Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs updates from Al Viro:
 "In this one:

   - d_move fixes (Eric Biederman)

   - UFS fixes (me; locking is mostly sane now, a bunch of bugs in error
     handling ought to be fixed)

   - switch of sb_writers to percpu rwsem (Oleg Nesterov)

   - superblock scalability (Josef Bacik and Dave Chinner)

   - swapon(2) race fix (Hugh Dickins)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (65 commits)
  vfs: Test for and handle paths that are unreachable from their mnt_root
  dcache: Reduce the scope of i_lock in d_splice_alias
  dcache: Handle escaped paths in prepend_path
  mm: fix potential data race in SyS_swapon
  inode: don't softlockup when evicting inodes
  inode: rename i_wb_list to i_io_list
  sync: serialise per-superblock sync operations
  inode: convert inode_sb_list_lock to per-sb
  inode: add hlist_fake to avoid the inode hash lock in evict
  writeback: plug writeback at a high level
  change sb_writers to use percpu_rw_semaphore
  shift percpu_counter_destroy() into destroy_super_work()
  percpu-rwsem: kill CONFIG_PERCPU_RWSEM
  percpu-rwsem: introduce percpu_rwsem_release() and percpu_rwsem_acquire()
  percpu-rwsem: introduce percpu_down_read_trylock()
  document rwsem_release() in sb_wait_write()
  fix the broken lockdep logic in __sb_start_write()
  introduce __sb_writers_{acquired,release}() helpers
  ufs_inode_get{frag,block}(): get rid of 'phys' argument
  ufs_getfrag_block(): tidy up a bit
  ...

arch/Kconfig

@@ -93,7 +93,6 @@ config KPROBES_ON_FTRACE
 
 config UPROBES
 	def_bool n
-	select PERCPU_RWSEM
 	help
 	  Uprobes is the user-space counterpart to kprobes: they
 	  enable instrumentation applications (such as 'perf probe')

fs/block_dev.c

@@ -1769,7 +1769,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 {
 	struct inode *inode, *old_inode = NULL;
 
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&blockdev_superblock->s_inode_list_lock);
 	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
 		struct address_space *mapping = inode->i_mapping;
 
@@ -1781,13 +1781,13 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_sb_list_lock);
+		spin_unlock(&blockdev_superblock->s_inode_list_lock);
 		/*
 		 * We hold a reference to 'inode' so it couldn't have been
 		 * removed from s_inodes list while we dropped the
-		 * inode_sb_list_lock.  We cannot iput the inode now as we can
+		 * s_inode_list_lock  We cannot iput the inode now as we can
 		 * be holding the last reference and we cannot iput it under
-		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * s_inode_list_lock. So we keep the reference and iput it
 		 * later.
 		 */
 		iput(old_inode);
@@ -1795,8 +1795,8 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
 
 		func(I_BDEV(inode), arg);
 
-		spin_lock(&inode_sb_list_lock);
+		spin_lock(&blockdev_superblock->s_inode_list_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&blockdev_superblock->s_inode_list_lock);
 	iput(old_inode);
 }

fs/btrfs/transaction.c

@@ -1640,9 +1640,7 @@ static void do_async_commit(struct work_struct *work)
 	 * Tell lockdep about it.
 	 */
 	if (ac->newtrans->type & __TRANS_FREEZABLE)
-		rwsem_acquire_read(
-		     &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
-		     0, 1, _THIS_IP_);
+		__sb_writers_acquired(ac->root->fs_info->sb, SB_FREEZE_FS);
 
 	current->journal_info = ac->newtrans;
 
@@ -1681,9 +1679,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	 * async commit thread will be the one to unlock it.
 	 */
 	if (ac->newtrans->type & __TRANS_FREEZABLE)
-		rwsem_release(
-			&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
-			1, _THIS_IP_);
+		__sb_writers_release(root->fs_info->sb, SB_FREEZE_FS);
 
 	schedule_work(&ac->work);
 

fs/dcache.c

@@ -2718,7 +2718,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * This helper attempts to cope with remotely renamed directories
  *
  * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex, inode->i_lock and rename_lock
+ * dentry->d_parent->d_inode->i_mutex, and rename_lock
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
@@ -2744,7 +2744,6 @@ static int __d_unalias(struct inode *inode,
 	__d_move(alias, dentry, false);
 	ret = 0;
 out_err:
-	spin_unlock(&inode->i_lock);
 	if (m2)
 		mutex_unlock(m2);
 	if (m1)
@@ -2790,10 +2789,11 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 	if (S_ISDIR(inode->i_mode)) {
 		struct dentry *new = __d_find_any_alias(inode);
 		if (unlikely(new)) {
+			/* The reference to new ensures it remains an alias */
+			spin_unlock(&inode->i_lock);
 			write_seqlock(&rename_lock);
 			if (unlikely(d_ancestor(new, dentry))) {
 				write_sequnlock(&rename_lock);
-				spin_unlock(&inode->i_lock);
 				dput(new);
 				new = ERR_PTR(-ELOOP);
 				pr_warn_ratelimited(
@@ -2812,7 +2812,6 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 			} else {
 				__d_move(new, dentry, false);
 				write_sequnlock(&rename_lock);
-				spin_unlock(&inode->i_lock);
 				security_d_instantiate(new, inode);
 			}
 			iput(inode);
@@ -2926,6 +2925,13 @@ static int prepend_path(const struct path *path,
 
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
 			struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
+			/* Escaped? */
+			if (dentry != vfsmnt->mnt_root) {
+				bptr = *buffer;
+				blen = *buflen;
+				error = 3;
+				break;
+			}
 			/* Global root? */
 			if (mnt != parent) {
 				dentry = ACCESS_ONCE(mnt->mnt_mountpoint);

fs/drop_caches.c

@@ -17,7 +17,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 {
 	struct inode *inode, *toput_inode = NULL;
 
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@@ -27,13 +27,15 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_sb_list_lock);
+		spin_unlock(&sb->s_inode_list_lock);
+
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
-		spin_lock(&inode_sb_list_lock);
+
+		spin_lock(&sb->s_inode_list_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 	iput(toput_inode);
 }
 

fs/fs-writeback.c

@@ -88,7 +88,7 @@ unsigned int dirtytime_expire_interval = 12 * 60 * 60;
 
 static inline struct inode *wb_inode(struct list_head *head)
 {
-	return list_entry(head, struct inode, i_wb_list);
+	return list_entry(head, struct inode, i_io_list);
 }
 
 /*
@@ -125,22 +125,22 @@ static void wb_io_lists_depopulated(struct bdi_writeback *wb)
 }
 
