Merge tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "We don't have any big feature updates this time, there are lots of
  small enhacements or fixes. A highlight perhaps is the parallel fsync
  performance improvements, numbers below.

  Regarding the dio/iomap that was reverted last time, the required API
  changes are likely to land in the upcoming cycle, the btrfs part will
  be updated afterwards.

  User visible changes:

   - new mount option rescue= to group all recovery-related mount
     options so we don't have many specific options, currently
     introducing only aliases for existing options, future extensions
     are in development to allow read-only mount with partially damaged
     structures:
      - usebackuproot is an alias for rescue=usebackuproot
      - nologreplay is an alias for rescue=nologreplay

   - start deprecation of mount option inode_cache, removal scheduled to
     v5.11

   - removed deprecated mount options alloc_start and subvolrootid

   - device stats corruption counter gets incremented when a checksum
     mismatch is found

   - qgroup information exported in /sys/fs/btrfs/<UUID>/qgroups/<id>
     using sysfs

   - add link /sys/fs/btrfs/<UUID>/bdi pointing to the associated
     backing dev info

   - FS_INFO ioctl enhancements:
      - add flags to request/describe newly added items
      - new item: numeric checksum type and checksum size
      - new item: generation
      - new item: metadata_uuid

   - seed device: with one new read-write device added, print the new
     device information in /proc/mounts

   - balance: detect cancellation by Ctrl-C in existing cancellation
     points

  Performance improvements:

   - optimized versions of various helpers on little-endian
     architectures, where we don't have to do LE/BE conversion from
     on-disk format

   - tree-log/fsync optimizations leading to lower max latency reported
     by dbench, reduced by about 12%

   - all chunk tree leaves are prefetched at mount time, can improve
     mount time on large (terabyte-sized) filesystems

   - speed up parallel fsync of files with reflinked/deduped extents,
     with jobs 16 to 1024 the throughput gets improved roughly by 50% on
     average and runtime decreased roughly by 30% on average, notable
     outlier is 128 jobs with +121.2% on throughput and -54.6% runtime

   - another speed up of parallel fsync, reduce number of checksum tree
     lookups and contention, the improvements start to show up with 2
     tasks with +20% throughput and -16% runtime up to 64 with +200%
     throughput and -66% runtime

  Core:

   - umount-time qgroup leak checker

   - qgroups
      - add a way to unreserve partial range after failure, avoiding
        some EDQUOT errors
      - improved flushing logic when EDQUOT is hit

   - possible EINTR interruption caused by failed reservations after
     transaction start is better handled and documented

   - transaction abort errors are unified to EROFS in case it's not the
     original reason of abort or we don't have other way to determine
     the reason

  Fixes:

   - make truncate succeed on a NOCOW file even if data space is
     exhausted

   - fix cancelling balance on filesystem with exhausted metadata space

   - anon block device:
      - preallocate anon bdev when subvolume is created to report
        failure early
      - shorten time the anon bdev id is allocated
      - don't allocate anon bdev for internal roots

   - minor memory leak in ref-verify

   - refuse invalid combinations of compression and NOCOW file flags

   - lockdep fixes, updating the device locks

   - remove obsolete fallback logic for block group profile adjustments
     when switching from 1 to more devices, causing allocation of
     unwanted block groups

  Other cleanups, refactoring, simplifications:

   - conversions from struct inode to struct btrfs_inode in internal
     functions

   - removal of unused struct members"

* tag 'for-5.9-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (151 commits)
  btrfs: do not set the full sync flag on the inode during page release
  btrfs: release old extent maps during page release
  btrfs: fix race between page release and a fast fsync
  btrfs: open-code remount flag setting in btrfs_remount
  btrfs: if we're restriping, use the target restripe profile
  btrfs: don't adjust bg flags and use default allocation profiles
  btrfs: fix lockdep splat from btrfs_dump_space_info
  btrfs: move the chunk_mutex in btrfs_read_chunk_tree
  btrfs: open device without device_list_mutex
  btrfs: sysfs: use NOFS for device creation
  btrfs: return EROFS for BTRFS_FS_STATE_ERROR cases
  btrfs: document special case error codes for fs errors
  btrfs: don't WARN if we abort a transaction with EROFS
  btrfs: reduce contention on log trees when logging checksums
  btrfs: remove done label in writepage_delalloc
  btrfs: add comments for btrfs_reserve_flush_enum
  btrfs: relocation: review the call sites which can be interrupted by signal
  btrfs: avoid possible signal interruption of btrfs_drop_snapshot() on relocation tree
  btrfs: relocation: allow signal to cancel balance
  btrfs: raid56: remove out label in __raid56_parity_recover
  ...

fs/btrfs/block-group.h

@@ -114,8 +114,7 @@ struct btrfs_block_group {
 	/* For block groups in the same raid type */
 	struct list_head list;
 
-	/* Usage count */
-	atomic_t count;
+	refcount_t refs;
 
 	/*
 	 * List of struct btrfs_free_clusters for this block group.

fs/btrfs/btrfs_inode.h

@@ -151,6 +151,17 @@ struct btrfs_inode {
 	 */
 	u64 last_unlink_trans;
 
+	/*
+	 * The id/generation of the last transaction where this inode was
+	 * either the source or the destination of a clone/dedupe operation.
+	 * Used when logging an inode to know if there are shared extents that
+	 * need special care when logging checksum items, to avoid duplicate
+	 * checksum items in a log (which can lead to a corruption where we end
+	 * up with missing checksum ranges after log replay).
+	 * Protected by the vfs inode lock.
+	 */
+	u64 last_reflink_trans;
+
 	/*
 	 * Number of bytes outstanding that are going to need csums.  This is
 	 * used in ENOSPC accounting.

fs/btrfs/check-integrity.c

@@ -631,10 +631,8 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 	int pass;
 
 	selected_super = kzalloc(sizeof(*selected_super), GFP_NOFS);
-	if (NULL == selected_super) {
-		pr_info("btrfsic: error, kmalloc failed!\n");
+	if (!selected_super)
 		return -ENOMEM;
-	}
 
 	list_for_each_entry(device, dev_head, dev_list) {
 		int i;
@@ -795,7 +793,6 @@ static int btrfsic_process_superblock_dev_mirror(
 	if (NULL == superblock_tmp) {
 		superblock_tmp = btrfsic_block_alloc();
 		if (NULL == superblock_tmp) {
-			pr_info("btrfsic: error, kmalloc failed!\n");
 			ret = -1;
 			goto out;
 		}
@@ -921,9 +918,7 @@ static struct btrfsic_stack_frame *btrfsic_stack_frame_alloc(void)
 	struct btrfsic_stack_frame *sf;
 
 	sf = kzalloc(sizeof(*sf), GFP_NOFS);
-	if (NULL == sf)
-		pr_info("btrfsic: alloc memory failed!\n");
-	else
+	if (sf)
 		sf->magic = BTRFSIC_BLOCK_STACK_FRAME_MAGIC_NUMBER;
 	return sf;
 }
@@ -1313,7 +1308,6 @@ static int btrfsic_create_link_to_next_block(
 	if (NULL == l) {
 		l = btrfsic_block_link_alloc();
 		if (NULL == l) {
-			pr_info("btrfsic: error, kmalloc failed!\n");
 			btrfsic_release_block_ctx(next_block_ctx);
 			*next_blockp = NULL;
 			return -1;
@@ -1470,7 +1464,6 @@ static int btrfsic_handle_extent_data(
 					mirror_num,
 					&block_was_created);
 			if (NULL == next_block) {
-				pr_info("btrfsic: error, kmalloc failed!\n");
 				btrfsic_release_block_ctx(&next_block_ctx);
 				return -1;
 			}
@@ -2013,7 +2006,6 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state,
 
 		block = btrfsic_block_alloc();
 		if (NULL == block) {
-			pr_info("btrfsic: error, kmalloc failed!\n");
 			btrfsic_release_block_ctx(&block_ctx);
 			goto continue_loop;
 		}
@@ -2234,7 +2226,6 @@ static int btrfsic_process_written_superblock(
 					mirror_num,
 					&was_created);
 			if (NULL == next_block) {
-				pr_info("btrfsic: error, kmalloc failed!\n");
 				btrfsic_release_block_ctx(&tmp_next_block_ctx);
 				return -1;
 			}
@@ -2542,10 +2533,8 @@ static struct btrfsic_block_link *btrfsic_block_link_lookup_or_add(
 						&state->block_link_hashtable);
 	if (NULL == l) {
 		l = btrfsic_block_link_alloc();
-		if (NULL == l) {
-			pr_info("btrfsic: error, kmalloc failed!\n");
+		if (!l)
 			return NULL;
-		}
 
