Merge branch 'master' into upstream.

This is sync with Linus' tree to receive KEY_IMAGES definition
that went in through input tree.

30 files changed, 2095 insertions, 1221 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 9c949348510..44ea5b92e1b 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -170,7 +170,7 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
 	int ret;
 	struct posix_acl *acl = NULL;
 
-	if (!is_owner_or_cap(dentry->d_inode))
+	if (!inode_owner_or_capable(dentry->d_inode))
 		return -EPERM;
 
 	if (!IS_POSIXACL(dentry->d_inode))
@@ -178,16 +178,18 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
 
 	if (value) {
 		acl = posix_acl_from_xattr(value, size);
-		if (acl == NULL) {
-			value = NULL;
-			size = 0;
-		} else if (IS_ERR(acl)) {
+		if (IS_ERR(acl))
 			return PTR_ERR(acl);
+
+		if (acl) {
+			ret = posix_acl_valid(acl);
+			if (ret)
+				goto out;
 		}
 	}
 
 	ret = btrfs_set_acl(NULL, dentry->d_inode, acl, type);
-
+out:
 	posix_acl_release(acl);
 
 	return ret;
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index ccc991c542d..57c3bb2884c 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -136,9 +136,8 @@ struct btrfs_inode {
 	 * items we think we'll end up using, and reserved_extents is the number
 	 * of extent items we've reserved metadata for.
 	 */
-	spinlock_t accounting_lock;
 	atomic_t outstanding_extents;
-	int reserved_extents;
+	atomic_t reserved_extents;
 
 	/*
 	 * ordered_data_close is set by truncate when a file that used
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 4d2110eafe2..41d1d7c70e2 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -340,6 +340,8 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 	WARN_ON(start & ((u64)PAGE_CACHE_SIZE - 1));
 	cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
+	if (!cb)
+		return -ENOMEM;
 	atomic_set(&cb->pending_bios, 0);
 	cb->errors = 0;
 	cb->inode = inode;
@@ -354,6 +356,10 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 
 	bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
+	if(!bio) {
+		kfree(cb);
+		return -ENOMEM;
+	}
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
 	atomic_inc(&cb->pending_bios);
@@ -657,8 +663,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			atomic_inc(&cb->pending_bios);
 
 			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
-				btrfs_lookup_bio_sums(root, inode, comp_bio,
-						      sums);
+				ret = btrfs_lookup_bio_sums(root, inode,
+							comp_bio, sums);
+				BUG_ON(ret);
 			}
 			sums += (comp_bio->bi_size + root->sectorsize - 1) /
 				root->sectorsize;
@@ -683,8 +690,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
 	BUG_ON(ret);
 
-	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
-		btrfs_lookup_bio_sums(root, inode, comp_bio, sums);
+	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+		ret = btrfs_lookup_bio_sums(root, inode, comp_bio, sums);
+		BUG_ON(ret);
+	}
 
 	ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0);
 	BUG_ON(ret);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index b5baff0dccf..84d7ca1fe0b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -147,10 +147,11 @@ noinline void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p)
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
 {
 	struct extent_buffer *eb;
-	spin_lock(&root->node_lock);
-	eb = root->node;
+
+	rcu_read_lock();
+	eb = rcu_dereference(root->node);
 	extent_buffer_get(eb);
-	spin_unlock(&root->node_lock);
+	rcu_read_unlock();
 	return eb;
 }
 
@@ -165,14 +166,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
 	while (1) {
 		eb = btrfs_root_node(root);
 		btrfs_tree_lock(eb);
-
-		spin_lock(&root->node_lock);
-		if (eb == root->node) {
-			spin_unlock(&root->node_lock);
+		if (eb == root->node)
 			break;
-		}
-		spin_unlock(&root->node_lock);
-
 		btrfs_tree_unlock(eb);
 		free_extent_buffer(eb);
 	}
@@ -458,10 +453,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 		else
 			parent_start = 0;
 
-		spin_lock(&root->node_lock);
-		root->node = cow;
 		extent_buffer_get(cow);
-		spin_unlock(&root->node_lock);
+		rcu_assign_pointer(root->node, cow);
 
 		btrfs_free_tree_block(trans, root, buf, parent_start,
 				      last_ref);
@@ -542,6 +535,9 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	ret = __btrfs_cow_block(trans, root, buf, parent,
 				 parent_slot, cow_ret, search_start, 0);
+
+	trace_btrfs_cow_block(root, buf, *cow_ret);
+
 	return ret;
 }
 
@@ -686,6 +682,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			if (!cur) {
 				cur = read_tree_block(root, blocknr,
 							 blocksize, gen);
+				if (!cur)
+					return -EIO;
 			} else if (!uptodate) {
 				btrfs_read_buffer(cur, gen);
 			}
@@ -732,122 +730,6 @@ static inline unsigned int leaf_data_end(struct btrfs_root *root,
 	return btrfs_item_offset_nr(leaf, nr - 1);
 }
 
-/*
- * extra debugging checks to make sure all the items in a key are
- * well formed and in the proper order
- */
-static int check_node(struct btrfs_root *root, struct btrfs_path *path,
-		      int level)
-{
-	struct extent_buffer *parent = NULL;
-	struct extent_buffer *node = path->nodes[level];
-	struct btrfs_disk_key parent_key;
-	struct btrfs_disk_key node_key;
-	int parent_slot;
-	int slot;
-	struct btrfs_key cpukey;
-	u32 nritems = btrfs_header_nritems(node);
-
-	if (path->nodes[level + 1])
-		parent = path->nodes[level + 1];
-
-	slot = path->slots[level];
-	BUG_ON(nritems == 0);
-	if (parent) {
-		parent_slot = path->slots[level + 1];
-		btrfs_node_key(parent, &parent_key, parent_slot);
-		btrfs_node_key(node, &node_key, 0);
-		BUG_ON(memcmp(&parent_key, &node_key,
-			      sizeof(struct btrfs_disk_key)));
-		BUG_ON(btrfs_node_blockptr(parent, parent_slot) !=
-		       btrfs_header_bytenr(node));
-	}
-	BUG_ON(nritems > BTRFS_NODEPTRS_PER_BLOCK(root));
-	if (slot != 0) {
-		btrfs_node_key_to_cpu(node, &cpukey, slot - 1);
-		btrfs_node_key(node, &node_key, slot);
-		BUG_ON(comp_keys(&node_key, &cpukey) <= 0);
-	}
-	if (slot < nritems - 1) {
-		btrfs_node_key_to_cpu(node, &cpukey, slot + 1);
-		btrfs_node_key(node, &node_key, slot);
-		BUG_ON(comp_keys(&node_key, &cpukey) >= 0);
-	}
-	return 0;
-}
-
-/*
- * extra checking to make sure all the items in a leaf are
- * well formed and in the proper order
- */
-static int check_leaf(struct btrfs_root *root, struct btrfs_path *path,
-		      int level)
-{
-	struct extent_buffer *leaf = path->nodes[level];
-	struct extent_buffer *parent = NULL;
-	int parent_slot;
-	struct btrfs_key cpukey;
-	struct btrfs_disk_key parent_key;
-	struct btrfs_disk_key leaf_key;
-	int slot = path->slots[0];
-
-	u32 nritems = btrfs_header_nritems(leaf);
-
-	if (path->nodes[level + 1])
-		parent = path->nodes[level + 1];
-
-	if (nritems == 0)
-		return 0;
-
-	if (parent) {
-		parent_slot = path->slots[level + 1];
-		btrfs_node_key(parent, &parent_key, parent_slot);
-		btrfs_item_key(leaf, &leaf_key, 0);
-
-		BUG_ON(memcmp(&parent_key, &leaf_key,
-		       sizeof(struct btrfs_disk_key)));
-		BUG_ON(btrfs_node_blockptr(parent, parent_slot) !=
-		       btrfs_header_bytenr(leaf));
-	}
-	if (slot != 0 && slot < nritems - 1) {
-		btrfs_item_key(leaf, &leaf_key, slot);
-		btrfs_item_key_to_cpu(leaf, &cpukey, slot - 1);
-		if (comp_keys(&leaf_key, &cpukey) <= 0) {
-			btrfs_print_leaf(root, leaf);
-			printk(KERN_CRIT "slot %d offset bad key\n", slot);
-			BUG_ON(1);
-		}
-		if (btrfs_item_offset_nr(leaf, slot - 1) !=
-		       btrfs_item_end_nr(leaf, slot)) {
-			btrfs_print_leaf(root, leaf);
-			printk(KERN_CRIT "slot %d offset bad\n", slot);
-			BUG_ON(1);
-		}
-	}
-	if (slot < nritems - 1) {
-		btrfs_item_key(leaf, &leaf_key, slot);
-		btrfs_item_key_to_cpu(leaf, &cpukey, slot + 1);
-		BUG_ON(comp_keys(&leaf_key, &cpukey) >= 0);
-		if (btrfs_item_offset_nr(leaf, slot) !=
-			btrfs_item_end_nr(leaf, slot + 1)) {
-			btrfs_print_leaf(root, leaf);
-			printk(KERN_CRIT "slot %d offset bad\n", slot);
-			BUG_ON(1);
-		}
-	}
-	BUG_ON(btrfs_item_offset_nr(leaf, 0) +
-	       btrfs_item_size_nr(leaf, 0) != BTRFS_LEAF_DATA_SIZE(root));
-	return 0;
-}
-
-static noinline int check_block(struct btrfs_root *root,
-				struct btrfs_path *path, int level)
-{
-	return 0;
-	if (level == 0)
-		return check_leaf(root, path, level);
-	return check_node(root, path, level);
-}
 
 /*
  * search for key in the extent_buffer.  The items start at offset p,
@@ -1046,9 +928,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 			goto enospc;
 		}
 
-		spin_lock(&root->node_lock);
-		root->node = child;
-		spin_unlock(&root->node_lock);
+		rcu_assign_pointer(root->node, child);
 
 		add_root_to_dirty_list(root);
 		btrfs_tree_unlock(child);
@@ -1188,7 +1068,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		}
 	}
 	/* double check we haven't messed things up */
-	check_block(root, path, level);
 	if (orig_ptr !=
 	    btrfs_node_blockptr(path->nodes[level], path->slots[level]))
 		BUG();
@@ -1798,12 +1677,6 @@ cow_done:
 		if (!cow)
 			btrfs_unlock_up_safe(p, level + 1);
 
-		ret = check_block(root, p, level);
-		if (ret) {
-			ret = -1;
-			goto done;
-		}
-
 		ret = bin_search(b, key, level, &slot);
 
 		if (level != 0) {
@@ -2130,10 +2003,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	btrfs_mark_buffer_dirty(c);
 
-	spin_lock(&root->node_lock);
 	old = root->node;
-	root->node = c;
-	spin_unlock(&root->node_lock);
+	rcu_assign_pointer(root->node, c);
 
 	/* the super has an extra ref to root->node */
 	free_extent_buffer(old);
@@ -3840,7 +3711,8 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
 	unsigned long ptr;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	ret = btrfs_insert_empty_item(trans, root, path, cpu_key, data_size);
 	if (!ret) {
 		leaf = path->nodes[0];
@@ -4217,6 +4089,7 @@ find_next_key:
 		}
 		btrfs_set_path_blocking(path);
 		cur = read_node_slot(root, cur, slot);
+		BUG_ON(!cur);
 
 		btrfs_tree_lock(cur);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7f78cc78fdd..8f4b81de3ae 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -28,6 +28,7 @@
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/kobject.h>
+#include <trace/events/btrfs.h>
 #include <asm/kmap_types.h>
 #include "extent_io.h"
 #include "extent_map.h"
@@ -40,6 +41,7 @@ extern struct kmem_cache *btrfs_trans_handle_cachep;
 extern struct kmem_cache *btrfs_transaction_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
+extern struct kmem_cache *btrfs_free_space_cachep;
 struct btrfs_ordered_sum;
 
 #define BTRFS_MAGIC "_BHRfS_M"
@@ -716,7 +718,7 @@ struct btrfs_space_info {
 	u64 total_bytes;	/* total bytes in the space,
 				   this doesn't take mirrors into account */
 	u64 bytes_used;		/* total bytes used,
-				   this does't take mirrors into account */
+				   this doesn't take mirrors into account */
 	u64 bytes_pinned;	/* total bytes pinned, will be freed when the
 				   transaction finishes */
 	u64 bytes_reserved;	/* total bytes the allocator has reserved for
@@ -738,8 +740,10 @@ struct btrfs_space_info {
 	 */
 	unsigned long reservation_progress;
 
-	int full;		/* indicates that we cannot allocate any more
+	int full:1;		/* indicates that we cannot allocate any more
 				   chunks for this space */
+	int chunk_alloc:1;	/* set if we are allocating a chunk */
+
 	int force_alloc;	/* set if we need to force a chunk alloc for
 				   this space */
 
@@ -782,9 +786,6 @@ struct btrfs_free_cluster {
 	/* first extent starting offset */
 	u64 window_start;
 
-	/* if this cluster simply points at a bitmap in the block group */
-	bool points_to_bitmap;
-
 	struct btrfs_block_group_cache *block_group;
 	/*
 	 * when a cluster is allocated from a block group, we put the
@@ -1283,6 +1284,9 @@ struct btrfs_root {
 #define BTRFS_INODE_NODUMP		(1 << 8)
 #define BTRFS_INODE_NOATIME		(1 << 9)
 #define BTRFS_INODE_DIRSYNC		(1 << 10)
+#define BTRFS_INODE_COMPRESS		(1 << 11)
+
+#define BTRFS_INODE_ROOT_ITEM_INIT	(1 << 31)
 
 /* some macros to generate set/get funcs for the struct fields.  This
  * assumes there is a lefoo_to_cpu for every type, so lets make a simple
@@ -2157,6 +2161,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      u64 root_objectid, u64 owner, u64 offset);
 
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
+				u64 num_bytes, int reserve, int sinfo);
 int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
@@ -2227,10 +2233,12 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_root *root,
 				   u64 start, u64 end);
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
-			       u64 num_bytes);
+			       u64 num_bytes, u64 *actual_bytes);
 int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root, u64 type);
+int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range);
 
+int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
@@ -2355,6 +2363,8 @@ int btrfs_find_dead_roots(struct btrfs_root *root, u64 objectid);
 int btrfs_find_orphan_roots(struct btrfs_root *tree_root);
 int btrfs_set_root_node(struct btrfs_root_item *item,
 			struct extent_buffer *node);
+void btrfs_check_and_init_root_item(struct btrfs_root_item *item);
+
 /* dir-item.c */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
@@ -2392,6 +2402,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 					  struct btrfs_path *path, u64 dir,
 					  const char *name, u16 name_len,
 					  int mod);
+int verify_dir_item(struct btrfs_root *root,
+		    struct extent_buffer *leaf,
+		    struct btrfs_dir_item *dir_item);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
@@ -2528,7 +2541,7 @@ int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct inode *inode);
 int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
 int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);
-void btrfs_orphan_cleanup(struct btrfs_root *root);
+int btrfs_orphan_cleanup(struct btrfs_root *root);
 void btrfs_orphan_pre_snapshot(struct btrfs_trans_handle *trans,
 				struct btrfs_pending_snapshot *pending,
 				u64 *bytes_to_reserve);
@@ -2536,7 +2549,7 @@ void btrfs_orphan_post_snapshot(struct btrfs_trans_handle *trans,
 				struct btrfs_pending_snapshot *pending);
 void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
-int btrfs_cont_expand(struct inode *inode, loff_t size);
+int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
 int btrfs_invalidate_inodes(struct btrfs_root *root);
 void btrfs_add_delayed_iput(struct inode *inode);
 void btrfs_run_delayed_iputs(struct btrfs_root *root);
@@ -2565,6 +2578,11 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct inode *inode, u64 start, u64 end);
 int btrfs_release_file(struct inode *inode, struct file *file);
+void btrfs_drop_pages(struct page **pages, size_t num_pages);
+int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
+		      struct page **pages, size_t num_pages,
+		      loff_t pos, size_t write_bytes,
+		      struct extent_state **cached);
 
 /* tree-defrag.c */
 int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e807b143b85..bce28f65389 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -483,6 +483,8 @@ static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	INIT_LIST_HEAD(&head_ref->cluster);
 	mutex_init(&head_ref->mutex);
 
+	trace_btrfs_delayed_ref_head(ref, head_ref, action);
+
 	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
 
 	if (existing) {
@@ -537,6 +539,8 @@ static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	}
 	full_ref->level = level;
 
+	trace_btrfs_delayed_tree_ref(ref, full_ref, action);
+
 	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
 
 	if (existing) {
@@ -591,6 +595,8 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	full_ref->objectid = owner;
 	full_ref->offset = offset;
 
+	trace_btrfs_delayed_data_ref(ref, full_ref, action);
+
 	existing = tree_insert(&delayed_refs->root, &ref->rb_node);
 
 	if (existing) {
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index f0cad5ae5be..c62f02f6ae6 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -151,7 +151,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 		ret = PTR_ERR(dir_item);
 		if (ret == -EEXIST)
 			goto second_insert;
-		goto out;
+		goto out_free;
 	}
 
 	leaf = path->nodes[0];
@@ -170,7 +170,7 @@ second_insert:
 	/* FIXME, use some real flag for selecting the extra index */
 	if (root == root->fs_info->tree_root) {
 		ret = 0;
-		goto out;
+		goto out_free;
 	}
 	btrfs_release_path(root, path);
 
@@ -180,7 +180,7 @@ second_insert:
 					name, name_len);
 	if (IS_ERR(dir_item)) {
 		ret2 = PTR_ERR(dir_item);
-		goto out;
+		goto out_free;
 	}
 	leaf = path->nodes[0];
 	btrfs_cpu_key_to_disk(&disk_key, location);
@@ -192,7 +192,9 @@ second_insert:
 	name_ptr = (unsigned long)(dir_item + 1);
 	write_extent_buffer(leaf, name, name_ptr, name_len);
 	btrfs_mark_buffer_dirty(leaf);
-out:
+
+out_free:
+
 	btrfs_free_path(path);
 	if (ret)
 		return ret;
@@ -377,6 +379,9 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
 
 	leaf = path->nodes[0];
 	dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
+	if (verify_dir_item(root, leaf, dir_item))
+		return NULL;
+
 	total_len = btrfs_item_size_nr(leaf, path->slots[0]);
 	while (cur < total_len) {
 		this_len = sizeof(*dir_item) +
@@ -429,3 +434,35 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
 	}
 	return ret;
 }
+
+int verify_dir_item(struct btrfs_root *root,
+		    struct extent_buffer *leaf,
+		    struct btrfs_dir_item *dir_item)
+{
+	u16 namelen = BTRFS_NAME_LEN;
+	u8 type = btrfs_dir_type(leaf, dir_item);
+
+	if (type >= BTRFS_FT_MAX) {
+		printk(KERN_CRIT "btrfs: invalid dir item type: %d\n",
+		       (int)type);
+		return 1;
+	}
+
+	if (type == BTRFS_FT_XATTR)
+		namelen = XATTR_NAME_MAX;
+
+	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
+		printk(KERN_CRIT "btrfS: invalid dir item name len: %u\n",
+		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
+		return 1;
+	}
+
+	/* BTRFS_MAX_XATTR_SIZE is the same for all dir items */
+	if (btrfs_dir_data_len(leaf, dir_item) > BTRFS_MAX_XATTR_SIZE(root)) {
+		printk(KERN_CRIT "btrfs: invalid dir item data len: %u\n",
+		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 100b07f021b..228cf36ece8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -29,6 +29,7 @@
 #include <linux/crc32c.h>
 #include <linux/slab.h>
 #include <linux/migrate.h>
+#include <asm/unaligned.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -198,7 +199,7 @@ u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len)
 
 void btrfs_csum_final(u32 crc, char *result)
 {
-	*(__le32 *)result = ~cpu_to_le32(crc);
+	put_unaligned_le32(~crc, result);
 }
 
 /*
@@ -323,6 +324,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 	int num_copies = 0;
 	int mirror_num = 0;
 
+	clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 	io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
 	while (1) {
 		ret = read_extent_buffer_pages(io_tree, eb, start, 1,
@@ -331,6 +333,14 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		    !verify_parent_transid(io_tree, eb, parent_transid))
 			return ret;
 
+		/*
+		 * This buffer's crc is fine, but its contents are corrupted, so
+		 * there is no reason to read the other copies, they won't be
+		 * any less wrong.
+		 */
+		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+			return ret;
+
 		num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
 					      eb->start, eb->len);
 		if (num_copies == 1)
@@ -419,6 +429,73 @@ static int check_tree_block_fsid(struct btrfs_root *root,
 	return ret;
 }
 
+#define CORRUPT(reason, eb, root, slot)				\
+	printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu,"	\
+	       "root=%llu, slot=%d\n", reason,			\
+	       (unsigned long long)btrfs_header_bytenr(eb),	\
+	       (unsigned long long)root->objectid, slot)
+
+static noinline int check_leaf(struct btrfs_root *root,
+			       struct extent_buffer *leaf)
+{
+	struct btrfs_key key;
+	struct btrfs_key leaf_key;
+	u32 nritems = btrfs_header_nritems(leaf);
+	int slot;
+
+	if (nritems == 0)
+		return 0;
+
+	/* Check the 0 item */
+	if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
+	    BTRFS_LEAF_DATA_SIZE(root)) {
+		CORRUPT("invalid item offset size pair", leaf, root, 0);
+		return -EIO;
+	}
+
+	/*
+	 * Check to make sure each items keys are in the correct order and their
+	 * offsets make sense.  We only have to loop through nritems-1 because
+	 * we check the current slot against the next slot, which verifies the
+	 * next slot's offset+size makes sense and that the current's slot
+	 * offset is correct.
+	 */
+	for (slot = 0; slot < nritems - 1; slot++) {
+		btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
+		btrfs_item_key_to_cpu(leaf, &key, slot + 1);
+
+		/* Make sure the keys are in the right order */
+		if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
+			CORRUPT("bad key order", leaf, root, slot);
+			return -EIO;
+		}
+
+		/*
+		 * Make sure the offset and ends are right, remember that the
+		 * item data starts at the end of the leaf and grows towards the
+		 * front.
+		 */
+		if (btrfs_item_offset_nr(leaf, slot) !=
+			btrfs_item_end_nr(leaf, slot + 1)) {
+			CORRUPT("slot offset bad", leaf, root, slot);
+			return -EIO;
+		}
+
+		/*
+		 * Check to make sure that we don't point outside of the leaf,
+		 * just incase all the items are consistent to eachother, but
+		 * all point outside of the leaf.
+		 */
+		if (btrfs_item_end_nr(leaf, slot) >
+		    BTRFS_LEAF_DATA_SIZE(root)) {
+			CORRUPT("slot end outside of leaf", leaf, root, slot);
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_set_buffer_lockdep_class(struct extent_buffer *eb, int level)
 {
@@ -485,8 +562,20 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	btrfs_set_buffer_lockdep_class(eb, found_level);
 
 	ret = csum_tree_block(root, eb, 1);
-	if (ret)
+	if (ret) {
+		ret = -EIO;
+		goto err;
+	}
+
+	/*
+	 * If this is a leaf block and it is corrupt, set the corrupt bit so
+	 * that we don't try and read the other copies of this block, just
+	 * return -EIO.
+	 */
+	if (found_level == 0 && check_leaf(root, eb)) {
+		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 		ret = -EIO;
+	}
 
 	end = min_t(u64, eb->len, PAGE_CACHE_SIZE);
 	end = eb->start + end - 1;
@@ -847,7 +936,6 @@ static const struct address_space_operations btree_aops = {
 	.writepages	= btree_writepages,
 	.releasepage	= btree_releasepage,
 	.invalidatepage = btree_invalidatepage,
-	.sync_page	= block_sync_page,
 #ifdef CONFIG_MIGRATION
 	.migratepage	= btree_migratepage,
 #endif
@@ -1160,7 +1248,10 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 		     root, fs_info, location->objectid);
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path) {
+		kfree(root);
+		return ERR_PTR(-ENOMEM);
+	}
 	ret = btrfs_search_slot(NULL, tree_root, location, path, 0, 0);
 	if (ret == 0) {
 		l = path->nodes[0];
@@ -1184,8 +1275,10 @@ struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root,
 	root->commit_root = btrfs_root_node(root);
 	BUG_ON(!root->node);
 out:
-	if (location->objectid != BTRFS_TREE_LOG_OBJECTID)
+	if (location->objectid != BTRFS_TREE_LOG_OBJECTID) {
 		root->ref_cows = 1;
+		btrfs_check_and_init_root_item(&root->root_item);
+	}
 
 	return root;
 }
@@ -1331,82 +1424,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 }
 
