1 files changed, 147 insertions, 349 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 080e2ebb8aa0..efce9a2fa9be 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -50,6 +50,8 @@
 #include "sysfs.h"
 #include "qgroup.h"
 #include "compression.h"
+#include "tree-checker.h"
+#include "ref-verify.h"
 
 #ifdef CONFIG_X86
 #include <asm/cpufeature.h>
@@ -529,7 +531,7 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 				 struct extent_buffer *eb)
 {
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
-	u8 fsid[BTRFS_UUID_SIZE];
+	u8 fsid[BTRFS_FSID_SIZE];
 	int ret = 1;
 
 	read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
@@ -543,146 +545,6 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-#define CORRUPT(reason, eb, root, slot)					\
-	btrfs_crit(root->fs_info,					\
-		   "corrupt %s, %s: block=%llu, root=%llu, slot=%d",	\
-		   btrfs_header_level(eb) == 0 ? "leaf" : "node",	\
-		   reason, btrfs_header_bytenr(eb), root->objectid, slot)
-
-static noinline int check_leaf(struct btrfs_root *root,
-			       struct extent_buffer *leaf)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_key key;
-	struct btrfs_key leaf_key;
-	u32 nritems = btrfs_header_nritems(leaf);
-	int slot;
-
-	/*
-	 * Extent buffers from a relocation tree have a owner field that
-	 * corresponds to the subvolume tree they are based on. So just from an
-	 * extent buffer alone we can not find out what is the id of the
-	 * corresponding subvolume tree, so we can not figure out if the extent
-	 * buffer corresponds to the root of the relocation tree or not. So skip
-	 * this check for relocation trees.
-	 */
-	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
-		struct btrfs_root *check_root;
-
-		key.objectid = btrfs_header_owner(leaf);
-		key.type = BTRFS_ROOT_ITEM_KEY;
-		key.offset = (u64)-1;
-
-		check_root = btrfs_get_fs_root(fs_info, &key, false);
-		/*
-		 * The only reason we also check NULL here is that during
-		 * open_ctree() some roots has not yet been set up.
-		 */
-		if (!IS_ERR_OR_NULL(check_root)) {
-			struct extent_buffer *eb;
-
-			eb = btrfs_root_node(check_root);
-			/* if leaf is the root, then it's fine */
-			if (leaf != eb) {
-				CORRUPT("non-root leaf's nritems is 0",
-					leaf, check_root, 0);
-				free_extent_buffer(eb);
-				return -EIO;
-			}
-			free_extent_buffer(eb);
-		}
-		return 0;
-	}
-
-	if (nritems == 0)
-		return 0;
-
-	/* Check the 0 item */
-	if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
-	    BTRFS_LEAF_DATA_SIZE(fs_info)) {
-		CORRUPT("invalid item offset size pair", leaf, root, 0);
-		return -EIO;
-	}
-
-	/*
-	 * Check to make sure each items keys are in the correct order and their
-	 * offsets make sense.  We only have to loop through nritems-1 because
-	 * we check the current slot against the next slot, which verifies the
-	 * next slot's offset+size makes sense and that the current's slot
-	 * offset is correct.
-	 */
-	for (slot = 0; slot < nritems - 1; slot++) {
-		btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
-		btrfs_item_key_to_cpu(leaf, &key, slot + 1);
-
-		/* Make sure the keys are in the right order */
-		if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
-			CORRUPT("bad key order", leaf, root, slot);
-			return -EIO;
-		}
-
-		/*
-		 * Make sure the offset and ends are right, remember that the
-		 * item data starts at the end of the leaf and grows towards the
-		 * front.
-		 */
-		if (btrfs_item_offset_nr(leaf, slot) !=
-			btrfs_item_end_nr(leaf, slot + 1)) {
-			CORRUPT("slot offset bad", leaf, root, slot);
-			return -EIO;
-		}
-
-		/*
-		 * Check to make sure that we don't point outside of the leaf,
-		 * just in case all the items are consistent to each other, but
-		 * all point outside of the leaf.
-		 */
-		if (btrfs_item_end_nr(leaf, slot) >
-		    BTRFS_LEAF_DATA_SIZE(fs_info)) {
-			CORRUPT("slot end outside of leaf", leaf, root, slot);
-			return -EIO;
-		}
-	}
-
-	return 0;
-}
-
-static int check_node(struct btrfs_root *root, struct extent_buffer *node)
-{
-	unsigned long nr = btrfs_header_nritems(node);
-	struct btrfs_key key, next_key;
-	int slot;
-	u64 bytenr;
-	int ret = 0;
-
-	if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root->fs_info)) {
-		btrfs_crit(root->fs_info,
-			   "corrupt node: block %llu root %llu nritems %lu",
-			   node->start, root->objectid, nr);
-		return -EIO;
-	}
-
-	for (slot = 0; slot < nr - 1; slot++) {
-		bytenr = btrfs_node_blockptr(node, slot);
-		btrfs_node_key_to_cpu(node, &key, slot);
-		btrfs_node_key_to_cpu(node, &next_key, slot + 1);
-
-		if (!bytenr) {
-			CORRUPT("invalid item slot", node, root, slot);
-			ret = -EIO;
-			goto out;
-		}
-
-		if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) {
-			CORRUPT("bad key order", node, root, slot);
-			ret = -EIO;
-			goto out;
-		}
-	}
-out:
-	return ret;
-}
-
 static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 				      u64 phy_offset, struct page *page,
 				      u64 start, u64 end, int mirror)
@@ -748,12 +610,12 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	 * that we don't try and read the other copies of this block, just
 	 * return -EIO.
 	 */
-	if (found_level == 0 && check_leaf(root, eb)) {
+	if (found_level == 0 && btrfs_check_leaf(root, eb)) {
 		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
 		ret = -EIO;
 	}
 
