Linux-libre 4.7.1-gnupck-4.7.1-gnu

55 files changed, 2525 insertions, 2480 deletions

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 6d263bb16..67a607709 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -63,9 +63,6 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 	}
 	kfree(value);
 
-	if (!IS_ERR(acl))
-		set_cached_acl(inode, type, acl);
-
 	return acl;
 }
 
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 80e8472d6..8bb350909 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1939,7 +1939,7 @@ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off,
  * from ipath->fspath->val[i].
  * when it returns, there are ipath->fspath->elem_cnt number of paths available
  * in ipath->fspath->val[]. when the allocated space wasn't sufficient, the
- * number of missed paths in recored in ipath->fspath->elem_missed, otherwise,
+ * number of missed paths is recorded in ipath->fspath->elem_missed, otherwise,
  * it's zero. ipath->fspath->bytes_missing holds the number of bytes that would
  * have been needed to return all paths.
  */
@@ -1991,7 +1991,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 	ifp = kmalloc(sizeof(*ifp), GFP_NOFS);
 	if (!ifp) {
-		kfree(fspath);
+		vfree(fspath);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 61205e3bb..4919aedb5 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -196,6 +196,16 @@ struct btrfs_inode {
 	struct list_head delayed_iput;
 	long delayed_iput_count;
 
+	/*
+	 * To avoid races between lockless (i_mutex not held) direct IO writes
+	 * and concurrent fsync requests. Direct IO writes must acquire read
+	 * access on this semaphore for creating an extent map and its
+	 * corresponding ordered extent. The fast fsync path must acquire write
+	 * access on this semaphore before it collects ordered extents and
+	 * extent maps.
+	 */
+	struct rw_semaphore dio_sem;
+
 	struct inode vfs_inode;
 };
 
@@ -303,7 +313,7 @@ struct btrfs_dio_private {
 	struct bio *dio_bio;
 
 	/*
-	 * The original bio may be splited to several sub-bios, this is
+	 * The original bio may be split to several sub-bios, this is
 	 * done during endio of sub-bios
 	 */
 	int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 516e19d1d..7706c8dc5 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1939,7 +1939,7 @@ again:
 		/*
 		 * Clear all references of this block. Do not free
 		 * the block itself even if is not referenced anymore
-		 * because it still carries valueable information
+		 * because it still carries valuable information
 		 * like whether it was ever written and IO completed.
 		 */
 		list_for_each_entry_safe(l, tmp, &block->ref_to_list,
@@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
 	 * This algorithm is recursive because the amount of used stack space
 	 * is very small and the max recursion depth is limited.
 	 */
-	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
+	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)",
 			     btrfsic_get_block_type(state, block),
 			     block->logical_bytenr, block->dev_state->name,
 			     block->dev_bytenr, block->mirror_num);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ff61a41ac..658c39b70 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -743,8 +743,11 @@ out:
 static struct {
 	struct list_head idle_ws;
 	spinlock_t ws_lock;
-	int num_ws;
-	atomic_t alloc_ws;
+	/* Number of free workspaces */
+	int free_ws;
+	/* Total number of allocated workspaces */
+	atomic_t total_ws;
+	/* Waiters for a free workspace */
 	wait_queue_head_t ws_wait;
 } btrfs_comp_ws[BTRFS_COMPRESS_TYPES];
 
@@ -758,16 +761,34 @@ void __init btrfs_init_compress(void)
 	int i;
 
 	for (i = 0; i < BTRFS_COMPRESS_TYPES; i++) {
+		struct list_head *workspace;
+
 		INIT_LIST_HEAD(&btrfs_comp_ws[i].idle_ws);
 		spin_lock_init(&btrfs_comp_ws[i].ws_lock);
-		atomic_set(&btrfs_comp_ws[i].alloc_ws, 0);
+		atomic_set(&btrfs_comp_ws[i].total_ws, 0);
 		init_waitqueue_head(&btrfs_comp_ws[i].ws_wait);
+
+		/*
+		 * Preallocate one workspace for each compression type so
+		 * we can guarantee forward progress in the worst case
+		 */
+		workspace = btrfs_compress_op[i]->alloc_workspace();
+		if (IS_ERR(workspace)) {
+			printk(KERN_WARNING
+	"BTRFS: cannot preallocate compression workspace, will try later");
+		} else {
+			atomic_set(&btrfs_comp_ws[i].total_ws, 1);
+			btrfs_comp_ws[i].free_ws = 1;
+			list_add(workspace, &btrfs_comp_ws[i].idle_ws);
+		}
 	}
 }
 
 /*
- * this finds an available workspace or allocates a new one
- * ERR_PTR is returned if things go bad.
+ * This finds an available workspace or allocates a new one.
+ * If it's not possible to allocate a new one, waits until there's one.
+ * Preallocation makes a forward progress guarantees and we do not return
+ * errors.
  */
 static struct list_head *find_workspace(int type)
 {
@@ -777,36 +798,58 @@ static struct list_head *find_workspace(int type)
 
 	struct list_head *idle_ws	= &btrfs_comp_ws[idx].idle_ws;
 	spinlock_t *ws_lock		= &btrfs_comp_ws[idx].ws_lock;
-	atomic_t *alloc_ws		= &btrfs_comp_ws[idx].alloc_ws;
+	atomic_t *total_ws		= &btrfs_comp_ws[idx].total_ws;
 	wait_queue_head_t *ws_wait	= &btrfs_comp_ws[idx].ws_wait;
-	int *num_ws			= &btrfs_comp_ws[idx].num_ws;
+	int *free_ws			= &btrfs_comp_ws[idx].free_ws;
 again:
 	spin_lock(ws_lock);
 	if (!list_empty(idle_ws)) {
 		workspace = idle_ws->next;
 		list_del(workspace);
-		(*num_ws)--;
+		(*free_ws)--;
 		spin_unlock(ws_lock);
 		return workspace;
 
 	}
-	if (atomic_read(alloc_ws) > cpus) {
+	if (atomic_read(total_ws) > cpus) {
 		DEFINE_WAIT(wait);
 
 		spin_unlock(ws_lock);
 		prepare_to_wait(ws_wait, &wait, TASK_UNINTERRUPTIBLE);
-		if (atomic_read(alloc_ws) > cpus && !*num_ws)
+		if (atomic_read(total_ws) > cpus && !*free_ws)
 			schedule();
 		finish_wait(ws_wait, &wait);
 		goto again;
 	}
-	atomic_inc(alloc_ws);
+	atomic_inc(total_ws);
 	spin_unlock(ws_lock);
 
 	workspace = btrfs_compress_op[idx]->alloc_workspace();
 	if (IS_ERR(workspace)) {
-		atomic_dec(alloc_ws);
+		atomic_dec(total_ws);
 		wake_up(ws_wait);
+
+		/*
+		 * Do not return the error but go back to waiting. There's a
+		 * workspace preallocated for each type and the compression
+		 * time is bounded so we get to a workspace eventually. This
+		 * makes our caller's life easier.
+		 *
+		 * To prevent silent and low-probability deadlocks (when the
+		 * initial preallocation fails), check if there are any
+		 * workspaces at all.
+		 */
+		if (atomic_read(total_ws) == 0) {
+			static DEFINE_RATELIMIT_STATE(_rs,
+					/* once per minute */ 60 * HZ,
+					/* no burst */ 1);
+
+			if (__ratelimit(&_rs)) {
+				printk(KERN_WARNING
+			    "no compression workspaces, low memory, retrying");
+			}
+		}
+		goto again;
 	}
 	return workspace;
 }
@@ -820,21 +863,21 @@ static void free_workspace(int type, struct list_head *workspace)
 	int idx = type - 1;
 	struct list_head *idle_ws	= &btrfs_comp_ws[idx].idle_ws;
 	spinlock_t *ws_lock		= &btrfs_comp_ws[idx].ws_lock;
-	atomic_t *alloc_ws		= &btrfs_comp_ws[idx].alloc_ws;
+	atomic_t *total_ws		= &btrfs_comp_ws[idx].total_ws;
 	wait_queue_head_t *ws_wait	= &btrfs_comp_ws[idx].ws_wait;
-	int *num_ws			= &btrfs_comp_ws[idx].num_ws;
+	int *free_ws			= &btrfs_comp_ws[idx].free_ws;
 
 	spin_lock(ws_lock);
-	if (*num_ws < num_online_cpus()) {
+	if (*free_ws < num_online_cpus()) {
 		list_add(workspace, idle_ws);
-		(*num_ws)++;
+		(*free_ws)++;
 		spin_unlock(ws_lock);
 		goto wake;
 	}
 	spin_unlock(ws_lock);
 
 	btrfs_compress_op[idx]->free_workspace(workspace);
-	atomic_dec(alloc_ws);
+	atomic_dec(total_ws);
 wake:
 	/*
 	 * Make sure counter is updated before we wake up waiters.
@@ -857,7 +900,7 @@ static void free_workspaces(void)
 			workspace = btrfs_comp_ws[i].idle_ws.next;
 			list_del(workspace);
 			btrfs_compress_op[i]->free_workspace(workspace);
-			atomic_dec(&btrfs_comp_ws[i].alloc_ws);
+			atomic_dec(&btrfs_comp_ws[i].total_ws);
 		}
 	}
 }
@@ -894,8 +937,6 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
 						      start, len, pages,
@@ -930,8 +971,6 @@ static int btrfs_decompress_biovec(int type, struct page **pages_in,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
 							 disk_start,
@@ -952,8 +991,6 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 	int ret;
 
 	workspace = find_workspace(type);
-	if (IS_ERR(workspace))
-		return PTR_ERR(workspace);
 
 	ret = btrfs_compress_op[type-1]->decompress(workspace, data_in,
 						  dest_page, start_byte,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 234707cc4..a85cf7d23 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -156,7 +156,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
 
 		/*
 		 * RCU really hurts here, we could free up the root node because
-		 * it was cow'ed but we may not get the new root node yet so do
+		 * it was COWed but we may not get the new root node yet so do
 		 * the inc_not_zero dance and if it doesn't work then
 		 * synchronize_rcu and try again.
 		 */
@@ -955,7 +955,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
 			      struct extent_buffer *buf)
 {
 	/*
-	 * Tree blocks not in refernece counted trees and tree roots
+	 * Tree blocks not in reference counted trees and tree roots
 	 * are never shared. If a block was allocated after the last
 	 * snapshot and the block was not allocated by tree relocation,
 	 * we know the block is not shared.
@@ -1011,7 +1011,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			return ret;
 		if (refs == 0) {
 			ret = -EROFS;
-			btrfs_std_error(root->fs_info, ret, NULL);
+			btrfs_handle_fs_error(root->fs_info, ret, NULL);
 			return ret;
 		}
 	} else {
@@ -1270,7 +1270,7 @@ __tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info,
 
 /*
  * tm is a pointer to the first operation to rewind within eb. then, all
- * previous operations will be rewinded (until we reach something older than
+ * previous operations will be rewound (until we reach something older than
  * time_seq).
  */
 static void
@@ -1345,7 +1345,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 }
 
 /*
- * Called with eb read locked. If the buffer cannot be rewinded, the same buffer
+ * Called with eb read locked. If the buffer cannot be rewound, the same buffer
  * is returned. If rewind operations happen, a fresh buffer is returned. The
  * returned buffer is always read-locked. If the returned buffer is not the
  * input buffer, the lock on the input buffer is released and the input buffer
@@ -1373,7 +1373,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 
 	if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		BUG_ON(tm->slot != 0);
-		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
+		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start,
+						eb->len);
 		if (!eb_rewin) {
 			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
@@ -1454,7 +1455,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	} else if (old_root) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		eb = alloc_dummy_extent_buffer(root->fs_info, logical);
+		eb = alloc_dummy_extent_buffer(root->fs_info, logical,
+					root->nodesize);
 	} else {
 		btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
 		eb = btrfs_clone_extent_buffer(eb_root);
@@ -1516,7 +1518,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 	 * 3) the root is not forced COW.
 	 *
 	 * What is forced COW:
-	 *    when we create snapshot during commiting the transaction,
+	 *    when we create snapshot during committing the transaction,
 	 *    after we've finished coping src root, we must COW the shared
 	 *    block to ensure the metadata consistency.
 	 */
@@ -1531,7 +1533,7 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 
 /*
  * cows a single block, see __btrfs_cow_block for the real work.
- * This version of it has extra checks so that a block isn't cow'd more than
+ * This version of it has extra checks so that a block isn't COWed more than
  * once per transaction, as long as it hasn't been written yet
  */
 noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
@@ -1784,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 			if (!err) {
 				tmp = (struct btrfs_disk_key *)(kaddr + offset -
 							map_start);
-			} else {
+			} else if (err == 1) {
 				read_extent_buffer(eb, &unaligned,
 						   offset, sizeof(unaligned));
 				tmp = &unaligned;
+			} else {
+				return err;
 			}
 
 		} else {
@@ -1929,7 +1933,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		child = read_node_slot(root, mid, 0);
 		if (!child) {
 			ret = -EROFS;
-			btrfs_std_error(root->fs_info, ret, NULL);
+			btrfs_handle_fs_error(root->fs_info, ret, NULL);
 			goto enospc;
 		}
 
@@ -2032,7 +2036,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		 */
 		if (!left) {
 			ret = -EROFS;
-			btrfs_std_error(root->fs_info, ret, NULL);
+			btrfs_handle_fs_error(root->fs_info, ret, NULL);
 			goto enospc;
 		}
 		wret = balance_node_right(trans, root, mid, left);
@@ -2511,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 		if (!btrfs_buffer_uptodate(tmp, 0, 0))
 			ret = -EIO;
 		free_extent_buffer(tmp);
+	} else {
+		ret = PTR_ERR(tmp);
 	}
 	return ret;
 }
@@ -2826,6 +2832,8 @@ cow_done:
 		}
 
 		ret = key_search(b, key, level, &prev_cmp, &slot);
+		if (ret < 0)
+			goto done;
 
 		if (level != 0) {
 			int dec = 0;
@@ -2989,7 +2997,7 @@ again:
 		btrfs_unlock_up_safe(p, level + 1);
 
 		/*
-		 * Since we can unwind eb's we want to do a real search every
+		 * Since we can unwind ebs we want to do a real search every
 		 * time.
 		 */
 		prev_cmp = -1;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 208d19938..4274a7bfd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -33,6 +33,7 @@
 #include <asm/kmap_types.h>
 #include <linux/pagemap.h>
 #include <linux/btrfs.h>
+#include <linux/btrfs_tree.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 #include <linux/sizes.h>
@@ -64,98 +65,6 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_COMPAT_EXTENT_TREE_V0
 
-/* holds pointers to all of the tree roots */
-#define BTRFS_ROOT_TREE_OBJECTID 1ULL
-
-/* stores information about which extents are in use, and reference counts */
-#define BTRFS_EXTENT_TREE_OBJECTID 2ULL
-
-/*
- * chunk tree stores translations from logical -> physical block numbering
- * the super block points to the chunk tree
- */
-#define BTRFS_CHUNK_TREE_OBJECTID 3ULL
-
-/*
- * stores information about which areas of a given device are in use.
- * one per device.  The tree of tree roots points to the device tree
- */
-#define BTRFS_DEV_TREE_OBJECTID 4ULL
-
-/* one per subvolume, storing files and directories */
-#define BTRFS_FS_TREE_OBJECTID 5ULL
-
-/* directory objectid inside the root tree */
-#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL
-
-/* holds checksums of all the data extents */
-#define BTRFS_CSUM_TREE_OBJECTID 7ULL
-
-/* holds quota configuration and tracking */
-#define BTRFS_QUOTA_TREE_OBJECTID 8ULL
-
-/* for storing items that use the BTRFS_UUID_KEY* types */
-#define BTRFS_UUID_TREE_OBJECTID 9ULL
-
-/* tracks free space in block groups. */
-#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
-
-/* device stats in the device tree */
-#define BTRFS_DEV_STATS_OBJECTID 0ULL
-
-/* for storing balance parameters in the root tree */
-#define BTRFS_BALANCE_OBJECTID -4ULL
-
-/* orhpan objectid for tracking unlinked/truncated files */
-#define BTRFS_ORPHAN_OBJECTID -5ULL
-
-/* does write ahead logging to speed up fsyncs */
-#define BTRFS_TREE_LOG_OBJECTID -6ULL
-#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL
-
-/* for space balancing */
-#define BTRFS_TREE_RELOC_OBJECTID -8ULL
-#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL
-
-/*
- * extent checksums all have this objectid
- * this allows them to share the logging tree
- * for fsyncs
- */
-#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL
-
-/* For storing free space cache */
-#define BTRFS_FREE_SPACE_OBJECTID -11ULL
-
-/*
- * The inode number assigned to the special inode for storing
- * free ino cache
- */
-#define BTRFS_FREE_INO_OBJECTID -12ULL
-
-/* dummy objectid represents multiple objectids */
-#define BTRFS_MULTIPLE_OBJECTIDS -255ULL
-
-/*
- * All files have objectids in this range.
- */
-#define BTRFS_FIRST_FREE_OBJECTID 256ULL
-#define BTRFS_LAST_FREE_OBJECTID -256ULL
-#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL
-
-
-/*
- * the device items go into the chunk tree.  The key is in the form
- * [ 1 BTRFS_DEV_ITEM_KEY device_id ]
- */
-#define BTRFS_DEV_ITEMS_OBJECTID 1ULL
-
-#define BTRFS_BTREE_INODE_OBJECTID 1
-
-#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2
-
-#define BTRFS_DEV_REPLACE_DEVID 0ULL
-
 /*
  * the max metadata block size.  This limit is somewhat artificial,
  * but the memmove costs go through the roof for larger blocks.
@@ -175,31 +84,14 @@ struct btrfs_ordered_sum;
  */
 #define BTRFS_LINK_MAX 65535U
 
-/* 32 bytes in various csum fields */
-#define BTRFS_CSUM_SIZE 32
-
-/* csum types */
-#define BTRFS_CSUM_TYPE_CRC32	0
-
 static const int btrfs_csum_sizes[] = { 4 };
 
 /* four bytes for CRC32 */
 #define BTRFS_EMPTY_DIR_SIZE 0
 
-/* spefic to btrfs_map_block(), therefore not in include/linux/blk_types.h */
+/* specific to btrfs_map_block(), therefore not in include/linux/blk_types.h */
 #define REQ_GET_READ_MIRRORS	(1 << 30)
 
-#define BTRFS_FT_UNKNOWN	0
-#define BTRFS_FT_REG_FILE	1
-#define BTRFS_FT_DIR		2
-#define BTRFS_FT_CHRDEV		3
-#define BTRFS_FT_BLKDEV		4
-#define BTRFS_FT_FIFO		5
-#define BTRFS_FT_SOCK		6
-#define BTRFS_FT_SYMLINK	7
-#define BTRFS_FT_XATTR		8
-#define BTRFS_FT_MAX		9
-
 /* ioprio of readahead is set to idle */
 #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
 
@@ -207,138 +99,10 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
-/*
- * The key defines the order in the tree, and so it also defines (optimal)
- * block layout.
- *
- * objectid corresponds to the inode number.
- *
- * type tells us things about the object, and is a kind of stream selector.
- * so for a given inode, keys with type of 1 might refer to the inode data,
- * type of 2 may point to file data in the btree and type == 3 may point to
- * extents.
- *
- * offset is the starting byte offset for this key in the stream.
- *
- * btrfs_disk_key is in disk byte order.  struct btrfs_key is always
- * in cpu native order.  Otherwise they are identical and their sizes
- * should be the same (ie both packed)
- */
-struct btrfs_disk_key {
-	__le64 objectid;
-	u8 type;
-	__le64 offset;
-} __attribute__ ((__packed__));
-
-struct btrfs_key {
-	u64 objectid;
-	u8 type;
-	u64 offset;
-} __attribute__ ((__packed__));
-
 struct btrfs_mapping_tree {
 	struct extent_map_tree map_tree;
 };
 
-struct btrfs_dev_item {
-	/* the internal btrfs device id */
-	__le64 devid;
-
-	/* size of the device */
-	__le64 total_bytes;
-
-	/* bytes used */
-	__le64 bytes_used;
-
-	/* optimal io alignment for this device */
-	__le32 io_align;
-
-	/* optimal io width for this device */
-	__le32 io_width;
-
-	/* minimal io size for this device */
-	__le32 sector_size;
-
-	/* type and info about this device */
-	__le64 type;
-
-	/* expected generation for this device */
-	__le64 generation;
-
-	/*
-	 * starting byte of this partition on the device,
-	 * to allow for stripe alignment in the future
-	 */
-	__le64 start_offset;
-
-	/* grouping information for allocation decisions */
-	__le32 dev_group;
-
-	/* seek speed 0-100 where 100 is fastest */
-	u8 seek_speed;
-
-	/* bandwidth 0-100 where 100 is fastest */
-	u8 bandwidth;
-
-	/* btrfs generated uuid for this device */
-	u8 uuid[BTRFS_UUID_SIZE];
-
-	/* uuid of FS who owns this device */
-	u8 fsid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_stripe {
-	__le64 devid;
-	__le64 offset;
-	u8 dev_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_chunk {
-	/* size of this chunk in bytes */
-	__le64 length;
-
-	/* objectid of the root referencing this chunk */
-	__le64 owner;
-
-	__le64 stripe_len;
-	__le64 type;
-
-	/* optimal io alignment for this chunk */
-	__le32 io_align;
-
-	/* optimal io width for this chunk */
-	__le32 io_width;
-
-	/* minimal io size for this chunk */
-	__le32 sector_size;
-
-	/* 2^16 stripes is quite a lot, a second limit is the size of a single
-	 * item in the btree
-	 */
-	__le16 num_stripes;
-
-	/* sub stripes only matter for raid10 */
-	__le16 sub_stripes;
-	struct btrfs_stripe stripe;
-	/* additional stripes go here */
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_EXTENT	1
-#define BTRFS_FREE_SPACE_BITMAP	2
-
-struct btrfs_free_space_entry {
-	__le64 offset;
-	__le64 bytes;
-	u8 type;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_header {
-	struct btrfs_disk_key location;
-	__le64 generation;
-	__le64 num_entries;
-	__le64 num_bitmaps;
-} __attribute__ ((__packed__));
-
 static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 {
 	BUG_ON(num_stripes == 0);
@@ -346,9 +110,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 		sizeof(struct btrfs_stripe) * (num_stripes - 1);
 }
 
-#define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
-#define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
-
 /*
  * File system states
  */
@@ -357,13 +118,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 #define BTRFS_FS_STATE_TRANS_ABORTED	2
 #define BTRFS_FS_STATE_DEV_REPLACING	3
 
-/* Super block flags */
-/* Errors detected */
-#define BTRFS_SUPER_FLAG_ERROR		(1ULL << 2)
-
-#define BTRFS_SUPER_FLAG_SEEDING	(1ULL << 32)
-#define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
-
 #define BTRFS_BACKREF_REV_MAX		256
 #define BTRFS_BACKREF_REV_SHIFT		56
 #define BTRFS_BACKREF_REV_MASK		(((u64)BTRFS_BACKREF_REV_MAX - 1) << \
@@ -410,7 +164,6 @@ struct btrfs_header {
  * room to translate 14 chunks with 3 stripes each.
  */
 #define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048
-#define BTRFS_LABEL_SIZE 256
 
 /*
  * just in case we somehow lose the roots and are not able to mount,
@@ -507,31 +260,6 @@ struct btrfs_super_block {
  * Compat flags that we support.  If any incompat flags are set other than the
  * ones specified below then we will fail to mount
  */
-#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE	(1ULL << 0)
-
-#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
-#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
-#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
-/*
- * some patches floated around with a second compression method
- * lets save that incompat here for when they do get in
- * Note we don't actually support it, we're just reserving the
- * number
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2	(1ULL << 4)
-
-/*
- * older kernels tried to do bigger metadata blocks, but the
- * code was pretty buggy.  Lets not let them try anymore.
- */
-#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA	(1ULL << 5)
-
-#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF	(1ULL << 6)
-#define BTRFS_FEATURE_INCOMPAT_RAID56		(1ULL << 7)
-#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA	(1ULL << 8)
-#define BTRFS_FEATURE_INCOMPAT_NO_HOLES		(1ULL << 9)
-
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_SAFE_SET		0ULL
 #define BTRFS_FEATURE_COMPAT_SAFE_CLEAR		0ULL
@@ -624,357 +352,8 @@ struct btrfs_path {
 	unsigned int need_commit_sem:1;
 	unsigned int skip_release_on_error:1;
 };
-
-/*
- * items in the extent btree are used to record the objectid of the
- * owner of the block and the number of references
- */
-
-struct btrfs_extent_item {
-	__le64 refs;
-	__le64 generation;
-	__le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_item_v0 {
-	__le32 refs;
-} __attribute__ ((__packed__));
-
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r) >> 4) - \
 					sizeof(struct btrfs_item))
-
-#define BTRFS_EXTENT_FLAG_DATA		(1ULL << 0)
-#define BTRFS_EXTENT_FLAG_TREE_BLOCK	(1ULL << 1)
-
-/* following flags only apply to tree blocks */
-
-/* use full backrefs for extent pointers in the block */
-#define BTRFS_BLOCK_FLAG_FULL_BACKREF	(1ULL << 8)
-
-/*
- * this flag is only used internally by scrub and may be changed at any time
- * it is only declared here to avoid collisions
- */
-#define BTRFS_EXTENT_FLAG_SUPER		(1ULL << 48)
-
-struct btrfs_tree_block_info {
-	struct btrfs_disk_key key;
-	u8 level;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_data_ref {
-	__le64 root;
-	__le64 objectid;
-	__le64 offset;
-	__le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_shared_data_ref {
-	__le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_inline_ref {
-	u8 type;
-	__le64 offset;
-} __attribute__ ((__packed__));
-
-/* old style backrefs item */
-struct btrfs_extent_ref_v0 {
-	__le64 root;
-	__le64 generation;
-	__le64 objectid;
-	__le32 count;
-} __attribute__ ((__packed__));
-
-
-/* dev extents record free space on individual devices.  The owner
- * field points back to the chunk allocation mapping tree that allocated
- * the extent.  The chunk tree uuid field is a way to double check the owner
- */
-struct btrfs_dev_extent {
-	__le64 chunk_tree;
-	__le64 chunk_objectid;
-	__le64 chunk_offset;
-	__le64 length;
-	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_ref {
-	__le64 index;
-	__le16 name_len;
-	/* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_extref {
-	__le64 parent_objectid;
-	__le64 index;
-	__le16 name_len;
-	__u8   name[0];
-	/* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_timespec {
-	__le64 sec;
-	__le32 nsec;
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_item {
-	/* nfs style generation number */
-	__le64 generation;
-	/* transid that last touched this inode */
-	__le64 transid;
-	__le64 size;
-	__le64 nbytes;
-	__le64 block_group;
-	__le32 nlink;
-	__le32 uid;
-	__le32 gid;
-	__le32 mode;
-	__le64 rdev;
-	__le64 flags;
-
-	/* modification sequence number for NFS */
-	__le64 sequence;
-
-	/*
-	 * a little future expansion, for more than this we can
-	 * just grow the inode item and version it
-	 */
-	__le64 reserved[4];
-	struct btrfs_timespec atime;
-	struct btrfs_timespec ctime;
-	struct btrfs_timespec mtime;
-	struct btrfs_timespec otime;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_log_item {
-	__le64 end;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_item {
-	struct btrfs_disk_key location;
-	__le64 transid;
-	__le16 data_len;
-	__le16 name_len;
-	u8 type;
-} __attribute__ ((__packed__));
-
-#define BTRFS_ROOT_SUBVOL_RDONLY	(1ULL << 0)
-
-/*
- * Internal in-memory flag that a subvolume has been marked for deletion but
- * still visible as a directory
- */
-#define BTRFS_ROOT_SUBVOL_DEAD		(1ULL << 48)
-
-struct btrfs_root_item {
-	struct btrfs_inode_item inode;
-	__le64 generation;
-	__le64 root_dirid;
-	__le64 bytenr;
-	__le64 byte_limit;
-	__le64 bytes_used;
-	__le64 last_snapshot;
-	__le64 flags;
-	__le32 refs;
-	struct btrfs_disk_key drop_progress;
-	u8 drop_level;
-	u8 level;
-
-	/*
-	 * The following fields appear after subvol_uuids+subvol_times
-	 * were introduced.
-	 */
-
-	/*
-	 * This generation number is used to test if the new fields are valid
-	 * and up to date while reading the root item. Every time the root item
-	 * is written out, the "generation" field is copied into this field. If
-	 * anyone ever mounted the fs with an older kernel, we will have
-	 * mismatching generation values here and thus must invalidate the
-	 * new fields. See btrfs_update_root and btrfs_find_last_root for
-	 * details.
-	 * the offset of generation_v2 is also used as the start for the memset
-	 * when invalidating the fields.
-	 */
-	__le64 generation_v2;
-	u8 uuid[BTRFS_UUID_SIZE];
-	u8 parent_uuid[BTRFS_UUID_SIZE];
-	u8 received_uuid[BTRFS_UUID_SIZE];
-	__le64 ctransid; /* updated when an inode changes */
-	__le64 otransid; /* trans when created */
-	__le64 stransid; /* trans when sent. non-zero for received subvol */
-	__le64 rtransid; /* trans when received. non-zero for received subvol */
-	struct btrfs_timespec ctime;
-	struct btrfs_timespec otime;
-	struct btrfs_timespec stime;
-	struct btrfs_timespec rtime;
-	__le64 reserved[8]; /* for future */
-} __attribute__ ((__packed__));
-
-/*
- * this is used for both forward and backward root refs
- */
-struct btrfs_root_ref {
-	__le64 dirid;
-	__le64 sequence;
-	__le16 name_len;
-} __attribute__ ((__packed__));
-
-struct btrfs_disk_balance_args {
-	/*
-	 * profiles to operate on, single is denoted by
-	 * BTRFS_AVAIL_ALLOC_BIT_SINGLE
-	 */
-	__le64 profiles;
-
-	/*
-	 * usage filter
-	 * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N'
-	 * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max
-	 */
-	union {
-		__le64 usage;
-		struct {
-			__le32 usage_min;
-			__le32 usage_max;
-		};
-	};
-
-	/* devid filter */
-	__le64 devid;
-
-	/* devid subset filter [pstart..pend) */
-	__le64 pstart;
-	__le64 pend;
-
-	/* btrfs virtual address space subset filter [vstart..vend) */
-	__le64 vstart;
-	__le64 vend;
-
-	/*
-	 * profile to convert to, single is denoted by
-	 * BTRFS_AVAIL_ALLOC_BIT_SINGLE
-	 */
-	__le64 target;
-
-	/* BTRFS_BALANCE_ARGS_* */
-	__le64 flags;
-
-	/*
-	 * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
-	 * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
-	 * and maximum
-	 */
-	union {
-		__le64 limit;
-		struct {
-			__le32 limit_min;
-			__le32 limit_max;
-		};
-	};
-
-	/*
-	 * Process chunks that cross stripes_min..stripes_max devices,
-	 * BTRFS_BALANCE_ARGS_STRIPES_RANGE
-	 */
-	__le32 stripes_min;
-	__le32 stripes_max;
-
-	__le64 unused[6];
-} __attribute__ ((__packed__));
-
-/*
- * store balance parameters to disk so that balance can be properly
- * resumed after crash or unmount
- */
-struct btrfs_balance_item {
-	/* BTRFS_BALANCE_* */
-	__le64 flags;
-
-	struct btrfs_disk_balance_args data;
-	struct btrfs_disk_balance_args meta;
-	struct btrfs_disk_balance_args sys;
-
-	__le64 unused[4];
-} __attribute__ ((__packed__));
-
-#define BTRFS_FILE_EXTENT_INLINE 0
-#define BTRFS_FILE_EXTENT_REG 1
-#define BTRFS_FILE_EXTENT_PREALLOC 2
-
-struct btrfs_file_extent_item {
-	/*
-	 * transaction id that created this extent
-	 */
-	__le64 generation;
-	/*
-	 * max number of bytes to hold this extent in ram
-	 * when we split a compressed extent we can't know how big
-	 * each of the resulting pieces will be.  So, this is
-	 * an upper limit on the size of the extent in ram instead of
-	 * an exact limit.
-	 */
-	__le64 ram_bytes;
-
-	/*
-	 * 32 bits for the various ways we might encode the data,
-	 * including compression and encryption.  If any of these
-	 * are set to something a given disk format doesn't understand
-	 * it is treated like an incompat flag for reading and writing,
-	 * but not for stat.
-	 */
-	u8 compression;
-	u8 encryption;
-	__le16 other_encoding; /* spare for later use */
-
-	/* are we inline data or a real extent? */
-	u8 type;
-
-	/*
-	 * disk space consumed by the extent, checksum blocks are included
-	 * in these numbers
-	 *
-	 * At this offset in the structure, the inline extent data start.
-	 */
-	__le64 disk_bytenr;
-	__le64 disk_num_bytes;
-	/*
-	 * the logical offset in file blocks (no csums)
-	 * this extent record is for.  This allows a file extent to point
-	 * into the middle of an existing extent on disk, sharing it
-	 * between two snapshots (useful if some bytes in the middle of the
-	 * extent have changed
-	 */
-	__le64 offset;
-	/*
-	 * the logical number of file blocks (no csums included).  This
-	 * always reflects the size uncompressed and without encoding.
-	 */
-	__le64 num_bytes;
-
-} __attribute__ ((__packed__));
-
-struct btrfs_csum_item {
-	u8 csum;
-} __attribute__ ((__packed__));
-
-struct btrfs_dev_stats_item {
-	/*
-	 * grow this item struct at the end for future enhancements and keep
-	 * the existing values unchanged
-	 */
-	__le64 values[BTRFS_DEV_STAT_VALUES_MAX];
-} __attribute__ ((__packed__));
-
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS	0
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID	1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED	0
-#define BTRFS_DEV_REPLACE_ITEM_STATE_STARTED		1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_SUSPENDED		2
-#define BTRFS_DEV_REPLACE_ITEM_STATE_FINISHED		3
-#define BTRFS_DEV_REPLACE_ITEM_STATE_CANCELED		4
-
 struct btrfs_dev_replace {
 	u64 replace_state;	/* see #define above */
 	u64 time_started;	/* seconds since 1-Jan-1970 */
@@ -1005,175 +384,6 @@ struct btrfs_dev_replace {
 	struct btrfs_scrub_progress scrub_progress;
 };
 
