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
  ...

1 files changed, 31 insertions, 19 deletions

diff --git a/fs/inode.c b/fs/inode.c
index d30640f7a193..78a17b8859e1 100644
--- a/fs/inode.c
+++ b/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)