-	if (found_level > 0 && check_node(root, eb))
+	if (found_level > 0 && btrfs_check_node(root, eb))
 		ret = -EIO;
 
 	if (!ret)
@@ -879,22 +741,9 @@ static void run_one_async_start(struct btrfs_work *work)
 
 static void run_one_async_done(struct btrfs_work *work)
 {
-	struct btrfs_fs_info *fs_info;
 	struct async_submit_bio *async;
-	int limit;
 
 	async = container_of(work, struct  async_submit_bio, work);
-	fs_info = async->fs_info;
-
-	limit = btrfs_async_submit_limit(fs_info);
-	limit = limit * 2 / 3;
-
-	/*
-	 * atomic_dec_return implies a barrier for waitqueue_active
-	 */
-	if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
-	    waitqueue_active(&fs_info->async_submit_wait))
-		wake_up(&fs_info->async_submit_wait);
 
 	/* If an error occurred we just want to clean up the bio and move on */
 	if (async->status) {
@@ -942,19 +791,10 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 
 	async->status = 0;
 
-	atomic_inc(&fs_info->nr_async_submits);
-
 	if (op_is_sync(bio->bi_opf))
 		btrfs_set_work_high_priority(&async->work);
 
 	btrfs_queue_work(fs_info->workers, &async->work);
-
-	while (atomic_read(&fs_info->async_submit_draining) &&
-	      atomic_read(&fs_info->nr_async_submits)) {
-		wait_event(fs_info->async_submit_wait,
-			   (atomic_read(&fs_info->nr_async_submits) == 0));
-	}
-
 	return 0;
 }
 
@@ -1005,9 +845,9 @@ static blk_status_t __btree_submit_bio_done(void *private_data, struct bio *bio,
 	return ret;
 }
 
-static int check_async_write(unsigned long bio_flags)
+static int check_async_write(struct btrfs_inode *bi)
 {
-	if (bio_flags & EXTENT_BIO_TREE_LOG)
+	if (atomic_read(&bi->sync_writers))
 		return 0;
 #ifdef CONFIG_X86
 	if (static_cpu_has(X86_FEATURE_XMM4_2))
@@ -1022,7 +862,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
 {
 	struct inode *inode = private_data;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int async = check_async_write(bio_flags);
+	int async = check_async_write(BTRFS_I(inode));
 	blk_status_t ret;
 
 	if (bio_op(bio) != REQ_OP_WRITE) {
@@ -1343,7 +1183,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	atomic_set(&root->log_batch, 0);
 	atomic_set(&root->orphan_inodes, 0);
 	refcount_set(&root->refs, 1);
-	atomic_set(&root->will_be_snapshoted, 0);
+	atomic_set(&root->will_be_snapshotted, 0);
 	atomic64_set(&root->qgroup_meta_rsv, 0);
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
@@ -2478,7 +2318,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 		return ret;
 	}
 