 		l->block_ref_to = next_block;
 		l->block_ref_from = from_block;
@@ -2589,10 +2578,9 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add(
 		struct btrfsic_dev_state *dev_state;
 
 		block = btrfsic_block_alloc();
-		if (NULL == block) {
-			pr_info("btrfsic: error, kmalloc failed!\n");
+		if (!block)
 			return NULL;
-		}
+
 		dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev->bd_dev);
 		if (NULL == dev_state) {
 			pr_info("btrfsic: error, lookup dev_state failed!\n");
@@ -2797,10 +2785,8 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 		return -1;
 	}
 	state = kvzalloc(sizeof(*state), GFP_KERNEL);
-	if (!state) {
-		pr_info("btrfs check-integrity: allocation failed!\n");
+	if (!state)
 		return -ENOMEM;
-	}
 
 	if (!btrfsic_is_initialized) {
 		mutex_init(&btrfsic_mutex);
@@ -2829,7 +2815,6 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 
 		ds = btrfsic_dev_state_alloc();
 		if (NULL == ds) {
-			pr_info("btrfs check-integrity: kmalloc() failed!\n");
 			mutex_unlock(&btrfsic_mutex);
 			return -ENOMEM;
 		}

fs/btrfs/compression.c

@@ -172,18 +172,17 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
 		(DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size;
 }
 
-static int check_compressed_csum(struct btrfs_inode *inode,
-				 struct compressed_bio *cb,
+static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
 				 u64 disk_start)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
-	int ret;
 	struct page *page;
 	unsigned long i;
 	char *kaddr;
 	u8 csum[BTRFS_CSUM_SIZE];
+	struct compressed_bio *cb = bio->bi_private;
 	u8 *cb_sum = cb->sums;
 
 	if (inode->flags & BTRFS_INODE_NODATASUM)
@@ -201,15 +200,15 @@ static int check_compressed_csum(struct btrfs_inode *inode,
 		if (memcmp(&csum, cb_sum, csum_size)) {
 			btrfs_print_data_csum_error(inode, disk_start,
 					csum, cb_sum, cb->mirror_num);
-			ret = -EIO;
-			goto fail;
+			if (btrfs_io_bio(bio)->device)
+				btrfs_dev_stat_inc_and_print(
+					btrfs_io_bio(bio)->device,
+					BTRFS_DEV_STAT_CORRUPTION_ERRS);
+			return -EIO;
 		}
 		cb_sum += csum_size;
-
 	}
-	ret = 0;
-fail:
-	return ret;
+	return 0;
 }
 
 /* when we finish reading compressed pages from the disk, we
@@ -244,7 +243,6 @@ static void end_compressed_bio_read(struct bio *bio)
 	 * Record the correct mirror_num in cb->orig_bio so that
 	 * read-repair can work properly.
 	 */
-	ASSERT(btrfs_io_bio(cb->orig_bio));
 	btrfs_io_bio(cb->orig_bio)->mirror_num = mirror;
 	cb->mirror_num = mirror;
 
@@ -256,7 +254,7 @@ static void end_compressed_bio_read(struct bio *bio)
 		goto csum_failed;
 
 	inode = cb->inode;
-	ret = check_compressed_csum(BTRFS_I(inode), cb,
+	ret = check_compressed_csum(BTRFS_I(inode), bio,
 				    (u64)bio->bi_iter.bi_sector << 9);
 	if (ret)
 		goto csum_failed;
@@ -405,7 +403,7 @@ static void end_compressed_bio_write(struct bio *bio)
  * This also checksums the file bytes and gets things ready for
  * the end io hooks.
  */
-blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
+blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				 unsigned long len, u64 disk_start,
 				 unsigned long compressed_len,
 				 struct page **compressed_pages,
@@ -413,7 +411,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				 unsigned int write_flags,
 				 struct cgroup_subsys_state *blkcg_css)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct bio *bio = NULL;
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
@@ -421,7 +419,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct page *page;
 	u64 first_byte = disk_start;
 	blk_status_t ret;
-	int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+	int skip_sum = inode->flags & BTRFS_INODE_NODATASUM;
 
 	WARN_ON(!PAGE_ALIGNED(start));
 	cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
@@ -429,7 +427,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		return BLK_STS_RESOURCE;
 	refcount_set(&cb->pending_bios, 0);
 	cb->errors = 0;
-	cb->inode = inode;
+	cb->inode = &inode->vfs_inode;
 	cb->start = start;
 	cb->len = len;
 	cb->mirror_num = 0;
@@ -455,7 +453,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		int submit = 0;
 
 		page = compressed_pages[pg_index];
-		page->mapping = inode->i_mapping;
+		page->mapping = inode->vfs_inode.i_mapping;
 		if (bio->bi_iter.bi_size)
 			submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio,
 							  0);

fs/btrfs/compression.h

@@ -8,6 +8,8 @@
 
 #include <linux/sizes.h>
 
+struct btrfs_inode;
+
 /*
  * We want to make sure that amount of RAM required to uncompress an extent is
  * reasonable, so we limit the total size in ram of a compressed extent to
@@ -88,7 +90,7 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio);
 
-blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
+blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				  unsigned long len, u64 disk_start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,

fs/btrfs/ctree.c

@@ -1501,6 +1501,22 @@ static int close_blocks(u64 blocknr, u64 other, u32 blocksize)
 	return 0;
 }
 
+#ifdef __LITTLE_ENDIAN
+
+/*
+ * Compare two keys, on little-endian the disk order is same as CPU order and
+ * we can avoid the conversion.
+ */
+static int comp_keys(const struct btrfs_disk_key *disk_key,
+		     const struct btrfs_key *k2)
+{
+	const struct btrfs_key *k1 = (const struct btrfs_key *)disk_key;
+
+	return btrfs_comp_cpu_keys(k1, k2);
+}
+
+#else
+
 /*
  * compare two keys in a memcmp fashion
  */
@@ -1513,6 +1529,7 @@ static int comp_keys(const struct btrfs_disk_key *disk,
 
 	return btrfs_comp_cpu_keys(&k1, k2);
 }
+#endif
 
 /*
  * same as comp_keys only with two btrfs_key's

fs/btrfs/delalloc-space.c

@@ -237,10 +237,10 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 	return 0;
 }
 
-int btrfs_check_data_free_space(struct inode *inode,
+int btrfs_check_data_free_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 
 	/* align the range */
@@ -248,14 +248,14 @@ int btrfs_check_data_free_space(struct inode *inode,
 	      round_down(start, fs_info->sectorsize);
 	start = round_down(start, fs_info->sectorsize);
 
-	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
+	ret = btrfs_alloc_data_chunk_ondemand(inode, len);
 	if (ret < 0)
 		return ret;
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
 	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
 	if (ret < 0)
-		btrfs_free_reserved_data_space_noquota(inode, start, len);
+		btrfs_free_reserved_data_space_noquota(fs_info, len);
 	else
 		ret = 0;
 	return ret;
@@ -269,16 +269,12 @@ int btrfs_check_data_free_space(struct inode *inode,
  * which we can't sleep and is sure it won't affect qgroup reserved space.
  * Like clear_bit_hook().
  */
-void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info,
 					    u64 len)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_space_info *data_sinfo;
 
-	/* Make sure the range is aligned to sectorsize */
-	len = round_up(start + len, fs_info->sectorsize) -
-	      round_down(start, fs_info->sectorsize);
-	start = round_down(start, fs_info->sectorsize);
+	ASSERT(IS_ALIGNED(len, fs_info->sectorsize));
 
 	data_sinfo = fs_info->data_sinfo;
 	spin_lock(&data_sinfo->lock);
@@ -293,17 +289,17 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
  * This one will handle the per-inode data rsv map for accurate reserved
  * space framework.
  */
-void btrfs_free_reserved_data_space(struct inode *inode,
+void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	/* Make sure the range is aligned to sectorsize */
-	len = round_up(start + len, root->fs_info->sectorsize) -
-	      round_down(start, root->fs_info->sectorsize);
-	start = round_down(start, root->fs_info->sectorsize);
+	len = round_up(start + len, fs_info->sectorsize) -
+	      round_down(start, fs_info->sectorsize);
+	start = round_down(start, fs_info->sectorsize);
 
