Merge remote-tracking branch 'btrfs-kdave/for-next'

21 files changed, 706 insertions, 404 deletions

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index ab14c2e635ca..6cabc8acee2a 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1668,14 +1668,8 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		dev_bytenr += (j - i) * PAGE_SIZE;
 		i = j;
 	}
-	for (i = 0; i < num_pages; i++) {
+	for (i = 0; i < num_pages; i++)
 		block_ctx->datav[i] = kmap(block_ctx->pagev[i]);
-		if (!block_ctx->datav[i]) {
-			pr_info("btrfsic: kmap() failed (dev %s)!\n",
-			       block_ctx->dev->name);
-			return -1;
-		}
-	}
 
 	return block_ctx->len;
 }
@@ -2822,44 +2816,47 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev);
 	if (NULL != dev_state &&
 	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
-		unsigned int i;
+		unsigned int i = 0;
 		u64 dev_bytenr;
 		u64 cur_bytenr;
-		struct bio_vec *bvec;
+		struct bio_vec bvec;
+		struct bvec_iter iter;
 		int bio_is_patched;
 		char **mapped_datav;
+		unsigned int segs = bio_segments(bio);
 
 		dev_bytenr = 512 * bio->bi_iter.bi_sector;
 		bio_is_patched = 0;
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
-			       bio_op(bio), bio->bi_opf, bio->bi_vcnt,
+			       bio_op(bio), bio->bi_opf, segs,
 			       (unsigned long long)bio->bi_iter.bi_sector,
 			       dev_bytenr, bio->bi_bdev);
 
-		mapped_datav = kmalloc_array(bio->bi_vcnt,
+		mapped_datav = kmalloc_array(segs,
 					     sizeof(*mapped_datav), GFP_NOFS);
 		if (!mapped_datav)
 			goto leave;
 		cur_bytenr = dev_bytenr;
 
-		bio_for_each_segment_all(bvec, bio, i) {
-			BUG_ON(bvec->bv_len != PAGE_SIZE);
-			mapped_datav[i] = kmap(bvec->bv_page);
+		bio_for_each_segment(bvec, bio, iter) {
+			BUG_ON(bvec.bv_len != PAGE_SIZE);
+			mapped_datav[i] = kmap(bvec.bv_page);
+			i++;
 
 			if (dev_state->state->print_mask &
 			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
 				pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
-				       i, cur_bytenr, bvec->bv_len, bvec->bv_offset);
-			cur_bytenr += bvec->bv_len;
+				       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
+			cur_bytenr += bvec.bv_len;
 		}
 		btrfsic_process_written_block(dev_state, dev_bytenr,
-					      mapped_datav, bio->bi_vcnt,
+					      mapped_datav, segs,
 					      bio, &bio_is_patched,
 					      NULL, bio->bi_opf);
-		bio_for_each_segment_all(bvec, bio, i)
-			kunmap(bvec->bv_page);
+		bio_for_each_segment(bvec, bio, iter)
+			kunmap(bvec.bv_page);
 		kfree(mapped_datav);
 	} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
 		if (dev_state->state->print_mask &
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 643c70d2b2e6..160e4b8b510a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -48,7 +48,6 @@ struct btrfs_trans_handle;
 struct btrfs_transaction;
 struct btrfs_pending_snapshot;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
-extern struct kmem_cache *btrfs_transaction_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
 extern struct kmem_cache *btrfs_free_space_cachep;
@@ -716,6 +715,8 @@ struct btrfs_delayed_root;
 #define BTRFS_FS_BTREE_ERR			11
 #define BTRFS_FS_LOG1_ERR			12
 #define BTRFS_FS_LOG2_ERR			13
+#define BTRFS_FS_QUOTA_OVERRIDE			14
+
 /*
  * Indicate that a whole-filesystem exclusive operation is running
  * (device replace, resize, device add/delete, balance)
@@ -748,8 +749,7 @@ struct btrfs_fs_info {
 	struct rb_root block_group_cache_tree;
 
 	/* keep track of unallocated space */
-	spinlock_t free_chunk_lock;
-	u64 free_chunk_space;
+	atomic64_t free_chunk_space;
 
 	struct extent_io_tree freed_extents[2];
 	struct extent_io_tree *pinned_extents;
@@ -2703,9 +2703,13 @@ enum btrfs_flush_state {
 	COMMIT_TRANS		=	6,
 };
 
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
 int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
-void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
+void btrfs_delalloc_release_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
@@ -2722,8 +2726,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
-void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
 struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
 					      unsigned short type);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8685d67185d0..f52e98210590 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -89,7 +89,6 @@ struct btrfs_end_io_wq {
 	struct btrfs_fs_info *info;
 	int error;
 	enum btrfs_wq_endio_type metadata;
-	struct list_head list;
 	struct btrfs_work work;
 };
 
@@ -120,7 +119,6 @@ void btrfs_end_io_wq_exit(void)
 struct async_submit_bio {
 	struct inode *inode;
 	struct bio *bio;
-	struct list_head list;
 	extent_submit_bio_hook_t *submit_bio_start;
 	extent_submit_bio_hook_t *submit_bio_done;
 	int mirror_num;
@@ -2626,7 +2624,6 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->free_chunk_lock);
 	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->qgroup_op_lock);
@@ -2667,7 +2664,7 @@ int open_ctree(struct super_block *sb,
 	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
-	fs_info->free_chunk_space = 0;
+	atomic64_set(&fs_info->free_chunk_space, 0);
 	fs_info->tree_mod_log = RB_ROOT;
 	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
@@ -3467,10 +3464,12 @@ static int write_dev_supers(struct btrfs_device *device,
 		 * we fua the first super.  The others we allow
 		 * to go down lazy.
 		 */
-		if (i == 0)
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
-		else
+		if (i == 0) {
+			ret = btrfsic_submit_bh(REQ_OP_WRITE,
+						REQ_SYNC | REQ_FUA, bh);
+		} else {
 			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+		}
 		if (ret)
 			errors++;
 	}
@@ -3507,6 +3506,10 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 	if (wait) {
 		bio = device->flush_bio;
 		if (!bio)
+			/*
+			 * This means the alloc has failed with ENOMEM, however
+			 * here we return 0, as its not a device error.
+			 */
 			return 0;
 
 		wait_for_completion(&device->flush_wait);
@@ -3535,7 +3538,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	bio->bi_bdev = device->bdev;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 	device->flush_bio = bio;
@@ -3546,6 +3549,32 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
 	return 0;
 }
 
+static int check_barrier_error(struct btrfs_fs_devices *fsdevs)
+{
+	int submit_flush_error = 0;
+	int dev_flush_error = 0;
+	struct btrfs_device *dev;
+	int tolerance;
+
+	list_for_each_entry_rcu(dev, &fsdevs->devices, dev_list) {
+		if (!dev->bdev) {
+			submit_flush_error++;
+			dev_flush_error++;
+			continue;
+		}
+		if (dev->last_flush_error == -ENOMEM)
+			submit_flush_error++;
+		if (dev->last_flush_error && dev->last_flush_error != -ENOMEM)
+			dev_flush_error++;
+	}
+
+	tolerance = fsdevs->fs_info->num_tolerated_disk_barrier_failures;
+	if (submit_flush_error > tolerance || dev_flush_error > tolerance)
+		return -EIO;
+
+	return 0;
+}
+
 /*
  * send an empty flush down to each device in parallel,
  * then wait for them
@@ -3573,6 +3602,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 		ret = write_dev_flush(dev, 0);
 		if (ret)
 			errors_send++;
+		dev->last_flush_error = ret;
 	}
 
 	/* wait for all the barriers */
@@ -3587,12 +3617,30 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 			continue;
 
 		ret = write_dev_flush(dev, 1);
-		if (ret)
+		if (ret) {
+			dev->last_flush_error = ret;
 			errors_wait++;
+		}
+	}
+
+	/*
+	 * Try hard in case of flush. Lets say, in RAID1 we have
+	 * the following situation
+	 *  dev1: EIO dev2: ENOMEM
+	 * this is not a fatal error as we hope to recover from
+	 * ENOMEM in the next attempt to flush.
+	 * But the following is considered as fatal
+	 *  dev1: ENOMEM dev2: ENOMEM
+	 *  dev1: bdev == NULL dev2: ENOMEM
+	 */
+	if (errors_send || errors_wait) {
+		/*
+		 * At some point we need the status of all disks
+		 * to arrive at the volume status. So error checking
+		 * is being pushed to a separate loop.
+		 */
+		return check_barrier_error(info->fs_devices);
 	}
-	if (errors_send > info->num_tolerated_disk_barrier_failures ||
-	    errors_wait > info->num_tolerated_disk_barrier_failures)
-		return -EIO;
 	return 0;
 }
 
