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, 156 insertions, 0 deletions

diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
new file mode 100644
index 000000000..9ef88383b
--- /dev/null
+++ b/io_uring/rsrc.h
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_RSRC_H
+#define IOU_RSRC_H
+
+#include <linux/bvec.h>
+#include <linux/io_uring_types.h>
+#include <linux/lockdep.h>
+#include <linux/uio.h>
+
+#define IO_VEC_CACHE_SOFT_CAP		256
+
+enum {
+	IORING_RSRC_FILE		= 0,
+	IORING_RSRC_BUFFER		= 1,
+};
+
+struct io_rsrc_node {
+	unsigned char			type;
+	int				refs;
+
+	u64 tag;
+	union {
+		unsigned long file_ptr;
+		struct io_mapped_ubuf *buf;
+	};
+};
+
+enum {
+	IO_REGBUF_F_KBUF		= 1,
+};
+
+struct io_mapped_ubuf {
+	u64		ubuf;
+	size_t		len;
+	unsigned int	nr_bvecs;
+	unsigned int    folio_shift;
+	refcount_t	refs;
+	u8		flags;
+	u8		dir;
+	void		(*release)(void *);
+	void		*priv;
+	struct bio_vec	bvec[] __counted_by(nr_bvecs);
+};
+
+struct io_imu_folio_data {
+	/* Head folio can be partially included in the fixed buf */
+	unsigned int	nr_pages_head;
+	/* For non-head/tail folios, has to be fully included */
+	unsigned int	nr_pages_mid;
+	unsigned int	folio_shift;
+	unsigned int	nr_folios;
+	unsigned long	first_folio_page_idx;
+};
+
+bool io_rsrc_cache_init(struct io_ring_ctx *ctx);
+void io_rsrc_cache_free(struct io_ring_ctx *ctx);
+struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type);
+void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node);
+void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data);
+int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr);
+
+struct io_rsrc_node *io_find_buf_node(struct io_kiocb *req,
+				      unsigned issue_flags);
+int io_import_reg_buf(struct io_kiocb *req, struct iov_iter *iter,
+			u64 buf_addr, size_t len, int ddir,
+			unsigned issue_flags);
+int io_import_reg_vec(int ddir, struct iov_iter *iter,
+			struct io_kiocb *req, struct iou_vec *vec,
+			unsigned nr_iovs, unsigned issue_flags);
+int io_prep_reg_iovec(struct io_kiocb *req, struct iou_vec *iv,
+			const struct iovec __user *uvec, size_t uvec_segs);
+
+int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg);
+int io_sqe_buffers_unregister(struct io_ring_ctx *ctx);
+int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
+			    unsigned int nr_args, u64 __user *tags);
+int io_sqe_files_unregister(struct io_ring_ctx *ctx);
+int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
+			  unsigned nr_args, u64 __user *tags);
+
+int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg,
+			     unsigned nr_args);
+int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
+			    unsigned size, unsigned type);
+int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
+			unsigned int size, unsigned int type);
+int io_validate_user_buf_range(u64 uaddr, u64 ulen);
+
+bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
+			      struct io_imu_folio_data *data);
+
+static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data,
+						       unsigned int index)
+{
+	if (index < data->nr)
+		return data->nodes[array_index_nospec(index, data->nr)];
+	return NULL;
+}
+
+static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	if (!--node->refs)
+		io_free_rsrc_node(ctx, node);
+}
+
+static inline bool io_reset_rsrc_node(struct io_ring_ctx *ctx,
+				      struct io_rsrc_data *data,
+				      unsigned int index)
+{
+	struct io_rsrc_node *node;
+
+	if (index >= data->nr)
+		return false;
+	index = array_index_nospec(index, data->nr);
+	node = data->nodes[index];
+	if (!node)
+		return false;
+	io_put_rsrc_node(ctx, node);
+	data->nodes[index] = NULL;
+	return true;
+}
+
+int io_files_update(struct io_kiocb *req, unsigned int issue_flags);
+int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+int __io_account_mem(struct user_struct *user, unsigned long nr_pages);
+int io_account_mem(struct user_struct *user, struct mm_struct *mm_account,
+		   unsigned long nr_pages);
+void io_unaccount_mem(struct user_struct *user, struct mm_struct *mm_account,
+		      unsigned long nr_pages);
+
+static inline void __io_unaccount_mem(struct user_struct *user,
+				      unsigned long nr_pages)
+{
+	atomic_long_sub(nr_pages, &user->locked_vm);
+}
+
+void io_vec_free(struct iou_vec *iv);
+int io_vec_realloc(struct iou_vec *iv, unsigned nr_entries);
+
+static inline void io_vec_reset_iovec(struct iou_vec *iv,
+				      struct iovec *iovec, unsigned nr)
+{
+	io_vec_free(iv);
+	iv->iovec = iovec;
+	iv->nr = nr;
+}
+
+static inline void io_alloc_cache_vec_kasan(struct iou_vec *iv)
+{
+	if (IS_ENABLED(CONFIG_KASAN))
+		io_vec_free(iv);
+}
+
+#endif