-	btrfs_free_reserved_data_space_noquota(inode, start, len);
+	btrfs_free_reserved_data_space_noquota(fs_info, len);
 	btrfs_qgroup_free_data(inode, reserved, start, len);
 }
 
@@ -557,7 +553,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
  * Return 0 for success
  * Return <0 for error(-ENOSPC or -EQUOT)
  */
-int btrfs_delalloc_reserve_space(struct inode *inode,
+int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	int ret;
@@ -565,7 +561,7 @@ int btrfs_delalloc_reserve_space(struct inode *inode,
 	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
+	ret = btrfs_delalloc_reserve_metadata(inode, len);
 	if (ret < 0)
 		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 	return ret;
@@ -583,10 +579,10 @@ int btrfs_delalloc_reserve_space(struct inode *inode,
  * list if there are no delalloc bytes left.
  * Also it will handle the qgroup reserved space.
  */
-void btrfs_delalloc_release_space(struct inode *inode,
+void btrfs_delalloc_release_space(struct btrfs_inode *inode,
 				  struct extent_changeset *reserved,
 				  u64 start, u64 len, bool qgroup_free)
 {
-	btrfs_delalloc_release_metadata(BTRFS_I(inode), len, qgroup_free);
+	btrfs_delalloc_release_metadata(inode, len, qgroup_free);
 	btrfs_free_reserved_data_space(inode, reserved, start, len);
 }

fs/btrfs/delalloc-space.h

@@ -6,18 +6,18 @@
 struct extent_changeset;
 
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
-int btrfs_check_data_free_space(struct inode *inode,
+int btrfs_check_data_free_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
-void btrfs_free_reserved_data_space(struct inode *inode,
+void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 			struct extent_changeset *reserved, u64 start, u64 len);
-void btrfs_delalloc_release_space(struct inode *inode,
+void btrfs_delalloc_release_space(struct btrfs_inode *inode,
 				  struct extent_changeset *reserved,
 				  u64 start, u64 len, bool qgroup_free);
-void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
+void btrfs_free_reserved_data_space_noquota(struct btrfs_fs_info *fs_info,
 					    u64 len);
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free);
-int btrfs_delalloc_reserve_space(struct inode *inode,
+int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
 
 #endif /* BTRFS_DELALLOC_SPACE_H */

fs/btrfs/disk-io.c

@@ -1116,6 +1116,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	mutex_init(&root->log_mutex);
 	mutex_init(&root->ordered_extent_mutex);
 	mutex_init(&root->delalloc_mutex);
+	init_waitqueue_head(&root->qgroup_flush_wait);
 	init_waitqueue_head(&root->log_writer_wait);
 	init_waitqueue_head(&root->log_commit_wait[0]);
 	init_waitqueue_head(&root->log_commit_wait[1]);
@@ -1141,10 +1142,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
 	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
-	if (!dummy)
-		root->defrag_trans_start = fs_info->generation;
-	else
-		root->defrag_trans_start = 0;
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
 
@@ -1395,7 +1392,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	goto out;
 }
 
-static int btrfs_init_fs_root(struct btrfs_root *root)
+/*
+ * Initialize subvolume root in-memory structure
+ *
+ * @anon_dev:	anonymous device to attach to the root, if zero, allocate new
+ */
+static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 {
 	int ret;
 	unsigned int nofs_flag;
@@ -1428,9 +1430,20 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
 	spin_lock_init(&root->ino_cache_lock);
 	init_waitqueue_head(&root->ino_cache_wait);
 
-	ret = get_anon_bdev(&root->anon_dev);
-	if (ret)
-		goto fail;
+	/*
+	 * Don't assign anonymous block device to roots that are not exposed to
+	 * userspace, the id pool is limited to 1M
+	 */
+	if (is_fstree(root->root_key.objectid) &&
+	    btrfs_root_refs(&root->root_item) > 0) {
+		if (!anon_dev) {
+			ret = get_anon_bdev(&root->anon_dev);
+			if (ret)
+				goto fail;
+		} else {
+			root->anon_dev = anon_dev;
+		}
+	}
 
 	mutex_lock(&root->objectid_mutex);
 	ret = btrfs_find_highest_objectid(root,
@@ -1534,8 +1547,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 }
 
 
-struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
-				     u64 objectid, bool check_ref)
+/*
+ * Get an in-memory reference of a root structure.
+ *
+ * For essential trees like root/extent tree, we grab it from fs_info directly.
+ * For subvolume trees, we check the cached filesystem roots first. If not
+ * found, then read it from disk and add it to cached fs roots.
+ *
+ * Caller should release the root by calling btrfs_put_root() after the usage.
+ *
+ * NOTE: Reloc and log trees can't be read by this function as they share the
+ *	 same root objectid.
+ *
+ * @objectid:	root id
+ * @anon_dev:	preallocated anonymous block device number for new roots,
+ * 		pass 0 for new allocation.
+ * @check_ref:	whether to check root item references, If true, return -ENOENT
+ *		for orphan roots
+ */
+static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
+					     u64 objectid, dev_t anon_dev,
+					     bool check_ref)
 {
 	struct btrfs_root *root;
 	struct btrfs_path *path;
@@ -1564,6 +1596,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
+		/* Shouldn't get preallocated anon_dev for cached roots */
+		ASSERT(!anon_dev);
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1583,7 +1617,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root);
+	ret = btrfs_init_fs_root(root, anon_dev);
 	if (ret)
 		goto fail;
 
@@ -1616,6 +1650,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 	return ERR_PTR(ret);
 }
 
+/*
+ * Get in-memory reference of a root structure
+ *
+ * @objectid:	tree objectid
+ * @check_ref:	if set, verify that the tree exists and the item has at least
+ *		one reference
+ */
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+				     u64 objectid, bool check_ref)
+{
+	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+}
+
+/*
+ * Get in-memory reference of a root structure, created as new, optionally pass
+ * the anonymous block device id
+ *
+ * @objectid:	tree objectid
+ * @anon_dev:	if zero, allocate a new anonymous block device or use the
+ *		parameter value
+ */
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+					 u64 objectid, dev_t anon_dev)
+{
+	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
+}
+
 static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 {
 	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
@@ -1749,7 +1810,6 @@ static int transaction_kthread(void *arg)
 
 		now = ktime_get_seconds();
 		if (cur->state < TRANS_STATE_COMMIT_START &&
-		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
 		     now - cur->start_time < fs_info->commit_interval)) {
 			spin_unlock(&fs_info->trans_lock);
@@ -2001,8 +2061,7 @@ void btrfs_put_root(struct btrfs_root *root)
 		if (root->anon_dev)
 			free_anon_bdev(root->anon_dev);
 		btrfs_drew_lock_destroy(&root->snapshot_lock);
-		free_extent_buffer(root->node);
-		free_extent_buffer(root->commit_root);
+		free_root_extent_buffers(root);
 		kfree(root->free_ino_ctl);
 		kfree(root->free_ino_pinned);
 #ifdef CONFIG_BTRFS_DEBUG
@@ -4058,6 +4117,11 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	ASSERT(list_empty(&fs_info->delayed_iputs));
 	set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
 
+	if (btrfs_check_quota_leak(fs_info)) {
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+		btrfs_err(fs_info, "qgroup reserved space leaked");
+	}
+
 	btrfs_free_qgroup_config(fs_info);
 	ASSERT(list_empty(&fs_info->delalloc_roots));
 

fs/btrfs/disk-io.h

@@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
 
 struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
 				     u64 objectid, bool check_ref);
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+					 u64 objectid, dev_t anon_dev);
 
 void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);

fs/btrfs/extent-io-tree.h

@@ -233,14 +233,11 @@ bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,
 			       struct extent_state **cached_state);
 
 /* This should be reworked in the future and put elsewhere. */
-int get_state_failrec(struct extent_io_tree *tree, u64 start,
-		      struct io_failure_record **failrec);
+struct io_failure_record *get_state_failrec(struct extent_io_tree *tree, u64 start);
 int set_state_failrec(struct extent_io_tree *tree, u64 start,
 		      struct io_failure_record *failrec);
 void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
 		u64 end);
-int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
-				struct io_failure_record **failrec_ret);
 int free_io_failure(struct extent_io_tree *failure_tree,
 		    struct extent_io_tree *io_tree,
 		    struct io_failure_record *rec);

fs/btrfs/extent-tree.c

@@ -5298,7 +5298,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		goto out;
 	}
 