 /**
- * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
+ * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list
  * @inode: inode to be moved
  * @wb: target bdi_writeback
  * @head: one of @wb->b_{dirty|io|more_io}
  *
- * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
+ * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io.
  * Returns %true if @inode is the first occupant of the !dirty_time IO
  * lists; otherwise, %false.
  */
-static bool inode_wb_list_move_locked(struct inode *inode,
+static bool inode_io_list_move_locked(struct inode *inode,
 				      struct bdi_writeback *wb,
 				      struct list_head *head)
 {
 	assert_spin_locked(&wb->list_lock);
 
-	list_move(&inode->i_wb_list, head);
+	list_move(&inode->i_io_list, head);
 
 	/* dirty_time doesn't count as dirty_io until expiration */
 	if (head != &wb->b_dirty_time)
@@ -151,19 +151,19 @@ static bool inode_wb_list_move_locked(struct inode *inode,
 }
 
 /**
- * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
+ * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list
  * @inode: inode to be removed
  * @wb: bdi_writeback @inode is being removed from
  *
  * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
  * clear %WB_has_dirty_io if all are empty afterwards.
  */
-static void inode_wb_list_del_locked(struct inode *inode,
+static void inode_io_list_del_locked(struct inode *inode,
 				     struct bdi_writeback *wb)
 {
 	assert_spin_locked(&wb->list_lock);
 
-	list_del_init(&inode->i_wb_list);
+	list_del_init(&inode->i_io_list);
 	wb_io_lists_depopulated(wb);
 }
 
@@ -351,7 +351,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 
 	/*
 	 * Once I_FREEING is visible under i_lock, the eviction path owns
-	 * the inode and we shouldn't modify ->i_wb_list.
+	 * the inode and we shouldn't modify ->i_io_list.
 	 */
 	if (unlikely(inode->i_state & I_FREEING))
 		goto skip_switch;
@@ -390,16 +390,16 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 	 * is always correct including from ->b_dirty_time.  The transfer
 	 * preserves @inode->dirtied_when ordering.
 	 */
-	if (!list_empty(&inode->i_wb_list)) {
+	if (!list_empty(&inode->i_io_list)) {
 		struct inode *pos;
 
-		inode_wb_list_del_locked(inode, old_wb);
+		inode_io_list_del_locked(inode, old_wb);
 		inode->i_wb = new_wb;
-		list_for_each_entry(pos, &new_wb->b_dirty, i_wb_list)
+		list_for_each_entry(pos, &new_wb->b_dirty, i_io_list)
 			if (time_after_eq(inode->dirtied_when,
 					  pos->dirtied_when))
 				break;
-		inode_wb_list_move_locked(inode, new_wb, pos->i_wb_list.prev);
+		inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev);
 	} else {
 		inode->i_wb = new_wb;
 	}
@@ -961,12 +961,12 @@ void wb_start_background_writeback(struct bdi_writeback *wb)
 /*
  * Remove the inode from the writeback list it is on.
  */
-void inode_wb_list_del(struct inode *inode)
+void inode_io_list_del(struct inode *inode)
 {
 	struct bdi_writeback *wb;
 
 	wb = inode_to_wb_and_lock_list(inode);
-	inode_wb_list_del_locked(inode, wb);
+	inode_io_list_del_locked(inode, wb);
 	spin_unlock(&wb->list_lock);
 }
 
@@ -988,7 +988,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
 		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
+	inode_io_list_move_locked(inode, wb, &wb->b_dirty);
 }
 
 /*
@@ -996,7 +996,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
  */
 static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
 {
-	inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
+	inode_io_list_move_locked(inode, wb, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -1055,7 +1055,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 		if (older_than_this &&
 		    inode_dirtied_after(inode, *older_than_this))
 			break;
-		list_move(&inode->i_wb_list, &tmp);
+		list_move(&inode->i_io_list, &tmp);
 		moved++;
 		if (flags & EXPIRE_DIRTY_ATIME)
 			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
@@ -1078,7 +1078,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
 		list_for_each_prev_safe(pos, node, &tmp) {
 			inode = wb_inode(pos);
 			if (inode->i_sb == sb)
-				list_move(&inode->i_wb_list, dispatch_queue);
+				list_move(&inode->i_io_list, dispatch_queue);
 		}
 	}
 out:
@@ -1232,10 +1232,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
 		redirty_tail(inode, wb);
 	} else if (inode->i_state & I_DIRTY_TIME) {
 		inode->dirtied_when = jiffies;
-		inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
+		inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
 	} else {
 		/* The inode is clean. Remove from writeback lists. */
-		inode_wb_list_del_locked(inode, wb);
+		inode_io_list_del_locked(inode, wb);
 	}
 }
 
@@ -1378,7 +1378,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
 	 * touch it. See comment above for explanation.
 	 */
 	if (!(inode->i_state & I_DIRTY_ALL))
-		inode_wb_list_del_locked(inode, wb);
+		inode_io_list_del_locked(inode, wb);
 	spin_unlock(&wb->list_lock);
 	inode_sync_complete(inode);
 out:
@@ -1439,7 +1439,9 @@ static long writeback_sb_inodes(struct super_block *sb,
 	unsigned long start_time = jiffies;
 	long write_chunk;
 	long wrote = 0;  /* count both pages and inodes */
+	struct blk_plug plug;
 
+	blk_start_plug(&plug);
 	while (!list_empty(&wb->b_io)) {
 		struct inode *inode = wb_inode(wb->b_io.prev);
 
@@ -1537,6 +1539,7 @@ static long writeback_sb_inodes(struct super_block *sb,
 				break;
 		}
 	}
+	blk_finish_plug(&plug);
 	return wrote;
 }
 
@@ -2088,7 +2091,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			else
 				dirty_list = &wb->b_dirty_time;
 
-			wakeup_bdi = inode_wb_list_move_locked(inode, wb,
+			wakeup_bdi = inode_io_list_move_locked(inode, wb,
 							       dirty_list);
 
 			spin_unlock(&wb->list_lock);
@@ -2111,6 +2114,15 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
+/*
+ * The @s_sync_lock is used to serialise concurrent sync operations
+ * to avoid lock contention problems with concurrent wait_sb_inodes() calls.
+ * Concurrent callers will block on the s_sync_lock rather than doing contending
+ * walks. The queueing maintains sync(2) required behaviour as all the IO that
+ * has been issued up to the time this function is enter is guaranteed to be
+ * completed by the time we have gained the lock and waited for all IO that is
+ * in progress regardless of the order callers are granted the lock.
+ */
 static void wait_sb_inodes(struct super_block *sb)
 {
 	struct inode *inode, *old_inode = NULL;
@@ -2121,7 +2133,8 @@ static void wait_sb_inodes(struct super_block *sb)
 	 */
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	spin_lock(&inode_sb_list_lock);
+	mutex_lock(&sb->s_sync_lock);
+	spin_lock(&sb->s_inode_list_lock);
 