-struct btrfs_dev_replace_item {
-	/*
-	 * grow this item struct at the end for future enhancements and keep
-	 * the existing values unchanged
-	 */
-	__le64 src_devid;
-	__le64 cursor_left;
-	__le64 cursor_right;
-	__le64 cont_reading_from_srcdev_mode;
-
-	__le64 replace_state;
-	__le64 time_started;
-	__le64 time_stopped;
-	__le64 num_write_errors;
-	__le64 num_uncorrectable_read_errors;
-} __attribute__ ((__packed__));
-
-/* different types of block groups (and chunks) */
-#define BTRFS_BLOCK_GROUP_DATA		(1ULL << 0)
-#define BTRFS_BLOCK_GROUP_SYSTEM	(1ULL << 1)
-#define BTRFS_BLOCK_GROUP_METADATA	(1ULL << 2)
-#define BTRFS_BLOCK_GROUP_RAID0		(1ULL << 3)
-#define BTRFS_BLOCK_GROUP_RAID1		(1ULL << 4)
-#define BTRFS_BLOCK_GROUP_DUP		(1ULL << 5)
-#define BTRFS_BLOCK_GROUP_RAID10	(1ULL << 6)
-#define BTRFS_BLOCK_GROUP_RAID5         (1ULL << 7)
-#define BTRFS_BLOCK_GROUP_RAID6         (1ULL << 8)
-#define BTRFS_BLOCK_GROUP_RESERVED	(BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
-					 BTRFS_SPACE_INFO_GLOBAL_RSV)
-
-enum btrfs_raid_types {
-	BTRFS_RAID_RAID10,
-	BTRFS_RAID_RAID1,
-	BTRFS_RAID_DUP,
-	BTRFS_RAID_RAID0,
-	BTRFS_RAID_SINGLE,
-	BTRFS_RAID_RAID5,
-	BTRFS_RAID_RAID6,
-	BTRFS_NR_RAID_TYPES
-};
-
-#define BTRFS_BLOCK_GROUP_TYPE_MASK	(BTRFS_BLOCK_GROUP_DATA |    \
-					 BTRFS_BLOCK_GROUP_SYSTEM |  \
-					 BTRFS_BLOCK_GROUP_METADATA)
-
-#define BTRFS_BLOCK_GROUP_PROFILE_MASK	(BTRFS_BLOCK_GROUP_RAID0 |   \
-					 BTRFS_BLOCK_GROUP_RAID1 |   \
-					 BTRFS_BLOCK_GROUP_RAID5 |   \
-					 BTRFS_BLOCK_GROUP_RAID6 |   \
-					 BTRFS_BLOCK_GROUP_DUP |     \
-					 BTRFS_BLOCK_GROUP_RAID10)
-#define BTRFS_BLOCK_GROUP_RAID56_MASK	(BTRFS_BLOCK_GROUP_RAID5 |   \
-					 BTRFS_BLOCK_GROUP_RAID6)
-
-/*
- * We need a bit for restriper to be able to tell when chunks of type
- * SINGLE are available.  This "extended" profile format is used in
- * fs_info->avail_*_alloc_bits (in-memory) and balance item fields
- * (on-disk).  The corresponding on-disk bit in chunk.type is reserved
- * to avoid remappings between two formats in future.
- */
-#define BTRFS_AVAIL_ALLOC_BIT_SINGLE	(1ULL << 48)
-
-/*
- * A fake block group type that is used to communicate global block reserve
- * size to userspace via the SPACE_INFO ioctl.
- */
-#define BTRFS_SPACE_INFO_GLOBAL_RSV	(1ULL << 49)
-
-#define BTRFS_EXTENDED_PROFILE_MASK	(BTRFS_BLOCK_GROUP_PROFILE_MASK | \
-					 BTRFS_AVAIL_ALLOC_BIT_SINGLE)
-
-static inline u64 chunk_to_extended(u64 flags)
-{
-	if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)
-		flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-
-	return flags;
-}
-static inline u64 extended_to_chunk(u64 flags)
-{
-	return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-}
-
-struct btrfs_block_group_item {
-	__le64 used;
-	__le64 chunk_objectid;
-	__le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_info {
-	__le32 extent_count;
-	__le32 flags;
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
-
-#define BTRFS_QGROUP_LEVEL_SHIFT		48
-static inline u64 btrfs_qgroup_level(u64 qgroupid)
-{
-	return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
-}
-
-/*
- * is subvolume quota turned on?
- */
-#define BTRFS_QGROUP_STATUS_FLAG_ON		(1ULL << 0)
-/*
- * RESCAN is set during the initialization phase
- */
-#define BTRFS_QGROUP_STATUS_FLAG_RESCAN		(1ULL << 1)
-/*
- * Some qgroup entries are known to be out of date,
- * either because the configuration has changed in a way that
- * makes a rescan necessary, or because the fs has been mounted
- * with a non-qgroup-aware version.
- * Turning qouta off and on again makes it inconsistent, too.
- */
-#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT	(1ULL << 2)
-
-#define BTRFS_QGROUP_STATUS_VERSION        1
-
-struct btrfs_qgroup_status_item {
-	__le64 version;
-	/*
-	 * the generation is updated during every commit. As older
-	 * versions of btrfs are not aware of qgroups, it will be
-	 * possible to detect inconsistencies by checking the
-	 * generation on mount time
-	 */
-	__le64 generation;
-
-	/* flag definitions see above */
-	__le64 flags;
-
-	/*
-	 * only used during scanning to record the progress
-	 * of the scan. It contains a logical address
-	 */
-	__le64 rescan;
-} __attribute__ ((__packed__));
-
-struct btrfs_qgroup_info_item {
-	__le64 generation;
-	__le64 rfer;
-	__le64 rfer_cmpr;
-	__le64 excl;
-	__le64 excl_cmpr;
-} __attribute__ ((__packed__));
-
-/* flags definition for qgroup limits */
-#define BTRFS_QGROUP_LIMIT_MAX_RFER	(1ULL << 0)
-#define BTRFS_QGROUP_LIMIT_MAX_EXCL	(1ULL << 1)
-#define BTRFS_QGROUP_LIMIT_RSV_RFER	(1ULL << 2)
-#define BTRFS_QGROUP_LIMIT_RSV_EXCL	(1ULL << 3)
-#define BTRFS_QGROUP_LIMIT_RFER_CMPR	(1ULL << 4)
-#define BTRFS_QGROUP_LIMIT_EXCL_CMPR	(1ULL << 5)
-
-struct btrfs_qgroup_limit_item {
-	/*
-	 * only updated when any of the other values change
-	 */
-	__le64 flags;
-	__le64 max_rfer;
-	__le64 max_excl;
-	__le64 rsv_rfer;
-	__le64 rsv_excl;
-} __attribute__ ((__packed__));
-
 /* For raid type sysfs entries */
 struct raid_kobject {
 	int raid_type;
@@ -1221,7 +431,7 @@ struct btrfs_space_info {
 	 * bytes_pinned does not reflect the bytes that will be pinned once the
 	 * delayed refs are flushed, so this counter is inc'ed every time we
 	 * call btrfs_free_extent so it is a realtime count of what will be
-	 * freed once the transaction is committed.  It will be zero'ed every
+	 * freed once the transaction is committed.  It will be zeroed every
 	 * time the transaction commits.
 	 */
 	struct percpu_counter total_bytes_pinned;
@@ -1408,6 +618,27 @@ struct btrfs_block_group_cache {
 
 	struct btrfs_io_ctl io_ctl;
 
+	/*
+	 * Incremented when doing extent allocations and holding a read lock
+	 * on the space_info's groups_sem semaphore.
+	 * Decremented when an ordered extent that represents an IO against this
+	 * block group's range is created (after it's added to its inode's
+	 * root's list of ordered extents) or immediately after the allocation
+	 * if it's a metadata extent or fallocate extent (for these cases we
+	 * don't create ordered extents).
+	 */
+	atomic_t reservations;
+
+	/*
+	 * Incremented while holding the spinlock *lock* by a task checking if
+	 * it can perform a nocow write (incremented if the value for the *ro*
+	 * field is 0). Decremented by such tasks once they create an ordered
+	 * extent or before that if some error happens before reaching that step.
+	 * This is to prevent races between block group relocation and nocow
+	 * writes through direct IO.
+	 */
+	atomic_t nocow_writers;
+
 	/* Lock for free space tree operations. */
 	struct mutex free_space_lock;
 
@@ -2026,228 +1257,6 @@ struct btrfs_root {
 	atomic_t qgroup_meta_rsv;
 };
 
-struct btrfs_ioctl_defrag_range_args {
-	/* start of the defrag operation */
-	__u64 start;
-
-	/* number of bytes to defrag, use (u64)-1 to say all */
-	__u64 len;
-
-	/*
-	 * flags for the operation, which can include turning
-	 * on compression for this one defrag
-	 */
-	__u64 flags;
-
-	/*
-	 * any extent bigger than this will be considered
-	 * already defragged.  Use 0 to take the kernel default
-	 * Use 1 to say every single extent must be rewritten
-	 */
-	__u32 extent_thresh;
-
-	/*
-	 * which compression method to use if turning on compression
-	 * for this defrag operation.  If unspecified, zlib will
-	 * be used
-	 */
-	__u32 compress_type;
-
-	/* spare for later */
-	__u32 unused[4];
-};
-
-
-/*
- * inode items have the data typically returned from stat and store other
- * info about object characteristics.  There is one for every file and dir in
- * the FS
- */
-#define BTRFS_INODE_ITEM_KEY		1
-#define BTRFS_INODE_REF_KEY		12
-#define BTRFS_INODE_EXTREF_KEY		13
-#define BTRFS_XATTR_ITEM_KEY		24
-#define BTRFS_ORPHAN_ITEM_KEY		48
-/* reserve 2-15 close to the inode for later flexibility */
-
-/*
- * dir items are the name -> inode pointers in a directory.  There is one
- * for every name in a directory.
- */
-#define BTRFS_DIR_LOG_ITEM_KEY  60
-#define BTRFS_DIR_LOG_INDEX_KEY 72
-#define BTRFS_DIR_ITEM_KEY	84
-#define BTRFS_DIR_INDEX_KEY	96
-/*
- * extent data is for file data
- */
-#define BTRFS_EXTENT_DATA_KEY	108
-
-/*
- * extent csums are stored in a separate tree and hold csums for
- * an entire extent on disk.
- */
-#define BTRFS_EXTENT_CSUM_KEY	128
-
-/*
- * root items point to tree roots.  They are typically in the root
- * tree used by the super block to find all the other trees
- */
-#define BTRFS_ROOT_ITEM_KEY	132
-
-/*
- * root backrefs tie subvols and snapshots to the directory entries that
- * reference them
- */
-#define BTRFS_ROOT_BACKREF_KEY	144
-
-/*
- * root refs make a fast index for listing all of the snapshots and
- * subvolumes referenced by a given root.  They point directly to the
- * directory item in the root that references the subvol
- */
-#define BTRFS_ROOT_REF_KEY	156
-
-/*
- * extent items are in the extent map tree.  These record which blocks
- * are used, and how many references there are to each block
- */
-#define BTRFS_EXTENT_ITEM_KEY	168
-
-/*
- * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know
- * the length, so we save the level in key->offset instead of the length.
- */
-#define BTRFS_METADATA_ITEM_KEY	169
-
-#define BTRFS_TREE_BLOCK_REF_KEY	176
-
-#define BTRFS_EXTENT_DATA_REF_KEY	178
-
-#define BTRFS_EXTENT_REF_V0_KEY		180
-
-#define BTRFS_SHARED_BLOCK_REF_KEY	182
-
-#define BTRFS_SHARED_DATA_REF_KEY	184
-
-/*
- * block groups give us hints into the extent allocation trees.  Which
- * blocks are free etc etc
- */
-#define BTRFS_BLOCK_GROUP_ITEM_KEY 192
-
-/*
- * Every block group is represented in the free space tree by a free space info
- * item, which stores some accounting information. It is keyed on
- * (block_group_start, FREE_SPACE_INFO, block_group_length).
- */
-#define BTRFS_FREE_SPACE_INFO_KEY 198
-
-/*
- * A free space extent tracks an extent of space that is free in a block group.
- * It is keyed on (start, FREE_SPACE_EXTENT, length).
- */
-#define BTRFS_FREE_SPACE_EXTENT_KEY 199
-
-/*
- * When a block group becomes very fragmented, we convert it to use bitmaps
- * instead of extents. A free space bitmap is keyed on
- * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with
- * (length / sectorsize) bits.
- */
-#define BTRFS_FREE_SPACE_BITMAP_KEY 200
-
-#define BTRFS_DEV_EXTENT_KEY	204
-#define BTRFS_DEV_ITEM_KEY	216
-#define BTRFS_CHUNK_ITEM_KEY	228
-
-/*
- * Records the overall state of the qgroups.
- * There's only one instance of this key present,
- * (0, BTRFS_QGROUP_STATUS_KEY, 0)
- */
-#define BTRFS_QGROUP_STATUS_KEY         240
-/*
- * Records the currently used space of the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_INFO_KEY           242
-/*
- * Contains the user configured limits for the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_LIMIT_KEY          244
-/*
- * Records the child-parent relationship of qgroups. For
- * each relation, 2 keys are present:
- * (childid, BTRFS_QGROUP_RELATION_KEY, parentid)
- * (parentid, BTRFS_QGROUP_RELATION_KEY, childid)
- */
-#define BTRFS_QGROUP_RELATION_KEY       246
-
-/*
- * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
- */
-#define BTRFS_BALANCE_ITEM_KEY	248
-
-/*
- * The key type for tree items that are stored persistently, but do not need to
- * exist for extended period of time. The items can exist in any tree.
- *
- * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - balance status item
- *   (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
- */
-#define BTRFS_TEMPORARY_ITEM_KEY	248
-
-/*
- * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
- */
-#define BTRFS_DEV_STATS_KEY		249
-
-/*
- * The key type for tree items that are stored persistently and usually exist
- * for a long period, eg. filesystem lifetime. The item kinds can be status
- * information, stats or preference values. The item can exist in any tree.
- *
- * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - device statistics, store IO stats in the device tree, one key for all
- *   stats
- *   (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
- */
-#define BTRFS_PERSISTENT_ITEM_KEY	249
-
-/*
- * Persistantly stores the device replace state in the device tree.
- * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0).
- */
-#define BTRFS_DEV_REPLACE_KEY	250
-
-/*
- * Stores items that allow to quickly map UUIDs to something else.
- * These items are part of the filesystem UUID tree.
- * The key is built like this:
- * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits).
- */
-#if BTRFS_UUID_SIZE != 16
-#error "UUID items require BTRFS_UUID_SIZE == 16!"
-#endif
-#define BTRFS_UUID_KEY_SUBVOL	251	/* for UUIDs assigned to subvols */
-#define BTRFS_UUID_KEY_RECEIVED_SUBVOL	252	/* for UUIDs assigned to
-						 * received subvols */
-
-/*
- * string items are for debugging.  They just store a short string of
- * data in the FS
- */
-#define BTRFS_STRING_ITEM_KEY	253
-
 /*
  * Flags for mount options.
  *
@@ -2392,7 +1401,7 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token)
 	token->kaddr = NULL;
 }
 
-/* some macros to generate set/get funcs for the struct fields.  This
+/* some macros to generate set/get functions for the struct fields.  This
  * assumes there is a lefoo_to_cpu for every type, so lets make a simple
  * one for u8:
  */
@@ -3499,11 +2508,17 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root);
 int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
 				       struct btrfs_root *root);
+void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+					 const u64 start);
+void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait);
+				 unsigned long count, u64 transid, int wait);
 int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 bytenr,
@@ -4327,10 +3342,9 @@ static inline void assfail(char *expr, char *file, int line)
 #define ASSERT(expr)	((void)0)
 #endif
 
-#define btrfs_assert()
 __printf(5, 6)
 __cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
 		     unsigned int line, int errno, const char *fmt, ...);
 
 const char *btrfs_decode_error(int errno);
@@ -4340,6 +3354,46 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root, const char *function,
 			       unsigned int line, int errno);
 
+/*
+ * Call btrfs_abort_transaction as early as possible when an error condition is
+ * detected, that way the exact line number is reported.
+ */
+#define btrfs_abort_transaction(trans, root, errno)		\
+do {								\
+	/* Report first abort since mount */			\
+	if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,	\
+			&((root)->fs_info->fs_state))) {	\
+		WARN(1, KERN_DEBUG				\
+		"BTRFS: Transaction aborted (error %d)\n",	\
+		(errno));					\
+	}							\
+	__btrfs_abort_transaction((trans), (root), __func__,	\
+				  __LINE__, (errno));		\
+} while (0)
+
+#define btrfs_handle_fs_error(fs_info, errno, fmt, args...)		\
+do {								\
+	__btrfs_handle_fs_error((fs_info), __func__, __LINE__,	\
+			  (errno), fmt, ##args);		\
+} while (0)
+
+__printf(5, 6)
+__cold
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+		   unsigned int line, int errno, const char *fmt, ...);
+/*
+ * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
+ * will panic().  Otherwise we BUG() here.
+ */
+#define btrfs_panic(fs_info, errno, fmt, args...)			\
+do {									\
+	__btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args);	\
+	BUG();								\
+} while (0)
+
+
+/* compatibility and incompatibility defines */
+
 #define btrfs_set_fs_incompat(__fs_info, opt) \
 	__btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
 
@@ -4456,44 +3510,6 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
 	return !!(btrfs_super_compat_ro_flags(disk_super) & flag);
 }
 
-/*
- * Call btrfs_abort_transaction as early as possible when an error condition is
- * detected, that way the exact line number is reported.
- */
-#define btrfs_abort_transaction(trans, root, errno)		\
-do {								\
-	/* Report first abort since mount */			\
-	if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,	\
-			&((root)->fs_info->fs_state))) {	\
-		WARN(1, KERN_DEBUG				\
-		"BTRFS: Transaction aborted (error %d)\n",	\
-		(errno));					\
-	}							\
-	__btrfs_abort_transaction((trans), (root), __func__,	\
-				  __LINE__, (errno));		\
-} while (0)
-
-#define btrfs_std_error(fs_info, errno, fmt, args...)		\
-do {								\
-	__btrfs_std_error((fs_info), __func__, __LINE__,	\
-			  (errno), fmt, ##args);		\
-} while (0)
-
-__printf(5, 6)
-__cold
-void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
-		   unsigned int line, int errno, const char *fmt, ...);
-
-/*
- * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
- * will panic().  Otherwise we BUG() here.
- */
-#define btrfs_panic(fs_info, errno, fmt, args...)			\
-do {									\
-	__btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args);	\
-	BUG();								\
-} while (0)
-
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6cef0062f..d3aaabbfa 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -134,7 +134,7 @@ again:
 	/* cached in the btrfs inode and can be accessed */
 	atomic_add(2, &node->refs);
 
-	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	ret = radix_tree_preload(GFP_NOFS);
 	if (ret) {
 		kmem_cache_free(delayed_node_cache, node);
 		return ERR_PTR(ret);
@@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
 	return 0;
 }
 
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list)
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_delayed_item *item;
 
 	delayed_node = btrfs_get_delayed_node(inode);
 	if (!delayed_node)
-		return;
+		return false;
+
+	/*
+	 * We can only do one readdir with delayed items at a time because of
+	 * item->readdir_list.
+	 */
+	inode_unlock_shared(inode);
+	inode_lock(inode);
 
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
 	 * requeue or dequeue this delayed node.
 	 */
 	atomic_dec(&delayed_node->refs);
+
+	return true;
 }
 
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list)
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_item *curr, *next;
 
@@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 		if (atomic_dec_and_test(&curr->refs))
 			kfree(curr);
 	}
+
+	/*
+	 * The VFS is going to do up_read(), so we need to downgrade back to a
+	 * read lock.
+	 */
+	downgrade_write(&inode->i_rwsem);
 }
 
 int btrfs_should_delete_dir_index(struct list_head *del_list,
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 0167853c8..2495b3d40 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
 void btrfs_destroy_delayed_inodes(struct btrfs_root *root);
 
 /* Used for readdir() */
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list);
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list);
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index c24b653c7..5fca9534a 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -188,7 +188,7 @@ struct btrfs_delayed_ref_root {
 
 	/*
 	 * To make qgroup to skip given root.
-	 * This is for snapshot, as btrfs_qgroup_inherit() will manully
+	 * This is for snapshot, as btrfs_qgroup_inherit() will manually
 	 * modify counters for snapshot and its source, so we should skip
 	 * the snapshot in new_root/old_roots or it will get calculated twice
 	 */
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 26bcb487f..63ef9cdf0 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -44,9 +44,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 						struct btrfs_fs_info *fs_info,
 						struct btrfs_device *srcdev,
 						struct btrfs_device *tgtdev);
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
-					 char *srcdev_name,
-					 struct btrfs_device **device);
 static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 static int btrfs_dev_replace_kthread(void *data);
 static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
@@ -305,8 +302,8 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
 		dev_replace->cursor_left_last_write_of_item;
 }
 
-int btrfs_dev_replace_start(struct btrfs_root *root,
-			    struct btrfs_ioctl_dev_replace_args *args)
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+				u64 srcdevid, char *srcdev_name, int read_src)
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -315,29 +312,16 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	struct btrfs_device *tgt_device = NULL;
 	struct btrfs_device *src_device = NULL;
 
-	switch (args->start.cont_reading_from_srcdev_mode) {
-	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
-	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
-	    args->start.tgtdev_name[0] == '\0')
-		return -EINVAL;
-
 	/* the disk copy procedure reuses the scrub code */
 	mutex_lock(&fs_info->volume_mutex);
-	ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
-					    args->start.srcdev_name,
-					    &src_device);
+	ret = btrfs_find_device_by_devspec(root, srcdevid,
+					    srcdev_name, &src_device);
 	if (ret) {
 		mutex_unlock(&fs_info->volume_mutex);
 		return ret;
 	}
 
-	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
+	ret = btrfs_init_dev_replace_tgtdev(root, tgtdev_name,
 					    src_device, &tgt_device);
 	mutex_unlock(&fs_info->volume_mutex);
 	if (ret)
@@ -364,18 +348,17 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
-		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
+		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
 		goto leave;
 	}
 
-	dev_replace->cont_reading_from_srcdev_mode =
-		args->start.cont_reading_from_srcdev_mode;
+	dev_replace->cont_reading_from_srcdev_mode = read_src;
 	WARN_ON(!src_device);
 	dev_replace->srcdev = src_device;
 	WARN_ON(!tgt_device);
 	dev_replace->tgtdev = tgt_device;
 
-	btrfs_info_in_rcu(root->fs_info,
+	btrfs_info_in_rcu(fs_info,
 		      "dev_replace from %s (devid %llu) to %s started",
 		      src_device->missing ? "<missing disk>" :
 		        rcu_str_deref(src_device->name),
@@ -396,14 +379,13 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 	dev_replace->item_needs_writeback = 1;
 	atomic64_set(&dev_replace->num_write_errors, 0);
 	atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
-	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
 	btrfs_dev_replace_unlock(dev_replace, 1);
 
 	ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
+		btrfs_err(fs_info, "kobj add dev failed %d\n", ret);
 
-	btrfs_wait_ordered_roots(root->fs_info, -1);
+	btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
 
 	/* force writing the updated state information to disk */
 	trans = btrfs_start_transaction(root, 0);
@@ -421,11 +403,9 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
 			      btrfs_device_get_total_bytes(src_device),
 			      &dev_replace->scrub_progress, 0, 1);
 
-	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
-	/* don't warn if EINPROGRESS, someone else might be running scrub */
+	ret = btrfs_dev_replace_finishing(fs_info, ret);
 	if (ret == -EINPROGRESS) {
-		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
-		ret = 0;
+		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
 	} else {
 		WARN_ON(ret);
 	}
@@ -440,8 +420,37 @@ leave:
 	return ret;
 }
 
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
+			    struct btrfs_ioctl_dev_replace_args *args)
+{
+	int ret;
+
+	switch (args->start.cont_reading_from_srcdev_mode) {
+	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
+	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
+	    args->start.tgtdev_name[0] == '\0')
+		return -EINVAL;
+
+	ret = btrfs_dev_replace_start(root, args->start.tgtdev_name,
+					args->start.srcdevid,
+					args->start.srcdev_name,
+					args->start.cont_reading_from_srcdev_mode);
+	args->result = ret;
+	/* don't warn if EINPROGRESS, someone else might be running scrub */
+	if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS)
+		ret = 0;
+
+	return ret;
+}
+
 /*
- * blocked until all flighting bios are finished.
+ * blocked until all in-flight bios operations are finished.
  */
 static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info)
 {
@@ -495,7 +504,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
 	}
-	btrfs_wait_ordered_roots(root->fs_info, -1);
+	btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
@@ -560,10 +569,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	ASSERT(list_empty(&src_device->resized_list));
 	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
 	tgt_device->commit_bytes_used = src_device->bytes_used;
-	if (fs_info->sb->s_bdev == src_device->bdev)
-		fs_info->sb->s_bdev = tgt_device->bdev;
-	if (fs_info->fs_devices->latest_bdev == src_device->bdev)
-		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
+
+	btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
 
@@ -626,25 +634,6 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
 	write_unlock(&em_tree->lock);
 }
 
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
-					 char *srcdev_name,
-					 struct btrfs_device **device)
-{
-	int ret;
-
-	if (srcdevid) {
-		ret = 0;
-		*device = btrfs_find_device(root->fs_info, srcdevid, NULL,
-					    NULL);
-		if (!*device)
-			ret = -ENOENT;
-	} else {
-		ret = btrfs_find_device_missing_or_by_path(root, srcdev_name,
-							   device);
-	}
-	return ret;
-}
-
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args)
 {
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 29e3ef5f9..e922b42d9 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -25,8 +25,10 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 			  struct btrfs_fs_info *fs_info);
 void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info);
-int btrfs_dev_replace_start(struct btrfs_root *root,
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
 			    struct btrfs_ioctl_dev_replace_args *args);
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+				u64 srcdevid, char *srcdev_name, int read_src);
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args);
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4e47849d7..60ce11903 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -384,7 +384,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 	/*
 	 * Things reading via commit roots that don't have normal protection,
 	 * like send, can have a really old block in cache that may point at a
-	 * block that has been free'd and re-allocated.  So don't clear uptodate
+	 * block that has been freed and re-allocated.  So don't clear uptodate
 	 * if we find an eb that is under IO (dirty/writeback) because we could
 	 * end up reading in the stale data and then writing it back out and
 	 * making everybody very sad.
@@ -418,7 +418,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
 		/*
 		 * The super_block structure does not span the whole
 		 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
-		 * is filled with zeros and is included in the checkum.
+		 * is filled with zeros and is included in the checksum.
 		 */
 		crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
 				crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
@@ -600,7 +600,7 @@ static noinline int check_leaf(struct btrfs_root *root,
 
 		/*
 		 * Check to make sure that we don't point outside of the leaf,
-		 * just incase all the items are consistent to eachother, but
+		 * just in case all the items are consistent to each other, but
 		 * all point outside of the leaf.
 		 */
 		if (btrfs_item_end_nr(leaf, slot) >
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
 	struct inode *btree_inode = root->fs_info->btree_inode;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return 0;
 
 	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1147,7 +1147,8 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr)
 {
 	if (btrfs_test_is_dummy_root(root))
-		return alloc_test_extent_buffer(root->fs_info, bytenr);
+		return alloc_test_extent_buffer(root->fs_info, bytenr,
+				root->nodesize);
 	return alloc_extent_buffer(root->fs_info, bytenr);
 }
 
@@ -1171,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 	if (ret) {
@@ -1314,14 +1315,16 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 /* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 
 	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, root, NULL, 1);
+	/* We don't use the stripesize in selftest, set it as sectorsize */
+	__setup_root(nodesize, sectorsize, sectorsize, root, NULL,
+			BTRFS_ROOT_TREE_OBJECTID);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1640,7 +1643,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 {
 	int ret;
 
-	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	ret = radix_tree_preload(GFP_NOFS);
 	if (ret)
 		return ret;
 
@@ -1803,6 +1806,13 @@ static int cleaner_kthread(void *arg)
 		if (btrfs_need_cleaner_sleep(root))
 			goto sleep;
 
+		/*
+		 * Do not do anything if we might cause open_ctree() to block
+		 * before we have finished mounting the filesystem.
+		 */
+		if (!root->fs_info->open)
+			goto sleep;
+
 		if (!mutex_trylock(&root->fs_info->cleaner_mutex))
 			goto sleep;
 
@@ -2417,7 +2427,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 	/* returns with log_tree_root freed on success */
 	ret = btrfs_recover_log_trees(log_tree_root);
 	if (ret) {
-		btrfs_std_error(tree_root->fs_info, ret,
+		btrfs_handle_fs_error(tree_root->fs_info, ret,
 			    "Failed to recover log tree");
 		free_extent_buffer(log_tree_root->node);
 		kfree(log_tree_root);
@@ -2713,7 +2723,7 @@ int open_ctree(struct super_block *sb,
 	 * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
 	 */
 	if (btrfs_check_super_csum(bh->b_data)) {
-		printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
+		btrfs_err(fs_info, "superblock checksum mismatch");
 		err = -EINVAL;
 		brelse(bh);
 		goto fail_alloc;
@@ -2733,7 +2743,7 @@ int open_ctree(struct super_block *sb,
 
 	ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
+		btrfs_err(fs_info, "superblock contains fatal errors");
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2768,9 +2778,9 @@ int open_ctree(struct super_block *sb,
 	features = btrfs_super_incompat_flags(disk_super) &
 		~BTRFS_FEATURE_INCOMPAT_SUPP;
 	if (features) {
-		printk(KERN_ERR "BTRFS: couldn't mount because of "
-		       "unsupported optional features (%Lx).\n",
-		       features);
+		btrfs_err(fs_info,
+		    "cannot mount because of unsupported optional features (%llx)",
+		    features);
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2781,7 +2791,7 @@ int open_ctree(struct super_block *sb,
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
 
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
-		printk(KERN_INFO "BTRFS: has skinny extents\n");
+		btrfs_info(fs_info, "has skinny extents");
 
 	/*
 	 * flag our filesystem as having big metadata blocks if
@@ -2789,13 +2799,14 @@ int open_ctree(struct super_block *sb,
 	 */
 	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
 		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
-			printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
+			btrfs_info(fs_info,
+				"flagging fs with big metadata feature");
 		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
 	}
 
 	nodesize = btrfs_super_nodesize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = btrfs_super_stripesize(disk_super);
+	stripesize = sectorsize;
 	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
@@ -2805,9 +2816,9 @@ int open_ctree(struct super_block *sb,
 	 */
 	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
 	    (sectorsize != nodesize)) {
-		printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes "
-				"are not allowed for mixed block groups on %s\n",
-				sb->s_id);
+		btrfs_err(fs_info,
+"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
+			nodesize, sectorsize);
 		goto fail_alloc;
 	}
 
@@ -2820,8 +2831,8 @@ int open_ctree(struct super_block *sb,
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
 	if (!(sb->s_flags & MS_RDONLY) && features) {
-		printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
-		       "unsupported option features (%Lx).\n",
+		btrfs_err(fs_info,
+	"cannot mount read-write because of unsupported optional features (%llx)",
 		       features);
 		err = -EINVAL;
 		goto fail_alloc;
@@ -2850,8 +2861,7 @@ int open_ctree(struct super_block *sb,
 	ret = btrfs_read_sys_array(tree_root);
 	mutex_unlock(&fs_info->chunk_mutex);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: failed to read the system "
-		       "array on %s\n", sb->s_id);
+		btrfs_err(fs_info, "failed to read the system array: %d", ret);
 		goto fail_sb_buffer;
 	}
 
@@ -2865,8 +2875,7 @@ int open_ctree(struct super_block *sb,
 					   generation);
 	if (IS_ERR(chunk_root->node) ||
 	    !extent_buffer_uptodate(chunk_root->node)) {
-		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
-		       sb->s_id);
+		btrfs_err(fs_info, "failed to read chunk root");
 		if (!IS_ERR(chunk_root->node))
 			free_extent_buffer(chunk_root->node);
 		chunk_root->node = NULL;
@@ -2880,8 +2889,7 @@ int open_ctree(struct super_block *sb,
 
 	ret = btrfs_read_chunk_tree(chunk_root);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n",
-		       sb->s_id);
+		btrfs_err(fs_info, "failed to read chunk tree: %d", ret);
 		goto fail_tree_roots;
 	}
 
@@ -2892,8 +2900,7 @@ int open_ctree(struct super_block *sb,
 	btrfs_close_extra_devices(fs_devices, 0);
 
 	if (!fs_devices->latest_bdev) {
-		printk(KERN_ERR "BTRFS: failed to read devices on %s\n",
-		       sb->s_id);
+		btrfs_err(fs_info, "failed to read devices");
 		goto fail_tree_roots;
 	}
 
@@ -2905,8 +2912,7 @@ retry_root_backup:
 					  generation);
 	if (IS_ERR(tree_root->node) ||
 	    !extent_buffer_uptodate(tree_root->node)) {
-		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
-		       sb->s_id);
+		btrfs_warn(fs_info, "failed to read tree root");
 		if (!IS_ERR(tree_root->node))
 			free_extent_buffer(tree_root->node);
 		tree_root->node = NULL;
@@ -2938,20 +2944,19 @@ retry_root_backup:
 
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: failed to recover balance\n");
+		btrfs_err(fs_info, "failed to recover balance: %d", ret);
 		goto fail_block_groups;
 	}
 
 	ret = btrfs_init_dev_stats(fs_info);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
-		       ret);
+		btrfs_err(fs_info, "failed to init dev_stats: %d", ret);
 		goto fail_block_groups;
 	}
 
 	ret = btrfs_init_dev_replace(fs_info);
 	if (ret) {
-		pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
+		btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
 		goto fail_block_groups;
 	}
 
@@ -2959,31 +2964,33 @@ retry_root_backup:
 
 	ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
 	if (ret) {
-		pr_err("BTRFS: failed to init sysfs fsid interface: %d\n", ret);
+		btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
+				ret);
 		goto fail_block_groups;
 	}
 
 	ret = btrfs_sysfs_add_device(fs_devices);
 	if (ret) {
-		pr_err("BTRFS: failed to init sysfs device interface: %d\n", ret);
+		btrfs_err(fs_info, "failed to init sysfs device interface: %d",
+				ret);
 		goto fail_fsdev_sysfs;
 	}
 
 	ret = btrfs_sysfs_add_mounted(fs_info);
 	if (ret) {
-		pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
+		btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
 		goto fail_fsdev_sysfs;
 	}
 
 	ret = btrfs_init_space_info(fs_info);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+		btrfs_err(fs_info, "failed to initialize space info: %d", ret);
 		goto fail_sysfs;
 	}
 
 	ret = btrfs_read_block_groups(fs_info->extent_root);
 	if (ret) {
-		printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+		btrfs_err(fs_info, "failed to read block groups: %d", ret);
 		goto fail_sysfs;
 	}
 	fs_info->num_tolerated_disk_barrier_failures =
@@ -2991,7 +2998,8 @@ retry_root_backup:
 	if (fs_info->fs_devices->missing_devices >
 	     fs_info->num_tolerated_disk_barrier_failures &&
 	    !(sb->s_flags & MS_RDONLY)) {
-		pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n",
+		btrfs_warn(fs_info,
+"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed",
 			fs_info->fs_devices->missing_devices,
 			fs_info->num_tolerated_disk_barrier_failures);
 		goto fail_sysfs;
@@ -3011,13 +3019,12 @@ retry_root_backup:
 	if (!btrfs_test_opt(tree_root, SSD) &&
 	    !btrfs_test_opt(tree_root, NOSSD) &&
 	    !fs_info->fs_devices->rotating) {
-		printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
-		       "mode\n");
+		btrfs_info(fs_info, "detected SSD devices, enabling SSD mode");
 		btrfs_set_opt(fs_info->mount_opt, SSD);
 	}
 
 	/*
-	 * Mount does not set all options immediatelly, we can do it now and do
+	 * Mount does not set all options immediately, we can do it now and do
 	 * not have to wait for transaction commit
 	 */
 	btrfs_apply_pending_changes(fs_info);
@@ -3030,8 +3037,9 @@ retry_root_backup:
 				    1 : 0,
 				    fs_info->check_integrity_print_mask);
 		if (ret)
-			printk(KERN_WARNING "BTRFS: failed to initialize"
-			       " integrity check module %s\n", sb->s_id);
+			btrfs_warn(fs_info,
+				"failed to initialize integrity check module: %d",
+				ret);
 	}
 #endif
 	ret = btrfs_read_qgroup_config(fs_info);
@@ -3061,8 +3069,8 @@ retry_root_backup:
 		ret = btrfs_recover_relocation(tree_root);
 		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
-			printk(KERN_WARNING
-			       "BTRFS: failed to recover relocation\n");
+			btrfs_warn(fs_info, "failed to recover relocation: %d",
+					ret);
 			err = -EINVAL;
 			goto fail_qgroup;
 		}
@@ -3083,11 +3091,11 @@ retry_root_backup:
 
 	if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) &&
 	    !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
-		pr_info("BTRFS: creating free space tree\n");
+		btrfs_info(fs_info, "creating free space tree");
 		ret = btrfs_create_free_space_tree(fs_info);
 		if (ret) {
-			pr_warn("BTRFS: failed to create free space tree %d\n",
-				ret);
+			btrfs_warn(fs_info,
+				"failed to create free space tree: %d", ret);
 			close_ctree(tree_root);
 			return ret;
 		}
@@ -3104,14 +3112,14 @@ retry_root_backup:
 
 	ret = btrfs_resume_balance_async(fs_info);
 	if (ret) {
-		printk(KERN_WARNING "BTRFS: failed to resume balance\n");
+		btrfs_warn(fs_info, "failed to resume balance: %d", ret);
 		close_ctree(tree_root);
 		return ret;
 	}
 
 	ret = btrfs_resume_dev_replace_async(fs_info);
 	if (ret) {
-		pr_warn("BTRFS: failed to resume dev_replace\n");
+		btrfs_warn(fs_info, "failed to resume device replace: %d", ret);
 		close_ctree(tree_root);
 		return ret;
 	}
@@ -3120,33 +3128,33 @@ retry_root_backup:
 
 	if (btrfs_test_opt(tree_root, CLEAR_CACHE) &&
 	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
-		pr_info("BTRFS: clearing free space tree\n");
+		btrfs_info(fs_info, "clearing free space tree");
 		ret = btrfs_clear_free_space_tree(fs_info);
 		if (ret) {
-			pr_warn("BTRFS: failed to clear free space tree %d\n",
-				ret);
+			btrfs_warn(fs_info,
+				"failed to clear free space tree: %d", ret);
 			close_ctree(tree_root);
 			return ret;
 		}
 	}
 
 	if (!fs_info->uuid_root) {
-		pr_info("BTRFS: creating UUID tree\n");
+		btrfs_info(fs_info, "creating UUID tree");
 		ret = btrfs_create_uuid_tree(fs_info);
 		if (ret) {
-			pr_warn("BTRFS: failed to create the UUID tree %d\n",
-				ret);
+			btrfs_warn(fs_info,
+				"failed to create the UUID tree: %d", ret);
 			close_ctree(tree_root);
 			return ret;
 		}
 	} else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) ||
 		   fs_info->generation !=
 				btrfs_super_uuid_tree_generation(disk_super)) {
-		pr_info("BTRFS: checking UUID tree\n");
+		btrfs_info(fs_info, "checking UUID tree");
 		ret = btrfs_check_uuid_tree(fs_info);
 		if (ret) {
-			pr_warn("BTRFS: failed to check the UUID tree %d\n",
-				ret);
+			btrfs_warn(fs_info,
+				"failed to check the UUID tree: %d", ret);
 			close_ctree(tree_root);
 			return ret;
 		}
@@ -3245,7 +3253,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 		btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
 				"lost page write due to IO error on %s",
 					  rcu_str_deref(device->name));
-		/* note, we dont' set_buffer_write_io_error because we have
+		/* note, we don't set_buffer_write_io_error because we have
 		 * our own ways of dealing with the IO errors
 		 */
 		clear_buffer_uptodate(bh);
@@ -3646,7 +3654,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		if (ret) {
 			mutex_unlock(
 				&root->fs_info->fs_devices->device_list_mutex);
-			btrfs_std_error(root->fs_info, ret,
+			btrfs_handle_fs_error(root->fs_info, ret,
 				    "errors while submitting device barriers.");
 			return ret;
 		}
@@ -3686,7 +3694,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 		/* FUA is masked off if unsupported and can't be the reason */
-		btrfs_std_error(root->fs_info, -EIO,
+		btrfs_handle_fs_error(root->fs_info, -EIO,
 			    "%d errors while writing supers", total_errors);
 		return -EIO;
 	}
@@ -3704,7 +3712,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 	}
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 	if (total_errors > max_errors) {
-		btrfs_std_error(root->fs_info, -EIO,
+		btrfs_handle_fs_error(root->fs_info, -EIO,
 			    "%d errors while writing supers", total_errors);
 		return -EIO;
 	}
@@ -4120,6 +4128,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
 	 */
+	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+		btrfs_err(fs_info, "bytes_used is too small %llu",
+		       btrfs_super_bytes_used(sb));
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+		btrfs_err(fs_info, "invalid stripesize %u",
+		       btrfs_super_stripesize(sb));
+		ret = -EINVAL;
+	}
 	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
 				btrfs_super_num_devices(sb));
@@ -4357,7 +4375,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 		if (ret)
 			break;
 
