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, 107 insertions, 0 deletions

diff --git a/drivers/md/dm-path-selector.h b/drivers/md/dm-path-selector.h
new file mode 100644
index 000000000..7b2270532
--- /dev/null
+++ b/drivers/md/dm-path-selector.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2003 Sistina Software.
+ * Copyright (C) 2004 Red Hat, Inc. All rights reserved.
+ *
+ * Module Author: Heinz Mauelshagen
+ *
+ * This file is released under the GPL.
+ *
+ * Path-Selector registration.
+ */
+
+#ifndef	DM_PATH_SELECTOR_H
+#define	DM_PATH_SELECTOR_H
+
+#include <linux/device-mapper.h>
+
+#include "dm-mpath.h"
+
+/*
+ * We provide an abstraction for the code that chooses which path
+ * to send some io down.
+ */
+struct path_selector_type;
+struct path_selector {
+	struct path_selector_type *type;
+	void *context;
+};
+
+/*
+ * If a path selector uses this flag, a high resolution timer is used
+ * (via ktime_get_ns) to account for IO start time in BIO-based mpath.
+ * This improves performance of some path selectors (i.e. HST), in
+ * exchange for slightly higher overhead when submitting the BIO.
+ * The extra cost is usually offset by improved path selection for
+ * some benchmarks.
+ *
+ * This has no effect for request-based mpath, since it already uses a
+ * higher precision timer by default.
+ */
+#define DM_PS_USE_HR_TIMER		0x00000001
+#define dm_ps_use_hr_timer(type)	((type)->features & DM_PS_USE_HR_TIMER)
+
+/* Information about a path selector type */
+struct path_selector_type {
+	char *name;
+	struct module *module;
+
+	unsigned int features;
+	unsigned int table_args;
+	unsigned int info_args;
+
+	/*
+	 * Constructs a path selector object, takes custom arguments
+	 */
+	int (*create)(struct path_selector *ps, unsigned int argc, char **argv);
+	void (*destroy)(struct path_selector *ps);
+
+	/*
+	 * Add an opaque path object, along with some selector specific
+	 * path args (eg, path priority).
+	 */
+	int (*add_path)(struct path_selector *ps, struct dm_path *path,
+			int argc, char **argv, char **error);
+
+	/*
+	 * Chooses a path for this io, if no paths are available then
+	 * NULL will be returned.
+	 */
+	struct dm_path *(*select_path)(struct path_selector *ps, size_t nr_bytes);
+
+	/*
+	 * Notify the selector that a path has failed.
+	 */
+	void (*fail_path)(struct path_selector *ps, struct dm_path *p);
+
+	/*
+	 * Ask selector to reinstate a path.
+	 */
+	int (*reinstate_path)(struct path_selector *ps, struct dm_path *p);
+
+	/*
+	 * Table content based on parameters added in ps_add_path_fn
+	 * or path selector status
+	 */
+	int (*status)(struct path_selector *ps, struct dm_path *path,
+		      status_type_t type, char *result, unsigned int maxlen);
+
+	int (*start_io)(struct path_selector *ps, struct dm_path *path,
+			size_t nr_bytes);
+	int (*end_io)(struct path_selector *ps, struct dm_path *path,
+		      size_t nr_bytes, u64 start_time);
+};
+
+/* Register a path selector */
+int dm_register_path_selector(struct path_selector_type *type);
+
+/* Unregister a path selector */
+void dm_unregister_path_selector(struct path_selector_type *type);
+
+/* Returns a registered path selector type */
+struct path_selector_type *dm_get_path_selector(const char *name);
+
+/* Releases a path selector  */
+void dm_put_path_selector(struct path_selector_type *pst);
+
+#endif