-	trans = btrfs_start_transaction(tree_root, 0);
+	/*
+	 * Use join to avoid potential EINTR from transaction start. See
+	 * wait_reserve_ticket and the whole reservation callchain.
+	 */
+	if (for_reloc)
+		trans = btrfs_join_transaction(tree_root);
+	else
+		trans = btrfs_start_transaction(tree_root, 0);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto out_free;
@@ -5466,6 +5473,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		}
 	}
 
+	/*
+	 * This subvolume is going to be completely dropped, and won't be
+	 * recorded as dirty roots, thus pertrans meta rsv will not be freed at
+	 * commit transaction time.  So free it here manually.
+	 */
+	btrfs_qgroup_convert_reserved_meta(root, INT_MAX);
+	btrfs_qgroup_free_meta_all_pertrans(root);
+
 	if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state))
 		btrfs_add_dropped_root(trans, root);
 	else

fs/btrfs/extent_io.h

@@ -204,7 +204,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 			    struct writeback_control *wbc);
 void extent_readahead(struct readahead_control *rac);
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len);
+		  u64 start, u64 len);
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
@@ -277,7 +277,7 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb);
 int extent_buffer_under_io(const struct extent_buffer *eb);
 void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
-void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
 				  unsigned bits_to_clear,
 				  unsigned long page_ops);

fs/btrfs/file-item.c

@@ -522,10 +522,10 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
  *		 means this bio can contains potentially discontigous bio vecs
  *		 so the logical offset of each should be calculated separately.
  */
-blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 		       u64 file_start, int contig)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;

fs/btrfs/free-space-cache.c

@@ -1334,8 +1334,9 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	io_ctl_zero_remaining_pages(io_ctl);
 
 	/* Everything is written out, now we dirty the pages in the file. */
-	ret = btrfs_dirty_pages(inode, io_ctl->pages, io_ctl->num_pages, 0,
-				i_size_read(inode), &cached_state);
+	ret = btrfs_dirty_pages(BTRFS_I(inode), io_ctl->pages,
+				io_ctl->num_pages, 0, i_size_read(inode),
+				&cached_state);
 	if (ret)
 		goto out_nospc;
 
@@ -2703,8 +2704,7 @@ void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group)
  * pointed to by the cluster, someone else raced in and freed the
  * cluster already.  In that case, we just return without changing anything
  */
-static int
-__btrfs_return_cluster_to_free_space(
+static void __btrfs_return_cluster_to_free_space(
 			     struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster)
 {
@@ -2756,7 +2756,6 @@ __btrfs_return_cluster_to_free_space(
 out:
 	spin_unlock(&cluster->lock);
 	btrfs_put_block_group(block_group);
-	return 0;
 }
 
 static void __btrfs_remove_free_space_cache_locked(
@@ -2907,12 +2906,11 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
  * Otherwise, it'll get a reference on the block group pointed to by the
  * cluster and remove the cluster from it.
  */
-int btrfs_return_cluster_to_free_space(
+void btrfs_return_cluster_to_free_space(
 			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster)
 {
 	struct btrfs_free_space_ctl *ctl;
-	int ret;
 
 	/* first, get a safe pointer to the block group */
 	spin_lock(&cluster->lock);
@@ -2920,28 +2918,27 @@ int btrfs_return_cluster_to_free_space(
 		block_group = cluster->block_group;
 		if (!block_group) {
 			spin_unlock(&cluster->lock);
-			return 0;
+			return;
 		}
 	} else if (cluster->block_group != block_group) {
 		/* someone else has already freed it don't redo their work */
 		spin_unlock(&cluster->lock);
-		return 0;
+		return;
 	}
-	atomic_inc(&block_group->count);
+	btrfs_get_block_group(block_group);
 	spin_unlock(&cluster->lock);
 
 	ctl = block_group->free_space_ctl;
 
 	/* now return any extents the cluster had on it */
 	spin_lock(&ctl->tree_lock);
-	ret = __btrfs_return_cluster_to_free_space(block_group, cluster);
+	__btrfs_return_cluster_to_free_space(block_group, cluster);
 	spin_unlock(&ctl->tree_lock);
 
 	btrfs_discard_queue_work(&block_group->fs_info->discard_ctl, block_group);
 
 	/* finally drop our ref */
 	btrfs_put_block_group(block_group);
-	return ret;
 }
 
 static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group,
@@ -3358,7 +3355,7 @@ int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
 		list_del_init(&entry->list);
 
 	if (!ret) {
-		atomic_inc(&block_group->count);
+		btrfs_get_block_group(block_group);
 		list_add_tail(&cluster->block_group_list,
 			      &block_group->cluster_list);
 		cluster->block_group = block_group;

fs/btrfs/free-space-cache.h

@@ -136,7 +136,7 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
 u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     struct btrfs_free_cluster *cluster, u64 bytes,
 			     u64 min_start, u64 *max_extent_size);
-int btrfs_return_cluster_to_free_space(
+void btrfs_return_cluster_to_free_space(
 			       struct btrfs_block_group *block_group,
 			       struct btrfs_free_cluster *cluster);
 int btrfs_trim_block_group(struct btrfs_block_group *block_group,

fs/btrfs/inode-map.c

@@ -495,7 +495,8 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_SIZE;
 
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc);
+	ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, 0,
+					   prealloc);
 	if (ret)
 		goto out_put;
 

fs/btrfs/ioctl.c

@@ -164,8 +164,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
 	return 0;
 }
 
-/* Check if @flags are a supported and valid set of FS_*_FL flags */
-static int check_fsflags(unsigned int flags)
+/*
+ * Check if @flags are a supported and valid set of FS_*_FL flags and that
+ * the old and new flags are not conflicting
+ */
+static int check_fsflags(unsigned int old_flags, unsigned int flags)
 {
 	if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
 		      FS_NOATIME_FL | FS_NODUMP_FL | \
@@ -174,9 +177,19 @@ static int check_fsflags(unsigned int flags)
 		      FS_NOCOW_FL))
 		return -EOPNOTSUPP;
 
+	/* COMPR and NOCOMP on new/old are valid */
 	if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
 		return -EINVAL;
 
+	if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL))
+		return -EINVAL;
+
+	/* NOCOW and compression options are mutually exclusive */
+	if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL)))
+		return -EINVAL;
+	if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL)))
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -190,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	unsigned int fsflags, old_fsflags;
 	int ret;
 	const char *comp = NULL;
-	u32 binode_flags = binode->flags;
+	u32 binode_flags;
 
 	if (!inode_owner_or_capable(inode))
 		return -EPERM;
@@ -201,22 +214,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
 		return -EFAULT;
 
-	ret = check_fsflags(fsflags);
-	if (ret)
-		return ret;
-
 	ret = mnt_want_write_file(file);
 	if (ret)
 		return ret;
 
 	inode_lock(inode);
-
 	fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
 	old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
+
 	ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
 	if (ret)
 		goto out_unlock;
 
+	ret = check_fsflags(old_fsflags, fsflags);
+	if (ret)
+		goto out_unlock;
+
+	binode_flags = binode->flags;
 	if (fsflags & FS_SYNC_FL)
 		binode_flags |= BTRFS_INODE_SYNC;
 	else
@@ -566,6 +580,7 @@ static noinline int create_subvol(struct inode *dir,
 	struct inode *inode;
 	int ret;
 	int err;
+	dev_t anon_dev = 0;
 	u64 objectid;
 	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
@@ -578,6 +593,10 @@ static noinline int create_subvol(struct inode *dir,
 	if (ret)
 		goto fail_free;
 
+	ret = get_anon_bdev(&anon_dev);
+	if (ret < 0)
+		goto fail_free;
+
 	/*
 	 * Don't create subvolume whose level is not zero. Or qgroup will be
 	 * screwed up since it assumes subvolume qgroup's level to be 0.
@@ -660,12 +679,15 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 
 	key.offset = (u64)-1;
-	new_root = btrfs_get_fs_root(fs_info, objectid, true);
+	new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
 	if (IS_ERR(new_root)) {
+		free_anon_bdev(anon_dev);
 		ret = PTR_ERR(new_root);
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
+	/* Freeing will be done in btrfs_put_root() of new_root */
+	anon_dev = 0;
 
 	btrfs_record_root_in_trans(trans, new_root);
 
@@ -735,6 +757,8 @@ static noinline int create_subvol(struct inode *dir,
 	return ret;
 
 fail_free:
+	if (anon_dev)
+		free_anon_bdev(anon_dev);
 	kfree(root_item);
 	return ret;
 }
@@ -762,6 +786,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (!pending_snapshot)
 		return -ENOMEM;
 
