Merge branch 'for-linus-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "This has our merge window series of cleanups and fixes.  These target
  a wide range of issues, but do include some important fixes for
  qgroups, O_DIRECT, and fsync handling.  Jeff Mahoney moved around a
  few definitions to make them easier for userland to consume.

  Also whiteout support is included now that issues with overlayfs have
  been cleared up.

  I have one more fix pending for page faults during btrfs_copy_from_user,
  but I wanted to get this bulk out the door first"

* 'for-linus-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (90 commits)
  btrfs: fix memory leak during RAID 5/6 device replacement
  Btrfs: add semaphore to synchronize direct IO writes with fsync
  Btrfs: fix race between block group relocation and nocow writes
  Btrfs: fix race between fsync and direct IO writes for prealloc extents
  Btrfs: fix number of transaction units for renames with whiteout
  Btrfs: pin logs earlier when doing a rename exchange operation
  Btrfs: unpin logs if rename exchange operation fails
  Btrfs: fix inode leak on failure to setup whiteout inode in rename
  btrfs: add support for RENAME_EXCHANGE and RENAME_WHITEOUT
  Btrfs: pin log earlier when renaming
  Btrfs: unpin log if rename operation fails
  Btrfs: don't do unnecessary delalloc flushes when relocating
  Btrfs: don't wait for unrelated IO to finish before relocation
  Btrfs: fix empty symlink after creating symlink and fsync parent dir
  Btrfs: fix for incorrect directory entries after fsync log replay
  btrfs: build fixup for qgroup_account_snapshot
  btrfs: qgroup: Fix qgroup accounting when creating snapshot
  Btrfs: fix fspath error deallocation
  btrfs: make find_workspace warn if there are no workspaces
  btrfs: make find_workspace always succeed
  ...

fs/btrfs/backref.c

@@ -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);
 	}
 

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;
 };
 

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,

fs/btrfs/ctree.c

@@ -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 {
@@ -1928,7 +1928,7 @@ 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;
 		}
 
@@ -2031,7 +2031,7 @@ 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);

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.
@@ -175,12 +84,6 @@ 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 */
@@ -189,17 +92,6 @@ static const int btrfs_csum_sizes[] = { 4 };
 /* spefic 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;
@@ -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.
  *
@@ -3499,6 +2508,12 @@ 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);
@@ -4122,6 +3137,7 @@ void btrfs_test_inode_set_ops(struct inode *inode);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_update_iflags(struct inode *inode);
 void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
@@ -4326,10 +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);
@@ -4339,6 +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)
 
@@ -4455,44 +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);

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);

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);
 	}
@@ -440,6 +420,35 @@ 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.
  */
@@ -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)
 {

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,

fs/btrfs/disk-io.c

@@ -1640,7 +1640,7 @@ 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;
 
@@ -2417,7 +2417,7 @@ 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);
@@ -2517,6 +2517,7 @@ int open_ctree(struct super_block *sb,
 	int num_backups_tried = 0;
 	int backup_index = 0;
 	int max_active;
+	bool cleaner_mutex_locked = false;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2713,7 +2714,7 @@ 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 +2734,7 @@ 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 +2769,9 @@ 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 +2782,7 @@ 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
@@ -2789,7 +2790,8 @@ 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;
 	}
 
@@ -2805,9 +2807,9 @@ 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 +2822,8 @@ 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 +2852,7 @@ 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 +2866,7 @@ 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 +2880,7 @@ 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 +2891,7 @@ 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 +2903,7 @@ 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 +2935,19 @@ 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 +2955,33 @@ 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 =
@@ -2991,12 +2989,20 @@ 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;
 	}
 
+	/*
+	 * Hold the cleaner_mutex thread here so that we don't block
+	 * for a long time on btrfs_recover_relocation.  cleaner_kthread
+	 * will wait for us to finish mounting the filesystem.
+	 */
+	mutex_lock(&fs_info->cleaner_mutex);
+	cleaner_mutex_locked = true;
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
@@ -3011,8 +3017,7 @@ 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);
 	}
 