-	if (fs_info->sb->s_flags & MS_RDONLY) {
+	if (sb_rdonly(fs_info->sb)) {
 		ret = btrfs_commit_super(fs_info);
 		if (ret)
 			return ret;
@@ -2607,14 +2447,6 @@ int open_ctree(struct super_block *sb,
 		goto fail_delalloc_bytes;
 	}
 
-	fs_info->btree_inode = new_inode(sb);
-	if (!fs_info->btree_inode) {
-		err = -ENOMEM;
-		goto fail_bio_counter;
-	}
-
-	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
-
 	INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
 	INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
 	INIT_LIST_HEAD(&fs_info->trans_list);
@@ -2647,17 +2479,12 @@ int open_ctree(struct super_block *sb,
 	btrfs_mapping_init(&fs_info->mapping_tree);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
-	btrfs_init_block_rsv(&fs_info->delalloc_block_rsv,
-			     BTRFS_BLOCK_RSV_DELALLOC);
 	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
 	btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
 	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
 	btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
 			     BTRFS_BLOCK_RSV_DELOPS);
-	atomic_set(&fs_info->nr_async_submits, 0);
 	atomic_set(&fs_info->async_delalloc_pages, 0);
-	atomic_set(&fs_info->async_submit_draining, 0);
-	atomic_set(&fs_info->nr_async_bios, 0);
 	atomic_set(&fs_info->defrag_running, 0);
 	atomic_set(&fs_info->qgroup_op_seq, 0);
 	atomic_set(&fs_info->reada_works_cnt, 0);
@@ -2673,12 +2500,21 @@ int open_ctree(struct super_block *sb,
 	/* readahead state */
 	INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
 	spin_lock_init(&fs_info->reada_lock);
+	btrfs_init_ref_verify(fs_info);
 
 	fs_info->thread_pool_size = min_t(unsigned long,
 					  num_online_cpus() + 2, 8);
 
 	INIT_LIST_HEAD(&fs_info->ordered_roots);
 	spin_lock_init(&fs_info->ordered_root_lock);
+
+	fs_info->btree_inode = new_inode(sb);
+	if (!fs_info->btree_inode) {
+		err = -ENOMEM;
+		goto fail_bio_counter;
+	}
+	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
+
 	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
 					GFP_KERNEL);
 	if (!fs_info->delayed_root) {
@@ -2694,8 +2530,8 @@ int open_ctree(struct super_block *sb,
 	btrfs_init_balance(fs_info);
 	btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
 
-	sb->s_blocksize = 4096;
-	sb->s_blocksize_bits = blksize_bits(4096);
+	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
+	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);
 
 	btrfs_init_btree_inode(fs_info);
 
@@ -2828,6 +2664,8 @@ int open_ctree(struct super_block *sb,
 	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
 	if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
 		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+	else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;
 
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
 		btrfs_info(fs_info, "has skinny extents");
@@ -2874,7 +2712,7 @@ int open_ctree(struct super_block *sb,
 
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
-	if (!(sb->s_flags & MS_RDONLY) && features) {
+	if (!sb_rdonly(sb) && features) {
 		btrfs_err(fs_info,
 	"cannot mount read-write because of unsupported optional features (%llx)",
 		       features);
@@ -2893,12 +2731,13 @@ int open_ctree(struct super_block *sb,
 	sb->s_bdi->congested_fn = btrfs_congested_fn;
 	sb->s_bdi->congested_data = fs_info;
 	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
-	sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+	sb->s_bdi->ra_pages = VM_MAX_READAHEAD * SZ_1K / PAGE_SIZE;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
+	memcpy(&sb->s_uuid, fs_info->fsid, BTRFS_FSID_SIZE);
 
 	mutex_lock(&fs_info->chunk_mutex);
 	ret = btrfs_read_sys_array(fs_info);
@@ -3035,15 +2874,10 @@ retry_root_backup:
 		btrfs_err(fs_info, "failed to read block groups: %d", ret);
 		goto fail_sysfs;
 	}
-	fs_info->num_tolerated_disk_barrier_failures =
-		btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
-	if (fs_info->fs_devices->missing_devices >
-	     fs_info->num_tolerated_disk_barrier_failures &&
-	    !(sb->s_flags & MS_RDONLY)) {
+
+	if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info)) {
 		btrfs_warn(fs_info,
-"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed",
-			fs_info->fs_devices->missing_devices,
-			fs_info->num_tolerated_disk_barrier_failures);
+		"writeable mount is not allowed due to too many missing devices");
 		goto fail_sysfs;
 	}
 
