Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  fs: simplify iget & friends
  fs: pull inode->i_lock up out of writeback_single_inode
  fs: rename inode_lock to inode_hash_lock
  fs: move i_wb_list out from under inode_lock
  fs: move i_sb_list out from under inode_lock
  fs: remove inode_lock from iput_final and prune_icache
  fs: Lock the inode LRU list separately
  fs: factor inode disposal
  fs: protect inode->i_state with inode->i_lock
  autofs4: Do not potentially dereference NULL pointer returned by fget() in autofs_dev_ioctl_setpipefd()
  autofs4 - remove autofs4_lock
  autofs4 - fix d_manage() return on rcu-walk
  autofs4 - fix autofs4_expire_indirect() traversal
  autofs4 - fix dentry leak in autofs4_expire_direct()
  autofs4 - reinstate last used update on access
  vfs - check non-mountpoint dentry might block in __follow_mount_rcu()

Documentation/filesystems/Locking

@@ -128,7 +128,7 @@ alloc_inode:
 destroy_inode:
 dirty_inode:				(must not sleep)
 write_inode:
-drop_inode:				!!!inode_lock!!!
+drop_inode:				!!!inode->i_lock!!!
 evict_inode:
 put_super:		write
 write_super:		read

Documentation/filesystems/porting

@@ -298,11 +298,14 @@ be used instead.  It gets called whenever the inode is evicted, whether it has
 remaining links or not.  Caller does *not* evict the pagecache or inode-associated
 metadata buffers; getting rid of those is responsibility of method, as it had
 been for ->delete_inode().
-	->drop_inode() returns int now; it's called on final iput() with inode_lock
-held and it returns true if filesystems wants the inode to be dropped.  As before,
-generic_drop_inode() is still the default and it's been updated appropriately.
-generic_delete_inode() is also alive and it consists simply of return 1.  Note that
-all actual eviction work is done by caller after ->drop_inode() returns.
+
+	->drop_inode() returns int now; it's called on final iput() with
+inode->i_lock held and it returns true if filesystems wants the inode to be
+dropped.  As before, generic_drop_inode() is still the default and it's been
+updated appropriately.  generic_delete_inode() is also alive and it consists
+simply of return 1.  Note that all actual eviction work is done by caller after
+->drop_inode() returns.
+
 	clear_inode() is gone; use end_writeback() instead.  As before, it must
 be called exactly once on each call of ->evict_inode() (as it used to be for
 each call of ->delete_inode()).  Unlike before, if you are using inode-associated
@@ -395,6 +398,9 @@ Currently you can only have FALLOC_FL_PUNCH_HOLE with FALLOC_FL_KEEP_SIZE set,
 so the i_size should not change when hole punching, even when puching the end of
 a file off.
 
+--
+[mandatory]
+
 --
 [mandatory]
 	->get_sb() is gone.  Switch to use of ->mount().  Typically it's just

Documentation/filesystems/vfs.txt

@@ -254,7 +254,7 @@ or bottom half).
 	should be synchronous or not, not all filesystems check this flag.
 
   drop_inode: called when the last access to the inode is dropped,
-	with the inode_lock spinlock held.
+	with the inode->i_lock spinlock held.
 
 	This method should be either NULL (normal UNIX filesystem
 	semantics) or "generic_delete_inode" (for filesystems that do not

fs/autofs4/autofs_i.h

@@ -61,8 +61,6 @@ do {							\
 		current->pid, __func__, ##args);	\
 } while (0)
 
-extern spinlock_t autofs4_lock;
-
 /* Unified info structure.  This is pointed to by both the dentry and
    inode structures.  Each file in the filesystem has an instance of this
    structure.  It holds a reference to the dentry, so dentries are never

fs/autofs4/dev-ioctl.c

@@ -372,6 +372,10 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp,
 		return -EBUSY;
 	} else {
 		struct file *pipe = fget(pipefd);
+		if (!pipe) {
+			err = -EBADF;
+			goto out;
+		}
 		if (!pipe->f_op || !pipe->f_op->write) {
 			err = -EPIPE;
 			fput(pipe);

fs/autofs4/expire.c

@@ -86,19 +86,71 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	return status;
 }
 