@@ -4576,11 +4624,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
-
-	/*
-	memset(cur_trans, 0, sizeof(*cur_trans));
-	kmem_cache_free(btrfs_transaction_cachep, cur_trans);
-	*/
 }
 
 static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e390451c72e6..6e9e4461c2e9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3364,6 +3364,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_root *root = fs_info->tree_root;
 	struct inode *inode = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 alloc_hint = 0;
 	int dcs = BTRFS_DC_ERROR;
 	u64 num_pages = 0;
@@ -3483,7 +3484,7 @@ again:
 	num_pages *= 16;
 	num_pages *= PAGE_SIZE;
 
-	ret = btrfs_check_data_free_space(inode, 0, num_pages);
+	ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages);
 	if (ret)
 		goto out_put;
 
@@ -3514,6 +3515,7 @@ out:
 	block_group->disk_cache_state = dcs;
 	spin_unlock(&block_group->lock);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -4277,12 +4279,8 @@ commit_trans:
 	return ret;
 }
 
-/*
- * New check_data_free_space() with ability for precious data reservation
- * Will replace old btrfs_check_data_free_space(), but for patch split,
- * add a new function first and then replace it.
- */
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int ret;
@@ -4297,9 +4295,11 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
 		return ret;
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
-	ret = btrfs_qgroup_reserve_data(inode, start, len);
-	if (ret)
+	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
+	if (ret < 0)
 		btrfs_free_reserved_data_space_noquota(inode, start, len);
+	else
+		ret = 0;
 	return ret;
 }
 
@@ -4340,7 +4340,8 @@ 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, u64 start, u64 len)
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
@@ -4350,7 +4351,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
 	start = round_down(start, root->fs_info->sectorsize);
 
 	btrfs_free_reserved_data_space_noquota(inode, start, len);
-	btrfs_qgroup_free_data(inode, start, len);
+	btrfs_qgroup_free_data(inode, reserved, start, len);
 }
 
 static void force_metadata_allocation(struct btrfs_fs_info *info)
@@ -4645,9 +4646,7 @@ static int can_overcommit(struct btrfs_root *root,
 
 	used += space_info->bytes_may_use;
 
-	spin_lock(&fs_info->free_chunk_lock);
-	avail = fs_info->free_chunk_space;
-	spin_unlock(&fs_info->free_chunk_lock);
+	avail = atomic64_read(&fs_info->free_chunk_space);
 
 	/*
 	 * If we have dup, raid1 or raid10 then only half of the free
@@ -6123,6 +6122,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes)
  * @inode: inode we're writing to
  * @start: start range we are writing to
  * @len: how long the range we are writing to
+ * @reserved: mandatory parameter, record actually reserved qgroup ranges of
+ * 	      current reservation.
  *
  * This will do the following things
  *
@@ -6140,16 +6141,17 @@ void btrfs_delalloc_release_metadata(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, u64 start, u64 len)
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	int ret;
 
-	ret = btrfs_check_data_free_space(inode, start, len);
+	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
 	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
 	if (ret < 0)
-		btrfs_free_reserved_data_space(inode, start, len);
+		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 	return ret;
 }
 
@@ -6168,10 +6170,11 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
  * list if there are no delalloc bytes left.
  * Also it will handle the qgroup reserved space.
  */
-void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len)
+void btrfs_delalloc_release_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
 	btrfs_delalloc_release_metadata(BTRFS_I(inode), len);
-	btrfs_free_reserved_data_space(inode, start, len);
+	btrfs_free_reserved_data_space(inode, reserved, start, len);
 }
 
 static int update_block_group(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d8da3edf2ac3..da4658feb69d 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2458,7 +2458,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
-		ret = ret < 0 ? ret : -EIO;
+		ret = err < 0 ? err : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
 }
@@ -2713,7 +2713,7 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
 	struct btrfs_io_bio *btrfs_bio;
 	struct bio *new;
 
-	new = bio_clone_bioset(bio, gfp_mask, btrfs_bioset);
+	new = bio_clone_fast(bio, gfp_mask, btrfs_bioset);
 	if (new) {
 		btrfs_bio = btrfs_io_bio(new);
 		btrfs_bio->csum = NULL;
@@ -2739,6 +2739,24 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio;
 }
 
+struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
+{
+	struct bio *bio;
+	struct btrfs_io_bio *btrfs_bio;
+
+	/* this will fail when it's backed by a bioset */
+	bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset);
+	ASSERT(bio);
+
+	btrfs_bio = btrfs_io_bio(bio);
+	btrfs_bio->csum = NULL;
+	btrfs_bio->csum_allocated = NULL;
+	btrfs_bio->end_io = NULL;
+
+	bio_trim(bio, offset >> 9, size >> 9);
+	btrfs_bio->iter = bio->bi_iter;
+	return bio;
+}
 
 static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 				       unsigned long bio_flags)
@@ -4377,6 +4395,123 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 	return NULL;
 }
 
+/*
+ * To cache previous fiemap extent
+ *
+ * Will be used for merging fiemap extent
+ */
+struct fiemap_cache {
+	u64 offset;
+	u64 phys;
+	u64 len;
+	u32 flags;
+	bool cached;
+};
+
+/*
+ * Helper to submit fiemap extent.
+ *
+ * Will try to merge current fiemap extent specified by @offset, @phys,
+ * @len and @flags with cached one.
+ * And only when we fails to merge, cached one will be submitted as
+ * fiemap extent.
+ *
+ * Return value is the same as fiemap_fill_next_extent().
+ */
+static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
+				struct fiemap_cache *cache,
+				u64 offset, u64 phys, u64 len, u32 flags)
+{
+	int ret = 0;
+
+	if (!cache->cached)
+		goto assign;
+
+	/*
+	 * Sanity check, extent_fiemap() should have ensured that new
+	 * fiemap extent won't overlap with cahced one.
+	 * Not recoverable.
+	 *
+	 * NOTE: Physical address can overlap, due to compression
+	 */
+	if (cache->offset + cache->len > offset) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	/*
+	 * Only merges fiemap extents if
+	 * 1) Their logical addresses are continuous
+	 *
+	 * 2) Their physical addresses are continuous
+	 *    So truly compressed (physical size smaller than logical size)
+	 *    extents won't get merged with each other
+	 *
+	 * 3) Share same flags except FIEMAP_EXTENT_LAST
+	 *    So regular extent won't get merged with prealloc extent
+	 */
+	if (cache->offset + cache->len  == offset &&
+	    cache->phys + cache->len == phys  &&
+	    (cache->flags & ~FIEMAP_EXTENT_LAST) ==
+			(flags & ~FIEMAP_EXTENT_LAST)) {
+		cache->len += len;
+		cache->flags |= flags;
+		goto try_submit_last;
+	}
+
+	/* Not mergeable, need to submit cached one */
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret)
+		return ret;
+assign:
+	cache->cached = true;
+	cache->offset = offset;
+	cache->phys = phys;
+	cache->len = len;
+	cache->flags = flags;
+try_submit_last:
+	if (cache->flags & FIEMAP_EXTENT_LAST) {
+		ret = fiemap_fill_next_extent(fieinfo, cache->offset,
+				cache->phys, cache->len, cache->flags);
+		cache->cached = false;
+	}
+	return ret;
+}
+
+/*
+ * Sanity check for fiemap cache
+ *
+ * All fiemap cache should be submitted by emit_fiemap_extent()
+ * Iteration should be terminated either by last fiemap extent or
+ * fieinfo->fi_extents_max.
+ * So no cached fiemap should exist.
+ */
+static int check_fiemap_cache(struct btrfs_fs_info *fs_info,
+			       struct fiemap_extent_info *fieinfo,
+			       struct fiemap_cache *cache)
+{
+	int ret;
+
+	if (!cache->cached)
+		return 0;
+
+	/* Small and recoverbale problem, only to info developer */
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_ON(1);
+#endif
+	btrfs_warn(fs_info,
+		   "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x",
+		   cache->offset, cache->phys, cache->len, cache->flags);
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret > 0)
+		ret = 0;
+	return ret;
+}
+
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent)
 {
@@ -4394,6 +4529,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct fiemap_cache cache = { 0 };
 	int end = 0;
 	u64 em_start = 0;
 	u64 em_len = 0;
@@ -4573,8 +4709,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			flags |= FIEMAP_EXTENT_LAST;
 			end = 1;
 		}
-		ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
-					      em_len, flags);
+		ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko,
+					   em_len, flags);
 		if (ret) {
 			if (ret == 1)
 				ret = 0;
@@ -4582,6 +4718,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 	}
 out_free:
+	if (!ret)
+		ret = check_fiemap_cache(root->fs_info, fieinfo, &cache);
 	free_extent_map(em);
 out:
 	btrfs_free_path(path);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 1eafa2f0ede3..204c7660a746 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -205,12 +205,46 @@ struct extent_buffer {
  */
 struct extent_changeset {
 	/* How many bytes are set/cleared in this operation */
-	u64 bytes_changed;
+	unsigned int bytes_changed;
 