-		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+		clear_extent_bits(dirty_pages, start, end, mark);
 		while (start <= end) {
 			eb = btrfs_find_tree_block(root->fs_info, start);
 			start += root->nodesize;
@@ -4392,7 +4410,7 @@ again:
 		if (ret)
 			break;
 
-		clear_extent_dirty(unpin, start, end, GFP_NOFS);
+		clear_extent_dirty(unpin, start, end);
 		btrfs_error_unpin_extent_range(root, start, end);
 		cond_resched();
 	}
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8e79d0070..acba82149 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -90,7 +90,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 void btrfs_free_fs_root(struct btrfs_root *root);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-struct btrfs_root *btrfs_alloc_dummy_root(void);
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize);
 #endif
 
 /*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 78f1b57d0..82b912a29 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -231,9 +231,9 @@ static int add_excluded_extent(struct btrfs_root *root,
 {
 	u64 end = start + num_bytes - 1;
 	set_extent_bits(&root->fs_info->freed_extents[0],
-			start, end, EXTENT_UPTODATE, GFP_NOFS);
+			start, end, EXTENT_UPTODATE);
 	set_extent_bits(&root->fs_info->freed_extents[1],
-			start, end, EXTENT_UPTODATE, GFP_NOFS);
+			start, end, EXTENT_UPTODATE);
 	return 0;
 }
 
@@ -246,9 +246,9 @@ static void free_excluded_extents(struct btrfs_root *root,
 	end = start + cache->key.offset - 1;
 
 	clear_extent_bits(&root->fs_info->freed_extents[0],
-			  start, end, EXTENT_UPTODATE, GFP_NOFS);
+			  start, end, EXTENT_UPTODATE);
 	clear_extent_bits(&root->fs_info->freed_extents[1],
-			  start, end, EXTENT_UPTODATE, GFP_NOFS);
+			  start, end, EXTENT_UPTODATE);
 }
 
 static int exclude_super_stripes(struct btrfs_root *root,
@@ -980,7 +980,7 @@ out_free:
  * event that tree block loses its owner tree's reference and do the
  * back refs conversion.
  *
- * When a tree block is COW'd through a tree, there are four cases:
+ * When a tree block is COWed through a tree, there are four cases:
  *
  * The reference count of the block is one and the tree is the block's
  * owner tree. Nothing to do in this case.
@@ -2042,6 +2042,11 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	struct btrfs_bio *bbio = NULL;
 
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are discarding.
+	 */
+	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
 	ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
@@ -2074,6 +2079,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 		}
 		btrfs_put_bbio(bbio);
 	}
+	btrfs_bio_counter_dec(root->fs_info);
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
@@ -2595,7 +2601,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			}
 
 			/*
-			 * Need to drop our head ref lock and re-aqcuire the
+			 * Need to drop our head ref lock and re-acquire the
 			 * delayed ref lock and then re-check to make sure
 			 * nobody got added.
 			 */
@@ -2747,7 +2753,7 @@ static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads)
 
 	/*
 	 * We don't ever fill up leaves all the way so multiply by 2 just to be
-	 * closer to what we're really going to want to ouse.
+	 * closer to what we're really going to want to use.
 	 */
 	return div_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root));
 }
@@ -2829,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 
 struct async_delayed_refs {
 	struct btrfs_root *root;
+	u64 transid;
 	int count;
 	int error;
 	int sync;
@@ -2844,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 
 	async = container_of(work, struct async_delayed_refs, work);
 
+	/* if the commit is already started, we don't need to wait here */
+	if (btrfs_transaction_blocked(async->root->fs_info))
+		goto done;
+
 	trans = btrfs_join_transaction(async->root);
 	if (IS_ERR(trans)) {
 		async->error = PTR_ERR(trans);
@@ -2851,14 +2862,19 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 	}
 
 	/*
-	 * trans->sync means that when we call end_transaciton, we won't
+	 * trans->sync means that when we call end_transaction, we won't
 	 * wait on delayed refs
 	 */
 	trans->sync = true;
+
+	/* Don't bother flushing if we got into a different transaction */
+	if (trans->transid > async->transid)
+		goto end;
+
 	ret = btrfs_run_delayed_refs(trans, async->root, async->count);
 	if (ret)
 		async->error = ret;
-
+end:
 	ret = btrfs_end_transaction(trans, async->root);
 	if (ret && !async->error)
 		async->error = ret;
@@ -2870,7 +2886,7 @@ done:
 }
 
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait)
+				 unsigned long count, u64 transid, int wait)
 {
 	struct async_delayed_refs *async;
 	int ret;
@@ -2882,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 	async->root = root->fs_info->tree_root;
 	async->count = count;
 	async->error = 0;
+	async->transid = transid;
 	if (wait)
 		async->sync = 1;
 	else
@@ -3824,6 +3841,59 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
 	return readonly;
 }
 
+bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+	struct btrfs_block_group_cache *bg;
+	bool ret = true;
+
+	bg = btrfs_lookup_block_group(fs_info, bytenr);
+	if (!bg)
+		return false;
+
+	spin_lock(&bg->lock);
+	if (bg->ro)
+		ret = false;
+	else
+		atomic_inc(&bg->nocow_writers);
+	spin_unlock(&bg->lock);
+
+	/* no put on block group, done by btrfs_dec_nocow_writers */
+	if (!ret)
+		btrfs_put_block_group(bg);
+
+	return ret;
+
+}
+
+void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+	struct btrfs_block_group_cache *bg;
+
+	bg = btrfs_lookup_block_group(fs_info, bytenr);
+	ASSERT(bg);
+	if (atomic_dec_and_test(&bg->nocow_writers))
+		wake_up_atomic_t(&bg->nocow_writers);
+	/*
+	 * Once for our lookup and once for the lookup done by a previous call
+	 * to btrfs_inc_nocow_writers()
+	 */
+	btrfs_put_block_group(bg);
+	btrfs_put_block_group(bg);
+}
+
+static int btrfs_wait_nocow_writers_atomic_t(atomic_t *a)
+{
+	schedule();
+	return 0;
+}
+
+void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+{
+	wait_on_atomic_t(&bg->nocow_writers,
+			 btrfs_wait_nocow_writers_atomic_t,
+			 TASK_UNINTERRUPTIBLE);
+}
+
 static const char *alloc_name(u64 flags)
 {
 	switch (flags) {
@@ -4141,7 +4211,7 @@ commit_trans:
 
 			if (need_commit > 0) {
 				btrfs_start_delalloc_roots(fs_info, 0, -1);
-				btrfs_wait_ordered_roots(fs_info, -1);
+				btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
 			}
 
 			trans = btrfs_join_transaction(root);
@@ -4243,7 +4313,7 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
  * Called if we need to clear a data reservation for this inode
  * Normally in a error case.
  *
- * This one will handle the per-indoe data rsv map for accurate reserved
+ * This one will handle the per-inode data rsv map for accurate reserved
  * space framework.
  */
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
@@ -4583,7 +4653,8 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root,
 		 */
 		btrfs_start_delalloc_roots(root->fs_info, 0, nr_items);
 		if (!current->journal_info)
-			btrfs_wait_ordered_roots(root->fs_info, nr_items);
+			btrfs_wait_ordered_roots(root->fs_info, nr_items,
+						 0, (u64)-1);
 	}
 }
 
@@ -4620,7 +4691,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 
 	/* Calc the number of the pages we need flush for space reservation */
 	items = calc_reclaim_items_nr(root, to_reclaim);
-	to_reclaim = items * EXTENT_SIZE_PER_ITEM;
+	to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM;
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 	block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -4632,7 +4703,8 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
 		if (trans)
 			return;
 		if (wait_ordered)
-			btrfs_wait_ordered_roots(root->fs_info, items);
+			btrfs_wait_ordered_roots(root->fs_info, items,
+						 0, (u64)-1);
 		return;
 	}
 
@@ -4671,7 +4743,8 @@ skip_async:
 
 		loops++;
 		if (wait_ordered && !trans) {
-			btrfs_wait_ordered_roots(root->fs_info, items);
+			btrfs_wait_ordered_roots(root->fs_info, items,
+						 0, (u64)-1);
 		} else {
 			time_left = schedule_timeout_killable(1);
 			if (time_left)
@@ -4911,7 +4984,7 @@ void btrfs_init_async_reclaim_work(struct work_struct *work)
  * @orig_bytes - the number of bytes we want
  * @flush - whether or not we can flush to make our reservation
  *
- * This will reserve orgi_bytes number of bytes from the space info associated
+ * This will reserve orig_bytes number of bytes from the space info associated
  * with the block_rsv.  If there is not enough space it will make an attempt to
  * flush out space to make room.  It will do this by flushing delalloc if
  * possible or committing the transaction.  If flush is 0 then no attempts to
@@ -5516,7 +5589,7 @@ void btrfs_orphan_release_metadata(struct inode *inode)
  * common file/directory operations, they change two fs/file trees
  * and root tree, the number of items that the qgroup reserves is
  * different with the free space reservation. So we can not use
- * the space reseravtion mechanism in start_transaction().
+ * the space reservation mechanism in start_transaction().
  */
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
@@ -5565,7 +5638,7 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 /**
  * drop_outstanding_extent - drop an outstanding extent
  * @inode: the inode we're dropping the extent for
- * @num_bytes: the number of bytes we're relaseing.
+ * @num_bytes: the number of bytes we're releasing.
  *
  * This is called when we are freeing up an outstanding extent, either called
  * after an error or after an extent is written.  This will return the number of
@@ -5591,7 +5664,7 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
 		drop_inode_space = 1;
 
 	/*
-	 * If we have more or the same amount of outsanding extents than we have
+	 * If we have more or the same amount of outstanding extents than we have
 	 * reserved then we need to leave the reserved extents count alone.
 	 */
 	if (BTRFS_I(inode)->outstanding_extents >=
@@ -5605,8 +5678,8 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
 }
 
 /**
- * calc_csum_metadata_size - return the amount of metada space that must be
- *	reserved/free'd for the given bytes.
+ * calc_csum_metadata_size - return the amount of metadata space that must be
+ *	reserved/freed for the given bytes.
  * @inode: the inode we're manipulating
  * @num_bytes: the number of bytes in question
  * @reserve: 1 if we are reserving space, 0 if we are freeing space
@@ -5758,7 +5831,7 @@ out_fail:
 
 		/*
 		 * This is tricky, but first we need to figure out how much we
-		 * free'd from any free-ers that occurred during this
+		 * freed from any free-ers that occurred during this
 		 * reservation, so we reset ->csum_bytes to the csum_bytes
 		 * before we dropped our lock, and then call the free for the
 		 * number of bytes that were freed while we were trying our
@@ -5780,7 +5853,7 @@ out_fail:
 
 		/*
 		 * Now reset ->csum_bytes to what it should be.  If bytes is
-		 * more than to_free then we would have free'd more space had we
+		 * more than to_free then we would have freed more space had we
 		 * not had an artificially high ->csum_bytes, so we need to free
 		 * the remainder.  If bytes is the same or less then we don't
 		 * need to do anything, the other free-ers did the correct
@@ -6172,6 +6245,57 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log,
 	return 0;
 }
 
+static void
+btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+{
+	atomic_inc(&bg->reservations);
+}
+
+void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+					const u64 start)
+{
+	struct btrfs_block_group_cache *bg;
+
+	bg = btrfs_lookup_block_group(fs_info, start);
+	ASSERT(bg);
+	if (atomic_dec_and_test(&bg->reservations))
+		wake_up_atomic_t(&bg->reservations);
+	btrfs_put_block_group(bg);
+}
+
+static int btrfs_wait_bg_reservations_atomic_t(atomic_t *a)
+{
+	schedule();
+	return 0;
+}
+
+void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+{
+	struct btrfs_space_info *space_info = bg->space_info;
+
+	ASSERT(bg->ro);
+
+	if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA))
+		return;
+
+	/*
+	 * Our block group is read only but before we set it to read only,
+	 * some task might have had allocated an extent from it already, but it
+	 * has not yet created a respective ordered extent (and added it to a
+	 * root's list of ordered extents).
+	 * Therefore wait for any task currently allocating extents, since the
+	 * block group's reservations counter is incremented while a read lock
+	 * on the groups' semaphore is held and decremented after releasing
+	 * the read access on that semaphore and creating the ordered extent.
+	 */
+	down_write(&space_info->groups_sem);
+	up_write(&space_info->groups_sem);
+
+	wait_on_atomic_t(&bg->reservations,
+			 btrfs_wait_bg_reservations_atomic_t,
+			 TASK_UNINTERRUPTIBLE);
+}
+
 /**
  * btrfs_update_reserved_bytes - update the block_group and space info counters
  * @cache:	The cache we are manipulating
@@ -6408,7 +6532,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 			ret = btrfs_discard_extent(root, start,
 						   end + 1 - start, NULL);
 
-		clear_extent_dirty(unpin, start, end, GFP_NOFS);
+		clear_extent_dirty(unpin, start, end);
 		unpin_extent_range(root, start, end, true);
 		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 		cond_resched();
@@ -7025,36 +7149,35 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
 		   int delalloc)
 {
 	struct btrfs_block_group_cache *used_bg = NULL;
-	bool locked = false;
-again:
+
 	spin_lock(&cluster->refill_lock);
-	if (locked) {
-		if (used_bg == cluster->block_group)
+	while (1) {
+		used_bg = cluster->block_group;
+		if (!used_bg)
+			return NULL;
+
+		if (used_bg == block_group)
 			return used_bg;
 
-		up_read(&used_bg->data_rwsem);
-		btrfs_put_block_group(used_bg);
-	}
+		btrfs_get_block_group(used_bg);
 
-	used_bg = cluster->block_group;
-	if (!used_bg)
-		return NULL;
+		if (!delalloc)
+			return used_bg;
 
-	if (used_bg == block_group)
-		return used_bg;
+		if (down_read_trylock(&used_bg->data_rwsem))
+			return used_bg;
 
-	btrfs_get_block_group(used_bg);
+		spin_unlock(&cluster->refill_lock);
 
-	if (!delalloc)
-		return used_bg;
+		down_read(&used_bg->data_rwsem);
 
-	if (down_read_trylock(&used_bg->data_rwsem))
-		return used_bg;
+		spin_lock(&cluster->refill_lock);
+		if (used_bg == cluster->block_group)
+			return used_bg;
 
-	spin_unlock(&cluster->refill_lock);
-	down_read(&used_bg->data_rwsem);
-	locked = true;
-	goto again;
+		up_read(&used_bg->data_rwsem);
+		btrfs_put_block_group(used_bg);
+	}
 }
 
 static inline void
@@ -7431,6 +7554,7 @@ checks:
 			btrfs_add_free_space(block_group, offset, num_bytes);
 			goto loop;
 		}
+		btrfs_inc_block_group_reservations(block_group);
 
 		/* we are all good, lets return */
 		ins->objectid = search_start;
@@ -7471,7 +7595,7 @@ loop:
 		if (loop == LOOP_CACHING_NOWAIT) {
 			/*
 			 * We want to skip the LOOP_CACHING_WAIT step if we
-			 * don't have any unached bgs and we've alrelady done a
+			 * don't have any uncached bgs and we've already done a
 			 * full search through.
 			 */
 			if (orig_have_caching_bg || !full_search)
@@ -7612,8 +7736,10 @@ again:
 	WARN_ON(num_bytes < root->sectorsize);
 	ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
 			       flags, delalloc);
-
-	if (ret == -ENOSPC) {
+	if (!ret && !is_data) {
+		btrfs_dec_block_group_reservations(root->fs_info,
+						   ins->objectid);
+	} else if (ret == -ENOSPC) {
 		if (!final_tried && ins->offset) {
 			num_bytes = min(num_bytes >> 1, ins->offset);
 			num_bytes = round_down(num_bytes, root->sectorsize);
@@ -7873,7 +7999,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 
 	/*
 	 * Mixed block groups will exclude before processing the log so we only
-	 * need to do the exlude dance if this fs isn't mixed.
+	 * need to do the exclude dance if this fs isn't mixed.
 	 */
 	if (!btrfs_fs_incompat(root->fs_info, MIXED_GROUPS)) {
 		ret = __exclude_logged_extent(root, ins->objectid, ins->offset);
@@ -7901,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	struct extent_buffer *buf;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -7923,7 +8050,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 					buf->start + buf->len - 1, GFP_NOFS);
 		else
 			set_extent_new(&root->dirty_log_pages, buf->start,
-					buf->start + buf->len - 1, GFP_NOFS);
+					buf->start + buf->len - 1);
 	} else {
 		buf->log_index = -1;
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
@@ -8544,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	next = btrfs_find_tree_block(root->fs_info, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr);
-		if (!next)
-			return -ENOMEM;
+		if (IS_ERR(next))
+			return PTR_ERR(next);
+
 		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
 					       level - 1);
 		reada = 1;
@@ -9058,7 +9186,7 @@ out:
 	if (!for_reloc && root_dropped == false)
 		btrfs_add_dead_root(root);
 	if (err && err != -EAGAIN)
-		btrfs_std_error(root->fs_info, err, NULL);
+		btrfs_handle_fs_error(root->fs_info, err, NULL);
 	return err;
 }
 
@@ -9317,7 +9445,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 	u64 free_bytes = 0;
 	int factor;
 
-	/* It's df, we don't care if it's racey */
+	/* It's df, we don't care if it's racy */
 	if (list_empty(&sinfo->ro_bgs))
 		return 0;
 
@@ -10526,14 +10654,14 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 */
 		mutex_lock(&fs_info->unused_bg_unpin_mutex);
 		ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
-				  EXTENT_DIRTY, GFP_NOFS);
+				  EXTENT_DIRTY);
 		if (ret) {
 			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			btrfs_dec_block_group_ro(root, block_group);
 			goto end_trans;
 		}
 		ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
-				  EXTENT_DIRTY, GFP_NOFS);
+				  EXTENT_DIRTY);
 		if (ret) {
 			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 			btrfs_dec_block_group_ro(root, block_group);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d247fc0ee..75533adef 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -726,14 +726,6 @@ next:
 	start = last_end + 1;
 	if (start <= end && state && !need_resched())
 		goto hit_next;
-	goto search_again;
-
-out:
-	spin_unlock(&tree->lock);
-	if (prealloc)
-		free_extent_state(prealloc);
-
-	return 0;
 
 search_again:
 	if (start > end)
@@ -742,6 +734,14 @@ search_again:
 	if (gfpflags_allow_blocking(mask))
 		cond_resched();
 	goto again;
+
+out:
+	spin_unlock(&tree->lock);
+	if (prealloc)
+		free_extent_state(prealloc);
+
+	return 0;
+
 }
 
 static void wait_on_state(struct extent_io_tree *tree,
@@ -873,8 +873,14 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	bits |= EXTENT_FIRST_DELALLOC;
 again:
 	if (!prealloc && gfpflags_allow_blocking(mask)) {
+		/*
+		 * Don't care for allocation failure here because we might end
+		 * up not needing the pre-allocated extent state at all, which
+		 * is the case if we only have in the tree extent states that
+		 * cover our input range and don't cover too any other range.
+		 * If we end up needing a new extent state we allocate it later.
+		 */
 		prealloc = alloc_extent_state(mask);
-		BUG_ON(!prealloc);
 	}
 
 	spin_lock(&tree->lock);
@@ -1037,7 +1043,13 @@ hit_next:
 		goto out;
 	}
 
-	goto search_again;
+search_again:
+	if (start > end)
+		goto out;
+	spin_unlock(&tree->lock);
+	if (gfpflags_allow_blocking(mask))
+		cond_resched();
+	goto again;
 
 out:
 	spin_unlock(&tree->lock);
@@ -1046,13 +1058,6 @@ out:
 
 	return err;
 
-search_again:
-	if (start > end)
-		goto out;
-	spin_unlock(&tree->lock);
-	if (gfpflags_allow_blocking(mask))
-		cond_resched();
-	goto again;
 }
 
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1073,17 +1078,18 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
  * @bits:	the bits to set in this range
  * @clear_bits:	the bits to clear in this range
  * @cached_state:	state that we're going to cache
- * @mask:	the allocation mask
  *
  * This will go through and set bits for the given range.  If any states exist
  * already in this range they are set with the given bit and cleared of the
  * clear_bits.  This is only meant to be used by things that are mergeable, ie
  * converting from say DELALLOC to DIRTY.  This is not meant to be used with
  * boundary bits like LOCK.
+ *
+ * All allocations are done with GFP_NOFS.
  */
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       unsigned bits, unsigned clear_bits,
-		       struct extent_state **cached_state, gfp_t mask)
+		       struct extent_state **cached_state)
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
@@ -1098,7 +1104,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	btrfs_debug_check_extent_io_range(tree, start, end);
 
 again:
-	if (!prealloc && gfpflags_allow_blocking(mask)) {
+	if (!prealloc) {
 		/*
 		 * Best effort, don't worry if extent state allocation fails
 		 * here for the first iteration. We might have a cached state
@@ -1106,7 +1112,7 @@ again:
 		 * extent state allocations are needed. We'll only know this
 		 * after locking the tree.
 		 */
-		prealloc = alloc_extent_state(mask);
+		prealloc = alloc_extent_state(GFP_NOFS);
 		if (!prealloc && !first_iteration)
 			return -ENOMEM;
 	}
@@ -1263,7 +1269,13 @@ hit_next:
 		goto out;
 	}
 
-	goto search_again;
+search_again:
+	if (start > end)
+		goto out;
+	spin_unlock(&tree->lock);
+	cond_resched();
+	first_iteration = false;
+	goto again;
 
 out:
 	spin_unlock(&tree->lock);
@@ -1271,21 +1283,11 @@ out:
 		free_extent_state(prealloc);
 
 	return err;
-
-search_again:
-	if (start > end)
-		goto out;
-	spin_unlock(&tree->lock);
-	if (gfpflags_allow_blocking(mask))
-		cond_resched();
-	first_iteration = false;
-	goto again;
 }
 
 /* wrappers around set/clear extent bit */
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits, gfp_t mask,
-			   struct extent_changeset *changeset)
+			   unsigned bits, struct extent_changeset *changeset)
 {
 	/*
 	 * We don't support EXTENT_LOCKED yet, as current changeset will
@@ -1295,7 +1297,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	BUG_ON(bits & EXTENT_LOCKED);
 
-	return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask,
+	return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
 				changeset);
 }
 
@@ -1308,8 +1310,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 }
 
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			     unsigned bits, gfp_t mask,
-			     struct extent_changeset *changeset)
+		unsigned bits, struct extent_changeset *changeset)
 {
 	/*
 	 * Don't support EXTENT_LOCKED case, same reason as
@@ -1317,7 +1318,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	BUG_ON(bits & EXTENT_LOCKED);
 
-	return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask,
+	return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, GFP_NOFS,
 				  changeset);
 }
 
@@ -1975,13 +1976,13 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 	set_state_failrec(failure_tree, rec->start, NULL);
 	ret = clear_extent_bits(failure_tree, rec->start,
 				rec->start + rec->len - 1,
-				EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+				EXTENT_LOCKED | EXTENT_DIRTY);
 	if (ret)
 		err = ret;
 
 	ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
 				rec->start + rec->len - 1,
-				EXTENT_DAMAGED, GFP_NOFS);
+				EXTENT_DAMAGED);
 	if (ret && !err)
 		err = ret;
 
@@ -2024,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_block(fs_info, WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2036,6 +2044,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	dev = bbio->stripes[mirror_num-1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2044,6 +2053,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 
 	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
@@ -2053,6 +2063,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
+	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
 	return 0;
 }
@@ -2232,13 +2243,12 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 
 		/* set the bits in the private failure tree */
 		ret = set_extent_bits(failure_tree, start, end,
-					EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+					EXTENT_LOCKED | EXTENT_DIRTY);
 		if (ret >= 0)
 			ret = set_state_failrec(failure_tree, start, failrec);
 		/* set the bits in the inode's tree */
 		if (ret >= 0)
-			ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED,
-						GFP_NOFS);
+			ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED);
 		if (ret < 0) {
 			kfree(failrec);
 			return ret;
@@ -3200,14 +3210,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-static noinline void update_nr_written(struct page *page,
-				      struct writeback_control *wbc,
-				      unsigned long nr_written)
+static void update_nr_written(struct page *page, struct writeback_control *wbc,
+			      unsigned long nr_written)
 {
 	wbc->nr_to_write -= nr_written;
-	if (wbc->range_cyclic || (wbc->nr_to_write > 0 &&
-	    wbc->range_start == 0 && wbc->range_end == LLONG_MAX))
-		page->mapping->writeback_index = page->index + nr_written;
 }
 
 /*
@@ -3368,6 +3374,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 	while (cur <= end) {
 		u64 em_end;
+		unsigned long max_nr;
+
 		if (cur >= i_size) {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
 				tree->ops->writepage_end_io_hook(page, cur,
@@ -3423,32 +3431,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			continue;
 		}
 
-		if (tree->ops && tree->ops->writepage_io_hook) {
-			ret = tree->ops->writepage_io_hook(page, cur,
-						cur + iosize - 1);
-		} else {
-			ret = 0;
+		max_nr = (i_size >> PAGE_SHIFT) + 1;
+
+		set_range_writeback(tree, cur, cur + iosize - 1);
+		if (!PageWriteback(page)) {
+			btrfs_err(BTRFS_I(inode)->root->fs_info,
+				   "page %lu not writeback, cur %llu end %llu",
+			       page->index, cur, end);
 		}
-		if (ret) {
-			SetPageError(page);
-		} else {
-			unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1;
 
-			set_range_writeback(tree, cur, cur + iosize - 1);
-			if (!PageWriteback(page)) {
-				btrfs_err(BTRFS_I(inode)->root->fs_info,
-					   "page %lu not writeback, cur %llu end %llu",
-				       page->index, cur, end);
-			}
+		ret = submit_extent_page(write_flags, tree, wbc, page,
+					 sector, iosize, pg_offset,
+					 bdev, &epd->bio, max_nr,
+					 end_bio_extent_writepage,
+					 0, 0, 0, false);
+		if (ret)
+			SetPageError(page);
 
-			ret = submit_extent_page(write_flags, tree, wbc, page,
-						 sector, iosize, pg_offset,
-						 bdev, &epd->bio, max_nr,
-						 end_bio_extent_writepage,
-						 0, 0, 0, false);
-			if (ret)
-				SetPageError(page);
-		}
 		cur = cur + iosize;
 		pg_offset += iosize;
 		nr++;
@@ -3920,12 +3919,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 	struct inode *inode = mapping->host;
 	int ret = 0;
 	int done = 0;
-	int err = 0;
 	int nr_to_write_done = 0;
 	struct pagevec pvec;
 	int nr_pages;
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
+	pgoff_t done_index;
+	int range_whole = 0;
 	int scanned = 0;
 	int tag;
 
@@ -3948,6 +3948,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 	} else {
 		index = wbc->range_start >> PAGE_SHIFT;
 		end = wbc->range_end >> PAGE_SHIFT;
+		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+			range_whole = 1;
 		scanned = 1;
 	}
 	if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3957,6 +3959,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 retry:
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		tag_pages_for_writeback(mapping, index, end);
+	done_index = index;
 	while (!done && !nr_to_write_done && (index <= end) &&
 	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
@@ -3966,6 +3969,7 @@ retry:
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
+			done_index = page->index;
 			/*
 			 * At this point we hold neither mapping->tree_lock nor
 			 * lock on the page itself: the page may be truncated or
@@ -4007,8 +4011,20 @@ retry:
 				unlock_page(page);
 				ret = 0;
 			}
-			if (!err && ret < 0)
-				err = ret;
+			if (ret < 0) {
+				/*
+				 * done_index is set past this page,
+				 * so media errors will not choke
+				 * background writeout for the entire
+				 * file. This has consequences for
+				 * range_cyclic semantics (ie. it may
+				 * not be suitable for data integrity
+				 * writeout).
+				 */
+				done_index = page->index + 1;
+				done = 1;
+				break;
+			}
 
 			/*
 			 * the filesystem may choose to bump up nr_to_write.
@@ -4020,7 +4036,7 @@ retry:
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!scanned && !done && !err) {
+	if (!scanned && !done) {
 		/*
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
@@ -4029,8 +4045,12 @@ retry:
 		index = 0;
 		goto retry;
 	}
+
+	if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
+		mapping->writeback_index = done_index;
+
 	btrfs_add_delayed_iput(inode);
-	return err;
+	return ret;
 }
 
 static void flush_epd_write_bio(struct extent_page_data *epd)
@@ -4379,8 +4399,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
+	} else {
+		WARN_ON(!ret);
+		if (ret == 1)
+			ret = 0;
 	}
-	WARN_ON(!ret);
+
 	path->slots[0]--;
 	btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
 	found_type = found_key.type;
@@ -4591,7 +4615,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 		if (mapped)
 			spin_unlock(&page->mapping->private_lock);
 
-		/* One for when we alloced the page */
+		/* One for when we allocated the page */
 		put_page(page);
 	} while (index != 0);
 }
@@ -4704,16 +4728,16 @@ err:
 }
 
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+						u64 start, u32 nodesize)
 {
 	unsigned long len;
 
 	if (!fs_info) {
 		/*
 		 * Called only from tests that don't always have a fs_info
-		 * available, but we know that nodesize is 4096
+		 * available
 		 */
-		len = 4096;
+		len = nodesize;
 	} else {
 		len = fs_info->tree_root->nodesize;
 	}
@@ -4809,7 +4833,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start)
+					u64 start, u32 nodesize)
 {
 	struct extent_buffer *eb, *exists = NULL;
 	int ret;
@@ -4817,12 +4841,12 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
-	eb = alloc_dummy_extent_buffer(fs_info, start);
+	eb = alloc_dummy_extent_buffer(fs_info, start, nodesize);
 	if (!eb)
 		return NULL;
 	eb->fs_info = fs_info;
 again:
-	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+	ret = radix_tree_preload(GFP_NOFS);
 	if (ret)
 		goto free_eb;
 	spin_lock(&fs_info->buffer_lock);
@@ -4868,18 +4892,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	int uptodate = 1;
 	int ret;
 
+	if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+		btrfs_err(fs_info, "bad tree block start %llu", start);
+		return ERR_PTR(-EINVAL);
+	}
+
 	eb = find_extent_buffer(fs_info, start);
 	if (eb)
 		return eb;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
-		if (!p)
+		if (!p) {
+			exists = ERR_PTR(-ENOMEM);
 			goto free_eb;
+		}
 
 		spin_lock(&mapping->private_lock);
 		if (PagePrivate(p)) {
@@ -4923,9 +4954,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (uptodate)
 		set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 again:
-	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
-	if (ret)
+	ret = radix_tree_preload(GFP_NOFS);
+	if (ret) {
+		exists = ERR_PTR(ret);
 		goto free_eb;
+	}
 
 	spin_lock(&fs_info->buffer_lock);
 	ret = radix_tree_insert(&fs_info->buffer_radix,
@@ -5309,6 +5342,11 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
 	return ret;
 }
 
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
 int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 			       unsigned long min_len, char **map,
 			       unsigned long *map_start,
@@ -5323,7 +5361,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		PAGE_SHIFT;
 
 	if (i != end_i)
-		return -EINVAL;
+		return 1;
 
 	if (i == 0) {
 		offset = start_offset;
@@ -5751,7 +5789,7 @@ int try_release_extent_buffer(struct page *page)
 	struct extent_buffer *eb;
 
 	/*
-	 * We need to make sure noboody is attaching this page to an eb right
+	 * We need to make sure nobody is attaching this page to an eb right
 	 * now.
 	 */
 	spin_lock(&page->mapping->private_lock);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b5e0ade90..c0c1c4fef 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -71,7 +71,6 @@ struct extent_io_ops {
 			     u64 start, u64 end, int *page_started,
 			     unsigned long *nr_written);
 	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
-	int (*writepage_io_hook)(struct page *page, u64 start, u64 end);
 	extent_submit_bio_hook_t *submit_bio_hook;
 	int (*merge_bio_hook)(int rw, struct page *page, unsigned long offset,
 			      size_t size, struct bio *bio,
@@ -221,8 +220,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   unsigned bits, int filled,
 		   struct extent_state *cached_state);
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			     unsigned bits, gfp_t mask,
-			     struct extent_changeset *changeset);
+		unsigned bits, struct extent_changeset *changeset);
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		     unsigned bits, int wake, int delete,
 		     struct extent_state **cached, gfp_t mask);
@@ -241,27 +239,27 @@ static inline int unlock_extent_cached(struct extent_io_tree *tree, u64 start,
 }
 
 static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits, gfp_t mask)
+		u64 end, unsigned bits)
 {
 	int wake = 0;
 
 	if (bits & EXTENT_LOCKED)
 		wake = 1;
 
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
+	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL,
+			GFP_NOFS);
 }
 
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits, gfp_t mask,
-			   struct extent_changeset *changeset);
+			   unsigned bits, struct extent_changeset *changeset);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		   unsigned bits, u64 *failed_start,
 		   struct extent_state **cached_state, gfp_t mask);
 
 static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits, gfp_t mask)
+		u64 end, unsigned bits)
 {
-	return set_extent_bit(tree, start, end, bits, NULL, NULL, mask);
+	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
 }
 
 static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -279,37 +277,38 @@ static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
 }
 
 static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
-		u64 end, gfp_t mask)
+		u64 end)
 {
 	return clear_extent_bit(tree, start, end,
 				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, NULL, mask);
+				EXTENT_DO_ACCOUNTING, 0, 0, NULL, GFP_NOFS);
 }
 