 	/*
 	 * Data integrity sync. Must wait for all pages under writeback,
@@ -2141,14 +2154,14 @@ static void wait_sb_inodes(struct super_block *sb)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_sb_list_lock);
+		spin_unlock(&sb->s_inode_list_lock);
 
 		/*
 		 * We hold a reference to 'inode' so it couldn't have been
 		 * removed from s_inodes list while we dropped the
-		 * inode_sb_list_lock.  We cannot iput the inode now as we can
+		 * s_inode_list_lock.  We cannot iput the inode now as we can
 		 * be holding the last reference and we cannot iput it under
-		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * s_inode_list_lock. So we keep the reference and iput it
 		 * later.
 		 */
 		iput(old_inode);
@@ -2158,10 +2171,11 @@ static void wait_sb_inodes(struct super_block *sb)
 
 		cond_resched();
 
-		spin_lock(&inode_sb_list_lock);
+		spin_lock(&sb->s_inode_list_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 	iput(old_inode);
+	mutex_unlock(&sb->s_sync_lock);
 }
 
 static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,

fs/inode.c

@@ -28,16 +28,16 @@
  *   inode->i_state, inode->i_hash, __iget()
  * Inode LRU list locks protect:
  *   inode->i_sb->s_inode_lru, inode->i_lru
- * inode_sb_list_lock protects:
- *   sb->s_inodes, inode->i_sb_list
+ * inode->i_sb->s_inode_list_lock protects:
+ *   inode->i_sb->s_inodes, inode->i_sb_list
  * bdi->wb.list_lock protects:
- *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list
+ *   bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
  * inode_hash_lock protects:
  *   inode_hashtable, inode->i_hash
  *
  * Lock ordering:
  *
- * inode_sb_list_lock
+ * inode->i_sb->s_inode_list_lock
  *   inode->i_lock
  *     Inode LRU list locks
  *
@@ -45,7 +45,7 @@
  *   inode->i_lock
  *
  * inode_hash_lock
- *   inode_sb_list_lock
+ *   inode->i_sb->s_inode_list_lock
  *   inode->i_lock
  *
  * iunique_lock
@@ -57,8 +57,6 @@ static unsigned int i_hash_shift __read_mostly;
 static struct hlist_head *inode_hashtable __read_mostly;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
-
 /*
  * Empty aops. Can be used for the cases where the user does not
  * define any of the address_space operations.
@@ -359,7 +357,7 @@ void inode_init_once(struct inode *inode)
 	memset(inode, 0, sizeof(*inode));
 	INIT_HLIST_NODE(&inode->i_hash);
 	INIT_LIST_HEAD(&inode->i_devices);
-	INIT_LIST_HEAD(&inode->i_wb_list);
+	INIT_LIST_HEAD(&inode->i_io_list);
 	INIT_LIST_HEAD(&inode->i_lru);
 	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
@@ -426,18 +424,18 @@ static void inode_lru_list_del(struct inode *inode)
  */
 void inode_sb_list_add(struct inode *inode)
 {
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&inode->i_sb->s_inode_list_lock);
 	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&inode->i_sb->s_inode_list_lock);
 }
 EXPORT_SYMBOL_GPL(inode_sb_list_add);
 
 static inline void inode_sb_list_del(struct inode *inode)
 {
 	if (!list_empty(&inode->i_sb_list)) {
-		spin_lock(&inode_sb_list_lock);
+		spin_lock(&inode->i_sb->s_inode_list_lock);
 		list_del_init(&inode->i_sb_list);
-		spin_unlock(&inode_sb_list_lock);
+		spin_unlock(&inode->i_sb->s_inode_list_lock);
 	}
 }
 
@@ -527,8 +525,8 @@ static void evict(struct inode *inode)
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(!list_empty(&inode->i_lru));
 
-	if (!list_empty(&inode->i_wb_list))
-		inode_wb_list_del(inode);
+	if (!list_empty(&inode->i_io_list))
+		inode_io_list_del(inode);
 
 	inode_sb_list_del(inode);
 
@@ -577,6 +575,7 @@ static void dispose_list(struct list_head *head)
 		list_del_init(&inode->i_lru);
 
 		evict(inode);
+		cond_resched();
 	}
 }
 
@@ -594,7 +593,8 @@ void evict_inodes(struct super_block *sb)
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode_sb_list_lock);
+again:
+	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		if (atomic_read(&inode->i_count))
 			continue;
@@ -609,8 +609,20 @@ void evict_inodes(struct super_block *sb)
 		inode_lru_list_del(inode);
 		spin_unlock(&inode->i_lock);
 		list_add(&inode->i_lru, &dispose);
+
+		/*
+		 * We can have a ton of inodes to evict at unmount time given
+		 * enough memory, check to see if we need to go to sleep for a
+		 * bit so we don't livelock.
+		 */
+		if (need_resched()) {
+			spin_unlock(&sb->s_inode_list_lock);
+			cond_resched();
+			dispose_list(&dispose);
+			goto again;
+		}
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
 }
@@ -631,7 +643,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 	struct inode *inode, *next;
 	LIST_HEAD(dispose);
 
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
@@ -654,7 +666,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 		spin_unlock(&inode->i_lock);
 		list_add(&inode->i_lru, &dispose);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 
 	dispose_list(&dispose);
 
@@ -890,7 +902,7 @@ struct inode *new_inode(struct super_block *sb)
 {
 	struct inode *inode;
 
-	spin_lock_prefetch(&inode_sb_list_lock);
+	spin_lock_prefetch(&sb->s_inode_list_lock);
 
 	inode = new_inode_pseudo(sb);
 	if (inode)

fs/internal.h

@@ -112,14 +112,13 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
 /*
  * inode.c
  */
-extern spinlock_t inode_sb_list_lock;
 extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
 extern void inode_add_lru(struct inode *inode);
 
 /*
  * fs-writeback.c
  */
-extern void inode_wb_list_del(struct inode *inode);
+extern void inode_io_list_del(struct inode *inode);
 
 extern long get_nr_dirty_inodes(void);
 extern void evict_inodes(struct super_block *);

fs/namei.c

@@ -560,6 +560,24 @@ static int __nd_alloc_stack(struct nameidata *nd)
 	return 0;
 }
 
