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, 141 insertions, 0 deletions

diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
new file mode 100644
index 000000000..401773e1e
--- /dev/null
+++ b/io_uring/kbuf.h
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_KBUF_H
+#define IOU_KBUF_H
+
+#include <uapi/linux/io_uring.h>
+#include <linux/io_uring_types.h>
+
+enum {
+	/* ring mapped provided buffers */
+	IOBL_BUF_RING	= 1,
+	/* buffers are consumed incrementally rather than always fully */
+	IOBL_INC	= 2,
+};
+
+struct io_buffer_list {
+	/*
+	 * If the IOBL_BUF_RING flag is set, then buf_ring is used. If not, then
+	 * these are classic provided buffers and ->buf_list is used.
+	 */
+	union {
+		struct list_head buf_list;
+		struct io_uring_buf_ring *buf_ring;
+	};
+	/* count of classic/legacy buffers in buffer list */
+	int nbufs;
+
+	__u16 bgid;
+
+	/* below is for ring provided buffers */
+	__u16 head;
+	__u16 mask;
+
+	__u16 flags;
+
+	/*
+	 * minimum required amount to be left to reuse an incrementally
+	 * consumed buffer. If less than this is left at consumption time,
+	 * buffer is done and head is incremented to the next buffer.
+	 */
+	__u32 min_left_sub_one;
+
+	struct io_mapped_region region;
+};
+
+struct io_buffer {
+	struct list_head list;
+	__u64 addr;
+	__u32 len;
+	__u16 bid;
+	__u16 bgid;
+};
+
+enum {
+	/* can alloc a bigger vec */
+	KBUF_MODE_EXPAND	= 1,
+	/* if bigger vec allocated, free old one */
+	KBUF_MODE_FREE		= 2,
+};
+
+struct buf_sel_arg {
+	struct iovec *iovs;
+	size_t out_len;
+	size_t max_len;
+	unsigned short nr_iovs;
+	unsigned short mode;
+	unsigned short buf_group;
+	unsigned short partial_map;
+};
+
+struct io_br_sel io_buffer_select(struct io_kiocb *req, size_t *len,
+				  unsigned buf_group, unsigned int issue_flags);
+int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg,
+		      struct io_br_sel *sel, unsigned int issue_flags);
+int io_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
+		    struct io_br_sel *sel);
+void io_destroy_buffers(struct io_ring_ctx *ctx);
+
+int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+int io_manage_buffers_legacy(struct io_kiocb *req, unsigned int issue_flags);
+
+int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
+int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg);
+int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg);
+
+bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
+void io_kbuf_drop_legacy(struct io_kiocb *req);
+
+unsigned int __io_put_kbufs(struct io_kiocb *req, struct io_buffer_list *bl,
+			    int len, int nbufs);
+bool io_kbuf_commit(struct io_kiocb *req,
+		    struct io_buffer_list *bl, int len, int nr);
+
+struct io_mapped_region *io_pbuf_get_region(struct io_ring_ctx *ctx,
+					    unsigned int bgid);
+
+static inline bool io_kbuf_recycle_ring(struct io_kiocb *req,
+					struct io_buffer_list *bl)
+{
+	if (bl) {
+		req->flags &= ~(REQ_F_BUFFER_RING|REQ_F_BUFFERS_COMMIT);
+		return true;
+	}
+	return false;
+}
+
+static inline bool io_do_buffer_select(struct io_kiocb *req)
+{
+	if (!(req->flags & REQ_F_BUFFER_SELECT))
+		return false;
+	return !(req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING));
+}
+
+static inline bool io_kbuf_recycle(struct io_kiocb *req, struct io_buffer_list *bl,
+				   unsigned issue_flags)
+{
+	if (req->flags & REQ_F_BL_NO_RECYCLE)
+		return false;
+	if (req->flags & REQ_F_BUFFER_RING)
+		return io_kbuf_recycle_ring(req, bl);
+	if (req->flags & REQ_F_BUFFER_SELECTED)
+		return io_kbuf_recycle_legacy(req, issue_flags);
+	return false;
+}
+
+static inline unsigned int io_put_kbuf(struct io_kiocb *req, int len,
+				       struct io_buffer_list *bl)
+{
+	if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
+		return 0;
+	return __io_put_kbufs(req, bl, len, 1);
+}
+
+static inline unsigned int io_put_kbufs(struct io_kiocb *req, int len,
+					struct io_buffer_list *bl, int nbufs)
+{
+	if (!(req->flags & (REQ_F_BUFFER_RING | REQ_F_BUFFER_SELECTED)))
+		return 0;
+	return __io_put_kbufs(req, bl, len, nbufs);
+}
+#endif