Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (58 commits)
  Btrfs: use the device_list_mutex during write_dev_supers
  Btrfs: setup free ino caching in a more asynchronous way
  btrfs scrub: don't coalesce pages that are logically discontiguous
  Btrfs: return -ENOMEM in clear_extent_bit
  Btrfs: add mount -o auto_defrag
  Btrfs: using rcu lock in the reader side of devices list
  Btrfs: drop unnecessary device lock
  Btrfs: fix the race between remove dev and alloc chunk
  Btrfs: fix the race between reading and updating devices
  Btrfs: fix bh leak on __btrfs_open_devices path
  Btrfs: fix unsafe usage of merge_state
  Btrfs: allocate extent state and check the result properly
  fs/btrfs: Add missing btrfs_free_path
  Btrfs: check return value of btrfs_inc_extent_ref()
  Btrfs: return error to caller if read_one_inode() fails
  Btrfs: BUG_ON is deleted from the caller of btrfs_truncate_item & btrfs_extend_item
  Btrfs: return error code to caller when btrfs_del_item fails
  Btrfs: return error code to caller when btrfs_previous_item fails
  btrfs: fix typo 'testeing' -> 'testing'
  btrfs: typo: 'btrfS' -> 'btrfs'
  ...

48 files changed, 6481 insertions, 4557 deletions

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 31610ea73ae..9b72dcf1cd2 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -7,4 +7,4 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
-	   compression.o delayed-ref.o relocation.o
+	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 44ea5b92e1b..f66fc995973 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -288,7 +288,7 @@ int btrfs_acl_chmod(struct inode *inode)
 		return 0;
 
 	acl = btrfs_get_acl(inode, ACL_TYPE_ACCESS);
-	if (IS_ERR(acl) || !acl)
+	if (IS_ERR_OR_NULL(acl))
 		return PTR_ERR(acl);
 
 	clone = posix_acl_clone(acl, GFP_KERNEL);
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 57c3bb2884c..93b1aa93201 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -22,6 +22,7 @@
 #include "extent_map.h"
 #include "extent_io.h"
 #include "ordered-data.h"
+#include "delayed-inode.h"
 
 /* in memory btrfs inode */
 struct btrfs_inode {
@@ -152,20 +153,34 @@ struct btrfs_inode {
 	unsigned ordered_data_close:1;
 	unsigned orphan_meta_reserved:1;
 	unsigned dummy_inode:1;
+	unsigned in_defrag:1;
 
 	/*
 	 * always compress this one file
 	 */
 	unsigned force_compress:4;
 
+	struct btrfs_delayed_node *delayed_node;
+
 	struct inode vfs_inode;
 };
 
+extern unsigned char btrfs_filetype_table[];
+
 static inline struct btrfs_inode *BTRFS_I(struct inode *inode)
 {
 	return container_of(inode, struct btrfs_inode, vfs_inode);
 }
 
+static inline u64 btrfs_ino(struct inode *inode)
+{
+	u64 ino = BTRFS_I(inode)->location.objectid;
+
+	if (ino <= BTRFS_FIRST_FREE_OBJECTID)
+		ino = inode->i_ino;
+	return ino;
+}
+
 static inline void btrfs_i_size_write(struct inode *inode, u64 size)
 {
 	i_size_write(inode, size);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 41d1d7c70e2..bfe42b03eaf 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -125,9 +125,10 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr, KM_USER0);
 
 		if (csum != *cb_sum) {
-			printk(KERN_INFO "btrfs csum failed ino %lu "
+			printk(KERN_INFO "btrfs csum failed ino %llu "
 			       "extent %llu csum %u "
-			       "wanted %u mirror %d\n", inode->i_ino,
+			       "wanted %u mirror %d\n",
+			       (unsigned long long)btrfs_ino(inode),
 			       (unsigned long long)disk_start,
 			       csum, *cb_sum, cb->mirror_num);
 			ret = -EIO;
@@ -332,7 +333,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
-	int page_index = 0;
+	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
 	struct block_device *bdev;
@@ -366,8 +367,8 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 	/* create and submit bios for the compressed pages */
 	bytes_left = compressed_len;
-	for (page_index = 0; page_index < cb->nr_pages; page_index++) {
-		page = compressed_pages[page_index];
+	for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
+		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_size)
 			ret = io_tree->ops->merge_bio_hook(page, 0,
@@ -432,7 +433,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 				     struct compressed_bio *cb)
 {
 	unsigned long end_index;
-	unsigned long page_index;
+	unsigned long pg_index;
 	u64 last_offset;
 	u64 isize = i_size_read(inode);
 	int ret;
@@ -456,13 +457,13 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
 
 	while (last_offset < compressed_end) {
-		page_index = last_offset >> PAGE_CACHE_SHIFT;
+		pg_index = last_offset >> PAGE_CACHE_SHIFT;
 
