When waiting for response to fanotify permission events, we currently
use uninterruptible waits. That makes code simple however it can cause
lots of processes to end up in uninterruptible sleep with hard reboot
being the only alternative in case fanotify listener process stops
responding (e.g. due to a bug in its implementation). Uninterruptible
sleep also makes system hibernation fail if the listener gets frozen
before the process generating fanotify permission event.
Fix these problems by using interruptible sleep for waiting for response
to fanotify event. This is slightly tricky though - we have to
detect when the event got already reported to userspace as in that
case we must not free the event. Instead we push the responsibility for
freeing the event to the process that will write response to the
event.
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
fs/notify/fanotify/fanotify.c | 36 ++++++++++++++++++++++++++----
fs/notify/fanotify/fanotify.h | 1 +
fs/notify/fanotify/fanotify_user.c | 45 ++++++++++++++++++++++++--------------
fs/notify/notification.c | 20 +++++++++++------
include/linux/fsnotify_backend.h | 3 +++
5 files changed, 78 insertions(+), 27 deletions(-)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index cca13adc3a4c..cb7f7c5484fc 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -57,6 +57,13 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
return 0;
}
+/*
+ * Wait for response to permission event. The function also takes care of
+ * freeing the permission event (or offloads that in case the wait is canceled
+ * by a signal). The function returns 0 in case access got allowed by userspace,
+ * -EPERM in case userspace disallowed the access, and -ERESTARTSYS in case
+ * the wait got interrupted by a signal.
+ */
static int fanotify_get_response(struct fsnotify_group *group,
struct fanotify_perm_event_info *event,
struct fsnotify_iter_info *iter_info)
@@ -67,9 +74,31 @@ static int fanotify_get_response(struct fsnotify_group *group,
BUILD_BUG_ON(FAN_EVENT_STATE_MASK & (FAN_AUDIT | FAN_ALLOW | FAN_DENY));
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- wait_event(group->fanotify_data.access_waitq,
+ ret = wait_event_interruptible(group->fanotify_data.access_waitq,
(event->response & FAN_EVENT_STATE_MASK) ==
FAN_EVENT_ANSWERED);
+ /* Signal pending? */
+ if (ret < 0) {
+ spin_lock(&group->notification_lock);
+ /* Event reported to userspace and no answer yet? */
+ if ((event->response & FAN_EVENT_STATE_MASK) ==
+ FAN_EVENT_REPORTED) {
+ /* Event will get freed once userspace answers to it */
+ event->response = FAN_EVENT_CANCELED;
+ spin_unlock(&group->notification_lock);
+ return ret;
+ }
+ /* Event not yet reported? Just remove it. */
+ if ((event->response & FAN_EVENT_STATE_MASK) == 0)
+ fsnotify_remove_queued_event(group, &event->fae.fse);
+ /*
+ * Event may be also answered in case signal delivery raced
+ * with wakeup. In that case we have nothing to do besides
+ * freeing the event and reporting error.
+ */
+ spin_unlock(&group->notification_lock);
+ goto out;
+ }
response = event->response & ~FAN_EVENT_STATE_MASK;
@@ -87,8 +116,8 @@ static int fanotify_get_response(struct fsnotify_group *group,
if (response & FAN_AUDIT)
audit_fanotify(response & ~FAN_AUDIT);
- pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
- group, event, ret);
+out:
+ fsnotify_destroy_event(group, &event->fae.fse);
return ret;
}
@@ -259,7 +288,6 @@ static int fanotify_handle_event(struct fsnotify_group *group,
} else if (fanotify_is_perm_event(mask)) {
ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
iter_info);
- fsnotify_destroy_event(group, fsn_event);
}
finish:
if (fanotify_is_perm_event(mask))
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 954d997745c3..57286518f420 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -27,6 +27,7 @@ struct fanotify_event_info {
#define FAN_EVENT_REPORTED 0x40000000 /* Event reported to userspace */
#define FAN_EVENT_ANSWERED 0x80000000 /* Event answered by userspace */
+#define FAN_EVENT_CANCELED 0xc0000000 /* Event got canceled by a signal */
/*
* Structure for permission fanotify events. It gets allocated and freed in
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 611c2ff50d64..d6ae9e9338e6 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -146,6 +146,21 @@ static int fill_event_metadata(struct fsnotify_group *group,
return ret;
}
+static void set_event_response(struct fsnotify_group *group,
+ struct fanotify_perm_event_info *event,
+ unsigned int response)
+{