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       unsigned bits, unsigned clear_bits,
-		       struct extent_state **cached_state, gfp_t mask);
+		       struct extent_state **cached_state);
 
 static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state, gfp_t mask)
+		u64 end, struct extent_state **cached_state)
 {
 	return set_extent_bit(tree, start, end,
 			      EXTENT_DELALLOC | EXTENT_UPTODATE,
-			      NULL, cached_state, mask);
+			      NULL, cached_state, GFP_NOFS);
 }
 
 static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
-		u64 end, struct extent_state **cached_state, gfp_t mask)
+		u64 end, struct extent_state **cached_state)
 {
 	return set_extent_bit(tree, start, end,
 			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, mask);
+			      NULL, cached_state, GFP_NOFS);
 }
 
 static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
-		u64 end, gfp_t mask)
+		u64 end)
 {
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL, mask);
+	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+			GFP_NOFS);
 }
 
 static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -349,7 +348,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len);
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start);
+						u64 start, u32 nodesize);
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 					 u64 start);
@@ -469,5 +468,5 @@ noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      u64 *end, u64 max_bytes);
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
-					       u64 start);
+					       u64 start, u32 nodesize);
 #endif
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 318b048eb..e0715fcfb 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -62,7 +62,7 @@ struct extent_map *alloc_extent_map(void)
 
 /**
  * free_extent_map - drop reference count of an extent_map
- * @em:		extent map being releasead
+ * @em:		extent map being released
  *
  * Drops the reference out on @em by one and free the structure
  * if the reference count hits zero.
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 7a7d6e253..62a81ee13 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -248,7 +248,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 					set_extent_bits(io_tree, offset,
 						offset + root->sectorsize - 1,
-						EXTENT_NODATASUM, GFP_NOFS);
+						EXTENT_NODATASUM);
 				} else {
 					btrfs_info(BTRFS_I(inode)->root->fs_info,
 						   "no csum found for inode %llu start %llu",
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index af5c7fa22..2234e88cf 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1534,30 +1534,30 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				root->sectorsize);
 
-		if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-					      BTRFS_INODE_PREALLOC)) &&
-		    check_can_nocow(inode, pos, &write_bytes) > 0) {
-			/*
-			 * For nodata cow case, no need to reserve
-			 * data space.
-			 */
-			only_release_metadata = true;
-			/*
-			 * our prealloc extent may be smaller than
-			 * write_bytes, so scale down.
-			 */
-			num_pages = DIV_ROUND_UP(write_bytes + offset,
-						 PAGE_SIZE);
-			reserve_bytes = round_up(write_bytes + sector_offset,
-					root->sectorsize);
-			goto reserve_metadata;
-		}
-
 		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
-		if (ret < 0)
-			break;
+		if (ret < 0) {
+			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+						      BTRFS_INODE_PREALLOC)) &&
+			    check_can_nocow(inode, pos, &write_bytes) > 0) {
+				/*
+				 * For nodata cow case, no need to reserve
+				 * data space.
+				 */
+				only_release_metadata = true;
+				/*
+				 * our prealloc extent may be smaller than
+				 * write_bytes, so scale down.
+				 */
+				num_pages = DIV_ROUND_UP(write_bytes + offset,
+							 PAGE_SIZE);
+				reserve_bytes = round_up(write_bytes +
+							 sector_offset,
+							 root->sectorsize);
+			} else {
+				break;
+			}
+		}
 
-reserve_metadata:
 		ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
@@ -1703,25 +1703,26 @@ again:
 			btrfs_end_write_no_snapshoting(root);
 			btrfs_delalloc_release_metadata(inode, release_bytes);
 		} else {
-			btrfs_delalloc_release_space(inode, pos, release_bytes);
+			btrfs_delalloc_release_space(inode,
+						round_down(pos, root->sectorsize),
+						release_bytes);
 		}
 	}
 
 	return num_written ? num_written : ret;
 }
 
-static ssize_t __btrfs_direct_write(struct kiocb *iocb,
-				    struct iov_iter *from,
-				    loff_t pos)
+static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	loff_t pos = iocb->ki_pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, from, pos);
+	written = generic_file_direct_write(iocb, from);
 
 	if (written < 0 || !iov_iter_count(from))
 		return written;
@@ -1839,7 +1840,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
 	if (iocb->ki_flags & IOCB_DIRECT) {
-		num_written = __btrfs_direct_write(iocb, from, pos);
+		num_written = __btrfs_direct_write(iocb, from);
 	} else {
 		num_written = __btrfs_buffered_write(file, from, pos);
 		if (num_written > 0)
@@ -1859,11 +1860,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
 	spin_unlock(&BTRFS_I(inode)->lock);
-	if (num_written > 0) {
-		err = generic_write_sync(file, pos, num_written);
-		if (err < 0)
-			num_written = err;
-	}
+	if (num_written > 0)
+		num_written = generic_write_sync(iocb, num_written);
 
 	if (sync)
 		atomic_dec(&BTRFS_I(inode)->sync_writers);
@@ -2031,7 +2029,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	     BTRFS_I(inode)->last_trans
 	     <= root->fs_info->last_trans_committed)) {
 		/*
-		 * We'v had everything committed since the last time we were
+		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
 		 * reason, it's no longer relevant.
 		 */
@@ -2379,7 +2377,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 	/* Check the aligned pages after the first unaligned page,
 	 * if offset != orig_start, which means the first unaligned page
-	 * including serveral following pages are already in holes,
+	 * including several following pages are already in holes,
 	 * the extra check can be skipped */
 	if (offset == orig_start) {
 		/* after truncate page, check hole again */
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 5e6062c26..69d270f66 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -29,7 +29,7 @@
 #include "inode-map.h"
 #include "volumes.h"
 
-#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8UL)
 #define MAX_CACHE_BYTES_PER_GIG	SZ_32K
 
 struct btrfs_trim_range {
@@ -1415,11 +1415,11 @@ static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl,
 				   u64 offset)
 {
 	u64 bitmap_start;
-	u32 bytes_per_bitmap;
+	u64 bytes_per_bitmap;
 
 	bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit;
 	bitmap_start = offset - ctl->start;
-	bitmap_start = div_u64(bitmap_start, bytes_per_bitmap);
+	bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap);
 	bitmap_start *= bytes_per_bitmap;
 	bitmap_start += ctl->start;
 
@@ -1638,10 +1638,10 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	u64 bitmap_bytes;
 	u64 extent_bytes;
 	u64 size = block_group->key.offset;
-	u32 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
-	u32 max_bitmaps = div_u64(size + bytes_per_bg - 1, bytes_per_bg);
+	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
+	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
 
-	max_bitmaps = max_t(u32, max_bitmaps, 1);
+	max_bitmaps = max_t(u64, max_bitmaps, 1);
 
 	ASSERT(ctl->total_bitmaps <= max_bitmaps);
 
@@ -1660,7 +1660,7 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
 	 * sure we don't go over our overall goal of MAX_CACHE_BYTES_PER_GIG as
 	 * we add more bitmaps.
 	 */
-	bitmap_bytes = (ctl->total_bitmaps + 1) * PAGE_SIZE;
+	bitmap_bytes = (ctl->total_bitmaps + 1) * ctl->unit;
 
 	if (bitmap_bytes >= max_bytes) {
 		ctl->extents_thresh = 0;
@@ -1983,7 +1983,7 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 		/*
 		 * 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
+		 * to reserve them to larger extents, however if we have plenty
 		 * of cache left then go ahead an dadd them, no sense in adding
 		 * the overhead of a bitmap if we don't have to.
 		 */
@@ -3662,7 +3662,7 @@ have_info:
 			if (tmp->offset + tmp->bytes < offset)
 				break;
 			if (offset + bytes < tmp->offset) {
-				n = rb_prev(&info->offset_index);
+				n = rb_prev(&tmp->offset_index);
 				continue;
 			}
 			info = tmp;
@@ -3676,7 +3676,7 @@ have_info:
 			if (offset + bytes < tmp->offset)
 				break;
 			if (tmp->offset + tmp->bytes < offset) {
-				n = rb_next(&info->offset_index);
+				n = rb_next(&tmp->offset_index);
 				continue;
 			}
 			info = tmp;
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 33178c490..3af651c2b 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -123,7 +123,7 @@ int btrfs_return_cluster_to_free_space(
 int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
 			   u64 *trimmed, u64 start, u64 end, u64 minlen);
 
-/* Support functions for runnint our sanity tests */
+/* Support functions for running our sanity tests */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int test_add_free_space_entry(struct btrfs_block_group_cache *cache,
 			      u64 offset, u64 bytes, bool bitmap);
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
index aae520b2a..a97fdc156 100644
--- a/fs/btrfs/hash.c
+++ b/fs/btrfs/hash.c
@@ -24,6 +24,11 @@ int __init btrfs_hash_init(void)
 	return PTR_ERR_OR_ZERO(tfm);
 }
 
+const char* btrfs_crc32c_impl(void)
+{
+	return crypto_tfm_alg_driver_name(crypto_shash_tfm(tfm));
+}
+
 void btrfs_hash_exit(void)
 {
 	crypto_free_shash(tfm);
diff --git a/fs/btrfs/hash.h b/fs/btrfs/hash.h
index 118a2316e..c3a2ec554 100644
--- a/fs/btrfs/hash.h
+++ b/fs/btrfs/hash.h
@@ -22,6 +22,7 @@
 int __init btrfs_hash_init(void);
 
 void btrfs_hash_exit(void);
+const char* btrfs_crc32c_impl(void);
 
 u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length);
 
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index be4d22a50..b8acc07ac 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -157,7 +157,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
 	 */
 	if (!btrfs_find_name_in_ext_backref(path, ref_objectid,
 					    name, name_len, &extref)) {
-		btrfs_std_error(root->fs_info, -ENOENT, NULL);
+		btrfs_handle_fs_error(root->fs_info, -ENOENT, NULL);
 		ret = -EROFS;
 		goto out;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 167fc3d49..442195472 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -455,7 +455,7 @@ again:
 
 	/*
 	 * skip compression for a small file range(<=blocksize) that
-	 * isn't an inline extent, since it dosen't save disk space at all.
+	 * isn't an inline extent, since it doesn't save disk space at all.
 	 */
 	if (total_compressed <= blocksize &&
 	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
@@ -824,6 +824,7 @@ retry:
 						async_extent->ram_size - 1, 0);
 			goto out_free_reserve;
 		}
+		btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
 
 		/*
 		 * clear dirty, set writeback and unlock the pages.
@@ -861,6 +862,7 @@ retry:
 	}
 	return;
 out_free_reserve:
+	btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
 	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_free:
 	extent_clear_unlock_delalloc(inode, async_extent->start,
@@ -1038,6 +1040,8 @@ static noinline int cow_file_range(struct inode *inode,
 				goto out_drop_extent_cache;
 		}
 
+		btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
 		if (disk_num_bytes < cur_alloc_size)
 			break;
 
@@ -1066,6 +1070,7 @@ out:
 out_drop_extent_cache:
 	btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
 out_reserve:
+	btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
 	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
 out_unlock:
 	extent_clear_unlock_delalloc(inode, start, end, locked_page,
@@ -1377,6 +1382,9 @@ next_slot:
 			 */
 			if (csum_exist_in_range(root, disk_bytenr, num_bytes))
 				goto out_check;
+			if (!btrfs_inc_nocow_writers(root->fs_info,
+						     disk_bytenr))
+				goto out_check;
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
@@ -1391,6 +1399,9 @@ out_check:
 			path->slots[0]++;
 			if (!nolock && nocow)
 				btrfs_end_write_no_snapshoting(root);
+			if (nocow)
+				btrfs_dec_nocow_writers(root->fs_info,
+							disk_bytenr);
 			goto next_slot;
 		}
 		if (!nocow) {
@@ -1411,6 +1422,9 @@ out_check:
 			if (ret) {
 				if (!nolock && nocow)
 					btrfs_end_write_no_snapshoting(root);
+				if (nocow)
+					btrfs_dec_nocow_writers(root->fs_info,
+								disk_bytenr);
 				goto error;
 			}
 			cow_start = (u64)-1;
@@ -1453,6 +1467,8 @@ out_check:
 
 		ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
 					       num_bytes, num_bytes, type);
+		if (nocow)
+			btrfs_dec_nocow_writers(root->fs_info, disk_bytenr);
 		BUG_ON(ret); /* -ENOMEM */
 
 		if (root->root_key.objectid ==
@@ -1962,7 +1978,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 {
 	WARN_ON((end & (PAGE_SIZE - 1)) == 0);
 	return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
-				   cached_state, GFP_NOFS);
+				   cached_state);
 }
 
 /* see btrfs_writepage_start_hook for details on why this is required */
@@ -3103,8 +3119,7 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
 	    test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
-		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM,
-				  GFP_NOFS);
+		clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
 		return 0;
 	}
 
@@ -3256,7 +3271,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	/* grab metadata reservation from transaction handle */
 	if (reserve) {
 		ret = btrfs_orphan_reserve_metadata(trans, inode);
-		BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+		ASSERT(!ret);
+		if (ret) {
+			atomic_dec(&root->orphan_inodes);
+			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+				  &BTRFS_I(inode)->runtime_flags);
+			if (insert)
+				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+					  &BTRFS_I(inode)->runtime_flags);
+			return ret;
+		}
 	}
 
 	/* insert an orphan item to track this unlinked/truncated file */
@@ -3706,7 +3730,7 @@ cache_index:
 	 * and doesn't have an inode ref with the name "bar" anymore.
 	 *
 	 * Setting last_unlink_trans to last_trans is a pessimistic approach,
-	 * but it guarantees correctness at the expense of ocassional full
+	 * but it guarantees correctness at the expense of occasional full
 	 * transaction commits on fsync if our inode is a directory, or if our
 	 * inode is not a directory, logging its parent unnecessarily.
 	 */
@@ -4534,6 +4558,7 @@ delete:
 			BUG_ON(ret);
 			if (btrfs_should_throttle_delayed_refs(trans, root))
 				btrfs_async_run_delayed_refs(root,
+							     trans->transid,
 					trans->delayed_ref_updates * 2, 0);
 			if (be_nice) {
 				if (truncate_space_check(trans, root,
@@ -4962,7 +4987,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * be instantly completed which will give us extents that need
 		 * to be truncated.  If we fail to get an orphan inode down we
 		 * could have left over extents that were never meant to live,
-		 * so we need to garuntee from this point on that everything
+		 * so we need to guarantee from this point on that everything
 		 * will be consistent.
 		 */
 		ret = btrfs_orphan_add(trans, inode);
@@ -5232,7 +5257,7 @@ void btrfs_evict_inode(struct inode *inode)
 		}
 
 		/*
-		 * We can't just steal from the global reserve, we need tomake
+		 * We can't just steal from the global reserve, we need to make
 		 * sure there is room to do it, if not we need to commit and try
 		 * again.
 		 */
@@ -5733,6 +5758,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	int name_len;
 	int is_curr = 0;	/* ctx->pos points to the current index? */
 	bool emitted;
+	bool put = false;
 
 	/* FIXME, use a real flag for deciding about the key type */
 	if (root->fs_info->tree_root == root)
@@ -5750,7 +5776,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (key_type == BTRFS_DIR_INDEX_KEY) {
 		INIT_LIST_HEAD(&ins_list);
 		INIT_LIST_HEAD(&del_list);
-		btrfs_get_delayed_items(inode, &ins_list, &del_list);
+		put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+						      &del_list);
 	}
 
 	key.type = key_type;
@@ -5897,8 +5924,8 @@ next:
 nopos:
 	ret = 0;
 err:
-	if (key_type == BTRFS_DIR_INDEX_KEY)
-		btrfs_put_delayed_items(&ins_list, &del_list);
+	if (put)
+		btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
 	btrfs_free_path(path);
 	return ret;
 }
@@ -6964,7 +6991,18 @@ insert:
 		 * existing will always be non-NULL, since there must be
 		 * extent causing the -EEXIST.
 		 */
-		if (start >= extent_map_end(existing) ||
+		if (existing->start == em->start &&
+		    extent_map_end(existing) == extent_map_end(em) &&
+		    em->block_start == existing->block_start) {
+			/*
+			 * these two extents are the same, it happens
+			 * with inlines especially
+			 */
+			free_extent_map(em);
+			em = existing;
+			err = 0;
+
+		} else if (start >= extent_map_end(existing) ||
 		    start <= existing->start) {
 			/*
 			 * The existing extent map is the one nearest to
@@ -7129,6 +7167,43 @@ out:
 	return em;
 }
 
+static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
+						  const u64 start,
+						  const u64 len,
+						  const u64 orig_start,
+						  const u64 block_start,
+						  const u64 block_len,
+						  const u64 orig_block_len,
+						  const u64 ram_bytes,
+						  const int type)
+{
+	struct extent_map *em = NULL;
+	int ret;
+
+	down_read(&BTRFS_I(inode)->dio_sem);
+	if (type != BTRFS_ORDERED_NOCOW) {
+		em = create_pinned_em(inode, start, len, orig_start,
+				      block_start, block_len, orig_block_len,
+				      ram_bytes, type);
+		if (IS_ERR(em))
+			goto out;
+	}
+	ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
+					   len, block_len, type);
+	if (ret) {
+		if (em) {
+			free_extent_map(em);
+			btrfs_drop_extent_cache(inode, start,
+						start + len - 1, 0);
+		}
+		em = ERR_PTR(ret);
+	}
+ out:
+	up_read(&BTRFS_I(inode)->dio_sem);
+
+	return em;
+}
+
 static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 						  u64 start, u64 len)
 {
@@ -7144,41 +7219,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 	if (ret)
 		return ERR_PTR(ret);
 
-	/*
-	 * Create the ordered extent before the extent map. This is to avoid
-	 * races with the fast fsync path that would lead to it logging file
-	 * extent items that point to disk extents that were not yet written to.
-	 * The fast fsync path collects ordered extents into a local list and
-	 * then collects all the new extent maps, so we must create the ordered
-	 * extent first and make sure the fast fsync path collects any new
-	 * ordered extents after collecting new extent maps as well.
-	 * The fsync path simply can not rely on inode_dio_wait() because it
-	 * causes deadlock with AIO.
-	 */
-	ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
-					   ins.offset, ins.offset, 0);
-	if (ret) {
+	em = btrfs_create_dio_extent(inode, start, ins.offset, start,
+				     ins.objectid, ins.offset, ins.offset,
+				     ins.offset, 0);
+	btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+	if (IS_ERR(em))
 		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		return ERR_PTR(ret);
-	}
-
-	em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
-			      ins.offset, ins.offset, ins.offset, 0);
-	if (IS_ERR(em)) {
-		struct btrfs_ordered_extent *oe;
 
-		btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
-		oe = btrfs_lookup_ordered_extent(inode, start);
-		ASSERT(oe);
-		if (WARN_ON(!oe))
-			return em;
-		set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
-		set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
-		btrfs_remove_ordered_extent(inode, oe);
-		/* Once for our lookup and once for the ordered extents tree. */
-		btrfs_put_ordered_extent(oe);
-		btrfs_put_ordered_extent(oe);
-	}
 	return em;
 }
 
@@ -7408,7 +7455,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 				 cached_state);
 		/*
 		 * We're concerned with the entire range that we're going to be
-		 * doing DIO to, so we need to make sure theres no ordered
+		 * doing DIO to, so we need to make sure there's no ordered
 		 * extents in this range.
 		 */
 		ordered = btrfs_lookup_ordered_range(inode, lockstart,
@@ -7570,7 +7617,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	if (current->journal_info) {
 		/*
 		 * Need to pull our outstanding extents and set journal_info to NULL so
-		 * that anything that needs to check if there's a transction doesn't get
+		 * that anything that needs to check if there's a transaction doesn't get
 		 * confused.
 		 */
 		dio_data = current->journal_info;
@@ -7603,7 +7650,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	 * decompress it, so there will be buffering required no matter what we
 	 * do, so go ahead and fallback to buffered.
 	 *
-	 * We return -ENOTBLK because thats what makes DIO go ahead and go back
+	 * We return -ENOTBLK because that's what makes DIO go ahead and go back
 	 * to buffered IO.  Don't blame me, this is the price we pay for using
 	 * the generic code.
 	 */
@@ -7650,24 +7697,21 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		block_start = em->block_start + (start - em->start);
 
 		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes) == 1) {
+				     &orig_block_len, &ram_bytes) == 1 &&
+		    btrfs_inc_nocow_writers(root->fs_info, block_start)) {
+			struct extent_map *em2;
+
+			em2 = btrfs_create_dio_extent(inode, start, len,
+						      orig_start, block_start,
+						      len, orig_block_len,
+						      ram_bytes, type);
+			btrfs_dec_nocow_writers(root->fs_info, block_start);
 			if (type == BTRFS_ORDERED_PREALLOC) {
 				free_extent_map(em);
-				em = create_pinned_em(inode, start, len,
-						       orig_start,
-						       block_start, len,
-						       orig_block_len,
-						       ram_bytes, type);
-				if (IS_ERR(em)) {
-					ret = PTR_ERR(em);
-					goto unlock_err;
-				}
+				em = em2;
 			}
-
-			ret = btrfs_add_ordered_extent_dio(inode, start,
-					   block_start, len, len, type);
-			if (ret) {
-				free_extent_map(em);
+			if (em2 && IS_ERR(em2)) {
+				ret = PTR_ERR(em2);
 				goto unlock_err;
 			}
 			goto unlock;
@@ -8541,13 +8585,13 @@ out:
 	return retval;
 }
 
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-			       loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_dio_data dio_data = { 0 };
+	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8607,7 +8651,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 
 	ret = __blockdev_direct_IO(iocb, inode,
 				   BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
-				   iter, offset, btrfs_get_blocks_direct, NULL,
+				   iter, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
@@ -9019,7 +9063,7 @@ static int btrfs_truncate(struct inode *inode)
 		return ret;
 
 	/*
-	 * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+	 * Yes ladies and gentlemen, this is indeed ugly.  The fact is we have
 	 * 3 things going on here
 	 *
 	 * 1) We need to reserve space for our orphan item and the space to
@@ -9033,15 +9077,15 @@ static int btrfs_truncate(struct inode *inode)
 	 * space reserved in case it uses space during the truncate (thank you
 	 * very much snapshotting).
 	 *
-	 * And we need these to all be seperate.  The fact is we can use alot of
+	 * And we need these to all be separate.  The fact is we can use a lot of
 	 * space doing the truncate, and we have no earthly idea how much space
-	 * we will use, so we need the truncate reservation to be seperate so it
+	 * we will use, so we need the truncate reservation to be separate so it
 	 * doesn't end up using space reserved for updating the inode or
 	 * removing the orphan item.  We also need to be able to stop the
 	 * transaction and start a new one, which means we need to be able to
 	 * update the inode several times, and we have no idea of knowing how
 	 * many times that will be, so we can't just reserve 1 item for the
-	 * entirety of the opration, so that has to be done seperately as well.
+	 * entirety of the operation, so that has to be done separately as well.
 	 * Then there is the orphan item, which does indeed need to be held on
 	 * to for the whole operation, and we need nobody to touch this reserved
 	 * space except the orphan code.
@@ -9230,6 +9274,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->delayed_iput);
 	RB_CLEAR_NODE(&ei->rb_node);
+	init_rwsem(&ei->dio_sem);
 
 	return inode;
 }
@@ -9387,10 +9432,281 @@ static int btrfs_getattr(struct vfsmount *mnt,
 	return 0;
 }
 
+static int btrfs_rename_exchange(struct inode *old_dir,
+			      struct dentry *old_dentry,
+			      struct inode *new_dir,
+			      struct dentry *new_dentry)
+{
+	struct btrfs_trans_handle *trans;
+	struct btrfs_root *root = BTRFS_I(old_dir)->root;
+	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
+	struct inode *new_inode = new_dentry->d_inode;
+	struct inode *old_inode = old_dentry->d_inode;
+	struct timespec ctime = CURRENT_TIME;
+	struct dentry *parent;
+	u64 old_ino = btrfs_ino(old_inode);
+	u64 new_ino = btrfs_ino(new_inode);
+	u64 old_idx = 0;
+	u64 new_idx = 0;
+	u64 root_objectid;
+	int ret;
+	bool root_log_pinned = false;
+	bool dest_log_pinned = false;
+
+	/* we only allow rename subvolume link between subvolumes */
+	if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+		return -EXDEV;
+
+	/* close the race window with snapshot create/destroy ioctl */
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+		down_read(&root->fs_info->subvol_sem);
+	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+		down_read(&dest->fs_info->subvol_sem);
+
+	/*
+	 * We want to reserve the absolute worst case amount of items.  So if
+	 * both inodes are subvols and we need to unlink them then that would
+	 * require 4 item modifications, but if they are both normal inodes it
+	 * would require 5 item modifications, so we'll assume their normal
+	 * inodes.  So 5 * 2 is 10, plus 2 for the new links, so 12 total items
+	 * should cover the worst case number of items we'll modify.
+	 */
+	trans = btrfs_start_transaction(root, 12);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_notrans;
+	}
+
+	/*
+	 * We need to find a free sequence number both in the source and
+	 * in the destination directory for the exchange.
+	 */
+	ret = btrfs_set_inode_index(new_dir, &old_idx);
+	if (ret)
+		goto out_fail;
+	ret = btrfs_set_inode_index(old_dir, &new_idx);
+	if (ret)
+		goto out_fail;
+
+	BTRFS_I(old_inode)->dir_index = 0ULL;
+	BTRFS_I(new_inode)->dir_index = 0ULL;
+
+	/* Reference for the source. */
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		/* force full log commit if subvolume involved. */
+		btrfs_set_log_full_commit(root->fs_info, trans);
+	} else {
+		btrfs_pin_log_trans(root);
+		root_log_pinned = true;
+		ret = btrfs_insert_inode_ref(trans, dest,
+					     new_dentry->d_name.name,
+					     new_dentry->d_name.len,
+					     old_ino,
+					     btrfs_ino(new_dir), old_idx);
+		if (ret)
+			goto out_fail;
+	}
+
+	/* And now for the dest. */
+	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		/* force full log commit if subvolume involved. */
+		btrfs_set_log_full_commit(dest->fs_info, trans);
+	} else {
+		btrfs_pin_log_trans(dest);
+		dest_log_pinned = true;
+		ret = btrfs_insert_inode_ref(trans, root,
+					     old_dentry->d_name.name,
+					     old_dentry->d_name.len,
+					     new_ino,
+					     btrfs_ino(old_dir), new_idx);
+		if (ret)
+			goto out_fail;
+	}
+
+	/* Update inode version and ctime/mtime. */
+	inode_inc_iversion(old_dir);
+	inode_inc_iversion(new_dir);
+	inode_inc_iversion(old_inode);
+	inode_inc_iversion(new_inode);
+	old_dir->i_ctime = old_dir->i_mtime = ctime;
+	new_dir->i_ctime = new_dir->i_mtime = ctime;
+	old_inode->i_ctime = ctime;
+	new_inode->i_ctime = ctime;
+
+	if (old_dentry->d_parent != new_dentry->d_parent) {
+		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+		btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+	}
+
+	/* src is a subvolume */
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
+		ret = btrfs_unlink_subvol(trans, root, old_dir,
+					  root_objectid,
+					  old_dentry->d_name.name,
+					  old_dentry->d_name.len);
+	} else { /* src is an inode */
+		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);
+	}
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
+
+	/* dest is a subvolume */
+	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+		root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
+		ret = btrfs_unlink_subvol(trans, dest, new_dir,
+					  root_objectid,
+					  new_dentry->d_name.name,
+					  new_dentry->d_name.len);
+	} else { /* dest is an inode */
+		ret = __btrfs_unlink_inode(trans, dest, new_dir,
+					   new_dentry->d_inode,
+					   new_dentry->d_name.name,
+					   new_dentry->d_name.len);
+		if (!ret)
+			ret = btrfs_update_inode(trans, dest, new_inode);
+	}
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
+
+	ret = btrfs_add_link(trans, new_dir, old_inode,
+			     new_dentry->d_name.name,
+			     new_dentry->d_name.len, 0, old_idx);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
+
+	ret = btrfs_add_link(trans, old_dir, new_inode,
+			     old_dentry->d_name.name,
+			     old_dentry->d_name.len, 0, new_idx);
+	if (ret) {
+		btrfs_abort_transaction(trans, root, ret);
+		goto out_fail;
+	}
+
+	if (old_inode->i_nlink == 1)
+		BTRFS_I(old_inode)->dir_index = old_idx;
+	if (new_inode->i_nlink == 1)
+		BTRFS_I(new_inode)->dir_index = new_idx;
+
+	if (root_log_pinned) {
+		parent = new_dentry->d_parent;
+		btrfs_log_new_name(trans, old_inode, old_dir, parent);
+		btrfs_end_log_trans(root);
+		root_log_pinned = false;
+	}
+	if (dest_log_pinned) {
+		parent = old_dentry->d_parent;
+		btrfs_log_new_name(trans, new_inode, new_dir, parent);
+		btrfs_end_log_trans(dest);
+		dest_log_pinned = false;
+	}
+out_fail:
+	/*
+	 * If we have pinned a log and an error happened, we unpin tasks
+	 * trying to sync the log and force them to fallback to a transaction
+	 * commit if the log currently contains any of the inodes involved in
+	 * this rename operation (to ensure we do not persist a log with an
+	 * inconsistent state for any of these inodes or leading to any
+	 * inconsistencies when replayed). If the transaction was aborted, the
+	 * abortion reason is propagated to userspace when attempting to commit
+	 * the transaction. If the log does not contain any of these inodes, we
+	 * allow the tasks to sync it.
+	 */
+	if (ret && (root_log_pinned || dest_log_pinned)) {
+		if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+		    btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+		    btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+		    (new_inode &&
+		     btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+		    btrfs_set_log_full_commit(root->fs_info, trans);
+
+		if (root_log_pinned) {
+			btrfs_end_log_trans(root);
+			root_log_pinned = false;
+		}
+		if (dest_log_pinned) {
+			btrfs_end_log_trans(dest);
+			dest_log_pinned = false;
+		}
+	}
+	ret = btrfs_end_transaction(trans, root);
+out_notrans:
+	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+		up_read(&dest->fs_info->subvol_sem);
+	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+		up_read(&root->fs_info->subvol_sem);
+
+	return ret;
+}
+
+static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     struct inode *dir,
+				     struct dentry *dentry)
+{
+	int ret;
+	struct inode *inode;
+	u64 objectid;
+	u64 index;
+
+	ret = btrfs_find_free_ino(root, &objectid);
+	if (ret)
+		return ret;
+
+	inode = btrfs_new_inode(trans, root, dir,
+				dentry->d_name.name,
+				dentry->d_name.len,
+				btrfs_ino(dir),
+				objectid,
+				S_IFCHR | WHITEOUT_MODE,
+				&index);
+
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		return ret;
+	}
+
+	inode->i_op = &btrfs_special_inode_operations;
+	init_special_inode(inode, inode->i_mode,
+		WHITEOUT_DEV);
+
+	ret = btrfs_init_inode_security(trans, inode, dir,
+				&dentry->d_name);
+	if (ret)
+		goto out;
+
+	ret = btrfs_add_nondir(trans, dir, dentry,
+				inode, 0, index);
+	if (ret)
+		goto out;
+
+	ret = btrfs_update_inode(trans, root, inode);
+out:
+	unlock_new_inode(inode);
+	if (ret)
+		inode_dec_link_count(inode);
+	iput(inode);
+
+	return ret;
+}
+
 static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
-			   struct inode *new_dir, struct dentry *new_dentry)
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
 {
 	struct btrfs_trans_handle *trans;
+	unsigned int trans_num_items;
 	struct btrfs_root *root = BTRFS_I(old_dir)->root;
 	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
 	struct inode *new_inode = d_inode(new_dentry);
@@ -9399,6 +9715,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	u64 root_objectid;
 	int ret;
 	u64 old_ino = btrfs_ino(old_inode);
+	bool log_pinned = false;
 
 	if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
@@ -9449,15 +9766,21 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * We want to reserve the absolute worst case amount of items.  So if
 	 * both inodes are subvols and we need to unlink them then that would
 	 * require 4 item modifications, but if they are both normal inodes it
-	 * would require 5 item modifications, so we'll assume their normal
+	 * would require 5 item modifications, so we'll assume they are normal
 	 * inodes.  So 5 * 2 is 10, plus 1 for the new link, so 11 total items
 	 * should cover the worst case number of items we'll modify.
+	 * If our rename has the whiteout flag, we need more 5 units for the
+	 * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
+	 * when selinux is enabled).
 	 */
-	trans = btrfs_start_transaction(root, 11);
+	trans_num_items = 11;
+	if (flags & RENAME_WHITEOUT)
+		trans_num_items += 5;
+	trans = btrfs_start_transaction(root, trans_num_items);
 	if (IS_ERR(trans)) {
-                ret = PTR_ERR(trans);
-                goto out_notrans;
-        }
+		ret = PTR_ERR(trans);
+		goto out_notrans;
+	}
 
 	if (dest != root)
 		btrfs_record_root_in_trans(trans, dest);
@@ -9471,6 +9794,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		/* force full log commit if subvolume involved. */
 		btrfs_set_log_full_commit(root->fs_info, trans);
 	} else {
+		btrfs_pin_log_trans(root);
+		log_pinned = true;
 		ret = btrfs_insert_inode_ref(trans, dest,
 					     new_dentry->d_name.name,
 					     new_dentry->d_name.len,
@@ -9478,14 +9803,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 					     btrfs_ino(new_dir), index);
 		if (ret)
 			goto out_fail;
-		/*
-		 * this is an ugly little race, but the rename is required
-		 * to make sure that if we crash, the inode is either at the
-		 * old name or the new one.  pinning the log transaction lets
-		 * us make sure we don't allow a log commit to come in after
-		 * we unlink the name but before we add the new name back in.
-		 */
-		btrfs_pin_log_trans(root);
 	}
 
 	inode_inc_iversion(old_dir);
@@ -9552,12 +9869,46 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (old_inode->i_nlink == 1)
 		BTRFS_I(old_inode)->dir_index = index;
 
-	if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+	if (log_pinned) {
 		struct dentry *parent = new_dentry->d_parent;
+
 		btrfs_log_new_name(trans, old_inode, old_dir, parent);
 		btrfs_end_log_trans(root);
+		log_pinned = false;
+	}
+
+	if (flags & RENAME_WHITEOUT) {
+		ret = btrfs_whiteout_for_rename(trans, root, old_dir,
+						old_dentry);
+
+		if (ret) {
+			btrfs_abort_transaction(trans, root, ret);
+			goto out_fail;
+		}
 	}
 out_fail:
+	/*
+	 * If we have pinned the log and an error happened, we unpin tasks
+	 * trying to sync the log and force them to fallback to a transaction
+	 * commit if the log currently contains any of the inodes involved in
+	 * this rename operation (to ensure we do not persist a log with an
+	 * inconsistent state for any of these inodes or leading to any
+	 * inconsistencies when replayed). If the transaction was aborted, the
+	 * abortion reason is propagated to userspace when attempting to commit
+	 * the transaction. If the log does not contain any of these inodes, we
+	 * allow the tasks to sync it.
+	 */
+	if (ret && log_pinned) {
+		if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+		    btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+		    btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+		    (new_inode &&
+		     btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+		    btrfs_set_log_full_commit(root->fs_info, trans);
+
+		btrfs_end_log_trans(root);
+		log_pinned = false;
+	}
 	btrfs_end_transaction(trans, root);
 out_notrans:
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
@@ -9570,10 +9921,14 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			 struct inode *new_dir, struct dentry *new_dentry,
 			 unsigned int flags)
 {
-	if (flags & ~RENAME_NOREPLACE)
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
-	return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (flags & RENAME_EXCHANGE)
+		return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+					  new_dentry);
+
+	return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
 static void btrfs_run_delalloc_work(struct btrfs_work *work)
@@ -9942,6 +10297,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 				btrfs_end_transaction(trans, root);
 			break;
 		}
+		btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
 
 		last_alloc = ins.offset;
 		ret = insert_reserved_file_extent(trans, inode,
@@ -10160,10 +10516,10 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 	.symlink	= btrfs_symlink,
 	.setattr	= btrfs_setattr,
 	.mknod		= btrfs_mknod,
-	.setxattr	= btrfs_setxattr,
+	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
-	.removexattr	= btrfs_removexattr,
+	.removexattr	= generic_removexattr,
 	.permission	= btrfs_permission,
 	.get_acl	= btrfs_get_acl,
 	.set_acl	= btrfs_set_acl,
@@ -10181,7 +10537,7 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
 static const struct file_operations btrfs_dir_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
-	.iterate	= btrfs_real_readdir,
+	.iterate_shared	= btrfs_real_readdir,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= btrfs_compat_ioctl,
@@ -10237,10 +10593,10 @@ static const struct address_space_operations btrfs_symlink_aops = {
 static const struct inode_operations btrfs_file_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
-	.setxattr	= btrfs_setxattr,
+	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr      = btrfs_listxattr,
-	.removexattr	= btrfs_removexattr,
+	.removexattr	= generic_removexattr,
 	.permission	= btrfs_permission,
 	.fiemap		= btrfs_fiemap,
 	.get_acl	= btrfs_get_acl,
@@ -10251,10 +10607,10 @@ static const struct inode_operations btrfs_special_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
-	.setxattr	= btrfs_setxattr,
+	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
-	.removexattr	= btrfs_removexattr,
+	.removexattr	= generic_removexattr,
 	.get_acl	= btrfs_get_acl,
 	.set_acl	= btrfs_set_acl,
 	.update_time	= btrfs_update_time,
@@ -10265,10 +10621,10 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.setattr	= btrfs_setattr,
 	.permission	= btrfs_permission,
-	.setxattr	= btrfs_setxattr,
+	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
 	.listxattr	= btrfs_listxattr,
-	.removexattr	= btrfs_removexattr,
+	.removexattr	= generic_removexattr,
 	.update_time	= btrfs_update_time,
 };
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index f545f81f6..05173563e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -125,10 +125,10 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 	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)
+	if (flags & BTRFS_INODE_NOCOMPRESS)
 		iflags |= FS_NOCOMP_FL;
+	else if (flags & BTRFS_INODE_COMPRESS)
+		iflags |= FS_COMPR_FL;
 
 	return iflags;
 }
@@ -296,7 +296,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 		}
 	} else {
 		/*
-		 * Revert back under same assuptions as above
+		 * Revert back under same assumptions as above
 		 */
 		if (S_ISREG(mode)) {
 			if (inode->i_size == 0)
@@ -439,7 +439,7 @@ static noinline int create_subvol(struct inode *dir,
 {
 	struct btrfs_trans_handle *trans;
 	struct btrfs_key key;
-	struct btrfs_root_item root_item;
+	struct btrfs_root_item *root_item;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *leaf;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -455,16 +455,22 @@ static noinline int create_subvol(struct inode *dir,
 	u64 qgroup_reserved;
 	uuid_le new_uuid;
 