+/**
+ * path_connected - Verify that a path->dentry is below path->mnt.mnt_root
+ * @path: nameidate to verify
+ *
+ * Rename can sometimes move a file or directory outside of a bind
+ * mount, path_connected allows those cases to be detected.
+ */
+static bool path_connected(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+
+	/* Only bind mounts can have disconnected paths */
+	if (mnt->mnt_root == mnt->mnt_sb->s_root)
+		return true;
+
+	return is_subdir(path->dentry, mnt->mnt_root);
+}
+
 static inline int nd_alloc_stack(struct nameidata *nd)
 {
 	if (likely(nd->depth != EMBEDDED_LEVELS))
@@ -1296,6 +1314,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 				return -ECHILD;
 			nd->path.dentry = parent;
 			nd->seq = seq;
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		} else {
 			struct mount *mnt = real_mount(nd->path.mnt);
@@ -1396,7 +1416,7 @@ static void follow_mount(struct path *path)
 	}
 }
 
-static void follow_dotdot(struct nameidata *nd)
+static int follow_dotdot(struct nameidata *nd)
 {
 	if (!nd->root.mnt)
 		set_root(nd);
@@ -1412,6 +1432,8 @@ static void follow_dotdot(struct nameidata *nd)
 			/* rare case of legitimate dget_parent()... */
 			nd->path.dentry = dget_parent(nd->path.dentry);
 			dput(old);
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -1419,6 +1441,7 @@ static void follow_dotdot(struct nameidata *nd)
 	}
 	follow_mount(&nd->path);
 	nd->inode = nd->path.dentry->d_inode;
+	return 0;
 }
 
 /*
@@ -1634,7 +1657,7 @@ static inline int handle_dots(struct nameidata *nd, int type)
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
-			follow_dotdot(nd);
+			return follow_dotdot(nd);
 	}
 	return 0;
 }

fs/notify/inode_mark.c

@@ -143,17 +143,17 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 
 /**
  * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
- * @list: list of inodes being unmounted (sb->s_inodes)
+ * @sb: superblock being unmounted.
  *
  * Called during unmount with no locks held, so needs to be safe against
- * concurrent modifiers. We temporarily drop inode_sb_list_lock and CAN block.
+ * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
  */
-void fsnotify_unmount_inodes(struct list_head *list)
+void fsnotify_unmount_inodes(struct super_block *sb)
 {
 	struct inode *inode, *next_i, *need_iput = NULL;
 
-	spin_lock(&inode_sb_list_lock);
-	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry_safe(inode, next_i, &sb->s_inodes, i_sb_list) {
 		struct inode *need_iput_tmp;
 
 		/*
@@ -189,7 +189,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
-		while (&next_i->i_sb_list != list) {
+		while (&next_i->i_sb_list != &sb->s_inodes) {
 			spin_lock(&next_i->i_lock);
 			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
 						atomic_read(&next_i->i_count)) {
@@ -204,12 +204,12 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		}
 
 		/*
-		 * We can safely drop inode_sb_list_lock here because either
+		 * We can safely drop s_inode_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);
+		spin_unlock(&sb->s_inode_list_lock);
 
 		if (need_iput_tmp)
 			iput(need_iput_tmp);
@@ -221,7 +221,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
 
 		iput(inode);
 
-		spin_lock(&inode_sb_list_lock);
+		spin_lock(&sb->s_inode_list_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 }

fs/quota/dquot.c

@@ -928,7 +928,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	int reserved = 0;
 #endif
 
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		spin_lock(&inode->i_lock);
 		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@@ -939,7 +939,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&inode_sb_list_lock);
+		spin_unlock(&sb->s_inode_list_lock);
 
 #ifdef CONFIG_QUOTA_DEBUG
 		if (unlikely(inode_get_rsv_space(inode) > 0))
@@ -951,15 +951,15 @@ static void add_dquot_ref(struct super_block *sb, int type)
 		/*
 		 * We hold a reference to 'inode' so it couldn't have been
 		 * removed from s_inodes list while we dropped the
-		 * inode_sb_list_lock We cannot iput the inode now as we can be
+		 * s_inode_list_lock. We cannot iput the inode now as we can be
 		 * holding the last reference and we cannot iput it under
-		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * s_inode_list_lock. So we keep the reference and iput it
 		 * later.
 		 */
 		old_inode = inode;
-		spin_lock(&inode_sb_list_lock);
+		spin_lock(&sb->s_inode_list_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 	iput(old_inode);
 
 #ifdef CONFIG_QUOTA_DEBUG
@@ -1028,7 +1028,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 	struct inode *inode;
 	int reserved = 0;
 
-	spin_lock(&inode_sb_list_lock);
+	spin_lock(&sb->s_inode_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		/*
 		 *  We have to scan also I_NEW inodes because they can already
@@ -1044,7 +1044,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 		}
 		spin_unlock(&dq_data_lock);
 	}
-	spin_unlock(&inode_sb_list_lock);
+	spin_unlock(&sb->s_inode_list_lock);
 #ifdef CONFIG_QUOTA_DEBUG
 	if (reserved) {
 		printk(KERN_WARNING "VFS (%s): Writes happened after quota"

fs/super.c

@@ -135,6 +135,24 @@ static unsigned long super_cache_count(struct shrinker *shrink,
 	return total_objects;
 }
 
+static void destroy_super_work(struct work_struct *work)
+{
+	struct super_block *s = container_of(work, struct super_block,
+							destroy_work);
+	int i;
+
+	for (i = 0; i < SB_FREEZE_LEVELS; i++)
+		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
+	kfree(s);
+}
+
+static void destroy_super_rcu(struct rcu_head *head)
+{
+	struct super_block *s = container_of(head, struct super_block, rcu);
+	INIT_WORK(&s->destroy_work, destroy_super_work);
+	schedule_work(&s->destroy_work);
+}
+
 /**
  *	destroy_super	-	frees a superblock
  *	@s: superblock to free
@@ -143,16 +161,13 @@ static unsigned long super_cache_count(struct shrinker *shrink,
  */
 static void destroy_super(struct super_block *s)
 {
-	int i;
 	list_lru_destroy(&s->s_dentry_lru);
 	list_lru_destroy(&s->s_inode_lru);
-	for (i = 0; i < SB_FREEZE_LEVELS; i++)
-		percpu_counter_destroy(&s->s_writers.counter[i]);
 	security_sb_free(s);
 	WARN_ON(!list_empty(&s->s_mounts));
 	kfree(s->s_subtype);
 	kfree(s->s_options);
-	kfree_rcu(s, rcu);
+	call_rcu(&s->rcu, destroy_super_rcu);
 }
 
