diff options
| author | Eric Paris <eparis@redhat.com> | 2009-12-17 20:12:05 -0500 |
|---|---|---|
| committer | Eric Paris <eparis@redhat.com> | 2010-07-28 09:58:17 -0400 |
| commit | a05fb6cc573130915380e00d182a4c6571cec6b2 (patch) | |
| tree | c67e626c5307d89e6d7e65d0b2f9834c3591edb2 /kernel/auditfilter.c | |
| parent | e118e9c5638bbe877aa26b5cd2fd223cc24cdc8a (diff) | |
audit: do not get and put just to free a watch
deleting audit watch rules is not currently done under audit_filter_mutex.
It was done this way because we could not hold the mutex during inotify
manipulation. Since we are using fsnotify we don't need to do the extra
get/put pair nor do we need the private list on which to store the parents
while they are about to be freed.
Signed-off-by: Eric Paris <eparis@redhat.com>
Diffstat (limited to 'kernel/auditfilter.c')
| -rw-r--r-- | kernel/auditfilter.c | 6 |
1 files changed, 1 insertions, 5 deletions
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index ac87577f36b..eb7675499fb 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -945,7 +945,6 @@ static inline int audit_del_rule(struct audit_entry *entry) struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; - LIST_HEAD(inotify_unregister_list); int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; @@ -965,7 +964,7 @@ static inline int audit_del_rule(struct audit_entry *entry) } if (e->rule.watch) - audit_remove_watch_rule(&e->rule, &inotify_unregister_list); + audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); @@ -983,9 +982,6 @@ static inline int audit_del_rule(struct audit_entry *entry) #endif mutex_unlock(&audit_filter_mutex); - if (!list_empty(&inotify_unregister_list)) - audit_watch_inotify_unregister(&inotify_unregister_list); - out: if (watch) audit_put_watch(watch); /* match initial get */ |