Merge branch 'fsnotify' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "The branch contains mainly a rework of fsnotify infrastructure fixing
  a shortcoming that we have waited for response to fanotify permission
  events with SRCU read lock held and when the process consuming events
  was slow to respond the kernel has stalled.

  It also contains several cleanups of unnecessary indirections in
  fsnotify framework and a bugfix from Amir fixing leakage of kernel
  internal errno to userspace"

* 'fsnotify' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (37 commits)
  fanotify: don't expose EOPENSTALE to userspace
  fsnotify: remove a stray unlock
  fsnotify: Move ->free_mark callback to fsnotify_ops
  fsnotify: Add group pointer in fsnotify_init_mark()
  fsnotify: Drop inode_mark.c
  fsnotify: Remove fsnotify_find_{inode|vfsmount}_mark()
  fsnotify: Remove fsnotify_detach_group_marks()
  fsnotify: Rename fsnotify_clear_marks_by_group_flags()
  fsnotify: Inline fsnotify_clear_{inode|vfsmount}_mark_group()
  fsnotify: Remove fsnotify_recalc_{inode|vfsmount}_mask()
  fsnotify: Remove fsnotify_set_mark_{,ignored_}mask_locked()
  fanotify: Release SRCU lock when waiting for userspace response
  fsnotify: Pass fsnotify_iter_info into handle_event handler
  fsnotify: Provide framework for dropping SRCU lock in ->handle_event
  fsnotify: Remove special handling of mark destruction on group shutdown
  fsnotify: Detach mark from object list when last reference is dropped
  fsnotify: Move queueing of mark for destruction into fsnotify_put_mark()
  inotify: Do not drop mark reference under idr_lock
  fsnotify: Free fsnotify_mark_connector when there is no mark attached
  fsnotify: Lock object list with connector lock
  ...

4 files changed, 71 insertions, 32 deletions

diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c
index b16a5bdcea0d..52f368b6561e 100644
--- a/kernel/audit_fsnotify.c
+++ b/kernel/audit_fsnotify.c
@@ -103,15 +103,15 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa
 		goto out;
 	}
 
-	fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_free_mark);
+	fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_group);
 	audit_mark->mark.mask = AUDIT_FS_EVENTS;
 	audit_mark->path = pathname;
 	audit_update_mark(audit_mark, dentry->d_inode);
 	audit_mark->rule = krule;
 
-	ret = fsnotify_add_mark(&audit_mark->mark, audit_fsnotify_group, inode, NULL, true);
+	ret = fsnotify_add_mark(&audit_mark->mark, inode, NULL, true);
 	if (ret < 0) {
-		audit_fsnotify_mark_free(audit_mark);
+		fsnotify_put_mark(&audit_mark->mark);
 		audit_mark = ERR_PTR(ret);
 	}
 out:
@@ -168,7 +168,8 @@ static int audit_mark_handle_event(struct fsnotify_group *group,
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, const void *data, int data_type,
-				    const unsigned char *dname, u32 cookie)
+				    const unsigned char *dname, u32 cookie,
+				    struct fsnotify_iter_info *iter_info)
 {
 	struct audit_fsnotify_mark *audit_mark;
 	const struct inode *inode = NULL;
@@ -201,6 +202,7 @@ static int audit_mark_handle_event(struct fsnotify_group *group,
 
 static const struct fsnotify_ops audit_mark_fsnotify_ops = {
 	.handle_event =	audit_mark_handle_event,
+	.free_mark = audit_fsnotify_free_mark,
 };
 
 static int __init audit_fsnotify_init(void)
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 5cfd1ea18de0..011d46e5f73f 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -155,7 +155,7 @@ static struct audit_chunk *alloc_chunk(int count)
 		INIT_LIST_HEAD(&chunk->owners[i].list);
 		chunk->owners[i].index = i;
 	}
-	fsnotify_init_mark(&chunk->mark, audit_tree_destroy_watch);
+	fsnotify_init_mark(&chunk->mark, audit_tree_group);
 	chunk->mark.mask = FS_IN_IGNORED;
 	return chunk;
 }
@@ -164,33 +164,54 @@ enum {HASH_SIZE = 128};
 static struct list_head chunk_hash_heads[HASH_SIZE];
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(hash_lock);
 