 /**
@@ -178,19 +193,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 		goto fail;
 
 	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
-		if (percpu_counter_init(&s->s_writers.counter[i], 0,
-					GFP_KERNEL) < 0)
+		if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
+					sb_writers_name[i],
+					&type->s_writers_key[i]))
 			goto fail;
-		lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
-				 &type->s_writers_key[i], 0);
 	}
-	init_waitqueue_head(&s->s_writers.wait);
 	init_waitqueue_head(&s->s_writers.wait_unfrozen);
 	s->s_bdi = &noop_backing_dev_info;
 	s->s_flags = flags;
 	INIT_HLIST_NODE(&s->s_instances);
 	INIT_HLIST_BL_HEAD(&s->s_anon);
+	mutex_init(&s->s_sync_lock);
 	INIT_LIST_HEAD(&s->s_inodes);
+	spin_lock_init(&s->s_inode_list_lock);
 
 	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
@@ -399,7 +414,7 @@ void generic_shutdown_super(struct super_block *sb)
 		sync_filesystem(sb);
 		sb->s_flags &= ~MS_ACTIVE;
 
-		fsnotify_unmount_inodes(&sb->s_inodes);
+		fsnotify_unmount_inodes(sb);
 
 		evict_inodes(sb);
 
@@ -1146,72 +1161,46 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
  */
 void __sb_end_write(struct super_block *sb, int level)
 {
-	percpu_counter_dec(&sb->s_writers.counter[level-1]);
-	/*
-	 * Make sure s_writers are updated before we wake up waiters in
-	 * freeze_super().
-	 */
-	smp_mb();
-	if (waitqueue_active(&sb->s_writers.wait))
-		wake_up(&sb->s_writers.wait);
-	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_);
+	percpu_up_read(sb->s_writers.rw_sem + level-1);
 }
 EXPORT_SYMBOL(__sb_end_write);
 
-#ifdef CONFIG_LOCKDEP
-/*
- * We want lockdep to tell us about possible deadlocks with freezing but
- * it's it bit tricky to properly instrument it. Getting a freeze protection
- * works as getting a read lock but there are subtle problems. XFS for example
- * gets freeze protection on internal level twice in some cases, which is OK
- * only because we already hold a freeze protection also on higher level. Due
- * to these cases we have to tell lockdep we are doing trylock when we
- * already hold a freeze protection for a higher freeze level.
- */
-static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock,
-				unsigned long ip)
-{
-	int i;
-
-	if (!trylock) {
-		for (i = 0; i < level - 1; i++)
-			if (lock_is_held(&sb->s_writers.lock_map[i])) {
-				trylock = true;
-				break;
-			}
-	}
-	rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip);
-}
-#endif
-
 /*
  * This is an internal function, please use sb_start_{write,pagefault,intwrite}
  * instead.
  */
 int __sb_start_write(struct super_block *sb, int level, bool wait)
 {
-retry:
-	if (unlikely(sb->s_writers.frozen >= level)) {
-		if (!wait)
-			return 0;
-		wait_event(sb->s_writers.wait_unfrozen,
-			   sb->s_writers.frozen < level);
-	}
+	bool force_trylock = false;
+	int ret = 1;
 
 #ifdef CONFIG_LOCKDEP
-	acquire_freeze_lock(sb, level, !wait, _RET_IP_);
-#endif
-	percpu_counter_inc(&sb->s_writers.counter[level-1]);
 	/*
-	 * Make sure counter is updated before we check for frozen.
-	 * freeze_super() first sets frozen and then checks the counter.
+	 * We want lockdep to tell us about possible deadlocks with freezing
+	 * but it's it bit tricky to properly instrument it. Getting a freeze
+	 * protection works as getting a read lock but there are subtle
+	 * problems. XFS for example gets freeze protection on internal level
+	 * twice in some cases, which is OK only because we already hold a
+	 * freeze protection also on higher level. Due to these cases we have
+	 * to use wait == F (trylock mode) which must not fail.
 	 */
-	smp_mb();
-	if (unlikely(sb->s_writers.frozen >= level)) {
-		__sb_end_write(sb, level);
-		goto retry;
+	if (wait) {
+		int i;
+
+		for (i = 0; i < level - 1; i++)
+			if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
+				force_trylock = true;
+				break;
+			}
 	}
-	return 1;
+#endif
+	if (wait && !force_trylock)
+		percpu_down_read(sb->s_writers.rw_sem + level-1);
+	else
+		ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
+
+	WARN_ON(force_trylock & !ret);
+	return ret;
 }
 EXPORT_SYMBOL(__sb_start_write);
 
@@ -1221,37 +1210,33 @@ EXPORT_SYMBOL(__sb_start_write);
  * @level: type of writers we wait for (normal vs page fault)
  *
  * This function waits until there are no writers of given type to given file
- * system. Caller of this function should make sure there can be no new writers
- * of type @level before calling this function. Otherwise this function can
- * livelock.
+ * system.
  */
 static void sb_wait_write(struct super_block *sb, int level)
 {
-	s64 writers;
-
+	percpu_down_write(sb->s_writers.rw_sem + level-1);
 	/*
-	 * We just cycle-through lockdep here so that it does not complain
-	 * about returning with lock to userspace
+	 * We are going to return to userspace and forget about this lock, the
+	 * ownership goes to the caller of thaw_super() which does unlock.
+	 *
+	 * FIXME: we should do this before return from freeze_super() after we
+	 * called sync_filesystem(sb) and s_op->freeze_fs(sb), and thaw_super()
+	 * should re-acquire these locks before s_op->unfreeze_fs(sb). However
+	 * this leads to lockdep false-positives, so currently we do the early
+	 * release right after acquire.
 	 */
-	rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);
-	rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);
-
-	do {
-		DEFINE_WAIT(wait);
+	percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_);
+}
 
-		/*
-		 * We use a barrier in prepare_to_wait() to separate setting
-		 * of frozen and checking of the counter
-		 */
-		prepare_to_wait(&sb->s_writers.wait, &wait,
-				TASK_UNINTERRUPTIBLE);
+static void sb_freeze_unlock(struct super_block *sb)
+{
+	int level;
 
-		writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);
-		if (writers)
-			schedule();
+	for (level = 0; level < SB_FREEZE_LEVELS; ++level)
+		percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
 
-		finish_wait(&sb->s_writers.wait, &wait);
-	} while (writers);
+	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+		percpu_up_write(sb->s_writers.rw_sem + level);
 }
 