 	/* Changed ranges */
 	struct ulist range_changed;
 };
 
+static inline void extent_changeset_init(struct extent_changeset *changeset)
+{
+	changeset->bytes_changed = 0;
+	ulist_init(&changeset->range_changed);
+}
+
+static inline struct extent_changeset *extent_changeset_alloc(void)
+{
+	struct extent_changeset *ret;
+
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	extent_changeset_init(ret);
+	return ret;
+}
+
+static inline void extent_changeset_release(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	changeset->bytes_changed = 0;
+	ulist_release(&changeset->range_changed);
+}
+
+static inline void extent_changeset_free(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	extent_changeset_release(changeset);
+	kfree(changeset);
+}
+
 static inline void extent_set_compress_type(unsigned long *bio_flags,
 					    int compress_type)
 {
@@ -464,6 +498,7 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
 		gfp_t gfp_flags);
 struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs);
 struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask);
+struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size);
 
 struct btrfs_fs_info;
 struct btrfs_inode;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 64fcb31d7163..9f6062c82419 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -164,7 +164,8 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 				   u64 logical_offset, u32 *dst, int dio)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
 	struct btrfs_csum_item *item = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -177,7 +178,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
-	int count = 0, i;
+	int count = 0;
 	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
 	path = btrfs_alloc_path();
@@ -206,8 +207,6 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	if (bio->bi_iter.bi_size > PAGE_SIZE * 8)
 		path->reada = READA_FORWARD;
 
-	WARN_ON(bio->bi_vcnt <= 0);
-
 	/*
 	 * the free space stuff is only read when it hasn't been
 	 * updated in the current transaction.  So, we can safely
@@ -223,13 +222,13 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	if (dio)
 		offset = logical_offset;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		page_bytes_left = bvec->bv_len;
+	bio_for_each_segment(bvec, bio, iter) {
+		page_bytes_left = bvec.bv_len;
 		if (count)
 			goto next;
 
 		if (!dio)
-			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 		count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
 					       (u32 *)csum, nblocks);
 		if (count)
@@ -440,15 +439,15 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;
 	char *data;
-	struct bio_vec *bvec;
+	struct bvec_iter iter;
+	struct bio_vec bvec;
 	int index;
 	int nr_sectors;
-	int i, j;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
+	int i;
 	u64 offset;
 
-	WARN_ON(bio->bi_vcnt <= 0);
 	sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
 		       GFP_NOFS);
 	if (!sums)
@@ -465,19 +464,19 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	index = 0;
 
-	bio_for_each_segment_all(bvec, bio, j) {
+	bio_for_each_segment(bvec, bio, iter) {
 		if (!contig)
-			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 
 		if (!ordered) {
 			ordered = btrfs_lookup_ordered_extent(inode, offset);
 			BUG_ON(!ordered); /* Logic error */
 		}
 
-		data = kmap_atomic(bvec->bv_page);
+		data = kmap_atomic(bvec.bv_page);
 
 		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info,
-						 bvec->bv_len + fs_info->sectorsize
+						 bvec.bv_len + fs_info->sectorsize
 						 - 1);
 
 		for (i = 0; i < nr_sectors; i++) {
@@ -504,12 +503,12 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 					+ total_bytes;
 				index = 0;
 
-				data = kmap_atomic(bvec->bv_page);
+				data = kmap_atomic(bvec.bv_page);
 			}
 
 			sums->sums[index] = ~(u32)0;
 			sums->sums[index]
-				= btrfs_csum_data(data + bvec->bv_offset
+				= btrfs_csum_data(data + bvec.bv_offset
 						+ (i * fs_info->sectorsize),
 						sums->sums[index],
 						fs_info->sectorsize);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index da1096eb1a40..0502bd2272fe 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1581,6 +1581,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct page **pages = NULL;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 release_bytes = 0;
 	u64 lockstart;
 	u64 lockend;
@@ -1628,7 +1629,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
 
-		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
+		extent_changeset_release(data_reserved);
+		ret = btrfs_check_data_free_space(inode, &data_reserved, pos,
+						  write_bytes);
 		if (ret < 0) {
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
@@ -1657,8 +1660,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 				reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
-				btrfs_free_reserved_data_space(inode, pos,
-							       write_bytes);
+				btrfs_free_reserved_data_space(inode,
+						data_reserved, pos,
+						write_bytes);
 			else
 				btrfs_end_write_no_snapshoting(root);
 			break;
@@ -1740,8 +1744,9 @@ again:
 				__pos = round_down(pos,
 						   fs_info->sectorsize) +
 					(dirty_pages << PAGE_SHIFT);
-				btrfs_delalloc_release_space(inode, __pos,
-							     release_bytes);
+				btrfs_delalloc_release_space(inode,
+						data_reserved, __pos,
+						release_bytes);
 			}
 		}
 
@@ -1796,12 +1801,13 @@ again:
 			btrfs_delalloc_release_metadata(BTRFS_I(inode),
 					release_bytes);
 		} else {
-			btrfs_delalloc_release_space(inode,
-						round_down(pos, fs_info->sectorsize),
-						release_bytes);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					round_down(pos, fs_info->sectorsize),
+					release_bytes);
 		}
 	}
 
+	extent_changeset_free(data_reserved);
 	return num_written ? num_written : ret;
 }
 
@@ -2769,6 +2775,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct falloc_range *range;
 	struct falloc_range *tmp;
 	struct list_head reserve_list;
@@ -2898,8 +2905,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 				free_extent_map(em);
 				break;
 			}
-			ret = btrfs_qgroup_reserve_data(inode, cur_offset,
-					last_byte - cur_offset);
+			ret = btrfs_qgroup_reserve_data(inode, &data_reserved,
+					cur_offset, last_byte - cur_offset);
 			if (ret < 0) {
 				free_extent_map(em);
 				break;
@@ -2910,8 +2917,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 			 * range, free reserved data space first, otherwise
 			 * it'll result in false ENOSPC error.
 			 */
-			btrfs_free_reserved_data_space(inode, cur_offset,
-				last_byte - cur_offset);
+			btrfs_free_reserved_data_space(inode, data_reserved,
+					cur_offset, last_byte - cur_offset);
 		}
 		free_extent_map(em);
 		cur_offset = last_byte;
@@ -2930,8 +2937,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 					range->len, i_blocksize(inode),
 					offset + len, &alloc_hint);
 		else
-			btrfs_free_reserved_data_space(inode, range->start,
-						       range->len);
+			btrfs_free_reserved_data_space(inode,
+					data_reserved, range->start,
+					range->len);
 		list_del(&range->list);
 		kfree(range);
 	}
@@ -2969,8 +2977,9 @@ out:
 	inode_unlock(inode);
 	/* Let go of our reservation. */
 	if (ret != 0)
-		btrfs_free_reserved_data_space(inode, alloc_start,
-				       alloc_end - cur_offset);
+		btrfs_free_reserved_data_space(inode, data_reserved,
+				alloc_start, alloc_end - cur_offset);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 5c6c20ec64d8..d02019747d00 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -400,6 +400,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	struct btrfs_path *path;
 	struct inode *inode;
 	struct btrfs_block_rsv *rsv;
+	struct extent_changeset *data_reserved = NULL;
 	u64 num_bytes;
 	u64 alloc_hint = 0;
 	int ret;
@@ -492,7 +493,7 @@ again:
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_SIZE;
 
