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
  ...

4 files changed, 46 insertions, 16 deletions

diff --git a/include/linux/fs.h b/include/linux/fs.h
index dc634a55163b..b2f9b9c25e41 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1,7 +1,6 @@
 #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);
 }
 
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index e0727d77feaf..533c4408529a 100644
--- a/include/linux/fsnotify_backend.h
+++ b/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 */
diff --git a/include/linux/list.h b/include/linux/list.h
index feb773c76ee0..3e3e64a61002 100644
--- a/include/linux/list.h
+++ b/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.
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 3e88c9a7d57f..834c4e52cb2d 100644
--- a/include/linux/percpu-rwsem.h
+++ b/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