+	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
+	if (!root_item)
+		return -ENOMEM;
+
 	ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
 	if (ret)
-		return ret;
+		goto fail_free;
 
 	/*
 	 * Don't create subvolume whose level is not zero. Or qgroup will be
-	 * screwed up since it assume subvolme qgroup's level to be 0.
+	 * screwed up since it assumes subvolume qgroup's level to be 0.
 	 */
-	if (btrfs_qgroup_level(objectid))
-		return -ENOSPC;
+	if (btrfs_qgroup_level(objectid)) {
+		ret = -ENOSPC;
+		goto fail_free;
+	}
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
@@ -474,14 +480,14 @@ static noinline int create_subvol(struct inode *dir,
 	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
 					       8, &qgroup_reserved, false);
 	if (ret)
-		return ret;
+		goto fail_free;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_subvolume_release_metadata(root, &block_rsv,
 						 qgroup_reserved);
-		return ret;
+		goto fail_free;
 	}
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
@@ -509,47 +515,45 @@ static noinline int create_subvol(struct inode *dir,
 			    BTRFS_UUID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
-	memset(&root_item, 0, sizeof(root_item));
-
-	inode_item = &root_item.inode;
+	inode_item = &root_item->inode;
 	btrfs_set_stack_inode_generation(inode_item, 1);
 	btrfs_set_stack_inode_size(inode_item, 3);
 	btrfs_set_stack_inode_nlink(inode_item, 1);
 	btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
 	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
-	btrfs_set_root_flags(&root_item, 0);
-	btrfs_set_root_limit(&root_item, 0);
+	btrfs_set_root_flags(root_item, 0);
+	btrfs_set_root_limit(root_item, 0);
 	btrfs_set_stack_inode_flags(inode_item, 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);
-	btrfs_set_root_refs(&root_item, 1);
-	btrfs_set_root_used(&root_item, leaf->len);
-	btrfs_set_root_last_snapshot(&root_item, 0);
+	btrfs_set_root_bytenr(root_item, leaf->start);
+	btrfs_set_root_generation(root_item, trans->transid);
+	btrfs_set_root_level(root_item, 0);
+	btrfs_set_root_refs(root_item, 1);
+	btrfs_set_root_used(root_item, leaf->len);
+	btrfs_set_root_last_snapshot(root_item, 0);
 
-	btrfs_set_root_generation_v2(&root_item,
-			btrfs_root_generation(&root_item));
+	btrfs_set_root_generation_v2(root_item,
+			btrfs_root_generation(root_item));
 	uuid_le_gen(&new_uuid);
-	memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
-	btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
-	btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
-	root_item.ctime = root_item.otime;
-	btrfs_set_root_ctransid(&root_item, trans->transid);
-	btrfs_set_root_otransid(&root_item, trans->transid);
+	memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
+	btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec);
+	btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec);
+	root_item->ctime = root_item->otime;
+	btrfs_set_root_ctransid(root_item, trans->transid);
+	btrfs_set_root_otransid(root_item, trans->transid);
 
 	btrfs_tree_unlock(leaf);
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	btrfs_set_root_dirid(&root_item, new_dirid);
+	btrfs_set_root_dirid(root_item, new_dirid);
 
 	key.objectid = objectid;
 	key.offset = 0;
 	key.type = BTRFS_ROOT_ITEM_KEY;
 	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
-				&root_item);
+				root_item);
 	if (ret)
 		goto fail;
 
@@ -601,12 +605,13 @@ static noinline int create_subvol(struct inode *dir,
 	BUG_ON(ret);
 
 	ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
-				  root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+				  root_item->uuid, BTRFS_UUID_KEY_SUBVOL,
 				  objectid);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 
 fail:
+	kfree(root_item);
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
 	btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
@@ -629,6 +634,10 @@ fail:
 		d_instantiate(dentry, inode);
 	}
 	return ret;
+
+fail_free:
+	kfree(root_item);
+	return ret;
 }
 
 static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
@@ -681,7 +690,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto dec_and_free;
 
-	btrfs_wait_ordered_extents(root, -1);
+	btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
 
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
@@ -771,7 +780,7 @@ free_pending:
  *	a. be owner of dir, or
  *	b. be owner of victim, or
  *	c. have CAP_FOWNER capability
- *  6. If the victim is append-only or immutable we can't do antyhing with
+ *  6. If the victim is append-only or immutable we can't do anything with
  *     links pointing to it.
  *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
  *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
@@ -837,7 +846,7 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	struct dentry *dentry;
 	int error;
 
-	error = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
 	if (error == -EINTR)
 		return error;
 
@@ -1228,7 +1237,7 @@ again:
 
 
 	set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
-			  &cached_state, GFP_NOFS);
+			  &cached_state);
 
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree,
 			     page_start, page_end - 1, &cached_state,
@@ -2366,7 +2375,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 		goto out;
 
 
-	err = mutex_lock_killable_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
 	if (err == -EINTR)
 		goto out_drop_write;
 	dentry = lookup_one_len(vol_args->name, parent, namelen);
@@ -2667,10 +2676,10 @@ out:
 	return ret;
 }
 
-static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 {
 	struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
-	struct btrfs_ioctl_vol_args *vol_args;
+	struct btrfs_ioctl_vol_args_v2 *vol_args;
 	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -2686,7 +2695,9 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 		goto err_drop;
 	}
 
-	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	/* Check for compatibility reject unknown flags */
+	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
+		return -EOPNOTSUPP;
 
 	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
 			1)) {
@@ -2695,13 +2706,23 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	}
 
 	mutex_lock(&root->fs_info->volume_mutex);
-	ret = btrfs_rm_device(root, vol_args->name);
+	if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
+		ret = btrfs_rm_device(root, NULL, vol_args->devid);
+	} else {
+		vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+		ret = btrfs_rm_device(root, vol_args->name, 0);
+	}
 	mutex_unlock(&root->fs_info->volume_mutex);
 	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
 
-	if (!ret)
-		btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
-
+	if (!ret) {
+		if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
+			btrfs_info(root->fs_info, "device deleted: id %llu",
+					vol_args->devid);
+		else
+			btrfs_info(root->fs_info, "device deleted: %s",
+					vol_args->name);
+	}
 out:
 	kfree(vol_args);
 err_drop:
@@ -2709,6 +2730,47 @@ err_drop:
 	return ret;
 }
 
+static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+{
+	struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+	struct btrfs_ioctl_vol_args *vol_args;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
+	if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
+			1)) {
+		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+		goto out_drop_write;
+	}
+
+	vol_args = memdup_user(arg, sizeof(*vol_args));
+	if (IS_ERR(vol_args)) {
+		ret = PTR_ERR(vol_args);
+		goto out;
+	}
+
+	vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+	mutex_lock(&root->fs_info->volume_mutex);
+	ret = btrfs_rm_device(root, vol_args->name, 0);
+	mutex_unlock(&root->fs_info->volume_mutex);
+
+	if (!ret)
+		btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
+	kfree(vol_args);
+out:
+	atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+out_drop_write:
+	mnt_drop_write_file(file);
+
+	return ret;
+}
+
 static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
 {
 	struct btrfs_ioctl_fs_info_args *fi_args;
@@ -3468,13 +3530,16 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	u64 last_dest_end = destoff;
 
 	ret = -ENOMEM;
-	buf = vmalloc(root->nodesize);
-	if (!buf)
-		return ret;
+	buf = kmalloc(root->nodesize, GFP_KERNEL | __GFP_NOWARN);
+	if (!buf) {
+		buf = vmalloc(root->nodesize);
+		if (!buf)
+			return ret;
+	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
-		vfree(buf);
+		kvfree(buf);
 		return ret;
 	}
 
@@ -3775,7 +3840,7 @@ process_slot:
 
 out:
 	btrfs_free_path(path);
-	vfree(buf);
+	kvfree(buf);
 	return ret;
 }
 
@@ -4376,7 +4441,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_root *root, void __user *arg)
 			1)) {
 			ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 		} else {
-			ret = btrfs_dev_replace_start(root, p);
+			ret = btrfs_dev_replace_by_ioctl(root, p);
 			atomic_set(
 			 &root->fs_info->mutually_exclusive_operation_running,
 			 0);
@@ -4585,7 +4650,7 @@ again:
 	}
 
 	/*
-	 * mut. excl. ops lock is locked.  Three possibilites:
+	 * mut. excl. ops lock is locked.  Three possibilities:
 	 *   (1) some other op is running
 	 *   (2) balance is running
 	 *   (3) balance is paused -- special case (think resume)
@@ -4847,8 +4912,8 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	/* update qgroup status and info */
 	err = btrfs_run_qgroups(trans, root->fs_info);
 	if (err < 0)
-		btrfs_std_error(root->fs_info, ret,
-			    "failed to update qgroup status and info\n");
+		btrfs_handle_fs_error(root->fs_info, err,
+			    "failed to update qgroup status and info");
 	err = btrfs_end_transaction(trans, root);
 	if (err && !ret)
 		ret = err;
@@ -5394,9 +5459,15 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
 	trans = btrfs_start_transaction(root, 0);
-	if (IS_ERR(trans))
-		return PTR_ERR(trans);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out_drop_write;
+	}
 
 	spin_lock(&root->fs_info->super_lock);
 	newflags = btrfs_super_compat_flags(super_block);
@@ -5415,7 +5486,11 @@ static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
 	btrfs_set_super_incompat_flags(super_block, newflags);
 	spin_unlock(&root->fs_info->super_lock);
 
-	return btrfs_commit_transaction(trans, root);
+	ret = btrfs_commit_transaction(trans, root);
+out_drop_write:
+	mnt_drop_write_file(file);
+
+	return ret;
 }
 
 long btrfs_ioctl(struct file *file, unsigned int
@@ -5459,6 +5534,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_add_dev(root, argp);
 	case BTRFS_IOC_RM_DEV:
 		return btrfs_ioctl_rm_dev(file, argp);
+	case BTRFS_IOC_RM_DEV_V2:
+		return btrfs_ioctl_rm_dev_v2(file, argp);
 	case BTRFS_IOC_FS_INFO:
 		return btrfs_ioctl_fs_info(root, argp);
 	case BTRFS_IOC_DEV_INFO:
@@ -5490,7 +5567,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 		ret = btrfs_sync_fs(file_inode(file)->i_sb, 1);
 		/*
 		 * The transaction thread may want to do more work,
-		 * namely it pokes the cleaner ktread that will start
+		 * namely it pokes the cleaner kthread that will start
 		 * processing uncleaned subvols.
 		 */
 		wake_up_process(root->fs_info->transaction_kthread);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 0de7da5a6..aca8264f4 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -661,14 +661,15 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+			       const u64 range_start, const u64 range_len)
 {
-	struct list_head splice, works;
+	LIST_HEAD(splice);
+	LIST_HEAD(skipped);
+	LIST_HEAD(works);
 	struct btrfs_ordered_extent *ordered, *next;
 	int count = 0;
-
-	INIT_LIST_HEAD(&splice);
-	INIT_LIST_HEAD(&works);
+	const u64 range_end = range_start + range_len;
 
 	mutex_lock(&root->ordered_extent_mutex);
 	spin_lock(&root->ordered_extent_lock);
@@ -676,6 +677,14 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 	while (!list_empty(&splice) && nr) {
 		ordered = list_first_entry(&splice, struct btrfs_ordered_extent,
 					   root_extent_list);
+
+		if (range_end <= ordered->start ||
+		    ordered->start + ordered->disk_len <= range_start) {
+			list_move_tail(&ordered->root_extent_list, &skipped);
+			cond_resched_lock(&root->ordered_extent_lock);
+			continue;
+		}
+
 		list_move_tail(&ordered->root_extent_list,
 			       &root->ordered_extents);
 		atomic_inc(&ordered->refs);
@@ -694,6 +703,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 			nr--;
 		count++;
 	}
+	list_splice_tail(&skipped, &root->ordered_extents);
 	list_splice_tail(&splice, &root->ordered_extents);
 	spin_unlock(&root->ordered_extent_lock);
 
@@ -708,11 +718,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 	return count;
 }
 
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+			      const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
 	int done;
+	int total_done = 0;
 
 	INIT_LIST_HEAD(&splice);
 
@@ -728,8 +740,10 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 			       &fs_info->ordered_roots);
 		spin_unlock(&fs_info->ordered_root_lock);
 
-		done = btrfs_wait_ordered_extents(root, nr);
+		done = btrfs_wait_ordered_extents(root, nr,
+						  range_start, range_len);
 		btrfs_put_fs_root(root);
+		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
 		if (nr != -1) {
@@ -740,6 +754,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 	list_splice_tail(&splice, &fs_info->ordered_roots);
 	spin_unlock(&fs_info->ordered_root_lock);
 	mutex_unlock(&fs_info->ordered_operations_mutex);
+
+	return total_done;
 }
 
 /*
@@ -952,6 +968,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	struct rb_node *prev = NULL;
 	struct btrfs_ordered_extent *test;
 	int ret = 1;
+	u64 orig_offset = offset;
 
 	spin_lock_irq(&tree->lock);
 	if (ordered) {
@@ -967,7 +984,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 
 	/* truncate file */
 	if (disk_i_size > i_size) {
-		BTRFS_I(inode)->disk_i_size = i_size;
+		BTRFS_I(inode)->disk_i_size = orig_offset;
 		ret = 0;
 		goto out;
 	}
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 23c96059c..451507776 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -58,7 +58,7 @@ struct btrfs_ordered_sum {
 
 #define BTRFS_ORDERED_COMPRESSED 3 /* writing a zlib compressed extent */
 
-#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to prealloced extent */
+#define BTRFS_ORDERED_PREALLOC 4 /* set when writing to preallocated extent */
 
 #define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */
 
@@ -197,8 +197,10 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u32 *sum, int len);
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
-void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
+int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+			       const u64 range_start, const u64 range_len);
+int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+			      const u64 range_start, const u64 range_len);
 void btrfs_get_logged_extents(struct inode *inode,
 			      struct list_head *logged_list,
 			      const loff_t start,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 9e119552e..9d4c05b14 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -85,7 +85,7 @@ struct btrfs_qgroup {
 
 	/*
 	 * temp variables for accounting operations
-	 * Refer to qgroup_shared_accouting() for details.
+	 * Refer to qgroup_shared_accounting() for details.
 	 */
 	u64 old_refcnt;
 	u64 new_refcnt;
@@ -499,7 +499,7 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 	}
 	/*
 	 * we call btrfs_free_qgroup_config() when umounting
-	 * filesystem and disabling quota, so we set qgroup_ulit
+	 * filesystem and disabling quota, so we set qgroup_ulist
 	 * to be null here to avoid double free.
 	 */
 	ulist_free(fs_info->qgroup_ulist);
@@ -1036,7 +1036,7 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info,
 
 /*
  * The easy accounting, if we are adding/removing the only ref for an extent
- * then this qgroup and all of the parent qgroups get their refrence and
+ * then this qgroup and all of the parent qgroups get their reference and
  * exclusive counts adjusted.
  *
  * Caller should hold fs_info->qgroup_lock.
@@ -1436,7 +1436,7 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
 
 	/*
 	 * No need to do lock, since this function will only be called in
-	 * btrfs_commmit_transaction().
+	 * btrfs_commit_transaction().
 	 */
 	node = rb_first(&delayed_refs->dirty_extent_root);
 	while (node) {
@@ -1557,7 +1557,7 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info,
  * A:	cur_old_roots < nr_old_roots	(not exclusive before)
  * !A:	cur_old_roots == nr_old_roots	(possible exclusive before)
  * B:	cur_new_roots < nr_new_roots	(not exclusive now)
- * !B:	cur_new_roots == nr_new_roots	(possible exclsuive now)
+ * !B:	cur_new_roots == nr_new_roots	(possible exclusive now)
  *
  * Results:
  * +: Possible sharing -> exclusive	-: Possible exclusive -> sharing
@@ -1851,7 +1851,7 @@ out:
 }
 
 /*
- * Copy the acounting information between qgroups. This is necessary
+ * Copy the accounting information between qgroups. This is necessary
  * when a snapshot or a subvolume is created. Throwing an error will
  * cause a transaction abort so we take extra care here to only error
  * when a readonly fs is a reasonable outcome.
@@ -2340,7 +2340,7 @@ out:
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
 	/*
-	 * only update status, since the previous part has alreay updated the
+	 * only update status, since the previous part has already updated the
 	 * qgroup info.
 	 */
 	trans = btrfs_start_transaction(fs_info->quota_root, 1);
@@ -2542,8 +2542,7 @@ int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
 	changeset.bytes_changed = 0;
 	changeset.range_changed = ulist_alloc(GFP_NOFS);
 	ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
-			start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
-			&changeset);
+			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
 	trace_btrfs_qgroup_reserve_data(inode, start, len,
 					changeset.bytes_changed,
 					QGROUP_RESERVE);
@@ -2580,8 +2579,7 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
 		return -ENOMEM;
 
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, 
-			start + len -1, EXTENT_QGROUP_RESERVED, GFP_NOFS,
-			&changeset);
+			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
 	if (ret < 0)
 		goto out;
 
@@ -2672,7 +2670,7 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
 }
 
 /*
- * Check qgroup reserved space leaking, normally at destory inode
+ * Check qgroup reserved space leaking, normally at destroy inode
  * time
  */
 void btrfs_qgroup_check_reserved_leak(struct inode *inode)
@@ -2688,7 +2686,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
 		return;
 
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
-			EXTENT_QGROUP_RESERVED, GFP_NOFS, &changeset);
+			EXTENT_QGROUP_RESERVED, &changeset);
 
 	WARN_ON(ret < 0);
 	if (WARN_ON(changeset.bytes_changed)) {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0b7792e02..f8b6d411a 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -576,7 +576,7 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
 	 * we can't merge with cached rbios, since the
 	 * idea is that when we merge the destination
 	 * rbio is going to run our IO for us.  We can
-	 * steal from cached rbio's though, other functions
+	 * steal from cached rbios though, other functions
 	 * handle that.
 	 */
 	if (test_bit(RBIO_CACHE_BIT, &last->flags) ||
@@ -2368,7 +2368,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
-		/* Check scrubbing pairty and repair it */
+		/* Check scrubbing parity and repair it */
 		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		parity = kmap(p);
 		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
@@ -2493,7 +2493,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
 		/*
 		 * Here means we got one corrupted data stripe and one
 		 * corrupted parity on RAID6, if the corrupted parity
-		 * is scrubbing parity, luckly, use the other one to repair
+		 * is scrubbing parity, luckily, use the other one to repair
 		 * the data, or we can not repair the data stripe.
 		 */
 		if (failp != rbio->scrubp)
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 298631eae..8428db7cd 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -761,12 +761,14 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
 
 	do {
 		enqueued = 0;
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_for_each_entry(device, &fs_devices->devices, dev_list) {
 			if (atomic_read(&device->reada_in_flight) <
 			    MAX_IN_FLIGHT)
 				enqueued += reada_start_machine_dev(fs_info,
 								    device);
 		}
+		mutex_unlock(&fs_devices->device_list_mutex);
 		total += enqueued;
 	} while (enqueued && total < 10000);
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 08ef890de..0477dca15 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -668,8 +668,8 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
  * roots of b-trees that reference the tree block.
  *
  * the basic idea of this function is check backrefs of a given block
- * to find upper level blocks that refernece the block, and then check
- * bakcrefs of these upper level blocks recursively. the recursion stop
+ * to find upper level blocks that reference the block, and then check
+ * backrefs of these upper level blocks recursively. the recursion stop
  * when tree root is reached or backrefs for the block is cached.
  *
  * NOTE: if we find backrefs for a block are cached, we know backrefs
@@ -1160,7 +1160,7 @@ out:
 			if (!RB_EMPTY_NODE(&upper->rb_node))
 				continue;
 
-			/* Add this guy's upper edges to the list to proces */
+			/* Add this guy's upper edges to the list to process */
 			list_for_each_entry(edge, &upper->upper, list[LOWER])
 				list_add_tail(&edge->list[UPPER], &list);
 			if (list_empty(&upper->upper))
@@ -2396,7 +2396,7 @@ again:
 		}
 
 		/*
-		 * we keep the old last snapshod transid in rtranid when we
+		 * we keep the old last snapshot transid in rtranid when we
 		 * created the relocation tree.
 		 */
 		last_snap = btrfs_root_rtransid(&reloc_root->root_item);
@@ -2418,7 +2418,7 @@ again:
 	}
 out:
 	if (ret) {
-		btrfs_std_error(root->fs_info, ret, NULL);
+		btrfs_handle_fs_error(root->fs_info, ret, NULL);
 		if (!list_empty(&reloc_roots))
 			free_reloc_roots(&reloc_roots);
 
@@ -2616,7 +2616,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 			 * only one thread can access block_rsv at this point,
 			 * so we don't need hold lock to protect block_rsv.
 			 * we expand more reservation size here to allow enough
-			 * space for relocation and we will return eailer in
+			 * space for relocation and we will return earlier in
 			 * enospc case.
 			 */
 			rc->block_rsv->size = tmp + rc->extent_root->nodesize *
@@ -2814,7 +2814,7 @@ static void mark_block_processed(struct reloc_control *rc,
 				 u64 bytenr, u32 blocksize)
 {
 	set_extent_bits(&rc->processed_blocks, bytenr, bytenr + blocksize - 1,
-			EXTENT_DIRTY, GFP_NOFS);
+			EXTENT_DIRTY);
 }
 
 static void __mark_block_processed(struct reloc_control *rc,
@@ -3182,7 +3182,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		    page_start + offset == cluster->boundary[nr]) {
 			set_extent_bits(&BTRFS_I(inode)->io_tree,
 					page_start, page_end,
-					EXTENT_BOUNDARY, GFP_NOFS);
+					EXTENT_BOUNDARY);
 			nr++;
 		}
 
@@ -4059,8 +4059,7 @@ restart:
 	}
 
 	btrfs_release_path(path);
-	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
-			  GFP_NOFS);
+	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY);
 
 	if (trans) {
 		btrfs_end_transaction_throttle(trans, rc->extent_root);
@@ -4254,12 +4253,11 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
 	btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
 	       rc->block_group->key.objectid, rc->block_group->flags);
 
-	ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
-	if (ret < 0) {
-		err = ret;
-		goto out;
-	}
-	btrfs_wait_ordered_roots(fs_info, -1);
+	btrfs_wait_block_group_reservations(rc->block_group);
+	btrfs_wait_nocow_writers(rc->block_group);
+	btrfs_wait_ordered_roots(fs_info, -1,
+				 rc->block_group->key.objectid,
+				 rc->block_group->key.offset);
 
 	while (1) {
 		mutex_lock(&fs_info->cleaner_mutex);
@@ -4592,7 +4590,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 
 /*
  * called before creating snapshot. it calculates metadata reservation
- * requried for relocating tree blocks in the snapshot
+ * required for relocating tree blocks in the snapshot
  */
 void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
 			      u64 *bytes_to_reserve)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 9fcd6dfc3..f1c30861d 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -71,9 +71,9 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
  * search_key: the key to search
  * path: the path we search
  * root_item: the root item of the tree we look for
- * root_key: the reak key of the tree we look for
+ * root_key: the root key of the tree we look for
  *
- * If ->offset of 'seach_key' is -1ULL, it means we are not sure the offset
+ * If ->offset of 'search_key' is -1ULL, it means we are not sure the offset
  * of the search key, just lookup the root with the highest offset for a
  * given objectid.
  *
@@ -284,7 +284,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 			trans = btrfs_join_transaction(tree_root);
 			if (IS_ERR(trans)) {
 				err = PTR_ERR(trans);
-				btrfs_std_error(tree_root->fs_info, err,
+				btrfs_handle_fs_error(tree_root->fs_info, err,
 					    "Failed to start trans to delete "
 					    "orphan item");
 				break;
@@ -293,7 +293,7 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
 						    root_key.objectid);
 			btrfs_end_transaction(trans, tree_root);
 			if (err) {
-				btrfs_std_error(tree_root->fs_info, err,
+				btrfs_handle_fs_error(tree_root->fs_info, err,
 					    "Failed to delete root orphan "
 					    "item");
 				break;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 4678f03e8..70427ef66 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -745,7 +745,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 		 * sure we read the bad mirror.
 		 */
 		ret = set_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-					EXTENT_DAMAGED, GFP_NOFS);
+					EXTENT_DAMAGED);
 		if (ret) {
 			/* set_extent_bits should give proper error */
 			WARN_ON(ret > 0);
@@ -763,7 +763,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 						end, EXTENT_DAMAGED, 0, NULL);
 		if (!corrected)
 			clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-						EXTENT_DAMAGED, GFP_NOFS);
+						EXTENT_DAMAGED);
 	}
 
 out:
@@ -1044,7 +1044,7 @@ nodatasum_case:
 
 		/*
 		 * !is_metadata and !have_csum, this means that the data
-		 * might not be COW'ed, that it might be modified
+		 * might not be COWed, that it might be modified
 		 * concurrently. The general strategy to work on the
 		 * commit root does not help in the case when COW is not
 		 * used.
@@ -1125,7 +1125,7 @@ nodatasum_case:
 	 * the 2nd page of mirror #1 faces I/O errors, and the 2nd page
 	 * of mirror #2 is readable but the final checksum test fails,
 	 * then the 2nd page of mirror #3 could be tried, whether now
-	 * the final checksum succeedes. But this would be a rare
+	 * the final checksum succeeds. But this would be a rare
 	 * exception and is therefore not implemented. At least it is
 	 * avoided that the good copy is overwritten.
 	 * A more useful improvement would be to pick the sectors
@@ -1350,7 +1350,7 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		recover->bbio = bbio;
 		recover->map_length = mapped_length;
 
-		BUG_ON(page_index >= SCRUB_PAGES_PER_RD_BIO);
+		BUG_ON(page_index >= SCRUB_MAX_PAGES_PER_BLOCK);
 
 		nmirrors = min(scrub_nr_raid_mirrors(bbio), BTRFS_MAX_MIRRORS);
 
@@ -2127,6 +2127,8 @@ static void scrub_missing_raid56_end_io(struct bio *bio)
 	if (bio->bi_error)
 		sblock->no_io_error_seen = 0;
 
+	bio_put(bio);
+
 	btrfs_queue_work(fs_info->scrub_workers, &sblock->work);
 }
 
@@ -2179,7 +2181,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	struct btrfs_fs_info *fs_info = sctx->dev_root->fs_info;
 	u64 length = sblock->page_count * PAGE_SIZE;
 	u64 logical = sblock->pagev[0]->logical;
-	struct btrfs_bio *bbio;
+	struct btrfs_bio *bbio = NULL;
 	struct bio *bio;
 	struct btrfs_raid_bio *rbio;
 	int ret;
@@ -2860,7 +2862,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	int extent_mirror_num;
 	int stop_loop = 0;
 
-	nsectors = map->stripe_len / root->sectorsize;
+	nsectors = div_u64(map->stripe_len, root->sectorsize);
 	bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
 	sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
 			  GFP_NOFS);
@@ -2980,6 +2982,7 @@ again:
 						       extent_len);
 
 			mapped_length = extent_len;
+			bbio = NULL;
 			ret = btrfs_map_block(fs_info, READ, extent_logical,
 					      &mapped_length, &bbio, 0);
 			if (!ret) {
@@ -3070,7 +3073,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	int slot;
 	u64 nstripes;
 	struct extent_buffer *l;
-	struct btrfs_key key;
 	u64 physical;
 	u64 logical;
 	u64 logic_end;
@@ -3079,7 +3081,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	int mirror_num;
 	struct reada_control *reada1;
 	struct reada_control *reada2;
-	struct btrfs_key key_start;
+	struct btrfs_key key;
 	struct btrfs_key key_end;
 	u64 increment = map->stripe_len;
 	u64 offset;
@@ -3158,21 +3160,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	scrub_blocked_if_needed(fs_info);
 
 	/* FIXME it might be better to start readahead at commit root */
-	key_start.objectid = logical;
-	key_start.type = BTRFS_EXTENT_ITEM_KEY;
-	key_start.offset = (u64)0;
+	key.objectid = logical;
+	key.type = BTRFS_EXTENT_ITEM_KEY;
+	key.offset = (u64)0;
 	key_end.objectid = logic_end;
 	key_end.type = BTRFS_METADATA_ITEM_KEY;
 	key_end.offset = (u64)-1;
-	reada1 = btrfs_reada_add(root, &key_start, &key_end);
+	reada1 = btrfs_reada_add(root, &key, &key_end);
 
-	key_start.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
-	key_start.type = BTRFS_EXTENT_CSUM_KEY;
-	key_start.offset = logical;
+	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+	key.type = BTRFS_EXTENT_CSUM_KEY;
+	key.offset = logical;
 	key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
 	key_end.type = BTRFS_EXTENT_CSUM_KEY;
 	key_end.offset = logic_end;
-	reada2 = btrfs_reada_add(csum_root, &key_start, &key_end);
+	reada2 = btrfs_reada_add(csum_root, &key, &key_end);
 
 	if (!IS_ERR(reada1))
 		btrfs_reada_wait(reada1);
@@ -3580,6 +3582,46 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		scrub_pause_on(fs_info);
 		ret = btrfs_inc_block_group_ro(root, cache);
+		if (!ret && is_dev_replace) {
+			/*
+			 * If we are doing a device replace wait for any tasks
+			 * that started dellaloc right before we set the block
+			 * group to RO mode, as they might have just allocated
+			 * an extent from it or decided they could do a nocow
+			 * write. And if any such tasks did that, wait for their
+			 * ordered extents to complete and then commit the
+			 * current transaction, so that we can later see the new
+			 * extent items in the extent tree - the ordered extents
+			 * create delayed data references (for cow writes) when
+			 * they complete, which will be run and insert the
+			 * corresponding extent items into the extent tree when
+			 * we commit the transaction they used when running
+			 * inode.c:btrfs_finish_ordered_io(). We later use
+			 * the commit root of the extent tree to find extents
+			 * to copy from the srcdev into the tgtdev, and we don't
+			 * want to miss any new extents.
+			 */
+			btrfs_wait_block_group_reservations(cache);
+			btrfs_wait_nocow_writers(cache);
+			ret = btrfs_wait_ordered_roots(fs_info, -1,
+						       cache->key.objectid,
+						       cache->key.offset);
+			if (ret > 0) {
+				struct btrfs_trans_handle *trans;
+
+				trans = btrfs_join_transaction(root);
+				if (IS_ERR(trans))
+					ret = PTR_ERR(trans);
+				else
+					ret = btrfs_commit_transaction(trans,
+								       root);
+				if (ret) {
+					scrub_pause_off(fs_info);
+					btrfs_put_block_group(cache);
+					break;
+				}
+			}
+		}
 		scrub_pause_off(fs_info);
 
 		if (ret == 0) {
@@ -3600,9 +3642,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			break;
 		}
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;
 		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
 		ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
 				  found_key.offset, cache, is_dev_replace);
 
@@ -3638,6 +3682,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 
 		scrub_pause_off(fs_info);
 
+		btrfs_dev_replace_lock(&fs_info->dev_replace, 1);
+		dev_replace->cursor_left = dev_replace->cursor_right;
+		dev_replace->item_needs_writeback = 1;
+		btrfs_dev_replace_unlock(&fs_info->dev_replace, 1);
+
 		if (ro_set)
 			btrfs_dec_block_group_ro(root, cache);
 
@@ -3675,9 +3724,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			ret = -ENOMEM;
 			break;
 		}
-
-		dev_replace->cursor_left = dev_replace->cursor_right;
-		dev_replace->item_needs_writeback = 1;
 skip:
 		key.offset = found_key.offset + length;
 		btrfs_release_path(path);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 8d358c547..b71dd2983 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1831,7 +1831,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 
 	/*
 	 * If we have a parent root we need to verify that the parent dir was
-	 * not delted and then re-created, if it was then we have no overwrite
+	 * not deleted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
 	 */
 	if (sctx->parent_root) {
@@ -4192,9 +4192,9 @@ static int __process_new_xattr(int num, struct btrfs_key *di_key,
 		return -ENOMEM;
 
 	/*
-	 * This hack is needed because empty acl's are stored as zero byte
+	 * This hack is needed because empty acls are stored as zero byte
 	 * data in xattrs. Problem with that is, that receiving these zero byte
-	 * acl's will fail later. To fix this, we send a dummy acl list that
+	 * acls will fail later. To fix this, we send a dummy acl list that
 	 * only contains the version number and no entries.
 	 */
 	if (!strncmp(name, XATTR_NAME_POSIX_ACL_ACCESS, name_len) ||
@@ -5939,6 +5939,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	u32 i;
 	u64 *clone_sources_tmp = NULL;
 	int clone_sources_to_rollback = 0;
+	unsigned alloc_size;
 	int sort_clone_roots = 0;
 	int index;
 
@@ -5978,6 +5979,12 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
+	if (arg->clone_sources_count >
+	    ULLONG_MAX / sizeof(*arg->clone_sources)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!access_ok(VERIFY_READ, arg->clone_sources,
 			sizeof(*arg->clone_sources) *
 			arg->clone_sources_count)) {
@@ -6022,40 +6029,53 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
 	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
-	sctx->send_buf = vmalloc(sctx->send_max_size);
+	sctx->send_buf = kmalloc(sctx->send_max_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->send_buf) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->send_buf = vmalloc(sctx->send_max_size);
+		if (!sctx->send_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
-	sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+	sctx->read_buf = kmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->read_buf) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
+		if (!sctx->read_buf) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
 	sctx->pending_dir_moves = RB_ROOT;
 	sctx->waiting_dir_moves = RB_ROOT;
 	sctx->orphan_dirs = RB_ROOT;
 
-	sctx->clone_roots = vzalloc(sizeof(struct clone_root) *
-			(arg->clone_sources_count + 1));
+	alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1);
+
+	sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
 	if (!sctx->clone_roots) {
-		ret = -ENOMEM;
-		goto out;
+		sctx->clone_roots = vzalloc(alloc_size);
+		if (!sctx->clone_roots) {
+			ret = -ENOMEM;
+			goto out;
+		}
 	}
 
+	alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources);
+
 	if (arg->clone_sources_count) {
-		clone_sources_tmp = vmalloc(arg->clone_sources_count *
-				sizeof(*arg->clone_sources));
+		clone_sources_tmp = kmalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
 		if (!clone_sources_tmp) {
-			ret = -ENOMEM;
-			goto out;
+			clone_sources_tmp = vmalloc(alloc_size);
+			if (!clone_sources_tmp) {
+				ret = -ENOMEM;
+				goto out;
+			}
 		}
 
 		ret = copy_from_user(clone_sources_tmp, arg->clone_sources,
-				arg->clone_sources_count *
-				sizeof(*arg->clone_sources));
+				alloc_size);
 		if (ret) {
 			ret = -EFAULT;
 			goto out;
@@ -6089,7 +6109,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 			sctx->clone_roots[i].root = clone_root;
 			clone_sources_to_rollback = i + 1;
 		}
-		vfree(clone_sources_tmp);
+		kvfree(clone_sources_tmp);
 		clone_sources_tmp = NULL;
 	}
 