 /*
- * this unplugs every device on the box, and it is only used when page
- * is null
- */
-static void __unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-	struct btrfs_device *device;
-	struct btrfs_fs_info *info;
-
-	info = (struct btrfs_fs_info *)bdi->unplug_io_data;
-	list_for_each_entry(device, &info->fs_devices->devices, dev_list) {
-		if (!device->bdev)
-			continue;
-
-		bdi = blk_get_backing_dev_info(device->bdev);
-		if (bdi->unplug_io_fn)
-			bdi->unplug_io_fn(bdi, page);
-	}
-}
-
-static void btrfs_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-	struct inode *inode;
-	struct extent_map_tree *em_tree;
-	struct extent_map *em;
-	struct address_space *mapping;
-	u64 offset;
-
-	/* the generic O_DIRECT read code does this */
-	if (1 || !page) {
-		__unplug_io_fn(bdi, page);
-		return;
-	}
-
-	/*
-	 * page->mapping may change at any time.  Get a consistent copy
-	 * and use that for everything below
-	 */
-	smp_mb();
-	mapping = page->mapping;
-	if (!mapping)
-		return;
-
-	inode = mapping->host;
-
-	/*
-	 * don't do the expensive searching for a small number of
-	 * devices
-	 */
-	if (BTRFS_I(inode)->root->fs_info->fs_devices->open_devices <= 2) {
-		__unplug_io_fn(bdi, page);
-		return;
-	}
-
-	offset = page_offset(page);
-
-	em_tree = &BTRFS_I(inode)->extent_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, offset, PAGE_CACHE_SIZE);
-	read_unlock(&em_tree->lock);
-	if (!em) {
-		__unplug_io_fn(bdi, page);
-		return;
-	}
-
-	if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
-		free_extent_map(em);
-		__unplug_io_fn(bdi, page);
-		return;
-	}
-	offset = offset - em->start;
-	btrfs_unplug_page(&BTRFS_I(inode)->root->fs_info->mapping_tree,
-			  em->block_start + offset, page);
-	free_extent_map(em);
-}
-
-/*
  * If this fails, caller must call bdi_destroy() to get rid of the
  * bdi again.
  */
@@ -1420,8 +1437,6 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 		return err;
 
 	bdi->ra_pages	= default_backing_dev_info.ra_pages;
-	bdi->unplug_io_fn	= btrfs_unplug_io_fn;
-	bdi->unplug_io_data	= info;
 	bdi->congested_fn	= btrfs_congested_fn;
 	bdi->congested_data	= info;
 	return 0;
@@ -1632,6 +1647,8 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		goto fail_bdi;
 	}
 
+	fs_info->btree_inode->i_mapping->flags &= ~__GFP_FS;
+
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
 	INIT_LIST_HEAD(&fs_info->trans_list);
 	INIT_LIST_HEAD(&fs_info->dead_roots);
@@ -1762,6 +1779,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
 
+	/*
+	 * In the long term, we'll store the compression type in the super
+	 * block, and it'll be used for per file compression control.
+	 */
+	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
+
 	ret = btrfs_parse_options(tree_root, options);
 	if (ret) {
 		err = ret;
@@ -1967,6 +1990,12 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->metadata_alloc_profile = (u64)-1;
 	fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
 
+	ret = btrfs_init_space_info(fs_info);
+	if (ret) {
+		printk(KERN_ERR "Failed to initial space info: %d\n", ret);
+		goto fail_block_groups;
+	}
+
 	ret = btrfs_read_block_groups(extent_root);
 	if (ret) {
 		printk(KERN_ERR "Failed to read block groups: %d\n", ret);
@@ -2058,9 +2087,14 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		down_read(&fs_info->cleanup_work_sem);
-		btrfs_orphan_cleanup(fs_info->fs_root);
-		btrfs_orphan_cleanup(fs_info->tree_root);
+		err = btrfs_orphan_cleanup(fs_info->fs_root);
+		if (!err)
+			err = btrfs_orphan_cleanup(fs_info->tree_root);
 		up_read(&fs_info->cleanup_work_sem);
+		if (err) {
+			close_ctree(tree_root);
+			return ERR_PTR(err);
+		}
 	}
 
 	return tree_root;
@@ -2435,8 +2469,12 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 
 		root_objectid = gang[ret - 1]->root_key.objectid + 1;
 		for (i = 0; i < ret; i++) {
+			int err;
+
 			root_objectid = gang[i]->root_key.objectid;
-			btrfs_orphan_cleanup(gang[i]);
+			err = btrfs_orphan_cleanup(gang[i]);
+			if (err)
+				return err;
 		}
 		root_objectid++;
 	}
@@ -2786,6 +2824,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 
 	spin_lock(&delayed_refs->lock);
 	if (delayed_refs->num_entries == 0) {
+		spin_unlock(&delayed_refs->lock);
 		printk(KERN_INFO "delayed_refs has NO entry\n");
 		return ret;
 	}
@@ -2947,7 +2986,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
 			break;
 
 		/* opt_discard */
-		ret = btrfs_error_discard_extent(root, start, end + 1 - start);
+		if (btrfs_test_opt(root, DISCARD))
+			ret = btrfs_error_discard_extent(root, start,
+							 end + 1 - start,
+							 NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);
@@ -3016,7 +3058,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 		btrfs_destroy_pinned_extent(root,
 					    root->fs_info->pinned_extents);
 
-		t->use_count = 0;
+		atomic_set(&t->use_count, 0);
 		list_del_init(&t->list);
 		memset(t, 0, sizeof(*t));
 		kmem_cache_free(btrfs_transaction_cachep, t);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7b3089b5c2d..9ee6bd55e16 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -33,11 +33,28 @@
 #include "locking.h"
 #include "free-space-cache.h"
 
+/* control flags for do_chunk_alloc's force field
+ * CHUNK_ALLOC_NO_FORCE means to only allocate a chunk
+ * if we really need one.
+ *
+ * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
+ * CHUNK_ALLOC_LIMITED means to only try and allocate one
+ * if we have very few chunks already allocated.  This is
+ * used as part of the clustering code to help make sure
+ * we have a good pool of storage to cluster in, without
+ * filling the FS with empty chunks
+ *
+ */
+enum {
+	CHUNK_ALLOC_NO_FORCE = 0,
+	CHUNK_ALLOC_FORCE = 1,
+	CHUNK_ALLOC_LIMITED = 2,
+};
+
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      u64 bytenr, u64 num_bytes, int alloc);
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				 u64 num_bytes, int reserve, int sinfo);
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				u64 bytenr, u64 num_bytes, u64 parent,
@@ -442,7 +459,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	 * allocate blocks for the tree root we can't do the fast caching since
 	 * we likely hold important locks.
 	 */
-	if (!trans->transaction->in_commit &&
+	if (trans && (!trans->transaction->in_commit) &&
 	    (root && root != root->fs_info->tree_root)) {
 		spin_lock(&cache->lock);
 		if (cache->cached != BTRFS_CACHE_NO) {
@@ -471,7 +488,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	if (load_cache_only)
 		return 0;
 
-	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_KERNEL);
+	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
 	BUG_ON(!caching_ctl);
 
 	INIT_LIST_HEAD(&caching_ctl->list);
@@ -1740,39 +1757,45 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static void btrfs_issue_discard(struct block_device *bdev,
+static int btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
 {
-	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
+	return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0);
 }
 
 static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
-				u64 num_bytes)
+				u64 num_bytes, u64 *actual_bytes)
 {
 	int ret;
-	u64 map_length = num_bytes;
+	u64 discarded_bytes = 0;
 	struct btrfs_multi_bio *multi = NULL;
 
-	if (!btrfs_test_opt(root, DISCARD))
-		return 0;
 
 	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(&root->fs_info->mapping_tree, READ,
-			      bytenr, &map_length, &multi, 0);
+	ret = btrfs_map_block(&root->fs_info->mapping_tree, REQ_DISCARD,
+			      bytenr, &num_bytes, &multi, 0);
 	if (!ret) {
 		struct btrfs_bio_stripe *stripe = multi->stripes;
 		int i;
 
-		if (map_length > num_bytes)
-			map_length = num_bytes;
 
 		for (i = 0; i < multi->num_stripes; i++, stripe++) {
-			btrfs_issue_discard(stripe->dev->bdev,
-					    stripe->physical,
-					    map_length);
+			ret = btrfs_issue_discard(stripe->dev->bdev,
+						  stripe->physical,
+						  stripe->length);
+			if (!ret)
+				discarded_bytes += stripe->length;
+			else if (ret != -EOPNOTSUPP)
+				break;
 		}
 		kfree(multi);
 	}
+	if (discarded_bytes && ret == -EOPNOTSUPP)
+		ret = 0;
+
+	if (actual_bytes)
+		*actual_bytes = discarded_bytes;
+
 
 	return ret;
 }
@@ -3015,7 +3038,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	found->bytes_readonly = 0;
 	found->bytes_may_use = 0;
 	found->full = 0;
-	found->force_alloc = 0;
+	found->force_alloc = CHUNK_ALLOC_NO_FORCE;
+	found->chunk_alloc = 0;
 	*space_info = found;
 	list_add_rcu(&found->list, &info->space_info);
 	atomic_set(&found->caching_threads, 0);
@@ -3146,7 +3170,7 @@ again:
 		if (!data_sinfo->full && alloc_chunk) {
 			u64 alloc_target;
 
-			data_sinfo->force_alloc = 1;
+			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
 			spin_unlock(&data_sinfo->lock);
 alloc:
 			alloc_target = btrfs_get_alloc_profile(root, 1);
@@ -3156,7 +3180,8 @@ alloc:
 
 			ret = do_chunk_alloc(trans, root->fs_info->extent_root,
 					     bytes + 2 * 1024 * 1024,
-					     alloc_target, 0);
+					     alloc_target,
+					     CHUNK_ALLOC_NO_FORCE);
 			btrfs_end_transaction(trans, root);
 			if (ret < 0) {
 				if (ret != -ENOSPC)
@@ -3235,31 +3260,56 @@ static void force_metadata_allocation(struct btrfs_fs_info *info)
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
-			found->force_alloc = 1;
+			found->force_alloc = CHUNK_ALLOC_FORCE;
 	}
 	rcu_read_unlock();
 }
 
 static int should_alloc_chunk(struct btrfs_root *root,
-			      struct btrfs_space_info *sinfo, u64 alloc_bytes)
+			      struct btrfs_space_info *sinfo, u64 alloc_bytes,
+			      int force)
 {
 	u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly;
+	u64 num_allocated = sinfo->bytes_used + sinfo->bytes_reserved;
 	u64 thresh;
 
-	if (sinfo->bytes_used + sinfo->bytes_reserved +
-	    alloc_bytes + 256 * 1024 * 1024 < num_bytes)
+	if (force == CHUNK_ALLOC_FORCE)
+		return 1;
+
+	/*
+	 * in limited mode, we want to have some free space up to
+	 * about 1% of the FS size.
+	 */
+	if (force == CHUNK_ALLOC_LIMITED) {
+		thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+		thresh = max_t(u64, 64 * 1024 * 1024,
+			       div_factor_fine(thresh, 1));
+
+		if (num_bytes - num_allocated < thresh)
+			return 1;
+	}
+
+	/*
+	 * we have two similar checks here, one based on percentage
+	 * and once based on a hard number of 256MB.  The idea
+	 * is that if we have a good amount of free
+	 * room, don't allocate a chunk.  A good mount is
+	 * less than 80% utilized of the chunks we have allocated,
+	 * or more than 256MB free
+	 */
+	if (num_allocated + alloc_bytes + 256 * 1024 * 1024 < num_bytes)
 		return 0;
 
-	if (sinfo->bytes_used + sinfo->bytes_reserved +
-	    alloc_bytes < div_factor(num_bytes, 8))
+	if (num_allocated + alloc_bytes < div_factor(num_bytes, 8))
 		return 0;
 
 	thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+
+	/* 256MB or 5% of the FS */
 	thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5));
 
 	if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3))
 		return 0;
-
 	return 1;
 }
 
@@ -3269,10 +3319,9 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_space_info *space_info;
 	struct btrfs_fs_info *fs_info = extent_root->fs_info;
+	int wait_for_alloc = 0;
 	int ret = 0;
 
-	mutex_lock(&fs_info->chunk_mutex);
-
 	flags = btrfs_reduce_alloc_profile(extent_root, flags);
 
 	space_info = __find_space_info(extent_root->fs_info, flags);
@@ -3283,21 +3332,40 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 	}
 	BUG_ON(!space_info);
 
+again:
 	spin_lock(&space_info->lock);
 	if (space_info->force_alloc)
-		force = 1;
+		force = space_info->force_alloc;
 	if (space_info->full) {
 		spin_unlock(&space_info->lock);
-		goto out;
+		return 0;
 	}
 
-	if (!force && !should_alloc_chunk(extent_root, space_info,
-					  alloc_bytes)) {
+	if (!should_alloc_chunk(extent_root, space_info, alloc_bytes, force)) {
 		spin_unlock(&space_info->lock);
-		goto out;
+		return 0;
+	} else if (space_info->chunk_alloc) {
+		wait_for_alloc = 1;
+	} else {
+		space_info->chunk_alloc = 1;
 	}
+
 	spin_unlock(&space_info->lock);
 
+	mutex_lock(&fs_info->chunk_mutex);
+
+	/*
+	 * The chunk_mutex is held throughout the entirety of a chunk
+	 * allocation, so once we've acquired the chunk_mutex we know that the
+	 * other guy is done and we need to recheck and see if we should
+	 * allocate.
+	 */
+	if (wait_for_alloc) {
+		mutex_unlock(&fs_info->chunk_mutex);
+		wait_for_alloc = 0;
+		goto again;
+	}
+
 	/*
 	 * If we have mixed data/metadata chunks we want to make sure we keep
 	 * allocating mixed chunks instead of individual chunks.
@@ -3323,9 +3391,10 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 		space_info->full = 1;
 	else
 		ret = 1;
-	space_info->force_alloc = 0;
+
+	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
-out:
 	mutex_unlock(&extent_root->fs_info->chunk_mutex);
 	return ret;
 }
@@ -3996,6 +4065,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
 	u64 to_reserve;
 	int nr_extents;
+	int reserved_extents;
 	int ret;
 
 	if (btrfs_transaction_in_commit(root->fs_info))
@@ -4003,25 +4073,24 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 
-	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents) + 1;
-	if (nr_extents > BTRFS_I(inode)->reserved_extents) {
-		nr_extents -= BTRFS_I(inode)->reserved_extents;
+	reserved_extents = atomic_read(&BTRFS_I(inode)->reserved_extents);
+
+	if (nr_extents > reserved_extents) {
+		nr_extents -= reserved_extents;
 		to_reserve = calc_trans_metadata_size(root, nr_extents);
 	} else {
 		nr_extents = 0;
 		to_reserve = 0;
 	}
-	spin_unlock(&BTRFS_I(inode)->accounting_lock);
+
 	to_reserve += calc_csum_metadata_size(inode, num_bytes);
 	ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
 	if (ret)
 		return ret;
 
-	spin_lock(&BTRFS_I(inode)->accounting_lock);
-	BTRFS_I(inode)->reserved_extents += nr_extents;
+	atomic_add(nr_extents, &BTRFS_I(inode)->reserved_extents);
 	atomic_inc(&BTRFS_I(inode)->outstanding_extents);
-	spin_unlock(&BTRFS_I(inode)->accounting_lock);
 
 	block_rsv_add_bytes(block_rsv, to_reserve, 1);
 
@@ -4036,20 +4105,30 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 to_free;
 	int nr_extents;
+	int reserved_extents;
 
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
 	atomic_dec(&BTRFS_I(inode)->outstanding_extents);
 	WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents) < 0);
 
-	spin_lock(&BTRFS_I(inode)->accounting_lock);
-	nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
-	if (nr_extents < BTRFS_I(inode)->reserved_extents) {
-		nr_extents = BTRFS_I(inode)->reserved_extents - nr_extents;
-		BTRFS_I(inode)->reserved_extents -= nr_extents;
-	} else {
-		nr_extents = 0;
-	}
-	spin_unlock(&BTRFS_I(inode)->accounting_lock);
+	reserved_extents = atomic_read(&BTRFS_I(inode)->reserved_extents);
+	do {
+		int old, new;
+
+		nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
+		if (nr_extents >= reserved_extents) {
+			nr_extents = 0;
+			break;
+		}
+		old = reserved_extents;
+		nr_extents = reserved_extents - nr_extents;
+		new = reserved_extents - nr_extents;
+		old = atomic_cmpxchg(&BTRFS_I(inode)->reserved_extents,
+				     reserved_extents, new);
+		if (likely(old == reserved_extents))
+			break;
+		reserved_extents = old;
+	} while (1);
 
 	to_free = calc_csum_metadata_size(inode, num_bytes);
 	if (nr_extents > 0)
@@ -4223,8 +4302,8 @@ int btrfs_pin_extent(struct btrfs_root *root,
  * update size of reserved extents. this function may return -EAGAIN
  * if 'reserve' is true or 'sinfo' is false.
  */
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				 u64 num_bytes, int reserve, int sinfo)
+int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
+				u64 num_bytes, int reserve, int sinfo)
 {
 	int ret = 0;
 	if (sinfo) {
@@ -4363,7 +4442,9 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 		if (ret)
 			break;
 
-		ret = btrfs_discard_extent(root, start, end + 1 - start);
+		if (btrfs_test_opt(root, DISCARD))
+			ret = btrfs_discard_extent(root, start,
+						   end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		unpin_extent_range(root, start, end);
@@ -4704,10 +4785,10 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
-		ret = update_reserved_bytes(cache, buf->len, 0, 0);
+		ret = btrfs_update_reserved_bytes(cache, buf->len, 0, 0);
 		if (ret == -EAGAIN) {
 			/* block group became read-only */
-			update_reserved_bytes(cache, buf->len, 0, 1);
+			btrfs_update_reserved_bytes(cache, buf->len, 0, 1);
 			goto out;
 		}
 
@@ -4744,6 +4825,11 @@ pin:
 		}
 	}
 out:
+	/*
+	 * Deleting the buffer, clear the corrupt flag since it doesn't matter
+	 * anymore.
+	 */
+	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
 	btrfs_put_block_group(cache);
 }
 
@@ -5191,7 +5277,7 @@ checks:
 					     search_start - offset);
 		BUG_ON(offset > search_start);
 
-		ret = update_reserved_bytes(block_group, num_bytes, 1,
+		ret = btrfs_update_reserved_bytes(block_group, num_bytes, 1,
 					    (data & BTRFS_BLOCK_GROUP_DATA));
 		if (ret == -EAGAIN) {
 			btrfs_add_free_space(block_group, offset, num_bytes);
@@ -5282,11 +5368,13 @@ loop:
 
 		if (allowed_chunk_alloc) {
 			ret = do_chunk_alloc(trans, root, num_bytes +
-					     2 * 1024 * 1024, data, 1);
+					     2 * 1024 * 1024, data,
+					     CHUNK_ALLOC_LIMITED);
 			allowed_chunk_alloc = 0;
 			done_chunk_alloc = 1;
-		} else if (!done_chunk_alloc) {
-			space_info->force_alloc = 1;
+		} else if (!done_chunk_alloc &&
+			   space_info->force_alloc == CHUNK_ALLOC_NO_FORCE) {
+			space_info->force_alloc = CHUNK_ALLOC_LIMITED;
 		}
 
 		if (loop < LOOP_NO_EMPTY_SIZE) {
@@ -5372,7 +5460,8 @@ again:
 	 */
 	if (empty_size || root->ref_cows)
 		ret = do_chunk_alloc(trans, root->fs_info->extent_root,
-				     num_bytes + 2 * 1024 * 1024, data, 0);
+				     num_bytes + 2 * 1024 * 1024, data,
+				     CHUNK_ALLOC_NO_FORCE);
 
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(trans, root, num_bytes, empty_size,
@@ -5384,7 +5473,7 @@ again:
 		num_bytes = num_bytes & ~(root->sectorsize - 1);
 		num_bytes = max(num_bytes, min_alloc_size);
 		do_chunk_alloc(trans, root->fs_info->extent_root,
-			       num_bytes, data, 1);
+			       num_bytes, data, CHUNK_ALLOC_FORCE);
 		goto again;
 	}
 	if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) {
@@ -5397,6 +5486,8 @@ again:
 		dump_space_info(sinfo, num_bytes, 1);
 	}
 
+	trace_btrfs_reserved_extent_alloc(root, ins->objectid, ins->offset);
+
 	return ret;
 }
 
@@ -5412,12 +5503,15 @@ int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len)
 		return -ENOSPC;
 	}
 
-	ret = btrfs_discard_extent(root, start, len);
+	if (btrfs_test_opt(root, DISCARD))
+		ret = btrfs_discard_extent(root, start, len, NULL);
 
 	btrfs_add_free_space(cache, start, len);
-	update_reserved_bytes(cache, len, 0, 1);
+	btrfs_update_reserved_bytes(cache, len, 0, 1);
 	btrfs_put_block_group(cache);
 
+	trace_btrfs_reserved_extent_free(root, start, len);
+
 	return ret;
 }
 
@@ -5444,7 +5538,8 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type);
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
@@ -5614,7 +5709,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 		put_caching_control(caching_ctl);
 	}
 
-	ret = update_reserved_bytes(block_group, ins->offset, 1, 1);
+	ret = btrfs_update_reserved_bytes(block_group, ins->offset, 1, 1);
 	BUG_ON(ret);
 	btrfs_put_block_group(block_group);
 	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
@@ -6047,6 +6142,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 		if (reada && level == 1)
 			reada_walk_down(trans, root, wc, path);
 		next = read_tree_block(root, bytenr, blocksize, generation);
+		if (!next)
+			return -EIO;
 		btrfs_tree_lock(next);
 		btrfs_set_lock_blocking(next);
 	}
@@ -6438,10 +6535,14 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 
 	wc = kzalloc(sizeof(*wc), GFP_NOFS);
-	BUG_ON(!wc);
+	if (!wc) {
+		btrfs_free_path(path);
+		return -ENOMEM;
+	}
 
 	btrfs_assert_tree_locked(parent);
 	parent_level = btrfs_header_level(parent);
@@ -6899,7 +7000,11 @@ static noinline int get_new_locations(struct inode *reloc_inode,
 	}
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path) {
+		if (exts != *extents)
+			kfree(exts);
+		return -ENOMEM;
+	}
 
 	cur_pos = extent_key->objectid - offset;
 	last_byte = extent_key->objectid + extent_key->offset;
@@ -6941,6 +7046,10 @@ static noinline int get_new_locations(struct inode *reloc_inode,
 			struct disk_extent *old = exts;
 			max *= 2;
 			exts = kzalloc(sizeof(*exts) * max, GFP_NOFS);
+			if (!exts) {
+				ret = -ENOMEM;
+				goto out;
+			}
 			memcpy(exts, old, sizeof(*exts) * nr);
 			if (old != *extents)
 				kfree(old);
@@ -7423,7 +7532,8 @@ static noinline int replace_extents_in_leaf(struct btrfs_trans_handle *trans,
 	int ret;
 
 	new_extent = kmalloc(sizeof(*new_extent), GFP_NOFS);
-	BUG_ON(!new_extent);
+	if (!new_extent)
+		return -ENOMEM;
 
 	ref = btrfs_lookup_leaf_ref(root, leaf->start);
 	BUG_ON(!ref);
@@ -7609,7 +7719,8 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root)
 
 	reloc_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
 	BUG_ON(!reloc_root);
-	btrfs_orphan_cleanup(reloc_root);
+	ret = btrfs_orphan_cleanup(reloc_root);
+	BUG_ON(ret);
 	return 0;
 }
 
@@ -7627,7 +7738,8 @@ static noinline int init_reloc_tree(struct btrfs_trans_handle *trans,
 		return 0;
 
 	root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
-	BUG_ON(!root_item);
+	if (!root_item)
+		return -ENOMEM;
 
 	ret = btrfs_copy_root(trans, root, root->commit_root,
 			      &eb, BTRFS_TREE_RELOC_OBJECTID);
@@ -7653,7 +7765,7 @@ static noinline int init_reloc_tree(struct btrfs_trans_handle *trans,
 
 	reloc_root = btrfs_read_fs_root_no_radix(root->fs_info->tree_root,
 						 &root_key);
-	BUG_ON(!reloc_root);
+	BUG_ON(IS_ERR(reloc_root));
 	reloc_root->last_trans = trans->transid;
 	reloc_root->commit_root = NULL;
 	reloc_root->ref_tree = &root->fs_info->reloc_ref_tree;
@@ -7906,6 +8018,10 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root,
 
 			eb = read_tree_block(found_root, block_start,
 					     block_size, 0);
+			if (!eb) {
+				ret = -EIO;
+				goto out;
+			}
 			btrfs_tree_lock(eb);
 			BUG_ON(level != btrfs_header_level(eb));
 