@@ -3058,11 +2892,9 @@ retry_root_backup:
 	if (IS_ERR(fs_info->transaction_kthread))
 		goto fail_cleaner;
 
-	if (!btrfs_test_opt(fs_info, SSD) &&
-	    !btrfs_test_opt(fs_info, NOSSD) &&
+	if (!btrfs_test_opt(fs_info, NOSSD) &&
 	    !fs_info->fs_devices->rotating) {
-		btrfs_info(fs_info, "detected SSD devices, enabling SSD mode");
-		btrfs_set_opt(fs_info->mount_opt, SSD);
+		btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations");
 	}
 
 	/*
@@ -3088,6 +2920,9 @@ retry_root_backup:
 	if (ret)
 		goto fail_trans_kthread;
 
+	if (btrfs_build_ref_tree(fs_info))
+		btrfs_err(fs_info, "couldn't build ref tree");
+
 	/* do not make disk changes in broken FS or nologreplay is given */
 	if (btrfs_super_log_root(disk_super) != 0 &&
 	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
@@ -3102,7 +2937,7 @@ retry_root_backup:
 	if (ret)
 		goto fail_qgroup;
 
-	if (!(sb->s_flags & MS_RDONLY)) {
+	if (!sb_rdonly(sb)) {
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
@@ -3128,7 +2963,7 @@ retry_root_backup:
 		goto fail_qgroup;
 	}
 
-	if (sb->s_flags & MS_RDONLY)
+	if (sb_rdonly(sb))
 		return 0;
 
 	if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
@@ -3321,7 +3156,7 @@ int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
 	if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode))
 		return -EINVAL;
 
-	bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE);
+	bh = __bread(bdev, bytenr / BTRFS_BDEV_BLOCKSIZE, BTRFS_SUPER_INFO_SIZE);
 	/*
 	 * If we fail to read from the underlying devices, as of now
 	 * the best option we have is to mark it EIO.
@@ -3378,19 +3213,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
 }
 
 /*
- * this should be called twice, once with wait == 0 and
- * once with wait == 1.  When wait == 0 is done, all the buffer heads
- * we write are pinned.
+ * Write superblock @sb to the @device. Do not wait for completion, all the
+ * buffer heads we write are pinned.
  *
- * They are released when wait == 1 is done.
- * max_mirrors must be the same for both runs, and it indicates how
- * many supers on this one device should be written.
+ * Write @max_mirrors copies of the superblock, where 0 means default that fit
+ * the expected device size at commit time. Note that max_mirrors must be
+ * same for write and wait phases.
  *
- * max_mirrors == 0 means to write them all.
+ * Return number of errors when buffer head is not found or submission fails.
  */
 static int write_dev_supers(struct btrfs_device *device,
-			    struct btrfs_super_block *sb,
-			    int wait, int max_mirrors)
+			    struct btrfs_super_block *sb, int max_mirrors)
 {
 	struct buffer_head *bh;
 	int i;
@@ -3408,57 +3241,33 @@ static int write_dev_supers(struct btrfs_device *device,
 		    device->commit_total_bytes)
 			break;
 
-		if (wait) {
-			bh = __find_get_block(device->bdev, bytenr / 4096,
-					      BTRFS_SUPER_INFO_SIZE);
-			if (!bh) {
-				errors++;
-				continue;
-			}
-			wait_on_buffer(bh);
-			if (!buffer_uptodate(bh))
-				errors++;
+		btrfs_set_super_bytenr(sb, bytenr);
 
-			/* drop our reference */
-			brelse(bh);
+		crc = ~(u32)0;
+		crc = btrfs_csum_data((const char *)sb + BTRFS_CSUM_SIZE, crc,
+				      BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
+		btrfs_csum_final(crc, sb->csum);
 
