fsnotify: allow marks to not pin inodes in core

inotify marks must pin inodes in core.  dnotify doesn't technically need to
since they are closed when the directory is closed.  fanotify also need to
pin inodes in core as it works today.  But the next step is to introduce
the concept of 'ignored masks' which is actually a mask of events for an
inode of no interest.  I claim that these should be liberally sent to the
kernel and should not pin the inode in core.  If the inode is brought back
in the listener will get an event it may have thought excluded, but this is
not a serious situation and one any listener should deal with.

This patch lays the ground work for non-pinning inode marks by using lazy
inode pinning.  We do not pin a mark until it has a non-zero mask entry.  If a
listener new sets a mask we never pin the inode.

Signed-off-by: Eric Paris <eparis@redhat.com>

fs/notify/dnotify/dnotify.c

@@ -65,7 +65,7 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
 	new_mask = 0;
 	for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
 		new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
-	fsn_mark->mask = new_mask;
+	fsnotify_set_mark_mask_locked(fsn_mark, new_mask);
 
 	if (old_mask == new_mask)
 		return;

fs/notify/fanotify/fanotify_user.c

@@ -302,7 +302,7 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark, __u3
 
 	spin_lock(&fsn_mark->lock);
 	oldmask = fsn_mark->mask;
-	fsn_mark->mask = oldmask & ~mask;
+	fsnotify_set_mark_mask_locked(fsn_mark, (oldmask & ~mask));
 	spin_unlock(&fsn_mark->lock);
 
 	if (!(oldmask & ~mask))
@@ -359,7 +359,7 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, __u32 mas
 
 	spin_lock(&fsn_mark->lock);
 	oldmask = fsn_mark->mask;
-	fsn_mark->mask = oldmask | mask;
+	fsnotify_set_mark_mask_locked(fsn_mark, (oldmask | mask));
 	spin_unlock(&fsn_mark->lock);
 
 	return mask & ~oldmask;

fs/notify/fsnotify.h

@@ -20,6 +20,8 @@ extern __u32 fsnotify_vfsmount_mask;
 /* destroy all events sitting in this groups notification queue */
 extern void fsnotify_flush_notify(struct fsnotify_group *group);
 
+extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
+						__u32 mask);
 /* add a mark to an inode */
 extern int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 				   struct fsnotify_group *group, struct inode *inode,

fs/notify/inode_mark.c

@@ -141,7 +141,32 @@ struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
 }
 
 /*
- * Attach an initialized mark mark to a given group and inode.
+ * If we are setting a mark mask on an inode mark we should pin the inode
+ * in memory.
+ */
+void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
+					 __u32 mask)
+{
+	struct inode *inode;
+
+	assert_spin_locked(&mark->lock);
+
+	if (mask &&
+	    mark->i.inode &&
+	    !(mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED)) {
+		mark->flags |= FSNOTIFY_MARK_FLAG_OBJECT_PINNED;
+		inode = igrab(mark->i.inode);
+		/*
+		 * we shouldn't be able to get here if the inode wasn't
+		 * already safely held in memory.  But bug in case it
+		 * ever is wrong.
+		 */
+		BUG_ON(!inode);
+	}
+}
+
+/*
+ * Attach an initialized mark to a given group and inode.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group and for which inodes.
  */
@@ -152,10 +177,6 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 	struct fsnotify_mark *lmark = NULL;
 	int ret = 0;
 
-	inode = igrab(inode);
-	if (unlikely(!inode))
-		return -EINVAL;
-
 	mark->flags = FSNOTIFY_MARK_FLAG_INODE;
 
 	assert_spin_locked(&mark->lock);
@@ -175,10 +196,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 
 	spin_unlock(&inode->i_lock);
 
-	if (lmark) {
+	if (lmark)
 		ret = -EEXIST;
-		iput(inode);
-	}
 
 	return ret;
 }

fs/notify/inotify/inotify_user.c

@@ -575,13 +575,11 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 	spin_lock(&fsn_mark->lock);
 
 	old_mask = fsn_mark->mask;
-	if (add) {
-		fsn_mark->mask |= mask;
-		new_mask = fsn_mark->mask;
-	} else {
-		fsn_mark->mask = mask;
-		new_mask = fsn_mark->mask;
-	}
+	if (add)
+		fsnotify_set_mark_mask_locked(fsn_mark, (fsn_mark->mask | mask));
+	else
+		fsnotify_set_mark_mask_locked(fsn_mark, mask);
+	new_mask = fsn_mark->mask;
 
 	spin_unlock(&fsn_mark->lock);
 

fs/notify/mark.c

@@ -168,7 +168,7 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 	 * is just a lazy update (and could be a perf win...)
 	 */
 
-	if (inode)
+	if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
 		iput(inode);
 
 	/*
@@ -180,6 +180,17 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark)
 		fsnotify_final_destroy_group(group);
 }
 
+void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
+{
+	assert_spin_locked(&mark->lock);
+
+	mark->mask = mask;
+
+	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE)
+		fsnotify_set_inode_mark_mask_locked(mark, mask);
+}
+
+
 /*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
@@ -230,6 +241,10 @@ int fsnotify_add_mark(struct fsnotify_mark *mark,
 	}
 
 	spin_unlock(&group->mark_lock);
+
+	/* this will pin the object if appropriate */
+	fsnotify_set_mark_mask_locked(mark, mark->mask);
+
 	spin_unlock(&mark->lock);
 
 	if (inode)

include/linux/fsnotify_backend.h

@@ -267,8 +267,9 @@ struct fsnotify_mark {
 		struct fsnotify_vfsmount_mark m;
 	};
 	struct list_head free_g_list;	/* tmp list used when freeing this mark */
-#define FSNOTIFY_MARK_FLAG_INODE	0x01
-#define FSNOTIFY_MARK_FLAG_VFSMOUNT	0x02
+#define FSNOTIFY_MARK_FLAG_INODE		0x01
+#define FSNOTIFY_MARK_FLAG_VFSMOUNT		0x02
+#define FSNOTIFY_MARK_FLAG_OBJECT_PINNED	0x04
 	unsigned int flags;		/* vfsmount or inode mark? */
 	void (*free_mark)(struct fsnotify_mark *mark); /* called on final put+free */
 };
@@ -372,6 +373,8 @@ extern struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *gro
 extern struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group, struct vfsmount *mnt);
 /* copy the values from old into new */
 extern void fsnotify_duplicate_mark(struct fsnotify_mark *new, struct fsnotify_mark *old);
+/* set the mask of a mark (might pin the object into memory */
+extern void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask);
 /* attach the mark to both the group and the inode */
 extern int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
 			     struct inode *inode, struct vfsmount *mnt, int allow_dups);