct io_meta_state		meta_state;
+			};
+		};
+	);
+};
+
+int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_write_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_readv_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_writev_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_readv(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_writev(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_prep_write(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_read(struct io_kiocb *req, unsigned int issue_flags);
+int io_write(struct io_kiocb *req, unsigned int issue_flags);
+int io_read_fixed(struct io_kiocb *req, unsigned int issue_flags);
+int io_write_fixed(struct io_kiocb *req, unsigned int issue_flags);
+void io_readv_writev_cleanup(struct io_kiocb *req);
+void io_rw_fail(struct io_kiocb *req);
+void io_req_rw_complete(struct io_tw_req tw_req, io_tw_token_t tw);
+int io_read_mshot_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags);
+void io_rw_cache_free(const void *entry);