-			/* drop the reference from the wait == 0 run */
-			brelse(bh);
+		/* One reference for us, and we leave it for the caller */
+		bh = __getblk(device->bdev, bytenr / BTRFS_BDEV_BLOCKSIZE,
+			      BTRFS_SUPER_INFO_SIZE);
+		if (!bh) {
+			btrfs_err(device->fs_info,
+			    "couldn't get super buffer head for bytenr %llu",
+			    bytenr);
+			errors++;
 			continue;
-		} else {
-			btrfs_set_super_bytenr(sb, bytenr);
-
-			crc = ~(u32)0;
-			crc = btrfs_csum_data((const char *)sb +
-					      BTRFS_CSUM_SIZE, crc,
-					      BTRFS_SUPER_INFO_SIZE -
-					      BTRFS_CSUM_SIZE);
-			btrfs_csum_final(crc, sb->csum);
-
-			/*
-			 * one reference for us, and we leave it for the
-			 * caller
-			 */
-			bh = __getblk(device->bdev, bytenr / 4096,
-				      BTRFS_SUPER_INFO_SIZE);
-			if (!bh) {
-				btrfs_err(device->fs_info,
-				    "couldn't get super buffer head for bytenr %llu",
-				    bytenr);
-				errors++;
-				continue;
-			}
+		}
 
-			memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE);
+		memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE);
 
-			/* one reference for submit_bh */
-			get_bh(bh);
+		/* one reference for submit_bh */
+		get_bh(bh);
 
-			set_buffer_uptodate(bh);
-			lock_buffer(bh);
-			bh->b_end_io = btrfs_end_buffer_write_sync;
-			bh->b_private = device;
-		}
+		set_buffer_uptodate(bh);
+		lock_buffer(bh);
+		bh->b_end_io = btrfs_end_buffer_write_sync;
+		bh->b_private = device;
 
 		/*
 		 * we fua the first super.  The others we allow
@@ -3466,9 +3275,10 @@ static int write_dev_supers(struct btrfs_device *device,
 		 */
 		if (i == 0) {
 			ret = btrfsic_submit_bh(REQ_OP_WRITE,
-						REQ_SYNC | REQ_FUA, bh);
+				REQ_SYNC | REQ_FUA | REQ_META | REQ_PRIO, bh);
 		} else {
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+			ret = btrfsic_submit_bh(REQ_OP_WRITE,
+				REQ_SYNC | REQ_META | REQ_PRIO, bh);
 		}
 		if (ret)
 			errors++;
@@ -3477,6 +3287,50 @@ static int write_dev_supers(struct btrfs_device *device,
 }
 
 /*
+ * Wait for write completion of superblocks done by write_dev_supers,
+ * @max_mirrors same for write and wait phases.
+ *
+ * Return number of errors when buffer head is not found or not marked up to
+ * date.
+ */
+static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
+{
+	struct buffer_head *bh;
+	int i;
+	int errors = 0;
+	u64 bytenr;
+
+	if (max_mirrors == 0)
+		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
+
+	for (i = 0; i < max_mirrors; i++) {
+		bytenr = btrfs_sb_offset(i);
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+		    device->commit_total_bytes)
+			break;
+
+		bh = __find_get_block(device->bdev,
+				      bytenr / BTRFS_BDEV_BLOCKSIZE,
+				      BTRFS_SUPER_INFO_SIZE);
+		if (!bh) {
+			errors++;
+			continue;
+		}
+		wait_on_buffer(bh);
+		if (!buffer_uptodate(bh))
+			errors++;
+
+		/* drop our reference */
+		brelse(bh);
+
+		/* drop the reference from the writing run */
+		brelse(bh);
+	}
+
+	return errors < i ? 0 : -1;
+}
+
+/*
  * endio for the write_dev_flush, this will wake anyone waiting
  * for the barrier when it is done
  */
@@ -3499,12 +3353,12 @@ static void write_dev_flush(struct btrfs_device *device)
 
 	bio_reset(bio);
 	bio->bi_end_io = btrfs_end_empty_barrier;
-	bio->bi_bdev = device->bdev;
+	bio_set_dev(bio, device->bdev);
 	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 
-	submit_bio(bio);
+	btrfsic_submit_bio(bio);
 	device->flush_bio_sent = 1;
 }
 