 /**
@@ -1310,20 +1295,14 @@ int freeze_super(struct super_block *sb)
 		return 0;
 	}
 
-	/* From now on, no new normal writers can start */
 	sb->s_writers.frozen = SB_FREEZE_WRITE;
-	smp_wmb();
-
 	/* Release s_umount to preserve sb_start_write -> s_umount ordering */
 	up_write(&sb->s_umount);
-
 	sb_wait_write(sb, SB_FREEZE_WRITE);
+	down_write(&sb->s_umount);
 
 	/* Now we go and block page faults... */
-	down_write(&sb->s_umount);
 	sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
-	smp_wmb();
-
 	sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
 
 	/* All writers are done so after syncing there won't be dirty data */
@@ -1331,7 +1310,6 @@ int freeze_super(struct super_block *sb)
 
 	/* Now wait for internal filesystem counter */
 	sb->s_writers.frozen = SB_FREEZE_FS;
-	smp_wmb();
 	sb_wait_write(sb, SB_FREEZE_FS);
 
 	if (sb->s_op->freeze_fs) {
@@ -1340,7 +1318,7 @@ int freeze_super(struct super_block *sb)
 			printk(KERN_ERR
 				"VFS:Filesystem freeze failed\n");
 			sb->s_writers.frozen = SB_UNFROZEN;
-			smp_wmb();
+			sb_freeze_unlock(sb);
 			wake_up(&sb->s_writers.wait_unfrozen);
 			deactivate_locked_super(sb);
 			return ret;
@@ -1372,8 +1350,10 @@ int thaw_super(struct super_block *sb)
 		return -EINVAL;
 	}
 
-	if (sb->s_flags & MS_RDONLY)
+	if (sb->s_flags & MS_RDONLY) {
+		sb->s_writers.frozen = SB_UNFROZEN;
 		goto out;
+	}
 
 	if (sb->s_op->unfreeze_fs) {
 		error = sb->s_op->unfreeze_fs(sb);
@@ -1385,12 +1365,11 @@ int thaw_super(struct super_block *sb)
 		}
 	}
 
-out:
 	sb->s_writers.frozen = SB_UNFROZEN;
-	smp_wmb();
+	sb_freeze_unlock(sb);
+out:
 	wake_up(&sb->s_writers.wait_unfrozen);
 	deactivate_locked_super(sb);
-
 	return 0;
 }
 EXPORT_SYMBOL(thaw_super);

fs/ufs/Makefile

@@ -5,5 +5,5 @@
 obj-$(CONFIG_UFS_FS) += ufs.o
 
 ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \
-	    namei.o super.o symlink.o truncate.o util.o
+	    namei.o super.o symlink.o util.o
 ccflags-$(CONFIG_UFS_DEBUG)    += -DDEBUG

fs/ufs/balloc.c

@@ -417,7 +417,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	if (oldcount == 0) {
 		result = ufs_alloc_fragments (inode, cgno, goal, count, err);
 		if (result) {
+			write_seqlock(&UFS_I(inode)->meta_lock);
 			ufs_cpu_to_data_ptr(sb, p, result);
+			write_sequnlock(&UFS_I(inode)->meta_lock);
 			*err = 0;
 			UFS_I(inode)->i_lastfrag =
 				max(UFS_I(inode)->i_lastfrag, fragment + count);
@@ -473,7 +475,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		ufs_change_blocknr(inode, fragment - oldcount, oldcount,
 				   uspi->s_sbbase + tmp,
 				   uspi->s_sbbase + result, locked_page);
+		write_seqlock(&UFS_I(inode)->meta_lock);
 		ufs_cpu_to_data_ptr(sb, p, result);
+		write_sequnlock(&UFS_I(inode)->meta_lock);
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);

fs/ufs/super.c

@@ -94,22 +94,6 @@
 #include "swab.h"
 #include "util.h"
 
-void lock_ufs(struct super_block *sb)
-{
-	struct ufs_sb_info *sbi = UFS_SB(sb);
-
-	mutex_lock(&sbi->mutex);
-	sbi->mutex_owner = current;
-}
-
-void unlock_ufs(struct super_block *sb)
-{
-	struct ufs_sb_info *sbi = UFS_SB(sb);
-
-	sbi->mutex_owner = NULL;
-	mutex_unlock(&sbi->mutex);
-}
-
 static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation)
 {
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
@@ -694,7 +678,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	struct ufs_super_block_third * usb3;
 	unsigned flags;
 
-	lock_ufs(sb);
 	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	UFSD("ENTER\n");
@@ -714,7 +697,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 
 	UFSD("EXIT\n");
 	mutex_unlock(&UFS_SB(sb)->s_lock);
-	unlock_ufs(sb);
 
 	return 0;
 }
@@ -758,7 +740,6 @@ static void ufs_put_super(struct super_block *sb)
 
 	ubh_brelse_uspi (sbi->s_uspi);
 	kfree (sbi->s_uspi);
-	mutex_destroy(&sbi->mutex);
 	kfree (sbi);
 	sb->s_fs_info = NULL;
 	UFSD("EXIT\n");
@@ -801,7 +782,6 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 
 	UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
 	
-	mutex_init(&sbi->mutex);
 	mutex_init(&sbi->s_lock);
 	spin_lock_init(&sbi->work_lock);
 	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
@@ -1257,7 +1237,6 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	return 0;
 
 failed:
-	mutex_destroy(&sbi->mutex);
 	if (ubh)
 		ubh_brelse_uspi (uspi);
 	kfree (uspi);
@@ -1280,7 +1259,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	unsigned flags;
 
 	sync_filesystem(sb);
-	lock_ufs(sb);
 	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
@@ -1296,7 +1274,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options (data, &new_mount_opt)) {
 		mutex_unlock(&UFS_SB(sb)->s_lock);
-		unlock_ufs(sb);
 		return -EINVAL;
 	}
 	if (!(new_mount_opt & UFS_MOUNT_UFSTYPE)) {
@@ -1304,14 +1281,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		pr_err("ufstype can't be changed during remount\n");
 		mutex_unlock(&UFS_SB(sb)->s_lock);
-		unlock_ufs(sb);
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
 		mutex_unlock(&UFS_SB(sb)->s_lock);
-		unlock_ufs(sb);
 		return 0;
 	}
 	