-	ret = btrfs_delalloc_reserve_space(inode, 0, prealloc);
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc);
 	if (ret)
 		goto out_put;
 
@@ -516,6 +517,7 @@ out:
 	trans->bytes_reserved = num_bytes;
 
 	btrfs_free_path(path);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17cbe9306faf..8c37b4fa4cbb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -86,7 +86,6 @@ static const struct extent_io_ops btrfs_extent_io_ops;
 
 static struct kmem_cache *btrfs_inode_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
-struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
 struct kmem_cache *btrfs_free_space_cachep;
 
@@ -350,7 +349,7 @@ out:
 	 * And at reserve time, it's always aligned to page size, so
 	 * just free one page here.
 	 */
-	btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
 	btrfs_free_path(path);
 	btrfs_end_transaction(trans);
 	return ret;
@@ -2035,6 +2034,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	struct btrfs_writepage_fixup *fixup;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct page *page;
 	struct inode *inode;
 	u64 page_start;
@@ -2072,7 +2072,7 @@ again:
 		goto again;
 	}
 
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   PAGE_SIZE);
 	if (ret) {
 		mapping_set_error(page->mapping, ret);
@@ -2092,6 +2092,7 @@ out_page:
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
+	extent_changeset_free(data_reserved);
 }
 
 /*
@@ -2143,6 +2144,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_key ins;
+	u64 qg_released;
 	int extent_inserted = 0;
 	int ret;
 
@@ -2198,13 +2200,17 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	ins.objectid = disk_bytenr;
 	ins.offset = disk_num_bytes;
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
-	ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
-			btrfs_ino(BTRFS_I(inode)), file_pos, ram_bytes, &ins);
+
 	/*
 	 * Release the reserved range from inode dirty range map, as it is
 	 * already moved into delayed_ref_head
 	 */
-	btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+	ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+	if (ret < 0)
+		goto out;
+	qg_released = ret;
+	ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
+			btrfs_ino(BTRFS_I(inode)), file_pos, qg_released, &ins);
 out:
 	btrfs_free_path(path);
 
@@ -2926,7 +2932,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		 * space for NOCOW range.
 		 * As NOCOW won't cause a new delayed ref, just free the space
 		 */
-		btrfs_qgroup_free_data(inode, ordered_extent->file_offset,
+		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
 				       ordered_extent->len);
 		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 		if (nolock)
@@ -2952,7 +2958,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 
 	ret = test_range_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
-			EXTENT_DEFRAG, 1, cached_state);
+			EXTENT_DEFRAG, 0, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
@@ -4762,6 +4768,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
@@ -4776,7 +4783,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	    (!len || ((len & (blocksize - 1)) == 0)))
 		goto out;
 
-	ret = btrfs_delalloc_reserve_space(inode,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			round_down(from, blocksize), blocksize);
 	if (ret)
 		goto out;
@@ -4784,7 +4791,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 again:
 	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
-		btrfs_delalloc_release_space(inode,
+		btrfs_delalloc_release_space(inode, data_reserved,
 				round_down(from, blocksize),
 				blocksize);
 		ret = -ENOMEM;
@@ -4856,11 +4863,12 @@ again:
 
 out_unlock:
 	if (ret)
-		btrfs_delalloc_release_space(inode, block_start,
+		btrfs_delalloc_release_space(inode, data_reserved, block_start,
 					     blocksize);
 	unlock_page(page);
 	put_page(page);
 out:
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -5255,7 +5263,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		 * Note, end is the bytenr of last byte, so we need + 1 here.
 		 */
 		if (state->state & EXTENT_DELALLOC)
-			btrfs_qgroup_free_data(inode, start, end - start + 1);
+			btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);
 
 		clear_extent_bit(io_tree, start, end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
@@ -5868,7 +5876,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_item *item;
 	struct btrfs_dir_item *di;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
@@ -5919,7 +5926,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
-		item = btrfs_item_nr(slot);
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
 		if (found_key.objectid != key.objectid)
@@ -7480,11 +7486,11 @@ out:
 bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct radix_tree_root *root = &inode->i_mapping->page_tree;
-	int found = false;
+	bool found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 
@@ -7981,6 +7987,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	struct bio *bio;
 	int isector;
 	int read_mode = 0;
+	int segs;
 	int ret;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -7996,9 +8003,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 		return -EIO;
 	}
 
-	if ((failed_bio->bi_vcnt > 1)
-		|| (failed_bio->bi_io_vec->bv_len
-			> btrfs_inode_sectorsize(inode)))
+	segs = bio_segments(failed_bio);
+	if (segs > 1 ||
+	    (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
 		read_mode |= REQ_FAILFAST_DEV;
 
 	isector = start - btrfs_io_bio(failed_bio)->logical;
@@ -8056,36 +8063,40 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
 				       struct btrfs_io_bio *io_bio)
 {
 	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_retry_complete done;
 	u64 start;
 	unsigned int pgoff;
 	u32 sectorsize;
 	int nr_sectors;
-	int i;
 	int ret;
+	int err = 0;
 
 	fs_info = BTRFS_I(inode)->root->fs_info;
 	sectorsize = fs_info->sectorsize;
 
 	start = io_bio->logical;
 	done.inode = inode;
+	io_bio->bio.bi_iter = io_bio->iter;
 
-	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		pgoff = bvec->bv_offset;
+	bio_for_each_segment(bvec, &io_bio->bio, iter) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
+		pgoff = bvec.bv_offset;
 
 next_block_or_try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+		ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
 				pgoff, start, start + sectorsize - 1,
 				io_bio->mirror_num,
 				btrfs_retry_endio_nocsum, &done);
-		if (ret)
-			return ret;
+		if (ret) {
+			err = ret;
+			goto next;
+		}
 
 		wait_for_completion(&done.done);
 
@@ -8094,6 +8105,7 @@ next_block_or_try_again:
 			goto next_block_or_try_again;
 		}
 
+next:
 		start += sectorsize;
 
 		nr_sectors--;
@@ -8104,7 +8116,7 @@ next_block_or_try_again:
 		}
 	}
 
-	return 0;
+	return err;
 }
 
 static void btrfs_retry_endio(struct bio *bio)
@@ -8145,7 +8157,8 @@ static int __btrfs_subio_endio_read(struct inode *inode,
 				    struct btrfs_io_bio *io_bio, int err)
 {
 	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_retry_complete done;
 	u64 start;
 	u64 offset = 0;
@@ -8153,7 +8166,7 @@ static int __btrfs_subio_endio_read(struct inode *inode,
 	int nr_sectors;
 	unsigned int pgoff;
 	int csum_pos;
-	int i;
+	int uptodate = !!(err == 0);
 	int ret;
 
 	fs_info = BTRFS_I(inode)->root->fs_info;
@@ -8162,24 +8175,27 @@ static int __btrfs_subio_endio_read(struct inode *inode,
 	err = 0;
 	start = io_bio->logical;
 	done.inode = inode;
+	io_bio->bio.bi_iter = io_bio->iter;
 
-	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+	bio_for_each_segment(bvec, &io_bio->bio, iter) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
 
-		pgoff = bvec->bv_offset;
+		pgoff = bvec.bv_offset;
 next_block:
-		csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
-		ret = __readpage_endio_check(inode, io_bio, csum_pos,
-					bvec->bv_page, pgoff, start,
-					sectorsize);
-		if (likely(!ret))
-			goto next;
+		if (uptodate) {
+			csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+			ret = __readpage_endio_check(inode, io_bio, csum_pos,
+						     bvec.bv_page, pgoff,
+						     start, sectorsize);
+			if (likely(!ret))
+				goto next;
+		}
 try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+		ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
 				pgoff, start, start + sectorsize - 1,
 				io_bio->mirror_num,
 				btrfs_retry_endio, &done);
@@ -8234,8 +8250,11 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	int err = bio->bi_error;
 