-		if (page_index > end_index)
+		if (pg_index > end_index)
 			break;
 
 		rcu_read_lock();
-		page = radix_tree_lookup(&mapping->page_tree, page_index);
+		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
 		if (page) {
 			misses++;
@@ -476,7 +477,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		if (!page)
 			break;
 
-		if (add_to_page_cache_lru(page, mapping, page_index,
+		if (add_to_page_cache_lru(page, mapping, pg_index,
 								GFP_NOFS)) {
 			page_cache_release(page);
 			goto next;
@@ -560,7 +561,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE;
 	unsigned long compressed_len;
 	unsigned long nr_pages;
-	unsigned long page_index;
+	unsigned long pg_index;
 	struct page *page;
 	struct block_device *bdev;
 	struct bio *comp_bio;
@@ -613,10 +614,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
 
-	for (page_index = 0; page_index < nr_pages; page_index++) {
-		cb->compressed_pages[page_index] = alloc_page(GFP_NOFS |
+	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+		cb->compressed_pages[pg_index] = alloc_page(GFP_NOFS |
 							      __GFP_HIGHMEM);
-		if (!cb->compressed_pages[page_index])
+		if (!cb->compressed_pages[pg_index])
 			goto fail2;
 	}
 	cb->nr_pages = nr_pages;
@@ -634,8 +635,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	atomic_inc(&cb->pending_bios);
 
-	for (page_index = 0; page_index < nr_pages; page_index++) {
-		page = cb->compressed_pages[page_index];
+	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+		page = cb->compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		page->index = em_start >> PAGE_CACHE_SHIFT;
 
@@ -702,8 +703,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	return 0;
 
 fail2:
-	for (page_index = 0; page_index < nr_pages; page_index++)
-		free_page((unsigned long)cb->compressed_pages[page_index]);
+	for (pg_index = 0; pg_index < nr_pages; pg_index++)
+		free_page((unsigned long)cb->compressed_pages[pg_index]);
 
 	kfree(cb->compressed_pages);
 fail1:
@@ -945,7 +946,7 @@ void btrfs_exit_compress(void)
 int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *page_index,
+			      unsigned long *pg_index,
 			      unsigned long *pg_offset)
 {
 	unsigned long buf_offset;
@@ -954,7 +955,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
-	struct page *page_out = bvec[*page_index].bv_page;
+	struct page *page_out = bvec[*pg_index].bv_page;
 
 	/*
 	 * start byte is the first byte of the page we're currently
@@ -995,11 +996,11 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 
 		/* check if we need to pick another page */
 		if (*pg_offset == PAGE_CACHE_SIZE) {
-			(*page_index)++;
-			if (*page_index >= vcnt)
+			(*pg_index)++;
+			if (*pg_index >= vcnt)
 				return 0;
 
-			page_out = bvec[*page_index].bv_page;
+			page_out = bvec[*pg_index].bv_page;
 			*pg_offset = 0;
 			start_byte = page_offset(page_out) - disk_start;
 
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 51000174b9d..a12059f4f0f 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -37,7 +37,7 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *page_index,
+			      unsigned long *pg_index,
 			      unsigned long *pg_offset);
 
 int btrfs_submit_compressed_write(struct inode *inode, u64 start,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 84d7ca1fe0b..b0e18d986e0 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -38,11 +38,6 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
 			      struct extent_buffer *src_buf);
 static int del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		   struct btrfs_path *path, int level, int slot);
-static int setup_items_for_insert(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root, struct btrfs_path *path,
-			struct btrfs_key *cpu_key, u32 *data_size,
-			u32 total_data, u32 total_size, int nr);
-
 
 struct btrfs_path *btrfs_alloc_path(void)
 {
@@ -107,7 +102,7 @@ void btrfs_free_path(struct btrfs_path *p)
 {
 	if (!p)
 		return;
-	btrfs_release_path(NULL, p);
+	btrfs_release_path(p);
 	kmem_cache_free(btrfs_path_cachep, p);
 }
 