@@ -1335,7 +1310,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #ifndef CONFIG_UFS_FS_WRITE
 		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
 		mutex_unlock(&UFS_SB(sb)->s_lock);
-		unlock_ufs(sb);
 		return -EINVAL;
 #else
 		if (ufstype != UFS_MOUNT_UFSTYPE_SUN && 
@@ -1345,13 +1319,11 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			pr_err("this ufstype is read-only supported\n");
 			mutex_unlock(&UFS_SB(sb)->s_lock);
-			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			pr_err("failed during remounting\n");
 			mutex_unlock(&UFS_SB(sb)->s_lock);
-			unlock_ufs(sb);
 			return -EPERM;
 		}
 		sb->s_flags &= ~MS_RDONLY;
@@ -1359,7 +1331,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
 	mutex_unlock(&UFS_SB(sb)->s_lock);
-	unlock_ufs(sb);
 	return 0;
 }
 
@@ -1391,8 +1362,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct ufs_super_block_third *usb3;
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
-	lock_ufs(sb);
-
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	usb3 = ubh_get_usb_third(uspi);
 	
 	if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) {
@@ -1413,7 +1383,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
 
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 
 	return 0;
 }
@@ -1429,6 +1399,8 @@ static struct inode *ufs_alloc_inode(struct super_block *sb)
 		return NULL;
 
 	ei->vfs_inode.i_version = 1;
+	seqlock_init(&ei->meta_lock);
+	mutex_init(&ei->truncate_mutex);
 	return &ei->vfs_inode;
 }
 

fs/ufs/ufs.h

@@ -24,8 +24,6 @@ struct ufs_sb_info {
 	unsigned s_cgno[UFS_MAX_GROUP_LOADED];
 	unsigned short s_cg_loaded;
 	unsigned s_mount_opt;
-	struct mutex mutex;
-	struct task_struct *mutex_owner;
 	struct super_block *sb;
 	int work_queued; /* non-zero if the delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
@@ -46,6 +44,8 @@ struct ufs_inode_info {
 	__u32	i_oeftflag;
 	__u16	i_osync;
 	__u64	i_lastfrag;
+	seqlock_t meta_lock;
+	struct mutex	truncate_mutex;
 	__u32   i_dir_start_lookup;
 	struct inode vfs_inode;
 };
@@ -122,7 +122,7 @@ extern struct inode *ufs_iget(struct super_block *, unsigned long);
 extern int ufs_write_inode (struct inode *, struct writeback_control *);
 extern int ufs_sync_inode (struct inode *);
 extern void ufs_evict_inode (struct inode *);
-extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create);
+extern int ufs_setattr(struct dentry *dentry, struct iattr *attr);
 
 /* namei.c */
 extern const struct file_operations ufs_dir_operations;
@@ -140,10 +140,6 @@ void ufs_mark_sb_dirty(struct super_block *sb);
 extern const struct inode_operations ufs_fast_symlink_inode_operations;
 extern const struct inode_operations ufs_symlink_inode_operations;
 
-/* truncate.c */
-extern int ufs_truncate (struct inode *, loff_t);
-extern int ufs_setattr(struct dentry *dentry, struct iattr *attr);
-
 static inline struct ufs_sb_info *UFS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -170,7 +166,4 @@ static inline u32 ufs_dtogd(struct ufs_sb_private_info * uspi, u64 b)
 	return do_div(b, uspi->s_fpg);
 }
 
-extern void lock_ufs(struct super_block *sb);
-extern void unlock_ufs(struct super_block *sb);
-
 #endif /* _UFS_UFS_H */

fs/xfs/xfs_aops.c

@@ -119,8 +119,7 @@ xfs_setfilesize_trans_alloc(
 	 * We may pass freeze protection with a transaction.  So tell lockdep
 	 * we released it.
 	 */
-	rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
-		      1, _THIS_IP_);
+	__sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
 	/*
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
@@ -171,8 +170,7 @@ xfs_setfilesize_ioend(
 	 * Similarly for freeze protection.
 	 */
 	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
-	rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
-			   0, 1, _THIS_IP_);
+	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
 }

include/linux/fs.h

 #ifndef _LINUX_FS_H
 #define _LINUX_FS_H
 
-
 #include <linux/linkage.h>
 #include <linux/wait.h>
 #include <linux/kdev_t.h>
@@ -30,6 +29,8 @@
 #include <linux/lockdep.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/blk_types.h>
+#include <linux/workqueue.h>
+#include <linux/percpu-rwsem.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
@@ -636,7 +637,7 @@ struct inode {
 	unsigned long		dirtied_time_when;
 
 	struct hlist_node	i_hash;
-	struct list_head	i_wb_list;	/* backing dev IO list */
+	struct list_head	i_io_list;	/* backing dev IO list */
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */
 
@@ -1281,16 +1282,9 @@ enum {
 #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
 
 struct sb_writers {
-	/* Counters for counting writers at each level */
-	struct percpu_counter	counter[SB_FREEZE_LEVELS];
-	wait_queue_head_t	wait;		/* queue for waiting for
-						   writers / faults to finish */
-	int			frozen;		/* Is sb frozen? */
-	wait_queue_head_t	wait_unfrozen;	/* queue for waiting for
-						   sb to be thawed */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	lock_map[SB_FREEZE_LEVELS];
-#endif
+	int				frozen;		/* Is sb frozen? */
+	wait_queue_head_t		wait_unfrozen;	/* for get_super_thawed() */
+	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
 struct super_block {
@@ -1316,7 +1310,6 @@ struct super_block {
 #endif
 	const struct xattr_handler **s_xattr;
 
-	struct list_head	s_inodes;	/* all inodes */
 	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	struct block_device	*s_bdev;
@@ -1382,11 +1375,18 @@ struct super_block {
 	struct list_lru		s_dentry_lru ____cacheline_aligned_in_smp;
 	struct list_lru		s_inode_lru ____cacheline_aligned_in_smp;
 	struct rcu_head		rcu;
+	struct work_struct	destroy_work;
+
+	struct mutex		s_sync_lock;	/* sync serialisation lock */
 
 	/*
 	 * Indicates how deep in a filesystem stack this SB is
 	 */
 	int s_stack_depth;
+
+	/* s_inode_list_lock protects s_inodes */
+	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
+	struct list_head	s_inodes;	/* all inodes */
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1398,6 +1398,11 @@ extern struct timespec current_fs_time(struct super_block *sb);
 void __sb_end_write(struct super_block *sb, int level);
 int __sb_start_write(struct super_block *sb, int level, bool wait);
 
