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()

27 files changed, 615 insertions, 536 deletions

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 2e994efe12c..61b31acb917 100644
--- a/Documentation/filesystems/Locking
+++ b/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
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 0c986c9e851..6e29954851a 100644
--- a/Documentation/filesystems/porting
+++ b/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
@@ -397,6 +400,9 @@ a file off.
 
 --
 [mandatory]
+
+--
+[mandatory]
 	->get_sb() is gone.  Switch to use of ->mount().  Typically it's just
 a matter of switching from calling get_sb_... to mount_... and changing the
 function type.  If you were doing it manually, just switch from setting ->mnt_root
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 306f0ae8df0..80815ed654c 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/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
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 54f92379272..475f9c597cb 100644
--- a/fs/autofs4/autofs_i.h
+++ b/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
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 1442da4860e..509fe1eb66a 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/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);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index f43100b9662..450f529a4ea 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -87,18 +87,70 @@ done:
 }
 
 /*
+ * 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 @@ again:
 
 			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 @@ again:
 	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 @@ found:
 	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))) &&
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index e6f84d26f4c..96804a17bbd 100644
--- a/fs/autofs4/root.c
+++ b/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);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 56010056b2e..25435987d6a 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -197,12 +197,12 @@ rename_retry:
 
 	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 @@ rename_retry:
 		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;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7d02afb2b7f..c1511c674f5 100644
--- a/fs/block_dev.c
+++ b/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)
diff --git a/fs/buffer.c b/fs/buffer.c
index 2e6b1a387b7..a08bb8e61c6 100644
--- a/fs/buffer.c
+++ b/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)
 {
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 816f88e6b9c..98b77c89494 100644
--- a/fs/drop_caches.c
+++ b/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);
 }
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 59c6e495678..b5ed541fb13 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -176,6 +176,17 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 }
 
 /*
+ * Remove the inode from the writeback list it is on.
+ */
+void inode_wb_list_del(struct inode *inode)
+{
+	spin_lock(&inode_wb_list_lock);
+	list_del_init(&inode->i_wb_list);
+	spin_unlock(&inode_wb_list_lock);
+}
+
+
+/*
  * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
  * furthest end of its superblock's dirty-inode list.
  *
@@ -188,6 +199,7 @@ static void redirty_tail(struct inode *inode)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 
+	assert_spin_locked(&inode_wb_list_lock);
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
@@ -205,14 +217,17 @@ static void requeue_io(struct inode *inode)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 
+	assert_spin_locked(&inode_wb_list_lock);
 	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
 {
 	/*
-	 * Prevent speculative execution through spin_unlock(&inode_lock);
+	 * Prevent speculative execution through
+	 * spin_unlock(&inode_wb_list_lock);
 	 */
+
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_SYNC);
 }
@@ -286,6 +301,7 @@ static void move_expired_inodes(struct list_head *delaying_queue,
  */
 static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
 {
+	assert_spin_locked(&inode_wb_list_lock);
 	list_splice_init(&wb->b_more_io, &wb->b_io);
 	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
 }
@@ -306,25 +322,25 @@ static void inode_wait_for_writeback(struct inode *inode)
 	wait_queue_head_t *wqh;
 
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	 while (inode->i_state & I_SYNC) {
-		spin_unlock(&inode_lock);
+	while (inode->i_state & I_SYNC) {
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_wb_list_lock);
 		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
-		spin_lock(&inode_lock);
+		spin_lock(&inode_wb_list_lock);
+		spin_lock(&inode->i_lock);
 	}
 }
 
 /*
- * Write out an inode's dirty pages.  Called under inode_lock.  Either the
- * caller has ref on the inode (either via __iget or via syscall against an fd)
- * or the inode has I_WILL_FREE set (via generic_forget_inode)
+ * Write out an inode's dirty pages.  Called under inode_wb_list_lock and
+ * inode->i_lock.  Either the caller has an active reference on the inode or
+ * the inode has I_WILL_FREE set.
  *
  * If `wait' is set, wait on the writeout.
  *
  * The whole writeout design is quite complex and fragile.  We want to avoid
  * starvation of particular inodes when others are being redirtied, prevent
  * livelocks, etc.
- *
- * Called under inode_lock.
  */
 static int
 writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
@@ -333,6 +349,9 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	unsigned dirty;
 	int ret;
 