-	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
+	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
 		err = btrfs_subio_endio_read(inode, io_bio, err);
+		if (!err)
+			bio->bi_error = 0;
+	}
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
 		      dip->logical_offset + dip->bytes - 1);
@@ -8358,16 +8377,6 @@ out:
 	bio_put(bio);
 }
 
-static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
-				       u64 first_sector, gfp_t gfp_flags)
-{
-	struct bio *bio;
-	bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
-	if (bio)
-		bio_associate_current(bio);
-	return bio;
-}
-
 static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode,
 						 struct btrfs_dio_private *dip,
 						 struct bio *bio,
@@ -8457,24 +8466,23 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct bio *bio;
 	struct bio *orig_bio = dip->orig_bio;
-	struct bio_vec *bvec;
 	u64 start_sector = orig_bio->bi_iter.bi_sector;
 	u64 file_offset = dip->logical_offset;
-	u64 submit_len = 0;
 	u64 map_length;
-	u32 blocksize = fs_info->sectorsize;
 	int async_submit = 0;
-	int nr_sectors;
+	u64 submit_len;
+	int clone_offset = 0;
+	int clone_len;
 	int ret;
-	int i, j;
 
 	map_length = orig_bio->bi_iter.bi_size;
+	submit_len = map_length;
 	ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9,
 			      &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
 
-	if (map_length >= orig_bio->bi_iter.bi_size) {
+	if (map_length >= submit_len) {
 		bio = orig_bio;
 		dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
 		goto submit;
@@ -8486,70 +8494,52 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	else
 		async_submit = 1;
 
-	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-
-	bio->bi_opf = orig_bio->bi_opf;
-	bio->bi_private = dip;
-	bio->bi_end_io = btrfs_end_dio_bio;
-	btrfs_io_bio(bio)->logical = file_offset;
+	/* bio split */
+	ASSERT(map_length <= INT_MAX);
 	atomic_inc(&dip->pending_bios);
+	while (submit_len > 0) {
+		clone_len = min_t(int, submit_len, map_length);
 
-	bio_for_each_segment_all(bvec, orig_bio, j) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		i = 0;
-next_block:
-		if (unlikely(map_length < submit_len + blocksize ||
-		    bio_add_page(bio, bvec->bv_page, blocksize,
-			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
-			/*
-			 * inc the count before we submit the bio so
-			 * we know the end IO handler won't happen before
-			 * we inc the count. Otherwise, the dip might get freed
-			 * before we're done setting it up
-			 */
-			atomic_inc(&dip->pending_bios);
-			ret = __btrfs_submit_dio_bio(bio, inode,
-						     file_offset, skip_sum,
-						     async_submit);
-			if (ret) {
-				bio_put(bio);
-				atomic_dec(&dip->pending_bios);
-				goto out_err;
-			}
-
-			start_sector += submit_len >> 9;
-			file_offset += submit_len;
+		/*
+		 * This will never fail as it's passing GPF_NOFS and
+		 * the allocation is backed by btrfs_bioset.
+		 */
+		bio = btrfs_bio_clone_partial(orig_bio, clone_offset,
+					      clone_len);
+		bio->bi_private = dip;
+		bio->bi_end_io = btrfs_end_dio_bio;
+		btrfs_io_bio(bio)->logical = file_offset;
+
+		ASSERT(submit_len >= clone_len);
+		submit_len -= clone_len;
+		if (submit_len == 0)
+			break;
 
-			submit_len = 0;
+		/*
+		 * Increase the count before we submit the bio so we know
+		 * the end IO handler won't happen before we increase the
+		 * count. Otherwise, the dip might get freed before we're
+		 * done setting it up.
+		 */
+		atomic_inc(&dip->pending_bios);
 
-			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
-						  start_sector, GFP_NOFS);
-			if (!bio)
-				goto out_err;
-			bio->bi_opf = orig_bio->bi_opf;
-			bio->bi_private = dip;
-			bio->bi_end_io = btrfs_end_dio_bio;
-			btrfs_io_bio(bio)->logical = file_offset;
+		ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
+					     async_submit);
+		if (ret) {
+			bio_put(bio);
+			atomic_dec(&dip->pending_bios);
+			goto out_err;
+		}
 
-			map_length = orig_bio->bi_iter.bi_size;
-			ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
-					      start_sector << 9,
-					      &map_length, NULL, 0);
-			if (ret) {
-				bio_put(bio);
-				goto out_err;
-			}
+		clone_offset += clone_len;
+		start_sector += clone_len >> 9;
+		file_offset += clone_len;
 
-			goto next_block;
-		} else {
-			submit_len += blocksize;
-			if (--nr_sectors) {
-				i++;
-				goto next_block;
-			}
-		}
+		map_length = submit_len;
+		ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
+				      start_sector << 9, &map_length, NULL, 0);
+		if (ret)
+			goto out_err;
 	}
 
 submit:
@@ -8577,16 +8567,16 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 				loff_t file_offset)
 {
 	struct btrfs_dio_private *dip = NULL;
-	struct bio *io_bio = NULL;
-	struct btrfs_io_bio *btrfs_bio;
+	struct bio *bio = NULL;
+	struct btrfs_io_bio *io_bio;
 	int skip_sum;
 	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	int ret = 0;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS);
-	if (!io_bio) {
+	bio = btrfs_bio_clone(dio_bio, GFP_NOFS);
+	if (!bio) {
 		ret = -ENOMEM;
 		goto free_ordered;
 	}
@@ -8602,17 +8592,17 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	dip->logical_offset = file_offset;
 	dip->bytes = dio_bio->bi_iter.bi_size;
 	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
-	io_bio->bi_private = dip;
-	dip->orig_bio = io_bio;
+	bio->bi_private = dip;
+	dip->orig_bio = bio;
 	dip->dio_bio = dio_bio;
 	atomic_set(&dip->pending_bios, 0);
-	btrfs_bio = btrfs_io_bio(io_bio);
-	btrfs_bio->logical = file_offset;
+	io_bio = btrfs_io_bio(bio);
+	io_bio->logical = file_offset;
 
 	if (write) {
-		io_bio->bi_end_io = btrfs_endio_direct_write;
+		bio->bi_end_io = btrfs_endio_direct_write;
 	} else {
-		io_bio->bi_end_io = btrfs_endio_direct_read;
+		bio->bi_end_io = btrfs_endio_direct_read;
 		dip->subio_endio = btrfs_subio_endio_read;
 	}
 
@@ -8635,8 +8625,8 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	if (!ret)
 		return;
 
-	if (btrfs_bio->end_io)
-		btrfs_bio->end_io(btrfs_bio, ret);
+	if (io_bio->end_io)
+		io_bio->end_io(io_bio, ret);
 
 free_ordered:
 	/*
@@ -8648,16 +8638,16 @@ free_ordered:
 	 * same as btrfs_endio_direct_[write|read] because we can't call these
 	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
-	if (io_bio && dip) {
-		io_bio->bi_error = -EIO;
-		bio_endio(io_bio);
+	if (bio && dip) {
+		bio->bi_error = -EIO;
+		bio_endio(bio);
 		/*
-		 * The end io callbacks free our dip, do the final put on io_bio
+		 * The end io callbacks free our dip, do the final put on bio
 		 * and all the cleanup and final put for dio_bio (through
 		 * dio_end_io()).
 		 */
 		dip = NULL;
-		io_bio = NULL;
+		bio = NULL;
 	} else {
 		if (write)
 			__endio_write_update_ordered(inode,
@@ -8675,8 +8665,8 @@ free_ordered:
 		 */
 		dio_end_io(dio_bio, ret);
 	}
-	if (io_bio)
-		bio_put(io_bio);
+	if (bio)
+		bio_put(bio);
 	kfree(dip);
 }
 