@@ -6207,15 +6227,15 @@ out:
 		btrfs_root_dec_send_in_progress(sctx->parent_root);
 
 	kfree(arg);
-	vfree(clone_sources_tmp);
+	kvfree(clone_sources_tmp);
 
 	if (sctx) {
 		if (sctx->send_filp)
 			fput(sctx->send_filp);
 
-		vfree(sctx->clone_roots);
-		vfree(sctx->send_buf);
-		vfree(sctx->read_buf);
+		kvfree(sctx->clone_roots);
+		kvfree(sctx->send_buf);
+		kvfree(sctx->read_buf);
 
 		name_cache_free(sctx);
 
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index e05619f24..875c757e7 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -36,7 +36,7 @@ static inline void put_unaligned_le8(u8 val, void *p)
  *
  * The end result is that anyone who #includes ctree.h gets a
  * declaration for the btrfs_set_foo functions and btrfs_foo functions,
- * which are wappers of btrfs_set_token_#bits functions and
+ * which are wrappers of btrfs_set_token_#bits functions and
  * btrfs_get_token_#bits functions, which are defined in this file.
  *
  * These setget functions do all the extent_buffer related mapping
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d7c138f42..60e7179ed 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -97,15 +97,6 @@ const char *btrfs_decode_error(int errno)
 	return errstr;
 }
 
-static void save_error_info(struct btrfs_fs_info *fs_info)
-{
-	/*
-	 * today we only save the error info into ram.  Long term we'll
-	 * also send it down to the disk
-	 */
-	set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
-}
-
 /* btrfs handle error by forcing the filesystem readonly */
 static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 {
@@ -121,7 +112,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 		 * Note that a running device replace operation is not
 		 * canceled here although there is no way to update
 		 * the progress. It would add the risk of a deadlock,
-		 * therefore the canceling is ommited. The only penalty
+		 * therefore the canceling is omitted. The only penalty
 		 * is that some I/O remains active until the procedure
 		 * completes. The next time when the filesystem is
 		 * mounted writeable again, the device replace
@@ -131,11 +122,11 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
 }
 
 /*
- * __btrfs_std_error decodes expected errors from the caller and
+ * __btrfs_handle_fs_error decodes expected errors from the caller and
  * invokes the approciate error response.
  */
 __cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
 		       unsigned int line, int errno, const char *fmt, ...)
 {
 	struct super_block *sb = fs_info->sb;
@@ -170,8 +161,13 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
 	}
 #endif
 
+	/*
+	 * Today we only save the error info to memory.  Long term we'll
+	 * also send it down to the disk
+	 */
+	set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
+
 	/* Don't go through full error handling during mount */
-	save_error_info(fs_info);
 	if (sb->s_flags & MS_BORN)
 		btrfs_handle_error(fs_info);
 }
@@ -252,7 +248,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 	/* Wake up anybody who may be waiting on this transaction */
 	wake_up(&root->fs_info->transaction_wait);
 	wake_up(&root->fs_info->transaction_blocked_wait);
-	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
+	__btrfs_handle_fs_error(root->fs_info, function, line, errno, NULL);
 }
 /*
  * __btrfs_panic decodes unexpected, fatal errors from the caller,
@@ -1160,7 +1156,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 		return 0;
 	}
 
-	btrfs_wait_ordered_roots(fs_info, -1);
+	btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
 
 	trans = btrfs_attach_transaction_barrier(root);
 	if (IS_ERR(trans)) {
@@ -1488,10 +1484,10 @@ static int setup_security_options(struct btrfs_fs_info *fs_info,
 		memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
 	} else {
 		/*
-		 * Since SELinux(the only one supports security_mnt_opts) does
-		 * NOT support changing context during remount/mount same sb,
-		 * This must be the same or part of the same security options,
-		 * just free it.
+		 * Since SELinux (the only one supporting security_mnt_opts)
+		 * does NOT support changing context during remount/mount of
+		 * the same sb, this must be the same or part of the same
+		 * security options, just free it.
 		 */
 		security_free_mnt_opts(sec_opts);
 	}
@@ -1669,8 +1665,8 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
 					 unsigned long old_opts)
 {
 	/*
-	 * We need cleanup all defragable inodes if the autodefragment is
-	 * close or the fs is R/O.
+	 * We need to cleanup all defragable inodes if the autodefragment is
+	 * close or the filesystem is read only.
 	 */
 	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
 	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
@@ -1811,6 +1807,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			}
 		}
 		sb->s_flags &= ~MS_RDONLY;
+
+		fs_info->open = 1;
 	}
 out:
 	wake_up_process(fs_info->transaction_kthread);
@@ -1881,7 +1879,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	int ret;
 
 	/*
-	 * We aren't under the device list lock, so this is racey-ish, but good
+	 * We aren't under the device list lock, so this is racy-ish, but good
 	 * enough for our purposes.
 	 */
 	nr_devices = fs_info->fs_devices->open_devices;
@@ -1900,7 +1898,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	if (!devices_info)
 		return -ENOMEM;
 
-	/* calc min stripe number for data space alloction */
+	/* calc min stripe number for data space allocation */
 	type = btrfs_get_alloc_profile(root, 1);
 	if (type & BTRFS_BLOCK_GROUP_RAID0) {
 		min_stripes = 2;
@@ -1936,7 +1934,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 		avail_space *= BTRFS_STRIPE_LEN;
 
 		/*
-		 * In order to avoid overwritting the superblock on the drive,
+		 * In order to avoid overwriting the superblock on the drive,
 		 * btrfs starts at an offset of at least 1MB when doing chunk
 		 * allocation.
 		 */
@@ -2051,9 +2049,10 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
 	int ret;
 	u64 thresh = 0;
+	int mixed = 0;
 
 	/*
-	 * holding chunk_muext to avoid allocating new chunks, holding
+	 * holding chunk_mutex to avoid allocating new chunks, holding
 	 * device_list_mutex to avoid the device being removed
 	 */
 	rcu_read_lock();
@@ -2076,8 +2075,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				}
 			}
 		}
-		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
-			total_free_meta += found->disk_total - found->disk_used;
+
+		/*
+		 * Metadata in mixed block goup profiles are accounted in data
+		 */
+		if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+			if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+				mixed = 1;
+			else
+				total_free_meta += found->disk_total -
+					found->disk_used;
+		}
 
 		total_used += found->disk_used;
 	}
@@ -2090,7 +2098,11 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	/* Account global block reserve as used, it's in logical size already */
 	spin_lock(&block_rsv->lock);
-	buf->f_bfree -= block_rsv->size >> bits;
+	/* Mixed block groups accounting is not byte-accurate, avoid overflow */
+	if (buf->f_bfree >= block_rsv->size >> bits)
+		buf->f_bfree -= block_rsv->size >> bits;
+	else
+		buf->f_bfree = 0;
 	spin_unlock(&block_rsv->lock);
 
 	buf->f_bavail = div_u64(total_free_data, factor);
@@ -2115,7 +2127,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	 */
 	thresh = 4 * 1024 * 1024;
 
-	if (total_free_meta - thresh < block_rsv->size)
+	if (!mixed && total_free_meta - thresh < block_rsv->size)
 		buf->f_bavail = 0;
 
 	buf->f_type = BTRFS_SUPER_MAGIC;
@@ -2293,7 +2305,7 @@ static void btrfs_interface_exit(void)
 
 static void btrfs_print_mod_info(void)
 {
-	printk(KERN_INFO "Btrfs loaded"
+	printk(KERN_INFO "Btrfs loaded, crc32c=%s"
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
@@ -2303,33 +2315,48 @@ static void btrfs_print_mod_info(void)
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 			", integrity-checker=on"
 #endif
-			"\n");
+			"\n",
+			btrfs_crc32c_impl());
 }
 
 static int btrfs_run_sanity_tests(void)
 {
-	int ret;
-
+	int ret, i;
+	u32 sectorsize, nodesize;
+	u32 test_sectorsize[] = {
+		PAGE_SIZE,
+	};
 	ret = btrfs_init_test_fs();
 	if (ret)
 		return ret;
-
-	ret = btrfs_test_free_space_cache();
-	if (ret)
-		goto out;
-	ret = btrfs_test_extent_buffer_operations();
-	if (ret)
-		goto out;
-	ret = btrfs_test_extent_io();
-	if (ret)
-		goto out;
-	ret = btrfs_test_inodes();
-	if (ret)
-		goto out;
-	ret = btrfs_test_qgroups();
-	if (ret)
-		goto out;
-	ret = btrfs_test_free_space_tree();
+	for (i = 0; i < ARRAY_SIZE(test_sectorsize); i++) {
+		sectorsize = test_sectorsize[i];
+		for (nodesize = sectorsize;
+		     nodesize <= BTRFS_MAX_METADATA_BLOCKSIZE;
+		     nodesize <<= 1) {
+			pr_info("BTRFS: selftest: sectorsize: %u  nodesize: %u\n",
+				sectorsize, nodesize);
+			ret = btrfs_test_free_space_cache(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_extent_buffer_operations(sectorsize,
+				nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_extent_io(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_inodes(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_qgroups(sectorsize, nodesize);
+			if (ret)
+				goto out;
+			ret = btrfs_test_free_space_tree(sectorsize, nodesize);
+			if (ret)
+				goto out;
+		}
+	}
 out:
 	btrfs_destroy_test_fs();
 	return ret;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 539e7b5e3..4879656bd 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -120,6 +120,9 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
 	if (!fs_info)
 		return -EPERM;
 
+	if (fs_info->sb->s_flags & MS_RDONLY)
+		return -EROFS;
+
 	ret = kstrtoul(skip_spaces(buf), 0, &val);
 	if (ret)
 		return ret;
@@ -364,7 +367,13 @@ static ssize_t btrfs_label_show(struct kobject *kobj,
 {
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 	char *label = fs_info->super_copy->label;
-	return snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+	ssize_t ret;
+
+	spin_lock(&fs_info->super_lock);
+	ret = snprintf(buf, PAGE_SIZE, label[0] ? "%s\n" : "%s", label);
+	spin_unlock(&fs_info->super_lock);
+
+	return ret;
 }
 
 static ssize_t btrfs_label_store(struct kobject *kobj,
@@ -374,6 +383,9 @@ static ssize_t btrfs_label_store(struct kobject *kobj,
 	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
 	size_t p_len;
 
+	if (!fs_info)
+		return -EPERM;
+
 	if (fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index f54bf450b..02223f3f7 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -68,7 +68,7 @@ int btrfs_init_test_fs(void)
 	if (IS_ERR(test_mnt)) {
 		printk(KERN_ERR "btrfs: cannot mount test file system\n");
 		unregister_filesystem(&test_type);
-		return ret;
+		return PTR_ERR(test_mnt);
 	}
 	return 0;
 }
@@ -175,7 +175,7 @@ void btrfs_free_dummy_root(struct btrfs_root *root)
 }
 
 struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length)
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize)
 {
 	struct btrfs_block_group_cache *cache;
 
@@ -192,8 +192,8 @@ btrfs_alloc_dummy_block_group(unsigned long length)
 	cache->key.objectid = 0;
 	cache->key.offset = length;
 	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
-	cache->sectorsize = 4096;
-	cache->full_stripe_len = 4096;
+	cache->sectorsize = sectorsize;
+	cache->full_stripe_len = sectorsize;
 
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index 054b8c73c..66fb6b701 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -26,27 +26,28 @@
 struct btrfs_root;
 struct btrfs_trans_handle;
 
-int btrfs_test_free_space_cache(void);
-int btrfs_test_extent_buffer_operations(void);
-int btrfs_test_extent_io(void);
-int btrfs_test_inodes(void);
-int btrfs_test_qgroups(void);
-int btrfs_test_free_space_tree(void);
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize);
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize);
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize);
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize);
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize);
 int btrfs_init_test_fs(void);
 void btrfs_destroy_test_fs(void);
 struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void);
 void btrfs_free_dummy_root(struct btrfs_root *root);
 struct btrfs_block_group_cache *
-btrfs_alloc_dummy_block_group(unsigned long length);
+btrfs_alloc_dummy_block_group(unsigned long length, u32 sectorsize);
 void btrfs_free_dummy_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans);
 #else
-static inline int btrfs_test_free_space_cache(void)
+static inline int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_extent_buffer_operations(void)
+static inline int btrfs_test_extent_buffer_operations(u32 sectorsize,
+	u32 nodesize)
 {
 	return 0;
 }
@@ -57,19 +58,19 @@ static inline int btrfs_init_test_fs(void)
 static inline void btrfs_destroy_test_fs(void)
 {
 }
-static inline int btrfs_test_extent_io(void)
+static inline int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_inodes(void)
+static inline int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_qgroups(void)
+static inline int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
-static inline int btrfs_test_free_space_tree(void)
+static inline int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
 {
 	return 0;
 }
diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c
index f51963a8f..4f8cbd1ec 100644
--- a/fs/btrfs/tests/extent-buffer-tests.c
+++ b/fs/btrfs/tests/extent-buffer-tests.c
@@ -22,7 +22,7 @@
 #include "../extent_io.h"
 #include "../disk-io.h"
 
-static int test_btrfs_split_item(void)
+static int test_btrfs_split_item(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_path *path;
 	struct btrfs_root *root;
@@ -40,7 +40,7 @@ static int test_btrfs_split_item(void)
 
 	test_msg("Running btrfs_split_item tests\n");
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Could not allocate root\n");
 		return PTR_ERR(root);
@@ -53,7 +53,8 @@ static int test_btrfs_split_item(void)
 		return -ENOMEM;
 	}
 
-	path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, 4096);
+	path->nodes[0] = eb = alloc_dummy_extent_buffer(NULL, nodesize,
+							nodesize);
 	if (!eb) {
 		test_msg("Could not allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -222,8 +223,8 @@ out:
 	return ret;
 }
 
-int btrfs_test_extent_buffer_operations(void)
+int btrfs_test_extent_buffer_operations(u32 sectorsize, u32 nodesize)
 {
-	test_msg("Running extent buffer operation tests");
-	return test_btrfs_split_item();
+	test_msg("Running extent buffer operation tests\n");
+	return test_btrfs_split_item(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 70948b13b..d19ab0317 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/sizes.h>
 #include "btrfs-tests.h"
+#include "../ctree.h"
 #include "../extent_io.h"
 
 #define PROCESS_UNLOCK		(1 << 0)
@@ -65,7 +66,7 @@ static noinline int process_page_range(struct inode *inode, u64 start, u64 end,
 	return count;
 }
 
-static int test_find_delalloc(void)
+static int test_find_delalloc(u32 sectorsize)
 {
 	struct inode *inode;
 	struct extent_io_tree tmp;
@@ -113,7 +114,7 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 * |---  search  ---|
 	 */
-	set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL);
+	set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL);
 	start = 0;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -122,9 +123,9 @@ static int test_find_delalloc(void)
 		test_msg("Should have found at least one delalloc\n");
 		goto out_bits;
 	}
-	if (start != 0 || end != 4095) {
-		test_msg("Expected start 0 end 4095, got start %Lu end %Lu\n",
-			 start, end);
+	if (start != 0 || end != (sectorsize - 1)) {
+		test_msg("Expected start 0 end %u, got start %llu end %llu\n",
+			sectorsize - 1, start, end);
 		goto out_bits;
 	}
 	unlock_extent(&tmp, start, end);
@@ -144,7 +145,7 @@ static int test_find_delalloc(void)
 		test_msg("Couldn't find the locked page\n");
 		goto out_bits;
 	}
-	set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL);
+	set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -172,11 +173,11 @@ static int test_find_delalloc(void)
 	 * |--- delalloc ---|
 	 *                    |--- search ---|
 	 */
-	test_start = max_bytes + 4096;
+	test_start = max_bytes + sectorsize;
 	locked_page = find_lock_page(inode->i_mapping, test_start >>
 				     PAGE_SHIFT);
 	if (!locked_page) {
-		test_msg("Could'nt find the locked page\n");
+		test_msg("Couldn't find the locked page\n");
 		goto out_bits;
 	}
 	start = test_start;
@@ -199,7 +200,7 @@ static int test_find_delalloc(void)
 	 *
 	 * We are re-using our test_start from above since it works out well.
 	 */
-	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL);
+	set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL);
 	start = test_start;
 	end = 0;
 	found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -262,7 +263,7 @@ static int test_find_delalloc(void)
 	}
 	ret = 0;
 out_bits:
-	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL);
+	clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1);
 out:
 	if (locked_page)
 		put_page(locked_page);
@@ -272,6 +273,16 @@ out:
 	return ret;
 }
 
+/**
+ * test_bit_in_byte - Determine whether a bit is set in a byte
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit_in_byte(int nr, const u8 *addr)
+{
+	return 1UL & (addr[nr / BITS_PER_BYTE] >> (nr & (BITS_PER_BYTE - 1)));
+}
+
 static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 			     unsigned long len)
 {
@@ -298,25 +309,29 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 		return -EINVAL;
 	}
 
-	bitmap_set(bitmap, (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
-		   sizeof(long) * BITS_PER_BYTE);
-	extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
-				 sizeof(long) * BITS_PER_BYTE);
-	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
-		test_msg("Setting straddling pages failed\n");
-		return -EINVAL;
-	}
+	/* Straddling pages test */
+	if (len > PAGE_SIZE) {
+		bitmap_set(bitmap,
+			(PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+			sizeof(long) * BITS_PER_BYTE);
+		extent_buffer_bitmap_set(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+					sizeof(long) * BITS_PER_BYTE);
+		if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+			test_msg("Setting straddling pages failed\n");
+			return -EINVAL;
+		}
 
-	bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
-	bitmap_clear(bitmap,
-		     (PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
-		     sizeof(long) * BITS_PER_BYTE);
-	extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
-	extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
-				   sizeof(long) * BITS_PER_BYTE);
-	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
-		test_msg("Clearing straddling pages failed\n");
-		return -EINVAL;
+		bitmap_set(bitmap, 0, len * BITS_PER_BYTE);
+		bitmap_clear(bitmap,
+			(PAGE_SIZE - sizeof(long) / 2) * BITS_PER_BYTE,
+			sizeof(long) * BITS_PER_BYTE);
+		extent_buffer_bitmap_set(eb, 0, 0, len * BITS_PER_BYTE);
+		extent_buffer_bitmap_clear(eb, PAGE_SIZE - sizeof(long) / 2, 0,
+					sizeof(long) * BITS_PER_BYTE);
+		if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
+			test_msg("Clearing straddling pages failed\n");
+			return -EINVAL;
+		}
 	}
 
 	/*
@@ -333,7 +348,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	for (i = 0; i < len * BITS_PER_BYTE; i++) {
 		int bit, bit1;
 
-		bit = !!test_bit(i, bitmap);
+		bit = !!test_bit_in_byte(i, (u8 *)bitmap);
 		bit1 = !!extent_buffer_test_bit(eb, 0, i);
 		if (bit1 != bit) {
 			test_msg("Testing bit pattern failed\n");
@@ -351,15 +366,22 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	return 0;
 }
 
-static int test_eb_bitmaps(void)
+static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 {
-	unsigned long len = PAGE_SIZE * 4;
+	unsigned long len;
 	unsigned long *bitmap;
 	struct extent_buffer *eb;
 	int ret;
 
 	test_msg("Running extent buffer bitmap tests\n");
 
+	/*
+	 * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
+	 * BTRFS_MAX_METADATA_BLOCKSIZE.
+	 */
+	len = (sectorsize < BTRFS_MAX_METADATA_BLOCKSIZE)
+		? sectorsize * 4 : sectorsize;
+
 	bitmap = kmalloc(len, GFP_KERNEL);
 	if (!bitmap) {
 		test_msg("Couldn't allocate test bitmap\n");
@@ -379,7 +401,7 @@ static int test_eb_bitmaps(void)
 
 	/* Do it over again with an extent buffer which isn't page-aligned. */
 	free_extent_buffer(eb);
-	eb = __alloc_dummy_extent_buffer(NULL, PAGE_SIZE / 2, len);
+	eb = __alloc_dummy_extent_buffer(NULL, nodesize / 2, len);
 	if (!eb) {
 		test_msg("Couldn't allocate test extent buffer\n");
 		kfree(bitmap);
@@ -393,17 +415,17 @@ out:
 	return ret;
 }
 
-int btrfs_test_extent_io(void)
+int btrfs_test_extent_io(u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
 	test_msg("Running extent I/O tests\n");
 
-	ret = test_find_delalloc();
+	ret = test_find_delalloc(sectorsize);
 	if (ret)
 		goto out;
 
-	ret = test_eb_bitmaps();
+	ret = test_eb_bitmaps(sectorsize, nodesize);
 out:
 	test_msg("Extent I/O tests finished\n");
 	return ret;
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index 514247515..3956bb2ff 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -22,10 +22,10 @@
 #include "../disk-io.h"
 #include "../free-space-cache.h"
 
-#define BITS_PER_BITMAP		(PAGE_SIZE * 8)
+#define BITS_PER_BITMAP		(PAGE_SIZE * 8UL)
 
 /*
- * This test just does basic sanity checking, making sure we can add an exten
+ * This test just does basic sanity checking, making sure we can add an extent
  * entry and remove space from either end and the middle, and make sure we can
  * remove space that covers adjacent extent entries.
  */
@@ -99,7 +99,8 @@ static int test_extents(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-static int test_bitmaps(struct btrfs_block_group_cache *cache)
+static int test_bitmaps(struct btrfs_block_group_cache *cache,
+			u32 sectorsize)
 {
 	u64 next_bitmap_offset;
 	int ret;
@@ -139,7 +140,7 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 	 * The first bitmap we have starts at offset 0 so the next one is just
 	 * at the end of the first bitmap.
 	 */
-	next_bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+	next_bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
 
 	/* Test a bit straddling two bitmaps */
 	ret = test_add_free_space_entry(cache, next_bitmap_offset - SZ_2M,
@@ -167,9 +168,10 @@ static int test_bitmaps(struct btrfs_block_group_cache *cache)
 }
 
 /* This is the high grade jackassery */
-static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache)
+static int test_bitmaps_and_extents(struct btrfs_block_group_cache *cache,
+				    u32 sectorsize)
 {
-	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * 4096);
+	u64 bitmap_offset = (u64)(BITS_PER_BITMAP * sectorsize);
 	int ret;
 
 	test_msg("Running bitmap and extent tests\n");
@@ -396,11 +398,13 @@ static int check_cache_empty(struct btrfs_block_group_cache *cache)
  * wasn't optimal as they could be spread all over the block group while under
  * concurrency (extra overhead and fragmentation).
  *
- * This stealing approach is benefical, since we always prefer to allocate from
- * extent entries, both for clustered and non-clustered allocation requests.
+ * This stealing approach is beneficial, since we always prefer to allocate
+ * from extent entries, both for clustered and non-clustered allocation
+ * requests.
  */
 static int
-test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
+test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache,
+				       u32 sectorsize)
 {
 	int ret;
 	u64 offset;
@@ -538,7 +542,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, 4096);
+	ret = btrfs_add_free_space(cache, SZ_128M + SZ_16M, sectorsize);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -596,8 +600,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (SZ_1M + 4096)) {
-		test_msg("Cache free space is not 1Mb + 4Kb\n");
+	if (cache->free_space_ctl->free_space != (SZ_1M + sectorsize)) {
+		test_msg("Cache free space is not 1Mb + %u\n", sectorsize);
 		return -EINVAL;
 	}
 
@@ -610,22 +614,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -EINVAL;
 	}
 
-	/* All that remains is a 4Kb free space region in a bitmap. Confirm. */
+	/*
+	 * All that remains is a sectorsize free space region in a bitmap.
+	 * Confirm.
+	 */
 	ret = check_num_extents_and_bitmaps(cache, 1, 1);
 	if (ret)
 		return ret;
 
-	if (cache->free_space_ctl->free_space != 4096) {
-		test_msg("Cache free space is not 4Kb\n");
+	if (cache->free_space_ctl->free_space != sectorsize) {
+		test_msg("Cache free space is not %u\n", sectorsize);
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache,
-					    0, 4096, 0,
+					    0, sectorsize, 0,
 					    &max_extent_size);
 	if (offset != (SZ_128M + SZ_16M)) {
-		test_msg("Failed to allocate 4Kb from space cache, returned offset is: %llu\n",
-			 offset);
+		test_msg("Failed to allocate %u, returned offset : %llu\n",
+			 sectorsize, offset);
 		return -EINVAL;
 	}
 
@@ -732,7 +739,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	 * The goal is to test that the bitmap entry space stealing doesn't
 	 * steal this space region.
 	 */
-	ret = btrfs_add_free_space(cache, SZ_32M, 8192);
+	ret = btrfs_add_free_space(cache, SZ_32M, 2 * sectorsize);
 	if (ret) {
 		test_msg("Error adding free space: %d\n", ret);
 		return ret;
@@ -756,7 +763,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 
 	/*
 	 * Confirm that our extent entry didn't stole all free space from the
-	 * bitmap, because of the small 8Kb free space region.
+	 * bitmap, because of the small 2 * sectorsize free space region.
 	 */
 	ret = check_num_extents_and_bitmaps(cache, 2, 1);
 	if (ret)
@@ -782,8 +789,8 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -ENOENT;
 	}
 
-	if (cache->free_space_ctl->free_space != (SZ_1M + 8192)) {
-		test_msg("Cache free space is not 1Mb + 8Kb\n");
+	if (cache->free_space_ctl->free_space != (SZ_1M + 2 * sectorsize)) {
+		test_msg("Cache free space is not 1Mb + %u\n", 2 * sectorsize);
 		return -EINVAL;
 	}
 
@@ -795,21 +802,25 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 		return -EINVAL;
 	}
 
-	/* All that remains is a 8Kb free space region in a bitmap. Confirm. */
+	/*
+	 * All that remains is 2 * sectorsize free space region
+	 * in a bitmap. Confirm.
+	 */
 	ret = check_num_extents_and_bitmaps(cache, 1, 1);
 	if (ret)
 		return ret;
 
-	if (cache->free_space_ctl->free_space != 8192) {
-		test_msg("Cache free space is not 8Kb\n");
+	if (cache->free_space_ctl->free_space != 2 * sectorsize) {
+		test_msg("Cache free space is not %u\n", 2 * sectorsize);
 		return -EINVAL;
 	}
 
 	offset = btrfs_find_space_for_alloc(cache,
-					    0, 8192, 0,
+					    0, 2 * sectorsize, 0,
 					    &max_extent_size);
 	if (offset != SZ_32M) {
-		test_msg("Failed to allocate 8Kb from space cache, returned offset is: %llu\n",
+		test_msg("Failed to allocate %u, offset: %llu\n",
+			 2 * sectorsize,
 			 offset);
 		return -EINVAL;
 	}
@@ -824,7 +835,7 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group_cache *cache)
 	return 0;
 }
 
-int btrfs_test_free_space_cache(void)
+int btrfs_test_free_space_cache(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_block_group_cache *cache;
 	struct btrfs_root *root = NULL;
@@ -832,13 +843,19 @@ int btrfs_test_free_space_cache(void)
 
 	test_msg("Running btrfs free space cache tests\n");
 
-	cache = btrfs_alloc_dummy_block_group(1024 * 1024 * 1024);
+	/*
+	 * For ppc64 (with 64k page size), bytes per bitmap might be
+	 * larger than 1G.  To make bitmap test available in ppc64,
+	 * alloc dummy block group whose size cross bitmaps.
+	 */
+	cache = btrfs_alloc_dummy_block_group(BITS_PER_BITMAP * sectorsize
+					+ PAGE_SIZE, sectorsize);
 	if (!cache) {
 		test_msg("Couldn't run the tests\n");
 		return 0;
 	}
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		ret = PTR_ERR(root);
 		goto out;
@@ -854,14 +871,14 @@ int btrfs_test_free_space_cache(void)
 	ret = test_extents(cache);
 	if (ret)
 		goto out;
-	ret = test_bitmaps(cache);
+	ret = test_bitmaps(cache, sectorsize);
 	if (ret)
 		goto out;
-	ret = test_bitmaps_and_extents(cache);
+	ret = test_bitmaps_and_extents(cache, sectorsize);
 	if (ret)
 		goto out;
 
-	ret = test_steal_space_from_bitmap_to_extent(cache);
+	ret = test_steal_space_from_bitmap_to_extent(cache, sectorsize);
 out:
 	btrfs_free_dummy_block_group(cache);
 	btrfs_free_dummy_root(root);
diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c
index 7cea4462a..aac507085 100644
--- a/fs/btrfs/tests/free-space-tree-tests.c
+++ b/fs/btrfs/tests/free-space-tree-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../disk-io.h"
@@ -30,7 +31,7 @@ struct free_space_extent {
  * The test cases align their operations to this in order to hit some of the
  * edge cases in the bitmap code.
  */
-#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * 4096)
+#define BITMAP_RANGE (BTRFS_FREE_SPACE_BITMAP_BITS * PAGE_SIZE)
 
 static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 				      struct btrfs_fs_info *fs_info,
@@ -439,7 +440,8 @@ typedef int (*test_func_t)(struct btrfs_trans_handle *,
 			   struct btrfs_block_group_cache *,
 			   struct btrfs_path *);
 
-static int run_test(test_func_t test_func, int bitmaps)
+static int run_test(test_func_t test_func, int bitmaps,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root = NULL;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -447,7 +449,7 @@ static int run_test(test_func_t test_func, int bitmaps)
 	struct btrfs_path *path = NULL;
 	int ret;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate dummy root\n");
 		ret = PTR_ERR(root);
@@ -466,7 +468,8 @@ static int run_test(test_func_t test_func, int bitmaps)
 	root->fs_info->free_space_root = root;
 	root->fs_info->tree_root = root;
 
-	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+	root->node = alloc_test_extent_buffer(root->fs_info,
+		nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -474,9 +477,9 @@ static int run_test(test_func_t test_func, int bitmaps)
 	}
 	btrfs_set_header_level(root->node, 0);
 	btrfs_set_header_nritems(root->node, 0);
-	root->alloc_bytenr += 8192;
+	root->alloc_bytenr += 2 * nodesize;
 
-	cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE);
+	cache = btrfs_alloc_dummy_block_group(8 * BITMAP_RANGE, sectorsize);
 	if (!cache) {
 		test_msg("Couldn't allocate dummy block group cache\n");
 		ret = -ENOMEM;
@@ -534,17 +537,18 @@ out:
 	return ret;
 }
 
-static int run_test_both_formats(test_func_t test_func)
+static int run_test_both_formats(test_func_t test_func,
+	u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
-	ret = run_test(test_func, 0);
+	ret = run_test(test_func, 0, sectorsize, nodesize);
 	if (ret)
 		return ret;
-	return run_test(test_func, 1);
+	return run_test(test_func, 1, sectorsize, nodesize);
 }
 
-int btrfs_test_free_space_tree(void)
+int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize)
 {
 	test_func_t tests[] = {
 		test_empty_block_group,
@@ -561,9 +565,11 @@ int btrfs_test_free_space_tree(void)
 
 	test_msg("Running free space tree tests\n");
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		int ret = run_test_both_formats(tests[i]);
+		int ret = run_test_both_formats(tests[i], sectorsize,
+			nodesize);
 		if (ret) {
-			test_msg("%pf failed\n", tests[i]);
+			test_msg("%pf : sectorsize %u failed\n",
+				tests[i], sectorsize);
 			return ret;
 		}
 	}
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 863a6a3af..29648c0a3 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../btrfs_inode.h"
@@ -86,19 +87,19 @@ static void insert_inode_item_key(struct btrfs_root *root)
  * diagram of how the extents will look though this may not be possible we still
  * want to make sure everything acts normally (the last number is not inclusive)
  *
- * [0 - 5][5 -  6][6 - 10][10 - 4096][  4096 - 8192 ][8192 - 12288]
- * [hole ][inline][ hole ][ regular ][regular1 split][    hole    ]
+ * [0 - 5][5 -  6][     6 - 4096     ][ 4096 - 4100][4100 - 8195][8195 - 12291]
+ * [hole ][inline][hole but no extent][  hole   ][   regular ][regular1 split]
  *
- * [ 12288 - 20480][20480 - 24576][  24576 - 28672  ][28672 - 36864][36864 - 45056]
- * [regular1 split][   prealloc1 ][prealloc1 written][   prealloc1 ][ compressed  ]
+ * [12291 - 16387][16387 - 24579][24579 - 28675][ 28675 - 32771][32771 - 36867 ]
+ * [    hole    ][regular1 split][   prealloc ][   prealloc1  ][prealloc1 written]
  *
- * [45056 - 49152][49152-53248][53248-61440][61440-65536][     65536+81920   ]
- * [ compressed1 ][  regular  ][compressed1][  regular  ][ hole but no extent]
+ * [36867 - 45059][45059 - 53251][53251 - 57347][57347 - 61443][61443- 69635]
+ * [  prealloc1  ][ compressed  ][ compressed1 ][    regular  ][ compressed1]
  *
- * [81920-86016]
- * [  regular  ]
+ * [69635-73731][   73731 - 86019   ][86019-90115]
+ * [  regular  ][ hole but no extent][  regular  ]
  */
-static void setup_file_extents(struct btrfs_root *root)
+static void setup_file_extents(struct btrfs_root *root, u32 sectorsize)
 {
 	int slot = 0;
 	u64 disk_bytenr = SZ_1M;
@@ -119,7 +120,7 @@ static void setup_file_extents(struct btrfs_root *root)
 	insert_extent(root, offset, 1, 1, 0, 0, 0, BTRFS_FILE_EXTENT_INLINE, 0,
 		      slot);
 	slot++;
-	offset = 4096;
+	offset = sectorsize;
 
 	/* Now another hole */
 	insert_extent(root, offset, 4, 4, 0, 0, 0, BTRFS_FILE_EXTENT_REG, 0,
@@ -128,99 +129,106 @@ static void setup_file_extents(struct btrfs_root *root)
 	offset += 4;
 
 	/* Now for a regular extent */
-	insert_extent(root, offset, 4095, 4095, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize - 1, sectorsize - 1, 0,
+		      disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	disk_bytenr += 4096;
-	offset += 4095;
+	disk_bytenr += sectorsize;
+	offset += sectorsize - 1;
 
 	/*
 	 * Now for 3 extents that were split from a hole punch so we test
 	 * offsets properly.
 	 */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, 0, 0, BTRFS_FILE_EXTENT_REG,
-		      0, slot);
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0, 0, 0,
+		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, 4 * sectorsize,
 		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 16384;
+	offset += 2 * sectorsize;
+	disk_bytenr += 4 * sectorsize;
 
 	/* Now for a unwritten prealloc extent */
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 4096;
+	offset += sectorsize;
 
 	/*
 	 * We want to jack up disk_bytenr a little more so the em stuff doesn't
 	 * merge our records.
 	 */
-	disk_bytenr += 8192;
+	disk_bytenr += 2 * sectorsize;
 
 	/*
 	 * Now for a partially written prealloc extent, basically the same as
 	 * the hole punch example above.  Ram_bytes never changes when you mark
 	 * extents written btw.
 	 */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      4 * sectorsize, BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 16384, 4096, disk_bytenr, 16384,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, sectorsize,
+		      disk_bytenr, 4 * sectorsize, BTRFS_FILE_EXTENT_REG, 0,
+		      slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 16384,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, 4 * sectorsize,
 		      BTRFS_FILE_EXTENT_PREALLOC, 0, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 16384;
+	offset += 2 * sectorsize;
+	disk_bytenr += 4 * sectorsize;
 
 	/* Now a normal compressed extent */
-	insert_extent(root, offset, 8192, 8192, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+	insert_extent(root, offset, 2 * sectorsize, 2 * sectorsize, 0,
+		      disk_bytenr, sectorsize, BTRFS_FILE_EXTENT_REG,
+		      BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 8192;
+	offset += 2 * sectorsize;
 	/* No merges */
-	disk_bytenr += 8192;
+	disk_bytenr += 2 * sectorsize;
 
