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, 77 insertions, 0 deletions

diff --git a/drivers/scsi/sr.h b/drivers/scsi/sr.h
new file mode 100644
index 000000000..2d92f9cb6
--- /dev/null
+++ b/drivers/scsi/sr.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *      sr.h by David Giller
+ *      CD-ROM disk driver header file
+ *      
+ *      adapted from:
+ *      sd.h Copyright (C) 1992 Drew Eckhardt 
+ *      SCSI disk driver header file by
+ *              Drew Eckhardt 
+ *
+ *      <drew@colorado.edu>
+ *
+ *       Modified by Eric Youngdale eric@andante.org to
+ *       add scatter-gather, multiple outstanding request, and other
+ *       enhancements.
+ */
+
+#ifndef _SR_H
+#define _SR_H
+
+#include <linux/mutex.h>
+
+#define MAX_RETRIES	3
+#define SR_TIMEOUT	(30 * HZ)
+
+struct scsi_device;
+
+/* The CDROM is fairly slow, so we need a little extra time */
+/* In fact, it is very slow if it has to spin up first */
+#define IOCTL_TIMEOUT 30*HZ
+
+
+typedef struct scsi_cd {
+	unsigned capacity;	/* size in blocks                       */
+	struct scsi_device *device;
+	unsigned int vendor;	/* vendor code, see sr_vendor.c         */
+	unsigned long ms_offset;	/* for reading multisession-CD's        */
+	unsigned use:1;		/* is this device still supportable     */
+	unsigned xa_flag:1;	/* CD has XA sectors ? */
+	unsigned readcd_known:1;	/* drive supports READ_CD (0xbe) */
+	unsigned readcd_cdda:1;	/* reading audio data using READ_CD */
+	unsigned media_present:1;	/* media is present */
+
+	/* GET_EVENT spurious event handling, blk layer guarantees exclusion */
+	int tur_mismatch;		/* nr of get_event TUR mismatches */
+	bool tur_changed:1;		/* changed according to TUR */
+	bool get_event_changed:1;	/* changed according to GET_EVENT */
+	bool ignore_get_event:1;	/* GET_EVENT is unreliable, use TUR */
+
+	struct cdrom_device_info cdi;
+	struct mutex lock;
+	struct gendisk *disk;
+} Scsi_CD;
+
+#define sr_printk(prefix, cd, fmt, a...) \
+	sdev_prefix_printk(prefix, (cd)->device, (cd)->cdi.name, fmt, ##a)
+
+int sr_do_ioctl(Scsi_CD *, struct packet_command *);
+
+int sr_lock_door(struct cdrom_device_info *, int);
+int sr_tray_move(struct cdrom_device_info *, int);
+int sr_drive_status(struct cdrom_device_info *, int);
+int sr_disk_status(struct cdrom_device_info *);
+int sr_get_last_session(struct cdrom_device_info *, struct cdrom_multisession *);
+int sr_get_mcn(struct cdrom_device_info *, struct cdrom_mcn *);
+int sr_reset(struct cdrom_device_info *);
+int sr_select_speed(struct cdrom_device_info *cdi, unsigned long speed);
+int sr_audio_ioctl(struct cdrom_device_info *, unsigned int, void *);
+
+int sr_is_xa(Scsi_CD *);
+
+/* sr_vendor.c */
+void sr_vendor_init(Scsi_CD *);
+int sr_cd_check(struct cdrom_device_info *);
+int sr_set_blocklength(Scsi_CD *, int blocklength);
+
+#endif