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, 177 insertions, 0 deletions

diff --git a/drivers/usb/usbip/vudc.h b/drivers/usb/usbip/vudc.h
new file mode 100644
index 000000000..5ef0e7d9b
--- /dev/null
+++ b/drivers/usb/usbip/vudc.h
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2015 Karol Kosik <karo9@interia.eu>
+ * Copyright (C) 2015-2016 Samsung Electronics
+ *               Igor Kotrasinski <i.kotrasinsk@samsung.com>
+ *               Krzysztof Opasiak <k.opasiak@samsung.com>
+ */
+
+#ifndef __USBIP_VUDC_H
+#define __USBIP_VUDC_H
+
+#include <linux/platform_device.h>
+#include <linux/usb.h>
+#include <linux/usb/gadget.h>
+#include <linux/usb/ch9.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/time.h>
+#include <linux/sysfs.h>
+
+#include "usbip_common.h"
+
+#define GADGET_NAME "usbip-vudc"
+
+struct vep {
+	struct usb_ep ep;
+	unsigned type:2; /* type, as USB_ENDPOINT_XFER_* */
+	char name[8];	/* space for ep name */
+
+	const struct usb_endpoint_descriptor *desc;
+	struct usb_gadget *gadget;
+	struct list_head req_queue; /* Request queue */
+	unsigned halted:1;
+	unsigned wedged:1;
+	unsigned already_seen:1;
+	unsigned setup_stage:1;
+};
+
+struct vrequest {
+	struct usb_request req;
+	struct list_head req_entry; /* Request queue */
+};
+
+struct urbp {
+	struct urb *urb;
+	struct vep *ep;
+	struct list_head urb_entry; /* urb queue */
+	unsigned long seqnum;
+	unsigned type:2; /* for tx, since ep type can change after */
+	unsigned new:1;
+};
+
+struct v_unlink {
+	unsigned long seqnum;
+	__u32 status;
+};
+
+enum tx_type {
+	TX_UNLINK,
+	TX_SUBMIT,
+};
+
+struct tx_item {
+	struct list_head tx_entry;
+	enum tx_type type;
+	union {
+		struct urbp *s;
+		struct v_unlink *u;
+	};
+};
+
+enum tr_state {
+	VUDC_TR_RUNNING,
+	VUDC_TR_IDLE,
+	VUDC_TR_STOPPED,
+};
+
+struct transfer_timer {
+	struct timer_list timer;
+	enum tr_state state;
+	unsigned long frame_start;
+	int frame_limit;
+};
+
+struct vudc {
+	struct usb_gadget gadget;
+	struct usb_gadget_driver *driver;
+	struct platform_device *pdev;
+
+	struct usb_device_descriptor dev_desc;
+
+	struct usbip_device ud;
+	struct transfer_timer tr_timer;
+	struct timespec64 start_time;
+
+	struct list_head urb_queue;
+
+	spinlock_t lock_tx;
+	struct list_head tx_queue;
+	wait_queue_head_t tx_waitq;
+
+	spinlock_t lock;
+	struct vep *ep;
+	int address;
+	u16 devstatus;
+
+	unsigned pullup:1;
+	unsigned connected:1;
+	unsigned desc_cached:1;
+};
+
+struct vudc_device {
+	struct platform_device *pdev;
+	struct list_head dev_entry;
+};
+
+extern const struct attribute_group *vudc_groups[];
+
+/* visible everywhere */
+
+static inline struct vep *to_vep(struct usb_ep *_ep)
+{
+	return container_of(_ep, struct vep, ep);
+}
+
+static inline struct vrequest *to_vrequest(
+	struct usb_request *_req)
+{
+	return container_of(_req, struct vrequest, req);
+}
+
+static inline struct vudc *usb_gadget_to_vudc(
+	struct usb_gadget *_gadget)
+{
+	return container_of(_gadget, struct vudc, gadget);
+}
+
+static inline struct vudc *ep_to_vudc(struct vep *ep)
+{
+	return container_of(ep->gadget, struct vudc, gadget);
+}
+
+/* vudc_sysfs.c */
+
+int get_gadget_descs(struct vudc *udc);
+
+/* vudc_tx.c */
+
+int v_tx_loop(void *data);
+void v_enqueue_ret_unlink(struct vudc *udc, __u32 seqnum, __u32 status);
+void v_enqueue_ret_submit(struct vudc *udc, struct urbp *urb_p);
+
+/* vudc_rx.c */
+
+int v_rx_loop(void *data);
+
+/* vudc_transfer.c */
+
+void v_init_timer(struct vudc *udc);
+void v_start_timer(struct vudc *udc);
+void v_kick_timer(struct vudc *udc, unsigned long time);
+void v_stop_timer(struct vudc *udc);
+
+/* vudc_dev.c */
+
+struct urbp *alloc_urbp(void);
+void free_urbp_and_urb(struct urbp *urb_p);
+
+struct vep *vudc_find_endpoint(struct vudc *udc, u8 address);
+
+struct vudc_device *alloc_vudc_device(int devid);
+void put_vudc_device(struct vudc_device *udc_dev);
+
+int vudc_probe(struct platform_device *pdev);
+void vudc_remove(struct platform_device *pdev);
+
+#endif /* __USBIP_VUDC_H */