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/include/sound/timer.h b/include/sound/timer.h
new file mode 100644
index 000000000..e549eab71
--- /dev/null
+++ b/include/sound/timer.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __SOUND_TIMER_H
+#define __SOUND_TIMER_H
+
+/*
+ *  Timer abstract layer
+ *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>,
+ *		     Abramo Bagnara <abramo@alsa-project.org>
+ */
+
+#include <sound/asound.h>
+#include <linux/interrupt.h>
+
+#define snd_timer_chip(timer) ((timer)->private_data)
+
+#define SNDRV_TIMER_DEVICES	16
+
+#define SNDRV_TIMER_DEV_FLG_PCM	0x10000000
+
+#define SNDRV_TIMER_HW_AUTO	0x00000001	/* auto trigger is supported */
+#define SNDRV_TIMER_HW_STOP	0x00000002	/* call stop before start */
+#define SNDRV_TIMER_HW_SLAVE	0x00000004	/* only slave timer (variable resolution) */
+#define SNDRV_TIMER_HW_FIRST	0x00000008	/* first tick can be incomplete */
+#define SNDRV_TIMER_HW_WORK	0x00000010	/* timer is called from work */
+
+#define SNDRV_TIMER_IFLG_SLAVE	  0x00000001
+#define SNDRV_TIMER_IFLG_RUNNING  0x00000002
+#define SNDRV_TIMER_IFLG_START	  0x00000004
+#define SNDRV_TIMER_IFLG_AUTO	  0x00000008	/* auto restart */
+#define SNDRV_TIMER_IFLG_FAST	  0x00000010	/* fast callback (do not use work) */
+#define SNDRV_TIMER_IFLG_CALLBACK 0x00000020	/* timer callback is active */
+#define SNDRV_TIMER_IFLG_EXCLUSIVE 0x00000040	/* exclusive owner - no more instances */
+#define SNDRV_TIMER_IFLG_EARLY_EVENT 0x00000080	/* write early event to the poll queue */
+
+#define SNDRV_TIMER_FLG_CHANGE	0x00000001
+#define SNDRV_TIMER_FLG_RESCHED	0x00000002	/* need reschedule */
+
+struct snd_timer;
+
+struct snd_timer_hardware {
+	/* -- must be filled with low-level driver */
+	unsigned int flags;		/* various flags */
+	unsigned long resolution;	/* average timer resolution for one tick in nsec */
+	unsigned long resolution_min;	/* minimal resolution */
+	unsigned long resolution_max;	/* maximal resolution */
+	unsigned long ticks;		/* max timer ticks per interrupt */
+	/* -- low-level functions -- */
+	int (*open) (struct snd_timer * timer);
+	int (*close) (struct snd_timer * timer);
+	unsigned long (*c_resolution) (struct snd_timer * timer);
+	int (*start) (struct snd_timer * timer);
+	int (*stop) (struct snd_timer * timer);
+	int (*set_period) (struct snd_timer * timer, unsigned long period_num, unsigned long period_den);
+	int (*precise_resolution) (struct snd_timer * timer, unsigned long *num, unsigned long *den);
+};
+
+struct snd_timer {
+	int tmr_class;
+	struct snd_card *card;
+	struct module *module;
+	int tmr_device;
+	int tmr_subdevice;
+	char id[64];
+	char name[80];
+	unsigned int flags;
+	int running;			/* running instances */
+	unsigned long sticks;		/* schedule ticks */
+	void *private_data;
+	void (*private_free) (struct snd_timer *timer);
+	struct snd_timer_hardware hw;
+	spinlock_t lock;
+	struct list_head device_list;
+	struct list_head open_list_head;
+	struct list_head active_list_head;
+	struct list_head ack_list_head;
+	struct list_head sack_list_head; /* slow ack list head */
+	struct work_struct task_work;
+	struct kref kref;
+	int max_instances;	/* upper limit of timer instances */
+	int num_instances;	/* current number of timer instances */
+};
+
+struct snd_timer_instance {
+	struct snd_timer *timer;
+	char *owner;
+	unsigned int flags;
+	void *private_data;
+	void (*private_free) (struct snd_timer_instance *ti);
+	void (*callback) (struct snd_timer_instance *timeri,
+			  unsigned long ticks, unsigned long resolution);
+	void (*ccallback) (struct snd_timer_instance * timeri,
+			   int event,
+			   struct timespec64 * tstamp,
+			   unsigned long resolution);
+	void (*disconnect)(struct snd_timer_instance *timeri);
+	void *callback_data;
+	unsigned long ticks;		/* auto-load ticks when expired */
+	unsigned long cticks;		/* current ticks */
+	unsigned long pticks;		/* accumulated ticks for callback */
+	unsigned long resolution;	/* current resolution for work */
+	unsigned long lost;		/* lost ticks */
+	int slave_class;
+	unsigned int slave_id;
+	struct list_head open_list;
+	struct list_head active_list;
+	struct list_head master_list;
+	struct list_head ack_list;
+	struct list_head slave_list_head;
+	struct list_head slave_active_head;
+	struct snd_timer_instance *master;
+};
+
+/*
+ *  Registering
+ */
+
+int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid, struct snd_timer **rtimer);
+void snd_timer_notify(struct snd_timer *timer, int event, struct timespec64 *tstamp);
+int snd_timer_global_new(char *id, int device, struct snd_timer **rtimer);
+int snd_timer_global_free(struct snd_timer *timer);
+int snd_timer_global_register(struct snd_timer *timer);
+
+struct snd_timer_instance *snd_timer_instance_new(const char *owner);
+void snd_timer_instance_free(struct snd_timer_instance *timeri);
+int snd_timer_open(struct snd_timer_instance *timeri, struct snd_timer_id *tid, unsigned int slave_id);
+void snd_timer_close(struct snd_timer_instance *timeri);
+unsigned long snd_timer_resolution(struct snd_timer_instance *timeri);
+int snd_timer_start(struct snd_timer_instance *timeri, unsigned int ticks);
+int snd_timer_stop(struct snd_timer_instance *timeri);
+int snd_timer_continue(struct snd_timer_instance *timeri);
+int snd_timer_pause(struct snd_timer_instance *timeri);
+
+void snd_timer_interrupt(struct snd_timer *timer, unsigned long ticks_left);
+
+struct snd_timer *snd_timeri_timer_get(struct snd_timer_instance *timeri);
+void snd_timeri_timer_put(struct snd_timer *timer);
+
+DEFINE_FREE(snd_timeri_timer, struct snd_timer *, if (_T) snd_timeri_timer_put(_T))
+
+#endif /* __SOUND_TIMER_H */