+	ret = get_anon_bdev(&pending_snapshot->anon_dev);
+	if (ret < 0)
+		goto free_pending;
 	pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
 			GFP_KERNEL);
 	pending_snapshot->path = btrfs_alloc_path();
@@ -823,10 +850,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 
 	d_instantiate(dentry, inode);
 	ret = 0;
+	pending_snapshot->anon_dev = 0;
 fail:
+	/* Prevent double freeing of anon_dev */
+	if (ret && pending_snapshot->snap)
+		pending_snapshot->snap->anon_dev = 0;
 	btrfs_put_root(pending_snapshot->snap);
 	btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
 free_pending:
+	if (pending_snapshot->anon_dev)
+		free_anon_bdev(pending_snapshot->anon_dev);
 	kfree(pending_snapshot->root_item);
 	btrfs_free_path(pending_snapshot->path);
 	kfree(pending_snapshot);
@@ -1243,7 +1276,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+	ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
 	if (ret)
@@ -1265,7 +1298,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		while (1) {
 			lock_extent_bits(tree, page_start, page_end,
 					 &cached_state);
-			ordered = btrfs_lookup_ordered_extent(inode,
+			ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode),
 							      page_start);
 			unlock_extent_cached(tree, page_start, page_end,
 					     &cached_state);
@@ -1333,7 +1366,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		spin_lock(&BTRFS_I(inode)->lock);
 		btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
 		spin_unlock(&BTRFS_I(inode)->lock);
-		btrfs_delalloc_release_space(inode, data_reserved,
+		btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
 				start_index << PAGE_SHIFT,
 				(page_cnt - i_done) << PAGE_SHIFT, true);
 	}
@@ -1361,7 +1394,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
-	btrfs_delalloc_release_space(inode, data_reserved,
+	btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT, true);
 	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
@@ -3198,11 +3231,15 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
 	struct btrfs_ioctl_fs_info_args *fi_args;
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	u64 flags_in;
 	int ret = 0;
 
-	fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
-	if (!fi_args)
-		return -ENOMEM;
+	fi_args = memdup_user(arg, sizeof(*fi_args));
+	if (IS_ERR(fi_args))
+		return PTR_ERR(fi_args);
+
+	flags_in = fi_args->flags;
+	memset(fi_args, 0, sizeof(*fi_args));
 
 	rcu_read_lock();
 	fi_args->num_devices = fs_devices->num_devices;
@@ -3218,6 +3255,23 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
 	fi_args->sectorsize = fs_info->sectorsize;
 	fi_args->clone_alignment = fs_info->sectorsize;
 
+	if (flags_in & BTRFS_FS_INFO_FLAG_CSUM_INFO) {
+		fi_args->csum_type = btrfs_super_csum_type(fs_info->super_copy);
+		fi_args->csum_size = btrfs_super_csum_size(fs_info->super_copy);
+		fi_args->flags |= BTRFS_FS_INFO_FLAG_CSUM_INFO;
+	}
+
+	if (flags_in & BTRFS_FS_INFO_FLAG_GENERATION) {
+		fi_args->generation = fs_info->generation;
+		fi_args->flags |= BTRFS_FS_INFO_FLAG_GENERATION;
+	}
+
+	if (flags_in & BTRFS_FS_INFO_FLAG_METADATA_UUID) {
+		memcpy(&fi_args->metadata_uuid, fs_devices->metadata_uuid,
+		       sizeof(fi_args->metadata_uuid));
+		fi_args->flags |= BTRFS_FS_INFO_FLAG_METADATA_UUID;
+	}
+
 	if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
 		ret = -EFAULT;
 

fs/btrfs/ordered-data.c

@@ -15,6 +15,7 @@
 #include "disk-io.h"
 #include "compression.h"
 #include "delalloc-space.h"
+#include "qgroup.h"
 
 static struct kmem_cache *btrfs_ordered_extent_cache;
 
@@ -152,23 +153,39 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
 	return ret;
 }
 
-/* allocate and add a new ordered_extent into the per-inode tree.
+/*
+ * Allocate and add a new ordered_extent into the per-inode tree.
  *
  * The tree is given a single reference on the ordered extent that was
  * inserted.
  */
-static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
+static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
 				      u64 disk_bytenr, u64 num_bytes,
 				      u64 disk_num_bytes, int type, int dio,
 				      int compress_type)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_ordered_inode_tree *tree;
+	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry;
+	int ret;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	if (type == BTRFS_ORDERED_NOCOW || type == BTRFS_ORDERED_PREALLOC) {
+		/* For nocow write, we can release the qgroup rsv right now */
+		ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes);
+		if (ret < 0)
+			return ret;
+		ret = 0;
+	} else {
+		/*
+		 * The ordered extent has reserved qgroup space, release now
+		 * and pass the reserved number for qgroup_record to free.
+		 */
+		ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes);
+		if (ret < 0)
+			return ret;
+	}
 	entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
 	if (!entry)
 		return -ENOMEM;
@@ -178,9 +195,10 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	entry->num_bytes = num_bytes;
 	entry->disk_num_bytes = disk_num_bytes;
 	entry->bytes_left = num_bytes;
-	entry->inode = igrab(inode);
+	entry->inode = igrab(&inode->vfs_inode);
 	entry->compress_type = compress_type;
 	entry->truncated_len = (u64)-1;
+	entry->qgroup_rsv = ret;
 	if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
 		set_bit(type, &entry->flags);
 
@@ -197,10 +215,8 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	INIT_LIST_HEAD(&entry->root_extent_list);
 	INIT_LIST_HEAD(&entry->work_list);
 	init_completion(&entry->completion);
-	INIT_LIST_HEAD(&entry->log_list);
-	INIT_LIST_HEAD(&entry->trans_list);
 
-	trace_btrfs_ordered_extent_add(inode, entry);
+	trace_btrfs_ordered_extent_add(&inode->vfs_inode, entry);
 
 	spin_lock_irq(&tree->lock);
 	node = tree_insert(&tree->tree, file_offset,
@@ -228,14 +244,14 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	 * that work has been done at higher layers, so this is truly the
 	 * smallest the extent is going to get.
 	 */
-	spin_lock(&BTRFS_I(inode)->lock);
-	btrfs_mod_outstanding_extents(BTRFS_I(inode), 1);
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
+	btrfs_mod_outstanding_extents(inode, 1);
+	spin_unlock(&inode->lock);
 
 	return 0;
 }
 
-int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
 			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
 			     int type)
 {
@@ -244,7 +260,7 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 					  BTRFS_COMPRESS_NONE);
 }
 
-int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
 				 u64 disk_bytenr, u64 num_bytes,
 				 u64 disk_num_bytes, int type)
 {
@@ -253,7 +269,7 @@ int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
 					  BTRFS_COMPRESS_NONE);
 }
 
-int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
 				      u64 disk_bytenr, u64 num_bytes,
 				      u64 disk_num_bytes, int type,
 				      int compress_type)
@@ -291,12 +307,12 @@ void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
  * file_offset is updated to one byte past the range that is recorded as
  * complete.  This allows you to walk forward in the file.
  */
-int btrfs_dec_test_first_ordered_pending(struct inode *inode,
+int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
 				   struct btrfs_ordered_extent **cached,
 				   u64 *file_offset, u64 io_size, int uptodate)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_ordered_inode_tree *tree;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry = NULL;
 	int ret;
@@ -305,7 +321,6 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 	u64 dec_start;
 	u64 to_dec;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
 	spin_lock_irqsave(&tree->lock, flags);
 	node = tree_search(tree, *file_offset);
 	if (!node) {
@@ -429,8 +444,6 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 	trace_btrfs_ordered_extent_put(entry->inode, entry);
 
 	if (refcount_dec_and_test(&entry->refs)) {
-		ASSERT(list_empty(&entry->log_list));
-		ASSERT(list_empty(&entry->trans_list));
 		ASSERT(list_empty(&entry->root_extent_list));
 		ASSERT(RB_EMPTY_NODE(&entry->rb_node));
 		if (entry->inode)
@@ -698,14 +711,14 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
  * find an ordered extent corresponding to file_offset.  return NULL if
  * nothing is found, otherwise take a reference on the extent and return it
  */
-struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
+struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
 							 u64 file_offset)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry = NULL;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	tree = &inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	node = tree_search(tree, file_offset);
 	if (!node)
@@ -803,7 +816,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 	int index = 0;
 
