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, 140 insertions, 0 deletions

diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
new file mode 100644
index 000000000..d4a54b4e1
--- /dev/null
+++ b/io_uring/zcrx.h
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZC_RX_H
+#define IOU_ZC_RX_H
+
+#include <linux/io_uring_types.h>
+#include <linux/dma-buf.h>
+#include <linux/socket.h>
+#include <net/page_pool/types.h>
+#include <net/net_trackers.h>
+
+#define ZCRX_SUPPORTED_REG_FLAGS	(ZCRX_REG_IMPORT | ZCRX_REG_NODEV)
+#define ZCRX_FEATURES			(ZCRX_FEATURE_RX_PAGE_SIZE |\
+					 ZCRX_FEATURE_EVENT)
+#define ZCRX_EVENT_TYPE_MASK		((1U << ZCRX_EVENT_ALLOC_FAIL) |\
+					 (1U << ZCRX_EVENT_COPY))
+
+struct io_zcrx_mem {
+	unsigned long			size;
+	bool				is_dmabuf;
+
+	struct page			**pages;
+	unsigned long			nr_folios;
+	struct sg_table			page_sg_table;
+	unsigned long			account_pages;
+	struct sg_table			*sgt;
+
+	struct dma_buf_attachment	*attach;
+	struct dma_buf			*dmabuf;
+};
+
+struct io_zcrx_area {
+	struct net_iov_area	nia;
+	struct io_zcrx_ifq	*ifq;
+	atomic_t		*user_refs;
+
+	bool			is_mapped;
+	u16			area_id;
+
+	/* freelist */
+	u32			free_count;
+	u32			*freelist;
+
+	struct io_zcrx_mem	mem;
+};
+
+struct zcrx_rq_hdr {
+	u32		head ____cacheline_aligned_in_smp;
+	u32		tail ____cacheline_aligned_in_smp;
+};
+
+struct zcrx_rq {
+	spinlock_t			lock;
+	struct zcrx_rq_hdr		*ring;
+	struct io_uring_zcrx_rqe	*rqes;
+	u32				cached_head;
+	u32				cached_tail;
+	u32				nr_entries;
+};
+
+struct io_zcrx_ifq {
+	/* read-protected by any of: ->pp_lock, ->alloc_lock, ->rq.lock */
+	struct io_zcrx_area		**areas;
+	unsigned			nr_areas;
+
+	unsigned			niov_shift;
+	struct user_struct		*user;
+	struct mm_struct		*mm_account;
+	bool				kern_readable;
+
+	struct zcrx_rq			rq ____cacheline_aligned_in_smp;
+	spinlock_t			alloc_lock ____cacheline_aligned_in_smp;
+
+	u32				if_rxq;
+	struct device			*dev;
+	struct net_device		*netdev;
+	netdevice_tracker		netdev_tracker;
+	refcount_t			refs;
+	/* counts userspace facing users like io_uring */
+	refcount_t			user_refs;
+
+	/*
+	 * Page pool and net configuration lock, can be taken deeper in the
+	 * net stack.
+	 */
+	struct mutex			pp_lock;
+	struct io_mapped_region		rq_region;
+
+	spinlock_t			ctx_lock;
+	struct io_ring_ctx		*master_ctx;
+	u32				allowed_notif_mask;
+	u32				fired_notifs;
+	u64				notif_data;
+	struct zcrx_stats		*notif_stats;
+};
+
+#if defined(CONFIG_IO_URING_ZCRX)
+int io_zcrx_ctrl(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_arg);
+int io_register_zcrx(struct io_ring_ctx *ctx,
+			 struct io_uring_zcrx_ifq_reg __user *arg);
+void io_unregister_zcrx(struct io_ring_ctx *ctx);
+void io_terminate_zcrx(struct io_ring_ctx *ctx);
+int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+		 struct socket *sock, unsigned int flags,
+		 unsigned issue_flags, unsigned int *len);
+struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
+					    unsigned int id);
+#else
+static inline int io_register_zcrx(struct io_ring_ctx *ctx,
+				   struct io_uring_zcrx_ifq_reg __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+static inline void io_unregister_zcrx(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_terminate_zcrx(struct io_ring_ctx *ctx)
+{
+}
+static inline int io_zcrx_recv(struct io_kiocb *req, struct io_zcrx_ifq *ifq,
+			       struct socket *sock, unsigned int flags,
+			       unsigned issue_flags, unsigned int *len)
+{
+	return -EOPNOTSUPP;
+}
+static inline struct io_mapped_region *io_zcrx_get_region(struct io_ring_ctx *ctx,
+							  unsigned int id)
+{
+	return NULL;
+}
+static inline int io_zcrx_ctrl(struct io_ring_ctx *ctx,
+				void __user *arg, unsigned nr_arg)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags);
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
+
+#endif