@@ -8720,6 +8710,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_data dio_data = { 0 };
+	struct extent_changeset *data_reserved = NULL;
 	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
 	int flags = 0;
@@ -8756,7 +8747,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			inode_unlock(inode);
 			relock = true;
 		}
-		ret = btrfs_delalloc_reserve_space(inode, offset, count);
+		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+						   offset, count);
 		if (ret)
 			goto out;
 		dio_data.outstanding_extents = count_max_extents(count);
@@ -8788,8 +8780,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
-				btrfs_delalloc_release_space(inode, offset,
-							     dio_data.reserve);
+				btrfs_delalloc_release_space(inode, data_reserved,
+					offset, dio_data.reserve);
 			/*
 			 * On error we might have left some ordered extents
 			 * without submitting corresponding bios for them, so
@@ -8804,8 +8796,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 					dio_data.unsubmitted_oe_range_start,
 					false);
 		} else if (ret >= 0 && (size_t)ret < count)
-			btrfs_delalloc_release_space(inode, offset,
-						     count - (size_t)ret);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					offset, count - (size_t)ret);
 	}
 out:
 	if (wakeup)
@@ -8813,6 +8805,7 @@ out:
 	if (relock)
 		inode_lock(inode);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -9003,7 +8996,7 @@ again:
 	 *    free the entire extent.
 	 */
 	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
@@ -9045,6 +9038,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	unsigned long zero_start;
 	loff_t size;
@@ -9070,7 +9064,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
 	 * end up waiting indefinitely to get a lock on the page currently
 	 * being processed by btrfs_page_mkwrite() function.
 	 */
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   reserved_space);
 	if (!ret) {
 		ret = file_update_time(vmf->vma->vm_file);
@@ -9124,8 +9118,8 @@ again:
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
-			btrfs_delalloc_release_space(inode, page_start,
-						PAGE_SIZE - reserved_space);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					page_start, PAGE_SIZE - reserved_space);
 		}
 	}
 
@@ -9176,13 +9170,16 @@ again:
 out_unlock:
 	if (!ret) {
 		sb_end_pagefault(inode->i_sb);
+		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
 	}
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_space(inode, page_start, reserved_space);
+	btrfs_delalloc_release_space(inode, data_reserved, page_start,
+				     reserved_space);
 out_noreserve:
 	sb_end_pagefault(inode->i_sb);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -9514,7 +9511,6 @@ void btrfs_destroy_cachep(void)
 	rcu_barrier();
 	kmem_cache_destroy(btrfs_inode_cachep);
 	kmem_cache_destroy(btrfs_trans_handle_cachep);
-	kmem_cache_destroy(btrfs_transaction_cachep);
 	kmem_cache_destroy(btrfs_path_cachep);
 	kmem_cache_destroy(btrfs_free_space_cachep);
 }
@@ -9534,12 +9530,6 @@ int btrfs_init_cachep(void)
 	if (!btrfs_trans_handle_cachep)
 		goto fail;
 
-	btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction",
-			sizeof(struct btrfs_transaction), 0,
-			SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
-	if (!btrfs_transaction_cachep)
-		goto fail;
-
 	btrfs_path_cachep = kmem_cache_create("btrfs_path",
 			sizeof(struct btrfs_path), 0,
 			SLAB_MEM_SPREAD, NULL);
@@ -10538,7 +10528,7 @@ next:
 			btrfs_end_transaction(trans);
 	}
 	if (cur_offset < end)
-		btrfs_free_reserved_data_space(inode, cur_offset,
+		btrfs_free_reserved_data_space(inode, NULL, cur_offset,
 			end - cur_offset + 1);
 	return ret;
 }
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e176375f374f..2bbcb334a32a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1127,6 +1127,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_io_tree *tree;
+	struct extent_changeset *data_reserved = NULL;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 
 	file_end = (isize - 1) >> PAGE_SHIFT;
@@ -1135,7 +1136,7 @@ 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,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
 	if (ret)
@@ -1226,7 +1227,7 @@ again:
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->lock);
-		btrfs_delalloc_release_space(inode,
+		btrfs_delalloc_release_space(inode, data_reserved,
 				start_index << PAGE_SHIFT,
 				(page_cnt - i_done) << PAGE_SHIFT);
 	}
@@ -1247,15 +1248,17 @@ again:
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
+	extent_changeset_free(data_reserved);
 	return i_done;
 out:
 	for (i = 0; i < i_done; i++) {
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
-	btrfs_delalloc_release_space(inode,
+	btrfs_delalloc_release_space(inode, data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
+	extent_changeset_free(data_reserved);
 	return ret;
 
 }
@@ -4897,7 +4900,6 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	if (sa->assign) {
 		ret = btrfs_add_qgroup_relation(trans, fs_info,
 						sa->src, sa->dst);
@@ -4956,7 +4958,6 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	if (sa->create) {
 		ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid);
 	} else {
@@ -5010,7 +5011,6 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		qgroupid = root->root_key.objectid;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim);
 
 	err = btrfs_end_transaction(trans);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index deffbeb74a0b..acfe37360084 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1406,38 +1406,6 @@ out:
 	return ret;
 }
 
-int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_qgroup_extent_record *record;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	struct rb_node *node;
-	u64 qgroup_to_skip;
-	int ret = 0;
-
-	delayed_refs = &trans->transaction->delayed_refs;
-	qgroup_to_skip = delayed_refs->qgroup_to_skip;
-
-	/*
-	 * No need to do lock, since this function will only be called in
-	 * btrfs_commit_transaction().
-	 */
-	node = rb_first(&delayed_refs->dirty_extent_root);
-	while (node) {
-		record = rb_entry(node, struct btrfs_qgroup_extent_record,
-				  node);
-		if (WARN_ON(!record->old_roots))
-			ret = btrfs_find_all_roots(NULL, fs_info,
-					record->bytenr, 0, &record->old_roots);
-		if (ret < 0)
-			break;
-		if (qgroup_to_skip)
-			ulist_del(record->old_roots, qgroup_to_skip, 0);
-		node = rb_next(node);
-	}
-	return ret;
-}
-
 int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_root *delayed_refs,
 				struct btrfs_qgroup_extent_record *record)
@@ -1918,6 +1886,33 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+/*
+ * Helper to check if the @roots is a list of fs tree roots
+ * Return 0 for definitely not a fs/subvol tree roots ulist
+ * Return 1 for possible fs/subvol tree roots ulist(including empty)
+ */
+static int maybe_fs_roots(struct ulist *roots)
+{
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+
+	/* Empty one, still possible for fs roots */
+	if (!roots || roots->nnodes == 0)
+		return 1;
+
+	ULIST_ITER_INIT(&uiter);
+	unode = ulist_next(roots, &uiter);
+	if (!unode)
+		return 1;
+
+	/*
+	 * If it contains fs tree roots, then it must belongs to fs/subvol
+	 * trees.
+	 * If it contains non-fs tree, it won't be shared to fs/subvol trees.
+	 */
+	return is_fstree(unode->val);
+}
+
 int
 btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info,
@@ -1934,10 +1929,20 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
 		return 0;
 
-	if (new_roots)
+	if (new_roots) {
+		if (!maybe_fs_roots(new_roots))
+			goto out_free;
 		nr_new_roots = new_roots->nnodes;
-	if (old_roots)
+	}
+	if (old_roots) {
+		if (!maybe_fs_roots(old_roots))
+			goto out_free;
 		nr_old_roots = old_roots->nnodes;
+	}
+
+	/* Quick exit, either not fs tree roots, or won't affect any qgroup */
+	if (nr_old_roots == 0 && nr_new_roots == 0)
+		goto out_free;
 
 	BUG_ON(!fs_info->quota_root);
 
@@ -2017,6 +2022,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
 
 		if (!ret) {
 			/*
+			 * old roots should be searched when inserting qgroup
+			 * extent record
+			 */
+			if (WARN_ON(!record->old_roots)) {
+				/* Search commit root to find old_roots */
+				ret = btrfs_find_all_roots(NULL, fs_info,
+						record->bytenr, 0,
+						&record->old_roots);
+				if (ret < 0)
+					goto cleanup;
+			}
+
+			/*
 			 * Use SEQ_LAST as time_seq to do special search, which
 			 * doesn't lock tree or delayed_refs and search current
 			 * root. It's safe inside commit_transaction().
@@ -2025,8 +2043,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
 					record->bytenr, SEQ_LAST, &new_roots);
 			if (ret < 0)
 				goto cleanup;
-			if (qgroup_to_skip)
+			if (qgroup_to_skip) {
 				ulist_del(new_roots, qgroup_to_skip, 0);
+				ulist_del(record->old_roots, qgroup_to_skip,
+					  0);
+			}
 			ret = btrfs_qgroup_account_extent(trans, fs_info,
 					record->bytenr, record->num_bytes,
 					record->old_roots, new_roots);
@@ -2338,6 +2359,11 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
 
 	if (num_bytes == 0)
 		return 0;
+
+	if (test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags) &&
+	    capable(CAP_SYS_RESOURCE))
+		enforce = false;
+
 retry:
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
@@ -2806,55 +2832,130 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
  * Return <0 for error (including -EQUOT)
  *
  * NOTE: this function may sleep for memory allocation.
+ *       if btrfs_qgroup_reserve_data() is called multiple times with
+ *       same @reserved, caller must ensure when error happens it's OK
+ *       to free *ALL* reserved space.
  */
-int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
+int btrfs_qgroup_reserve_data(struct inode *inode,
+			struct extent_changeset **reserved_ret, u64 start,
+			u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_changeset changeset;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
+	struct extent_changeset *reserved;
+	u64 orig_reserved;
+	u64 to_reserve;
 	int ret;
 