+/*
+ * Calculate and dget next entry in the subdirs list under root.
+ */
+static struct dentry *get_next_positive_subdir(struct dentry *prev,
+						struct dentry *root)
+{
+	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
+	struct list_head *next;
+	struct dentry *p, *q;
+
+	spin_lock(&sbi->lookup_lock);
+
+	if (prev == NULL) {
+		spin_lock(&root->d_lock);
+		prev = dget_dlock(root);
+		next = prev->d_subdirs.next;
+		p = prev;
+		goto start;
+	}
+
+	p = prev;
+	spin_lock(&p->d_lock);
+again:
+	next = p->d_u.d_child.next;
+start:
+	if (next == &root->d_subdirs) {
+		spin_unlock(&p->d_lock);
+		spin_unlock(&sbi->lookup_lock);
+		dput(prev);
+		return NULL;
+	}
+
+	q = list_entry(next, struct dentry, d_u.d_child);
+
+	spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED);
+	/* Negative dentry - try next */
+	if (!simple_positive(q)) {
+		spin_unlock(&p->d_lock);
+		p = q;
+		goto again;
+	}
+	dget_dlock(q);
+	spin_unlock(&q->d_lock);
+	spin_unlock(&p->d_lock);
+	spin_unlock(&sbi->lookup_lock);
+
+	dput(prev);
+
+	return q;
+}
+
 /*
  * Calculate and dget next entry in top down tree traversal.
  */
 static struct dentry *get_next_positive_dentry(struct dentry *prev,
 						struct dentry *root)
 {
+	struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb);
 	struct list_head *next;
 	struct dentry *p, *ret;
 
 	if (prev == NULL)
 		return dget(root);
 
-	spin_lock(&autofs4_lock);
+	spin_lock(&sbi->lookup_lock);
 relock:
 	p = prev;
 	spin_lock(&p->d_lock);
@@ -110,7 +162,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev,
 
 			if (p == root) {
 				spin_unlock(&p->d_lock);
-				spin_unlock(&autofs4_lock);
+				spin_unlock(&sbi->lookup_lock);
 				dput(prev);
 				return NULL;
 			}
@@ -140,7 +192,7 @@ static struct dentry *get_next_positive_dentry(struct dentry *prev,
 	dget_dlock(ret);
 	spin_unlock(&ret->d_lock);
 	spin_unlock(&p->d_lock);
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->lookup_lock);
 
 	dput(prev);
 
@@ -290,11 +342,8 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	spin_lock(&sbi->fs_lock);
 	ino = autofs4_dentry_ino(root);
 	/* No point expiring a pending mount */
-	if (ino->flags & AUTOFS_INF_PENDING) {
-		spin_unlock(&sbi->fs_lock);
-		return NULL;
-	}
-	managed_dentry_set_transit(root);
+	if (ino->flags & AUTOFS_INF_PENDING)
+		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 		struct autofs_info *ino = autofs4_dentry_ino(root);
 		ino->flags |= AUTOFS_INF_EXPIRING;
@@ -302,7 +351,7 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 		spin_unlock(&sbi->fs_lock);
 		return root;
 	}
-	managed_dentry_clear_transit(root);
+out:
 	spin_unlock(&sbi->fs_lock);
 	dput(root);
 
@@ -336,13 +385,12 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	timeout = sbi->exp_timeout;
 
 	dentry = NULL;
-	while ((dentry = get_next_positive_dentry(dentry, root))) {
+	while ((dentry = get_next_positive_subdir(dentry, root))) {
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
 		/* No point expiring a pending mount */
 		if (ino->flags & AUTOFS_INF_PENDING)
-			goto cont;
-		managed_dentry_set_transit(dentry);
+			goto next;
 
 		/*
 		 * Case 1: (i) indirect mount or top level pseudo direct mount
@@ -402,8 +450,6 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 			}
 		}
 next:
-		managed_dentry_clear_transit(dentry);
-cont:
 		spin_unlock(&sbi->fs_lock);
 	}
 	return NULL;
@@ -415,13 +461,13 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	ino->flags |= AUTOFS_INF_EXPIRING;
 	init_completion(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
-	spin_lock(&autofs4_lock);
+	spin_lock(&sbi->lookup_lock);
 	spin_lock(&expired->d_parent->d_lock);
 	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
 	list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
 	spin_unlock(&expired->d_lock);
 	spin_unlock(&expired->d_parent->d_lock);
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->lookup_lock);
 	return expired;
 }
 