@@ -7943,6 +8059,10 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root,
 				u64 group_start = group->key.objectid;
 				new_extents = kmalloc(sizeof(*new_extents),
 						      GFP_NOFS);
+				if (!new_extents) {
+					ret = -ENOMEM;
+					goto out;
+				}
 				nr_extents = 1;
 				ret = get_new_locations(reloc_inode,
 							extent_key,
@@ -8061,13 +8181,15 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 
 	alloc_flags = update_block_group_flags(root, cache->flags);
 	if (alloc_flags != cache->flags)
-		do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+		do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			       CHUNK_ALLOC_FORCE);
 
 	ret = set_block_group_ro(cache);
 	if (!ret)
 		goto out;
 	alloc_flags = get_alloc_profile(root, cache->space_info->flags);
-	ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+	ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			     CHUNK_ALLOC_FORCE);
 	if (ret < 0)
 		goto out;
 	ret = set_block_group_ro(cache);
@@ -8080,7 +8202,8 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root, u64 type)
 {
 	u64 alloc_flags = get_alloc_profile(root, type);
-	return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+	return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+			      CHUNK_ALLOC_FORCE);
 }
 
 /*
@@ -8621,6 +8744,12 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
+	/*
+	 * Free the reserved super bytes from this block group before
+	 * remove it.
+	 */
+	free_excluded_extents(root, block_group);
+
 	memcpy(&key, &block_group->key, sizeof(key));
 	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
 				  BTRFS_BLOCK_GROUP_RAID1 |
@@ -8724,13 +8853,99 @@ out:
 	return ret;
 }
 
+int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_space_info *space_info;
+	struct btrfs_super_block *disk_super;
+	u64 features;
+	u64 flags;
+	int mixed = 0;
+	int ret;
+
+	disk_super = &fs_info->super_copy;
+	if (!btrfs_super_root(disk_super))
+		return 1;
+
+	features = btrfs_super_incompat_flags(disk_super);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = 1;
+
+	flags = BTRFS_BLOCK_GROUP_SYSTEM;
+	ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+	if (ret)
+		goto out;
+
+	if (mixed) {
+		flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
+		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+	} else {
+		flags = BTRFS_BLOCK_GROUP_METADATA;
+		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+		if (ret)
+			goto out;
+
+		flags = BTRFS_BLOCK_GROUP_DATA;
+		ret = update_space_info(fs_info, flags, 0, 0, &space_info);
+	}
+out:
+	return ret;
+}
+
 int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 {
 	return unpin_extent_range(root, start, end);
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
-			       u64 num_bytes)
+			       u64 num_bytes, u64 *actual_bytes)
 {
-	return btrfs_discard_extent(root, bytenr, num_bytes);
+	return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes);
+}
+
+int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_block_group_cache *cache = NULL;
+	u64 group_trimmed;
+	u64 start;
+	u64 end;
+	u64 trimmed = 0;
+	int ret = 0;
+
+	cache = btrfs_lookup_block_group(fs_info, range->start);
+
+	while (cache) {
+		if (cache->key.objectid >= (range->start + range->len)) {
+			btrfs_put_block_group(cache);
+			break;
+		}
+
+		start = max(range->start, cache->key.objectid);
+		end = min(range->start + range->len,
+				cache->key.objectid + cache->key.offset);
+
+		if (end - start >= range->minlen) {
+			if (!block_group_cache_done(cache)) {
+				ret = cache_block_group(cache, NULL, root, 0);
+				if (!ret)
+					wait_block_group_cache_done(cache);
+			}
+			ret = btrfs_trim_block_group(cache,
+						     &group_trimmed,
+						     start,
+						     end,
+						     range->minlen);
+
+			trimmed += group_trimmed;
+			if (ret) {
+				btrfs_put_block_group(cache);
+				break;
+			}
+		}
+
+		cache = next_block_group(fs_info->tree_root, cache);
+	}
+
+	range->len = trimmed;
+	return ret;
 }
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 714adc4ac4c..ba41da59e31 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -690,6 +690,15 @@ static void cache_state(struct extent_state *state,
 	}
 }
 
+static void uncache_state(struct extent_state **cached_ptr)
+{
+	if (cached_ptr && (*cached_ptr)) {
+		struct extent_state *state = *cached_ptr;
+		*cached_ptr = NULL;
+		free_extent_state(state);
+	}
+}
+
 /*
  * set some bits on a range in the tree.  This may require allocations or
  * sleeping, so the gfp mask is used to indicate what is allowed.
@@ -940,10 +949,10 @@ static int clear_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
 }
 
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			gfp_t mask)
+			struct extent_state **cached_state, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL,
-			      NULL, mask);
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0,
+			      NULL, cached_state, mask);
 }
 
 static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -1012,8 +1021,7 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 				mask);
 }
 
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end,
-		  gfp_t mask)
+int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask)
 {
 	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
 				mask);
@@ -1735,6 +1743,9 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 
 	do {
 		struct page *page = bvec->bv_page;
+		struct extent_state *cached = NULL;
+		struct extent_state *state;
+
 		tree = &BTRFS_I(page->mapping->host)->io_tree;
 
 		start = ((u64)page->index << PAGE_CACHE_SHIFT) +
@@ -1749,9 +1760,20 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		if (++bvec <= bvec_end)
 			prefetchw(&bvec->bv_page->flags);
 
+		spin_lock(&tree->lock);
+		state = find_first_extent_bit_state(tree, start, EXTENT_LOCKED);
+		if (state && state->start == start) {
+			/*
+			 * take a reference on the state, unlock will drop
+			 * the ref
+			 */
+			cache_state(state, &cached);
+		}
+		spin_unlock(&tree->lock);
+
 		if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
 			ret = tree->ops->readpage_end_io_hook(page, start, end,
-							      NULL);
+							      state);
 			if (ret)
 				uptodate = 0;
 		}
@@ -1764,15 +1786,16 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				uncache_state(&cached);
 				continue;
 			}
 		}
 
 		if (uptodate) {
-			set_extent_uptodate(tree, start, end,
+			set_extent_uptodate(tree, start, end, &cached,
 					    GFP_ATOMIC);
 		}
-		unlock_extent(tree, start, end, GFP_ATOMIC);
+		unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
 
 		if (whole_page) {
 			if (uptodate) {
@@ -1811,6 +1834,7 @@ static void end_bio_extent_preparewrite(struct bio *bio, int err)
 
 	do {
 		struct page *page = bvec->bv_page;
+		struct extent_state *cached = NULL;
 		tree = &BTRFS_I(page->mapping->host)->io_tree;
 
 		start = ((u64)page->index << PAGE_CACHE_SHIFT) +
@@ -1821,13 +1845,14 @@ static void end_bio_extent_preparewrite(struct bio *bio, int err)
 			prefetchw(&bvec->bv_page->flags);
 
 		if (uptodate) {
-			set_extent_uptodate(tree, start, end, GFP_ATOMIC);
+			set_extent_uptodate(tree, start, end, &cached,
+					    GFP_ATOMIC);
 		} else {
 			ClearPageUptodate(page);
 			SetPageError(page);
 		}
 
-		unlock_extent(tree, start, end, GFP_ATOMIC);
+		unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
 
 	} while (bvec >= bio->bi_io_vec);
 
@@ -2016,14 +2041,17 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	while (cur <= end) {
 		if (cur >= last_byte) {
 			char *userpage;
+			struct extent_state *cached = NULL;
+
 			iosize = PAGE_CACHE_SIZE - page_offset;
 			userpage = kmap_atomic(page, KM_USER0);
 			memset(userpage + page_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
-					    GFP_NOFS);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+					    &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur, cur + iosize - 1,
+					     &cached, GFP_NOFS);
 			break;
 		}
 		em = get_extent(inode, page, page_offset, cur,
@@ -2063,14 +2091,17 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 		/* we've found a hole, just zero and go on */
 		if (block_start == EXTENT_MAP_HOLE) {
 			char *userpage;
+			struct extent_state *cached = NULL;
+
 			userpage = kmap_atomic(page, KM_USER0);
 			memset(userpage + page_offset, 0, iosize);
 			flush_dcache_page(page);
 			kunmap_atomic(userpage, KM_USER0);
 
 			set_extent_uptodate(tree, cur, cur + iosize - 1,
-					    GFP_NOFS);
-			unlock_extent(tree, cur, cur + iosize - 1, GFP_NOFS);
+					    &cached, GFP_NOFS);
+			unlock_extent_cached(tree, cur, cur + iosize - 1,
+			                     &cached, GFP_NOFS);
 			cur = cur + iosize;
 			page_offset += iosize;
 			continue;
@@ -2188,10 +2219,12 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	unsigned long nr_written = 0;
 
 	if (wbc->sync_mode == WB_SYNC_ALL)
-		write_flags = WRITE_SYNC_PLUG;
+		write_flags = WRITE_SYNC;
 	else
 		write_flags = WRITE;
 
+	trace___extent_writepage(page, inode, wbc);
+
 	WARN_ON(!PageLocked(page));
 	pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
 	if (page->index > end_index ||
@@ -2648,7 +2681,7 @@ int extent_readpages(struct extent_io_tree *tree,
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (!add_to_page_cache_lru(page, mapping,
-					page->index, GFP_KERNEL)) {
+					page->index, GFP_NOFS)) {
 			__extent_read_full_page(tree, page, get_extent,
 						&bio, 0, &bio_flags);
 		}
@@ -2787,9 +2820,12 @@ int extent_prepare_write(struct extent_io_tree *tree,
 			iocount++;
 			block_start = block_start + iosize;
 		} else {
-			set_extent_uptodate(tree, block_start, cur_end,
+			struct extent_state *cached = NULL;
+
+			set_extent_uptodate(tree, block_start, cur_end, &cached,
 					    GFP_NOFS);
-			unlock_extent(tree, block_start, cur_end, GFP_NOFS);
+			unlock_extent_cached(tree, block_start, cur_end,
+					     &cached, GFP_NOFS);
 			block_start = cur_end + 1;
 		}
 		page_offset = block_start & (PAGE_CACHE_SIZE - 1);
@@ -3455,7 +3491,7 @@ int set_extent_buffer_uptodate(struct extent_io_tree *tree,
 	num_pages = num_extent_pages(eb->start, eb->len);
 
 	set_extent_uptodate(tree, eb->start, eb->start + eb->len - 1,
-			    GFP_NOFS);
+			    NULL, GFP_NOFS);
 	for (i = 0; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);
 		if ((i == 0 && (eb->start & (PAGE_CACHE_SIZE - 1))) ||
@@ -3690,6 +3726,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		       "wanted %lu %lu\n", (unsigned long long)eb->start,
 		       eb->len, start, min_len);
 		WARN_ON(1);
+		return -EINVAL;
 	}
 
 	p = extent_buffer_page(eb, i);
@@ -3882,6 +3919,12 @@ static void move_pages(struct page *dst_page, struct page *src_page,
 	kunmap_atomic(dst_kaddr, KM_USER0);
 }
 
+static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
+{
+	unsigned long distance = (src > dst) ? src - dst : dst - src;
+	return distance < len;
+}
+
 static void copy_pages(struct page *dst_page, struct page *src_page,
 		       unsigned long dst_off, unsigned long src_off,
 		       unsigned long len)
@@ -3889,10 +3932,12 @@ static void copy_pages(struct page *dst_page, struct page *src_page,
 	char *dst_kaddr = kmap_atomic(dst_page, KM_USER0);
 	char *src_kaddr;
 
-	if (dst_page != src_page)
+	if (dst_page != src_page) {
 		src_kaddr = kmap_atomic(src_page, KM_USER1);
-	else
+	} else {
 		src_kaddr = dst_kaddr;
+		BUG_ON(areas_overlap(src_off, dst_off, len));
+	}
 
 	memcpy(dst_kaddr + dst_off, src_kaddr + src_off, len);
 	kunmap_atomic(dst_kaddr, KM_USER0);
@@ -3967,7 +4012,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 		       "len %lu len %lu\n", dst_offset, len, dst->len);
 		BUG_ON(1);
 	}
-	if (dst_offset < src_offset) {
+	if (!areas_overlap(src_offset, dst_offset, len)) {
 		memcpy_extent_buffer(dst, dst_offset, src_offset, len);
 		return;
 	}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 9318dfefd59..af2d7179c37 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -31,6 +31,7 @@
 #define EXTENT_BUFFER_UPTODATE 0
 #define EXTENT_BUFFER_BLOCKING 1
 #define EXTENT_BUFFER_DIRTY 2
+#define EXTENT_BUFFER_CORRUPT 3
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define EXTENT_CLEAR_UNLOCK_PAGE 0x1
@@ -207,7 +208,7 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   int bits, int exclusive_bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
 int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			gfp_t mask);
+			struct extent_state **cached_state, gfp_t mask);
 int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
 		   gfp_t mask);
 int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 2b6c12e983b..a24a3f2fa13 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -243,7 +243,7 @@ out:
  * Insert @em into @tree or perform a simple forward/backward merge with
  * existing mappings.  The extent_map struct passed in will be inserted
  * into the tree directly, with an additional reference taken, or a
- * reference dropped if the merge attempt was successfull.
+ * reference dropped if the merge attempt was successful.
  */
 int add_extent_mapping(struct extent_map_tree *tree,
 		       struct extent_map *em)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 4f19a3e1bf3..a6a9d4e8b49 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -48,7 +48,8 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	file_key.objectid = objectid;
 	file_key.offset = pos;
 	btrfs_set_key_type(&file_key, BTRFS_EXTENT_DATA_KEY);
@@ -169,6 +170,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 
 	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
 	if (bio->bi_size > PAGE_CACHE_SIZE * 8)
 		path->reada = 2;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f447b783bb8..75899a01dde 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -45,14 +45,14 @@
  * and be replaced with calls into generic code.
  */
 static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
-					 int write_bytes,
+					 size_t write_bytes,
 					 struct page **prepared_pages,
 					 struct iov_iter *i)
 {
 	size_t copied = 0;
+	size_t total_copied = 0;
 	int pg = 0;
 	int offset = pos & (PAGE_CACHE_SIZE - 1);
-	int total_copied = 0;
 
 	while (write_bytes > 0) {
 		size_t count = min_t(size_t,
@@ -88,9 +88,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 		total_copied += copied;
 
 		/* Return to btrfs_file_aio_write to fault page */
-		if (unlikely(copied == 0)) {
+		if (unlikely(copied == 0))
 			break;
-		}
 
 		if (unlikely(copied < PAGE_CACHE_SIZE - offset)) {
 			offset += copied;
@@ -105,12 +104,10 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
 /*
  * unlocks pages after btrfs_file_write is done with them
  */
-static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages)
+void btrfs_drop_pages(struct page **pages, size_t num_pages)
 {
 	size_t i;
 	for (i = 0; i < num_pages; i++) {
-		if (!pages[i])
-			break;
 		/* page checked is some magic around finding pages that
 		 * have been modified without going through btrfs_set_page_dirty
 		 * clear it here
@@ -130,17 +127,13 @@ static noinline void btrfs_drop_pages(struct page **pages, size_t num_pages)
  * this also makes the decision about creating an inline extent vs
  * doing real data extents, marking pages dirty and delalloc as required.
  */
-static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
-				   struct file *file,
-				   struct page **pages,
-				   size_t num_pages,
-				   loff_t pos,
-				   size_t write_bytes)
+int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
+		      struct page **pages, size_t num_pages,
+		      loff_t pos, size_t write_bytes,
+		      struct extent_state **cached)
 {
 	int err = 0;
 	int i;
-	struct inode *inode = fdentry(file)->d_inode;
 	u64 num_bytes;
 	u64 start_pos;
 	u64 end_of_last_block;
@@ -153,8 +146,9 @@ static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans,
 
 	end_of_last_block = start_pos + num_bytes - 1;
 	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
-					NULL);
-	BUG_ON(err);
+					cached);
+	if (err)
+		return err;
 
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = pages[i];
@@ -162,13 +156,14 @@ static noinline int dirty_and_release_pages(struct btrfs_trans_handle *trans,
 		ClearPageChecked(p);
 		set_page_dirty(p);
 	}
-	if (end_pos > isize) {
+
+	/*
+	 * we've only changed i_size in ram, and we haven't updated
+	 * the disk i_size.  There is no need to log the inode
+	 * at this time.
+	 */
+	if (end_pos > isize)
 		i_size_write(inode, end_pos);
-		/* we've only changed i_size in ram, and we haven't updated
-		 * the disk i_size.  There is no need to log the inode
-		 * at this time.
-		 */
-	}
 	return 0;
 }
 
@@ -610,6 +605,8 @@ again:
 	key.offset = split;
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	if (ret < 0)
+		goto out;
 	if (ret > 0 && path->slots[0] > 0)
 		path->slots[0]--;
 
@@ -819,12 +816,11 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 	last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;
 
 	if (start_pos > inode->i_size) {
-		err = btrfs_cont_expand(inode, start_pos);
+		err = btrfs_cont_expand(inode, i_size_read(inode), start_pos);
 		if (err)
 			return err;
 	}
 
-	memset(pages, 0, num_pages * sizeof(struct page *));
 again:
 	for (i = 0; i < num_pages; i++) {
 		pages[i] = grab_cache_page(inode->i_mapping, index + i);
@@ -896,156 +892,71 @@ fail:
 
 }
 
-static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
-				    const struct iovec *iov,
-				    unsigned long nr_segs, loff_t pos)
+static noinline ssize_t __btrfs_buffered_write(struct file *file,
+					       struct iov_iter *i,
+					       loff_t pos)
 {
-	struct file *file = iocb->ki_filp;
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct page **pages = NULL;
-	struct iov_iter i;
-	loff_t *ppos = &iocb->ki_pos;
-	loff_t start_pos;
-	ssize_t num_written = 0;
-	ssize_t err = 0;
-	size_t count;
-	size_t ocount;
-	int ret = 0;
-	int nrptrs;
 	unsigned long first_index;
 	unsigned long last_index;
-	int will_write;
-	int buffered = 0;
-	int copied = 0;
-	int dirty_pages = 0;
-
-	will_write = ((file->f_flags & O_DSYNC) || IS_SYNC(inode) ||
-		      (file->f_flags & O_DIRECT));
-
-	start_pos = pos;
-
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
-
-	mutex_lock(&inode->i_mutex);
-
-	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
-	if (err)
-		goto out;
-	count = ocount;
-
-	current->backing_dev_info = inode->i_mapping->backing_dev_info;
-	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
-	if (err)
-		goto out;
-
-	if (count == 0)
-		goto out;
-
-	err = file_remove_suid(file);
-	if (err)
-		goto out;
-
-	/*
-	 * If BTRFS flips readonly due to some impossible error
-	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
-	 * although we have opened a file as writable, we have
-	 * to stop this write operation to ensure FS consistency.
-	 */
-	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
-		err = -EROFS;
-		goto out;
-	}
-
-	file_update_time(file);
-	BTRFS_I(inode)->sequence++;
-
-	if (unlikely(file->f_flags & O_DIRECT)) {
-		num_written = generic_file_direct_write(iocb, iov, &nr_segs,
-							pos, ppos, count,
-							ocount);
-		/*
-		 * the generic O_DIRECT will update in-memory i_size after the
-		 * DIOs are done.  But our endio handlers that update the on
-		 * disk i_size never update past the in memory i_size.  So we
-		 * need one more update here to catch any additions to the
-		 * file
-		 */
-		if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
-			btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
-			mark_inode_dirty(inode);
-		}
-
-		if (num_written < 0) {
-			ret = num_written;
-			num_written = 0;
-			goto out;
-		} else if (num_written == count) {
-			/* pick up pos changes done by the generic code */
-			pos = *ppos;
-			goto out;
-		}
-		/*
-		 * We are going to do buffered for the rest of the range, so we
-		 * need to make sure to invalidate the buffered pages when we're
-		 * done.
-		 */
-		buffered = 1;
-		pos += num_written;
-	}
+	size_t num_written = 0;
+	int nrptrs;
+	int ret = 0;
 
-	iov_iter_init(&i, iov, nr_segs, count, num_written);
-	nrptrs = min((iov_iter_count(&i) + PAGE_CACHE_SIZE - 1) /
+	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
 		     (sizeof(struct page *)));
 	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
-	if (!pages) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/* generic_write_checks can change our pos */
-	start_pos = pos;
+	if (!pages)
+		return -ENOMEM;
 
 	first_index = pos >> PAGE_CACHE_SHIFT;
-	last_index = (pos + iov_iter_count(&i)) >> PAGE_CACHE_SHIFT;
+	last_index = (pos + iov_iter_count(i)) >> PAGE_CACHE_SHIFT;
 
-	while (iov_iter_count(&i) > 0) {
+	while (iov_iter_count(i) > 0) {
 		size_t offset = pos & (PAGE_CACHE_SIZE - 1);
-		size_t write_bytes = min(iov_iter_count(&i),
+		size_t write_bytes = min(iov_iter_count(i),
 					 nrptrs * (size_t)PAGE_CACHE_SIZE -
 					 offset);
 		size_t num_pages = (write_bytes + offset +
 				    PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+		size_t dirty_pages;
+		size_t copied;
 
 		WARN_ON(num_pages > nrptrs);
-		memset(pages, 0, sizeof(struct page *) * nrptrs);
 
 		/*
 		 * Fault pages before locking them in prepare_pages
 		 * to avoid recursive lock
 		 */
-		if (unlikely(iov_iter_fault_in_readable(&i, write_bytes))) {
+		if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) {
 			ret = -EFAULT;
-			goto out;
+			break;
 		}
 
 		ret = btrfs_delalloc_reserve_space(inode,
 					num_pages << PAGE_CACHE_SHIFT);
 		if (ret)
-			goto out;
+			break;
 
+		/*
+		 * This is going to setup the pages array with the number of
+		 * pages we want, so we don't really need to worry about the
+		 * contents of pages from loop to loop
+		 */
 		ret = prepare_pages(root, file, pages, num_pages,
 				    pos, first_index, last_index,
 				    write_bytes);
 		if (ret) {
 			btrfs_delalloc_release_space(inode,
 					num_pages << PAGE_CACHE_SHIFT);
-			goto out;
+			break;
 		}
 
 		copied = btrfs_copy_from_user(pos, num_pages,
-					   write_bytes, pages, &i);
+					   write_bytes, pages, i);
 
 		/*
 		 * if we have trouble faulting in the pages, fall
@@ -1061,6 +972,13 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 				       PAGE_CACHE_SIZE - 1) >>
 				       PAGE_CACHE_SHIFT;
 
+		/*
+		 * If we had a short copy we need to release the excess delaloc
+		 * bytes we reserved.  We need to increment outstanding_extents
+		 * because btrfs_delalloc_release_space will decrement it, but
+		 * we still have an outstanding extent for the chunk we actually
+		 * managed to copy.
+		 */
 		if (num_pages > dirty_pages) {
 			if (copied > 0)
 				atomic_inc(
@@ -1071,39 +989,157 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		}
 
 		if (copied > 0) {
-			dirty_and_release_pages(NULL, root, file, pages,
-						dirty_pages, pos, copied);
+			ret = btrfs_dirty_pages(root, inode, pages,
+						dirty_pages, pos, copied,
+						NULL);
+			if (ret) {
+				btrfs_delalloc_release_space(inode,
+					dirty_pages << PAGE_CACHE_SHIFT);
+				btrfs_drop_pages(pages, num_pages);
+				break;
+			}
 		}
 
 		btrfs_drop_pages(pages, num_pages);
 