@@ -117,7 +112,7 @@ void btrfs_free_path(struct btrfs_path *p)
  *
  * It is safe to call this on paths that no locks or extent buffers held.
  */
-noinline void btrfs_release_path(struct btrfs_root *root, struct btrfs_path *p)
+noinline void btrfs_release_path(struct btrfs_path *p)
 {
 	int i;
 
@@ -1328,7 +1323,7 @@ static noinline int reada_for_balance(struct btrfs_root *root,
 		ret = -EAGAIN;
 
 		/* release the whole path */
-		btrfs_release_path(root, path);
+		btrfs_release_path(path);
 
 		/* read the blocks */
 		if (block1)
@@ -1475,7 +1470,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 				return 0;
 			}
 			free_extent_buffer(tmp);
-			btrfs_release_path(NULL, p);
+			btrfs_release_path(p);
 			return -EIO;
 		}
 	}
@@ -1494,7 +1489,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	if (p->reada)
 		reada_for_search(root, p, level, slot, key->objectid);
 
-	btrfs_release_path(NULL, p);
+	btrfs_release_path(p);
 
 	ret = -EAGAIN;
 	tmp = read_tree_block(root, blocknr, blocksize, 0);
@@ -1563,7 +1558,7 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
 		}
 		b = p->nodes[level];
 		if (!b) {
-			btrfs_release_path(NULL, p);
+			btrfs_release_path(p);
 			goto again;
 		}
 		BUG_ON(btrfs_header_nritems(b) == 1);
@@ -1753,7 +1748,7 @@ done:
 	if (!p->leave_spinning)
 		btrfs_set_path_blocking(p);
 	if (ret < 0)
-		btrfs_release_path(root, p);
+		btrfs_release_path(p);
 	return ret;
 }
 
@@ -3026,7 +3021,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 				    struct btrfs_file_extent_item);
 		extent_len = btrfs_file_extent_num_bytes(leaf, fi);
 	}
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	path->keep_locks = 1;
 	path->search_for_split = 1;
@@ -3216,7 +3211,6 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 			struct btrfs_path *path,
 			u32 new_size, int from_end)
 {
-	int ret = 0;
 	int slot;
 	struct extent_buffer *leaf;
 	struct btrfs_item *item;
@@ -3314,12 +3308,11 @@ int btrfs_truncate_item(struct btrfs_trans_handle *trans,
 	btrfs_set_item_size(leaf, item, new_size);
 	btrfs_mark_buffer_dirty(leaf);
 
-	ret = 0;
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -3329,7 +3322,6 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, struct btrfs_path *path,
 		      u32 data_size)
 {
-	int ret = 0;
 	int slot;
 	struct extent_buffer *leaf;
 	struct btrfs_item *item;
@@ -3394,12 +3386,11 @@ int btrfs_extend_item(struct btrfs_trans_handle *trans,
 	btrfs_set_item_size(leaf, item, old_size + data_size);
 	btrfs_mark_buffer_dirty(leaf);
 
-	ret = 0;
 	if (btrfs_leaf_free_space(root, leaf) < 0) {
 		btrfs_print_leaf(root, leaf);
 		BUG();
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -3559,11 +3550,10 @@ out:
  * to save stack depth by doing the bulk of the work in a function
  * that doesn't call btrfs_search_slot
  */
-static noinline_for_stack int
-setup_items_for_insert(struct btrfs_trans_handle *trans,
-		      struct btrfs_root *root, struct btrfs_path *path,
-		      struct btrfs_key *cpu_key, u32 *data_size,
-		      u32 total_data, u32 total_size, int nr)
+int setup_items_for_insert(struct btrfs_trans_handle *trans,
+			   struct btrfs_root *root, struct btrfs_path *path,
+			   struct btrfs_key *cpu_key, u32 *data_size,
+			   u32 total_data, u32 total_size, int nr)
 {
 	struct btrfs_item *item;
 	int i;
@@ -3647,7 +3637,6 @@ setup_items_for_insert(struct btrfs_trans_handle *trans,
 
 	ret = 0;
 	if (slot == 0) {
-		struct btrfs_disk_key disk_key;
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
 		ret = fixup_low_keys(trans, root, path, &disk_key, 1);
 	}
@@ -3949,7 +3938,7 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 	else
 		return 1;
 