@@ -484,8 +530,6 @@ int autofs4_expire_run(struct super_block *sb,
 	spin_lock(&sbi->fs_lock);
 	ino = autofs4_dentry_ino(dentry);
 	ino->flags &= ~AUTOFS_INF_EXPIRING;
-	if (!d_unhashed(dentry))
-		managed_dentry_clear_transit(dentry);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -513,9 +557,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		spin_lock(&sbi->fs_lock);
 		ino->flags &= ~AUTOFS_INF_EXPIRING;
 		spin_lock(&dentry->d_lock);
-		if (ret)
-			__managed_dentry_clear_transit(dentry);
-		else {
+		if (!ret) {
 			if ((IS_ROOT(dentry) ||
 			    (autofs_type_indirect(sbi->type) &&
 			     IS_ROOT(dentry->d_parent))) &&

fs/autofs4/root.c

@@ -23,8 +23,6 @@
 
 #include "autofs_i.h"
 
-DEFINE_SPINLOCK(autofs4_lock);
-
 static int autofs4_dir_symlink(struct inode *,struct dentry *,const char *);
 static int autofs4_dir_unlink(struct inode *,struct dentry *);
 static int autofs4_dir_rmdir(struct inode *,struct dentry *);
@@ -125,15 +123,15 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
 	 * autofs file system so just let the libfs routines handle
 	 * it.
 	 */
-	spin_lock(&autofs4_lock);
+	spin_lock(&sbi->lookup_lock);
 	spin_lock(&dentry->d_lock);
 	if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
 		spin_unlock(&dentry->d_lock);
-		spin_unlock(&autofs4_lock);
+		spin_unlock(&sbi->lookup_lock);
 		return -ENOENT;
 	}
 	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->lookup_lock);
 
 out:
 	return dcache_dir_open(inode, file);
@@ -171,7 +169,6 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 	const unsigned char *str = name->name;
 	struct list_head *p, *head;
 
-	spin_lock(&autofs4_lock);
 	spin_lock(&sbi->lookup_lock);
 	head = &sbi->active_list;
 	list_for_each(p, head) {
@@ -204,14 +201,12 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 			dget_dlock(active);
 			spin_unlock(&active->d_lock);
 			spin_unlock(&sbi->lookup_lock);
-			spin_unlock(&autofs4_lock);
 			return active;
 		}
 next:
 		spin_unlock(&active->d_lock);
 	}
 	spin_unlock(&sbi->lookup_lock);
-	spin_unlock(&autofs4_lock);
 
 	return NULL;
 }
@@ -226,7 +221,6 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 	const unsigned char *str = name->name;
 	struct list_head *p, *head;
 
-	spin_lock(&autofs4_lock);
 	spin_lock(&sbi->lookup_lock);
 	head = &sbi->expiring_list;
 	list_for_each(p, head) {
@@ -259,14 +253,12 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 			dget_dlock(expiring);
 			spin_unlock(&expiring->d_lock);
 			spin_unlock(&sbi->lookup_lock);
-			spin_unlock(&autofs4_lock);
 			return expiring;
 		}
 next:
 		spin_unlock(&expiring->d_lock);
 	}
 	spin_unlock(&sbi->lookup_lock);
-	spin_unlock(&autofs4_lock);
 
 	return NULL;
 }
@@ -275,17 +267,16 @@ static int autofs4_mount_wait(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
-	int status;
+	int status = 0;
 
 	if (ino->flags & AUTOFS_INF_PENDING) {
 		DPRINTK("waiting for mount name=%.*s",
 			dentry->d_name.len, dentry->d_name.name);
 		status = autofs4_wait(sbi, dentry, NFY_MOUNT);
 		DPRINTK("mount wait done status=%d", status);
-		ino->last_used = jiffies;
-		return status;
 	}
-	return 0;
+	ino->last_used = jiffies;
+	return status;
 }
 
 static int do_expire_wait(struct dentry *dentry)
@@ -319,9 +310,12 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	 */
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
+		struct autofs_info *ino;
 		struct dentry *new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
+		ino = autofs4_dentry_ino(new);
+		ino->last_used = jiffies;
 		dput(path->dentry);
 		path->dentry = new;
 	}
@@ -338,18 +332,6 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 	DPRINTK("dentry=%p %.*s",
 		dentry, dentry->d_name.len, dentry->d_name.name);
 