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) ||
 	    !is_fstree(root->objectid) || len == 0)
 		return 0;
 
-	changeset.bytes_changed = 0;
-	ulist_init(&changeset.range_changed);
+	/* @reserved parameter is mandatory for qgroup */
+	if (WARN_ON(!reserved_ret))
+		return -EINVAL;
+	if (!*reserved_ret) {
+		*reserved_ret = extent_changeset_alloc();
+		if (!*reserved_ret)
+			return -ENOMEM;
+	}
+	reserved = *reserved_ret;
+	/* Record already reserved space */
+	orig_reserved = reserved->bytes_changed;
 	ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
-			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
+			start + len -1, EXTENT_QGROUP_RESERVED, reserved);
+
+	/* Newly reserved space */
+	to_reserve = reserved->bytes_changed - orig_reserved;
 	trace_btrfs_qgroup_reserve_data(inode, start, len,
-					changeset.bytes_changed,
-					QGROUP_RESERVE);
+					to_reserve, QGROUP_RESERVE);
 	if (ret < 0)
 		goto cleanup;
-	ret = qgroup_reserve(root, changeset.bytes_changed, true);
+	ret = qgroup_reserve(root, to_reserve, true);
 	if (ret < 0)
 		goto cleanup;
 
-	ulist_release(&changeset.range_changed);
 	return ret;
 
 cleanup:
-	/* cleanup already reserved ranges */
+	/* cleanup *ALL* already reserved ranges */
 	ULIST_ITER_INIT(&uiter);
-	while ((unode = ulist_next(&changeset.range_changed, &uiter)))
+	while ((unode = ulist_next(&reserved->range_changed, &uiter)))
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
 				 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
 				 GFP_NOFS);
-	ulist_release(&changeset.range_changed);
+	extent_changeset_release(reserved);
+	return ret;
+}
+
+/* Free ranges specified by @reserved, normally in error path */
+static int qgroup_free_reserved_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+	struct extent_changeset changeset;
+	int freed = 0;
+	int ret;
+
+	extent_changeset_init(&changeset);
+	len = round_up(start + len, root->fs_info->sectorsize);
+	start = round_down(start, root->fs_info->sectorsize);
+
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(&reserved->range_changed, &uiter))) {
+		u64 range_start = unode->val;
+		/* unode->aux is the inclusive end */
+		u64 range_len = unode->aux - range_start + 1;
+		u64 free_start;
+		u64 free_len;
+
+		extent_changeset_release(&changeset);
+
+		/* Only free range in range [start, start + len) */
+		if (range_start >= start + len ||
+		    range_start + range_len <= start)
+			continue;
+		free_start = max(range_start, start);
+		free_len = min(start + len, range_start + range_len) -
+			   free_start;
+		/*
+		 * TODO: To also modify reserved->ranges_reserved to reflect
+		 * the modification.
+		 *
+		 * However as long as we free qgroup reserved according to
+		 * EXTENT_QGROUP_RESERVED, we won't double free.
+		 * So not need to rush.
+		 */
+		ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree,
+				free_start, free_start + free_len - 1,
+				EXTENT_QGROUP_RESERVED, &changeset);
+		if (ret < 0)
+			goto out;
+		freed += changeset.bytes_changed;
+	}
+	btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed);
+	ret = freed;
+out:
+	extent_changeset_release(&changeset);
 	return ret;
 }
 
-static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
-				       int free)
+static int __btrfs_qgroup_release_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len,
+			int free)
 {
 	struct extent_changeset changeset;
 	int trace_op = QGROUP_RELEASE;
 	int ret;
 
-	changeset.bytes_changed = 0;
-	ulist_init(&changeset.range_changed);
+	/* In release case, we shouldn't have @reserved */
+	WARN_ON(!free && reserved);
+	if (free && reserved)
+		return qgroup_free_reserved_data(inode, reserved, start, len);
+	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, 
 			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
 	if (ret < 0)
@@ -2868,8 +2969,9 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
 		btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
 				BTRFS_I(inode)->root->objectid,
 				changeset.bytes_changed);
+	ret = changeset.bytes_changed;
 out:
-	ulist_release(&changeset.range_changed);
+	extent_changeset_release(&changeset);
 	return ret;
 }
 
@@ -2878,14 +2980,17 @@ out:
  *
  * Should be called when a range of pages get invalidated before reaching disk.
  * Or for error cleanup case.
+ * if @reserved is given, only reserved range in [@start, @start + @len) will
+ * be freed.
  *
  * For data written to disk, use btrfs_qgroup_release_data().
  *
  * NOTE: This function may sleep for memory allocation.
  */
-int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
+int btrfs_qgroup_free_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
-	return __btrfs_qgroup_release_data(inode, start, len, 1);
+	return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
 }
 
 /*
@@ -2905,7 +3010,7 @@ int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
  */
 int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len)
 {
-	return __btrfs_qgroup_release_data(inode, start, len, 0);
+	return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
 }
 
 int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
@@ -2969,8 +3074,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
 	struct ulist_iterator iter;
 	int ret;
 
-	changeset.bytes_changed = 0;
-	ulist_init(&changeset.range_changed);
+	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 			EXTENT_QGROUP_RESERVED, &changeset);
 
@@ -2987,5 +3091,5 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
 				changeset.bytes_changed);
 
 	}
-	ulist_release(&changeset.range_changed);
+	extent_changeset_release(&changeset);
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index fe04d3f295c6..102aa7fb342b 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -134,8 +134,6 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
 struct btrfs_delayed_extent_op;
-int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info);
 /*
  * Inform qgroup to trace one dirty extent, its info is recorded in @record.
  * So qgroup can account it at transaction committing time.
@@ -243,9 +241,11 @@ 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, u64 start, u64 len);
+int btrfs_qgroup_reserve_data(struct 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, u64 start, u64 len);
+int btrfs_qgroup_free_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
 
 int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 			      bool enforce);
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index a17e775a4a89..ab852b8e3e37 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -66,7 +66,6 @@ struct reada_extctl {
 struct reada_extent {
 	u64			logical;
 	struct btrfs_key	top;
-	int			err;
 	struct list_head	extctl;
 	int 			refcnt;
 	spinlock_t		lock;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index d60df51959f7..2115f3e02dd5 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3093,11 +3093,12 @@ int prealloc_file_extent_cluster(struct inode *inode,
 	u64 prealloc_start = cluster->start - offset;
 	u64 prealloc_end = cluster->end - offset;
 	u64 cur_offset;
+	struct extent_changeset *data_reserved = NULL;
 
 	BUG_ON(cluster->start != cluster->boundary[0]);
 	inode_lock(inode);
 
-	ret = btrfs_check_data_free_space(inode, prealloc_start,
+	ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start,
 					  prealloc_end + 1 - prealloc_start);
 	if (ret)
 		goto out;
@@ -3113,8 +3114,8 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
 		num_bytes = end + 1 - start;
 		if (cur_offset < start)
-			btrfs_free_reserved_data_space(inode, cur_offset,
-					start - cur_offset);
+			btrfs_free_reserved_data_space(inode, data_reserved,
+					cur_offset, start - cur_offset);
 		ret = btrfs_prealloc_file_range(inode, 0, start,
 						num_bytes, num_bytes,
 						end + 1, &alloc_hint);
@@ -3125,10 +3126,11 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		nr++;
 	}
 	if (cur_offset < prealloc_end)
-		btrfs_free_reserved_data_space(inode, cur_offset,
-				       prealloc_end + 1 - cur_offset);
+		btrfs_free_reserved_data_space(inode, data_reserved,
+				cur_offset, prealloc_end + 1 - cur_offset);
 out:
 	inode_unlock(inode);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index fc496a6f842a..e8185c83f667 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -2769,12 +2769,10 @@ out:
 
 struct recorded_ref {
 	struct list_head list;
-	char *dir_path;
 	char *name;
 	struct fs_path *full_path;
 	u64 dir;
 	u64 dir_gen;
-	int dir_path_len;
 	int name_len;
 };
 