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
 		return ret;
@@ -4073,7 +4062,7 @@ find_next_key:
 			sret = btrfs_find_next_key(root, path, min_key, level,
 						  cache_only, min_trans);
 			if (sret == 0) {
-				btrfs_release_path(root, path);
+				btrfs_release_path(path);
 				goto again;
 			} else {
 				goto out;
@@ -4152,7 +4141,7 @@ next:
 				btrfs_node_key_to_cpu(c, &cur_key, slot);
 
 			orig_lowest = path->lowest_level;
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			path->lowest_level = level;
 			ret = btrfs_search_slot(NULL, root, &cur_key, path,
 						0, 0);
@@ -4229,7 +4218,7 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 again:
 	level = 1;
 	next = NULL;
-	btrfs_release_path(root, path);
+	btrfs_release_path(path);
 
 	path->keep_locks = 1;
 
@@ -4285,7 +4274,7 @@ again:
 			goto again;
 
 		if (ret < 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto done;
 		}
 
@@ -4324,7 +4313,7 @@ again:
 			goto again;
 
 		if (ret < 0) {
-			btrfs_release_path(root, path);
+			btrfs_release_path(path);
 			goto done;
 		}
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8f4b81de3ae..332323e19dd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -23,6 +23,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
+#include <linux/rwsem.h>
 #include <linux/completion.h>
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
@@ -33,6 +34,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
+#include "ioctl.h"
 
 struct btrfs_trans_handle;
 struct btrfs_transaction;
@@ -105,6 +107,12 @@ struct btrfs_ordered_sum;
 /* For storing free space cache */
 #define BTRFS_FREE_SPACE_OBJECTID -11ULL
 
+/*
+ * The inode number assigned to the special inode for sotring
+ * free ino cache
+ */
+#define BTRFS_FREE_INO_OBJECTID -12ULL
+
 /* dummy objectid represents multiple objectids */
 #define BTRFS_MULTIPLE_OBJECTIDS -255ULL
 
@@ -187,7 +195,6 @@ struct btrfs_mapping_tree {
 	struct extent_map_tree map_tree;
 };
 
-#define BTRFS_UUID_SIZE 16
 struct btrfs_dev_item {
 	/* the internal btrfs device id */
 	__le64 devid;
@@ -294,7 +301,6 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 		sizeof(struct btrfs_stripe) * (num_stripes - 1);
 }
 
-#define BTRFS_FSID_SIZE 16
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
 
@@ -510,6 +516,12 @@ struct btrfs_extent_item_v0 {
 /* 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;
@@ -740,12 +752,12 @@ struct btrfs_space_info {
 	 */
 	unsigned long reservation_progress;
 
-	int full:1;		/* indicates that we cannot allocate any more
+	unsigned int full:1;	/* indicates that we cannot allocate any more
 				   chunks for this space */
-	int chunk_alloc:1;	/* set if we are allocating a chunk */
+	unsigned int chunk_alloc:1;	/* set if we are allocating a chunk */
 
-	int force_alloc;	/* set if we need to force a chunk alloc for
-				   this space */
+	unsigned int force_alloc;	/* set if we need to force a chunk
+					   alloc for this space */
 
 	struct list_head list;
 
@@ -830,9 +842,6 @@ struct btrfs_block_group_cache {
 	u64 bytes_super;
 	u64 flags;
 	u64 sectorsize;
-	int extents_thresh;
-	int free_extents;
-	int total_bitmaps;
 	unsigned int ro:1;
 	unsigned int dirty:1;
 	unsigned int iref:1;
@@ -847,9 +856,7 @@ struct btrfs_block_group_cache {
 	struct btrfs_space_info *space_info;
 
 	/* free space cache stuff */
-	spinlock_t tree_lock;
-	struct rb_root free_space_offset;
-	u64 free_space;
+	struct btrfs_free_space_ctl *free_space_ctl;
 
