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, 160 insertions, 0 deletions

diff --git a/fs/notify/group.c b/fs/notify/group.c
new file mode 100644
index 000000000..b56d1c1d9
--- /dev/null
+++ b/fs/notify/group.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/srcu.h>
+#include <linux/rculist.h>
+#include <linux/wait.h>
+#include <linux/memcontrol.h>
+
+#include <linux/fsnotify_backend.h>
+#include "fsnotify.h"
+
+#include <linux/atomic.h>
+
+/*
+ * Final freeing of a group
+ */
+static void fsnotify_final_destroy_group(struct fsnotify_group *group)
+{
+	if (group->ops->free_group_priv)
+		group->ops->free_group_priv(group);
+
+	mem_cgroup_put(group->memcg);
+	mutex_destroy(&group->mark_mutex);
+
+	kfree(group);
+}
+
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	spin_lock(&group->notification_lock);
+	group->shutdown = true;
+	spin_unlock(&group->notification_lock);
+}
+
+/*
+ * Trying to get rid of a group. Remove all marks, flush all events and release
+ * the group reference.
+ * Note that another thread calling fsnotify_clear_marks_by_group() may still
+ * hold a ref to the group.
+ */
+void fsnotify_destroy_group(struct fsnotify_group *group)
+{
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
+	/* Clear all marks for this group and queue them for destruction */
+	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY);
+
+	/*
+	 * Some marks can still be pinned when waiting for response from
+	 * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+	 * not succeed now so this wait is race-free.
+	 */
+	wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
+
+	/*
+	 * Wait until all marks get really destroyed. We could actually destroy
+	 * them ourselves instead of waiting for worker to do it, however that
+	 * would be racy as worker can already be processing some marks before
+	 * we even entered fsnotify_destroy_group().
+	 */
+	fsnotify_wait_marks_destroyed();
+
+	/*
+	 * Since we have waited for fsnotify_mark_srcu in
+	 * fsnotify_mark_destroy_list() there can be no outstanding event
+	 * notification against this group. So clearing the notification queue
+	 * of all events is reliable now.
+	 */
+	fsnotify_flush_notify(group);
+
+	/*
+	 * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+	 * that deliberately ignores overflow events.
+	 */
+	if (group->overflow_event)
+		group->ops->free_event(group, group->overflow_event);
+
+	fsnotify_put_group(group);
+}
+
+/*
+ * Get reference to a group.
+ */
+void fsnotify_get_group(struct fsnotify_group *group)
+{
+	refcount_inc(&group->refcnt);
+}
+
+/*
+ * Drop a reference to a group.  Free it if it's through.
+ */
+void fsnotify_put_group(struct fsnotify_group *group)
+{
+	if (refcount_dec_and_test(&group->refcnt))
+		fsnotify_final_destroy_group(group);
+}
+EXPORT_SYMBOL_GPL(fsnotify_put_group);
+
+static struct fsnotify_group *__fsnotify_alloc_group(
+				const struct fsnotify_ops *ops,
+				int flags, gfp_t gfp)
+{
+	struct fsnotify_group *group;
+
+	group = kzalloc_obj(struct fsnotify_group, gfp);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	/* set to 0 when there a no external references to this group */
+	refcount_set(&group->refcnt, 1);
+	atomic_set(&group->user_waits, 0);
+
+	spin_lock_init(&group->notification_lock);
+	INIT_LIST_HEAD(&group->notification_list);
+	init_waitqueue_head(&group->notification_waitq);
+	group->max_events = UINT_MAX;
+
+	mutex_init(&group->mark_mutex);
+	INIT_LIST_HEAD(&group->marks_list);
+
+	group->ops = ops;
+	group->flags = flags;
+
+	return group;
+}
+
+/*
+ * Create a new fsnotify_group and hold a reference for the group returned.
+ */
+struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops,
+					    int flags)
+{
+	gfp_t gfp = (flags & FSNOTIFY_GROUP_USER) ? GFP_KERNEL_ACCOUNT :
+						    GFP_KERNEL;
+
+	return __fsnotify_alloc_group(ops, flags, gfp);
+}
+EXPORT_SYMBOL_GPL(fsnotify_alloc_group);
+
+int fsnotify_fasync(int fd, struct file *file, int on)
+{
+	struct fsnotify_group *group = file->private_data;
+
+	return fasync_helper(fd, file, on, &group->fsn_fa) >= 0 ? 0 : -EIO;
+}