-static inline struct list_head *chunk_hash(const struct inode *inode)
+/* Function to return search key in our hash from inode. */
+static unsigned long inode_to_key(const struct inode *inode)
 {
-	unsigned long n = (unsigned long)inode / L1_CACHE_BYTES;
+	return (unsigned long)inode;
+}
+
+/*
+ * Function to return search key in our hash from chunk. Key 0 is special and
+ * should never be present in the hash.
+ */
+static unsigned long chunk_to_key(struct audit_chunk *chunk)
+{
+	/*
+	 * We have a reference to the mark so it should be attached to a
+	 * connector.
+	 */
+	if (WARN_ON_ONCE(!chunk->mark.connector))
+		return 0;
+	return (unsigned long)chunk->mark.connector->inode;
+}
+
+static inline struct list_head *chunk_hash(unsigned long key)
+{
+	unsigned long n = key / L1_CACHE_BYTES;
 	return chunk_hash_heads + n % HASH_SIZE;
 }
 
 /* hash_lock & entry->lock is held by caller */
 static void insert_hash(struct audit_chunk *chunk)
 {
-	struct fsnotify_mark *entry = &chunk->mark;
+	unsigned long key = chunk_to_key(chunk);
 	struct list_head *list;
 
-	if (!entry->inode)
+	if (!(chunk->mark.flags & FSNOTIFY_MARK_FLAG_ATTACHED))
 		return;
-	list = chunk_hash(entry->inode);
+	list = chunk_hash(key);
 	list_add_rcu(&chunk->hash, list);
 }
 
 /* called under rcu_read_lock */
 struct audit_chunk *audit_tree_lookup(const struct inode *inode)
 {
-	struct list_head *list = chunk_hash(inode);
+	unsigned long key = inode_to_key(inode);
+	struct list_head *list = chunk_hash(key);
 	struct audit_chunk *p;
 
 	list_for_each_entry_rcu(p, list, hash) {
-		/* mark.inode may have gone NULL, but who cares? */
-		if (p->mark.inode == inode) {
+		if (chunk_to_key(p) == key) {
 			atomic_long_inc(&p->refs);
 			return p;
 		}
@@ -234,11 +255,15 @@ static void untag_chunk(struct node *p)
 
 	mutex_lock(&entry->group->mark_mutex);
 	spin_lock(&entry->lock);
-	if (chunk->dead || !entry->inode) {
+	/*
+	 * mark_mutex protects mark from getting detached and thus also from
+	 * mark->connector->inode getting NULL.
+	 */
+	if (chunk->dead || !(entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
 		spin_unlock(&entry->lock);
 		mutex_unlock(&entry->group->mark_mutex);
 		if (new)
-			free_chunk(new);
+			fsnotify_put_mark(&new->mark);
 		goto out;
 	}
 
@@ -262,7 +287,7 @@ static void untag_chunk(struct node *p)
 	if (!new)
 		goto Fallback;
 
-	if (fsnotify_add_mark_locked(&new->mark, entry->group, entry->inode,
+	if (fsnotify_add_mark_locked(&new->mark, entry->connector->inode,
 				     NULL, 1)) {
 		fsnotify_put_mark(&new->mark);
 		goto Fallback;
@@ -328,7 +353,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree)
 		return -ENOMEM;
 
 	entry = &chunk->mark;
-	if (fsnotify_add_mark(entry, audit_tree_group, inode, NULL, 0)) {
+	if (fsnotify_add_mark(entry, inode, NULL, 0)) {
 		fsnotify_put_mark(entry);
 		return -ENOSPC;
 	}
@@ -367,7 +392,8 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 	struct node *p;
 	int n;
 
-	old_entry = fsnotify_find_inode_mark(audit_tree_group, inode);
+	old_entry = fsnotify_find_mark(&inode->i_fsnotify_marks,
+				       audit_tree_group);
 	if (!old_entry)
 		return create_chunk(inode, tree);
 
@@ -394,17 +420,21 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree)
 
 	mutex_lock(&old_entry->group->mark_mutex);
 	spin_lock(&old_entry->lock);
-	if (!old_entry->inode) {
+	/*
+	 * mark_mutex protects mark from getting detached and thus also from
+	 * mark->connector->inode getting NULL.
+	 */
+	if (!(old_entry->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
 		/* old_entry is being shot, lets just lie */
 		spin_unlock(&old_entry->lock);
 		mutex_unlock(&old_entry->group->mark_mutex);
 		fsnotify_put_mark(old_entry);
-		free_chunk(chunk);
+		fsnotify_put_mark(&chunk->mark);
 		return -ENOENT;
 	}
 