 	/* Now a split compressed extent */
-	insert_extent(root, offset, 4096, 16384, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
+	insert_extent(root, offset, sectorsize, 4 * sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG,
+		      BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr + 4096, 4096,
+	offset += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0,
+		      disk_bytenr + sectorsize, sectorsize,
 		      BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 4096;
-	insert_extent(root, offset, 8192, 16384, 8192, disk_bytenr, 4096,
+	offset += sectorsize;
+	insert_extent(root, offset, 2 * sectorsize, 4 * sectorsize,
+		      2 * sectorsize, disk_bytenr, sectorsize,
 		      BTRFS_FILE_EXTENT_REG, BTRFS_COMPRESS_ZLIB, slot);
 	slot++;
-	offset += 8192;
-	disk_bytenr += 8192;
+	offset += 2 * sectorsize;
+	disk_bytenr += 2 * sectorsize;
 
 	/* Now extents that have a hole but no hole extent */
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 	slot++;
-	offset += 16384;
-	disk_bytenr += 4096;
-	insert_extent(root, offset, 4096, 4096, 0, disk_bytenr, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, slot);
+	offset += 4 * sectorsize;
+	disk_bytenr += sectorsize;
+	insert_extent(root, offset, sectorsize, sectorsize, 0, disk_bytenr,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, slot);
 }
 
 static unsigned long prealloc_only = 0;
 static unsigned long compressed_only = 0;
 static unsigned long vacancy_only = 0;
 
-static noinline int test_btrfs_get_extent(void)
+static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -240,7 +248,7 @@ static noinline int test_btrfs_get_extent(void)
 	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	BTRFS_I(inode)->location.offset = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -256,7 +264,7 @@ static noinline int test_btrfs_get_extent(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(NULL, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -264,7 +272,7 @@ static noinline int test_btrfs_get_extent(void)
 
 	/*
 	 * We will just free a dummy node if it's ref count is 2 so we need an
-	 * extra ref so our searches don't accidently release our page.
+	 * extra ref so our searches don't accidentally release our page.
 	 */
 	extent_buffer_get(root->node);
 	btrfs_set_header_nritems(root->node, 0);
@@ -273,7 +281,7 @@ static noinline int test_btrfs_get_extent(void)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(inode, NULL, 0, 0, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_msg("Got an error when we shouldn't have\n");
@@ -295,7 +303,7 @@ static noinline int test_btrfs_get_extent(void)
 	 * setup_file_extents, so if you change anything there you need to
 	 * update the comment and update the expected values below.
 	 */
-	setup_file_extents(root);
+	setup_file_extents(root, sectorsize);
 
 	em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0);
 	if (IS_ERR(em)) {
@@ -318,7 +326,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -327,7 +335,8 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected an inline, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4091) {
+
+	if (em->start != offset || em->len != (sectorsize - 5)) {
 		test_msg("Unexpected extent wanted start %llu len 1, got start "
 			 "%llu len %llu\n", offset, em->start, em->len);
 		goto out;
@@ -344,7 +353,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -366,7 +375,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -375,7 +384,7 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4095) {
+	if (em->start != offset || em->len != sectorsize - 1) {
 		test_msg("Unexpected extent wanted start %llu len 4095, got "
 			 "start %llu len %llu\n", offset, em->start, em->len);
 		goto out;
@@ -393,7 +402,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -402,9 +411,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -421,7 +431,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -430,9 +440,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a hole, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -442,7 +453,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -451,9 +462,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -475,7 +487,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -484,9 +496,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -503,7 +516,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -512,9 +525,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -532,7 +546,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -541,9 +555,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -564,7 +579,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -573,9 +588,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != prealloc_only) {
@@ -598,7 +614,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -607,9 +623,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -631,7 +648,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -640,9 +657,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -665,7 +683,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -674,9 +692,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -691,7 +710,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -701,9 +720,10 @@ static noinline int test_btrfs_get_extent(void)
 			 disk_bytenr, em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 8192) {
-		test_msg("Unexpected extent wanted start %llu len 8192, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 2 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 2 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != compressed_only) {
@@ -725,7 +745,7 @@ static noinline int test_btrfs_get_extent(void)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset + 6, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -734,9 +754,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -765,9 +786,10 @@ static noinline int test_btrfs_get_extent(void)
 	 * length of the actual hole, if this changes we'll have to change this
 	 * test.
 	 */
-	if (em->start != offset || em->len != 12288) {
-		test_msg("Unexpected extent wanted start %llu len 12288, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != 3 * sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u, "
+			"got start %llu len %llu\n",
+			offset, 3 * sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
@@ -783,7 +805,7 @@ static noinline int test_btrfs_get_extent(void)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096, 0);
+	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -792,9 +814,10 @@ static noinline int test_btrfs_get_extent(void)
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != offset || em->len != 4096) {
-		test_msg("Unexpected extent wanted start %llu len 4096, got "
-			 "start %llu len %llu\n", offset, em->start, em->len);
+	if (em->start != offset || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %llu len %u,"
+			"got start %llu len %llu\n",
+			offset, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -815,7 +838,7 @@ out:
 	return ret;
 }
 
-static int test_hole_first(void)
+static int test_hole_first(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -832,7 +855,7 @@ static int test_hole_first(void)
 	BTRFS_I(inode)->location.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	BTRFS_I(inode)->location.offset = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -844,7 +867,7 @@ static int test_hole_first(void)
 		goto out;
 	}
 
-	root->node = alloc_dummy_extent_buffer(NULL, 4096);
+	root->node = alloc_dummy_extent_buffer(NULL, nodesize, nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		goto out;
@@ -861,9 +884,9 @@ static int test_hole_first(void)
 	 * btrfs_get_extent.
 	 */
 	insert_inode_item_key(root);
-	insert_extent(root, 4096, 4096, 4096, 0, 4096, 4096,
-		      BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(inode, NULL, 0, 0, 8192, 0);
+	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
+		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
+	em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -872,9 +895,10 @@ static int test_hole_first(void)
 		test_msg("Expected a hole, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != 0 || em->len != 4096) {
-		test_msg("Unexpected extent wanted start 0 len 4096, got start "
-			 "%llu len %llu\n", em->start, em->len);
+	if (em->start != 0 || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start 0 len %u, "
+			"got start %llu len %llu\n",
+			sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != vacancy_only) {
@@ -884,18 +908,19 @@ static int test_hole_first(void)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, 4096, 8192, 0);
+	em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
 	}
-	if (em->block_start != 4096) {
+	if (em->block_start != sectorsize) {
 		test_msg("Expected a real extent, got %llu\n", em->block_start);
 		goto out;
 	}
-	if (em->start != 4096 || em->len != 4096) {
-		test_msg("Unexpected extent wanted start 4096 len 4096, got "
-			 "start %llu len %llu\n", em->start, em->len);
+	if (em->start != sectorsize || em->len != sectorsize) {
+		test_msg("Unexpected extent wanted start %u len %u, "
+			"got start %llu len %llu\n",
+			sectorsize, sectorsize, em->start, em->len);
 		goto out;
 	}
 	if (em->flags != 0) {
@@ -912,7 +937,7 @@ out:
 	return ret;
 }
 
-static int test_extent_accounting(void)
+static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 {
 	struct inode *inode = NULL;
 	struct btrfs_root *root = NULL;
@@ -924,7 +949,7 @@ static int test_extent_accounting(void)
 		return ret;
 	}
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		goto out;
@@ -954,10 +979,11 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE][4k] */
+	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
 	BTRFS_I(inode)->outstanding_extents++;
 	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
-					BTRFS_MAX_EXTENT_SIZE + 4095, NULL);
+					BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
+					NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -969,10 +995,10 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE/2][4K HOLE][the rest] */
+	/* [BTRFS_MAX_EXTENT_SIZE/2][sectorsize HOLE][the rest] */
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
 			       BTRFS_MAX_EXTENT_SIZE >> 1,
-			       (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+			       (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1,
 			       EXTENT_DELALLOC | EXTENT_DIRTY |
 			       EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
 			       NULL, GFP_KERNEL);
@@ -987,10 +1013,11 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE][4K] */
+	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
 	BTRFS_I(inode)->outstanding_extents++;
 	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
-					(BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
+					(BTRFS_MAX_EXTENT_SIZE >> 1)
+					+ sectorsize - 1,
 					NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
@@ -1004,16 +1031,17 @@ static int test_extent_accounting(void)
 	}
 
 	/*
-	 * [BTRFS_MAX_EXTENT_SIZE+4K][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4K]
+	 * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize]
 	 *
 	 * I'm artificially adding 2 to outstanding_extents because in the
 	 * buffered IO case we'd add things up as we go, but I don't feel like
 	 * doing that here, this isn't the interesting case we want to test.
 	 */
 	BTRFS_I(inode)->outstanding_extents += 2;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE + 8192,
-					(BTRFS_MAX_EXTENT_SIZE << 1) + 12287,
-					NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
+			(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
+			NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1025,10 +1053,13 @@ static int test_extent_accounting(void)
 		goto out;
 	}
 
-	/* [BTRFS_MAX_EXTENT_SIZE+4k][4k][BTRFS_MAX_EXTENT_SIZE+4k] */
+	/*
+	* [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize]
+	*/
 	BTRFS_I(inode)->outstanding_extents++;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
-					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1042,8 +1073,8 @@ static int test_extent_accounting(void)
 
 	/* [BTRFS_MAX_EXTENT_SIZE+4k][4K HOLE][BTRFS_MAX_EXTENT_SIZE+4k] */
 	ret = clear_extent_bit(&BTRFS_I(inode)->io_tree,
-			       BTRFS_MAX_EXTENT_SIZE+4096,
-			       BTRFS_MAX_EXTENT_SIZE+8191,
+			       BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			       BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1,
 			       EXTENT_DIRTY | EXTENT_DELALLOC |
 			       EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
 			       NULL, GFP_KERNEL);
@@ -1063,8 +1094,9 @@ static int test_extent_accounting(void)
 	 * might fail and I'd rather satisfy my paranoia at this point.
 	 */
 	BTRFS_I(inode)->outstanding_extents++;
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE+4096,
-					BTRFS_MAX_EXTENT_SIZE+8191, NULL);
+	ret = btrfs_set_extent_delalloc(inode,
+			BTRFS_MAX_EXTENT_SIZE + sectorsize,
+			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL);
 	if (ret) {
 		test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
 		goto out;
@@ -1103,7 +1135,7 @@ out:
 	return ret;
 }
 
-int btrfs_test_inodes(void)
+int btrfs_test_inodes(u32 sectorsize, u32 nodesize)
 {
 	int ret;
 
@@ -1112,13 +1144,13 @@ int btrfs_test_inodes(void)
 	set_bit(EXTENT_FLAG_PREALLOC, &prealloc_only);
 
 	test_msg("Running btrfs_get_extent tests\n");
-	ret = test_btrfs_get_extent();
+	ret = test_btrfs_get_extent(sectorsize, nodesize);
 	if (ret)
 		return ret;
 	test_msg("Running hole first btrfs_get_extent test\n");
-	ret = test_hole_first();
+	ret = test_hole_first(sectorsize, nodesize);
 	if (ret)
 		return ret;
 	test_msg("Running outstanding_extents tests\n");
-	return test_extent_accounting();
+	return test_extent_accounting(sectorsize, nodesize);
 }
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 8ea5d34bc..57a12c0d6 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/types.h>
 #include "btrfs-tests.h"
 #include "../ctree.h"
 #include "../transaction.h"
@@ -216,7 +217,8 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 	return ret;
 }
 
-static int test_no_shared_qgroup(struct btrfs_root *root)
+static int test_no_shared_qgroup(struct btrfs_root *root,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_trans_handle trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -227,29 +229,30 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 	btrfs_init_dummy_trans(&trans);
 
 	test_msg("Qgroup basic add\n");
-	ret = btrfs_create_qgroup(NULL, fs_info, 5);
+	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
 		test_msg("Couldn't create a qgroup %d\n", ret);
 		return ret;
 	}
 
 	/*
-	 * Since the test trans doesn't havee the complicated delayed refs,
+	 * Since the test trans doesn't have the complicated delayed refs,
 	 * we can only call btrfs_qgroup_account_extent() directly to test
 	 * quota.
 	 */
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+				BTRFS_FS_TREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -257,32 +260,33 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+				nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 	old_roots = NULL;
 	new_roots = NULL;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = remove_extent_item(root, 4096, 4096);
+	ret = remove_extent_item(root, nodesize, nodesize);
 	if (ret)
 		return -EINVAL;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -290,14 +294,14 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 0, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, 0, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
@@ -310,7 +314,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root)
  * right, also remove one of the roots and make sure the exclusive count is
  * adjusted properly.
  */
-static int test_multiple_refs(struct btrfs_root *root)
+static int test_multiple_refs(struct btrfs_root *root,
+		u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_trans_handle trans;
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -322,25 +327,29 @@ static int test_multiple_refs(struct btrfs_root *root)
 
 	test_msg("Qgroup multiple refs test\n");
 
-	/* We have 5 created already from the previous test */
-	ret = btrfs_create_qgroup(NULL, fs_info, 256);
+	/*
+	 * We have BTRFS_FS_TREE_OBJECTID created already from the
+	 * previous test.
+	 */
+	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
 		test_msg("Couldn't create a qgroup %d\n", ret);
 		return ret;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = insert_normal_tree_ref(root, 4096, 4096, 0, 5);
+	ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
+				BTRFS_FS_TREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -348,30 +357,32 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+				       nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = add_tree_ref(root, 4096, 4096, 0, 256);
+	ret = add_tree_ref(root, nodesize, nodesize, 0,
+			BTRFS_FIRST_FREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -379,35 +390,38 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+					nodesize, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 256, 4096, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+					nodesize, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &old_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		test_msg("Couldn't find old roots: %d\n", ret);
 		return ret;
 	}
 
-	ret = remove_extent_ref(root, 4096, 4096, 0, 256);
+	ret = remove_extent_ref(root, nodesize, nodesize, 0,
+				BTRFS_FIRST_FREE_OBJECTID);
 	if (ret)
 		return ret;
 
-	ret = btrfs_find_all_roots(&trans, fs_info, 4096, 0, &new_roots);
+	ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots);
 	if (ret) {
 		ulist_free(old_roots);
 		ulist_free(new_roots);
@@ -415,19 +429,21 @@ static int test_multiple_refs(struct btrfs_root *root)
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, 4096, 4096,
-					  old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
+					  nodesize, old_roots, new_roots);
 	if (ret) {
 		test_msg("Couldn't account space for a qgroup %d\n", ret);
 		return ret;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 256, 0, 0)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FIRST_FREE_OBJECTID,
+					0, 0)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
 
-	if (btrfs_verify_qgroup_counts(fs_info, 5, 4096, 4096)) {
+	if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
+					nodesize, nodesize)) {
 		test_msg("Qgroup counts didn't match expected values\n");
 		return -EINVAL;
 	}
@@ -435,13 +451,13 @@ static int test_multiple_refs(struct btrfs_root *root)
 	return 0;
 }
 
-int btrfs_test_qgroups(void)
+int btrfs_test_qgroups(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 	struct btrfs_root *tmp_root;
 	int ret = 0;
 
-	root = btrfs_alloc_dummy_root();
+	root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(root)) {
 		test_msg("Couldn't allocate root\n");
 		return PTR_ERR(root);
@@ -468,7 +484,8 @@ int btrfs_test_qgroups(void)
 	 * Can't use bytenr 0, some things freak out
 	 * *cough*backref walking code*cough*
 	 */
-	root->node = alloc_test_extent_buffer(root->fs_info, 4096);
+	root->node = alloc_test_extent_buffer(root->fs_info, nodesize,
+					nodesize);
 	if (!root->node) {
 		test_msg("Couldn't allocate dummy buffer\n");
 		ret = -ENOMEM;
@@ -476,16 +493,16 @@ int btrfs_test_qgroups(void)
 	}
 	btrfs_set_header_level(root->node, 0);
 	btrfs_set_header_nritems(root->node, 0);
-	root->alloc_bytenr += 8192;
+	root->alloc_bytenr += 2 * nodesize;
 
-	tmp_root = btrfs_alloc_dummy_root();
+	tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(tmp_root)) {
 		test_msg("Couldn't allocate a fs root\n");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
 
-	tmp_root->root_key.objectid = 5;
+	tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID;
 	root->fs_info->fs_root = tmp_root;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
@@ -493,14 +510,14 @@ int btrfs_test_qgroups(void)
 		goto out;
 	}
 
-	tmp_root = btrfs_alloc_dummy_root();
+	tmp_root = btrfs_alloc_dummy_root(sectorsize, nodesize);
 	if (IS_ERR(tmp_root)) {
 		test_msg("Couldn't allocate a fs root\n");
 		ret = PTR_ERR(tmp_root);
 		goto out;
 	}
 
-	tmp_root->root_key.objectid = 256;
+	tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID;
 	ret = btrfs_insert_fs_root(root->fs_info, tmp_root);
 	if (ret) {
 		test_msg("Couldn't insert fs root %d\n", ret);
@@ -508,10 +525,10 @@ int btrfs_test_qgroups(void)
 	}
 
 	test_msg("Running qgroup tests\n");
-	ret = test_no_shared_qgroup(root);
+	ret = test_no_shared_qgroup(root, sectorsize, nodesize);
 	if (ret)
 		goto out;
-	ret = test_multiple_refs(root);
+	ret = test_multiple_refs(root, sectorsize, nodesize);
 out:
 	btrfs_free_dummy_root(root);
 	return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 43885e51b..948aa186b 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -311,10 +311,11 @@ loop:
  * when the transaction commits
  */
 static int record_root_in_trans(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root)
+			       struct btrfs_root *root,
+			       int force)
 {
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    root->last_trans < trans->transid) {
+	if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+	    root->last_trans < trans->transid) || force) {
 		WARN_ON(root == root->fs_info->extent_root);
 		WARN_ON(root->commit_root != root->node);
 
@@ -331,7 +332,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
 		smp_wmb();
 
 		spin_lock(&root->fs_info->fs_roots_radix_lock);
-		if (root->last_trans == trans->transid) {
+		if (root->last_trans == trans->transid && !force) {
 			spin_unlock(&root->fs_info->fs_roots_radix_lock);
 			return 0;
 		}
@@ -402,7 +403,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 		return 0;
 
 	mutex_lock(&root->fs_info->reloc_mutex);
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	mutex_unlock(&root->fs_info->reloc_mutex);
 
 	return 0;
@@ -817,6 +818,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *info = root->fs_info;
+	u64 transid = trans->transid;
 	unsigned long cur = trans->delayed_ref_updates;
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
@@ -904,7 +906,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 	if (must_run_delayed_refs) {
-		btrfs_async_run_delayed_refs(root, cur,
+		btrfs_async_run_delayed_refs(root, cur, transid,
 					     must_run_delayed_refs == 1);
 	}
 	return err;
@@ -943,7 +945,7 @@ int btrfs_write_marked_extents(struct btrfs_root *root,
 
 		err = convert_extent_bit(dirty_pages, start, end,
 					 EXTENT_NEED_WAIT,
-					 mark, &cached_state, GFP_NOFS);
+					 mark, &cached_state);
 		/*
 		 * convert_extent_bit can return -ENOMEM, which is most of the
 		 * time a temporary error. So when it happens, ignore the error
@@ -1311,6 +1313,92 @@ int btrfs_defrag_root(struct btrfs_root *root)
 }
 
 /*
+ * Do all special snapshot related qgroup dirty hack.
+ *
+ * Will do all needed qgroup inherit and dirty hack like switch commit
+ * roots inside one transaction and write all btree into disk, to make
+ * qgroup works.
+ */
+static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *src,
+				   struct btrfs_root *parent,
+				   struct btrfs_qgroup_inherit *inherit,
+				   u64 dst_objectid)
+{
+	struct btrfs_fs_info *fs_info = src->fs_info;
+	int ret;
+
+	/*
+	 * Save some performance in the case that qgroups are not
+	 * enabled. If this check races with the ioctl, rescan will
+	 * kick in anyway.
+	 */
+	mutex_lock(&fs_info->qgroup_ioctl_lock);
+	if (!fs_info->quota_enabled) {
+		mutex_unlock(&fs_info->qgroup_ioctl_lock);
+		return 0;
+	}
+	mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+	/*
+	 * We are going to commit transaction, see btrfs_commit_transaction()
+	 * comment for reason locking tree_log_mutex
+	 */
+	mutex_lock(&fs_info->tree_log_mutex);
+
+	ret = commit_fs_roots(trans, src);
+	if (ret)
+		goto out;
+	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+	ret = btrfs_qgroup_account_extents(trans, fs_info);
+	if (ret < 0)
+		goto out;
+
+	/* Now qgroup are all updated, we can inherit it to new qgroups */
+	ret = btrfs_qgroup_inherit(trans, fs_info,
+				   src->root_key.objectid, dst_objectid,
+				   inherit);
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Now we do a simplified commit transaction, which will:
+	 * 1) commit all subvolume and extent tree
+	 *    To ensure all subvolume and extent tree have a valid
+	 *    commit_root to accounting later insert_dir_item()
+	 * 2) write all btree blocks onto disk
+	 *    This is to make sure later btree modification will be cowed
+	 *    Or commit_root can be populated and cause wrong qgroup numbers
+	 * In this simplified commit, we don't really care about other trees
+	 * like chunk and root tree, as they won't affect qgroup.
+	 * And we don't write super to avoid half committed status.
+	 */
+	ret = commit_cowonly_roots(trans, src);
+	if (ret)
+		goto out;
+	switch_commit_roots(trans->transaction, fs_info);
+	ret = btrfs_write_and_wait_transaction(trans, src);
+	if (ret)
+		btrfs_handle_fs_error(fs_info, ret,
+			"Error while writing out transaction for qgroup");
+
+out:
+	mutex_unlock(&fs_info->tree_log_mutex);
+
+	/*
+	 * Force parent root to be updated, as we recorded it before so its
+	 * last_trans == cur_transid.
+	 * Or it won't be committed again onto disk after later
+	 * insert_dir_item()
+	 */
+	if (!ret)
+		record_root_in_trans(trans, parent, 1);
+	return ret;
+}
+
+/*
  * new snapshots need to be created at a very specific time in the
  * transaction commit.  This does the actual creation.
  *
@@ -1383,7 +1471,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	dentry = pending->dentry;
 	parent_inode = pending->dir;
 	parent_root = BTRFS_I(parent_inode)->root;
-	record_root_in_trans(trans, parent_root);
+	record_root_in_trans(trans, parent_root, 0);
 
 	cur_time = current_fs_time(parent_inode->i_sb);
 
@@ -1420,7 +1508,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	record_root_in_trans(trans, root);
+	record_root_in_trans(trans, root, 0);
 	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);
@@ -1516,6 +1604,17 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
+	/*
+	 * Do special qgroup accounting for snapshot, as we do some qgroup
+	 * snapshot hack to do fast snapshot.
+	 * To co-operate with that hack, we do hack again.
+	 * Or snapshot will be greatly slowed down by a subtree qgroup rescan
+	 */
+	ret = qgroup_account_snapshot(trans, root, parent_root,
+				      pending->inherit, objectid);
+	if (ret < 0)
+		goto fail;
+
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				    dentry->d_name.name, dentry->d_name.len,
 				    parent_inode, &key,
@@ -1559,23 +1658,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	/*
-	 * account qgroup counters before qgroup_inherit()
-	 */
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_account_extents(trans, fs_info);
-	if (ret)
-		goto fail;
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   root->root_key.objectid,
-				   objectid, pending->inherit);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		goto fail;
-	}
-
 fail:
 	pending->error = ret;
 dir_item_existed:
@@ -1821,7 +1903,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
-		btrfs_wait_ordered_roots(fs_info, -1);
+		btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
 }
 
 static inline void
@@ -2145,7 +2227,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_write_and_wait_transaction(trans, root);
 	if (ret) {
-		btrfs_std_error(root->fs_info, ret,
+		btrfs_handle_fs_error(root->fs_info, ret,
 			    "Error while writing out transaction");
 		mutex_unlock(&root->fs_info->tree_log_mutex);
 		goto scrub_continue;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index c0b501a5a..c5abee4f0 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -144,7 +144,7 @@ struct btrfs_pending_snapshot {
 	/* block reservation for the operation */
 	struct btrfs_block_rsv block_rsv;
 	u64 qgroup_reserved;
-	/* extra metadata reseration for relocation */
+	/* extra metadata reservation for relocation */
 	int error;
 	bool readonly;
 	struct list_head list;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 517d0ccb3..c05f69a8e 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2330,7 +2330,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 				break;
 
 			/* for regular files, make sure corresponding
-			 * orhpan item exist. extents past the new EOF
+			 * orphan item exist. extents past the new EOF
 			 * will be truncated later by orphan cleanup.
 			 */
 			if (S_ISREG(mode)) {
@@ -2422,8 +2422,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		root_owner = btrfs_header_owner(parent);
 
 		next = btrfs_find_create_tree_block(root, bytenr);
-		if (!next)
-			return -ENOMEM;
+		if (IS_ERR(next))
+			return PTR_ERR(next);
 
 		if (*level == 1) {
 			ret = wc->process_func(root, next, wc, ptr_gen);
@@ -3001,7 +3001,7 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 			break;
 
 		clear_extent_bits(&log->dirty_log_pages, start, end,
-				  EXTENT_DIRTY | EXTENT_NEW, GFP_NOFS);
+				  EXTENT_DIRTY | EXTENT_NEW);
 	}
 
 	/*
@@ -4141,6 +4141,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 
 	INIT_LIST_HEAD(&extents);
 
+	down_write(&BTRFS_I(inode)->dio_sem);
 	write_lock(&tree->lock);
 	test_gen = root->fs_info->last_trans_committed;
 
@@ -4169,13 +4170,20 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
+	btrfs_get_logged_extents(inode, logged_list, start, end);
 	/*
-	 * Collect any new ordered extents within the range. This is to
-	 * prevent logging file extent items without waiting for the disk
-	 * location they point to being written. We do this only to deal
-	 * with races against concurrent lockless direct IO writes.
+	 * Some ordered extents started by fsync might have completed
+	 * before we could collect them into the list logged_list, which
+	 * means they're gone, not in our logged_list nor in the inode's
+	 * ordered tree. We want the application/user space to know an
+	 * error happened while attempting to persist file data so that
+	 * it can take proper action. If such error happened, we leave
+	 * without writing to the log tree and the fsync must report the
+	 * file data write error and not commit the current transaction.
 	 */
-	btrfs_get_logged_extents(inode, logged_list, start, end);
+	ret = btrfs_inode_check_errors(inode);
+	if (ret)
+		ctx->io_err = ret;
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4202,6 +4210,7 @@ process:
 	}
 	WARN_ON(!list_empty(&extents));
 	write_unlock(&tree->lock);
+	up_write(&BTRFS_I(inode)->dio_sem);
 
 	btrfs_release_path(path);
 	return ret;
@@ -4623,23 +4632,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	mutex_lock(&BTRFS_I(inode)->log_mutex);
 
 	/*
-	 * Collect ordered extents only if we are logging data. This is to
-	 * ensure a subsequent request to log this inode in LOG_INODE_ALL mode
-	 * will process the ordered extents if they still exists at the time,
-	 * because when we collect them we test and set for the flag
-	 * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the
-	 * same ordered extents. The consequence for the LOG_INODE_ALL log mode
-	 * not processing the ordered extents is that we end up logging the
-	 * corresponding file extent items, based on the extent maps in the
-	 * inode's extent_map_tree's modified_list, without logging the
-	 * respective checksums (since the may still be only attached to the
-	 * ordered extents and have not been inserted in the csum tree by
-	 * btrfs_finish_ordered_io() yet).
-	 */
-	if (inode_only == LOG_INODE_ALL)
-		btrfs_get_logged_extents(inode, &logged_list, start, end);
-
-	/*
 	 * a brute force approach to making sure we get the most uptodate
 	 * copies of everything.
 	 */
@@ -4846,21 +4838,6 @@ log_extents:
 			goto out_unlock;
 	}
 	if (fast_search) {
-		/*
-		 * Some ordered extents started by fsync might have completed
-		 * before we collected the ordered extents in logged_list, which
-		 * means they're gone, not in our logged_list nor in the inode's
-		 * ordered tree. We want the application/user space to know an
-		 * error happened while attempting to persist file data so that
-		 * it can take proper action. If such error happened, we leave
-		 * without writing to the log tree and the fsync must report the
-		 * file data write error and not commit the current transaction.
-		 */
-		err = btrfs_inode_check_errors(inode);
-		if (err) {
-			ctx->io_err = err;
-			goto out_unlock;
-		}
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
 						&logged_list, ctx, start, end);
 		if (ret) {
@@ -4937,7 +4914,7 @@ out_unlock:
  * the actual unlink operation, so if we do this check before a concurrent task
  * sets last_unlink_trans it means we've logged a consistent version/state of
  * all the inode items, otherwise we are not sure and must do a transaction
- * commit (the concurrent task migth have only updated last_unlink_trans before
+ * commit (the concurrent task might have only updated last_unlink_trans before
  * we logged the inode or it might have also done the unlink).
  */
 static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
@@ -4988,7 +4965,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			goto out;
 
 	if (!S_ISDIR(inode->i_mode)) {
-		if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			goto out;
 		inode = d_inode(parent);
 	}
@@ -4996,7 +4973,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 	while (1) {
 		/*
 		 * If we are logging a directory then we start with our inode,
-		 * not our parents inode, so we need to skipp setting the
+		 * not our parent's inode, so we need to skip setting the
 		 * logged_trans so that further down in the log code we don't
 		 * think this inode has already been logged.
 		 */
@@ -5009,7 +4986,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			break;
 		}
 
-		if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			break;
 
 		if (IS_ROOT(parent))
@@ -5158,7 +5135,7 @@ process_leaf:
 			}
 
 			ctx->log_new_dentries = false;
-			if (type == BTRFS_FT_DIR)
+			if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
 				log_mode = LOG_INODE_ALL;
 			btrfs_release_path(path);
 			ret = btrfs_log_inode(trans, root, di_inode,
@@ -5278,11 +5255,16 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 			if (IS_ERR(dir_inode))
 				continue;
 
+			if (ctx)
+				ctx->log_new_dentries = false;
 			ret = btrfs_log_inode(trans, root, dir_inode,
 					      LOG_INODE_ALL, 0, LLONG_MAX, ctx);
 			if (!ret &&
 			    btrfs_must_commit_transaction(trans, dir_inode))
 				ret = 1;
+			if (!ret && ctx && ctx->log_new_dentries)
+				ret = log_new_dir_dentries(trans, root,
+							   dir_inode, ctx);
 			iput(dir_inode);
 			if (ret)
 				goto out;
@@ -5375,7 +5357,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		log_dentries = true;
 
 	/*
-	 * On unlink we must make sure all our current and old parent directores
+	 * On unlink we must make sure all our current and old parent directory
 	 * inodes are fully logged. This is to prevent leaving dangling
 	 * directory index entries in directories that were our parents but are
 	 * not anymore. Not doing this results in old parent directory being
@@ -5422,7 +5404,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	}
 
 	while (1) {
-		if (!parent || d_really_is_negative(parent) || sb != d_inode(parent)->i_sb)
+		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			break;
 
 		inode = d_inode(parent);
@@ -5519,7 +5501,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 
 	ret = walk_log_tree(trans, log_root_tree, &wc);
 	if (ret) {
-		btrfs_std_error(fs_info, ret, "Failed to pin buffers while "
+		btrfs_handle_fs_error(fs_info, ret, "Failed to pin buffers while "
 			    "recovering log root tree.");
 		goto error;
 	}
@@ -5533,7 +5515,7 @@ again:
 		ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
 
 		if (ret < 0) {
-			btrfs_std_error(fs_info, ret,
+			btrfs_handle_fs_error(fs_info, ret,
 				    "Couldn't find tree log root.");
 			goto error;
 		}
@@ -5551,7 +5533,7 @@ again:
 		log = btrfs_read_fs_root(log_root_tree, &found_key);
 		if (IS_ERR(log)) {
 			ret = PTR_ERR(log);
-			btrfs_std_error(fs_info, ret,
+			btrfs_handle_fs_error(fs_info, ret,
 				    "Couldn't read tree log root.");
 			goto error;
 		}
@@ -5566,7 +5548,7 @@ again:
 			free_extent_buffer(log->node);
 			free_extent_buffer(log->commit_root);
 			kfree(log);
-			btrfs_std_error(fs_info, ret, "Couldn't read target root "
+			btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root "
 				    "for tree log recovery.");
 			goto error;
 		}
@@ -5652,11 +5634,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	 * into the file.  When the file is logged we check it and
 	 * don't log the parents if the file is fully on disk.
 	 */
-	if (S_ISREG(inode->i_mode)) {
-		mutex_lock(&BTRFS_I(inode)->log_mutex);
-		BTRFS_I(inode)->last_unlink_trans = trans->transid;
-		mutex_unlock(&BTRFS_I(inode)->log_mutex);
-	}
+	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	BTRFS_I(inode)->last_unlink_trans = trans->transid;
+	mutex_unlock(&BTRFS_I(inode)->log_mutex);
 
 	/*
 	 * if this directory was already logged any new
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index 91feb2bde..b1434bb57 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -28,7 +28,7 @@
  * }
  * ulist_free(ulist);
  *
- * This assumes the graph nodes are adressable by u64. This stems from the
+ * This assumes the graph nodes are addressable by u64. This stems from the
  * usage for tree enumeration in btrfs, where the logical addresses are
  * 64 bit.
  *
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bd0f45fb3..589f12817 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -20,13 +20,13 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
 #include <linux/iocontext.h>
 #include <linux/capability.h>
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/semaphore.h>
+#include <linux/uuid.h>
 #include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
@@ -118,6 +118,21 @@ const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID6]  = BTRFS_BLOCK_GROUP_RAID6,
 };
 
+/*
+ * Table to convert BTRFS_RAID_* to the error code if minimum number of devices
+ * condition is not met. Zero means there's no corresponding
+ * BTRFS_ERROR_DEV_*_NOT_MET value.
+ */
+const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
+	[BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
+	[BTRFS_RAID_RAID1]  = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
+	[BTRFS_RAID_DUP]    = 0,
+	[BTRFS_RAID_RAID0]  = 0,
+	[BTRFS_RAID_SINGLE] = 0,
+	[BTRFS_RAID_RAID5]  = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
+	[BTRFS_RAID_RAID6]  = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
+};
+
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				struct btrfs_device *device);
@@ -699,7 +714,8 @@ static noinline int device_list_add(const char *path,
 	 * if there is new btrfs on an already registered device,
 	 * then remove the stale device entry.
 	 */
-	btrfs_free_stale_device(device);
+	if (ret > 0)
+		btrfs_free_stale_device(device);
 
 	*fs_devices_ret = fs_devices;
 
@@ -988,6 +1004,56 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 	return ret;
 }
 
+void btrfs_release_disk_super(struct page *page)
+{
+	kunmap(page);
+	put_page(page);
+}
+
+int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
+		struct page **page, struct btrfs_super_block **disk_super)
+{
+	void *p;
+	pgoff_t index;
+
+	/* make sure our super fits in the device */
+	if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
+		return 1;
+
+	/* make sure our super fits in the page */
+	if (sizeof(**disk_super) > PAGE_SIZE)
+		return 1;
+
+	/* make sure our super doesn't straddle pages on disk */
+	index = bytenr >> PAGE_SHIFT;
+	if ((bytenr + sizeof(**disk_super) - 1) >> PAGE_SHIFT != index)
+		return 1;
+
+	/* pull in the page with our super */
+	*page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
+				   index, GFP_KERNEL);
+
+	if (IS_ERR_OR_NULL(*page))
+		return 1;
+
+	p = kmap(*page);
+
+	/* align our pointer to the offset of the super block */
+	*disk_super = p + (bytenr & ~PAGE_MASK);
+
+	if (btrfs_super_bytenr(*disk_super) != bytenr ||
+	    btrfs_super_magic(*disk_super) != BTRFS_MAGIC) {
+		btrfs_release_disk_super(*page);
+		return 1;
+	}
+
+	if ((*disk_super)->label[0] &&
+		(*disk_super)->label[BTRFS_LABEL_SIZE - 1])
+		(*disk_super)->label[BTRFS_LABEL_SIZE - 1] = '\0';
+
+	return 0;
+}
+
 /*
  * Look for a btrfs signature on a device. This may be called out of the mount path
  * and we are not allowed to call set_blocksize during the scan. The superblock
@@ -999,13 +1065,11 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	struct btrfs_super_block *disk_super;
 	struct block_device *bdev;
 	struct page *page;
-	void *p;
 	int ret = -EINVAL;
 	u64 devid;
 	u64 transid;
 	u64 total_devices;
 	u64 bytenr;
-	pgoff_t index;
 
