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, 75 insertions, 0 deletions

diff --git a/drivers/block/rnbd/rnbd-srv.h b/drivers/block/rnbd/rnbd-srv.h
new file mode 100644
index 000000000..18d873808
--- /dev/null
+++ b/drivers/block/rnbd/rnbd-srv.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * RDMA Network Block Driver
+ *
+ * Copyright (c) 2014 - 2018 ProfitBricks GmbH. All rights reserved.
+ * Copyright (c) 2018 - 2019 1&1 IONOS Cloud GmbH. All rights reserved.
+ * Copyright (c) 2019 - 2020 1&1 IONOS SE. All rights reserved.
+ */
+#ifndef RNBD_SRV_H
+#define RNBD_SRV_H
+
+#include <linux/types.h>
+#include <linux/idr.h>
+#include <linux/kref.h>
+
+#include <rtrs.h>
+#include "rnbd-proto.h"
+#include "rnbd-log.h"
+
+struct rnbd_srv_session {
+	/* Entry inside global sess_list */
+	struct list_head        list;
+	struct rtrs_srv_sess	*rtrs;
+	char			sessname[NAME_MAX];
+	int			queue_depth;
+
+	struct xarray		index_idr;
+	struct mutex		lock;
+	u8			ver;
+};
+
+struct rnbd_srv_dev {
+	/* Entry inside global dev_list */
+	struct list_head                list;
+	struct kobject                  dev_kobj;
+	struct kobject                  *dev_sessions_kobj;
+	struct kref                     kref;
+	char				name[NAME_MAX];
+	/* List of rnbd_srv_sess_dev structs */
+	struct list_head		sess_dev_list;
+	struct mutex			lock;
+	int				open_write_cnt;
+};
+
+/* Structure which binds N devices and N sessions */
+struct rnbd_srv_sess_dev {
+	/* Entry inside rnbd_srv_dev struct */
+	struct list_head		dev_list;
+	struct file			*bdev_file;
+	struct rnbd_srv_session		*sess;
+	struct rnbd_srv_dev		*dev;
+	struct kobject                  kobj;
+	u32                             device_id;
+	bool				keep_id;
+	bool				readonly;
+	struct kref			kref;
+	struct completion               *destroy_comp;
+	char				pathname[NAME_MAX];
+	enum rnbd_access_mode		access_mode;
+};
+
+void rnbd_srv_sess_dev_force_close(struct rnbd_srv_sess_dev *sess_dev,
+				   struct kobj_attribute *attr);
+/* rnbd-srv-sysfs.c */
+
+int rnbd_srv_create_dev_sysfs(struct rnbd_srv_dev *dev,
+			      struct block_device *bdev);
+void rnbd_srv_destroy_dev_sysfs(struct rnbd_srv_dev *dev);
+int rnbd_srv_create_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);
+void rnbd_srv_destroy_dev_session_sysfs(struct rnbd_srv_sess_dev *sess_dev);
+int rnbd_srv_create_sysfs_files(void);
+void rnbd_srv_destroy_sysfs_files(void);
+void rnbd_destroy_sess_dev(struct rnbd_srv_sess_dev *sess_dev, bool keep_id);
+
+#endif /* RNBD_SRV_H */