-	/*
-	 * Someone may have manually umounted this or it was a submount
-	 * that has gone away.
-	 */
-	spin_lock(&dentry->d_lock);
-	if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
-		if (!(dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
-		     (dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
-			__managed_dentry_set_transit(path->dentry);
-	}
-	spin_unlock(&dentry->d_lock);
-
 	/* The daemon never triggers a mount. */
 	if (autofs4_oz_mode(sbi))
 		return NULL;
@@ -418,18 +400,17 @@ static struct vfsmount *autofs4_d_automount(struct path *path)
 done:
 	if (!(ino->flags & AUTOFS_INF_EXPIRING)) {
 		/*
-		 * Any needed mounting has been completed and the path updated
-		 * so turn this into a normal dentry so we don't continually
-		 * call ->d_automount() and ->d_manage().
-		 */
-		spin_lock(&dentry->d_lock);
-		__managed_dentry_clear_transit(dentry);
-		/*
+		 * Any needed mounting has been completed and the path
+		 * updated so clear DCACHE_NEED_AUTOMOUNT so we don't
+		 * call ->d_automount() on rootless multi-mounts since
+		 * it can lead to an incorrect ELOOP error return.
+		 *
 		 * Only clear DMANAGED_AUTOMOUNT for rootless multi-mounts and
 		 * symlinks as in all other cases the dentry will be covered by
 		 * an actual mount so ->d_automount() won't be called during
 		 * the follow.
 		 */
+		spin_lock(&dentry->d_lock);
 		if ((!d_mountpoint(dentry) &&
 		    !list_empty(&dentry->d_subdirs)) ||
 		    (dentry->d_inode && S_ISLNK(dentry->d_inode->i_mode)))
@@ -455,6 +436,8 @@ int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 
 	/* The daemon never waits. */
 	if (autofs4_oz_mode(sbi)) {
+		if (rcu_walk)
+			return 0;
 		if (!d_mountpoint(dentry))
 			return -EISDIR;
 		return 0;
@@ -612,12 +595,12 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
 
 	dir->i_mtime = CURRENT_TIME;
 
-	spin_lock(&autofs4_lock);
-	autofs4_add_expiring(dentry);
+	spin_lock(&sbi->lookup_lock);
+	__autofs4_add_expiring(dentry);
 	spin_lock(&dentry->d_lock);
 	__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->lookup_lock);
 
 	return 0;
 }
@@ -686,20 +669,17 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
 	if (!autofs4_oz_mode(sbi))
 		return -EACCES;
 
-	spin_lock(&autofs4_lock);
 	spin_lock(&sbi->lookup_lock);
 	spin_lock(&dentry->d_lock);
 	if (!list_empty(&dentry->d_subdirs)) {
 		spin_unlock(&dentry->d_lock);
 		spin_unlock(&sbi->lookup_lock);
-		spin_unlock(&autofs4_lock);
 		return -ENOTEMPTY;
 	}
 	__autofs4_add_expiring(dentry);
-	spin_unlock(&sbi->lookup_lock);
 	__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->lookup_lock);
 
 	if (sbi->version < 5)
 		autofs_clear_leaf_automount_flags(dentry);

fs/autofs4/waitq.c

@@ -197,12 +197,12 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
 
 	seq = read_seqbegin(&rename_lock);
 	rcu_read_lock();
-	spin_lock(&autofs4_lock);
+	spin_lock(&sbi->fs_lock);
 	for (tmp = dentry ; tmp != root ; tmp = tmp->d_parent)
 		len += tmp->d_name.len + 1;
 