-		if (copied > 0) {
-			if (will_write) {
-				filemap_fdatawrite_range(inode->i_mapping, pos,
-							 pos + copied - 1);
-			} else {
-				balance_dirty_pages_ratelimited_nr(
-							inode->i_mapping,
-							dirty_pages);
-				if (dirty_pages <
-				(root->leafsize >> PAGE_CACHE_SHIFT) + 1)
-					btrfs_btree_balance_dirty(root, 1);
-				btrfs_throttle(root);
-			}
-		}
+		cond_resched();
+
+		balance_dirty_pages_ratelimited_nr(inode->i_mapping,
+						   dirty_pages);
+		if (dirty_pages < (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
+			btrfs_btree_balance_dirty(root, 1);
+		btrfs_throttle(root);
 
 		pos += copied;
 		num_written += copied;
+	}
 
-		cond_resched();
+	kfree(pages);
+
+	return num_written ? num_written : ret;
+}
+
+static ssize_t __btrfs_direct_write(struct kiocb *iocb,
+				    const struct iovec *iov,
+				    unsigned long nr_segs, loff_t pos,
+				    loff_t *ppos, size_t count, size_t ocount)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = fdentry(file)->d_inode;
+	struct iov_iter i;
+	ssize_t written;
+	ssize_t written_buffered;
+	loff_t endbyte;
+	int err;
+
+	written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos,
+					    count, ocount);
+
+	/*
+	 * the generic O_DIRECT will update in-memory i_size after the
+	 * DIOs are done.  But our endio handlers that update the on
+	 * disk i_size never update past the in memory i_size.  So we
+	 * need one more update here to catch any additions to the
+	 * file
+	 */
+	if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
+		btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+		mark_inode_dirty(inode);
 	}
+
+	if (written < 0 || written == count)
+		return written;
+
+	pos += written;
+	count -= written;
+	iov_iter_init(&i, iov, nr_segs, count, written);
+	written_buffered = __btrfs_buffered_write(file, &i, pos);
+	if (written_buffered < 0) {
+		err = written_buffered;
+		goto out;
+	}
+	endbyte = pos + written_buffered - 1;
+	err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
+	if (err)
+		goto out;
+	written += written_buffered;
+	*ppos = pos + written_buffered;
+	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_CACHE_SHIFT,
+				 endbyte >> PAGE_CACHE_SHIFT);
 out:
-	mutex_unlock(&inode->i_mutex);
-	if (ret)
-		err = ret;
+	return written ? written : err;
+}
 
-	kfree(pages);
-	*ppos = pos;
+static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
+				    const struct iovec *iov,
+				    unsigned long nr_segs, loff_t pos)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = fdentry(file)->d_inode;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	loff_t *ppos = &iocb->ki_pos;
+	ssize_t num_written = 0;
+	ssize_t err = 0;
+	size_t count, ocount;
+
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
+	mutex_lock(&inode->i_mutex);
+
+	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
+	count = ocount;
+
+	current->backing_dev_info = inode->i_mapping->backing_dev_info;
+	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
+
+	if (count == 0) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
+
+	err = file_remove_suid(file);
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
+
+	/*
+	 * If BTRFS flips readonly due to some impossible error
+	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
+	 * although we have opened a file as writable, we have
+	 * to stop this write operation to ensure FS consistency.
+	 */
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		mutex_unlock(&inode->i_mutex);
+		err = -EROFS;
+		goto out;
+	}
+
+	file_update_time(file);
+	BTRFS_I(inode)->sequence++;
+
+	if (unlikely(file->f_flags & O_DIRECT)) {
+		num_written = __btrfs_direct_write(iocb, iov, nr_segs,
+						   pos, ppos, count, ocount);
+	} else {
+		struct iov_iter i;
+
+		iov_iter_init(&i, iov, nr_segs, count, num_written);
+
+		num_written = __btrfs_buffered_write(file, &i, pos);
+		if (num_written > 0)
+			*ppos = pos + num_written;
+	}
+
+	mutex_unlock(&inode->i_mutex);
 
 	/*
 	 * we want to make sure fsync finds this change
@@ -1118,43 +1154,12 @@ out:
 	 * one running right now.
 	 */
 	BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
-
-	if (num_written > 0 && will_write) {
-		struct btrfs_trans_handle *trans;
-
-		err = btrfs_wait_ordered_range(inode, start_pos, num_written);
-		if (err)
+	if (num_written > 0 || num_written == -EIOCBQUEUED) {
+		err = generic_write_sync(file, pos, num_written);
+		if (err < 0 && num_written > 0)
 			num_written = err;
-
-		if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
-			trans = btrfs_start_transaction(root, 0);
-			if (IS_ERR(trans)) {
-				num_written = PTR_ERR(trans);
-				goto done;
-			}
-			mutex_lock(&inode->i_mutex);
-			ret = btrfs_log_dentry_safe(trans, root,
-						    file->f_dentry);
-			mutex_unlock(&inode->i_mutex);
-			if (ret == 0) {
-				ret = btrfs_sync_log(trans, root);
-				if (ret == 0)
-					btrfs_end_transaction(trans, root);
-				else
-					btrfs_commit_transaction(trans, root);
-			} else if (ret != BTRFS_NO_LOG_SYNC) {
-				btrfs_commit_transaction(trans, root);
-			} else {
-				btrfs_end_transaction(trans, root);
-			}
-		}
-		if (file->f_flags & O_DIRECT && buffered) {
-			invalidate_mapping_pages(inode->i_mapping,
-			      start_pos >> PAGE_CACHE_SHIFT,
-			     (start_pos + num_written - 1) >> PAGE_CACHE_SHIFT);
-		}
 	}
-done:
+out:
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;
 }
@@ -1197,6 +1202,7 @@ int btrfs_sync_file(struct file *file, int datasync)
 	int ret = 0;
 	struct btrfs_trans_handle *trans;
 
+	trace_btrfs_sync_file(file, datasync);
 
 	/* we wait first, since the writeback may change the inode */
 	root->log_batch++;
@@ -1324,7 +1330,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 		goto out;
 
 	if (alloc_start > inode->i_size) {
-		ret = btrfs_cont_expand(inode, alloc_start);
+		ret = btrfs_cont_expand(inode, i_size_read(inode),
+					alloc_start);
 		if (ret)
 			goto out;
 	}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index a0390657451..63731a1fb0a 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -24,6 +24,7 @@
 #include "free-space-cache.h"
 #include "transaction.h"
 #include "disk-io.h"
+#include "extent_io.h"
 
 #define BITS_PER_BITMAP		(PAGE_CACHE_SIZE * 8)
 #define MAX_CACHE_BYTES_PER_GIG	(32 * 1024)
@@ -81,6 +82,8 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 		return ERR_PTR(-ENOENT);
 	}
 
+	inode->i_mapping->flags &= ~__GFP_FS;
+
 	spin_lock(&block_group->lock);
 	if (!root->fs_info->closing) {
 		block_group->inode = igrab(inode);
@@ -222,6 +225,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 	u64 num_entries;
 	u64 num_bitmaps;
 	u64 generation;
+	u64 used = btrfs_block_group_used(&block_group->item);
 	u32 cur_crc = ~(u32)0;
 	pgoff_t index = 0;
 	unsigned long first_page_offset;
@@ -393,7 +397,8 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 				break;
 
 			need_loop = 1;
-			e = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
+			e = kmem_cache_zalloc(btrfs_free_space_cachep,
+					      GFP_NOFS);
 			if (!e) {
 				kunmap(page);
 				unlock_page(page);
@@ -405,7 +410,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 			e->bytes = le64_to_cpu(entry->bytes);
 			if (!e->bytes) {
 				kunmap(page);
-				kfree(e);
+				kmem_cache_free(btrfs_free_space_cachep, e);
 				unlock_page(page);
 				page_cache_release(page);
 				goto free_cache;
@@ -420,7 +425,8 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 				e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
 				if (!e->bitmap) {
 					kunmap(page);
-					kfree(e);
+					kmem_cache_free(
+						btrfs_free_space_cachep, e);
 					unlock_page(page);
 					page_cache_release(page);
 					goto free_cache;
@@ -465,6 +471,17 @@ next:
 		index++;
 	}
 
+	spin_lock(&block_group->tree_lock);
+	if (block_group->free_space != (block_group->key.offset - used -
+					block_group->bytes_super)) {
+		spin_unlock(&block_group->tree_lock);
+		printk(KERN_ERR "block group %llu has an wrong amount of free "
+		       "space\n", block_group->key.objectid);
+		ret = 0;
+		goto free_cache;
+	}
+	spin_unlock(&block_group->tree_lock);
+
 	ret = 1;
 out:
 	kfree(checksums);
@@ -491,18 +508,23 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	struct inode *inode;
 	struct rb_node *node;
 	struct list_head *pos, *n;
+	struct page **pages;
 	struct page *page;
 	struct extent_state *cached_state = NULL;
+	struct btrfs_free_cluster *cluster = NULL;
+	struct extent_io_tree *unpin = NULL;
 	struct list_head bitmap_list;
 	struct btrfs_key key;
+	u64 start, end, len;
 	u64 bytes = 0;
 	u32 *crc, *checksums;
-	pgoff_t index = 0, last_index = 0;
 	unsigned long first_page_offset;
-	int num_checksums;
+	int index = 0, num_pages = 0;
 	int entries = 0;
 	int bitmaps = 0;
 	int ret = 0;
+	bool next_page = false;
+	bool out_of_space = false;
 
 	root = root->fs_info->tree_root;
 
@@ -530,24 +552,43 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		return 0;
 	}
 
-	last_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
+	num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
+		PAGE_CACHE_SHIFT;
 	filemap_write_and_wait(inode->i_mapping);
 	btrfs_wait_ordered_range(inode, inode->i_size &
 				 ~(root->sectorsize - 1), (u64)-1);
 
 	/* We need a checksum per page. */
-	num_checksums = i_size_read(inode) / PAGE_CACHE_SIZE;
-	crc = checksums  = kzalloc(sizeof(u32) * num_checksums, GFP_NOFS);
+	crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
 	if (!crc) {
 		iput(inode);
 		return 0;
 	}
 
+	pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS);
+	if (!pages) {
+		kfree(crc);
+		iput(inode);
+		return 0;
+	}
+
 	/* Since the first page has all of our checksums and our generation we
 	 * need to calculate the offset into the page that we can start writing
 	 * our entries.
 	 */
-	first_page_offset = (sizeof(u32) * num_checksums) + sizeof(u64);
+	first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
+
+	/* Get the cluster for this block_group if it exists */
+	if (!list_empty(&block_group->cluster_list))
+		cluster = list_entry(block_group->cluster_list.next,
+				     struct btrfs_free_cluster,
+				     block_group_list);
+
+	/*
+	 * We shouldn't have switched the pinned extents yet so this is the
+	 * right one
+	 */
+	unpin = root->fs_info->pinned_extents;
 
 	/*
 	 * Lock all pages first so we can lock the extent safely.
@@ -557,20 +598,18 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	 * after find_get_page at this point.  Just putting this here so people
 	 * know and don't freak out.
 	 */
-	while (index <= last_index) {
+	while (index < num_pages) {
 		page = grab_cache_page(inode->i_mapping, index);
 		if (!page) {
-			pgoff_t i = 0;
+			int i;
 
-			while (i < index) {
-				page = find_get_page(inode->i_mapping, i);
-				unlock_page(page);
-				page_cache_release(page);
-				page_cache_release(page);
-				i++;
+			for (i = 0; i < num_pages; i++) {
+				unlock_page(pages[i]);
+				page_cache_release(pages[i]);
 			}
 			goto out_free;
 		}
+		pages[index] = page;
 		index++;
 	}
 
@@ -578,6 +617,12 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
 			 0, &cached_state, GFP_NOFS);
 
+	/*
+	 * When searching for pinned extents, we need to start at our start
+	 * offset.
+	 */
+	start = block_group->key.objectid;
+
 	/* Write out the extent entries */
 	do {
 		struct btrfs_free_space_entry *entry;
@@ -585,18 +630,25 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		unsigned long offset = 0;
 		unsigned long start_offset = 0;
 
+		next_page = false;
+
 		if (index == 0) {
 			start_offset = first_page_offset;
 			offset = start_offset;
 		}
 
-		page = find_get_page(inode->i_mapping, index);
+		if (index >= num_pages) {
+			out_of_space = true;
+			break;
+		}
+
+		page = pages[index];
 
 		addr = kmap(page);
 		entry = addr + start_offset;
 
 		memset(addr, 0, PAGE_CACHE_SIZE);
-		while (1) {
+		while (node && !next_page) {
 			struct btrfs_free_space *e;
 
 			e = rb_entry(node, struct btrfs_free_space, offset_index);
@@ -612,12 +664,49 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 				entry->type = BTRFS_FREE_SPACE_EXTENT;
 			}
 			node = rb_next(node);
-			if (!node)
-				break;
+			if (!node && cluster) {
+				node = rb_first(&cluster->root);
+				cluster = NULL;
+			}
 			offset += sizeof(struct btrfs_free_space_entry);
 			if (offset + sizeof(struct btrfs_free_space_entry) >=
 			    PAGE_CACHE_SIZE)
+				next_page = true;
+			entry++;
+		}
+
+		/*
+		 * We want to add any pinned extents to our free space cache
+		 * so we don't leak the space
+		 */
+		while (!next_page && (start < block_group->key.objectid +
+				      block_group->key.offset)) {
+			ret = find_first_extent_bit(unpin, start, &start, &end,
+						    EXTENT_DIRTY);
+			if (ret) {
+				ret = 0;
+				break;
+			}
+
+			/* This pinned extent is out of our range */
+			if (start >= block_group->key.objectid +
+			    block_group->key.offset)
 				break;
+
+			len = block_group->key.objectid +
+				block_group->key.offset - start;
+			len = min(len, end + 1 - start);
+
+			entries++;
+			entry->offset = cpu_to_le64(start);
+			entry->bytes = cpu_to_le64(len);
+			entry->type = BTRFS_FREE_SPACE_EXTENT;
+
+			start = end + 1;
+			offset += sizeof(struct btrfs_free_space_entry);
+			if (offset + sizeof(struct btrfs_free_space_entry) >=
+			    PAGE_CACHE_SIZE)
+				next_page = true;
 			entry++;
 		}
 		*crc = ~(u32)0;
@@ -630,25 +719,8 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 
 		bytes += PAGE_CACHE_SIZE;
 
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-
-		/*
-		 * We need to release our reference we got for grab_cache_page,
-		 * except for the first page which will hold our checksums, we
-		 * do that below.
-		 */
-		if (index != 0) {
-			unlock_page(page);
-			page_cache_release(page);
-		}
-
-		page_cache_release(page);
-
 		index++;
-	} while (node);
+	} while (node || next_page);
 
 	/* Write out the bitmaps */
 	list_for_each_safe(pos, n, &bitmap_list) {
@@ -656,7 +728,11 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		struct btrfs_free_space *entry =
 			list_entry(pos, struct btrfs_free_space, list);
 
-		page = find_get_page(inode->i_mapping, index);
+		if (index >= num_pages) {
+			out_of_space = true;
+			break;
+		}
+		page = pages[index];
 
 		addr = kmap(page);
 		memcpy(addr, entry->bitmap, PAGE_CACHE_SIZE);
@@ -667,64 +743,58 @@ int btrfs_write_out_cache(struct btrfs_root *root,
 		crc++;
 		bytes += PAGE_CACHE_SIZE;
 
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 		list_del_init(&entry->list);
 		index++;
 	}
 
+	if (out_of_space) {
+		btrfs_drop_pages(pages, num_pages);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
+				     i_size_read(inode) - 1, &cached_state,
+				     GFP_NOFS);
+		ret = 0;
+		goto out_free;
+	}
+
 	/* Zero out the rest of the pages just to make sure */
-	while (index <= last_index) {
+	while (index < num_pages) {
 		void *addr;
 
-		page = find_get_page(inode->i_mapping, index);
-
+		page = pages[index];
 		addr = kmap(page);
 		memset(addr, 0, PAGE_CACHE_SIZE);
 		kunmap(page);
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 		bytes += PAGE_CACHE_SIZE;
 		index++;
 	}
 
-	btrfs_set_extent_delalloc(inode, 0, bytes - 1, &cached_state);
-
 	/* Write the checksums and trans id to the first page */
 	{
 		void *addr;
 		u64 *gen;
 
-		page = find_get_page(inode->i_mapping, 0);
+		page = pages[0];
 
 		addr = kmap(page);
-		memcpy(addr, checksums, sizeof(u32) * num_checksums);
-		gen = addr + (sizeof(u32) * num_checksums);
+		memcpy(addr, checksums, sizeof(u32) * num_pages);
+		gen = addr + (sizeof(u32) * num_pages);
 		*gen = trans->transid;
 		kunmap(page);
-		ClearPageChecked(page);
-		set_page_extent_mapped(page);
-		SetPageUptodate(page);
-		set_page_dirty(page);
-		unlock_page(page);
-		page_cache_release(page);
-		page_cache_release(page);
 	}
-	BTRFS_I(inode)->generation = trans->transid;
 
+	ret = btrfs_dirty_pages(root, inode, pages, num_pages, 0,
+					    bytes, &cached_state);
+	btrfs_drop_pages(pages, num_pages);
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
 			     i_size_read(inode) - 1, &cached_state, GFP_NOFS);
 
+	if (ret) {
+		ret = 0;
+		goto out_free;
+	}
+
+	BTRFS_I(inode)->generation = trans->transid;
+
 	filemap_write_and_wait(inode->i_mapping);
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
@@ -775,6 +845,7 @@ out_free:
 		BTRFS_I(inode)->generation = 0;
 	}
 	kfree(checksums);
+	kfree(pages);
 	btrfs_update_inode(trans, root, inode);
 	iput(inode);
 	return ret;
@@ -1187,7 +1258,7 @@ static void free_bitmap(struct btrfs_block_group_cache *block_group,
 {
 	unlink_free_space(block_group, bitmap_info);
 	kfree(bitmap_info->bitmap);
-	kfree(bitmap_info);
+	kmem_cache_free(btrfs_free_space_cachep, bitmap_info);
 	block_group->total_bitmaps--;
 	recalculate_thresholds(block_group);
 }
@@ -1285,9 +1356,22 @@ static int insert_into_bitmap(struct btrfs_block_group_cache *block_group,
 	 * If we are below the extents threshold then we can add this as an
 	 * extent, and don't have to deal with the bitmap
 	 */
-	if (block_group->free_extents < block_group->extents_thresh &&
-	    info->bytes > block_group->sectorsize * 4)
-		return 0;
+	if (block_group->free_extents < block_group->extents_thresh) {
+		/*
+		 * If this block group has some small extents we don't want to
+		 * use up all of our free slots in the cache with them, we want
+		 * to reserve them to larger extents, however if we have plent
+		 * of cache left then go ahead an dadd them, no sense in adding
+		 * the overhead of a bitmap if we don't have to.
+		 */
+		if (info->bytes <= block_group->sectorsize * 4) {
+			if (block_group->free_extents * 2 <=
+			    block_group->extents_thresh)
+				return 0;
+		} else {
+			return 0;
+		}
+	}
 
 	/*
 	 * some block groups are so tiny they can't be enveloped by a bitmap, so
@@ -1342,8 +1426,8 @@ new_bitmap:
 
 		/* no pre-allocated info, allocate a new one */
 		if (!info) {
-			info = kzalloc(sizeof(struct btrfs_free_space),
-				       GFP_NOFS);
+			info = kmem_cache_zalloc(btrfs_free_space_cachep,
+						 GFP_NOFS);
 			if (!info) {
 				spin_lock(&block_group->tree_lock);
 				ret = -ENOMEM;
@@ -1365,7 +1449,7 @@ out:
 	if (info) {
 		if (info->bitmap)
 			kfree(info->bitmap);
-		kfree(info);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 	}
 
 	return ret;
@@ -1398,7 +1482,7 @@ bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
 		else
 			__unlink_free_space(block_group, right_info);
 		info->bytes += right_info->bytes;
-		kfree(right_info);
+		kmem_cache_free(btrfs_free_space_cachep, right_info);
 		merged = true;
 	}
 
@@ -1410,7 +1494,7 @@ bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
 			__unlink_free_space(block_group, left_info);
 		info->offset = left_info->offset;
 		info->bytes += left_info->bytes;
-		kfree(left_info);
+		kmem_cache_free(btrfs_free_space_cachep, left_info);
 		merged = true;
 	}
 
@@ -1423,7 +1507,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 	struct btrfs_free_space *info;
 	int ret = 0;
 
-	info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
+	info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
 	if (!info)
 		return -ENOMEM;
 
@@ -1450,7 +1534,7 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
 link:
 	ret = link_free_space(block_group, info);
 	if (ret)
-		kfree(info);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 out:
 	spin_unlock(&block_group->tree_lock);
 
@@ -1520,7 +1604,7 @@ again:
 			kfree(info->bitmap);
 			block_group->total_bitmaps--;
 		}
-		kfree(info);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 		goto out_lock;
 	}
 
@@ -1556,7 +1640,7 @@ again:
 			/* the hole we're creating ends at the end
 			 * of the info struct, just free the info
 			 */
-			kfree(info);
+			kmem_cache_free(btrfs_free_space_cachep, info);
 		}
 		spin_unlock(&block_group->tree_lock);
 
@@ -1629,30 +1713,28 @@ __btrfs_return_cluster_to_free_space(
 {
 	struct btrfs_free_space *entry;
 	struct rb_node *node;
-	bool bitmap;
 
 	spin_lock(&cluster->lock);
 	if (cluster->block_group != block_group)
 		goto out;
 
-	bitmap = cluster->points_to_bitmap;
 	cluster->block_group = NULL;
 	cluster->window_start = 0;
 	list_del_init(&cluster->block_group_list);
-	cluster->points_to_bitmap = false;
-
-	if (bitmap)
-		goto out;
 
 	node = rb_first(&cluster->root);
 	while (node) {
+		bool bitmap;
+
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 		node = rb_next(&entry->offset_index);
 		rb_erase(&entry->offset_index, &cluster->root);
-		BUG_ON(entry->bitmap);
-		try_merge_free_space(block_group, entry, false);
+
+		bitmap = (entry->bitmap != NULL);
+		if (!bitmap)
+			try_merge_free_space(block_group, entry, false);
 		tree_insert_offset(&block_group->free_space_offset,
-				   entry->offset, &entry->offset_index, 0);
+				   entry->offset, &entry->offset_index, bitmap);
 	}
 	cluster->root = RB_ROOT;
 
@@ -1686,10 +1768,13 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 
 	while ((node = rb_last(&block_group->free_space_offset)) != NULL) {
 		info = rb_entry(node, struct btrfs_free_space, offset_index);
-		unlink_free_space(block_group, info);
-		if (info->bitmap)
-			kfree(info->bitmap);
-		kfree(info);
+		if (!info->bitmap) {
+			unlink_free_space(block_group, info);
+			kmem_cache_free(btrfs_free_space_cachep, info);
+		} else {
+			free_bitmap(block_group, info);
+		}
+
 		if (need_resched()) {
 			spin_unlock(&block_group->tree_lock);
 			cond_resched();
@@ -1722,7 +1807,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
 		entry->offset += bytes;
 		entry->bytes -= bytes;
 		if (!entry->bytes)
-			kfree(entry);
+			kmem_cache_free(btrfs_free_space_cachep, entry);
 		else
 			link_free_space(block_group, entry);
 	}
@@ -1775,50 +1860,24 @@ int btrfs_return_cluster_to_free_space(
 
 static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 				   struct btrfs_free_cluster *cluster,
+				   struct btrfs_free_space *entry,
 				   u64 bytes, u64 min_start)
 {
-	struct btrfs_free_space *entry;
 	int err;
 	u64 search_start = cluster->window_start;
 	u64 search_bytes = bytes;
 	u64 ret = 0;
 
-	spin_lock(&block_group->tree_lock);
-	spin_lock(&cluster->lock);
-
-	if (!cluster->points_to_bitmap)
-		goto out;
-
-	if (cluster->block_group != block_group)
-		goto out;
-
-	/*
-	 * search_start is the beginning of the bitmap, but at some point it may
-	 * be a good idea to point to the actual start of the free area in the
-	 * bitmap, so do the offset_to_bitmap trick anyway, and set bitmap_only
-	 * to 1 to make sure we get the bitmap entry
-	 */
-	entry = tree_search_offset(block_group,
-				   offset_to_bitmap(block_group, search_start),
-				   1, 0);
-	if (!entry || !entry->bitmap)
-		goto out;
-
 	search_start = min_start;
 	search_bytes = bytes;
 
 	err = search_bitmap(block_group, entry, &search_start,
 			    &search_bytes);
 	if (err)
-		goto out;
+		return 0;
 
 	ret = search_start;
 	bitmap_clear_bits(block_group, entry, ret, bytes);
-	if (entry->bytes == 0)
-		free_bitmap(block_group, entry);
-out:
-	spin_unlock(&cluster->lock);
-	spin_unlock(&block_group->tree_lock);
 
 	return ret;
 }
@@ -1836,10 +1895,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 	struct rb_node *node;
 	u64 ret = 0;
 
-	if (cluster->points_to_bitmap)
-		return btrfs_alloc_from_bitmap(block_group, cluster, bytes,
-					       min_start);
-
 	spin_lock(&cluster->lock);
 	if (bytes > cluster->max_size)
 		goto out;
@@ -1852,9 +1907,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 		goto out;
 
 	entry = rb_entry(node, struct btrfs_free_space, offset_index);
-
 	while(1) {
-		if (entry->bytes < bytes || entry->offset < min_start) {
+		if (entry->bytes < bytes ||
+		    (!entry->bitmap && entry->offset < min_start)) {
 			struct rb_node *node;
 
 			node = rb_next(&entry->offset_index);
@@ -1864,10 +1919,27 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 					 offset_index);
 			continue;
 		}
-		ret = entry->offset;
 