+	assert_spin_locked(&inode_wb_list_lock);
+	assert_spin_locked(&inode->i_lock);
+
 	if (!atomic_read(&inode->i_count))
 		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
 	else
@@ -363,7 +382,8 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	/* Set I_SYNC, reset I_DIRTY_PAGES */
 	inode->i_state |= I_SYNC;
 	inode->i_state &= ~I_DIRTY_PAGES;
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode->i_lock);
+	spin_unlock(&inode_wb_list_lock);
 
 	ret = do_writepages(mapping, wbc);
 
@@ -383,10 +403,10 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	 * due to delalloc, clear dirty metadata flags right before
 	 * write_inode()
 	 */
-	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	dirty = inode->i_state & I_DIRTY;
 	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode->i_lock);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
 		int err = write_inode(inode, wbc);
@@ -394,7 +414,8 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			ret = err;
 	}
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_wb_list_lock);
+	spin_lock(&inode->i_lock);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
 		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
@@ -506,7 +527,9 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		 * kind does not need peridic writeout yet, and for the latter
 		 * kind writeout is handled by the freer.
 		 */
+		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			spin_unlock(&inode->i_lock);
 			requeue_io(inode);
 			continue;
 		}
@@ -515,10 +538,13 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
 		 */
-		if (inode_dirtied_after(inode, wbc->wb_start))
+		if (inode_dirtied_after(inode, wbc->wb_start)) {
+			spin_unlock(&inode->i_lock);
 			return 1;
+		}
 
 		__iget(inode);
+
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
 		if (wbc->pages_skipped != pages_skipped) {
@@ -528,10 +554,11 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 			 */
 			redirty_tail(inode);
 		}
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&inode_wb_list_lock);
 		iput(inode);
 		cond_resched();
-		spin_lock(&inode_lock);
+		spin_lock(&inode_wb_list_lock);
 		if (wbc->nr_to_write <= 0) {
 			wbc->more_io = 1;
 			return 1;
@@ -550,7 +577,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 
 	if (!wbc->wb_start)
 		wbc->wb_start = jiffies; /* livelock avoidance */
-	spin_lock(&inode_lock);
+	spin_lock(&inode_wb_list_lock);
 	if (!wbc->for_kupdate || list_empty(&wb->b_io))
 		queue_io(wb, wbc->older_than_this);
 
@@ -568,7 +595,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 		if (ret)
 			break;
 	}
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_wb_list_lock);
 	/* Leave any unwritten inodes on b_io */
 }
 
@@ -577,11 +604,11 @@ static void __writeback_inodes_sb(struct super_block *sb,
 {
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode_wb_list_lock);
 	if (!wbc->for_kupdate || list_empty(&wb->b_io))
 		queue_io(wb, wbc->older_than_this);
 	writeback_sb_inodes(sb, wb, wbc, true);
-	spin_unlock(&inode_lock);
+	spin_unlock(&inode_wb_list_lock);
 }
 
 /*
@@ -720,13 +747,15 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 * become available for writeback. Otherwise
 		 * we'll just busyloop.
 		 */
-		spin_lock(&inode_lock);
+		spin_lock(&inode_wb_list_lock);
 		if (!list_empty(&wb->b_more_io))  {
 			inode = wb_inode(wb->b_more_io.prev);
 			trace_wbc_writeback_wait(&wbc, wb->bdi);
+			spin_lock(&inode->i_lock);
 			inode_wait_for_writeback(inode);
+			spin_unlock(&inode->i_lock);
 		}
-		spin_unlock(&inode_lock);
+		spin_unlock(&inode_wb_list_lock);
 	}
 
 	return wrote;
@@ -992,7 +1021,6 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 {
 	struct super_block *sb = inode->i_sb;
 	struct backing_dev_info *bdi = NULL;
-	bool wakeup_bdi = false;
 
 	/*
 	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
@@ -1016,7 +1044,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 	if (unlikely(block_dump))
 		block_dump___mark_inode_dirty(inode);
 
-	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
@@ -1028,7 +1056,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * superblock list, based upon its state.
 		 */
 		if (inode->i_state & I_SYNC)
-			goto out;
+			goto out_unlock_inode;
 
 		/*
 		 * Only add valid (hashed) inodes to the superblock's