for-5.11-tag

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAl/XdB4ACgkQxWXV+ddt
 WDv41g//dOkrwjAVBfDUwRT/yKqojyEsZB1aNyHlPHFw8KEw5oIW7wxR4oqXi2ed
 /i9KIJe4E9AfqAiexhLvA+Wyt/Sgwz+k4ys82PKhhRNQn7LE4tvhSBUu6JYJDU09
 6I1jagya7ILa8akFXZTmVbXdliI4Ab+pcXWAmQYK/xPVDxYTSsBf4o4MilNBA9FS
 lTwwBh5GTEtIkubr2yVd3pKfF4fT2g1hd+yglpHaOzpcrLMNN4hj4sUFlLbx/FlJ
 MWo+914cSNKJoebbnqhK9djD9hggaaXnNooqfBOXUhZN0VN9rQoKb5tW+TREQmFm
 shrmBSqN7CaqKfSOMZs7WOnTuTvmV/825PnLqDqcTUaLw+BgdyacpO9WflgfSs16
 Cdvagr1SqbrSQ/3WYCpbqPLDNP3XuZ6+m5OWizf6fhyo8xdFcUHZgRC8qejDlycy
 V/zP0c5OYOMi5vo6x/zhrD7Uft7xoFUVcSJCe8WPri082d9LbA2BqwCsullD60PQ
 K/fsmlHs5Uxxy3MFgBPVDdWGgaa9rQ2vXequezbozBIIeeVL+Q9zkeyBFSYuFeE8
 HToRE9B9BUEUh+p1JxPjOdFH/m+sKe1WMdmRLQthMzfOiNWW7pp/nL5rl4BUVmjm
 58dQS73Cj/YNdBomRJXPPtgKIJPAWRrzU/JBcwAdMoKy57oh9NQ=
 =5YAS
 -----END PGP SIGNATURE-----

Merge tag 'for-5.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "We have a mix of all kinds of changes, feature updates, core stuff,
  performance improvements and lots of cleanups and preparatory changes.

  User visible:

   - export filesystem generation in sysfs

   - new features for mount option 'rescue':
       - what's currently supported is exported in sysfs
       - 'ignorebadroots'/'ibadroots' - continue even if some essential
         tree roots are not usable (extent, uuid, data reloc, device,
         csum, free space)
       - 'ignoredatacsums'/'idatacsums' - skip checksum verification on
         data
       - 'all' - now enables 'ignorebadroots' + 'ignoredatacsums' +
         'nologreplay'

   - export read mirror policy settings to sysfs, new policies will be
     added in the future

   - remove inode number cache feature (mount -o inode_cache), obsoleted
     in 5.9

  User visible fixes:

   - async discard scheduling fixes on high loads

   - update inode byte counter atomically so stat() does not report
     wrong value in some cases

   - free space tree fixes:
       - correctly report status of v2 after remount
       - clear v1 cache inodes when v2 is newly enabled after remount

  Core:

   - switch own tree lock implementation to standard rw semaphore:
       - one-level lock nesting is not required anymore, the last use of
         this was in free space that's now loaded asynchronously
       - own implementation of adaptive spinning before taking mutex has
         been part of rwsem
       - performance seems to be better in general, much better (+tens
         of percents) for some workloads
       - lockdep does not complain

   - finish direct IO conversion to iomap infrastructure, remove
     temporary workaround for DSYNC after iomap API updates

   - preparatory work to support data and metadata blocks smaller than
     page:
       - generalize code that assumes sectorsize == PAGE_SIZE, lots of
         refactoring
       - planned namely for 64K pages (eg. arm64, ppc64)
       - scrub read-only support

   - preparatory work for zoned allocation mode (SMR/ZBC/ZNS friendly):
       - disable incompatible features
       - round-robin superblock write

   - free space cache (v1) is loaded asynchronously, remove tree path
     recursion

   - slightly improved time tacking for transaction kthread wake ups

  Performance improvements (note that the numbers depend on load type or
  other features and weren't run on the same machine):

   - skip unnecessary work:
       - do not start readahead for csum tree when scrubbing non-data
         block groups
       - do not start and wait for delalloc on snapshot roots on
         transaction commit
       - fix race when defragmenting leads to unnecessary IO

   - dbench speedups (+throughput%/-max latency%):
       - skip unnecessary searches for xattrs when logging an inode
         (+10.8/-8.2)
       - stop incrementing log batch when joining log transaction (1-2)
       - unlock path before checking if extent is shared during nocow
         writeback (+5.0/-20.5), on fio load +9.7% throughput/-9.8%
         runtime
       - several tree log improvements, eg. removing unnecessary
         operations, fixing races that lead to additional work
         (+12.7/-8.2)

   - tree-checker error branches annotated with unlikely() (+3%
     throughput)

  Other:

   - cleanups

   - lockdep fixes

   - more btrfs_inode conversions

   - error variable cleanups"

