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, 105 insertions, 0 deletions

diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h
new file mode 100644
index 000000000..d11270560
--- /dev/null
+++ b/drivers/usb/usbip/stub.h
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2003-2008 Takahiro Hirofuchi
+ */
+
+#ifndef __USBIP_STUB_H
+#define __USBIP_STUB_H
+
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+#include <linux/wait.h>
+
+#define STUB_BUSID_OTHER 0
+#define STUB_BUSID_REMOV 1
+#define STUB_BUSID_ADDED 2
+#define STUB_BUSID_ALLOC 3
+
+struct stub_device {
+	struct usb_device *udev;
+
+	struct usbip_device ud;
+	__u32 devid;
+
+	/*
+	 * stub_priv preserves private data of each urb.
+	 * It is allocated as stub_priv_cache and assigned to urb->context.
+	 *
+	 * stub_priv is always linked to any one of 3 lists;
+	 *	priv_init: linked to this until the comletion of a urb.
+	 *	priv_tx  : linked to this after the completion of a urb.
+	 *	priv_free: linked to this after the sending of the result.
+	 *
+	 * Any of these list operations should be locked by priv_lock.
+	 */
+	spinlock_t priv_lock;
+	struct list_head priv_init;
+	struct list_head priv_tx;
+	struct list_head priv_free;
+
+	/* see comments for unlinking in stub_rx.c */
+	struct list_head unlink_tx;
+	struct list_head unlink_free;
+
+	wait_queue_head_t tx_waitq;
+};
+
+/* private data into urb->priv */
+struct stub_priv {
+	unsigned long seqnum;
+	struct list_head list;
+	struct stub_device *sdev;
+	struct urb **urbs;
+	struct scatterlist *sgl;
+	int num_urbs;
+	int completed_urbs;
+	int urb_status;
+
+	int unlinking;
+};
+
+struct stub_unlink {
+	unsigned long seqnum;
+	struct list_head list;
+	__u32 status;
+};
+
+/* same as SYSFS_BUS_ID_SIZE */
+#define BUSID_SIZE 32
+
+struct bus_id_priv {
+	char name[BUSID_SIZE];
+	char status;
+	int interf_count;
+	struct stub_device *sdev;
+	struct usb_device *udev;
+	char shutdown_busid;
+	spinlock_t busid_lock;
+};
+
+/* stub_priv is allocated from stub_priv_cache */
+extern struct kmem_cache *stub_priv_cache;
+
+/* stub_dev.c */
+extern struct usb_device_driver stub_driver;
+
+/* stub_main.c */
+struct bus_id_priv *get_busid_priv(const char *busid);
+void put_busid_priv(struct bus_id_priv *bid);
+int del_match_busid(char *busid);
+void stub_free_priv_and_urb(struct stub_priv *priv);
+void stub_device_cleanup_urbs(struct stub_device *sdev);
+
+/* stub_rx.c */
+int stub_rx_loop(void *data);
+
+/* stub_tx.c */
+void stub_enqueue_ret_unlink(struct stub_device *sdev, __u32 seqnum,
+			     __u32 status);
+void stub_complete(struct urb *urb);
+int stub_tx_loop(void *data);
+
+#endif /* __USBIP_STUB_H */