 	if (!len || --len > NAME_MAX) {
-		spin_unlock(&autofs4_lock);
+		spin_unlock(&sbi->fs_lock);
 		rcu_read_unlock();
 		if (read_seqretry(&rename_lock, seq))
 			goto rename_retry;
@@ -218,7 +218,7 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
 		p -= tmp->d_name.len;
 		strncpy(p, tmp->d_name.name, tmp->d_name.len);
 	}
-	spin_unlock(&autofs4_lock);
+	spin_unlock(&sbi->fs_lock);
 	rcu_read_unlock();
 	if (read_seqretry(&rename_lock, seq))
 		goto rename_retry;

fs/block_dev.c

@@ -55,11 +55,13 @@ EXPORT_SYMBOL(I_BDEV);
 static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
-	spin_lock(&inode_lock);
+	spin_lock(&inode_wb_list_lock);
+	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
 	if (inode->i_state & I_DIRTY)
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&inode_wb_list_lock);
 }
 
 static sector_t max_block(struct block_device *bdev)

fs/buffer.c

@@ -1138,7 +1138,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and the global inode_lock.
+ * mapping->tree_lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
 {

fs/drop_caches.c

@@ -8,6 +8,7 @@
 #include <linux/writeback.h>
 #include <linux/sysctl.h>
 #include <linux/gfp.h>
+#include "internal.h"
 
 /* A global variable is a bit ugly, but it keeps the code simple */
 int sysctl_drop_caches;
@@ -16,20 +17,23 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 {
 	struct inode *inode, *toput_inode = NULL;
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_sb_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
-			continue;
-		if (inode->i_mapping->nrpages == 0)
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    (inode->i_mapping->nrpages == 0)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		__iget(inode);
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_sb_list_lock);
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);
 		toput_inode = inode;
-		spin_lock(&inode_lock);
+		spin_lock(&inode_sb_list_lock);
 	}
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_sb_list_lock);
 	iput(toput_inode);
 }
 

fs/internal.h

@@ -125,6 +125,13 @@ extern long do_handle_open(int mountdirfd,
 /*
  * inode.c
  */
+extern spinlock_t inode_sb_list_lock;
+
+/*
+ * fs-writeback.c
+ */
+extern void inode_wb_list_del(struct inode *inode);
+
 extern int get_nr_dirty_inodes(void);
 extern void evict_inodes(struct super_block *);
 extern int invalidate_inodes(struct super_block *, bool);

fs/logfs/inode.c

@@ -293,7 +293,7 @@ static int logfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return ret;
 }
 
-/* called with inode_lock held */
+/* called with inode->i_lock held */
 static int logfs_drop_inode(struct inode *inode)
 {
 	struct logfs_super *super = logfs_super(inode->i_sb);

fs/namei.c

@@ -992,6 +992,12 @@ int follow_down_one(struct path *path)
 	return 0;
 }
 
+static inline bool managed_dentry_might_block(struct dentry *dentry)
+{
+	return (dentry->d_flags & DCACHE_MANAGE_TRANSIT &&
+		dentry->d_op->d_manage(dentry, true) < 0);
+}
+
 /*
  * Skip to top of mountpoint pile in rcuwalk mode.  We abort the rcu-walk if we
  * meet a managed dentry and we're not walking to "..".  True is returned to
@@ -1000,19 +1006,26 @@ int follow_down_one(struct path *path)
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			       struct inode **inode, bool reverse_transit)
 {
-	while (d_mountpoint(path->dentry)) {
+	for (;;) {
 		struct vfsmount *mounted;
-		if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
-		    !reverse_transit &&
-		    path->dentry->d_op->d_manage(path->dentry, true) < 0)
+		/*
+		 * Don't forget we might have a non-mountpoint managed dentry
+		 * that wants to block transit.
+		 */
+		*inode = path->dentry->d_inode;
+		if (!reverse_transit &&
+		     unlikely(managed_dentry_might_block(path->dentry)))
 			return false;
+
+		if (!d_mountpoint(path->dentry))
+			break;
+
 		mounted = __lookup_mnt(path->mnt, path->dentry, 1);
 		if (!mounted)
 			break;
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
-		*inode = path->dentry->d_inode;
 	}
 
 	if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))

fs/notify/inode_mark.c

@@ -22,13 +22,14 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
-#include <linux/writeback.h> /* for inode_lock */
 
