Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

92 files changed, 5259 insertions, 3261 deletions

diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index a76803108d0..b7ff33c6310 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -186,6 +186,8 @@ int autofs4_expire_wait(struct dentry *dentry);
 int autofs4_expire_run(struct super_block *, struct vfsmount *,
 			struct autofs_sb_info *,
 			struct autofs_packet_expire __user *);
+int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
+			    struct autofs_sb_info *sbi, int when);
 int autofs4_expire_multi(struct super_block *, struct vfsmount *,
 			struct autofs_sb_info *, int __user *);
 struct dentry *autofs4_expire_direct(struct super_block *sb,
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 025e105bffe..9e5ae8a4f5c 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -525,40 +525,13 @@ static int autofs_dev_ioctl_expire(struct file *fp,
 				   struct autofs_sb_info *sbi,
 				   struct autofs_dev_ioctl *param)
 {
-	struct dentry *dentry;
 	struct vfsmount *mnt;
-	int err = -EAGAIN;
 	int how;
 
 	how = param->expire.how;
 	mnt = fp->f_path.mnt;
 
-	if (autofs_type_trigger(sbi->type))
-		dentry = autofs4_expire_direct(sbi->sb, mnt, sbi, how);
-	else
-		dentry = autofs4_expire_indirect(sbi->sb, mnt, sbi, how);
-
-	if (dentry) {
-		struct autofs_info *ino = autofs4_dentry_ino(dentry);
-
-		/*
-		 * This is synchronous because it makes the daemon a
-		 * little easier
-		*/
-		err = autofs4_wait(sbi, dentry, NFY_EXPIRE);
-
-		spin_lock(&sbi->fs_lock);
-		if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
-			ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
-			sbi->sb->s_root->d_mounted++;
-		}
-		ino->flags &= ~AUTOFS_INF_EXPIRING;
-		complete_all(&ino->expire_complete);
-		spin_unlock(&sbi->fs_lock);
-		dput(dentry);
-	}
-
-	return err;
+	return autofs4_do_expire_multi(sbi->sb, mnt, sbi, how);
 }
 
 /* Check if autofs mount point is in use */
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index e3bd50776f9..75f7ddacf7d 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -478,22 +478,16 @@ int autofs4_expire_run(struct super_block *sb,
 	return ret;
 }
 
-/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
-   more to be done */
-int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
-			struct autofs_sb_info *sbi, int __user *arg)
+int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
+			    struct autofs_sb_info *sbi, int when)
 {
 	struct dentry *dentry;
 	int ret = -EAGAIN;
-	int do_now = 0;
-
-	if (arg && get_user(do_now, arg))
-		return -EFAULT;
 
 	if (autofs_type_trigger(sbi->type))
-		dentry = autofs4_expire_direct(sb, mnt, sbi, do_now);
+		dentry = autofs4_expire_direct(sb, mnt, sbi, when);
 	else
-		dentry = autofs4_expire_indirect(sb, mnt, sbi, do_now);
+		dentry = autofs4_expire_indirect(sb, mnt, sbi, when);
 
 	if (dentry) {
 		struct autofs_info *ino = autofs4_dentry_ino(dentry);
@@ -516,3 +510,16 @@ int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 	return ret;
 }
 
+/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
+   more to be done */
+int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
+			struct autofs_sb_info *sbi, int __user *arg)
+{
+	int do_now = 0;
+
+	if (arg && get_user(do_now, arg))
+		return -EFAULT;
+
+	return autofs4_do_expire_multi(sb, mnt, sbi, do_now);
+}
+
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 74b1469a950..e383bf0334f 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -485,22 +485,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
 	DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
 		 current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
 