 	/* block group cache stuff */
 	struct rb_node cache_node;
@@ -869,6 +876,7 @@ struct btrfs_block_group_cache {
 struct reloc_control;
 struct btrfs_device;
 struct btrfs_fs_devices;
+struct btrfs_delayed_root;
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
 	u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
@@ -895,7 +903,10 @@ struct btrfs_fs_info {
 	/* logical->physical extent mapping */
 	struct btrfs_mapping_tree mapping_tree;
 
-	/* block reservation for extent, checksum and root tree */
+	/*
+	 * block reservation for extent, checksum, root tree and
+	 * delayed dir index item
+	 */
 	struct btrfs_block_rsv global_block_rsv;
 	/* block reservation for delay allocation */
 	struct btrfs_block_rsv delalloc_block_rsv;
@@ -1022,6 +1033,7 @@ struct btrfs_fs_info {
 	 * for the sys_munmap function call path
 	 */
 	struct btrfs_workers fixup_workers;
+	struct btrfs_workers delayed_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
 	int thread_pool_size;
@@ -1062,6 +1074,11 @@ struct btrfs_fs_info {
 	/* all metadata allocations go through this cluster */
 	struct btrfs_free_cluster meta_alloc_cluster;
 
+	/* auto defrag inodes go here */
+	spinlock_t defrag_inodes_lock;
+	struct rb_root defrag_inodes;
+	atomic_t defrag_running;
+
 	spinlock_t ref_cache_lock;
 	u64 total_ref_cache_size;
 
@@ -1077,8 +1094,21 @@ struct btrfs_fs_info {
 
 	void *bdev_holder;
 
+	/* private scrub information */
+	struct mutex scrub_lock;
+	atomic_t scrubs_running;
+	atomic_t scrub_pause_req;
+	atomic_t scrubs_paused;
+	atomic_t scrub_cancel_req;
+	wait_queue_head_t scrub_pause_wait;
+	struct rw_semaphore scrub_super_lock;
+	int scrub_workers_refcnt;
+	struct btrfs_workers scrub_workers;
+
 	/* filesystem state */
 	u64 fs_state;
+
+	struct btrfs_delayed_root *delayed_root;
 };
 
 /*
@@ -1088,9 +1118,6 @@ struct btrfs_fs_info {
 struct btrfs_root {
 	struct extent_buffer *node;
 
-	/* the node lock is held while changing the node pointer */
-	spinlock_t node_lock;
-
 	struct extent_buffer *commit_root;
 	struct btrfs_root *log_root;
 	struct btrfs_root *reloc_root;
@@ -1107,6 +1134,16 @@ struct btrfs_root {
 	spinlock_t accounting_lock;
 	struct btrfs_block_rsv *block_rsv;
 
+	/* free ino cache stuff */
+	struct mutex fs_commit_mutex;
+	struct btrfs_free_space_ctl *free_ino_ctl;
+	enum btrfs_caching_type cached;
+	spinlock_t cache_lock;
+	wait_queue_head_t cache_wait;
+	struct btrfs_free_space_ctl *free_ino_pinned;
+	u64 cache_progress;
+	struct inode *cache_inode;
+
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
 	wait_queue_head_t log_commit_wait[2];
@@ -1162,12 +1199,49 @@ struct btrfs_root {
 	struct rb_root inode_tree;
 
 	/*
+	 * radix tree that keeps track of delayed nodes of every inode,
+	 * protected by inode_lock
+	 */
+	struct radix_tree_root delayed_nodes_tree;
+	/*
 	 * right now this just gets used so that a root has its own devid
 	 * for stat.  It may be used for more later
 	 */
 	struct super_block anon_super;
 };
 
+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
@@ -1265,6 +1339,7 @@ struct btrfs_root {
 #define BTRFS_MOUNT_CLEAR_CACHE		(1 << 13)
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
+#define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -1440,26 +1515,12 @@ static inline u64 btrfs_stripe_offset_nr(struct extent_buffer *eb,
 	return btrfs_stripe_offset(eb, btrfs_stripe_nr(c, nr));
 }
 
-static inline void btrfs_set_stripe_offset_nr(struct extent_buffer *eb,
-					     struct btrfs_chunk *c, int nr,
-					     u64 val)
-{
-	btrfs_set_stripe_offs