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, 286 insertions, 0 deletions

diff --git a/drivers/md/dm-ps-queue-length.c b/drivers/md/dm-ps-queue-length.c
new file mode 100644
index 000000000..4afea160a
--- /dev/null
+++ b/drivers/md/dm-ps-queue-length.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2004-2005 IBM Corp.  All Rights Reserved.
+ * Copyright (C) 2006-2009 NEC Corporation.
+ *
+ * dm-queue-length.c
+ *
+ * Module Author: Stefan Bader, IBM
+ * Modified by: Kiyoshi Ueda, NEC
+ *
+ * This file is released under the GPL.
+ *
+ * queue-length path selector - choose a path with the least number of
+ * in-flight I/Os.
+ */
+
+#include "dm.h"
+#include "dm-path-selector.h"
+
+#include <linux/slab.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/atomic.h>
+
+#define DM_MSG_PREFIX	"multipath queue-length"
+#define QL_MIN_IO	1
+#define QL_VERSION	"0.2.0"
+
+struct selector {
+	struct list_head	valid_paths;
+	struct list_head	failed_paths;
+	spinlock_t lock;
+};
+
+struct path_info {
+	struct list_head	list;
+	struct dm_path		*path;
+	unsigned int		repeat_count;
+	atomic_t		qlen;	/* the number of in-flight I/Os */
+};
+
+static struct selector *alloc_selector(void)
+{
+	struct selector *s = kmalloc_obj(*s);
+
+	if (s) {
+		INIT_LIST_HEAD(&s->valid_paths);
+		INIT_LIST_HEAD(&s->failed_paths);
+		spin_lock_init(&s->lock);
+	}
+
+	return s;
+}
+
+static int ql_create(struct path_selector *ps, unsigned int argc, char **argv)
+{
+	struct selector *s = alloc_selector();
+
+	if (!s)
+		return -ENOMEM;
+
+	ps->context = s;
+	return 0;
+}
+
+static void ql_free_paths(struct list_head *paths)
+{
+	struct path_info *pi, *next;
+
+	list_for_each_entry_safe(pi, next, paths, list) {
+		list_del(&pi->list);
+		kfree(pi);
+	}
+}
+
+static void ql_destroy(struct path_selector *ps)
+{
+	struct selector *s = ps->context;
+
+	ql_free_paths(&s->valid_paths);
+	ql_free_paths(&s->failed_paths);
+	kfree(s);
+	ps->context = NULL;
+}
+
+static int ql_status(struct path_selector *ps, struct dm_path *path,
+		     status_type_t type, char *result, unsigned int maxlen)
+{
+	unsigned int sz = 0;
+	struct path_info *pi;
+
+	/* When called with NULL path, return selector status/args. */
+	if (!path)
+		DMEMIT("0 ");
+	else {
+		pi = path->pscontext;
+
+		switch (type) {
+		case STATUSTYPE_INFO:
+			DMEMIT("%d ", atomic_read(&pi->qlen));
+			break;
+		case STATUSTYPE_TABLE:
+			DMEMIT("%u ", pi->repeat_count);
+			break;
+		case STATUSTYPE_IMA:
+			*result = '\0';
+			break;
+		}
+	}
+
+	return sz;
+}
+
+static int ql_add_path(struct path_selector *ps, struct dm_path *path,
+		       int argc, char **argv, char **error)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi;
+	unsigned int repeat_count = QL_MIN_IO;
+	char dummy;
+	unsigned long flags;
+
+	/*
+	 * Arguments: [<repeat_count>]
+	 *	<repeat_count>: The number of I/Os before switching path.
+	 *			If not given, default (QL_MIN_IO) is used.