-	expiring = autofs4_lookup_expiring(sbi, dentry->d_parent, &dentry->d_name);
-	if (expiring) {
-		/*
-		 * If we are racing with expire the request might not
-		 * be quite complete but the directory has been removed
-		 * so it must have been successful, so just wait for it.
-		 */
-		ino = autofs4_dentry_ino(expiring);
-		autofs4_expire_wait(expiring);
-		spin_lock(&sbi->lookup_lock);
-		if (!list_empty(&ino->expiring))
-			list_del_init(&ino->expiring);
-		spin_unlock(&sbi->lookup_lock);
-		dput(expiring);
-	}
-
 	unhashed = autofs4_lookup_active(sbi, dentry->d_parent, &dentry->d_name);
 	if (unhashed)
 		dentry = unhashed;
@@ -538,14 +522,31 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
 	}
 
 	if (!oz_mode) {
+		mutex_unlock(&dir->i_mutex);
+		expiring = autofs4_lookup_expiring(sbi,
+						   dentry->d_parent,
+						   &dentry->d_name);
+		if (expiring) {
+			/*
+			 * If we are racing with expire the request might not
+			 * be quite complete but the directory has been removed
+			 * so it must have been successful, so just wait for it.
+			 */
+			ino = autofs4_dentry_ino(expiring);
+			autofs4_expire_wait(expiring);
+			spin_lock(&sbi->lookup_lock);
+			if (!list_empty(&ino->expiring))
+				list_del_init(&ino->expiring);
+			spin_unlock(&sbi->lookup_lock);
+			dput(expiring);
+		}
+
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags |= DCACHE_AUTOFS_PENDING;
 		spin_unlock(&dentry->d_lock);
-		if (dentry->d_op && dentry->d_op->d_revalidate) {
-			mutex_unlock(&dir->i_mutex);
+		if (dentry->d_op && dentry->d_op->d_revalidate)
 			(dentry->d_op->d_revalidate)(dentry, nd);
-			mutex_lock(&dir->i_mutex);
-		}
+		mutex_lock(&dir->i_mutex);
 	}
 
 	/*
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index d2cf5a54a4b..9adf5e4f7e9 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -8,7 +8,7 @@ btrfs-y := super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   ref-cache.o export.o tree-log.o acl.o free-space-cache.o zlib.o \
-	   compression.o
+	   compression.o delayed-ref.o
 else
 
 # Normal Makefile
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 72677ce2b74..b30986f00b9 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -66,6 +66,12 @@ struct btrfs_inode {
 	 */
 	struct list_head delalloc_inodes;
 
+	/*
+	 * list for tracking inodes that must be sent to disk before a
+	 * rename or truncate commit
+	 */
+	struct list_head ordered_operations;
+
 	/* the space_info for where this inode's data allocations are done */
 	struct btrfs_space_info *space_info;
 
@@ -86,12 +92,6 @@ struct btrfs_inode {
 	 */
 	u64 logged_trans;
 
-	/*
-	 * trans that last made a change that should be fully fsync'd.  This
-	 * gets reset to zero each time the inode is logged
-	 */
-	u64 log_dirty_trans;
-
 	/* total number of bytes pending delalloc, used by stat to calc the
 	 * real block usage of the file
 	 */
@@ -121,6 +121,25 @@ struct btrfs_inode {
 	/* the start of block group preferred for allocations. */
 	u64 block_group;
 
+	/* the fsync log has some corner cases that mean we have to check
+	 * directories to see if any unlinks have been done before
+	 * the directory was logged.  See tree-log.c for all the
+	 * details
+	 */
+	u64 last_unlink_trans;
+
+	/*
+	 * ordered_data_close is set by truncate when a file that used
+	 * to have good data has been truncated to zero.  When it is set
+	 * the btrfs file release call will add this inode to the
+	 * ordered operations list so that we make sure to flush out any
+	 * new data the application may have written before commit.
+	 *
+	 * yes, its silly to have a single bitflag, but we might grow more
+	 * of these.
+	 */
+	unsigned ordered_data_close:1;
+
 	struct inode vfs_inode;
 };
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 37f31b5529a..dbb72412463 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -254,18 +254,13 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
  * empty_size -- a hint that you plan on doing more cow.  This is the size in
  * bytes the allocator should try to find free next to the block it returns.
  * This is just a hint and may be ignored by the allocator.
- *
- * prealloc_dest -- if you have already reserved a destination for the cow,
- * this uses that block instead of allocating a new one.
- * btrfs_alloc_reserved_extent is used to finish the allocation.
  */
 static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct extent_buffer *buf,
 			     struct extent_buffer *parent, int parent_slot,
 			     struct extent_buffer **cow_ret,
-			     u64 search_start, u64 empty_size,
-			     u64 prealloc_dest)
+			     u64 search_start, u64 empty_size)
 {
 	u64 parent_start;
 	struct extent_buffer *cow;
@@ -291,26 +286,10 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	level = btrfs_header_level(buf);
 	nritems = btrfs_header_nritems(buf);
 