+#define __sb_writers_acquired(sb, lev)	\
+	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
+#define __sb_writers_release(sb, lev)	\
+	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
+
 /**
  * sb_end_write - drop write access to a superblock
  * @sb: the super we wrote to
@@ -2614,7 +2619,7 @@ static inline void insert_inode_hash(struct inode *inode)
 extern void __remove_inode_hash(struct inode *);
 static inline void remove_inode_hash(struct inode *inode)
 {
-	if (!inode_unhashed(inode))
+	if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
 		__remove_inode_hash(inode);
 }
 

include/linux/fsnotify_backend.h

@@ -368,7 +368,7 @@ extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, un
 extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group);
 extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
-extern void fsnotify_unmount_inodes(struct list_head *list);
+extern void fsnotify_unmount_inodes(struct super_block *sb);
 
 /* put here because inotify does some weird stuff when destroying watches */
 extern void fsnotify_init_event(struct fsnotify_event *event,
@@ -404,7 +404,7 @@ static inline u32 fsnotify_get_cookie(void)
 	return 0;
 }
 
-static inline void fsnotify_unmount_inodes(struct list_head *list)
+static inline void fsnotify_unmount_inodes(struct super_block *sb)
 {}
 
 #endif	/* CONFIG_FSNOTIFY */

include/linux/list.h

@@ -672,6 +672,11 @@ static inline void hlist_add_fake(struct hlist_node *n)
 	n->pprev = &n->next;
 }
 
+static inline bool hlist_fake(struct hlist_node *h)
+{
+	return h->pprev == &h->next;
+}
+
 /*
  * Move a list from one list head to another. Fixup the pprev
  * reference of the first entry if it exists.

include/linux/percpu-rwsem.h

@@ -16,6 +16,7 @@ struct percpu_rw_semaphore {
 };
 
 extern void percpu_down_read(struct percpu_rw_semaphore *);
+extern int  percpu_down_read_trylock(struct percpu_rw_semaphore *);
 extern void percpu_up_read(struct percpu_rw_semaphore *);
 
 extern void percpu_down_write(struct percpu_rw_semaphore *);
@@ -31,4 +32,23 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
 	__percpu_init_rwsem(brw, #brw, &rwsem_key);		\
 })
 
+
+#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
+
+static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
+					bool read, unsigned long ip)
+{
+	lock_release(&sem->rw_sem.dep_map, 1, ip);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	if (!read)
+		sem->rw_sem.owner = NULL;
+#endif
+}
+
+static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
+					bool read, unsigned long ip)
+{
+	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
+}
+
 #endif

init/Kconfig

@@ -927,7 +927,6 @@ config NUMA_BALANCING_DEFAULT_ENABLED
 menuconfig CGROUPS
 	bool "Control Group support"
 	select KERNFS
-	select PERCPU_RWSEM
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory

kernel/locking/Makefile

 
-obj-y += mutex.o semaphore.o rwsem.o
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -24,6 +24,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
-obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o

kernel/locking/percpu-rwsem.c

@@ -88,6 +88,19 @@ void percpu_down_read(struct percpu_rw_semaphore *brw)
 	__up_read(&brw->rw_sem);
 }
 
+int percpu_down_read_trylock(struct percpu_rw_semaphore *brw)
+{
+	if (unlikely(!update_fast_ctr(brw, +1))) {
+		if (!__down_read_trylock(&brw->rw_sem))
+			return 0;
+		atomic_inc(&brw->slow_read_ctr);
+		__up_read(&brw->rw_sem);
+	}
+
+	rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 1, _RET_IP_);
+	return 1;
+}
+
 void percpu_up_read(struct percpu_rw_semaphore *brw)
 {
 	rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);

lib/Kconfig

@@ -53,9 +53,6 @@ config GENERIC_IO
 config STMP_DEVICE
 	bool
 
-config PERCPU_RWSEM
-	bool
-
 config ARCH_USE_CMPXCHG_LOCKREF
 	bool
 

mm/backing-dev.c

@@ -55,13 +55,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 
 	nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0;
 	spin_lock(&wb->list_lock);
-	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
+	list_for_each_entry(inode, &wb->b_dirty, i_io_list)
 		nr_dirty++;
-	list_for_each_entry(inode, &wb->b_io, i_wb_list)
+	list_for_each_entry(inode, &wb->b_io, i_io_list)
 		nr_io++;
-	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
+	list_for_each_entry(inode, &wb->b_more_io, i_io_list)
 		nr_more_io++;
-	list_for_each_entry(inode, &wb->b_dirty_time, i_wb_list)
+	list_for_each_entry(inode, &wb->b_dirty_time, i_io_list)
 		if (inode->i_state & I_DIRTY_TIME)
 			nr_dirty_time++;
 	spin_unlock(&wb->list_lock);

mm/swapfile.c

@@ -2143,11 +2143,10 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	if (S_ISBLK(inode->i_mode)) {
 		p->bdev = bdgrab(I_BDEV(inode));
 		error = blkdev_get(p->bdev,
-				   FMODE_READ | FMODE_WRITE | FMODE_EXCL,
-				   sys_swapon);
+				   FMODE_READ | FMODE_WRITE | FMODE_EXCL, p);
 		if (error < 0) {
 			p->bdev = NULL;
-			return -EINVAL;
+			return error;
 		}
 		p->old_block_size = block_size(p->bdev);
 		error = set_blocksize(p->bdev, PAGE_SIZE);
@@ -2348,7 +2347,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	struct filename *name;
 	struct file *swap_file = NULL;
 	struct address_space *mapping;
-	int i;
 	int prio;
 	int error;
 	union swap_header *swap_header;
@@ -2388,19 +2386,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	p->swap_file = swap_file;
 	mapping = swap_file->f_mapping;
-
-	for (i = 0; i < nr_swapfiles; i++) {
-		struct swap_info_struct *q = swap_info[i];
-
-		if (q == p || !q->swap_file)
-			continue;
-		if (mapping == q->swap_file->f_mapping) {
-			error = -EBUSY;
-			goto bad_swap;
-		}
-	}
-
 	inode = mapping->host;
+
 	/* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */
 	error = claim_swapfile(p, inode);
 	if (unlikely(error))
@@ -2433,6 +2420,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap;
 	}
 	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
+		int cpu;
+
 		p->flags |= SWP_SOLIDSTATE;
 		/*
 		 * select a random position to start with to help wear leveling
@@ -2451,9 +2440,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			error = -ENOMEM;
 			goto bad_swap;
 		}
-		for_each_possible_cpu(i) {
+		for_each_possible_cpu(cpu) {
 			struct percpu_cluster *cluster;
-			cluster = per_cpu_ptr(p->percpu_cluster, i);
+			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
 			cluster_set_null(&cluster->index);
 		}
 	}