 #include <asm/atomic.h>
 
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
 
+#include "../internal.h"
+
 /*
  * Recalculate the mask of events relevant to a given inode locked.
  */
@@ -237,15 +238,14 @@ 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)
  *
- * Called with inode_lock held, protecting the unmounting super block's list
- * of inodes, and with iprune_mutex held, keeping shrink_icache_memory() at bay.
- * We temporarily drop inode_lock, however, and CAN block.
+ * 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.
  */
 void fsnotify_unmount_inodes(struct list_head *list)
 {
 	struct inode *inode, *next_i, *need_iput = NULL;
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_sb_list_lock);
 	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
 		struct inode *need_iput_tmp;
 
@@ -254,8 +254,11 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		 * I_WILL_FREE, or I_NEW which is fine because by that point
 		 * the inode cannot have any associated watches.
 		 */
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 
 		/*
 		 * If i_count is zero, the inode cannot have any watches and
@@ -263,8 +266,10 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		 * evict all inodes with zero i_count from icache which is
 		 * unnecessarily violent and may in fact be illegal to do.
 		 */
-		if (!atomic_read(&inode->i_count))
+		if (!atomic_read(&inode->i_count)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 
 		need_iput_tmp = need_iput;
 		need_iput = NULL;
@@ -274,22 +279,25 @@ void fsnotify_unmount_inodes(struct list_head *list)
 			__iget(inode);
 		else
 			need_iput_tmp = NULL;
+		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
 		if ((&next_i->i_sb_list != list) &&
-		    atomic_read(&next_i->i_count) &&
-		    !(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
-			__iget(next_i);
-			need_iput = next_i;
+		    atomic_read(&next_i->i_count)) {
+			spin_lock(&next_i->i_lock);
+			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+				__iget(next_i);
+				need_iput = next_i;
+			}
+			spin_unlock(&next_i->i_lock);
 		}
 
 		/*
-		 * We can safely drop inode_lock here because we hold
+		 * We can safely drop inode_sb_list_lock here because we hold
 		 * references on both inode and next_i.  Also no new inodes
-		 * will be added since the umount has begun.  Finally,
-		 * iprune_mutex keeps shrink_icache_memory() away.
+		 * will be added since the umount has begun.
 		 */
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode_sb_list_lock);
 
 		if (need_iput_tmp)
 			iput(need_iput_tmp);
@@ -301,7 +309,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
 
 		iput(inode);
 
-		spin_lock(&inode_lock);
+		spin_lock(&inode_sb_list_lock);
 	}
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_sb_list_lock);
 }

fs/notify/mark.c

@@ -91,7 +91,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/srcu.h>
-#include <linux/writeback.h> /* for inode_lock */
 
 #include <asm/atomic.h>
 

fs/notify/vfsmount_mark.c

@@ -23,7 +23,6 @@
 #include <linux/mount.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
-#include <linux/writeback.h> /* for inode_lock */
 
 #include <asm/atomic.h>
 

fs/ntfs/inode.c

@@ -54,7 +54,7 @@
  *
  * Return 1 if the attributes match and 0 if not.
  *
- * NOTE: This function runs with the inode_lock spin lock held so it is not
+ * NOTE: This function runs with the inode->i_lock spin lock held so it is not
  * allowed to sleep.
  */
 int ntfs_test_inode(struct inode *vi, ntfs_attr *na)
@@ -98,7 +98,7 @@ int ntfs_test_inode(struct inode *vi, ntfs_attr *na)
  *
  * Return 0 on success and -errno on error.
  *
- * NOTE: This function runs with the inode_lock spin lock held so it is not
+ * NOTE: This function runs with the inode->i_lock spin lock held so it is not
  * allowed to sleep. (Hence the GFP_ATOMIC allocation.)
  */
 static int ntfs_init_locked_inode(struct inode *vi, ntfs_attr *na)

fs/quota/dquot.c

@@ -76,7 +76,7 @@
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
 #include <linux/quotaops.h>
-#include <linux/writeback.h> /* for inode_lock, oddly enough.. */
+#include "../internal.h" /* ugh */
 