 	/*
 	 * we would like to check all the supers, but that would make
@@ -1018,41 +1082,14 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	mutex_lock(&uuid_mutex);
 
 	bdev = blkdev_get_by_path(path, flags, holder);
-
 	if (IS_ERR(bdev)) {
 		ret = PTR_ERR(bdev);
 		goto error;
 	}
 
-	/* make sure our super fits in the device */
-	if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode))
-		goto error_bdev_put;
-
-	/* make sure our super fits in the page */
-	if (sizeof(*disk_super) > PAGE_SIZE)
-		goto error_bdev_put;
-
-	/* make sure our super doesn't straddle pages on disk */
-	index = bytenr >> PAGE_SHIFT;
-	if ((bytenr + sizeof(*disk_super) - 1) >> PAGE_SHIFT != index)
-		goto error_bdev_put;
-
-	/* pull in the page with our super */
-	page = read_cache_page_gfp(bdev->bd_inode->i_mapping,
-				   index, GFP_NOFS);
-
-	if (IS_ERR_OR_NULL(page))
+	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super))
 		goto error_bdev_put;
 
-	p = kmap(page);
-
-	/* align our pointer to the offset of the super block */
-	disk_super = p + (bytenr & ~PAGE_MASK);
-
-	if (btrfs_super_bytenr(disk_super) != bytenr ||
-	    btrfs_super_magic(disk_super) != BTRFS_MAGIC)
-		goto error_unmap;
-
 	devid = btrfs_stack_device_id(&disk_super->dev_item);
 	transid = btrfs_super_generation(disk_super);
 	total_devices = btrfs_super_num_devices(disk_super);
@@ -1060,8 +1097,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	ret = device_list_add(path, disk_super, devid, fs_devices_ret);
 	if (ret > 0) {
 		if (disk_super->label[0]) {
-			if (disk_super->label[BTRFS_LABEL_SIZE - 1])
-				disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
 			printk(KERN_INFO "BTRFS: device label %s ", disk_super->label);
 		} else {
 			printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid);
@@ -1073,9 +1108,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	if (!ret && fs_devices_ret)
 		(*fs_devices_ret)->total_devices = total_devices;
 
-error_unmap:
-	kunmap(page);
-	put_page(page);
+	btrfs_release_disk_super(page);
 
 error_bdev_put:
 	blkdev_put(bdev, flags);
@@ -1454,7 +1487,7 @@ again:
 		extent = btrfs_item_ptr(leaf, path->slots[0],
 					struct btrfs_dev_extent);
 	} else {
-		btrfs_std_error(root->fs_info, ret, "Slot search failed");
+		btrfs_handle_fs_error(root->fs_info, ret, "Slot search failed");
 		goto out;
 	}
 
@@ -1462,7 +1495,7 @@ again:
 
 	ret = btrfs_del_item(trans, root, path);
 	if (ret) {
-		btrfs_std_error(root->fs_info, ret,
+		btrfs_handle_fs_error(root->fs_info, ret,
 			    "Failed to remove dev extent item");
 	} else {
 		set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags);
@@ -1688,32 +1721,92 @@ out:
 	return ret;
 }
 
-int btrfs_rm_device(struct btrfs_root *root, char *device_path)
+/*
+ * Verify that @num_devices satisfies the RAID profile constraints in the whole
+ * filesystem. It's up to the caller to adjust that number regarding eg. device
+ * replace.
+ */
+static int btrfs_check_raid_min_devices(struct btrfs_fs_info *fs_info,
+		u64 num_devices)
+{
+	u64 all_avail;
+	unsigned seq;
+	int i;
+
+	do {
+		seq = read_seqbegin(&fs_info->profiles_lock);
+
+		all_avail = fs_info->avail_data_alloc_bits |
+			    fs_info->avail_system_alloc_bits |
+			    fs_info->avail_metadata_alloc_bits;
+	} while (read_seqretry(&fs_info->profiles_lock, seq));
+
+	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+		if (!(all_avail & btrfs_raid_group[i]))
+			continue;
+
+		if (num_devices < btrfs_raid_array[i].devs_min) {
+			int ret = btrfs_raid_mindev_error[i];
+
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+struct btrfs_device *btrfs_find_next_active_device(struct btrfs_fs_devices *fs_devs,
+					struct btrfs_device *device)
 {
-	struct btrfs_device *device;
 	struct btrfs_device *next_device;
-	struct block_device *bdev;
-	struct buffer_head *bh = NULL;
-	struct btrfs_super_block *disk_super;
+
+	list_for_each_entry(next_device, &fs_devs->devices, dev_list) {
+		if (next_device != device &&
+			!next_device->missing && next_device->bdev)
+			return next_device;
+	}
+
+	return NULL;
+}
+
+/*
+ * Helper function to check if the given device is part of s_bdev / latest_bdev
+ * and replace it with the provided or the next active device, in the context
+ * where this function called, there should be always be another device (or
+ * this_dev) which is active.
+ */
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *device, struct btrfs_device *this_dev)
+{
+	struct btrfs_device *next_device;
+
+	if (this_dev)
+		next_device = this_dev;
+	else
+		next_device = btrfs_find_next_active_device(fs_info->fs_devices,
+								device);
+	ASSERT(next_device);
+
+	if (fs_info->sb->s_bdev &&
+			(fs_info->sb->s_bdev == device->bdev))
+		fs_info->sb->s_bdev = next_device->bdev;
+
+	if (fs_info->fs_devices->latest_bdev == device->bdev)
+		fs_info->fs_devices->latest_bdev = next_device->bdev;
+}
+
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid)
+{
+	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
-	u64 all_avail;
-	u64 devid;
 	u64 num_devices;
-	u8 *dev_uuid;
-	unsigned seq;
 	int ret = 0;
 	bool clear_super = false;
+	char *dev_name = NULL;
 
 	mutex_lock(&uuid_mutex);
 
-	do {
-		seq = read_seqbegin(&root->fs_info->profiles_lock);
-
-		all_avail = root->fs_info->avail_data_alloc_bits |
-			    root->fs_info->avail_system_alloc_bits |
-			    root->fs_info->avail_metadata_alloc_bits;
-	} while (read_seqretry(&root->fs_info->profiles_lock, seq));
-
 	num_devices = root->fs_info->fs_devices->num_devices;
 	btrfs_dev_replace_lock(&root->fs_info->dev_replace, 0);
 	if (btrfs_dev_replace_is_ongoing(&root->fs_info->dev_replace)) {
@@ -1722,78 +1815,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	}
 	btrfs_dev_replace_unlock(&root->fs_info->dev_replace, 0);
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && num_devices <= 4) {
-		ret = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET;
-		goto out;
-	}
-
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && num_devices <= 2) {
-		ret = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET;
+	ret = btrfs_check_raid_min_devices(root->fs_info, num_devices - 1);
+	if (ret)
 		goto out;
-	}
 
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID5) &&
-	    root->fs_info->fs_devices->rw_devices <= 2) {
-		ret = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET;
-		goto out;
-	}
-	if ((all_avail & BTRFS_BLOCK_GROUP_RAID6) &&
-	    root->fs_info->fs_devices->rw_devices <= 3) {
-		ret = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET;
+	ret = btrfs_find_device_by_devspec(root, devid, device_path,
+				&device);
+	if (ret)
 		goto out;
-	}
-
-	if (strcmp(device_path, "missing") == 0) {
-		struct list_head *devices;
-		struct btrfs_device *tmp;
-
-		device = NULL;
-		devices = &root->fs_info->fs_devices->devices;
-		/*
-		 * It is safe to read the devices since the volume_mutex
-		 * is held.
-		 */
-		list_for_each_entry(tmp, devices, dev_list) {
-			if (tmp->in_fs_metadata &&
-			    !tmp->is_tgtdev_for_dev_replace &&
-			    !tmp->bdev) {
-				device = tmp;
-				break;
-			}
-		}
-		bdev = NULL;
-		bh = NULL;
-		disk_super = NULL;
-		if (!device) {
-			ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND;
-			goto out;
-		}
-	} else {
-		ret = btrfs_get_bdev_and_sb(device_path,
-					    FMODE_WRITE | FMODE_EXCL,
-					    root->fs_info->bdev_holder, 0,
-					    &bdev, &bh);
-		if (ret)
-			goto out;
-		disk_super = (struct btrfs_super_block *)bh->b_data;
-		devid = btrfs_stack_device_id(&disk_super->dev_item);
-		dev_uuid = disk_super->dev_item.uuid;
-		device = btrfs_find_device(root->fs_info, devid, dev_uuid,
-					   disk_super->fsid);
-		if (!device) {
-			ret = -ENOENT;
-			goto error_brelse;
-		}
-	}
 
 	if (device->is_tgtdev_for_dev_replace) {
 		ret = BTRFS_ERROR_DEV_TGT_REPLACE;
-		goto error_brelse;
+		goto out;
 	}
 
 	if (device->writeable && root->fs_info->fs_devices->rw_devices == 1) {
 		ret = BTRFS_ERROR_DEV_ONLY_WRITABLE;
-		goto error_brelse;
+		goto out;
 	}
 
 	if (device->writeable) {
@@ -1801,6 +1839,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 		list_del_init(&device->dev_alloc_list);
 		device->fs_devices->rw_devices--;
 		unlock_chunks(root);
+		dev_name = kstrdup(device->name->str, GFP_KERNEL);
+		if (!dev_name) {
+			ret = -ENOMEM;
+			goto error_undo;
+		}
 		clear_super = true;
 	}
 
@@ -1842,12 +1885,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->missing)
 		device->fs_devices->missing_devices--;
 
-	next_device = list_entry(root->fs_info->fs_devices->devices.next,
-				 struct btrfs_device, dev_list);
-	if (device->bdev == root->fs_info->sb->s_bdev)
-		root->fs_info->sb->s_bdev = next_device->bdev;
-	if (device->bdev == root->fs_info->fs_devices->latest_bdev)
-		root->fs_info->fs_devices->latest_bdev = next_device->bdev;
+	btrfs_assign_next_active_device(root->fs_info, device, NULL);
 
 	if (device->bdev) {
 		device->fs_devices->open_devices--;
@@ -1883,63 +1921,23 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	 * at this point, the device is zero sized.  We want to
 	 * remove it from the devices list and zero out the old super
 	 */
-	if (clear_super && disk_super) {
-		u64 bytenr;
-		int i;
-
-		/* make sure this device isn't detected as part of
-		 * the FS anymore
-		 */
-		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-		set_buffer_dirty(bh);
-		sync_dirty_buffer(bh);
-
-		/* clear the mirror copies of super block on the disk
-		 * being removed, 0th copy is been taken care above and
-		 * the below would take of the rest
-		 */
-		for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) {
-			bytenr = btrfs_sb_offset(i);
-			if (bytenr + BTRFS_SUPER_INFO_SIZE >=
-					i_size_read(bdev->bd_inode))
-				break;
-
-			brelse(bh);
-			bh = __bread(bdev, bytenr / 4096,
-					BTRFS_SUPER_INFO_SIZE);
-			if (!bh)
-				continue;
-
-			disk_super = (struct btrfs_super_block *)bh->b_data;
-
-			if (btrfs_super_bytenr(disk_super) != bytenr ||
-				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
-				continue;
-			}
-			memset(&disk_super->magic, 0,
-						sizeof(disk_super->magic));
-			set_buffer_dirty(bh);
-			sync_dirty_buffer(bh);
+	if (clear_super) {
+		struct block_device *bdev;
+
+		bdev = blkdev_get_by_path(dev_name, FMODE_READ | FMODE_EXCL,
+						root->fs_info->bdev_holder);
+		if (!IS_ERR(bdev)) {
+			btrfs_scratch_superblocks(bdev, dev_name);
+			blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 		}
 	}
 
-	ret = 0;
-
-	if (bdev) {
-		/* Notify udev that device has changed */
-		btrfs_kobject_uevent(bdev, KOBJ_CHANGE);
-
-		/* Update ctime/mtime for device path for libblkid */
-		update_dev_time(device_path);
-	}
-
-error_brelse:
-	brelse(bh);
-	if (bdev)
-		blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
 out:
+	kfree(dev_name);
+
 	mutex_unlock(&uuid_mutex);
 	return ret;
+
 error_undo:
 	if (device->writeable) {
 		lock_chunks(root);
@@ -1948,7 +1946,7 @@ error_undo:
 		device->fs_devices->rw_devices++;
 		unlock_chunks(root);
 	}
-	goto error_brelse;
+	goto out;
 }
 
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
@@ -1972,11 +1970,8 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
 	if (srcdev->missing)
 		fs_devices->missing_devices--;
 
-	if (srcdev->writeable) {
+	if (srcdev->writeable)
 		fs_devices->rw_devices--;
-		/* zero out the old super if it is writable */
-		btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
-	}
 
 	if (srcdev->bdev)
 		fs_devices->open_devices--;
@@ -1987,6 +1982,10 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_fs_devices *fs_devices = srcdev->fs_devices;
 
+	if (srcdev->writeable) {
+		/* zero out the old super if it is writable */
+		btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
+	}
 	call_rcu(&srcdev->rcu, free_device);
 
 	/*
@@ -2016,32 +2015,33 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *tgtdev)
 {
-	struct btrfs_device *next_device;
-
 	mutex_lock(&uuid_mutex);
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
 
-	if (tgtdev->bdev) {
-		btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+	if (tgtdev->bdev)
 		fs_info->fs_devices->open_devices--;
-	}
+
 	fs_info->fs_devices->num_devices--;
 
-	next_device = list_entry(fs_info->fs_devices->devices.next,
-				 struct btrfs_device, dev_list);
-	if (tgtdev->bdev == fs_info->sb->s_bdev)
-		fs_info->sb->s_bdev = next_device->bdev;
-	if (tgtdev->bdev == fs_info->fs_devices->latest_bdev)
-		fs_info->fs_devices->latest_bdev = next_device->bdev;
-	list_del_rcu(&tgtdev->dev_list);
+	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
 
-	call_rcu(&tgtdev->rcu, free_device);
+	list_del_rcu(&tgtdev->dev_list);
 
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 	mutex_unlock(&uuid_mutex);
+
+	/*
+	 * The update_dev_time() with in btrfs_scratch_superblocks()
+	 * may lead to a call to btrfs_show_devname() which will try
+	 * to hold device_list_mutex. And here this device
+	 * is already out of device list, so we don't have to hold
+	 * the device_list_mutex lock.
+	 */
+	btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+	call_rcu(&tgtdev->rcu, free_device);
 }
 
 static int btrfs_find_device_by_path(struct btrfs_root *root, char *device_path,
@@ -2102,6 +2102,31 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
 }
 
 /*
+ * Lookup a device given by device id, or the path if the id is 0.
+ */
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+					 char *devpath,
+					 struct btrfs_device **device)
+{
+	int ret;
+
+	if (devid) {
+		ret = 0;
+		*device = btrfs_find_device(root->fs_info, devid, NULL,
+					    NULL);
+		if (!*device)
+			ret = -ENOENT;
+	} else {
+		if (!devpath || !devpath[0])
+			return -EINVAL;
+
+		ret = btrfs_find_device_missing_or_by_path(root, devpath,
+							   device);
+	}
+	return ret;
+}
+
+/*
  * does all the dirty work required for changing file system's UUID.
  */
 static int btrfs_prepare_sprout(struct btrfs_root *root)
@@ -2165,7 +2190,7 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
 }
 
 /*
- * strore the expected generation for seed devices in device items.
+ * Store the expected generation for seed devices in device items.
  */
 static int btrfs_finish_sprout(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root)
@@ -2418,7 +2443,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 
 		ret = btrfs_relocate_sys_chunks(root);
 		if (ret < 0)
-			btrfs_std_error(root->fs_info, ret,
+			btrfs_handle_fs_error(root->fs_info, ret,
 				    "Failed to relocate sys chunks after "
 				    "device initialization. This can be fixed "
 				    "using the \"btrfs balance\" command.");
@@ -2663,7 +2688,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
 	if (ret < 0)
 		goto out;
 	else if (ret > 0) { /* Logic error or corruption */
-		btrfs_std_error(root->fs_info, -ENOENT,
+		btrfs_handle_fs_error(root->fs_info, -ENOENT,
 			    "Failed lookup while freeing chunk.");
 		ret = -ENOENT;
 		goto out;
@@ -2671,7 +2696,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_del_item(trans, root, path);
 	if (ret < 0)
-		btrfs_std_error(root->fs_info, ret,
+		btrfs_handle_fs_error(root->fs_info, ret,
 			    "Failed to delete chunk item.");
 out:
 	btrfs_free_path(path);
@@ -2736,6 +2761,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	u64 dev_extent_len = 0;
 	u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
 	int i, ret = 0;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
 
 	/* Just in case */
 	root = root->fs_info->chunk_root;
@@ -2762,12 +2788,19 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	check_system_chunk(trans, extent_root, map->type);
 	unlock_chunks(root->fs_info->chunk_root);
 
+	/*
+	 * Take the device list mutex to prevent races with the final phase of
+	 * a device replace operation that replaces the device object associated
+	 * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+	 */
+	mutex_lock(&fs_devices->device_list_mutex);
 	for (i = 0; i < map->num_stripes; i++) {
 		struct btrfs_device *device = map->stripes[i].dev;
 		ret = btrfs_free_dev_extent(trans, device,
 					    map->stripes[i].physical,
 					    &dev_extent_len);
 		if (ret) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			btrfs_abort_transaction(trans, root, ret);
 			goto out;
 		}
@@ -2786,11 +2819,14 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		if (map->stripes[i].dev) {
 			ret = btrfs_update_device(trans, map->stripes[i].dev);
 			if (ret) {
+				mutex_unlock(&fs_devices->device_list_mutex);
 				btrfs_abort_transaction(trans, root, ret);
 				goto out;
 			}
 		}
 	}
+	mutex_unlock(&fs_devices->device_list_mutex);
+
 	ret = btrfs_free_chunk(trans, root, chunk_objectid, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, root, ret);
@@ -2857,7 +2893,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
 						     chunk_offset);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_std_error(root->fs_info, ret, NULL);
+		btrfs_handle_fs_error(root->fs_info, ret, NULL);
 		return ret;
 	}
 
@@ -3362,7 +3398,7 @@ static int should_balance_chunk(struct btrfs_root *root,
 	} else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
 		/*
 		 * Same logic as the 'limit' filter; the minimum cannot be
-		 * determined here because we do not have the global informatoin
+		 * determined here because we do not have the global information
 		 * about the count of all chunks that satisfy the filters.
 		 */
 		if (bargs->limit_max == 0)
@@ -3402,6 +3438,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	u32 count_meta = 0;
 	u32 count_sys = 0;
 	int chunk_reserved = 0;
+	u64 bytes_used = 0;
 
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
@@ -3540,7 +3577,13 @@ again:
 			goto loop;
 		}
 
-		if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) && !chunk_reserved) {
+		ASSERT(fs_info->data_sinfo);
+		spin_lock(&fs_info->data_sinfo->lock);
+		bytes_used = fs_info->data_sinfo->bytes_used;
+		spin_unlock(&fs_info->data_sinfo->lock);
+
+		if ((chunk_type & BTRFS_BLOCK_GROUP_DATA) &&
+		    !chunk_reserved && !bytes_used) {
 			trans = btrfs_start_transaction(chunk_root, 0);
 			if (IS_ERR(trans)) {
 				mutex_unlock(&fs_info->delete_unused_bgs_mutex);
@@ -3632,7 +3675,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info)
 	unset_balance_control(fs_info);
 	ret = del_balance_item(fs_info->tree_root);
 	if (ret)
-		btrfs_std_error(fs_info, ret, NULL);
+		btrfs_handle_fs_error(fs_info, ret, NULL);
 
 	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
 }
@@ -3693,10 +3736,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		num_devices--;
 	}
 	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
-	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-	if (num_devices == 1)
-		allowed |= BTRFS_BLOCK_GROUP_DUP;
-	else if (num_devices > 1)
+	allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE | BTRFS_BLOCK_GROUP_DUP;
+	if (num_devices > 1)
 		allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1);
 	if (num_devices > 2)
 		allowed |= BTRFS_BLOCK_GROUP_RAID5;
@@ -4200,6 +4241,7 @@ int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
 	if (IS_ERR(uuid_root)) {
 		ret = PTR_ERR(uuid_root);
 		btrfs_abort_transaction(trans, tree_root, ret);
+		btrfs_end_transaction(trans, tree_root);
 		return ret;
 	}
 
@@ -4652,12 +4694,12 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_RAID5) {
 		raid_stripe_len = find_raid56_stripe_len(ndevs - 1,
-				 btrfs_super_stripesize(info->super_copy));
+						extent_root->stripesize);
 		data_stripes = num_stripes - 1;
 	}
 	if (type & BTRFS_BLOCK_GROUP_RAID6) {
 		raid_stripe_len = find_raid56_stripe_len(ndevs - 2,
-				 btrfs_super_stripesize(info->super_copy));
+						extent_root->stripesize);
 		data_stripes = num_stripes - 2;
 	}
 
@@ -5278,7 +5320,15 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 	stripe_nr = div64_u64(stripe_nr, stripe_len);
 
 	stripe_offset = stripe_nr * stripe_len;
-	BUG_ON(offset < stripe_offset);
+	if (offset < stripe_offset) {
+		btrfs_crit(fs_info, "stripe math has gone wrong, "
+			   "stripe_offset=%llu, offset=%llu, start=%llu, "
+			   "logical=%llu, stripe_len=%llu",
+			   stripe_offset, offset, em->start, logical,
+			   stripe_len);
+		free_extent_map(em);
+		return -EINVAL;
+	}
 
 	/* stripe_offset is the offset of this block in its stripe*/
 	stripe_offset = offset - stripe_offset;
@@ -5519,7 +5569,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 				&stripe_index);
 		mirror_num = stripe_index + 1;
 	}
-	BUG_ON(stripe_index >= map->num_stripes);
+	if (stripe_index >= map->num_stripes) {
+		btrfs_crit(fs_info, "stripe index math went horribly wrong, "
+			   "got stripe_index=%u, num_stripes=%u",
+			   stripe_index, map->num_stripes);
+		ret = -EINVAL;
+		goto out;
+	}
 
 	num_alloc_stripes = num_stripes;
 	if (dev_replace_is_ongoing) {
@@ -5718,20 +5774,17 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
 			}
 		}
 		if (found) {
-			if (physical_of_found + map->stripe_len <=
-			    dev_replace->cursor_left) {
-				struct btrfs_bio_stripe *tgtdev_stripe =
-					bbio->stripes + num_stripes;
+			struct btrfs_bio_stripe *tgtdev_stripe =
+				bbio->stripes + num_stripes;
 
-				tgtdev_stripe->physical = physical_of_found;
-				tgtdev_stripe->length =
-					bbio->stripes[index_srcdev].length;
-				tgtdev_stripe->dev = dev_replace->tgtdev;
-				bbio->tgtdev_map[index_srcdev] = num_stripes;
+			tgtdev_stripe->physical = physical_of_found;
+			tgtdev_stripe->length =
+				bbio->stripes[index_srcdev].length;
+			tgtdev_stripe->dev = dev_replace->tgtdev;
+			bbio->tgtdev_map[index_srcdev] = num_stripes;
 
-				tgtdev_indexes++;
-				num_stripes++;
-			}
+			tgtdev_indexes++;
+			num_stripes++;
 		}
 	}
 
@@ -6032,7 +6085,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 {
 	atomic_inc(&bbio->error);
 	if (atomic_dec_and_test(&bbio->stripes_pending)) {
-		/* Shoud be the original bio. */
+		/* Should be the original bio. */
 		WARN_ON(bio != bbio->orig_bio);
 
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -6206,27 +6259,23 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	return dev;
 }
 
-static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
-			  struct extent_buffer *leaf,
-			  struct btrfs_chunk *chunk)
+/* Return -EIO if any error, otherwise return 0. */
+static int btrfs_check_chunk_valid(struct btrfs_root *root,
+				   struct extent_buffer *leaf,
+				   struct btrfs_chunk *chunk, u64 logical)
 {
-	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
-	struct map_lookup *map;
-	struct extent_map *em;
-	u64 logical;
 	u64 length;
 	u64 stripe_len;
-	u64 devid;
-	u8 uuid[BTRFS_UUID_SIZE];
-	int num_stripes;
-	int ret;
-	int i;
+	u16 num_stripes;
+	u16 sub_stripes;
+	u64 type;
 
-	logical = key->offset;
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
 	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
-	/* Validation check */
+	sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	type = btrfs_chunk_type(leaf, chunk);
+
 	if (!num_stripes) {
 		btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
 			  num_stripes);
@@ -6237,24 +6286,70 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			  "invalid chunk logical %llu", logical);
 		return -EIO;
 	}
+	if (btrfs_chunk_sector_size(leaf, chunk) != root->sectorsize) {
+		btrfs_err(root->fs_info, "invalid chunk sectorsize %u",
+			  btrfs_chunk_sector_size(leaf, chunk));
+		return -EIO;
+	}
 	if (!length || !IS_ALIGNED(length, root->sectorsize)) {
 		btrfs_err(root->fs_info,
 			"invalid chunk length %llu", length);
 		return -EIO;
 	}
-	if (!is_power_of_2(stripe_len)) {
+	if (!is_power_of_2(stripe_len) || stripe_len != BTRFS_STRIPE_LEN) {
 		btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
 			  stripe_len);
 		return -EIO;
 	}
 	if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
-	    btrfs_chunk_type(leaf, chunk)) {
+	    type) {
 		btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
 			  ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
 			    BTRFS_BLOCK_GROUP_PROFILE_MASK) &
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
+	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) ||
+	    ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
+	     num_stripes != 1)) {
+		btrfs_err(root->fs_info,
+			"invalid num_stripes:sub_stripes %u:%u for profile %llu",
+			num_stripes, sub_stripes,
+			type & BTRFS_BLOCK_GROUP_PROFILE_MASK);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
+			  struct extent_buffer *leaf,
+			  struct btrfs_chunk *chunk)
+{
+	struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree;
+	struct map_lookup *map;
+	struct extent_map *em;
+	u64 logical;
+	u64 length;
+	u64 stripe_len;
+	u64 devid;
+	u8 uuid[BTRFS_UUID_SIZE];
+	int num_stripes;
+	int ret;
+	int i;
+
+	logical = key->offset;
+	length = btrfs_chunk_length(leaf, chunk);
+	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+	num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+
+	ret = btrfs_check_chunk_valid(root, leaf, chunk, logical);
+	if (ret)
+		return ret;
 
 	read_lock(&map_tree->map_tree.lock);
 	em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6502,6 +6597,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	u32 array_size;
 	u32 len = 0;
 	u32 cur_offset;
+	u64 type;
 	struct btrfs_key key;
 
 	ASSERT(BTRFS_SUPER_INFO_SIZE <= root->nodesize);
@@ -6511,12 +6607,12 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 	 * overallocate but we can keep it as-is, only the first page is used.
 	 */
 	sb = btrfs_find_create_tree_block(root, BTRFS_SUPER_INFO_OFFSET);
-	if (!sb)
-		return -ENOMEM;
+	if (IS_ERR(sb))
+		return PTR_ERR(sb);
 	set_extent_buffer_uptodate(sb);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
 	/*
-	 * The sb extent buffer is artifical and just used to read the system array.
+	 * The sb extent buffer is artificial and just used to read the system array.
 	 * set_extent_buffer_uptodate() call does not properly mark all it's
 	 * pages up-to-date when the page is larger: extent does not cover the
 	 * whole page and consequently check_page_uptodate does not find all
@@ -6568,6 +6664,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 				break;
 			}
 
+			type = btrfs_chunk_type(sb, chunk);
+			if ((type & BTRFS_BLOCK_GROUP_SYSTEM) == 0) {
+				btrfs_err(root->fs_info,
+			    "invalid chunk type %llu in sys_array at offset %u",
+					type, cur_offset);
+				ret = -EIO;
+				break;
+			}
+
 			len = btrfs_chunk_item_size(num_stripes);
 			if (cur_offset + len > array_size)
 				goto out_short_read;
@@ -6586,13 +6691,15 @@ int btrfs_read_sys_array(struct btrfs_root *root)
 		sb_array_offset += len;
 		cur_offset += len;
 	}
-	free_extent_buffer(sb);
+	clear_extent_buffer_uptodate(sb);
+	free_extent_buffer_stale(sb);
 	return ret;
 
 out_short_read:
 	printk(KERN_ERR "BTRFS: sys_array too short to read %u bytes at offset %u\n",
 			len, cur_offset);
-	free_extent_buffer(sb);
+	clear_extent_buffer_uptodate(sb);
+	free_extent_buffer_stale(sb);
 	return -EIO;
 }
 
@@ -6604,6 +6711,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 	struct btrfs_key found_key;
 	int ret;
 	int slot;
+	u64 total_dev = 0;
 
 	root = root->fs_info->chunk_root;
 
@@ -6645,6 +6753,7 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 			ret = read_one_dev(root, leaf, dev_item);
 			if (ret)
 				goto error;
+			total_dev++;
 		} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
 			struct btrfs_chunk *chunk;
 			chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
@@ -6654,6 +6763,28 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 		}
 		path->slots[0]++;
 	}
+
+	/*
+	 * After loading chunk tree, we've got all device information,
+	 * do another round of validation checks.
+	 */
+	if (total_dev != root->fs_info->fs_devices->total_devices) {
+		btrfs_err(root->fs_info,
+	   "super_num_devices %llu mismatch with num_devices %llu found here",
+			  btrfs_super_num_devices(root->fs_info->super_copy),
+			  total_dev);
+		ret = -EINVAL;
+		goto error;
+	}
+	if (btrfs_super_total_bytes(root->fs_info->super_copy) <
+	    root->fs_info->fs_devices->total_rw_bytes) {
+		btrfs_err(root->fs_info,
+	"super_total_bytes %llu mismatch with fs_devices total_rw_bytes %llu",
+			  btrfs_super_total_bytes(root->fs_info->super_copy),
+			  root->fs_info->fs_devices->total_rw_bytes);
+		ret = -EINVAL;
+		goto error;
+	}
 	ret = 0;
 error:
 	unlock_chunks(root);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1939ebde6..0ac90f8d8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -340,14 +340,14 @@ struct btrfs_raid_attr {
 };
 
 extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];
-
+extern const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES];
 extern const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES];
 
 struct map_lookup {
 	u64 type;
 	int io_align;
 	int io_width;
-	int stripe_len;
+	u64 stripe_len;
 	int sector_size;
 	int num_stripes;
 	int sub_stripes;
@@ -357,52 +357,6 @@ struct map_lookup {
 #define map_lookup_size(n) (sizeof(struct map_lookup) + \
 			    (sizeof(struct btrfs_bio_stripe) * (n)))
 
-/*
- * Restriper's general type filter
- */
-#define BTRFS_BALANCE_DATA		(1ULL << 0)
-#define BTRFS_BALANCE_SYSTEM		(1ULL << 1)
-#define BTRFS_BALANCE_METADATA		(1ULL << 2)
-
-#define BTRFS_BALANCE_TYPE_MASK		(BTRFS_BALANCE_DATA |	    \
-					 BTRFS_BALANCE_SYSTEM |	    \
-					 BTRFS_BALANCE_METADATA)
-
-#define BTRFS_BALANCE_FORCE		(1ULL << 3)
-#define BTRFS_BALANCE_RESUME		(1ULL << 4)
-
-/*
- * Balance filters
- */
-#define BTRFS_BALANCE_ARGS_PROFILES	(1ULL << 0)
-#define BTRFS_BALANCE_ARGS_USAGE	(1ULL << 1)
-#define BTRFS_BALANCE_ARGS_DEVID	(1ULL << 2)
-#define BTRFS_BALANCE_ARGS_DRANGE	(1ULL << 3)
-#define BTRFS_BALANCE_ARGS_VRANGE	(1ULL << 4)
-#define BTRFS_BALANCE_ARGS_LIMIT	(1ULL << 5)
-#define BTRFS_BALANCE_ARGS_LIMIT_RANGE	(1ULL << 6)
-#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE	(1ULL << 10)
-
-#define BTRFS_BALANCE_ARGS_MASK			\
-	(BTRFS_BALANCE_ARGS_PROFILES |		\
-	 BTRFS_BALANCE_ARGS_USAGE |		\
-	 BTRFS_BALANCE_ARGS_DEVID | 		\
-	 BTRFS_BALANCE_ARGS_DRANGE |		\
-	 BTRFS_BALANCE_ARGS_VRANGE |		\
-	 BTRFS_BALANCE_ARGS_LIMIT |		\
-	 BTRFS_BALANCE_ARGS_LIMIT_RANGE |	\
-	 BTRFS_BALANCE_ARGS_STRIPES_RANGE |	\
-	 BTRFS_BALANCE_ARGS_USAGE_RANGE)
-
-/*
- * Profile changing flags.  When SOFT is set we won't relocate chunk if
- * it already has the target profile (even though it may be
- * half-filled).
- */
-#define BTRFS_BALANCE_ARGS_CONVERT	(1ULL << 8)
-#define BTRFS_BALANCE_ARGS_SOFT		(1ULL << 9)
-
 struct btrfs_balance_args;
 struct btrfs_balance_progress;
 struct btrfs_balance_control {
@@ -445,13 +399,18 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 			  struct btrfs_fs_devices **fs_devices_ret);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
+void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *device, struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
 					 char *device_path,
 					 struct btrfs_device **device);
+int btrfs_find_device_by_devspec(struct btrfs_root *root, u64 devid,
+					 char *devpath,
+					 struct btrfs_device **device);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
-int btrfs_rm_device(struct btrfs_root *root, char *device_path);
+int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid);
 void btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 145d2b89e..d1a177a3d 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -237,6 +237,9 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
+	if (btrfs_root_readonly(root))
+		return -EROFS;
+
 	if (trans)
 		return do_setxattr(trans, inode, name, value, size, flags);
 
@@ -369,33 +372,29 @@ err:
 }
 
 static int btrfs_xattr_handler_get(const struct xattr_handler *handler,
-				   struct dentry *dentry, const char *name,
-				   void *buffer, size_t size)
+				   struct dentry *unused, struct inode *inode,
+				   const char *name, void *buffer, size_t size)
 {
-	struct inode *inode = d_inode(dentry);
-
 	name = xattr_full_name(handler, name);
 	return __btrfs_getxattr(inode, name, buffer, size);
 }
 
 static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
-				   struct dentry *dentry, const char *name,
-				   const void *buffer, size_t size,
-				   int flags)
+				   struct dentry *unused, struct inode *inode,
+				   const char *name, const void *buffer,
+				   size_t size, int flags)
 {
-	struct inode *inode = d_inode(dentry);
-
 	name = xattr_full_name(handler, name);
 	return __btrfs_setxattr(NULL, inode, name, buffer, size, flags);
 }
 
 static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
-					struct dentry *dentry,
+					struct dentry *unused, struct inode *inode,
 					const char *name, const void *value,
 					size_t size, int flags)
 {
 	name = xattr_full_name(handler, name);
-	return btrfs_set_prop(d_inode(dentry), name, value, size, flags);
+	return btrfs_set_prop(inode, name, value, size, flags);
 }
 
 static const struct xattr_handler btrfs_security_xattr_handler = {
@@ -434,25 +433,6 @@ const struct xattr_handler *btrfs_xattr_handlers[] = {
 	NULL,
 };
 
-int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
-		   size_t size, int flags)
-{
-	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-
-	if (btrfs_root_readonly(root))
-		return -EROFS;
-	return generic_setxattr(dentry, name, value, size, flags);
-}
-
-int btrfs_removexattr(struct dentry *dentry, const char *name)
-{
-	struct btrfs_root *root = BTRFS_I(d_inode(dentry))->root;
-
-	if (btrfs_root_readonly(root))
-		return -EROFS;
-	return generic_removexattr(dentry, name);
-}
-
 static int btrfs_initxattrs(struct inode *inode,
 			    const struct xattr *xattr_array, void *fs_info)
 {
diff --git a/fs/btrfs/xattr.h b/fs/btrfs/xattr.h
index 96807b3d2..15fc4743d 100644
--- a/fs/btrfs/xattr.h
+++ b/fs/btrfs/xattr.h
@@ -28,9 +28,6 @@ extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 extern int __btrfs_setxattr(struct btrfs_trans_handle *trans,
 			    struct inode *inode, const char *name,
 			    const void *value, size_t size, int flags);
-extern int btrfs_setxattr(struct dentry *dentry, const char *name,
-		const void *value, size_t size, int flags);
-extern int btrfs_removexattr(struct dentry *dentry, const char *name);
 
 extern int btrfs_xattr_security_init(struct btrfs_trans_handle *trans,
 				     struct inode *inode, struct inode *dir,