+	 */
+	if (argc > 1) {
+		*error = "queue-length ps: incorrect number of arguments";
+		return -EINVAL;
+	}
+
+	if ((argc == 1) && (sscanf(argv[0], "%u%c", &repeat_count, &dummy) != 1)) {
+		*error = "queue-length ps: invalid repeat count";
+		return -EINVAL;
+	}
+
+	if (repeat_count > 1) {
+		DMWARN_LIMIT("repeat_count > 1 is deprecated, using 1 instead");
+		repeat_count = 1;
+	}
+
+	/* Allocate the path information structure */
+	pi = kmalloc_obj(*pi);
+	if (!pi) {
+		*error = "queue-length ps: Error allocating path information";
+		return -ENOMEM;
+	}
+
+	pi->path = path;
+	pi->repeat_count = repeat_count;
+	atomic_set(&pi->qlen, 0);
+
+	path->pscontext = pi;
+
+	spin_lock_irqsave(&s->lock, flags);
+	list_add_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
+
+	return 0;
+}
+
+static void ql_fail_path(struct path_selector *ps, struct dm_path *path)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi = path->pscontext;
+	unsigned long flags;
+
+	spin_lock_irqsave(&s->lock, flags);
+	list_move(&pi->list, &s->failed_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
+}
+
+static int ql_reinstate_path(struct path_selector *ps, struct dm_path *path)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi = path->pscontext;
+	unsigned long flags;
+
+	spin_lock_irqsave(&s->lock, flags);
+	list_move_tail(&pi->list, &s->valid_paths);
+	spin_unlock_irqrestore(&s->lock, flags);
+
+	return 0;
+}
+
+/*
+ * Select a path having the minimum number of in-flight I/Os
+ */
+static struct dm_path *ql_select_path(struct path_selector *ps, size_t nr_bytes)
+{
+	struct selector *s = ps->context;
+	struct path_info *pi = NULL, *best = NULL;
+	struct dm_path *ret = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&s->lock, flags);
+	if (list_empty(&s->valid_paths))
+		goto out;
+
+	list_for_each_entry(pi, &s->valid_paths, list) {
+		if (!best ||
+		    (atomic_read(&pi->qlen) < atomic_read(&best->qlen)))
+			best = pi;
+
+		if (!atomic_read(&best->qlen))
+			break;
+	}
+
+	if (!best)
+		goto out;
+
+	/* Move most recently used to least preferred to evenly balance. */
+	list_move_tail(&best->list, &s->valid_paths);
+
+	ret = best->path;
+out:
+	spin_unlock_irqrestore(&s->lock, flags);
+	return ret;
+}
+
+static int ql_start_io(struct path_selector *ps, struct dm_path *path,
+		       size_t nr_bytes)
+{
+	struct path_info *pi = path->pscontext;
+
+	atomic_inc(&pi->qlen);
+
+	return 0;
+}
+
+static int ql_end_io(struct path_selector *ps, struct dm_path *path,
+		     size_t nr_bytes, u64 start_time)
+{
+	struct path_info *pi = path->pscontext;
+
+	atomic_dec(&pi->qlen);
+
+	return 0;
+}
+
+static struct path_selector_type ql_ps = {
+	.name		= "queue-length",
+	.module		= THIS_MODULE,
+	.table_args	= 1,
+	.info_args	= 1,
+	.create		= ql_create,
+	.destroy	= ql_destroy,
+	.status		= ql_status,
+	.add_path	= ql_add_path,
+	.fail_path	= ql_fail_path,
+	.reinstate_path	= ql_reinstate_path,
+	.select_path	= ql_select_path,
+	.start_io	= ql_start_io,
+	.end_io		= ql_end_io,
+};
+
+static int __init dm_ql_init(void)
+{
+	int r = dm_register_path_selector(&ql_ps);
+
+	if (r < 0) {
+		DMERR("register failed %d", r);
+		return r;
+	}
+
+	DMINFO("version " QL_VERSION " loaded");
+
+	return r;
+}
+
+static void __exit dm_ql_exit(void)
+{
+	dm_unregister_path_selector(&ql_ps);
+}
+
+module_init(dm_ql_init);
+module_exit(dm_ql_exit);
+
+MODULE_AUTHOR("Stefan Bader <Stefan.Bader at de.ibm.com>");
+MODULE_DESCRIPTION(
+	"(C) Copyright IBM Corp. 2004,2005   All Rights Reserved.\n"
+	DM_NAME " path selector to balance the number of in-flight I/Os"
+);
+MODULE_LICENSE("GPL");