@@ -3516,7 +3370,7 @@ static blk_status_t wait_dev_flush(struct btrfs_device *device)
 	struct bio *bio = device->flush_bio;
 
 	if (!device->flush_bio_sent)
-		return 0;
+		return BLK_STS_OK;
 
 	device->flush_bio_sent = 0;
 	wait_for_completion_io(&device->flush_wait);
@@ -3524,20 +3378,10 @@ static blk_status_t wait_dev_flush(struct btrfs_device *device)
 	return bio->bi_status;
 }
 
-static int check_barrier_error(struct btrfs_fs_devices *fsdevs)
+static int check_barrier_error(struct btrfs_fs_info *fs_info)
 {
-	int dev_flush_error = 0;
-	struct btrfs_device *dev;
-
-	list_for_each_entry_rcu(dev, &fsdevs->devices, dev_list) {
-		if (!dev->bdev || dev->last_flush_error)
-			dev_flush_error++;
-	}
-
-	if (dev_flush_error >
-	    fsdevs->fs_info->num_tolerated_disk_barrier_failures)
+	if (!btrfs_check_rw_degradable(fs_info))
 		return -EIO;
-
 	return 0;
 }
 
@@ -3563,7 +3407,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 			continue;
 
 		write_dev_flush(dev);
-		dev->last_flush_error = 0;
+		dev->last_flush_error = BLK_STS_OK;
 	}
 
 	/* wait for all the barriers */
@@ -3592,7 +3436,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 		 * to arrive at the volume status. So error checking
 		 * is being pushed to a separate loop.
 		 */
-		return check_barrier_error(info->fs_devices);
+		return check_barrier_error(info);
 	}
 	return 0;
 }
@@ -3626,60 +3470,6 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
 	return min_tolerated;
 }
 
-int btrfs_calc_num_tolerated_disk_barrier_failures(
-	struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_ioctl_space_info space;
-	struct btrfs_space_info *sinfo;
-	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
-		       BTRFS_BLOCK_GROUP_SYSTEM,
-		       BTRFS_BLOCK_GROUP_METADATA,
-		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
-	int i;
-	int c;
-	int num_tolerated_disk_barrier_failures =
-		(int)fs_info->fs_devices->num_devices;
-
-	for (i = 0; i < ARRAY_SIZE(types); i++) {
-		struct btrfs_space_info *tmp;
-
-		sinfo = NULL;
-		rcu_read_lock();
-		list_for_each_entry_rcu(tmp, &fs_info->space_info, list) {
-			if (tmp->flags == types[i]) {
-				sinfo = tmp;
-				break;
-			}
-		}
-		rcu_read_unlock();
-
-		if (!sinfo)
-			continue;
-
-		down_read(&sinfo->groups_sem);
-		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
-			u64 flags;
-
-			if (list_empty(&sinfo->block_groups[c]))
-				continue;
-
-			btrfs_get_block_group_info(&sinfo->block_groups[c],
-						   &space);
-			if (space.total_bytes == 0 || space.used_bytes == 0)
-				continue;
-			flags = space.flags;
-
-			num_tolerated_disk_barrier_failures = min(
-				num_tolerated_disk_barrier_failures,
-				btrfs_get_num_tolerated_disk_barrier_failures(
-					flags));
-		}
-		up_read(&sinfo->groups_sem);
-	}
-
-	return num_tolerated_disk_barrier_failures;
-}
-
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 {
 	struct list_head *head;
@@ -3693,7 +3483,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 	u64 flags;
 
 	do_barriers = !btrfs_test_opt(fs_info, NOBARRIER);
-	backup_super_roots(fs_info);
+
+	/*
+	 * max_mirrors == 0 indicates we're from commit_transaction,
+	 * not from fsync where the tree roots in fs_info have not
+	 * been consistent on disk.
+	 */
+	if (max_mirrors == 0)
+		backup_super_roots(fs_info);
 
 	sb = fs_info->super_for_commit;
 	dev_item = &sb->dev_item;
@@ -3732,12 +3529,12 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
 		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
 		memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE);
-		memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE);
+		memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_FSID_SIZE);
 
 		flags = btrfs_super_flags(sb);
 		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);
 