@@ -3030,8 +3035,9 @@ 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);
@@ -3056,17 +3062,17 @@ retry_root_backup:
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
-
-		mutex_lock(&fs_info->cleaner_mutex);
+		/* We locked cleaner_mutex before creating cleaner_kthread. */
 		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;
 		}
 	}
+	mutex_unlock(&fs_info->cleaner_mutex);
+	cleaner_mutex_locked = false;
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3083,11 +3089,11 @@ 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 +3110,14 @@ 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 +3126,33 @@ 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;
 		}
@@ -3180,6 +3186,10 @@ fail_cleaner:
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 
 fail_sysfs:
+	if (cleaner_mutex_locked) {
+		mutex_unlock(&fs_info->cleaner_mutex);
+		cleaner_mutex_locked = false;
+	}
 	btrfs_sysfs_remove_mounted(fs_info);
 
 fail_fsdev_sysfs:
@@ -3646,7 +3656,7 @@ 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 +3696,7 @@ 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 +3714,7 @@ 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;
 	}

fs/btrfs/extent-tree.c

@@ -3824,6 +3824,59 @@ 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 +4194,7 @@ 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);
@@ -4583,7 +4636,8 @@ 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 +4674,7 @@ 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 +4686,8 @@ 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 +4726,8 @@ 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)
@@ -6172,6 +6228,57 @@ 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
@@ -7025,36 +7132,35 @@ 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 +7537,7 @@ 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;
@@ -7612,8 +7719,10 @@ 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);
@@ -9058,7 +9167,7 @@ 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;
 }
 

fs/btrfs/extent_io.c

@@ -3200,14 +3200,10 @@ 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 +3364,8 @@ 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 +3421,23 @@ 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 +3909,13 @@ 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 +3938,8 @@ 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 +3949,7 @@ 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 +3959,7 @@ 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 +4001,20 @@ 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 +4026,7 @@ 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 +4035,12 @@ 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)
@@ -4822,7 +4832,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 		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);
@@ -4923,7 +4933,7 @@ 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);
+	ret = radix_tree_preload(GFP_NOFS);
 	if (ret)
 		goto free_eb;
 

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,

fs/btrfs/file.c

@@ -1696,7 +1696,9 @@ 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);
 		}
 	}
 
@@ -2952,7 +2954,7 @@ const struct file_operations btrfs_file_operations = {
 	.fallocate	= btrfs_fallocate,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl	= btrfs_ioctl,
+	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
 	.copy_file_range = btrfs_copy_file_range,
 	.clone_file_range = btrfs_clone_file_range,

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;
 	}

fs/btrfs/inode.c

@@ -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 ==
@@ -7129,6 +7145,43 @@ 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 +7197,13 @@ 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;
 }
 
@@ -7650,24 +7675,21 @@ 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;
@@ -9230,6 +9252,7 @@ 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 +9410,281 @@ 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 +9693,7 @@ 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 +9744,21 @@ 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 +9772,8 @@ 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 +9781,6 @@ 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 +9847,46 @@ 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 +9899,14 @@ 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 +10275,7 @@ 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,
@@ -10184,7 +10518,7 @@ static const struct file_operations btrfs_dir_file_operations = {
 	.iterate	= btrfs_real_readdir,
 	.unlocked_ioctl	= btrfs_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl	= btrfs_ioctl,
+	.compat_ioctl	= btrfs_compat_ioctl,
 #endif
 	.release        = btrfs_release_file,
 	.fsync		= btrfs_sync_file,

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;
 }
@@ -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.
 	 */
-	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);
@@ -2671,10 +2680,10 @@ 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))
@@ -2690,7 +2699,9 @@ 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)) {
@@ -2699,13 +2710,23 @@ 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:
@@ -2713,6 +2734,47 @@ 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;
@@ -3472,13 +3534,16 @@ 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;
 	}
 
@@ -3779,7 +3844,7 @@ process_slot:
 
 out:
 	btrfs_free_path(path);
-	vfree(buf);
+	kvfree(buf);
 	return ret;
 }
 
@@ -4380,7 +4445,7 @@ 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);
@@ -4851,8 +4916,8 @@ 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;
@@ -5398,9 +5463,15 @@ 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);
@@ -5419,7 +5490,11 @@ 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
@@ -5463,6 +5538,8 @@ 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:
@@ -5556,3 +5633,24 @@ long btrfs_ioctl(struct file *file, unsigned int
 
 	return -ENOTTY;
 }
+
+#ifdef CONFIG_COMPAT
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case FS_IOC32_GETFLAGS:
+		cmd = FS_IOC_GETFLAGS;
+		break;
+	case FS_IOC32_SETFLAGS:
+		cmd = FS_IOC_SETFLAGS;
+		break;
+	case FS_IOC32_GETVERSION:
+		cmd = FS_IOC_GETVERSION;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif

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);
 