-		entry->offset += bytes;
-		entry->bytes -= bytes;
+		if (entry->bitmap) {
+			ret = btrfs_alloc_from_bitmap(block_group,
+						      cluster, entry, bytes,
+						      min_start);
+			if (ret == 0) {
+				struct rb_node *node;
+				node = rb_next(&entry->offset_index);
+				if (!node)
+					break;
+				entry = rb_entry(node, struct btrfs_free_space,
+						 offset_index);
+				continue;
+			}
+		} else {
+
+			ret = entry->offset;
+
+			entry->offset += bytes;
+			entry->bytes -= bytes;
+		}
 
 		if (entry->bytes == 0)
 			rb_erase(&entry->offset_index, &cluster->root);
@@ -1884,7 +1956,12 @@ out:
 	block_group->free_space -= bytes;
 	if (entry->bytes == 0) {
 		block_group->free_extents--;
-		kfree(entry);
+		if (entry->bitmap) {
+			kfree(entry->bitmap);
+			block_group->total_bitmaps--;
+			recalculate_thresholds(block_group);
+		}
+		kmem_cache_free(btrfs_free_space_cachep, entry);
 	}
 
 	spin_unlock(&block_group->tree_lock);
@@ -1904,12 +1981,13 @@ static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
 	unsigned long found_bits;
 	unsigned long start = 0;
 	unsigned long total_found = 0;
+	int ret;
 	bool found = false;
 
 	i = offset_to_bit(entry->offset, block_group->sectorsize,
 			  max_t(u64, offset, entry->offset));
-	search_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
-	total_bits = bytes_to_bits(bytes, block_group->sectorsize);
+	search_bits = bytes_to_bits(bytes, block_group->sectorsize);
+	total_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
 
 again:
 	found_bits = 0;
@@ -1926,7 +2004,7 @@ again:
 	}
 
 	if (!found_bits)
-		return -1;
+		return -ENOSPC;
 
 	if (!found) {
 		start = i;
@@ -1950,189 +2028,208 @@ again:
 
 	cluster->window_start = start * block_group->sectorsize +
 		entry->offset;
-	cluster->points_to_bitmap = true;
+	rb_erase(&entry->offset_index, &block_group->free_space_offset);
+	ret = tree_insert_offset(&cluster->root, entry->offset,
+				 &entry->offset_index, 1);
+	BUG_ON(ret);
 
 	return 0;
 }
 
 /*
- * here we try to find a cluster of blocks in a block group.  The goal
- * is to find at least bytes free and up to empty_size + bytes free.
- * We might not find them all in one contiguous area.
- *
- * returns zero and sets up cluster if things worked out, otherwise
- * it returns -enospc
+ * This searches the block group for just extents to fill the cluster with.
  */
-int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
-			     struct btrfs_root *root,
-			     struct btrfs_block_group_cache *block_group,
-			     struct btrfs_free_cluster *cluster,
-			     u64 offset, u64 bytes, u64 empty_size)
+static int setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
+				   struct btrfs_free_cluster *cluster,
+				   u64 offset, u64 bytes, u64 min_bytes)
 {
+	struct btrfs_free_space *first = NULL;
 	struct btrfs_free_space *entry = NULL;
+	struct btrfs_free_space *prev = NULL;
+	struct btrfs_free_space *last;
 	struct rb_node *node;
-	struct btrfs_free_space *next;
-	struct btrfs_free_space *last = NULL;
-	u64 min_bytes;
 	u64 window_start;
 	u64 window_free;
-	u64 max_extent = 0;
-	bool found_bitmap = false;
-	int ret;
-
-	/* for metadata, allow allocates with more holes */
-	if (btrfs_test_opt(root, SSD_SPREAD)) {
-		min_bytes = bytes + empty_size;
-	} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
-		/*
-		 * we want to do larger allocations when we are
-		 * flushing out the delayed refs, it helps prevent
-		 * making more work as we go along.
-		 */
-		if (trans->transaction->delayed_refs.flushing)
-			min_bytes = max(bytes, (bytes + empty_size) >> 1);
-		else
-			min_bytes = max(bytes, (bytes + empty_size) >> 4);
-	} else
-		min_bytes = max(bytes, (bytes + empty_size) >> 2);
-
-	spin_lock(&block_group->tree_lock);
-	spin_lock(&cluster->lock);
+	u64 max_extent;
+	u64 max_gap = 128 * 1024;
 
-	/* someone already found a cluster, hooray */
-	if (cluster->block_group) {
-		ret = 0;
-		goto out;
-	}
-again:
-	entry = tree_search_offset(block_group, offset, found_bitmap, 1);
-	if (!entry) {
-		ret = -ENOSPC;
-		goto out;
-	}
+	entry = tree_search_offset(block_group, offset, 0, 1);
+	if (!entry)
+		return -ENOSPC;
 
 	/*
-	 * If found_bitmap is true, we exhausted our search for extent entries,
-	 * and we just want to search all of the bitmaps that we can find, and
-	 * ignore any extent entries we find.
+	 * We don't want bitmaps, so just move along until we find a normal
+	 * extent entry.
 	 */
-	while (entry->bitmap || found_bitmap ||
-	       (!entry->bitmap && entry->bytes < min_bytes)) {
-		struct rb_node *node = rb_next(&entry->offset_index);
-
-		if (entry->bitmap && entry->bytes > bytes + empty_size) {
-			ret = btrfs_bitmap_cluster(block_group, entry, cluster,
-						   offset, bytes + empty_size,
-						   min_bytes);
-			if (!ret)
-				goto got_it;
-		}
-
-		if (!node) {
-			ret = -ENOSPC;
-			goto out;
-		}
+	while (entry->bitmap) {
+		node = rb_next(&entry->offset_index);
+		if (!node)
+			return -ENOSPC;
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 	}
 
-	/*
-	 * We already searched all the extent entries from the passed in offset
-	 * to the end and didn't find enough space for the cluster, and we also
-	 * didn't find any bitmaps that met our criteria, just go ahead and exit
-	 */
-	if (found_bitmap) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	cluster->points_to_bitmap = false;
 	window_start = entry->offset;
 	window_free = entry->bytes;
-	last = entry;
 	max_extent = entry->bytes;
+	first = entry;
+	last = entry;
+	prev = entry;
 
-	while (1) {
-		/* out window is just right, lets fill it */
-		if (window_free >= bytes + empty_size)
-			break;
-
-		node = rb_next(&last->offset_index);
-		if (!node) {
-			if (found_bitmap)
-				goto again;
-			ret = -ENOSPC;
-			goto out;
-		}
-		next = rb_entry(node, struct btrfs_free_space, offset_index);
+	while (window_free <= min_bytes) {
+		node = rb_next(&entry->offset_index);
+		if (!node)
+			return -ENOSPC;
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 
-		/*
-		 * we found a bitmap, so if this search doesn't result in a
-		 * cluster, we know to go and search again for the bitmaps and
-		 * start looking for space there
-		 */
-		if (next->bitmap) {
-			if (!found_bitmap)
-				offset = next->offset;
-			found_bitmap = true;
-			last = next;
+		if (entry->bitmap)
 			continue;
-		}
-
 		/*
 		 * we haven't filled the empty size and the window is
 		 * very large.  reset and try again
 		 */
-		if (next->offset - (last->offset + last->bytes) > 128 * 1024 ||
-		    next->offset - window_start > (bytes + empty_size) * 2) {
-			entry = next;
+		if (entry->offset - (prev->offset + prev->bytes) > max_gap ||
+		    entry->offset - window_start > (min_bytes * 2)) {
+			first = entry;
 			window_start = entry->offset;
 			window_free = entry->bytes;
 			last = entry;
 			max_extent = entry->bytes;
 		} else {
-			last = next;
-			window_free += next->bytes;
+			last = entry;
+			window_free += entry->bytes;
 			if (entry->bytes > max_extent)
 				max_extent = entry->bytes;
 		}
+		prev = entry;
 	}
 
-	cluster->window_start = entry->offset;
+	cluster->window_start = first->offset;
+
+	node = &first->offset_index;
 
 	/*
 	 * now we've found our entries, pull them out of the free space
 	 * cache and put them into the cluster rbtree
-	 *
-	 * The cluster includes an rbtree, but only uses the offset index
-	 * of each free space cache entry.
 	 */
-	while (1) {
+	do {
+		int ret;
+
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 		node = rb_next(&entry->offset_index);
-		if (entry->bitmap && node) {
-			entry = rb_entry(node, struct btrfs_free_space,
-					 offset_index);
+		if (entry->bitmap)
 			continue;
-		} else if (entry->bitmap && !node) {
-			break;
-		}
 
 		rb_erase(&entry->offset_index, &block_group->free_space_offset);
 		ret = tree_insert_offset(&cluster->root, entry->offset,
 					 &entry->offset_index, 0);
 		BUG_ON(ret);
+	} while (node && entry != last);
 
-		if (!node || entry == last)
-			break;
+	cluster->max_size = max_extent;
+
+	return 0;
+}
+
+/*
+ * This specifically looks for bitmaps that may work in the cluster, we assume
+ * that we have already failed to find extents that will work.
+ */
+static int setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
+				struct btrfs_free_cluster *cluster,
+				u64 offset, u64 bytes, u64 min_bytes)
+{
+	struct btrfs_free_space *entry;
+	struct rb_node *node;
+	int ret = -ENOSPC;
+
+	if (block_group->total_bitmaps == 0)
+		return -ENOSPC;
+
+	entry = tree_search_offset(block_group,
+				   offset_to_bitmap(block_group, offset),
+				   0, 1);
+	if (!entry)
+		return -ENOSPC;
 
+	node = &entry->offset_index;
+	do {
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
+		node = rb_next(&entry->offset_index);
+		if (!entry->bitmap)
+			continue;
+		if (entry->bytes < min_bytes)
+			continue;
+		ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
+					   bytes, min_bytes);
+	} while (ret && node);
+
+	return ret;
+}
+
+/*
+ * here we try to find a cluster of blocks in a block group.  The goal
+ * is to find at least bytes free and up to empty_size + bytes free.
+ * We might not find them all in one contiguous area.
+ *
+ * returns zero and sets up cluster if things worked out, otherwise
+ * it returns -enospc
+ */
+int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
+			     struct btrfs_root *root,
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster,
+			     u64 offset, u64 bytes, u64 empty_size)
+{
+	u64 min_bytes;
+	int ret;
+
+	/* for metadata, allow allocates with more holes */
+	if (btrfs_test_opt(root, SSD_SPREAD)) {
+		min_bytes = bytes + empty_size;
+	} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
+		/*
+		 * we want to do larger allocations when we are
+		 * flushing out the delayed refs, it helps prevent
+		 * making more work as we go along.
+		 */
+		if (trans->transaction->delayed_refs.flushing)
+			min_bytes = max(bytes, (bytes + empty_size) >> 1);
+		else
+			min_bytes = max(bytes, (bytes + empty_size) >> 4);
+	} else
+		min_bytes = max(bytes, (bytes + empty_size) >> 2);
+
+	spin_lock(&block_group->tree_lock);
+
+	/*
+	 * If we know we don't have enough space to make a cluster don't even
+	 * bother doing all the work to try and find one.
+	 */
+	if (block_group->free_space < min_bytes) {
+		spin_unlock(&block_group->tree_lock);
+		return -ENOSPC;
 	}
 
-	cluster->max_size = max_extent;
-got_it:
-	ret = 0;
-	atomic_inc(&block_group->count);
-	list_add_tail(&cluster->block_group_list, &block_group->cluster_list);
-	cluster->block_group = block_group;
+	spin_lock(&cluster->lock);
+
+	/* someone already found a cluster, hooray */
+	if (cluster->block_group) {
+		ret = 0;
+		goto out;
+	}
+
+	ret = setup_cluster_no_bitmap(block_group, cluster, offset, bytes,
+				      min_bytes);
+	if (ret)
+		ret = setup_cluster_bitmap(block_group, cluster, offset,
+					   bytes, min_bytes);
+
+	if (!ret) {
+		atomic_inc(&block_group->count);
+		list_add_tail(&cluster->block_group_list,
+			      &block_group->cluster_list);
+		cluster->block_group = block_group;
+	}
 out:
 	spin_unlock(&cluster->lock);
 	spin_unlock(&block_group->tree_lock);
@@ -2149,8 +2246,99 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
 	spin_lock_init(&cluster->refill_lock);
 	cluster->root = RB_ROOT;
 	cluster->max_size = 0;
-	cluster->points_to_bitmap = false;
 	INIT_LIST_HEAD(&cluster->block_group_list);
 	cluster->block_group = NULL;
 }
 
+int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+			   u64 *trimmed, u64 start, u64 end, u64 minlen)
+{
+	struct btrfs_free_space *entry = NULL;
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	u64 bytes = 0;
+	u64 actually_trimmed;
+	int ret = 0;
+
+	*trimmed = 0;
+
+	while (start < end) {
+		spin_lock(&block_group->tree_lock);
+
+		if (block_group->free_space < minlen) {
+			spin_unlock(&block_group->tree_lock);
+			break;
+		}
+
+		entry = tree_search_offset(block_group, start, 0, 1);
+		if (!entry)
+			entry = tree_search_offset(block_group,
+						   offset_to_bitmap(block_group,
+								    start),
+						   1, 1);
+
+		if (!entry || entry->offset >= end) {
+			spin_unlock(&block_group->tree_lock);
+			break;
+		}
+
+		if (entry->bitmap) {
+			ret = search_bitmap(block_group, entry, &start, &bytes);
+			if (!ret) {
+				if (start >= end) {
+					spin_unlock(&block_group->tree_lock);
+					break;
+				}
+				bytes = min(bytes, end - start);
+				bitmap_clear_bits(block_group, entry,
+						  start, bytes);
+				if (entry->bytes == 0)
+					free_bitmap(block_group, entry);
+			} else {
+				start = entry->offset + BITS_PER_BITMAP *
+					block_group->sectorsize;
+				spin_unlock(&block_group->tree_lock);
+				ret = 0;
+				continue;
+			}
+		} else {
+			start = entry->offset;
+			bytes = min(entry->bytes, end - start);
+			unlink_free_space(block_group, entry);
+			kmem_cache_free(btrfs_free_space_cachep, entry);
+		}
+
+		spin_unlock(&block_group->tree_lock);
+
+		if (bytes >= minlen) {
+			int update_ret;
+			update_ret = btrfs_update_reserved_bytes(block_group,
+								 bytes, 1, 1);
+
+			ret = btrfs_error_discard_extent(fs_info->extent_root,
+							 start,
+							 bytes,
+							 &actually_trimmed);
+
+			btrfs_add_free_space(block_group,
+					     start, bytes);
+			if (!update_ret)
+				btrfs_update_reserved_bytes(block_group,
+							    bytes, 0, 1);
+
+			if (ret)
+				break;
+			*trimmed += actually_trimmed;
+		}
+		start += bytes;
+		bytes = 0;
+
+		if (fatal_signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		cond_resched();
+	}
+
+	return ret;
+}
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index e49ca5c321b..65c3b935289 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -68,4 +68,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 int btrfs_return_cluster_to_free_space(
 			       struct btrfs_block_group_cache *block_group,
 			       struct btrfs_free_cluster *cluster);
+int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+			   u64 *trimmed, u64 start, u64 end, u64 minlen);
 #endif
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index c56eb590917..c05a08f4c41 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -30,7 +30,8 @@ int btrfs_find_highest_inode(struct btrfs_root *root, u64 *objectid)
 	int slot;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 
 	search_key.objectid = BTRFS_LAST_FREE_OBJECTID;
 	search_key.type = -1;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 512c3d1da08..7cd8ab0ef04 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -50,6 +50,7 @@
 #include "tree-log.h"
 #include "compression.h"
 #include "locking.h"
+#include "free-space-cache.h"
 
 struct btrfs_iget_args {
 	u64 ino;
@@ -70,6 +71,7 @@ static struct kmem_cache *btrfs_inode_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
 struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
+struct kmem_cache *btrfs_free_space_cachep;
 
 #define S_SHIFT 12
 static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
@@ -82,7 +84,8 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
 };
 
-static void btrfs_truncate(struct inode *inode);
+static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end);
 static noinline int cow_file_range(struct inode *inode,
 				   struct page *locked_page,
@@ -109,6 +112,7 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root, struct inode *inode,
 				u64 start, size_t size, size_t compressed_size,
+				int compress_type,
 				struct page **compressed_pages)
 {
 	struct btrfs_key key;
@@ -123,12 +127,9 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
 	size_t cur_size = size;
 	size_t datasize;
 	unsigned long offset;
-	int compress_type = BTRFS_COMPRESS_NONE;
 
-	if (compressed_size && compressed_pages) {
-		compress_type = root->fs_info->compress_type;
+	if (compressed_size && compressed_pages)
 		cur_size = compressed_size;
-	}
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -218,7 +219,7 @@ fail:
 static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 struct inode *inode, u64 start, u64 end,
-				 size_t compressed_size,
+				 size_t compressed_size, int compress_type,
 				 struct page **compressed_pages)
 {
 	u64 isize = i_size_read(inode);
@@ -251,7 +252,7 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
 		inline_len = min_t(u64, isize, actual_end);
 	ret = insert_inline_extent(trans, root, inode, start,
 				   inline_len, compressed_size,
-				   compressed_pages);
+				   compress_type, compressed_pages);
 	BUG_ON(ret);
 	btrfs_delalloc_release_metadata(inode, end + 1 - start);
 	btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
@@ -288,6 +289,7 @@ static noinline int add_async_extent(struct async_cow *cow,
 	struct async_extent *async_extent;
 
 	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
+	BUG_ON(!async_extent);
 	async_extent->start = start;
 	async_extent->ram_size = ram_size;
 	async_extent->compressed_size = compressed_size;
@@ -382,9 +384,11 @@ again:
 	 */
 	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) &&
 	    (btrfs_test_opt(root, COMPRESS) ||
-	     (BTRFS_I(inode)->force_compress))) {
+	     (BTRFS_I(inode)->force_compress) ||
+	     (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))) {
 		WARN_ON(pages);
 		pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+		BUG_ON(!pages);
 
 		if (BTRFS_I(inode)->force_compress)
 			compress_type = BTRFS_I(inode)->force_compress;
@@ -427,12 +431,13 @@ again:
 			 * to make an uncompressed inline extent.
 			 */
 			ret = cow_file_range_inline(trans, root, inode,
-						    start, end, 0, NULL);
+						    start, end, 0, 0, NULL);
 		} else {
 			/* try making a compressed inline extent */
 			ret = cow_file_range_inline(trans, root, inode,
 						    start, end,
-						    total_compressed, pages);
+						    total_compressed,
+						    compress_type, pages);
 		}
 		if (ret == 0) {
 			/*
@@ -786,7 +791,7 @@ static noinline int cow_file_range(struct inode *inode,
 	if (start == 0) {
 		/* lets try to make an inline extent */
 		ret = cow_file_range_inline(trans, root, inode,
-					    start, end, 0, NULL);
+					    start, end, 0, 0, NULL);
 		if (ret == 0) {
 			extent_clear_unlock_delalloc(inode,
 				     &BTRFS_I(inode)->io_tree,
@@ -949,6 +954,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 			 1, 0, NULL, GFP_NOFS);
 	while (start < end) {
 		async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS);
+		BUG_ON(!async_cow);
 		async_cow->inode = inode;
 		async_cow->root = root;
 		async_cow->locked_page = locked_page;
@@ -1254,7 +1260,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, 0, nr_written);
 	else if (!btrfs_test_opt(root, COMPRESS) &&
-		 !(BTRFS_I(inode)->force_compress))
+		 !(BTRFS_I(inode)->force_compress) &&
+		 !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS))
 		ret = cow_file_range(inode, locked_page, start, end,
 				      page_started, nr_written, 1);
 	else
@@ -1461,8 +1468,11 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 		if (bio_flags & EXTENT_BIO_COMPRESSED) {
 			return btrfs_submit_compressed_read(inode, bio,
 						    mirror_num, bio_flags);
-		} else if (!skip_sum)
-			btrfs_lookup_bio_sums(root, inode, bio, NULL);
+		} else if (!skip_sum) {
+			ret = btrfs_lookup_bio_sums(root, inode, bio, NULL);
+			if (ret)
+				return ret;
+		}
 		goto mapit;
 	} else if (!skip_sum) {
 		/* csum items have already been cloned */
@@ -1761,9 +1771,12 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
 	add_pending_csums(trans, inode, ordered_extent->file_offset,
 			  &ordered_extent->list);
 
-	btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-	ret = btrfs_update_inode(trans, root, inode);
-	BUG_ON(ret);
+	ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
+	if (!ret) {
+		ret = btrfs_update_inode(trans, root, inode);
+		BUG_ON(ret);
+	}
+	ret = 0;
 out:
 	if (nolock) {
 		if (trans)
@@ -1785,6 +1798,8 @@ out:
 static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 				struct extent_state *state, int uptodate)
 {
+	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
+
 	ClearPagePrivate2(page);
 	return btrfs_finish_ordered_io(page->mapping->host, start, end);
 }
@@ -1895,10 +1910,10 @@ static int btrfs_io_failed_hook(struct bio *failed_bio,
 	else
 		rw = READ;
 
-	BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
+	ret = BTRFS_I(inode)->io_tree.ops->submit_bio_hook(inode, rw, bio,
 						      failrec->last_mirror,
 						      failrec->bio_flags, 0);
-	return 0;
+	return ret;
 }
 
 /*
@@ -2210,8 +2225,6 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 			insert = 1;
 #endif
 		insert = 1;
-	} else {
-		WARN_ON(!BTRFS_I(inode)->orphan_meta_reserved);
 	}
 
 	if (!BTRFS_I(inode)->orphan_meta_reserved) {
@@ -2282,7 +2295,7 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode)
  * this cleans up any orphans that may be left on the list from the last use
  * of this root.
  */
-void btrfs_orphan_cleanup(struct btrfs_root *root)
+int btrfs_orphan_cleanup(struct btrfs_root *root)
 {
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
@@ -2292,10 +2305,13 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 	int ret = 0, nr_unlink = 0, nr_truncate = 0;
 
 	if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED))
-		return;
+		return 0;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	path->reada = -1;
 
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
@@ -2304,18 +2320,16 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
 	while (1) {
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-		if (ret < 0) {
-			printk(KERN_ERR "Error searching slot for orphan: %d"
-			       "\n", ret);
-			break;
-		}
+		if (ret < 0)
+			goto out;
 
 		/*
 		 * if ret == 0 means we found what we were searching for, which
-		 * is weird, but possible, so only screw with path if we didnt
+		 * is weird, but possible, so only screw with path if we didn't
 		 * find the key and see if we have stuff that matches
 		 */
 		if (ret > 0) {
+			ret = 0;
 			if (path->slots[0] == 0)
 				break;
 			path->slots[0]--;
@@ -2343,7 +2357,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 		found_key.type = BTRFS_INODE_ITEM_KEY;
 		found_key.offset = 0;
 		inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
-		BUG_ON(IS_ERR(inode));
+		if (IS_ERR(inode)) {
+			ret = PTR_ERR(inode);
+			goto out;
+		}
 
 		/*
 		 * add this inode to the orphan list so btrfs_orphan_del does
@@ -2361,7 +2378,10 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 		 */
 		if (is_bad_inode(inode)) {
 			trans = btrfs_start_transaction(root, 0);
-			BUG_ON(IS_ERR(trans));
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+				goto out;
+			}
 			btrfs_orphan_del(trans, inode);
 			btrfs_end_transaction(trans, root);
 			iput(inode);
@@ -2370,17 +2390,22 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
 		/* if we have links, this was a truncate, lets do that */
 		if (inode->i_nlink) {
+			if (!S_ISREG(inode->i_mode)) {
+				WARN_ON(1);
+				iput(inode);
+				continue;
+			}
 			nr_truncate++;
-			btrfs_truncate(inode);
+			ret = btrfs_truncate(inode);
 		} else {
 			nr_unlink++;
 		}
 
 		/* this will do delete_inode and everything for us */
 		iput(inode);
+		if (ret)
+			goto out;
 	}
-	btrfs_free_path(path);
-
 	root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE;
 
 	if (root->orphan_block_rsv)
@@ -2389,14 +2414,20 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
 
 	if (root->orphan_block_rsv || root->orphan_item_inserted) {
 		trans = btrfs_join_transaction(root, 1);
-		BUG_ON(IS_ERR(trans));
-		btrfs_end_transaction(trans, root);
+		if (!IS_ERR(trans))
+			btrfs_end_transaction(trans, root);
 	}
 
 	if (nr_unlink)
 		printk(KERN_INFO "btrfs: unlinked %d orphans\n", nr_unlink);
 	if (nr_truncate)
 		printk(KERN_INFO "btrfs: truncated %d orphans\n", nr_truncate);
+
+out:
+	if (ret)
+		printk(KERN_CRIT "btrfs: could not do orphan cleanup %d\n", ret);
+	btrfs_free_path(path);
+	return ret;
 }
 