@@ -2798,12 +2796,6 @@ static int __record_ref(struct list_head *head, u64 dir,
 
 	ref->name = (char *)kbasename(ref->full_path->start);
 	ref->name_len = ref->full_path->end - ref->name;
-	ref->dir_path = ref->full_path->start;
-	if (ref->name == ref->full_path->start)
-		ref->dir_path_len = 0;
-	else
-		ref->dir_path_len = ref->full_path->end -
-				ref->full_path->start - 1 - ref->name_len;
 
 	list_add_tail(&ref->list, head);
 	return 0;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 1f157fba8940..c2d5f3580b4c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -447,11 +447,52 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 
 BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show);
 
+static ssize_t quota_override_show(struct kobject *kobj,
+				   struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	int quota_override;
+
+	quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+	return snprintf(buf, PAGE_SIZE, "%d\n", quota_override);
+}
+
+static ssize_t quota_override_store(struct kobject *kobj,
+				    struct kobj_attribute *a,
+				    const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	unsigned long knob;
+	int err;
+
+	if (!fs_info)
+		return -EPERM;
+
+	if (!capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+
+	err = kstrtoul(buf, 10, &knob);
+	if (err)
+		return err;
+	if (knob > 1)
+		return -EINVAL;
+
+	if (knob)
+		set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+	else
+		clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+
+	return len;
+}
+
+BTRFS_ATTR_RW(quota_override, quota_override_show, quota_override_store);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(label),
 	BTRFS_ATTR_PTR(nodesize),
 	BTRFS_ATTR_PTR(sectorsize),
 	BTRFS_ATTR_PTR(clone_alignment),
+	BTRFS_ATTR_PTR(quota_override),
 	NULL,
 };
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2168654c90a1..a109db56c4bf 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -93,7 +93,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 			btrfs_put_block_group_trimming(cache);
 			btrfs_put_block_group(cache);
 		}
-		kmem_cache_free(btrfs_transaction_cachep, transaction);
+		kfree(transaction);
 	}
 }
 
@@ -228,7 +228,7 @@ loop:
 	 */
 	BUG_ON(type == TRANS_JOIN_NOLOCK);
 
-	cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+	cur_trans = kmalloc(sizeof(*cur_trans), GFP_NOFS);
 	if (!cur_trans)
 		return -ENOMEM;
 
@@ -238,11 +238,11 @@ loop:
 		 * someone started a transaction after we unlocked.  Make sure
 		 * to redo the checks above
 		 */
-		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		kfree(cur_trans);
 		goto loop;
 	} else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
 		spin_unlock(&fs_info->trans_lock);
-		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		kfree(cur_trans);
 		return -EROFS;
 	}
 
@@ -1374,9 +1374,6 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	ret = commit_fs_roots(trans, fs_info);
 	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;
@@ -2180,13 +2177,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		goto scrub_continue;
 	}
 
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret) {
-		mutex_unlock(&fs_info->tree_log_mutex);
-		mutex_unlock(&fs_info->reloc_mutex);
-		goto scrub_continue;
-	}
-
 	/*
 	 * Since fs roots are all committed, we can get a quite accurate
 	 * new_roots. So let's do quota accounting.
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 017b67daa3bb..e37f95976443 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2417,9 +2417,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	fs_info->fs_devices->total_devices++;
 	fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
-	spin_lock(&fs_info->free_chunk_lock);
-	fs_info->free_chunk_space += device->total_bytes;
-	spin_unlock(&fs_info->free_chunk_lock);
+	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
 		fs_info->fs_devices->rotating = 1;
@@ -2874,9 +2872,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 			mutex_lock(&fs_info->chunk_mutex);
 			btrfs_device_set_bytes_used(device,
 					device->bytes_used - dev_extent_len);
-			spin_lock(&fs_info->free_chunk_lock);
-			fs_info->free_chunk_space += dev_extent_len;
-			spin_unlock(&fs_info->free_chunk_lock);
+			atomic64_add(dev_extent_len, &fs_info->free_chunk_space);
 			btrfs_clear_space_info_full(fs_info);
 			mutex_unlock(&fs_info->chunk_mutex);
 		}
@@ -4409,9 +4405,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	btrfs_device_set_total_bytes(device, new_size);
 	if (device->writeable) {
 		device->fs_devices->total_rw_bytes -= diff;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space -= diff;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_sub(diff, &fs_info->free_chunk_space);
 	}
 	mutex_unlock(&fs_info->chunk_mutex);
 
@@ -4535,9 +4529,7 @@ done:
 		btrfs_device_set_total_bytes(device, old_size);
 		if (device->writeable)
 			device->fs_devices->total_rw_bytes += diff;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space += diff;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_add(diff, &fs_info->free_chunk_space);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
 	return ret;
@@ -4882,9 +4874,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
 	}
 
-	spin_lock(&info->free_chunk_lock);
-	info->free_chunk_space -= (stripe_size * map->num_stripes);
-	spin_unlock(&info->free_chunk_lock);
+	atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space);
 
 	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
@@ -6684,10 +6674,8 @@ static int read_one_dev(struct btrfs_fs_info *fs_info,
 	device->in_fs_metadata = 1;
 	if (device->writeable && !device->is_tgtdev_for_dev_replace) {
 		device->fs_devices->total_rw_bytes += device->total_bytes;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space += device->total_bytes -
-			device->bytes_used;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_add(device->total_bytes - device->bytes_used,
+				&fs_info->free_chunk_space);
 	}
 	ret = 0;
 	return ret;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index c7d0fbc915ca..58b97b6f5f02 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -74,6 +74,7 @@ struct btrfs_device {
 	int missing;
 	int can_discard;
 	int is_tgtdev_for_dev_replace;
+	int last_flush_error;
 
 #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
 	seqcount_t data_seqcount;
@@ -279,6 +280,7 @@ struct btrfs_io_bio {
 	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
 	u8 *csum_allocated;
 	btrfs_io_bio_end_io_t *end_io;
+	struct bvec_iter iter;
 	struct bio bio;
 };
 
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e37973526153..cd99a3658156 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1410,42 +1410,6 @@ DEFINE_EVENT(btrfs__workqueue_done, btrfs_workqueue_destroy,
 	TP_ARGS(wq)
 );
 
-DECLARE_EVENT_CLASS(btrfs__qgroup_data_map,
-
-	TP_PROTO(struct inode *inode, u64 free_reserved),
-
-	TP_ARGS(inode, free_reserved),
-
-	TP_STRUCT__entry_btrfs(
-		__field(	u64,		rootid		)
-		__field(	unsigned long,	ino		)
-		__field(	u64,		free_reserved	)
-	),
-
-	TP_fast_assign_btrfs(btrfs_sb(inode->i_sb),
-		__entry->rootid		=	BTRFS_I(inode)->root->objectid;
-		__entry->ino		=	inode->i_ino;
-		__entry->free_reserved	=	free_reserved;
-	),
-
-	TP_printk_btrfs("rootid=%llu ino=%lu free_reserved=%llu",
-		  __entry->rootid, __entry->ino, __entry->free_reserved)
-);
-
-DEFINE_EVENT(btrfs__qgroup_data_map, btrfs_qgroup_init_data_rsv_map,
-
-	TP_PROTO(struct inode *inode, u64 free_reserved),
-
-	TP_ARGS(inode, free_reserved)
-);
-
-DEFINE_EVENT(btrfs__qgroup_data_map, btrfs_qgroup_free_data_rsv_map,
-
-	TP_PROTO(struct inode *inode, u64 free_reserved),
-
-	TP_ARGS(inode, free_reserved)
-);
-
 #define BTRFS_QGROUP_OPERATIONS				\
 	{ QGROUP_RESERVE,	"reserve"	},	\
 	{ QGROUP_RELEASE,	"release"	},	\