@@ -708,7 +718,8 @@ 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)
+void 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;
@@ -728,7 +739,8 @@ 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);
 
 		spin_lock(&fs_info->ordered_root_lock);

fs/btrfs/ordered-data.h

@@ -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);
+void 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,

fs/btrfs/relocation.c

@@ -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);
 
@@ -4254,12 +4254,11 @@ 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);

fs/btrfs/root-tree.c

@@ -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;

fs/btrfs/scrub.c

@@ -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);
 }
 
@@ -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);
@@ -3070,7 +3072,6 @@ 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 +3080,7 @@ 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 +3159,21 @@ 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);

fs/btrfs/send.c

@@ -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);
 

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)
 {
@@ -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) ||
@@ -2051,9 +2047,10 @@ 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 +2073,17 @@ 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 +2096,11 @@ 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 +2125,7 @@ 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;

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;
 

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;
@@ -1310,6 +1311,97 @@ int btrfs_defrag_root(struct btrfs_root *root)
 	return ret;
 }
 
+/* Bisesctability fixup, remove in 4.8 */
+#ifndef btrfs_std_error
+#define btrfs_std_error btrfs_handle_fs_error
+#endif
+
+/*
+ * 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_std_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 +1475,7 @@ 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 +1512,7 @@ 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 +1608,17 @@ 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 +1662,6 @@ 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 +1907,7 @@ 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 +2231,7 @@ 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;

fs/btrfs/tree-log.c

@@ -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;
@@ -4622,23 +4631,6 @@ 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) {
@@ -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;
@@ -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

fs/btrfs/volumes.c

@@ -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,
@@ -2101,6 +2101,31 @@ 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.
  */
@@ -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);
@@ -2857,7 +2882,7 @@ 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;
 	}
 
@@ -3402,6 +3427,7 @@ 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 +3566,13 @@ 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 +3664,7 @@ 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 +3725,8 @@ 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;
@@ -5278,7 +5308,15 @@ 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 +5557,13 @@ 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) {
@@ -6242,7 +6286,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
 			"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;

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,

include/uapi/linux/btrfs.h

@@ -23,6 +23,7 @@
 
 #define BTRFS_IOCTL_MAGIC 0x94
 #define BTRFS_VOL_NAME_MAX 255
+#define BTRFS_LABEL_SIZE 256
 
 /* this should be 4k */
 #define BTRFS_PATH_NAME_MAX 4087
@@ -33,14 +34,31 @@ struct btrfs_ioctl_vol_args {
 
 #define BTRFS_DEVICE_PATH_NAME_MAX 1024
 
-#define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
-#define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
-#define BTRFS_SUBVOL_QGROUP_INHERIT	(1ULL << 2)
+#define BTRFS_DEVICE_SPEC_BY_ID		(1ULL << 3)
+
+#define BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED		\
+			(BTRFS_SUBVOL_CREATE_ASYNC |	\
+			BTRFS_SUBVOL_RDONLY |		\
+			BTRFS_SUBVOL_QGROUP_INHERIT |	\
+			BTRFS_DEVICE_SPEC_BY_ID)
+
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_UUID_SIZE 16
 #define BTRFS_UUID_UNPARSED_SIZE	37
 
-#define BTRFS_QGROUP_INHERIT_SET_LIMITS	(1ULL << 0)
+/*
+ * flags definition for qgroup limits
+ *
+ * Used by:
+ * struct btrfs_qgroup_limit.flags
+ * struct btrfs_qgroup_limit_item.flags
+ */
+#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 {
 	__u64	flags;
@@ -50,6 +68,14 @@ struct btrfs_qgroup_limit {
 	__u64	rsv_excl;
 };
 
+/*
+ * flags definition for qgroup inheritance
+ *
+ * Used by:
+ * struct btrfs_qgroup_inherit.flags
+ */
+#define BTRFS_QGROUP_INHERIT_SET_LIMITS	(1ULL << 0)
+
 struct btrfs_qgroup_inherit {
 	__u64	flags;
 	__u64	num_qgroups;
@@ -64,6 +90,20 @@ struct btrfs_ioctl_qgroup_limit_args {
 	struct btrfs_qgroup_limit lim;
 };
 