-	if (prealloc_dest) {
-		struct btrfs_key ins;
-
-		ins.objectid = prealloc_dest;
-		ins.offset = buf->len;
-		ins.type = BTRFS_EXTENT_ITEM_KEY;
-
-		ret = btrfs_alloc_reserved_extent(trans, root, parent_start,
-						  root->root_key.objectid,
-						  trans->transid, level, &ins);
-		BUG_ON(ret);
-		cow = btrfs_init_new_buffer(trans, root, prealloc_dest,
-					    buf->len, level);
-	} else {
-		cow = btrfs_alloc_free_block(trans, root, buf->len,
-					     parent_start,
-					     root->root_key.objectid,
-					     trans->transid, level,
-					     search_start, empty_size);
-	}
+	cow = btrfs_alloc_free_block(trans, root, buf->len,
+				     parent_start, root->root_key.objectid,
+				     trans->transid, level,
+				     search_start, empty_size);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -413,7 +392,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, struct extent_buffer *buf,
 		    struct extent_buffer *parent, int parent_slot,
-		    struct extent_buffer **cow_ret, u64 prealloc_dest)
+		    struct extent_buffer **cow_ret)
 {
 	u64 search_start;
 	int ret;
@@ -436,7 +415,6 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 	    btrfs_header_owner(buf) == root->root_key.objectid &&
 	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
 		*cow_ret = buf;
-		WARN_ON(prealloc_dest);
 		return 0;
 	}
 
@@ -447,8 +425,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 	btrfs_set_lock_blocking(buf);
 
 	ret = __btrfs_cow_block(trans, root, buf, parent,
-				 parent_slot, cow_ret, search_start, 0,
-				 prealloc_dest);
+				 parent_slot, cow_ret, search_start, 0);
 	return ret;
 }
 
@@ -617,7 +594,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 		err = __btrfs_cow_block(trans, root, cur, parent, i,
 					&cur, search_start,
 					min(16 * blocksize,
-					    (end_slot - i) * blocksize), 0);
+					    (end_slot - i) * blocksize));
 		if (err) {
 			btrfs_tree_unlock(cur);
 			free_extent_buffer(cur);
@@ -937,7 +914,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		BUG_ON(!child);
 		btrfs_tree_lock(child);
 		btrfs_set_lock_blocking(child);
-		ret = btrfs_cow_block(trans, root, child, mid, 0, &child, 0);
+		ret = btrfs_cow_block(trans, root, child, mid, 0, &child);
 		BUG_ON(ret);
 
 		spin_lock(&root->node_lock);
@@ -945,6 +922,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		spin_unlock(&root->node_lock);
 
 		ret = btrfs_update_extent_ref(trans, root, child->start,
+					      child->len,
 					      mid->start, child->start,
 					      root->root_key.objectid,
 					      trans->transid, level - 1);
@@ -971,6 +949,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 	    BTRFS_NODEPTRS_PER_BLOCK(root) / 4)
 		return 0;
 
+	if (trans->transaction->delayed_refs.flushing &&
+	    btrfs_header_nritems(mid) > 2)
+		return 0;
+
 	if (btrfs_header_nritems(mid) < 2)
 		err_on_enospc = 1;
 
@@ -979,7 +961,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		btrfs_tree_lock(left);
 		btrfs_set_lock_blocking(left);
 		wret = btrfs_cow_block(trans, root, left,
-				       parent, pslot - 1, &left, 0);
+				       parent, pslot - 1, &left);
 		if (wret) {
 			ret = wret;
 			goto enospc;