-	if (fsnotify_add_mark_locked(chunk_entry, old_entry->group,
-				     old_entry->inode, NULL, 1)) {
+	if (fsnotify_add_mark_locked(chunk_entry,
+			     old_entry->connector->inode, NULL, 1)) {
 		spin_unlock(&old_entry->lock);
 		mutex_unlock(&old_entry->group->mark_mutex);
 		fsnotify_put_mark(chunk_entry);
@@ -589,7 +619,8 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 
 static int compare_root(struct vfsmount *mnt, void *arg)
 {
-	return d_backing_inode(mnt->mnt_root) == arg;
+	return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
+	       (unsigned long)arg;
 }
 
 void audit_trim_trees(void)
@@ -624,9 +655,10 @@ void audit_trim_trees(void)
 		list_for_each_entry(node, &tree->chunks, list) {
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
-			struct inode *inode = chunk->mark.inode;
 			node->index |= 1U<<31;
-			if (iterate_mounts(compare_root, inode, root_mnt))
+			if (iterate_mounts(compare_root,
+					   (void *)chunk_to_key(chunk),
+					   root_mnt))
 				node->index &= ~(1U<<31);
 		}
 		spin_unlock(&hash_lock);
@@ -959,7 +991,8 @@ static int audit_tree_handle_event(struct fsnotify_group *group,
 				   struct fsnotify_mark *inode_mark,
 				   struct fsnotify_mark *vfsmount_mark,
 				   u32 mask, const void *data, int data_type,
-				   const unsigned char *file_name, u32 cookie)
+				   const unsigned char *file_name, u32 cookie,
+				   struct fsnotify_iter_info *iter_info)
 {
 	return 0;
 }
@@ -980,6 +1013,7 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *entry, struct fsnotify
 static const struct fsnotify_ops audit_tree_ops = {
 	.handle_event = audit_tree_handle_event,
 	.freeing_mark = audit_tree_freeing_mark,
+	.free_mark = audit_tree_destroy_watch,
 };
 
 static int __init audit_tree_init(void)
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index e0656bd63036..62d686d96581 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -103,7 +103,7 @@ static inline struct audit_parent *audit_find_parent(struct inode *inode)
 	struct audit_parent *parent = NULL;
 	struct fsnotify_mark *entry;
 
-	entry = fsnotify_find_inode_mark(audit_watch_group, inode);
+	entry = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_watch_group);
 	if (entry)
 		parent = container_of(entry, struct audit_parent, mark);
 
@@ -158,9 +158,9 @@ static struct audit_parent *audit_init_parent(struct path *path)
 
 	INIT_LIST_HEAD(&parent->watches);
 
-	fsnotify_init_mark(&parent->mark, audit_watch_free_mark);
+	fsnotify_init_mark(&parent->mark, audit_watch_group);
 	parent->mark.mask = AUDIT_FS_WATCH;
-	ret = fsnotify_add_mark(&parent->mark, audit_watch_group, inode, NULL, 0);
+	ret = fsnotify_add_mark(&parent->mark, inode, NULL, 0);
 	if (ret < 0) {
 		audit_free_parent(parent);
 		return ERR_PTR(ret);
@@ -473,7 +473,8 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 				    struct fsnotify_mark *inode_mark,
 				    struct fsnotify_mark *vfsmount_mark,
 				    u32 mask, const void *data, int data_type,
-				    const unsigned char *dname, u32 cookie)
+				    const unsigned char *dname, u32 cookie,
+				    struct fsnotify_iter_info *iter_info)
 {
 	const struct inode *inode;
 	struct audit_parent *parent;
@@ -507,6 +508,7 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 
 static const struct fsnotify_ops audit_watch_fsnotify_ops = {
 	.handle_event = 	audit_watch_handle_event,
+	.free_mark =		audit_watch_free_mark,
 };
 
 static int __init audit_watch_init(void)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b2dcbe637b7c..bb724baa7ac9 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -73,6 +73,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
+#include <linux/fsnotify_backend.h>
 #include <uapi/linux/limits.h>
 
 #include "audit.h"
@@ -1596,7 +1597,7 @@ static inline void handle_one(const struct inode *inode)
 	struct audit_tree_refs *p;
 	struct audit_chunk *chunk;
 	int count;
-	if (likely(hlist_empty(&inode->i_fsnotify_marks)))
+	if (likely(!inode->i_fsnotify_marks))
 		return;
 	context = current->audit_context;
 	p = context->trees;
@@ -1639,7 +1640,7 @@ retry:
 	seq = read_seqbegin(&rename_lock);
 	for(;;) {
 		struct inode *inode = d_backing_inode(d);
-		if (inode && unlikely(!hlist_empty(&inode->i_fsnotify_marks))) {
+		if (inode && unlikely(inode->i_fsnotify_marks)) {
 			struct audit_chunk *chunk;
 			chunk = audit_tree_lookup(inode);
 			if (chunk) {