 #include <asm/uaccess.h>
 
@@ -900,33 +900,38 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	int reserved = 0;
 #endif
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_sb_list_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    !atomic_read(&inode->i_writecount) ||
+		    !dqinit_needed(inode, type)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 #ifdef CONFIG_QUOTA_DEBUG
 		if (unlikely(inode_get_rsv_space(inode) > 0))
 			reserved = 1;
 #endif
-		if (!atomic_read(&inode->i_writecount))
-			continue;
-		if (!dqinit_needed(inode, type))
-			continue;
-
 		__iget(inode);
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_sb_list_lock);
 
 		iput(old_inode);
 		__dquot_initialize(inode, type);
-		/* We hold a reference to 'inode' so it couldn't have been
-		 * removed from s_inodes list while we dropped the inode_lock.
-		 * We cannot iput the inode now as we can be holding the last
-		 * reference and we cannot iput it under inode_lock. So we
-		 * keep the reference and iput it later. */
+
+		/*
+		 * 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
+		 * holding the last reference and we cannot iput it under
+		 * inode_sb_list_lock. So we keep the reference and iput it
+		 * later.
+		 */
 		old_inode = inode;
-		spin_lock(&inode_lock);
+		spin_lock(&inode_sb_list_lock);
 	}
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_sb_list_lock);
 	iput(old_inode);
 
 #ifdef CONFIG_QUOTA_DEBUG
@@ -1007,7 +1012,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 	struct inode *inode;
 	int reserved = 0;
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_sb_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
@@ -1021,7 +1026,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
 			remove_inode_dquot_ref(inode, type, tofree_head);
 		}
 	}
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_sb_list_lock);
 #ifdef CONFIG_QUOTA_DEBUG
 	if (reserved) {
 		printk(KERN_WARNING "VFS (%s): Writes happened after quota"

include/linux/fs.h

@@ -1636,7 +1636,7 @@ struct super_operations {
 };
 
 /*
- * Inode state bits.  Protected by inode_lock.
+ * Inode state bits.  Protected by inode->i_lock
  *
  * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
  * I_DIRTY_DATASYNC and I_DIRTY_PAGES.

include/linux/quotaops.h

@@ -277,7 +277,7 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr)
 		/*
 		 * Mark inode fully dirty. Since we are allocating blocks, inode
 		 * would become fully dirty soon anyway and it reportedly
-		 * reduces inode_lock contention.
+		 * reduces lock contention.
 		 */
 		mark_inode_dirty(inode);
 	}

include/linux/writeback.h

@@ -9,7 +9,7 @@
 
 struct backing_dev_info;
 
-extern spinlock_t inode_lock;
+extern spinlock_t inode_wb_list_lock;
 
 /*
  * fs/fs-writeback.c

mm/backing-dev.c

@@ -67,14 +67,14 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	struct inode *inode;
 
 	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
-	spin_lock(&inode_lock);
+	spin_lock(&inode_wb_list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_wb_list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
@@ -676,11 +676,11 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_lock);
+		spin_lock(&inode_wb_list_lock);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode_wb_list_lock);
 	}
 
 	bdi_unregister(bdi);

mm/filemap.c

@@ -80,8 +80,8 @@
  *  ->i_mutex
  *    ->i_alloc_sem             (various)
  *
- *  ->inode_lock
- *    ->sb_lock			(fs/fs-writeback.c)
+ *  inode_wb_list_lock
+ *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
  *  ->i_mmap_lock
@@ -98,8 +98,10 @@
  *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode_lock		(page_remove_rmap->set_page_dirty)
- *    ->inode_lock		(zap_pte_range->set_page_dirty)
+ *    inode_wb_list_lock	(page_remove_rmap->set_page_dirty)
+ *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
+ *    inode_wb_list_lock	(zap_pte_range->set_page_dirty)
+ *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
  *  (code doesn't rely on that order, so you could switch it around)

mm/rmap.c

@@ -31,11 +31,12 @@
  *             swap_lock (in swap_duplicate, swap_info_get)
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
- *               inode_lock (in set_page_dirty's __mark_inode_dirty)
+ *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
+ *               inode_wb_list_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
- *                           within inode_lock in __sync_single_inode)
+ *                           within inode_wb_list_lock in __sync_single_inode)
  *
  * (code doesn't rely on that order so it could be switched around)
  * ->tasklist_lock