-	ordered = btrfs_lookup_ordered_extent(inode, offset);
+	ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), offset);
 	if (!ordered)
 		return 0;
 

fs/btrfs/ordered-data.h

@@ -92,6 +92,9 @@ struct btrfs_ordered_extent {
 	/* compression algorithm */
 	int compress_type;
 
+	/* Qgroup reserved space */
+	int qgroup_rsv;
+
 	/* reference count */
 	refcount_t refs;
 
@@ -101,12 +104,6 @@ struct btrfs_ordered_extent {
 	/* list of checksums for insertion when the extent io is done */
 	struct list_head list;
 
-	/* If we need to wait on this to be done */
-	struct list_head log_list;
-
-	/* If the transaction needs to wait on this ordered extent */
-	struct list_head trans_list;
-
 	/* used to wait for the BTRFS_ORDERED_COMPLETE bit */
 	wait_queue_head_t wait;
 
@@ -150,23 +147,23 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 int btrfs_dec_test_ordered_pending(struct inode *inode,
 				   struct btrfs_ordered_extent **cached,
 				   u64 file_offset, u64 io_size, int uptodate);
-int btrfs_dec_test_first_ordered_pending(struct inode *inode,
+int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
 				   struct btrfs_ordered_extent **cached,
 				   u64 *file_offset, u64 io_size,
 				   int uptodate);
-int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
 			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
 			     int type);
-int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
 				 u64 disk_bytenr, u64 num_bytes,
 				 u64 disk_num_bytes, int type);
-int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
+int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
 				      u64 disk_bytenr, u64 num_bytes,
 				      u64 disk_num_bytes, int type,
 				      int compress_type);
 void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 			   struct btrfs_ordered_sum *sum);
-struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
+struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
 							 u64 file_offset);
 void btrfs_start_ordered_extent(struct inode *inode,
 				struct btrfs_ordered_extent *entry, int wait);

fs/btrfs/qgroup.h

@@ -8,6 +8,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/rbtree.h>
+#include <linux/kobject.h>
 #include "ulist.h"
 #include "delayed-ref.h"
 
@@ -223,8 +224,18 @@ struct btrfs_qgroup {
 	 */
 	u64 old_refcnt;
 	u64 new_refcnt;
+
+	/*
+	 * Sysfs kobjectid
+	 */
+	struct kobject kobj;
 };
 
+static inline u64 btrfs_qgroup_subvolid(u64 qgroupid)
+{
+	return (qgroupid & ((1ULL << BTRFS_QGROUP_LEVEL_SHIFT) - 1));
+}
+
 /*
  * For qgroup event trace points only
  */
@@ -344,12 +355,12 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 #endif
 
 /* New io_tree based accurate qgroup reserve API */
-int btrfs_qgroup_reserve_data(struct inode *inode,
+int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
 			struct extent_changeset **reserved, u64 start, u64 len);
-int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len);
-int btrfs_qgroup_free_data(struct inode *inode,
-			struct extent_changeset *reserved, u64 start, u64 len);
-
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len);
+int btrfs_qgroup_free_data(struct btrfs_inode *inode,
+			   struct extent_changeset *reserved, u64 start,
+			   u64 len);
 int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 				enum btrfs_qgroup_rsv_type type, bool enforce);
 /* Reserve metadata space for pertrans and prealloc type */
@@ -399,7 +410,7 @@ void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root);
  */
 void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes);
 
-void btrfs_qgroup_check_reserved_leak(struct inode *inode);
+void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode);
 
 /* btrfs_qgroup_swapped_blocks related functions */
 void btrfs_qgroup_init_swapped_blocks(
@@ -415,5 +426,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 		struct btrfs_root *root, struct extent_buffer *eb);
 void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
+bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info);
 
 #endif

fs/btrfs/raid56.c

@@ -1083,7 +1083,6 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 			    unsigned long bio_max_len)
 {
 	struct bio *last = bio_list->tail;
-	u64 last_end = 0;
 	int ret;
 	struct bio *bio;
 	struct btrfs_bio_stripe *stripe;
@@ -1098,15 +1097,14 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 
 	/* see if we can add this page onto our existing bio */
 	if (last) {
-		last_end = (u64)last->bi_iter.bi_sector << 9;
+		u64 last_end = (u64)last->bi_iter.bi_sector << 9;
 		last_end += last->bi_iter.bi_size;
 
 		/*
 		 * we can't merge these if they are from different
 		 * devices or if they are not contiguous
 		 */
-		if (last_end == disk_start && stripe->dev->bdev &&
-		    !last->bi_status &&
+		if (last_end == disk_start && !last->bi_status &&
 		    last->bi_disk == stripe->dev->bdev->bd_disk &&
 		    last->bi_partno == stripe->dev->bdev->bd_partno) {
 			ret = bio_add_page(last, page, PAGE_SIZE, 0);
@@ -1117,6 +1115,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 
 	/* put a new bio on the list */
 	bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
+	btrfs_io_bio(bio)->device = stripe->dev;
 	bio->bi_iter.bi_size = 0;
 	bio_set_dev(bio, stripe->dev->bdev);
 	bio->bi_iter.bi_sector = disk_start >> 9;
@@ -1325,11 +1324,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 	atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list));
 	BUG_ON(atomic_read(&rbio->stripes_pending) == 0);
 
-	while (1) {
-		bio = bio_list_pop(&bio_list);
-		if (!bio)
-			break;
-
+	while ((bio = bio_list_pop(&bio_list))) {
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
 		bio->bi_opf = REQ_OP_WRITE;
@@ -1354,7 +1349,6 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 			   struct bio *bio)
 {
 	u64 physical = bio->bi_iter.bi_sector;
-	u64 stripe_start;
 	int i;
 	struct btrfs_bio_stripe *stripe;
 
@@ -1362,9 +1356,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 
 	for (i = 0; i < rbio->bbio->num_stripes; i++) {
 		stripe = &rbio->bbio->stripes[i];
-		stripe_start = stripe->physical;
-		if (physical >= stripe_start &&
-		    physical < stripe_start + rbio->stripe_len &&
+		if (in_range(physical, stripe->physical, rbio->stripe_len) &&
 		    stripe->dev->bdev &&
 		    bio->bi_disk == stripe->dev->bdev->bd_disk &&
 		    bio->bi_partno == stripe->dev->bdev->bd_partno) {
@@ -1382,18 +1374,14 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
 				   struct bio *bio)
 {
-	u64 logical = bio->bi_iter.bi_sector;
-	u64 stripe_start;
+	u64 logical = (u64)bio->bi_iter.bi_sector << 9;
 	int i;
 
-	logical <<= 9;
-
 	for (i = 0; i < rbio->nr_data; i++) {
-		stripe_start = rbio->bbio->raid_map[i];
-		if (logical >= stripe_start &&
-		    logical < stripe_start + rbio->stripe_len) {
+		u64 stripe_start = rbio->bbio->raid_map[i];
+
+		if (in_range(logical, stripe_start, rbio->stripe_len))
 			return i;
-		}
 	}
 	return -1;
 }
@@ -1567,11 +1555,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 	 * not to touch it after that
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
-	while (1) {
-		bio = bio_list_pop(&bio_list);
-		if (!bio)
-			break;
-
+	while ((bio = bio_list_pop(&bio_list))) {
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
 		bio->bi_opf = REQ_OP_READ;
@@ -1878,11 +1862,8 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			}
 
 			/* make sure our ps and qs are in order */
-			if (faila > failb) {
-				int tmp = failb;
-				failb = faila;
-				faila = tmp;
-			}
+			if (faila > failb)
+				swap(faila, failb);
 
 			/* if the q stripe is failed, do a pstripe reconstruction
 			 * from the xors.
@@ -2102,7 +2083,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 		 */
 		if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) {
 			__raid_recover_end_io(rbio);
-			goto out;
+			return 0;
 		} else {
 			goto cleanup;
 		}
@@ -2113,11 +2094,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	 * not to touch it after that
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
-	while (1) {
-		bio = bio_list_pop(&bio_list);
-		if (!bio)
-			break;
-
+	while ((bio = bio_list_pop(&bio_list))) {
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
 		bio->bi_opf = REQ_OP_READ;
@@ -2126,7 +2103,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 		submit_bio(bio);
 	}
-out:
+
 	return 0;
 
 cleanup:
@@ -2482,11 +2459,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 
 	atomic_set(&rbio->stripes_pending, nr_data);
 