 /*
@@ -2563,6 +2594,13 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 			    struct btrfs_inode_item *item,
 			    struct inode *inode)
 {
+	if (!leaf->map_token)
+		map_private_extent_buffer(leaf, (unsigned long)item,
+					  sizeof(struct btrfs_inode_item),
+					  &leaf->map_token, &leaf->kaddr,
+					  &leaf->map_start, &leaf->map_len,
+					  KM_USER1);
+
 	btrfs_set_inode_uid(leaf, item, inode->i_uid);
 	btrfs_set_inode_gid(leaf, item, inode->i_gid);
 	btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
@@ -2591,6 +2629,11 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 	btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
 	btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
 	btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+
+	if (leaf->map_token) {
+		unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+		leaf->map_token = NULL;
+	}
 }
 
 /*
@@ -2635,10 +2678,10 @@ failed:
  * recovery code.  It remove a link in a directory with a given name, and
  * also drops the back refs in the inode to the directory
  */
-int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root,
-		       struct inode *dir, struct inode *inode,
-		       const char *name, int name_len)
+static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct inode *dir, struct inode *inode,
+				const char *name, int name_len)
 {
 	struct btrfs_path *path;
 	int ret = 0;
@@ -2710,12 +2753,25 @@ err:
 	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
 	inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
 	btrfs_update_inode(trans, root, dir);
-	btrfs_drop_nlink(inode);
-	ret = btrfs_update_inode(trans, root, inode);
 out:
 	return ret;
 }
 
+int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root,
+		       struct inode *dir, struct inode *inode,
+		       const char *name, int name_len)
+{
+	int ret;
+	ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
+	if (!ret) {
+		btrfs_drop_nlink(inode);
+		ret = btrfs_update_inode(trans, root, inode);
+	}
+	return ret;
+}
+		
+
 /* helper to check if there is any shared block in the path */
 static int check_path_shared(struct btrfs_root *root,
 			     struct btrfs_path *path)
@@ -3537,7 +3593,13 @@ out:
 	return ret;
 }
 
-int btrfs_cont_expand(struct inode *inode, loff_t size)
+/*
+ * This function puts in dummy file extents for the area we're creating a hole
+ * for.  So if we are truncating this file to a larger size we need to insert
+ * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for
+ * the range between oldsize and size
+ */
+int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -3545,7 +3607,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
 	struct extent_map *em = NULL;
 	struct extent_state *cached_state = NULL;
 	u64 mask = root->sectorsize - 1;
-	u64 hole_start = (inode->i_size + mask) & ~mask;
+	u64 hole_start = (oldsize + mask) & ~mask;
 	u64 block_end = (size + mask) & ~mask;
 	u64 last_byte;
 	u64 cur_offset;
@@ -3590,13 +3652,15 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
 			err = btrfs_drop_extents(trans, inode, cur_offset,
 						 cur_offset + hole_size,
 						 &hint_byte, 1);
-			BUG_ON(err);
+			if (err)
+				break;
 
 			err = btrfs_insert_file_extent(trans, root,
 					inode->i_ino, cur_offset, 0,
 					0, hole_size, 0, hole_size,
 					0, 0, 0);
-			BUG_ON(err);
+			if (err)
+				break;
 
 			btrfs_drop_extent_cache(inode, hole_start,
 					last_byte - 1, 0);
@@ -3616,81 +3680,41 @@ int btrfs_cont_expand(struct inode *inode, loff_t size)
 	return err;
 }
 
-static int btrfs_setattr_size(struct inode *inode, struct iattr *attr)
+static int btrfs_setsize(struct inode *inode, loff_t newsize)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_trans_handle *trans;
-	unsigned long nr;
+	loff_t oldsize = i_size_read(inode);
 	int ret;
 
-	if (attr->ia_size == inode->i_size)
+	if (newsize == oldsize)
 		return 0;
 
-	if (attr->ia_size > inode->i_size) {
-		unsigned long limit;
-		limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
-		if (attr->ia_size > inode->i_sb->s_maxbytes)
-			return -EFBIG;
-		if (limit != RLIM_INFINITY && attr->ia_size > limit) {
-			send_sig(SIGXFSZ, current, 0);
-			return -EFBIG;
-		}
-	}
-
-	trans = btrfs_start_transaction(root, 5);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
-
-	btrfs_set_trans_block_group(trans, inode);
-
-	ret = btrfs_orphan_add(trans, inode);
-	BUG_ON(ret);
-
-	nr = trans->blocks_used;
-	btrfs_end_transaction(trans, root);
-	btrfs_btree_balance_dirty(root, nr);
-
-	if (attr->ia_size > inode->i_size) {
-		ret = btrfs_cont_expand(inode, attr->ia_size);
+	if (newsize > oldsize) {
+		i_size_write(inode, newsize);
+		btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+		truncate_pagecache(inode, oldsize, newsize);
+		ret = btrfs_cont_expand(inode, oldsize, newsize);
 		if (ret) {
-			btrfs_truncate(inode);
+			btrfs_setsize(inode, oldsize);
 			return ret;
 		}
 
-		i_size_write(inode, attr->ia_size);
-		btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
+		mark_inode_dirty(inode);
+	} else {
 
-		trans = btrfs_start_transaction(root, 0);
-		BUG_ON(IS_ERR(trans));
-		btrfs_set_trans_block_group(trans, inode);
-		trans->block_rsv = root->orphan_block_rsv;
-		BUG_ON(!trans->block_rsv);
+		/*
+		 * We're truncating a file that used to have good data down to
+		 * zero. Make sure it gets into the ordered flush list so that
+		 * any new writes get down to disk quickly.
+		 */
+		if (newsize == 0)
+			BTRFS_I(inode)->ordered_data_close = 1;
 
-		ret = btrfs_update_inode(trans, root, inode);
-		BUG_ON(ret);
-		if (inode->i_nlink > 0) {
-			ret = btrfs_orphan_del(trans, inode);
-			BUG_ON(ret);
-		}
-		nr = trans->blocks_used;
-		btrfs_end_transaction(trans, root);
-		btrfs_btree_balance_dirty(root, nr);
-		return 0;
+		/* we don't support swapfiles, so vmtruncate shouldn't fail */
+		truncate_setsize(inode, newsize);
+		ret = btrfs_truncate(inode);
 	}
 
-	/*
-	 * We're truncating a file that used to have good data down to
-	 * zero. Make sure it gets into the ordered flush list so that
-	 * any new writes get down to disk quickly.
-	 */
-	if (attr->ia_size == 0)
-		BTRFS_I(inode)->ordered_data_close = 1;
-
-	/* we don't support swapfiles, so vmtruncate shouldn't fail */
-	ret = vmtruncate(inode, attr->ia_size);
-	BUG_ON(ret);
-
-	return 0;
+	return ret;
 }
 
 static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -3707,7 +3731,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		err = btrfs_setattr_size(inode, attr);
+		err = btrfs_setsize(inode, attr->ia_size);
 		if (err)
 			return err;
 	}
@@ -3730,6 +3754,8 @@ void btrfs_evict_inode(struct inode *inode)
 	unsigned long nr;
 	int ret;
 
+	trace_btrfs_inode_evict(inode);
+
 	truncate_inode_pages(&inode->i_data, 0);
 	if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 ||
 			       root == root->fs_info->tree_root))
@@ -4072,7 +4098,6 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 		BTRFS_I(inode)->root = root;
 		memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
 		btrfs_read_locked_inode(inode);
-
 		inode_tree_add(inode);
 		unlock_new_inode(inode);
 		if (new)
@@ -4147,8 +4172,10 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	if (!IS_ERR(inode) && root != sub_root) {
 		down_read(&root->fs_info->cleanup_work_sem);
 		if (!(inode->i_sb->s_flags & MS_RDONLY))
-			btrfs_orphan_cleanup(sub_root);
+			ret = btrfs_orphan_cleanup(sub_root);
 		up_read(&root->fs_info->cleanup_work_sem);
+		if (ret)
+			inode = ERR_PTR(ret);
 	}
 
 	return inode;
@@ -4196,10 +4223,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 	struct btrfs_key found_key;
 	struct btrfs_path *path;
 	int ret;
-	u32 nritems;
 	struct extent_buffer *leaf;
 	int slot;
-	int advance;
 	unsigned char d_type;
 	int over = 0;
 	u32 di_cur;
@@ -4242,27 +4267,19 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto err;
-	advance = 0;
 
 	while (1) {
 		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
 		slot = path->slots[0];
-		if (advance || slot >= nritems) {
-			if (slot >= nritems - 1) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret)
-					break;
-				leaf = path->nodes[0];
-				nritems = btrfs_header_nritems(leaf);
-				slot = path->slots[0];
-			} else {
-				slot++;
-				path->slots[0]++;
-			}
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto err;
+			else if (ret > 0)
+				break;
+			continue;
 		}
 
-		advance = 1;
 		item = btrfs_item_nr(leaf, slot);
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
@@ -4271,7 +4288,7 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 		if (btrfs_key_type(&found_key) != key_type)
 			break;
 		if (found_key.offset < filp->f_pos)
-			continue;
+			goto next;
 
 		filp->f_pos = found_key.offset;
 
@@ -4282,6 +4299,9 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
 		while (di_cur < di_total) {
 			struct btrfs_key location;
 
+			if (verify_dir_item(root, leaf, di))
+				break;
+
 			name_len = btrfs_dir_name_len(leaf, di);
 			if (name_len <= sizeof(tmp_name)) {
 				name_ptr = tmp_name;
@@ -4321,6 +4341,8 @@ skip:
 			di_cur += di_len;
 			di = (struct btrfs_dir_item *)((char *)di + di_len);
 		}
+next:
+		path->slots[0]++;
 	}
 
 	/* Reached end of directory/root. Bump pos past the last item. */
@@ -4513,12 +4535,17 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	BUG_ON(!path);
 
 	inode = new_inode(root->fs_info->sb);
-	if (!inode)
+	if (!inode) {
+		btrfs_free_path(path);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	if (dir) {
+		trace_btrfs_inode_request(dir);
+
 		ret = btrfs_set_inode_index(dir, index);
 		if (ret) {
+			btrfs_free_path(path);
 			iput(inode);
 			return ERR_PTR(ret);
 		}
@@ -4585,12 +4612,16 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	if ((mode & S_IFREG)) {
 		if (btrfs_test_opt(root, NODATASUM))
 			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
-		if (btrfs_test_opt(root, NODATACOW))
+		if (btrfs_test_opt(root, NODATACOW) ||
+		    (BTRFS_I(dir)->flags & BTRFS_INODE_NODATACOW))
 			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
 	}
 
 	insert_inode_hash(inode);
 	inode_tree_add(inode);
+
+	trace_btrfs_inode_new(inode);
+
 	return inode;
 fail:
 	if (dir)
@@ -4701,9 +4732,10 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, dir->i_ino, objectid,
 				BTRFS_I(dir)->block_group, mode, &index);
-	err = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
 		goto out_unlock;
+	}
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
@@ -4762,9 +4794,10 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
 				dentry->d_name.len, dir->i_ino, objectid,
 				BTRFS_I(dir)->block_group, mode, &index);
-	err = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
 		goto out_unlock;
+	}
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
@@ -4809,10 +4842,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	/* do not allow sys_link's with other subvols of the same device */
 	if (root->objectid != BTRFS_I(inode)->root->objectid)
-		return -EPERM;
+		return -EXDEV;
 
-	btrfs_inc_nlink(inode);
-	inode->i_ctime = CURRENT_TIME;
+	if (inode->i_nlink == ~0U)
+		return -EMLINK;
 
 	err = btrfs_set_inode_index(dir, &index);
 	if (err)
@@ -4829,6 +4862,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 		goto fail;
 	}
 
+	btrfs_inc_nlink(inode);
+	inode->i_ctime = CURRENT_TIME;
+
 	btrfs_set_trans_block_group(trans, dir);
 	ihold(inode);
 
@@ -4966,6 +5002,8 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	inline_size = btrfs_file_extent_inline_item_len(leaf,
 					btrfs_item_nr(leaf, path->slots[0]));
 	tmp = kmalloc(inline_size, GFP_NOFS);
+	if (!tmp)
+		return -ENOMEM;
 	ptr = btrfs_file_extent_inline_start(item);
 
 	read_extent_buffer(leaf, tmp, ptr, inline_size);
@@ -5198,7 +5236,7 @@ again:
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		set_extent_uptodate(io_tree, em->start,
-				    extent_map_end(em) - 1, GFP_NOFS);
+				    extent_map_end(em) - 1, NULL, GFP_NOFS);
 		goto insert;
 	} else {
 		printk(KERN_ERR "btrfs unknown found_type %d\n", found_type);
@@ -5265,6 +5303,9 @@ insert:
 	}
 	write_unlock(&em_tree->lock);
 out:
+
+	trace_btrfs_get_extent(root, em);
+
 	if (path)
 		btrfs_free_path(path);
 	if (trans) {
@@ -5402,17 +5443,30 @@ out:
 }
 
 static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
+						  struct extent_map *em,
 						  u64 start, u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
-	struct extent_map *em;
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct btrfs_key ins;
 	u64 alloc_hint;
 	int ret;
+	bool insert = false;
 
-	btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+	/*
+	 * Ok if the extent map we looked up is a hole and is for the exact
+	 * range we want, there is no reason to allocate a new one, however if
+	 * it is not right then we need to free this one and drop the cache for
+	 * our range.
+	 */
+	if (em->block_start != EXTENT_MAP_HOLE || em->start != start ||
+	    em->len != len) {
+		free_extent_map(em);
+		em = NULL;
+		insert = true;
+		btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
+	}
 
 	trans = btrfs_join_transaction(root, 0);
 	if (IS_ERR(trans))
@@ -5428,10 +5482,12 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 		goto out;
 	}
 
-	em = alloc_extent_map(GFP_NOFS);
 	if (!em) {
-		em = ERR_PTR(-ENOMEM);
-		goto out;
+		em = alloc_extent_map(GFP_NOFS);
+		if (!em) {
+			em = ERR_PTR(-ENOMEM);
+			goto out;
+		}
 	}
 
 	em->start = start;
@@ -5441,9 +5497,15 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	em->block_start = ins.objectid;
 	em->block_len = ins.offset;
 	em->bdev = root->fs_info->fs_devices->latest_bdev;
+
+	/*
+	 * We need to do this because if we're using the original em we searched
+	 * for, we could have EXTENT_FLAG_VACANCY set, and we don't want that.
+	 */
+	em->flags = 0;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
 
-	while (1) {
+	while (insert) {
 		write_lock(&em_tree->lock);
 		ret = add_extent_mapping(em_tree, em);
 		write_unlock(&em_tree->lock);
@@ -5661,8 +5723,7 @@ must_cow:
 	 * it above
 	 */
 	len = bh_result->b_size;
-	free_extent_map(em);
-	em = btrfs_new_extent_direct(inode, start, len);
+	em = btrfs_new_extent_direct(inode, em, start, len);
 	if (IS_ERR(em))
 		return PTR_ERR(em);
 	len = min(len, em->len - (start - em->start));
@@ -5748,6 +5809,10 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
 
 	kfree(dip->csums);
 	kfree(dip);
+
+	/* If we had a csum failure make sure to clear the uptodate flag */
+	if (err)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	dio_end_io(bio, err);
 }
 
@@ -5821,8 +5886,10 @@ again:
 	}
 
 	add_pending_csums(trans, inode, ordered->file_offset, &ordered->list);
-	btrfs_ordered_update_i_size(inode, 0, ordered);
-	btrfs_update_inode(trans, root, inode);
+	ret = btrfs_ordered_update_i_size(inode, 0, ordered);
+	if (!ret)
+		btrfs_update_inode(trans, root, inode);
+	ret = 0;
 out_unlock:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset,
 			     ordered->file_offset + ordered->len - 1,
@@ -5849,6 +5916,10 @@ out_done:
 
 	kfree(dip->csums);
 	kfree(dip);
+
+	/* If we had an error make sure to clear the uptodate flag */
+	if (err)
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
 	dio_end_io(bio, err);
 }
 
@@ -5904,7 +5975,7 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
 
 static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 					 int rw, u64 file_offset, int skip_sum,
-					 u32 *csums)
+					 u32 *csums, int async_submit)
 {
 	int write = rw & REQ_WRITE;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -5915,18 +5986,33 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 	if (ret)
 		goto err;
 
-	if (write && !skip_sum) {
+	if (skip_sum)
+		goto map;
+
+	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(root->fs_info,
 				   inode, rw, bio, 0, 0,
 				   file_offset,
 				   __btrfs_submit_bio_start_direct_io,
 				   __btrfs_submit_bio_done);
 		goto err;
-	} else if (!skip_sum)
-		btrfs_lookup_bio_sums_dio(root, inode, bio,
+	} else if (write) {
+		/*
+		 * If we aren't doing async submit, calculate the csum of the
+		 * bio now.
+		 */
+		ret = btrfs_csum_one_bio(root, inode, bio, file_offset, 1);
+		if (ret)
+			goto err;
+	} else if (!skip_sum) {
+		ret = btrfs_lookup_bio_sums_dio(root, inode, bio,
 					  file_offset, csums);
+		if (ret)
+			goto err;
+	}
 
-	ret = btrfs_map_bio(root, rw, bio, 0, 1);
+map:
+	ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
 err:
 	bio_put(bio);
 	return ret;
@@ -5948,22 +6034,30 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 	int nr_pages = 0;
 	u32 *csums = dip->csums;
 	int ret = 0;
-
-	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-	bio->bi_private = dip;
-	bio->bi_end_io = btrfs_end_dio_bio;
-	atomic_inc(&dip->pending_bios);
+	int async_submit = 0;
+	int write = rw & REQ_WRITE;
 
 	map_length = orig_bio->bi_size;
 	ret = btrfs_map_block(map_tree, READ, start_sector << 9,
 			      &map_length, NULL, 0);
 	if (ret) {
-		bio_put(bio);
+		bio_put(orig_bio);
 		return -EIO;
 	}
 
+	if (map_length >= orig_bio->bi_size) {
+		bio = orig_bio;
+		goto submit;
+	}
+
+	async_submit = 1;
+	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
+	if (!bio)
+		return -ENOMEM;
+	bio->bi_private = dip;
+	bio->bi_end_io = btrfs_end_dio_bio;
+	atomic_inc(&dip->pending_bios);
+
 	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
 		if (unlikely(map_length < submit_len + bvec->bv_len ||
 		    bio_add_page(bio, bvec->bv_page, bvec->bv_len,
@@ -5977,14 +6071,15 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 			atomic_inc(&dip->pending_bios);
 			ret = __btrfs_submit_dio_bio(bio, inode, rw,
 						     file_offset, skip_sum,
-						     csums);
+						     csums, async_submit);
 			if (ret) {
 				bio_put(bio);
 				atomic_dec(&dip->pending_bios);
 				goto out_err;
 			}
 
-			if (!skip_sum)
+			/* Write's use the ordered csums */
+			if (!write && !skip_sum)
 				csums = csums + nr_pages;
 			start_sector += submit_len >> 9;
 			file_offset += submit_len;
@@ -6013,8 +6108,9 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
 		}
 	}
 
+submit:
 	ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
-				     csums);
+				     csums, async_submit);
 	if (!ret)
 		return 0;
 
@@ -6052,7 +6148,8 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode,
 	}
 	dip->csums = NULL;
 
-	if (!skip_sum) {
+	/* Write's use the ordered csum stuff, so we don't need dip->csums */
+	if (!write && !skip_sum) {
 		dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS);
 		if (!dip->csums) {
 			kfree(dip);
@@ -6108,6 +6205,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
 			unsigned long nr_segs)
 {
 	int seg;
+	int i;
 	size_t size;
 	unsigned long addr;
 	unsigned blocksize_mask = root->sectorsize - 1;
@@ -6122,8 +6220,22 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
 		addr = (unsigned long)iov[seg].iov_base;
 		size = iov[seg].iov_len;
 		end += size;
-		if ((addr & blocksize_mask) || (size & blocksize_mask)) 
+		if ((addr & blocksize_mask) || (size & blocksize_mask))
 			goto out;
+
+		/* If this is a write we don't need to check anymore */
+		if (rw & WRITE)
+			continue;
+
+		/*
+		 * Check to make sure we don't have duplicate iov_base's in this
+		 * iovec, if so return EINVAL, otherwise we'll get csum errors
+		 * when reading back.
+		 */
+		for (i = seg + 1; i < nr_segs; i++) {
+			if (iov[seg].iov_base == iov[i].iov_base)
+				goto out;
+		}
 	}
 	retval = 0;
 out:
@@ -6474,28 +6586,42 @@ out:
 	return ret;
 }
 
-static void btrfs_truncate(struct inode *inode)
+static int btrfs_truncate(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
+	int err = 0;
 	struct btrfs_trans_handle *trans;
 	unsigned long nr;
 	u64 mask = root->sectorsize - 1;
 
-	if (!S_ISREG(inode->i_mode)) {
-		WARN_ON(1);
-		return;
-	}
-
 	ret = btrfs_truncate_page(inode->i_mapping, inode->i_size);
 	if (ret)
-		return;
+		return ret;
 
 	btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
 	btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
+	trans = btrfs_start_transaction(root, 5);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	btrfs_set_trans_block_group(trans, inode);
+
+	ret = btrfs_orphan_add(trans, inode);
+	if (ret) {
+		btrfs_end_transaction(trans, root);
+		return ret;
+	}
+
+	nr = trans->blocks_used;
+	btrfs_end_transaction(trans, root);
+	btrfs_btree_balance_dirty(root, nr);
+
+	/* Now start a transaction for the truncate */
 	trans = btrfs_start_transaction(root, 0);
-	BUG_ON(IS_ERR(trans));
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 	btrfs_set_trans_block_group(trans, inode);
 	trans->block_rsv = root->orphan_block_rsv;
 
@@ -6522,29 +6648,38 @@ static void btrfs_truncate(struct inode *inode)
 	while (1) {
 		if (!trans) {
 			trans = btrfs_start_transaction(root, 0);
-			BUG_ON(IS_ERR(trans));
+			if (IS_ERR(trans))
+				return PTR_ERR(trans);
 			btrfs_set_trans_block_group(trans, inode);
 			trans->block_rsv = root->orphan_block_rsv;
 		}
 
 		ret = btrfs_block_rsv_check(trans, root,
 					    root->orphan_block_rsv, 0, 5);
-		if (ret) {
-			BUG_ON(ret != -EAGAIN);
+		if (ret == -EAGAIN) {
 			ret = btrfs_commit_transaction(trans, root);
-			BUG_ON(ret);
+			if (ret)
+				return ret;
 			trans = NULL;
 			continue;
+		} else if (ret) {
+			err = ret;
+			break;
 		}
 
 		ret = btrfs_truncate_inode_items(trans, root, inode,
 						 inode->i_size,
 						 BTRFS_EXTENT_DATA_KEY);
-		if (ret != -EAGAIN)
+		if (ret != -EAGAIN) {
+			err = ret;
 			break;
+		}
 
 		ret = btrfs_update_inode(trans, root, inode);
-		BUG_ON(ret);
+		if (ret) {
+			err = ret;
+			break;
+		}
 
 		nr = trans->blocks_used;
 		btrfs_end_transaction(trans, root);
@@ -6554,16 +6689,27 @@ static void btrfs_truncate(struct inode *inode)
 
 	if (ret == 0 && inode->i_nlink > 0) {
 		ret = btrfs_orphan_del(trans, inode);
-		BUG_ON(ret);
+		if (ret)
+			err = ret;
+	} else if (ret && inode->i_nlink > 0) {
+		/*
+		 * Failed to do the truncate, remove us from the in memory
+		 * orphan list.
+		 */
+		ret = btrfs_orphan_del(NULL, inode);
 	}
 
 	ret = btrfs_update_inode(trans, root, inode);
-	BUG_ON(ret);
+	if (ret && !err)
+		err = ret;
 
 	nr = trans->blocks_used;
 	ret = btrfs_end_transaction_throttle(trans, root);
-	BUG_ON(ret);
+	if (ret && !err)
+		err = ret;
 	btrfs_btree_balance_dirty(root, nr);
+
+	return err;
 }
 
 /*
@@ -6630,9 +6776,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->index_cnt = (u64)-1;
 	ei->last_unlink_trans = 0;
 