-		ret = write_dev_supers(dev, sb, 0, max_mirrors);
+		ret = write_dev_supers(dev, sb, max_mirrors);
 		if (ret)
 			total_errors++;
 	}
@@ -3760,7 +3557,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		if (!dev->in_fs_metadata || !dev->writeable)
 			continue;
 
-		ret = write_dev_supers(dev, sb, 1, max_mirrors);
+		ret = wait_dev_supers(dev, max_mirrors);
 		if (ret)
 			total_errors++;
 	}
@@ -3928,7 +3725,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
 
-	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
+	if (!sb_rdonly(fs_info->sb)) {
 		/*
 		 * If the cleaner thread is stopped and there are
 		 * block groups queued for removal, the deletion will be
@@ -3991,11 +3788,11 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	cleanup_srcu_struct(&fs_info->subvol_srcu);
 
 	btrfs_free_stripe_hash_table(fs_info);
+	btrfs_free_ref_cache(fs_info);
 
 	__btrfs_free_block_rsv(root->orphan_block_rsv);
 	root->orphan_block_rsv = NULL;
 
-	mutex_lock(&fs_info->chunk_mutex);
 	while (!list_empty(&fs_info->pinned_chunks)) {
 		struct extent_map *em;
 
@@ -4004,7 +3801,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 		list_del_init(&em->list);
 		free_extent_map(em);
 	}
-	mutex_unlock(&fs_info->chunk_mutex);
 }
 
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -4052,8 +3848,8 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 					 buf->len,
 					 fs_info->dirty_metadata_batch);
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
-	if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
-		btrfs_print_leaf(fs_info, buf);
+	if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(root, buf)) {
+		btrfs_print_leaf(buf);
 		ASSERT(0);
 	}
 #endif
@@ -4173,7 +3969,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
 		ret = -EINVAL;
 	}
 
-	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
+	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) {
 		btrfs_err(fs_info,
 			   "dev_item UUID does not match fsid: %pU != %pU",
 			   fs_info->fsid, sb->dev_item.fsid);
@@ -4317,26 +4113,28 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 
 	while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
 		struct btrfs_delayed_ref_head *head;
-		struct btrfs_delayed_ref_node *tmp;
+		struct rb_node *n;
 		bool pin_bytes = false;
 
 		head = rb_entry(node, struct btrfs_delayed_ref_head,
 				href_node);
 		if (!mutex_trylock(&head->mutex)) {
-			refcount_inc(&head->node.refs);
+			refcount_inc(&head->refs);
 			spin_unlock(&delayed_refs->lock);
 
 			mutex_lock(&head->mutex);
 			mutex_unlock(&head->mutex);
-			btrfs_put_delayed_ref(&head->node);
+			btrfs_put_delayed_ref_head(head);
 			spin_lock(&delayed_refs->lock);
 			continue;
 		}
 		spin_lock(&head->lock);
-		list_for_each_entry_safe_reverse(ref, tmp, &head->ref_list,
-						 list) {
+		while ((n = rb_first(&head->ref_tree)) != NULL) {
+			ref = rb_entry(n, struct btrfs_delayed_ref_node,
+				       ref_node);
 			ref->in_tree = 0;
-			list_del(&ref->list);
+			rb_erase(&ref->ref_node, &head->ref_tree);
+			RB_CLEAR_NODE(&ref->ref_node);
 			if (!list_empty(&ref->add_list))
 				list_del(&ref->add_list);
 			atomic_dec(&delayed_refs->num_entries);
@@ -4349,16 +4147,16 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		if (head->processing == 0)
 			delayed_refs->num_heads_ready--;
 		atomic_dec(&delayed_refs->num_entries);
-		head->node.in_tree = 0;
 		rb_erase(&head->href_node, &delayed_refs->href_root);
+		RB_CLEAR_NODE(&head->href_node);
 		spin_unlock(&head->lock);
 		spin_unlock(&delayed_refs->lock);
 		mutex_unlock(&head->mutex);
 
 		if (pin_bytes)
-			btrfs_pin_extent(fs_info, head->node.bytenr,
-					 head->node.num_bytes, 1);
-		btrfs_put_delayed_ref(&head->node);
+			btrfs_pin_extent(fs_info, head->bytenr,
+					 head->num_bytes, 1);
+		btrfs_put_delayed_ref_head(head);
 		cond_resched();
 		spin_lock(&delayed_refs->lock);
 	}