-	while (1) {
-		bio = bio_list_pop(&bio_list);
-		if (!bio)
-			break;
-
+	while ((bio = bio_list_pop(&bio_list))) {
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
 		bio->bi_opf = REQ_OP_WRITE;
@@ -2664,11 +2637,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 	 * not to touch it after that
 	 */
 	atomic_set(&rbio->stripes_pending, bios_to_read);
-	while (1) {
-		bio = bio_list_pop(&bio_list);
-		if (!bio)
-			break;
-
+	while ((bio = bio_list_pop(&bio_list))) {
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
 		bio->bi_opf = REQ_OP_READ;

fs/btrfs/ref-verify.c

@@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info,
 			exist_re = insert_root_entry(&exist->roots, re);
 			if (exist_re)
 				kfree(re);
+		} else {
+			kfree(re);
 		}
 		kfree(be);
 		return exist;

fs/btrfs/reflink.c

@@ -68,8 +68,8 @@ static int copy_inline_to_page(struct inode *inode,
 	 * reservation here. Also we must not do the reservation while holding
 	 * a transaction open, otherwise we would deadlock.
 	 */
-	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, file_offset,
-					   block_size);
+	ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
+					   file_offset, block_size);
 	if (ret)
 		goto out;
 
@@ -84,7 +84,8 @@ static int copy_inline_to_page(struct inode *inode,
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, file_offset, range_end,
 			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			 0, 0, NULL);
-	ret = btrfs_set_extent_delalloc(inode, file_offset, range_end, 0, NULL);
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode), file_offset, range_end,
+					0, NULL);
 	if (ret)
 		goto out_unlock;
 
@@ -133,8 +134,8 @@ static int copy_inline_to_page(struct inode *inode,
 		put_page(page);
 	}
 	if (ret)
-		btrfs_delalloc_release_space(inode, data_reserved, file_offset,
-					     block_size, true);
+		btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved,
+					     file_offset, block_size, true);
 	btrfs_delalloc_release_extents(BTRFS_I(inode), block_size);
 out:
 	extent_changeset_free(data_reserved);
@@ -336,6 +337,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	while (1) {
 		u64 next_key_min_offset = key.offset + 1;
 		struct btrfs_file_extent_item *extent;
+		u64 extent_gen;
 		int type;
 		u32 size;
 		struct btrfs_key new_key;
@@ -384,6 +386,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 
 		extent = btrfs_item_ptr(leaf, slot,
 					struct btrfs_file_extent_item);
+		extent_gen = btrfs_file_extent_generation(leaf, extent);
 		comp = btrfs_file_extent_compression(leaf, extent);
 		type = btrfs_file_extent_type(leaf, extent);
 		if (type == BTRFS_FILE_EXTENT_REG ||
@@ -488,6 +491,19 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 
 		btrfs_release_path(path);
 
+		/*
+		 * If this is a new extent update the last_reflink_trans of both
+		 * inodes. This is used by fsync to make sure it does not log
+		 * multiple checksum items with overlapping ranges. For older
+		 * extents we don't need to do it since inode logging skips the
+		 * checksums for older extents. Also ignore holes and inline
+		 * extents because they don't have checksums in the csum tree.
+		 */
+		if (extent_gen == trans->transid && disko > 0) {
+			BTRFS_I(src)->last_reflink_trans = trans->transid;
+			BTRFS_I(inode)->last_reflink_trans = trans->transid;
+		}
+
 		last_dest_end = ALIGN(new_key.offset + datal,
 				      fs_info->sectorsize);
 		ret = clone_finish_inode_update(trans, inode, last_dest_end,

fs/btrfs/relocation.c

@@ -1686,12 +1686,20 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 		btrfs_unlock_up_safe(path, 0);
 	}
 
-	min_reserved = fs_info->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
+	/*
+	 * In merge_reloc_root(), we modify the upper level pointer to swap the
+	 * tree blocks between reloc tree and subvolume tree.  Thus for tree
+	 * block COW, we COW at most from level 1 to root level for each tree.
+	 *
+	 * Thus the needed metadata size is at most root_level * nodesize,
+	 * and * 2 since we have two trees to COW.
+	 */
+	min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2;
 	memset(&next_key, 0, sizeof(next_key));
 
 	while (1) {
 		ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved,
-					     BTRFS_RESERVE_FLUSH_ALL);
+					     BTRFS_RESERVE_FLUSH_LIMIT);
 		if (ret) {
 			err = ret;
 			goto out;
@@ -2571,58 +2579,50 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	return err;
 }
 
-static noinline_for_stack
-int prealloc_file_extent_cluster(struct inode *inode,
-				 struct file_extent_cluster *cluster)
+static noinline_for_stack int prealloc_file_extent_cluster(
+				struct btrfs_inode *inode,
+				struct file_extent_cluster *cluster)
 {
 	u64 alloc_hint = 0;
 	u64 start;
 	u64 end;
-	u64 offset = BTRFS_I(inode)->index_cnt;
+	u64 offset = inode->index_cnt;
 	u64 num_bytes;
-	int nr = 0;
+	int nr;
 	int ret = 0;
 	u64 prealloc_start = cluster->start - offset;
 	u64 prealloc_end = cluster->end - offset;
-	u64 cur_offset;
-	struct extent_changeset *data_reserved = NULL;
+	u64 cur_offset = prealloc_start;
 
 	BUG_ON(cluster->start != cluster->boundary[0]);
-	inode_lock(inode);
-
-	ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start,
-					  prealloc_end + 1 - prealloc_start);
+	ret = btrfs_alloc_data_chunk_ondemand(inode,
+					      prealloc_end + 1 - prealloc_start);
 	if (ret)
-		goto out;
+		return ret;
 
-	cur_offset = prealloc_start;
-	while (nr < cluster->nr) {
+	inode_lock(&inode->vfs_inode);
+	for (nr = 0; nr < cluster->nr; nr++) {
 		start = cluster->boundary[nr] - offset;
 		if (nr + 1 < cluster->nr)
 			end = cluster->boundary[nr + 1] - 1 - offset;
 		else
 			end = cluster->end - offset;
 
-		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
+		lock_extent(&inode->io_tree, start, end);
 		num_bytes = end + 1 - start;
-		if (cur_offset < start)
-			btrfs_free_reserved_data_space(inode, data_reserved,
-					cur_offset, start - cur_offset);
-		ret = btrfs_prealloc_file_range(inode, 0, start,
+		ret = btrfs_prealloc_file_range(&inode->vfs_inode, 0, start,
 						num_bytes, num_bytes,
 						end + 1, &alloc_hint);
 		cur_offset = end + 1;
-		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
+		unlock_extent(&inode->io_tree, start, end);
 		if (ret)
 			break;
-		nr++;
 	}
+	inode_unlock(&inode->vfs_inode);
+
 	if (cur_offset < prealloc_end)
-		btrfs_free_reserved_data_space(inode, data_reserved,
-				cur_offset, prealloc_end + 1 - cur_offset);
-out:
-	inode_unlock(inode);
-	extent_changeset_free(data_reserved);
+		btrfs_free_reserved_data_space_noquota(inode->root->fs_info,
+					       prealloc_end + 1 - cur_offset);
 	return ret;
 }
 
@@ -2664,7 +2664,8 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
  */
 int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
 {
-	return atomic_read(&fs_info->balance_cancel_req);
+	return atomic_read(&fs_info->balance_cancel_req) ||
+		fatal_signal_pending(current);
 }
 ALLOW_ERROR_INJECTION(btrfs_should_cancel_balance, TRUE);
 
@@ -2690,7 +2691,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	if (!ra)
 		return -ENOMEM;
 
-	ret = prealloc_file_extent_cluster(inode, cluster);
+	ret = prealloc_file_extent_cluster(BTRFS_I(inode), cluster);
 	if (ret)
 		goto out;
 
@@ -2762,8 +2763,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			nr++;
 		}
 
-		ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
-						NULL);
+		ret = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start,
+						page_end, 0, NULL);
 		if (ret) {
 			unlock_page(page);
 			put_page(page);
@@ -3872,9 +3873,9 @@ int btrfs_recover_relocation(struct btrfs_root *root)
  * cloning checksum properly handles the nodatasum extents.
  * it also saves CPU time to re-calculate the checksum.
  */
-int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
+int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered;
 	int ret;
@@ -3885,7 +3886,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len)
 	ordered = btrfs_lookup_ordered_extent(inode, file_pos);
 	BUG_ON(ordered->file_offset != file_pos || ordered->num_bytes != len);
 