-	spin_lock_init(&ei->accounting_lock);
 	atomic_set(&ei->outstanding_extents, 0);
-	ei->reserved_extents = 0;
+	atomic_set(&ei->reserved_extents, 0);
 
 	ei->ordered_data_close = 0;
 	ei->orphan_meta_reserved = 0;
@@ -6668,7 +6813,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	WARN_ON(!list_empty(&inode->i_dentry));
 	WARN_ON(inode->i_data.nrpages);
 	WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents));
-	WARN_ON(BTRFS_I(inode)->reserved_extents);
+	WARN_ON(atomic_read(&BTRFS_I(inode)->reserved_extents));
 
 	/*
 	 * This can happen where we create an inode, but somebody else also
@@ -6760,6 +6905,8 @@ void btrfs_destroy_cachep(void)
 		kmem_cache_destroy(btrfs_transaction_cachep);
 	if (btrfs_path_cachep)
 		kmem_cache_destroy(btrfs_path_cachep);
+	if (btrfs_free_space_cachep)
+		kmem_cache_destroy(btrfs_free_space_cachep);
 }
 
 int btrfs_init_cachep(void)
@@ -6788,6 +6935,12 @@ int btrfs_init_cachep(void)
 	if (!btrfs_path_cachep)
 		goto fail;
 
+	btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space_cache",
+			sizeof(struct btrfs_free_space), 0,
+			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+	if (!btrfs_free_space_cachep)
+		goto fail;
+
 	return 0;
 fail:
 	btrfs_destroy_cachep();
@@ -6806,6 +6959,26 @@ static int btrfs_getattr(struct vfsmount *mnt,
 	return 0;
 }
 
+/*
+ * If a file is moved, it will inherit the cow and compression flags of the new
+ * directory.
+ */
+static void fixup_inode_flags(struct inode *dir, struct inode *inode)
+{
+	struct btrfs_inode *b_dir = BTRFS_I(dir);
+	struct btrfs_inode *b_inode = BTRFS_I(inode);
+
+	if (b_dir->flags & BTRFS_INODE_NODATACOW)
+		b_inode->flags |= BTRFS_INODE_NODATACOW;
+	else
+		b_inode->flags &= ~BTRFS_INODE_NODATACOW;
+
+	if (b_dir->flags & BTRFS_INODE_COMPRESS)
+		b_inode->flags |= BTRFS_INODE_COMPRESS;
+	else
+		b_inode->flags &= ~BTRFS_INODE_COMPRESS;
+}
+
 static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			   struct inode *new_dir, struct dentry *new_dentry)
 {
@@ -6854,8 +7027,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * should cover the worst case number of items we'll modify.
 	 */
 	trans = btrfs_start_transaction(root, 20);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	if (IS_ERR(trans)) {
+                ret = PTR_ERR(trans);
+                goto out_notrans;
+        }
 
 	btrfs_set_trans_block_group(trans, new_dir);
 
@@ -6908,11 +7083,12 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 	} else {
-		btrfs_inc_nlink(old_dentry->d_inode);
-		ret = btrfs_unlink_inode(trans, root, old_dir,
-					 old_dentry->d_inode,
-					 old_dentry->d_name.name,
-					 old_dentry->d_name.len);
+		ret = __btrfs_unlink_inode(trans, root, old_dir,
+					old_dentry->d_inode,
+					old_dentry->d_name.name,
+					old_dentry->d_name.len);
+		if (!ret)
+			ret = btrfs_update_inode(trans, root, old_inode);
 	}
 	BUG_ON(ret);
 
@@ -6939,6 +7115,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		}
 	}
 
+	fixup_inode_flags(new_dir, old_inode);
+
 	ret = btrfs_add_link(trans, new_dir, old_inode,
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, index);
@@ -6952,7 +7130,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 out_fail:
 	btrfs_end_transaction_throttle(trans, root);
-
+out_notrans:
 	if (old_inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
 		up_read(&root->fs_info->subvol_sem);
 
@@ -7100,9 +7278,10 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				dentry->d_name.len, dir->i_ino, objectid,
 				BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
 				&index);
-	err = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
 		goto out_unlock;
+	}
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err) {
@@ -7340,7 +7519,6 @@ static const struct address_space_operations btrfs_aops = {
 	.writepage	= btrfs_writepage,
 	.writepages	= btrfs_writepages,
 	.readpages	= btrfs_readpages,
-	.sync_page	= block_sync_page,
 	.direct_IO	= btrfs_direct_IO,
 	.invalidatepage = btrfs_invalidatepage,
 	.releasepage	= btrfs_releasepage,
@@ -7356,7 +7534,6 @@ static const struct address_space_operations btrfs_symlink_aops = {
 };
 
 static const struct inode_operations btrfs_file_inode_operations = {
-	.truncate	= btrfs_truncate,
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.setxattr	= btrfs_setxattr,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5fdb2abc4fa..2616f7ed479 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -40,6 +40,7 @@
 #include <linux/xattr.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -80,6 +81,13 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 		iflags |= FS_NOATIME_FL;
 	if (flags & BTRFS_INODE_DIRSYNC)
 		iflags |= FS_DIRSYNC_FL;
+	if (flags & BTRFS_INODE_NODATACOW)
+		iflags |= FS_NOCOW_FL;
+
+	if ((flags & BTRFS_INODE_COMPRESS) && !(flags & BTRFS_INODE_NOCOMPRESS))
+		iflags |= FS_COMPR_FL;
+	else if (flags & BTRFS_INODE_NOCOMPRESS)
+		iflags |= FS_NOCOMP_FL;
 
 	return iflags;
 }
@@ -138,6 +146,21 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
 	return 0;
 }
 
+static int check_flags(unsigned int flags)
+{
+	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
+		      FS_NOATIME_FL | FS_NODUMP_FL | \
+		      FS_SYNC_FL | FS_DIRSYNC_FL | \
+		      FS_NOCOMP_FL | FS_COMPR_FL |
+		      FS_NOCOW_FL))
+		return -EOPNOTSUPP;
+
+	if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
@@ -153,12 +176,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (copy_from_user(&flags, arg, sizeof(flags)))
 		return -EFAULT;
 
-	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
-		      FS_NOATIME_FL | FS_NODUMP_FL | \
-		      FS_SYNC_FL | FS_DIRSYNC_FL))
-		return -EOPNOTSUPP;
+	ret = check_flags(flags);
+	if (ret)
+		return ret;
 
-	if (!is_owner_or_cap(inode))
+	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
 	mutex_lock(&inode->i_mutex);
@@ -200,7 +222,25 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		ip->flags |= BTRFS_INODE_DIRSYNC;
 	else
 		ip->flags &= ~BTRFS_INODE_DIRSYNC;
+	if (flags & FS_NOCOW_FL)
+		ip->flags |= BTRFS_INODE_NODATACOW;
+	else
+		ip->flags &= ~BTRFS_INODE_NODATACOW;
 
+	/*
+	 * The COMPRESS flag can only be changed by users, while the NOCOMPRESS
+	 * flag may be changed automatically if compression code won't make
+	 * things smaller.
+	 */
+	if (flags & FS_NOCOMP_FL) {
+		ip->flags &= ~BTRFS_INODE_COMPRESS;
+		ip->flags |= BTRFS_INODE_NOCOMPRESS;
+	} else if (flags & FS_COMPR_FL) {
+		ip->flags |= BTRFS_INODE_COMPRESS;
+		ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+	} else {
+		ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
+	}
 
 	trans = btrfs_join_transaction(root, 1);
 	BUG_ON(IS_ERR(trans));
@@ -213,9 +253,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	btrfs_end_transaction(trans, root);
 
 	mnt_drop_write(file->f_path.mnt);
+
+	ret = 0;
  out_unlock:
 	mutex_unlock(&inode->i_mutex);
-	return 0;
+	return ret;
 }
 
 static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
@@ -225,6 +267,49 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 	return put_user(inode->i_generation, arg);
 }
 
+static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+{
+	struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_device *device;
+	struct request_queue *q;
+	struct fstrim_range range;
+	u64 minlen = ULLONG_MAX;
+	u64 num_devices = 0;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
+		if (!device->bdev)
+			continue;
+		q = bdev_get_queue(device->bdev);
+		if (blk_queue_discard(q)) {
+			num_devices++;
+			minlen = min((u64)q->limits.discard_granularity,
+				     minlen);
+		}
+	}
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	if (!num_devices)
+		return -EOPNOTSUPP;
+
+	if (copy_from_user(&range, arg, sizeof(range)))
+		return -EFAULT;
+
+	range.minlen = max(range.minlen, minlen);
+	ret = btrfs_trim_fs(root, &range);
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(arg, &range, sizeof(range)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static noinline int create_subvol(struct btrfs_root *root,
 				  struct dentry *dentry,
 				  char *name, int namelen,
@@ -294,6 +379,10 @@ static noinline int create_subvol(struct btrfs_root *root,
 	inode_item->nbytes = cpu_to_le64(root->leafsize);
 	inode_item->mode = cpu_to_le32(S_IFDIR | 0755);
 
+	root_item.flags = 0;
+	root_item.byte_limit = 0;
+	inode_item->flags = cpu_to_le64(BTRFS_INODE_ROOT_ITEM_INIT);
+
 	btrfs_set_root_bytenr(&root_item, leaf->start);
 	btrfs_set_root_generation(&root_item, trans->transid);
 	btrfs_set_root_level(&root_item, 0);
@@ -409,7 +498,9 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry,
 	if (ret)
 		goto fail;
 
-	btrfs_orphan_cleanup(pending_snapshot->snap);
+	ret = btrfs_orphan_cleanup(pending_snapshot->snap);
+	if (ret)
+		goto fail;
 
 	parent = dget_parent(dentry);
 	inode = btrfs_lookup_dentry(parent->d_inode, dentry);
@@ -1077,7 +1168,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 	if (flags & ~BTRFS_SUBVOL_RDONLY)
 		return -EOPNOTSUPP;
 
-	if (!is_owner_or_cap(inode))
+	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
 	down_write(&root->fs_info->subvol_sem);
@@ -2202,7 +2293,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 	struct btrfs_ioctl_space_info space;
 	struct btrfs_ioctl_space_info *dest;
 	struct btrfs_ioctl_space_info *dest_orig;
-	struct btrfs_ioctl_space_info *user_dest;
+	struct btrfs_ioctl_space_info __user *user_dest;
 	struct btrfs_space_info *info;
 	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
 		       BTRFS_BLOCK_GROUP_SYSTEM,
@@ -2348,12 +2439,17 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp
 	struct btrfs_root *root = BTRFS_I(file->f_dentry->d_inode)->root;
 	struct btrfs_trans_handle *trans;
 	u64 transid;
+	int ret;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 	transid = trans->transid;
-	btrfs_commit_transaction_async(trans, root, 0);
+	ret = btrfs_commit_transaction_async(trans, root, 0);
+	if (ret) {
+		btrfs_end_transaction(trans, root);
+		return ret;
+	}
 
 	if (argp)
 		if (copy_to_user(argp, &transid, sizeof(transid)))
@@ -2388,6 +2484,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_setflags(file, argp);
 	case FS_IOC_GETVERSION:
 		return btrfs_ioctl_getversion(file, argp);
+	case FITRIM:
+		return btrfs_ioctl_fitrim(file, argp);
 	case BTRFS_IOC_SNAP_CREATE:
 		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SNAP_CREATE_V2:
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 083a5547737..a1c94042530 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -202,6 +202,8 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	INIT_LIST_HEAD(&entry->list);
 	INIT_LIST_HEAD(&entry->root_extent_list);
 
+	trace_btrfs_ordered_extent_add(inode, entry);
+
 	spin_lock(&tree->lock);
 	node = tree_insert(&tree->tree, file_offset,
 			   &entry->rb_node);
@@ -387,6 +389,8 @@ int btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 	struct list_head *cur;
 	struct btrfs_ordered_sum *sum;
 
+	trace_btrfs_ordered_extent_put(entry->inode, entry);
+
 	if (atomic_dec_and_test(&entry->refs)) {
 		while (!list_empty(&entry->list)) {
 			cur = entry->list.next;
@@ -420,6 +424,8 @@ static int __btrfs_remove_ordered_extent(struct inode *inode,
 	spin_lock(&root->fs_info->ordered_extent_lock);
 	list_del_init(&entry->root_extent_list);
 
+	trace_btrfs_ordered_extent_remove(inode, entry);
+
 	/*
 	 * we have no more ordered extents for this inode and
 	 * no dirty pages.  We can safely remove it from the
@@ -585,6 +591,8 @@ void btrfs_start_ordered_extent(struct inode *inode,
 	u64 start = entry->file_offset;
 	u64 end = start + entry->len - 1;
 
+	trace_btrfs_ordered_extent_start(inode, entry);
+
 	/*
 	 * pages in the range can be dirty, clean or writeback.  We
 	 * start IO on any dirty ones so the wait doesn't stall waiting
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 31ade5802ae..199a8013431 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1724,6 +1724,7 @@ again:
 
 			eb = read_tree_block(dest, old_bytenr, blocksize,
 					     old_ptr_gen);
+			BUG_ON(!eb);
 			btrfs_tree_lock(eb);
 			if (cow) {
 				ret = btrfs_cow_block(trans, dest, eb, parent,
@@ -2345,7 +2346,7 @@ struct btrfs_root *select_one_root(struct btrfs_trans_handle *trans,
 		root = next->root;
 		BUG_ON(!root);
 
-		/* no other choice for non-refernce counted tree */
+		/* no other choice for non-references counted tree */
 		if (!root->ref_cows)
 			return root;
 
@@ -2513,6 +2514,10 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 		blocksize = btrfs_level_size(root, node->level);
 		generation = btrfs_node_ptr_generation(upper->eb, slot);
 		eb = read_tree_block(root, bytenr, blocksize, generation);
+		if (!eb) {
+			err = -EIO;
+			goto next;
+		}
 		btrfs_tree_lock(eb);
 		btrfs_set_lock_blocking(eb);
 
@@ -2670,6 +2675,7 @@ static int get_tree_block_key(struct reloc_control *rc,
 	BUG_ON(block->key_ready);
 	eb = read_tree_block(rc->extent_root, block->bytenr,
 			     block->key.objectid, block->key.offset);
+	BUG_ON(!eb);
 	WARN_ON(btrfs_header_level(eb) != block->level);
 	if (block->level == 0)
 		btrfs_item_key_to_cpu(eb, &block->key, 0);
@@ -4209,7 +4215,7 @@ out:
 		if (IS_ERR(fs_root))
 			err = PTR_ERR(fs_root);
 		else
-			btrfs_orphan_cleanup(fs_root);
+			err = btrfs_orphan_cleanup(fs_root);
 	}
 	return err;
 }
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 6a1086e83ff..6928bff62da 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -88,7 +88,8 @@ int btrfs_find_last_root(struct btrfs_root *root, u64 objectid,
 	search_key.offset = (u64)-1;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	if (ret < 0)
 		goto out;
@@ -332,7 +333,8 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	struct extent_buffer *leaf;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	ret = btrfs_search_slot(trans, root, key, path, -1, 1);
 	if (ret < 0)
 		goto out;
@@ -471,3 +473,21 @@ again:
 	btrfs_free_path(path);
 	return 0;
 }
+
+/*
+ * Old btrfs forgets to init root_item->flags and root_item->byte_limit
+ * for subvolumes. To work around this problem, we steal a bit from
+ * root_item->inode_item->flags, and use it to indicate if those fields
+ * have been properly initialized.
+ */
+void btrfs_check_and_init_root_item(struct btrfs_root_item *root_item)
+{
+	u64 inode_flags = le64_to_cpu(root_item->inode.flags);
+
+	if (!(inode_flags & BTRFS_INODE_ROOT_ITEM_INIT)) {
+		inode_flags |= BTRFS_INODE_ROOT_ITEM_INIT;
+		root_item->inode.flags = cpu_to_le64(inode_flags);
+		root_item->flags = 0;
+		root_item->byte_limit = 0;
+	}
+}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d39a9895d93..0ac712efcdf 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -52,6 +52,9 @@
 #include "export.h"
 #include "compression.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/btrfs.h>
+
 static const struct super_operations btrfs_super_ops;
 
 static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
@@ -156,7 +159,7 @@ enum {
 	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
 	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
 	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-	Opt_enospc_debug, Opt_err,
+	Opt_enospc_debug, Opt_subvolrootid, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -186,6 +189,7 @@ static match_table_t tokens = {
 	{Opt_clear_cache, "clear_cache"},
 	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
 	{Opt_enospc_debug, "enospc_debug"},
+	{Opt_subvolrootid, "subvolrootid=%d"},
 	{Opt_err, NULL},
 };
 
@@ -229,6 +233,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			break;
 		case Opt_subvol:
 		case Opt_subvolid:
+		case Opt_subvolrootid:
 		case Opt_device:
 			/*
 			 * These are parsed by btrfs_parse_early_options
@@ -385,7 +390,7 @@ out:
  */
 static int btrfs_parse_early_options(const char *options, fmode_t flags,
 		void *holder, char **subvol_name, u64 *subvol_objectid,
-		struct btrfs_fs_devices **fs_devices)
+		u64 *subvol_rootid, struct btrfs_fs_devices **fs_devices)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *opts, *orig, *p;
@@ -426,6 +431,18 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 					*subvol_objectid = intarg;
 			}
 			break;
+		case Opt_subvolrootid:
+			intarg = 0;
+			error = match_int(&args[0], &intarg);
+			if (!error) {
+				/* we want the original fs_tree */
+				if (!intarg)
+					*subvol_rootid =
+						BTRFS_FS_TREE_OBJECTID;
+				else
+					*subvol_rootid = intarg;
+			}
+			break;
 		case Opt_device:
 			error = btrfs_scan_one_device(match_strdup(&args[0]),
 					flags, holder, fs_devices);
@@ -620,6 +637,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	struct btrfs_root *root = btrfs_sb(sb);
 	int ret;
 
+	trace_btrfs_sync_fs(wait);
+
 	if (!wait) {
 		filemap_flush(root->fs_info->btree_inode->i_mapping);
 		return 0;
@@ -639,6 +658,7 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 {
 	struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
 	struct btrfs_fs_info *info = root->fs_info;
+	char *compress_type;
 
 	if (btrfs_test_opt(root, DEGRADED))
 		seq_puts(seq, ",degraded");
@@ -657,8 +677,16 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (info->thread_pool_size !=  min_t(unsigned long,
 					     num_online_cpus() + 2, 8))
 		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
-	if (btrfs_test_opt(root, COMPRESS))
-		seq_puts(seq, ",compress");
+	if (btrfs_test_opt(root, COMPRESS)) {
+		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
+			compress_type = "zlib";
+		else
+			compress_type = "lzo";
+		if (btrfs_test_opt(root, FORCE_COMPRESS))
+			seq_printf(seq, ",compress-force=%s", compress_type);
+		else
+			seq_printf(seq, ",compress=%s", compress_type);
+	}
 	if (btrfs_test_opt(root, NOSSD))
 		seq_puts(seq, ",nossd");
 	if (btrfs_test_opt(root, SSD_SPREAD))
@@ -673,6 +701,12 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",discard");
 	if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
 		seq_puts(seq, ",noacl");
+	if (btrfs_test_opt(root, SPACE_CACHE))
+		seq_puts(seq, ",space_cache");
+	if (btrfs_test_opt(root, CLEAR_CACHE))
+		seq_puts(seq, ",clear_cache");
+	if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
+		seq_puts(seq, ",user_subvol_rm_allowed");
 	return 0;
 }
 
@@ -716,6 +750,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	fmode_t mode = FMODE_READ;
 	char *subvol_name = NULL;
 	u64 subvol_objectid = 0;
+	u64 subvol_rootid = 0;
 	int error = 0;
 
 	if (!(flags & MS_RDONLY))
@@ -723,7 +758,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 
 	error = btrfs_parse_early_options(data, mode, fs_type,
 					  &subvol_name, &subvol_objectid,
-					  &fs_devices);
+					  &subvol_rootid, &fs_devices);
 	if (error)
 		return ERR_PTR(error);
 
@@ -787,15 +822,17 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 		s->s_flags |= MS_ACTIVE;
 	}
 
-	root = get_default_root(s, subvol_objectid);
-	if (IS_ERR(root)) {
-		error = PTR_ERR(root);
-		deactivate_locked_super(s);
-		goto error_free_subvol_name;
-	}
 	/* if they gave us a subvolume name bind mount into that */
 	if (strcmp(subvol_name, ".")) {
 		struct dentry *new_root;
+
+		root = get_default_root(s, subvol_rootid);
+		if (IS_ERR(root)) {
+			error = PTR_ERR(root);
+			deactivate_locked_super(s);
+			goto error_free_subvol_name;
+		}
+
 		mutex_lock(&root->d_inode->i_mutex);
 		new_root = lookup_one_len(subvol_name, root,
 				      strlen(subvol_name));
@@ -816,6 +853,13 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 		}
 		dput(root);
 		root = new_root;
+	} else {
+		root = get_default_root(s, subvol_objectid);
+		if (IS_ERR(root)) {
+			error = PTR_ERR(root);
+			deactivate_locked_super(s);
+			goto error_free_subvol_name;
+		}
 	}
 
 	kfree(subvol_name);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 3d73c8d93bb..c571734d5e5 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -32,10 +32,8 @@
 
 static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
-	WARN_ON(transaction->use_count == 0);
-	transaction->use_count--;
-	if (transaction->use_count == 0) {
-		list_del_init(&transaction->list);
+	WARN_ON(atomic_read(&transaction->use_count) == 0);
+	if (atomic_dec_and_test(&transaction->use_count)) {
 		memset(transaction, 0, sizeof(*transaction));
 		kmem_cache_free(btrfs_transaction_cachep, transaction);
 	}
@@ -57,16 +55,17 @@ static noinline int join_transaction(struct btrfs_root *root)
 	if (!cur_trans) {
 		cur_trans = kmem_cache_alloc(btrfs_transaction_cachep,
 					     GFP_NOFS);
-		BUG_ON(!cur_trans);
+		if (!cur_trans)
+			return -ENOMEM;
 		root->fs_info->generation++;
-		cur_trans->num_writers = 1;
+		atomic_set(&cur_trans->num_writers, 1);
 		cur_trans->num_joined = 0;
 		cur_trans->transid = root->fs_info->generation;
 		init_waitqueue_head(&cur_trans->writer_wait);
 		init_waitqueue_head(&cur_trans->commit_wait);
 		cur_trans->in_commit = 0;
 		cur_trans->blocked = 0;
-		cur_trans->use_count = 1;
+		atomic_set(&cur_trans->use_count, 1);
 		cur_trans->commit_done = 0;
 		cur_trans->start_time = get_seconds();
 
@@ -87,7 +86,7 @@ static noinline int join_transaction(struct btrfs_root *root)
 		root->fs_info->running_transaction = cur_trans;
 		spin_unlock(&root->fs_info->new_trans_lock);
 	} else {
-		cur_trans->num_writers++;
+		atomic_inc(&cur_trans->num_writers);
 		cur_trans->num_joined++;
 	}
 
@@ -144,7 +143,7 @@ static void wait_current_trans(struct btrfs_root *root)
 	cur_trans = root->fs_info->running_transaction;
 	if (cur_trans && cur_trans->blocked) {
 		DEFINE_WAIT(wait);
-		cur_trans->use_count++;
+		atomic_inc(&cur_trans->use_count);
 		while (1) {
 			prepare_to_wait(&root->fs_info->transaction_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
@@ -180,6 +179,7 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 {
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
+	int retries = 0;
 	int ret;
 
 	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
@@ -195,10 +195,15 @@ again:
 		wait_current_trans(root);
 
 	ret = join_transaction(root);
-	BUG_ON(ret);
+	if (ret < 0) {
+		kmem_cache_free(btrfs_trans_handle_cachep, h);
+		if (type != TRANS_JOIN_NOLOCK)
+			mutex_unlock(&root->fs_info->trans_mutex);
+		return ERR_PTR(ret);
+	}
 
 	cur_trans = root->fs_info->running_transaction;
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	if (type != TRANS_JOIN_NOLOCK)
 		mutex_unlock(&root->fs_info->trans_mutex);
 
@@ -218,10 +223,18 @@ again:
 
 	if (num_items > 0) {
 		ret = btrfs_trans_reserve_metadata(h, root, num_items);
-		if (ret == -EAGAIN) {
+		if (ret == -EAGAIN && !retries) {
+			retries++;
 			btrfs_commit_transaction(h, root);
 			goto again;
+		} else if (ret == -EAGAIN) {
+			/*
+			 * We have already retried and got EAGAIN, so really we
+			 * don't have space, so set ret to -ENOSPC.
+			 */
+			ret = -ENOSPC;
 		}
+
 		if (ret < 0) {
 			btrfs_end_transaction(h, root);
 			return ERR_PTR(ret);
@@ -321,7 +334,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
 			goto out_unlock;  /* nothing committing|committed */
 	}
 