+ spin_lock(&group->notification_lock);
+ /* Waiter got aborted by a signal? Free the event. */
+ if (unlikely(event->response == FAN_EVENT_CANCELED)) {
+ spin_unlock(&group->notification_lock);
+ fsnotify_destroy_event(group, &event->fae.fse);
+ return;
+ }
+ event->response = response | FAN_EVENT_ANSWERED;
+ spin_unlock(&group->notification_lock);
+}
+
static int process_access_response(struct fsnotify_group *group,
struct fanotify_response *response_struct)
{
@@ -181,8 +196,8 @@ static int process_access_response(struct fsnotify_group *group,
continue;
list_del_init(&event->fae.fse.list);
- event->response = response | FAN_EVENT_ANSWERED;
spin_unlock(&group->notification_lock);
+ set_event_response(group, event, response);
wake_up(&group->fanotify_data.access_waitq);
return 0;
}
@@ -304,10 +319,8 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
fsnotify_destroy_event(group, kevent);
} else {
if (ret <= 0) {
- spin_lock(&group->notification_lock);
- FANOTIFY_PE(kevent)->response =
- FAN_DENY | FAN_EVENT_ANSWERED;
- spin_unlock(&group->notification_lock);
+ set_event_response(group, FANOTIFY_PE(kevent),
+ FAN_DENY);
wake_up(&group->fanotify_data.access_waitq);
} else {
spin_lock(&group->notification_lock);
@@ -357,7 +370,7 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t
static int fanotify_release(struct inode *ignored, struct file *file)
{
struct fsnotify_group *group = file->private_data;
- struct fanotify_perm_event_info *event, *next;
+ struct fanotify_perm_event_info *event;
struct fsnotify_event *fsn_event;
/*
@@ -372,13 +385,13 @@ static int fanotify_release(struct inode *ignored, struct file *file)
* and simulate reply from userspace.
*/
spin_lock(&group->notification_lock);
- list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
- fae.fse.list) {
- pr_debug("%s: found group=%p event=%p\n", __func__, group,
- event);
-
+ while (!list_empty(&group->fanotify_data.access_list)) {
+ event = list_first_entry(&group->fanotify_data.access_list,
+ struct fanotify_perm_event_info, fae.fse.list);
list_del_init(&event->fae.fse.list);
- event->response = FAN_ALLOW | FAN_EVENT_ANSWERED;
+ spin_unlock(&group->notification_lock);
+ set_event_response(group, event, FAN_ALLOW);
+ spin_lock(&group->notification_lock);
}
/*
@@ -388,14 +401,14 @@ static int fanotify_release(struct inode *ignored, struct file *file)
*/
while (!fsnotify_notify_queue_is_empty(group)) {
fsn_event = fsnotify_remove_first_event(group);
+ spin_unlock(&group->notification_lock);
if (!(fsn_event->mask & FANOTIFY_PERM_EVENTS)) {
- spin_unlock(&group->notification_lock);
fsnotify_destroy_event(group, fsn_event);
- spin_lock(&group->notification_lock);
} else {
- FANOTIFY_PE(fsn_event)->response =
- FAN_ALLOW | FAN_EVENT_ANSWERED;
+ set_event_response(group, FANOTIFY_PE(fsn_event),
+ FAN_ALLOW);
}
+ spin_lock(&group->notification_lock);
}
spin_unlock(&group->notification_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 3c3e36745f59..2195a5cf745a 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -141,6 +141,18 @@ int fsnotify_add_event(struct fsnotify_group *group,
return ret;
}
+void fsnotify_remove_queued_event(struct fsnotify_group *group,
+ struct fsnotify_event *event)
+{
+ assert_spin_locked(&group->notification_lock);
+ /*
+ * We need to init list head for the case of overflow event so that
+ * check in fsnotify_add_event() works
+ */
+ list_del_init(&event->list);
+ group->q_len--;
+}
+
/*
* Remove and return the first event from the notification list. It is the
* responsibility of the caller to destroy the obtained event
@@ -155,13 +167,7 @@ struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
event = list_first_entry(&group->notification_list,
struct fsnotify_event, list);
- /*
- * We need to init list head for the case of overflow event so that
- * check in fsnotify_add_event() works
- */
- list_del_init(&event->list);
- group->q_len--;
-
+ fsnotify_remove_queued_event(group, event);
return event;
}
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 7639774e7475..cddf839bac96 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -416,6 +416,9 @@ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group);
/* return AND dequeue the first event on the notification queue */
extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group);
+/* Remove event queued in the notification list */
+extern void fsnotify_remove_queued_event(struct fsnotify_group *group,
+ struct fsnotify_event *event);
/* functions used to manipulate the marks attached to inodes */
--
2.16.4