-	disk_bytenr = file_pos + BTRFS_I(inode)->index_cnt;
+	disk_bytenr = file_pos + inode->index_cnt;
 	ret = btrfs_lookup_csums_range(fs_info->csum_root, disk_bytenr,
 				       disk_bytenr + len - 1, &list, 0);
 	if (ret)

fs/btrfs/space-info.c

@@ -468,8 +468,8 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
 			"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
 			cache->start, cache->length, cache->used, cache->pinned,
 			cache->reserved, cache->ro ? "[readonly]" : "");
-		btrfs_dump_free_space(cache, bytes);
 		spin_unlock(&cache->lock);
+		btrfs_dump_free_space(cache, bytes);
 	}
 	if (++index < BTRFS_NR_RAID_TYPES)
 		goto again;

fs/btrfs/sysfs.h

@@ -36,4 +36,11 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
 void btrfs_sysfs_update_devid(struct btrfs_device *device);
 
+int btrfs_sysfs_add_one_qgroup(struct btrfs_fs_info *fs_info,
+				struct btrfs_qgroup *qgroup);
+void btrfs_sysfs_del_qgroups(struct btrfs_fs_info *fs_info);
+int btrfs_sysfs_add_qgroups(struct btrfs_fs_info *fs_info);
+void btrfs_sysfs_del_one_qgroup(struct btrfs_fs_info *fs_info,
+				struct btrfs_qgroup *qgroup);
+
 #endif

fs/btrfs/tests/free-space-tree-tests.c

@@ -60,8 +60,6 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans,
 				if (prev_bit == 0 && bit == 1) {
 					extent_start = offset;
 				} else if (prev_bit == 1 && bit == 0) {
-					if (i >= num_extents)
-						goto invalid;
 					if (i >= num_extents ||
 					    extent_start != extents[i].start ||
 					    offset - extent_start != extents[i].length)

fs/btrfs/tests/inode-tests.c

@@ -954,8 +954,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	btrfs_test_inode_set_ops(inode);
 
 	/* [BTRFS_MAX_EXTENT_SIZE] */
-	ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0,
-					NULL);
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode), 0,
+					BTRFS_MAX_EXTENT_SIZE - 1, 0, NULL);
 	if (ret) {
 		test_err("btrfs_set_extent_delalloc returned %d", ret);
 		goto out;
@@ -968,7 +968,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	}
 
 	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE,
 					BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
 					0, NULL);
 	if (ret) {
@@ -999,7 +999,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	}
 
 	/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
-	ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode), BTRFS_MAX_EXTENT_SIZE >> 1,
 					(BTRFS_MAX_EXTENT_SIZE >> 1)
 					+ sectorsize - 1,
 					0, NULL);
@@ -1017,7 +1017,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	/*
 	 * [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize HOLE][BTRFS_MAX_EXTENT_SIZE+sectorsize]
 	 */
-	ret = btrfs_set_extent_delalloc(inode,
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode),
 			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
 			(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
 			0, NULL);
@@ -1035,7 +1035,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	/*
 	* [BTRFS_MAX_EXTENT_SIZE+sectorsize][sectorsize][BTRFS_MAX_EXTENT_SIZE+sectorsize]
 	*/
-	ret = btrfs_set_extent_delalloc(inode,
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode),
 			BTRFS_MAX_EXTENT_SIZE + sectorsize,
 			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL);
 	if (ret) {
@@ -1069,7 +1069,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
 	 * Refill the hole again just for good measure, because I thought it
 	 * might fail and I'd rather satisfy my paranoia at this point.
 	 */
-	ret = btrfs_set_extent_delalloc(inode,
+	ret = btrfs_set_extent_delalloc(BTRFS_I(inode),
 			BTRFS_MAX_EXTENT_SIZE + sectorsize,
 			BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL);
 	if (ret) {

fs/btrfs/transaction.c

@@ -937,7 +937,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (TRANS_ABORTED(trans) ||
 	    test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) {
 		wake_up_process(info->transaction_kthread);
-		err = -EIO;
+		if (TRANS_ABORTED(trans))
+			err = trans->aborted;
+		else
+			err = -EROFS;
 	}
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
@@ -1630,7 +1633,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	}
 
 	key.offset = (u64)-1;
-	pending->snap = btrfs_get_fs_root(fs_info, objectid, true);
+	pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
 	if (IS_ERR(pending->snap)) {
 		ret = PTR_ERR(pending->snap);
 		btrfs_abort_transaction(trans, ret);
@@ -2351,7 +2354,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	 */
 	cur_trans->state = TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
-	clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
 
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&cur_trans->list);

fs/btrfs/transaction.h

@@ -151,18 +151,20 @@ struct btrfs_pending_snapshot {
 	struct btrfs_block_rsv block_rsv;
 	/* extra metadata reservation for relocation */
 	int error;
+	/* Preallocated anonymous block device number */
+	dev_t anon_dev;
 	bool readonly;
 	struct list_head list;
 };
 
 static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
-					      struct inode *inode)
+					      struct btrfs_inode *inode)
 {
-	spin_lock(&BTRFS_I(inode)->lock);
-	BTRFS_I(inode)->last_trans = trans->transaction->transid;
-	BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
-	BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
+	inode->last_trans = trans->transaction->transid;
+	inode->last_sub_trans = inode->root->log_transid;
+	inode->last_log_commit = inode->root->last_log_commit;
+	spin_unlock(&inode->lock);
 }
 
 /*
@@ -208,20 +210,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
 int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 				   int wait_for_unblock);
-
-/*
- * Try to commit transaction asynchronously, so this is safe to call
- * even holding a spinlock.
- *
- * It's done by informing transaction_kthread to commit transaction without
- * waiting for commit interval.
- */
-static inline void btrfs_commit_transaction_locksafe(
-		struct btrfs_fs_info *fs_info)
-{
-	set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
-	wake_up_process(fs_info->transaction_kthread);
-}
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
 int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
 void btrfs_throttle(struct btrfs_fs_info *fs_info);

fs/btrfs/tree-defrag.c

@@ -133,10 +133,9 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		ret = 0;
 	}
 done:
-	if (ret != -EAGAIN) {
+	if (ret != -EAGAIN)
 		memset(&root->defrag_progress, 0,
 		       sizeof(root->defrag_progress));
-		root->defrag_trans_start = trans->transid;
-	}
+
 	return ret;
 }

fs/btrfs/volumes.h

@@ -288,7 +288,7 @@ struct btrfs_fs_devices {
  */
 struct btrfs_io_bio {
 	unsigned int mirror_num;
-	unsigned int stripe_index;
+	struct btrfs_device *device;
 	u64 logical;
 	u8 *csum;
 	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];

include/uapi/linux/btrfs.h

@@ -243,6 +243,18 @@ struct btrfs_ioctl_dev_info_args {
 	__u8 path[BTRFS_DEVICE_PATH_NAME_MAX];	/* out */
 };
 
+/*
+ * Retrieve information about the filesystem
+ */
+
+/* Request information about checksum type and size */
+#define BTRFS_FS_INFO_FLAG_CSUM_INFO			(1 << 0)
+
+/* Request information about filesystem generation */
+#define BTRFS_FS_INFO_FLAG_GENERATION			(1 << 1)
+/* Request information about filesystem metadata UUID */
+#define BTRFS_FS_INFO_FLAG_METADATA_UUID		(1 << 2)
+
 struct btrfs_ioctl_fs_info_args {
 	__u64 max_id;				/* out */
 	__u64 num_devices;			/* out */
@@ -250,8 +262,13 @@ struct btrfs_ioctl_fs_info_args {
 	__u32 nodesize;				/* out */
 	__u32 sectorsize;			/* out */
 	__u32 clone_alignment;			/* out */
-	__u32 reserved32;
-	__u64 reserved[122];			/* pad to 1k */
+	/* See BTRFS_FS_INFO_FLAG_* */
+	__u16 csum_type;			/* out */
+	__u16 csum_size;			/* out */
+	__u64 flags;				/* in/out */
+	__u64 generation;			/* out */
+	__u8 metadata_uuid[BTRFS_FSID_SIZE];	/* out */
+	__u8 reserved[944];			/* pad to 1k */
 };
 
 /*

include/uapi/linux/btrfs_tree.h

@@ -913,9 +913,9 @@ struct btrfs_free_space_info {
 #define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
 
 #define BTRFS_QGROUP_LEVEL_SHIFT		48
-static inline __u64 btrfs_qgroup_level(__u64 qgroupid)
+static inline __u16 btrfs_qgroup_level(__u64 qgroupid)
 {
-	return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
+	return (__u16)(qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT);
 }
 
 /*