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	wait_for_commit(root, cur_trans);
@@ -451,18 +464,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 			wake_up_process(info->transaction_kthread);
 	}
 
-	if (lock)
-		mutex_lock(&info->trans_mutex);
 	WARN_ON(cur_trans != info->running_transaction);
-	WARN_ON(cur_trans->num_writers < 1);
-	cur_trans->num_writers--;
+	WARN_ON(atomic_read(&cur_trans->num_writers) < 1);
+	atomic_dec(&cur_trans->num_writers);
 
 	smp_mb();
 	if (waitqueue_active(&cur_trans->writer_wait))
 		wake_up(&cur_trans->writer_wait);
 	put_transaction(cur_trans);
-	if (lock)
-		mutex_unlock(&info->trans_mutex);
 
 	if (current->journal_info == trans)
 		current->journal_info = NULL;
@@ -970,6 +979,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	record_root_in_trans(trans, root);
 	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
 	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
+	btrfs_check_and_init_root_item(new_root_item);
 
 	root_flags = btrfs_root_flags(new_root_item);
 	if (pending->readonly)
@@ -1156,7 +1166,8 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *cur_trans;
 
 	ac = kmalloc(sizeof(*ac), GFP_NOFS);
-	BUG_ON(!ac);
+	if (!ac)
+		return -ENOMEM;
 
 	INIT_DELAYED_WORK(&ac->work, do_async_commit);
 	ac->root = root;
@@ -1170,7 +1181,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 	/* take transaction reference */
 	mutex_lock(&root->fs_info->trans_mutex);
 	cur_trans = trans->transaction;
-	cur_trans->use_count++;
+	atomic_inc(&cur_trans->use_count);
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	btrfs_end_transaction(trans, root);
@@ -1229,7 +1240,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	mutex_lock(&root->fs_info->trans_mutex);
 	if (cur_trans->in_commit) {
-		cur_trans->use_count++;
+		atomic_inc(&cur_trans->use_count);
 		mutex_unlock(&root->fs_info->trans_mutex);
 		btrfs_end_transaction(trans, root);
 
@@ -1251,7 +1262,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		prev_trans = list_entry(cur_trans->list.prev,
 					struct btrfs_transaction, list);
 		if (!prev_trans->commit_done) {
-			prev_trans->use_count++;
+			atomic_inc(&prev_trans->use_count);
 			mutex_unlock(&root->fs_info->trans_mutex);
 
 			wait_for_commit(root, prev_trans);
@@ -1292,14 +1303,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 				TASK_UNINTERRUPTIBLE);
 
 		smp_mb();
-		if (cur_trans->num_writers > 1)
+		if (atomic_read(&cur_trans->num_writers) > 1)
 			schedule_timeout(MAX_SCHEDULE_TIMEOUT);
 		else if (should_grow)
 			schedule_timeout(1);
 
 		mutex_lock(&root->fs_info->trans_mutex);
 		finish_wait(&cur_trans->writer_wait, &wait);
-	} while (cur_trans->num_writers > 1 ||
+	} while (atomic_read(&cur_trans->num_writers) > 1 ||
 		 (should_grow && cur_trans->num_joined != joined));
 
 	ret = create_pending_snapshots(trans, root->fs_info);
@@ -1386,9 +1397,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	wake_up(&cur_trans->commit_wait);
 
+	list_del_init(&cur_trans->list);
 	put_transaction(cur_trans);
 	put_transaction(cur_trans);
 
+	trace_btrfs_transaction_commit(root);
+
 	mutex_unlock(&root->fs_info->trans_mutex);
 
 	if (current->journal_info == trans)
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 229a594cacd..e441acc6c58 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -27,11 +27,11 @@ struct btrfs_transaction {
 	 * total writers in this transaction, it must be zero before the
 	 * transaction can end
 	 */
-	unsigned long num_writers;
+	atomic_t num_writers;
 
 	unsigned long num_joined;
 	int in_commit;
-	int use_count;
+	atomic_t use_count;
 	int commit_done;
 	int blocked;
 	struct list_head list;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index a4bbb854dfd..f997ec0c1ba 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -799,12 +799,12 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 	struct inode *dir;
 	int ret;
 	struct btrfs_inode_ref *ref;
-	struct btrfs_dir_item *di;
 	struct inode *inode;
 	char *name;
 	int namelen;
 	unsigned long ref_ptr;
 	unsigned long ref_end;
+	int search_done = 0;
 
 	/*
 	 * it is possible that we didn't log all the parent directories
@@ -845,7 +845,10 @@ again:
 	 * existing back reference, and we don't want to create
 	 * dangling pointers in the directory.
 	 */
-conflict_again:
+
+	if (search_done)
+		goto insert;
+
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
 	if (ret == 0) {
 		char *victim_name;
@@ -886,37 +889,21 @@ conflict_again:
 				ret = btrfs_unlink_inode(trans, root, dir,
 							 inode, victim_name,
 							 victim_name_len);
-				kfree(victim_name);
-				btrfs_release_path(root, path);
-				goto conflict_again;
 			}
 			kfree(victim_name);
 			ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
 		}
 		BUG_ON(ret);
-	}
-	btrfs_release_path(root, path);
 
-	/* look for a conflicting sequence number */
-	di = btrfs_lookup_dir_index_item(trans, root, path, dir->i_ino,
-					 btrfs_inode_ref_index(eb, ref),
-					 name, namelen, 0);
-	if (di && !IS_ERR(di)) {
-		ret = drop_one_dir_item(trans, root, path, dir, di);
-		BUG_ON(ret);
-	}
-	btrfs_release_path(root, path);
-
-
-	/* look for a conflicting name */
-	di = btrfs_lookup_dir_item(trans, root, path, dir->i_ino,
-				   name, namelen, 0);
-	if (di && !IS_ERR(di)) {
-		ret = drop_one_dir_item(trans, root, path, dir, di);
-		BUG_ON(ret);
+		/*
+		 * NOTE: we have searched root tree and checked the
+		 * coresponding ref, it does not need to check again.
+		 */
+		search_done = 1;
 	}
 	btrfs_release_path(root, path);
 
+insert:
 	/* insert our name */
 	ret = btrfs_add_link(trans, dir, inode, name, namelen, 0,
 			     btrfs_inode_ref_index(eb, ref));
@@ -1286,6 +1273,8 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
+		if (verify_dir_item(root, eb, di))
+			return -EIO;
 		name_len = btrfs_dir_name_len(eb, di);
 		ret = replay_one_name(trans, root, path, eb, di, key);
 		BUG_ON(ret);
@@ -1412,6 +1401,11 @@ again:
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
+		if (verify_dir_item(root, eb, di)) {
+			ret = -EIO;
+			goto out;
+		}
+
 		name_len = btrfs_dir_name_len(eb, di);
 		name = kmalloc(name_len, GFP_NOFS);
 		if (!name) {
@@ -1821,7 +1815,8 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 	int orig_level;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 
 	level = btrfs_header_level(log->node);
 	orig_level = level;
@@ -2214,8 +2209,10 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 
 	log = root->log_root;
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
 
 	di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
 				   name, name_len, -1);
@@ -2276,6 +2273,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	}
 fail:
 	btrfs_free_path(path);
+out_unlock:
 	mutex_unlock(&BTRFS_I(dir)->log_mutex);
 	if (ret == -ENOSPC) {
 		root->fs_info->last_trans_log_full_commit = trans->transid;
@@ -3107,9 +3105,11 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 		.stage = 0,
 	};
 
-	fs_info->log_root_recovering = 1;
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
+
+	fs_info->log_root_recovering = 1;
 
 	trans = btrfs_start_transaction(fs_info->tree_root, 0);
 	BUG_ON(IS_ERR(trans));
@@ -3117,7 +3117,8 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 	wc.trans = trans;
 	wc.pin = 1;
 
-	walk_log_tree(trans, log_root_tree, &wc);
+	ret = walk_log_tree(trans, log_root_tree, &wc);
+	BUG_ON(ret);
 
 again:
 	key.objectid = BTRFS_TREE_LOG_OBJECTID;
@@ -3141,8 +3142,7 @@ again:
 
 		log = btrfs_read_fs_root_no_radix(log_root_tree,
 						  &found_key);
-		BUG_ON(!log);
-
+		BUG_ON(IS_ERR(log));
 
 		tmp_key.objectid = found_key.offset;
 		tmp_key.type = BTRFS_ROOT_ITEM_KEY;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index dd13eb81ee4..c7367ae5a3e 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -33,17 +33,6 @@
 #include "volumes.h"
 #include "async-thread.h"
 
-struct map_lookup {
-	u64 type;
-	int io_align;
-	int io_width;
-	int stripe_len;
-	int sector_size;
-	int num_stripes;
-	int sub_stripes;
-	struct btrfs_bio_stripe stripes[];
-};
-
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				struct btrfs_device *device);
@@ -162,22 +151,25 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	struct bio *cur;
 	int again = 0;
 	unsigned long num_run;
-	unsigned long num_sync_run;
 	unsigned long batch_run = 0;
 	unsigned long limit;
 	unsigned long last_waited = 0;
 	int force_reg = 0;
+	struct blk_plug plug;
+
+	/*
+	 * this function runs all the bios we've collected for
+	 * a particular device.  We don't want to wander off to
+	 * another device without first sending all of these down.
+	 * So, setup a plug here and finish it off before we return
+	 */
+	blk_start_plug(&plug);
 
 	bdi = blk_get_backing_dev_info(device->bdev);
 	fs_info = device->dev_root->fs_info;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
-	/* we want to make sure that every time we switch from the sync
-	 * list to the normal list, we unplug
-	 */
-	num_sync_run = 0;
-
 loop:
 	spin_lock(&device->io_lock);
 
@@ -223,15 +215,6 @@ loop_lock:
 
 	spin_unlock(&device->io_lock);
 
-	/*
-	 * if we're doing the regular priority list, make sure we unplug
-	 * for any high prio bios we've sent down
-	 */
-	if (pending_bios == &device->pending_bios && num_sync_run > 0) {
-		num_sync_run = 0;
-		blk_run_backing_dev(bdi, NULL);
-	}
-
 	while (pending) {
 
 		rmb();
@@ -259,19 +242,11 @@ loop_lock:
 
 		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
 
-		if (cur->bi_rw & REQ_SYNC)
-			num_sync_run++;
-
 		submit_bio(cur->bi_rw, cur);
 		num_run++;
 		batch_run++;
-		if (need_resched()) {
-			if (num_sync_run) {
-				blk_run_backing_dev(bdi, NULL);
-				num_sync_run = 0;
-			}
+		if (need_resched())
 			cond_resched();
-		}
 
 		/*
 		 * we made progress, there is more work to do and the bdi
@@ -304,13 +279,8 @@ loop_lock:
 				 * against it before looping
 				 */
 				last_waited = ioc->last_waited;
-				if (need_resched()) {
-					if (num_sync_run) {
-						blk_run_backing_dev(bdi, NULL);
-						num_sync_run = 0;
-					}
+				if (need_resched())
 					cond_resched();
-				}
 				continue;
 			}
 			spin_lock(&device->io_lock);
@@ -323,22 +293,6 @@ loop_lock:
 		}
 	}
 
-	if (num_sync_run) {
-		num_sync_run = 0;
-		blk_run_backing_dev(bdi, NULL);
-	}
-	/*
-	 * IO has already been through a long path to get here.  Checksumming,
-	 * async helper threads, perhaps compression.  We've done a pretty
-	 * good job of collecting a batch of IO and should just unplug
-	 * the device right away.
-	 *
-	 * This will help anyone who is waiting on the IO, they might have
-	 * already unplugged, but managed to do so before the bio they
-	 * cared about found its way down here.
-	 */
-	blk_run_backing_dev(bdi, NULL);
-
 	cond_resched();
 	if (again)
 		goto loop;
@@ -349,6 +303,7 @@ loop_lock:
 	spin_unlock(&device->io_lock);
 
 done:
+	blk_finish_plug(&plug);
 	return 0;
 }
 
@@ -1923,6 +1878,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 
 	BUG_ON(ret);
 
+	trace_btrfs_chunk_free(root, map, chunk_offset, em->len);
+
 	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		ret = btrfs_del_sys_chunk(root, chunk_objectid, chunk_offset);
 		BUG_ON(ret);
@@ -2650,6 +2607,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	*num_bytes = chunk_bytes_by_type(type, calc_size,
 					 map->num_stripes, sub_stripes);
 
+	trace_btrfs_chunk_alloc(info->chunk_root, map, start, *num_bytes);
+
 	em = alloc_extent_map(GFP_NOFS);
 	if (!em) {
 		ret = -ENOMEM;
@@ -2758,6 +2717,7 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
 					     item_size);
 		BUG_ON(ret);
 	}
+
 	kfree(chunk);
 	return 0;
 }
@@ -2955,14 +2915,17 @@ static int find_live_mirror(struct map_lookup *map, int first, int num,
 static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 			     u64 logical, u64 *length,
 			     struct btrfs_multi_bio **multi_ret,
-			     int mirror_num, struct page *unplug_page)
+			     int mirror_num)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
 	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	u64 offset;
 	u64 stripe_offset;
+	u64 stripe_end_offset;
 	u64 stripe_nr;
+	u64 stripe_nr_orig;
+	u64 stripe_nr_end;
 	int stripes_allocated = 8;
 	int stripes_required = 1;
 	int stripe_index;
@@ -2971,7 +2934,7 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 	int max_errors = 0;
 	struct btrfs_multi_bio *multi = NULL;
 
-	if (multi_ret && !(rw & REQ_WRITE))
+	if (multi_ret && !(rw & (REQ_WRITE | REQ_DISCARD)))
 		stripes_allocated = 1;
 again:
 	if (multi_ret) {
@@ -2987,11 +2950,6 @@ again:
 	em = lookup_extent_mapping(em_tree, logical, *length);
 	read_unlock(&em_tree->lock);
 
-	if (!em && unplug_page) {
-		kfree(multi);
-		return 0;
-	}
-
 	if (!em) {
 		printk(KERN_CRIT "unable to find logical %llu len %llu\n",
 		       (unsigned long long)logical,
@@ -3017,7 +2975,15 @@ again:
 			max_errors = 1;
 		}
 	}
-	if (multi_ret && (rw & REQ_WRITE) &&
+	if (rw & REQ_DISCARD) {
+		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+				 BTRFS_BLOCK_GROUP_RAID1 |
+				 BTRFS_BLOCK_GROUP_DUP |
+				 BTRFS_BLOCK_GROUP_RAID10)) {
+			stripes_required = map->num_stripes;
+		}
+	}
+	if (multi_ret && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    stripes_allocated < stripes_required) {
 		stripes_allocated = map->num_stripes;
 		free_extent_map(em);
@@ -3037,23 +3003,37 @@ again:
 	/* stripe_offset is the offset of this block in its stripe*/
 	stripe_offset = offset - stripe_offset;
 
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
-			 BTRFS_BLOCK_GROUP_RAID10 |
-			 BTRFS_BLOCK_GROUP_DUP)) {
+	if (rw & REQ_DISCARD)
+		*length = min_t(u64, em->len - offset, *length);
+	else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+			      BTRFS_BLOCK_GROUP_RAID1 |
+			      BTRFS_BLOCK_GROUP_RAID10 |
+			      BTRFS_BLOCK_GROUP_DUP)) {
 		/* we limit the length of each bio to what fits in a stripe */
 		*length = min_t(u64, em->len - offset,
-			      map->stripe_len - stripe_offset);
+				map->stripe_len - stripe_offset);
 	} else {
 		*length = em->len - offset;
 	}
 
-	if (!multi_ret && !unplug_page)
+	if (!multi_ret)
 		goto out;
 
 	num_stripes = 1;
 	stripe_index = 0;
-	if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
-		if (unplug_page || (rw & REQ_WRITE))
+	stripe_nr_orig = stripe_nr;
+	stripe_nr_end = (offset + *length + map->stripe_len - 1) &
+			(~(map->stripe_len - 1));
+	do_div(stripe_nr_end, map->stripe_len);
+	stripe_end_offset = stripe_nr_end * map->stripe_len -
+			    (offset + *length);
+	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+		if (rw & REQ_DISCARD)
+			num_stripes = min_t(u64, map->num_stripes,
+					    stripe_nr_end - stripe_nr_orig);
+		stripe_index = do_div(stripe_nr, map->num_stripes);
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
+		if (rw & (REQ_WRITE | REQ_DISCARD))
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -3064,7 +3044,7 @@ again:
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (rw & REQ_WRITE)
+		if (rw & (REQ_WRITE | REQ_DISCARD))
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -3075,8 +3055,12 @@ again:
 		stripe_index = do_div(stripe_nr, factor);
 		stripe_index *= map->sub_stripes;
 
-		if (unplug_page || (rw & REQ_WRITE))
+		if (rw & REQ_WRITE)
 			num_stripes = map->sub_stripes;
+		else if (rw & REQ_DISCARD)
+			num_stripes = min_t(u64, map->sub_stripes *
+					    (stripe_nr_end - stripe_nr_orig),
+					    map->num_stripes);
 		else if (mirror_num)
 			stripe_index += mirror_num - 1;
 		else {
@@ -3094,24 +3078,101 @@ again:
 	}
 	BUG_ON(stripe_index >= map->num_stripes);
 
-	for (i = 0; i < num_stripes; i++) {
-		if (unplug_page) {
-			struct btrfs_device *device;
-			struct backing_dev_info *bdi;
-
-			device = map->stripes[stripe_index].dev;
-			if (device->bdev) {
-				bdi = blk_get_backing_dev_info(device->bdev);
-				if (bdi->unplug_io_fn)
-					bdi->unplug_io_fn(bdi, unplug_page);
-			}
-		} else {
+	if (rw & REQ_DISCARD) {
+		for (i = 0; i < num_stripes; i++) {
 			multi->stripes[i].physical =
 				map->stripes[stripe_index].physical +
 				stripe_offset + stripe_nr * map->stripe_len;
 			multi->stripes[i].dev = map->stripes[stripe_index].dev;
+
+			if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+				u64 stripes;
+				u32 last_stripe = 0;
+				int j;
+
+				div_u64_rem(stripe_nr_end - 1,
+					    map->num_stripes,
+					    &last_stripe);
+
+				for (j = 0; j < map->num_stripes; j++) {
+					u32 test;
+
+					div_u64_rem(stripe_nr_end - 1 - j,
+						    map->num_stripes, &test);
+					if (test == stripe_index)
+						break;
+				}
+				stripes = stripe_nr_end - 1 - j;
+				do_div(stripes, map->num_stripes);
+				multi->stripes[i].length = map->stripe_len *
+					(stripes - stripe_nr + 1);
+
+				if (i == 0) {
+					multi->stripes[i].length -=
+						stripe_offset;
+					stripe_offset = 0;
+				}
+				if (stripe_index == last_stripe)
+					multi->stripes[i].length -=
+						stripe_end_offset;
+			} else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
+				u64 stripes;
+				int j;
+				int factor = map->num_stripes /
+					     map->sub_stripes;
+				u32 last_stripe = 0;
+
+				div_u64_rem(stripe_nr_end - 1,
+					    factor, &last_stripe);
+				last_stripe *= map->sub_stripes;
+
+				for (j = 0; j < factor; j++) {
+					u32 test;
+
+					div_u64_rem(stripe_nr_end - 1 - j,
+						    factor, &test);
+
+					if (test ==
+					    stripe_index / map->sub_stripes)
+						break;
+				}
+				stripes = stripe_nr_end - 1 - j;
+				do_div(stripes, factor);
+				multi->stripes[i].length = map->stripe_len *
+					(stripes - stripe_nr + 1);
+
+				if (i < map->sub_stripes) {
+					multi->stripes[i].length -=
+						stripe_offset;
+					if (i == map->sub_stripes - 1)
+						stripe_offset = 0;
+				}
+				if (stripe_index >= last_stripe &&
+				    stripe_index <= (last_stripe +
+						     map->sub_stripes - 1)) {
+					multi->stripes[i].length -=
+						stripe_end_offset;
+				}
+			} else
+				multi->stripes[i].length = *length;
+
+			stripe_index++;
+			if (stripe_index == map->num_stripes) {
+				/* This could only happen for RAID0/10 */
+				stripe_index = 0;
+				stripe_nr++;
+			}
+		}
+	} else {
+		for (i = 0; i < num_stripes; i++) {
+			multi->stripes[i].physical =
+				map->stripes[stripe_index].physical +
+				stripe_offset +
+				stripe_nr * map->stripe_len;
+			multi->stripes[i].dev =
+				map->stripes[stripe_index].dev;
+			stripe_index++;
 		}
-		stripe_index++;
 	}
 	if (multi_ret) {
 		*multi_ret = multi;
@@ -3128,7 +3189,7 @@ int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 		      struct btrfs_multi_bio **multi_ret, int mirror_num)
 {
 	return __btrfs_map_block(map_tree, rw, logical, length, multi_ret,
-				 mirror_num, NULL);
+				 mirror_num);
 }
 
 int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
@@ -3196,14 +3257,6 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	return 0;
 }
 
-int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree,
-		      u64 logical, struct page *page)
-{
-	u64 length = PAGE_CACHE_SIZE;
-	return __btrfs_map_block(map_tree, READ, logical, &length,
-				 NULL, 0, page);
-}
-
 static void end_bio_multi_stripe(struct bio *bio, int err)
 {
 	struct btrfs_multi_bio *multi = bio->bi_private;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7fb59d45fe8..cc2eadaf7a2 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -126,6 +126,7 @@ struct btrfs_fs_devices {
 struct btrfs_bio_stripe {
 	struct btrfs_device *dev;
 	u64 physical;
+	u64 length; /* only used for discard mappings */
 };
 
 struct btrfs_multi_bio {
@@ -145,6 +146,17 @@ struct btrfs_device_info {
 	u64 max_avail;
 };
 
+struct map_lookup {
+	u64 type;
+	int io_align;
+	int io_width;
+	int stripe_len;
+	int sector_size;
+	int num_stripes;
+	int sub_stripes;
+	struct btrfs_bio_stripe stripes[];
+};
+
 /* Used to sort the devices by max_avail(descending sort) */
 int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2);
 
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index d779cefcfd7..cfd660550de 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -180,11 +180,10 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
-	int ret = 0, slot, advance;
+	int ret = 0, slot;
 	size_t total_size = 0, size_left = size;
 	unsigned long name_ptr;
 	size_t name_len;
-	u32 nritems;
 
 	/*
 	 * ok we want all objects associated with this id.
@@ -204,34 +203,24 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		goto err;
-	advance = 0;
+
 	while (1) {
 		leaf = path->nodes[0];
-		nritems = btrfs_header_nritems(leaf);
 		slot = path->slots[0];
 
 		/* this is where we start walking through the path */
-		if (advance || slot >= nritems) {
+		if (slot >= btrfs_header_nritems(leaf)) {
 			/*
 			 * if we've reached the last slot in this leaf we need
 			 * to go to the next leaf and reset everything
 			 */
-			if (slot >= nritems-1) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret)
-					break;
-				leaf = path->nodes[0];
-				nritems = btrfs_header_nritems(leaf);
-				slot = path->slots[0];
-			} else {
-				/*
-				 * just walking through the slots on this leaf
-				 */
-				slot++;
-				path->slots[0]++;
-			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto err;
+			else if (ret > 0)
+				break;
+			continue;
 		}
-		advance = 1;
 
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
@@ -242,13 +231,15 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 			break;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+		if (verify_dir_item(root, leaf, di))
+			continue;
 
 		name_len = btrfs_dir_name_len(leaf, di);
 		total_size += name_len + 1;
 
 		/* we are just looking for how big our buffer needs to be */
 		if (!size)
-			continue;
+			goto next;
 
 		if (!buffer || (name_len + 1) > size_left) {
 			ret = -ERANGE;
@@ -261,6 +252,8 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 
 		size_left -= name_len + 1;
 		buffer += name_len + 1;
+next:
+		path->slots[0]++;
 	}
 	ret = total_size;
 
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index f5ec2d44150..faccd47c6c4 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -57,7 +57,8 @@ static struct list_head *zlib_alloc_workspace(void)
 	if (!workspace)
 		return ERR_PTR(-ENOMEM);
 
-	workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize());
+	workspace->def_strm.workspace = vmalloc(zlib_deflate_workspacesize(
+						MAX_WBITS, MAX_MEM_LEVEL));
 	workspace->inf_strm.workspace = vmalloc(zlib_inflate_workspacesize());
 	workspace->buf = kmalloc(PAGE_CACHE_SIZE, GFP_NOFS);
 	if (!workspace->def_strm.workspace ||