+/*
+ * flags for subvolumes
+ *
+ * Used by:
+ * struct btrfs_ioctl_vol_args_v2.flags
+ *
+ * BTRFS_SUBVOL_RDONLY is also provided/consumed by the following ioctls:
+ * - BTRFS_IOC_SUBVOL_GETFLAGS
+ * - BTRFS_IOC_SUBVOL_SETFLAGS
+ */
+#define BTRFS_SUBVOL_CREATE_ASYNC	(1ULL << 0)
+#define BTRFS_SUBVOL_RDONLY		(1ULL << 1)
+#define BTRFS_SUBVOL_QGROUP_INHERIT	(1ULL << 2)
+
 #define BTRFS_SUBVOL_NAME_MAX 4039
 struct btrfs_ioctl_vol_args_v2 {
 	__s64 fd;
@@ -76,7 +116,10 @@ struct btrfs_ioctl_vol_args_v2 {
 		};
 		__u64 unused[4];
 	};
-	char name[BTRFS_SUBVOL_NAME_MAX + 1];
+	union {
+		char name[BTRFS_SUBVOL_NAME_MAX + 1];
+		u64 devid;
+	};
 };
 
 /*
@@ -190,6 +233,37 @@ struct btrfs_ioctl_fs_info_args {
 	__u64 reserved[122];			/* pad to 1k */
 };
 
+/*
+ * feature flags
+ *
+ * Used by:
+ * struct btrfs_ioctl_feature_flags
+ */
+#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)
+
 struct btrfs_ioctl_feature_flags {
 	__u64 compat_flags;
 	__u64 compat_ro_flags;
@@ -254,6 +328,70 @@ struct btrfs_balance_progress {
 	__u64 completed;	/* # of chunks relocated so far */
 };
 
+/*
+ * flags definition for balance
+ *
+ * Restriper's general type filter
+ *
+ * Used by:
+ * btrfs_ioctl_balance_args.flags
+ * btrfs_balance_control.flags (internal)
+ */
+#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)
+
+/*
+ * flags definitions for per-type balance args
+ *
+ * Balance filters
+ *
+ * Used by:
+ * struct btrfs_balance_args
+ */
+#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)
+
+
+/*
+ * flags definition for balance state
+ *
+ * Used by:
+ * struct btrfs_ioctl_balance_args.state
+ */
 #define BTRFS_BALANCE_STATE_RUNNING	(1ULL << 0)
 #define BTRFS_BALANCE_STATE_PAUSE_REQ	(1ULL << 1)
 #define BTRFS_BALANCE_STATE_CANCEL_REQ	(1ULL << 2)
@@ -347,9 +485,45 @@ struct btrfs_ioctl_clone_range_args {
   __u64 dest_offset;
 };
 
-/* flags for the defrag range ioctl */
+/*
+ * flags definition for the defrag range ioctl
+ *
+ * Used by:
+ * struct btrfs_ioctl_defrag_range_args.flags
+ */
 #define BTRFS_DEFRAG_RANGE_COMPRESS 1
 #define BTRFS_DEFRAG_RANGE_START_IO 2
+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];
+};
+
 
 #define BTRFS_SAME_DATA_DIFFERS	1
 /* For extent-same ioctl */
@@ -659,5 +833,7 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				   struct btrfs_ioctl_feature_flags[2])
 #define BTRFS_IOC_GET_SUPPORTED_FEATURES _IOR(BTRFS_IOCTL_MAGIC, 57, \
 				   struct btrfs_ioctl_feature_flags[3])
+#define BTRFS_IOC_RM_DEV_V2 _IOW(BTRFS_IOCTL_MAGIC, 58, \
+				   struct btrfs_ioctl_vol_args_v2)
 
 #endif /* _UAPI_LINUX_BTRFS_H */

include/uapi/linux/btrfs_tree.h

@@ -0,0 +1,966 @@
+#ifndef _BTRFS_CTREE_H_
+#define _BTRFS_CTREE_H_
+
+/*
+ * This header contains the structure definitions and constants used
+ * by file system objects that can be retrieved using
+ * the BTRFS_IOC_SEARCH_TREE ioctl.  That means basically anything that
+ * is needed to describe a leaf node's key or item contents.
+ */
+
+/* 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
+
+/*
+ * 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
+
+
+
+/* 32 bytes in various csum fields */
+#define BTRFS_CSUM_SIZE 32
+
+/* csum types */
+#define BTRFS_CSUM_TYPE_CRC32	0
+
+/*
+ * flags definitions for directory entry item type
+ *
+ * Used by:
+ * struct btrfs_dir_item.type
+ */
+#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
+
+/*
+ * 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_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__));
+
+#define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
+#define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
+
+/* 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)
+
+
+/*
+ * 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_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_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__));
+
+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__));
+
+#endif /* _BTRFS_CTREE_H_ */