5 files changed, 78 insertions, 31 deletions

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 700129940c6e..41e39102743a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
                                               &fsnotify_mark_srcu);
         }
 
+        /*
+         * We need to merge inode & vfsmount mark lists so that inode mark
+         * ignore masks are properly reflected for mount mark notifications.
+         * That's why this traversal is so complicated...
+         */
         while (inode_node || vfsmount_node) {
-                inode_group = vfsmount_group = NULL;
+                inode_group = NULL;
+                inode_mark = NULL;
+                vfsmount_group = NULL;
+                vfsmount_mark = NULL;
 
                 if (inode_node) {
                         inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
@@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
                         vfsmount_group = vfsmount_mark->group;
                 }
 
-                if (inode_group > vfsmount_group) {
-                        /* handle inode */
-                        ret = send_to_group(to_tell, inode_mark, NULL, mask,
-                                            data, data_is, cookie, file_name);
-                        /* we didn't use the vfsmount_mark */
-                        vfsmount_group = NULL;
-                } else if (vfsmount_group > inode_group) {
-                        ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
-                                            data, data_is, cookie, file_name);
-                        inode_group = NULL;
-                } else {
-                        ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
-                                            mask, data, data_is, cookie,
-                                            file_name);
+                if (inode_group && vfsmount_group) {
+                        int cmp = fsnotify_compare_groups(inode_group,
+                                                          vfsmount_group);
+                        if (cmp > 0) {
+                                inode_group = NULL;
+                                inode_mark = NULL;
+                        } else if (cmp < 0) {
+                                vfsmount_group = NULL;
+                                vfsmount_mark = NULL;
+                        }
                 }
+                ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
+                                    data, data_is, cookie, file_name);
 
                 if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
                         goto out;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 9c0898c4cfe1..3b68b0ae0a97 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+                                   struct fsnotify_group *b);
+
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
                                                 __u32 mask);
 /* add a mark to an inode */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 9ce062218de9..dfbf5447eea4 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 {
         struct fsnotify_mark *lmark, *last = NULL;
         int ret = 0;
+        int cmp;
 
         mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
@@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
                         goto out;
                 }
 
-                if (mark->group->priority < lmark->group->priority)
-                        continue;
-
-                if ((mark->group->priority == lmark->group->priority) &&
-                    (mark->group < lmark->group))
+                cmp = fsnotify_compare_groups(lmark->group, mark->group);
+                if (cmp < 0)
                         continue;
 
                 hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
@@ -288,20 +286,25 @@ void fsnotify_unmount_inodes(struct list_head *list)
                 spin_unlock(&inode->i_lock);
 
                 /* In case the dropping of a reference would nuke next_i. */
-                if ((&next_i->i_sb_list != list) &&
-                    atomic_read(&next_i->i_count)) {
+                while (&next_i->i_sb_list != list) {
                         spin_lock(&next_i->i_lock);
-                        if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+                        if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
+                                                atomic_read(&next_i->i_count)) {
                                 __iget(next_i);
                                 need_iput = next_i;
+                                spin_unlock(&next_i->i_lock);
+                                break;
                         }
                         spin_unlock(&next_i->i_lock);
+                        next_i = list_entry(next_i->i_sb_list.next,
+                                                struct inode, i_sb_list);
                 }
 
                 /*
-                 * We can safely drop inode_sb_list_lock here because we hold
-                 * references on both inode and next_i.  Also no new inodes
-                 * will be added since the umount has begun.
+                 * We can safely drop inode_sb_list_lock here because either
+                 * we actually hold references on both inode and next_i or
+                 * end of list.  Also no new inodes will be added since the
+                 * umount has begun.
                  */
                 spin_unlock(&inode_sb_list_lock);
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d90deaa08e78..34c38fabf514 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
 }
 
 /*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+        if (a == b)
+                return 0;
+        if (!a)
+                return 1;
+        if (!b)
+                return -1;
+        if (a->priority < b->priority)
+                return 1;
+        if (a->priority > b->priority)
+                return -1;
+        if (a < b)
+                return 1;
+        return -1;
+}
+
+/*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index ac851e8376b1..faefa72a11eb 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
         struct mount *m = real_mount(mnt);
         struct fsnotify_mark *lmark, *last = NULL;
         int ret = 0;
+        int cmp;
 
         mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
@@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
                         goto out;
                 }
 
-                if (mark->group->priority < lmark->group->priority)
-                        continue;
-
-                if ((mark->group->priority == lmark->group->priority) &&
-                    (mark->group < lmark->group))
+                cmp = fsnotify_compare_groups(lmark->group, mark->group);
+                if (cmp < 0)
                         continue;
 
                 hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);