* tag 'for-5.11-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (198 commits)
  btrfs: scrub: allow scrub to work with subpage sectorsize
  btrfs: scrub: support subpage data scrub
  btrfs: scrub: support subpage tree block scrub
  btrfs: scrub: always allocate one full page for one sector for RAID56
  btrfs: scrub: reduce width of extent_len/stripe_len from 64 to 32 bits
  btrfs: refactor btrfs_lookup_bio_sums to handle out-of-order bvecs
  btrfs: remove btrfs_find_ordered_sum call from btrfs_lookup_bio_sums
  btrfs: handle sectorsize < PAGE_SIZE case for extent buffer accessors
  btrfs: update num_extent_pages to support subpage sized extent buffer
  btrfs: don't allow tree block to cross page boundary for subpage support
  btrfs: calculate inline extent buffer page size based on page size
  btrfs: factor out btree page submission code to a helper
  btrfs: make btrfs_verify_data_csum follow sector size
  btrfs: pass bio_offset to check_data_csum() directly
  btrfs: rename bio_offset of extent_submit_bio_start_t to dio_file_offset
  btrfs: fix lockdep warning when creating free space tree
  btrfs: skip space_cache v1 setup when not using it
  btrfs: remove free space items when disabling space cache v1
  btrfs: warn when remount will not change the free space tree
  btrfs: use superblock state to print space_cache mount option
  ...

fs/btrfs/Makefile

@@ -3,7 +3,7 @@
 obj-$(CONFIG_BTRFS_FS) := btrfs.o
 
 btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
-	   file-item.o inode-item.o inode-map.o disk-io.o \
+	   file-item.o inode-item.o disk-io.o \
 	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
@@ -16,6 +16,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
 btrfs-$(CONFIG_BTRFS_FS_REF_VERIFY) += ref-verify.o
+btrfs-$(CONFIG_BLK_DEV_ZONED) += zoned.o
 
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \

fs/btrfs/backref.c

@@ -783,8 +783,8 @@ static int add_missing_keys(struct btrfs_fs_info *fs_info,
 		BUG_ON(ref->key_for_search.type);
 		BUG_ON(!ref->wanted_disk_byte);
 
-		eb = read_tree_block(fs_info, ref->wanted_disk_byte, 0,
+		eb = read_tree_block(fs_info, ref->wanted_disk_byte,
-				     ref->level - 1, NULL);
+				     ref->root_id, 0, ref->level - 1, NULL);
 		if (IS_ERR(eb)) {
 			free_pref(ref);
 			return PTR_ERR(eb);
@@ -1331,7 +1331,7 @@ again:
 				struct extent_buffer *eb;
 
 				eb = read_tree_block(fs_info, ref->parent, 0,
-						     ref->level, NULL);
+						     0, ref->level, NULL);
 				if (IS_ERR(eb)) {
 					ret = PTR_ERR(eb);
 					goto out;
@@ -1341,14 +1341,12 @@ again:
 					goto out;
 				}
 
-				if (!path->skip_locking) {
+				if (!path->skip_locking)
 					btrfs_tree_read_lock(eb);
-					btrfs_set_lock_blocking_read(eb);
-				}
 				ret = find_extent_in_eb(eb, bytenr,
 							*extent_item_pos, &eie, ignore_offset);
 				if (!path->skip_locking)
-					btrfs_tree_read_unlock_blocking(eb);
+					btrfs_tree_read_unlock(eb);
 				free_extent_buffer(eb);
 				if (ret < 0)
 					goto out;
@@ -1671,13 +1669,11 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 	s64 bytes_left = ((s64)size) - 1;
 	struct extent_buffer *eb = eb_in;
 	struct btrfs_key found_key;
-	int leave_spinning = path->leave_spinning;
 	struct btrfs_inode_ref *iref;
 
 	if (bytes_left >= 0)
 		dest[bytes_left] = '\0';
 
-	path->leave_spinning = 1;
 	while (1) {
 		bytes_left -= name_len;
 		if (bytes_left >= 0)
@@ -1685,7 +1681,7 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 					   name_off, name_len);
 		if (eb != eb_in) {
 			if (!path->skip_locking)
-				btrfs_tree_read_unlock_blocking(eb);
+				btrfs_tree_read_unlock(eb);
 			free_extent_buffer(eb);
 		}
 		ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1705,8 +1701,6 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		if (eb != eb_in) {
-			if (!path->skip_locking)
-				btrfs_set_lock_blocking_read(eb);
 			path->nodes[0] = NULL;
 			path->locks[0] = 0;
 		}
@@ -1723,7 +1717,6 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 	}
 
 	btrfs_release_path(path);
-	path->leave_spinning = leave_spinning;
 
 	if (ret)
 		return ERR_PTR(ret);

fs/btrfs/block-group.c

@@ -424,6 +424,23 @@ int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 	return ret;
 }
 
+static bool space_cache_v1_done(struct btrfs_block_group *cache)
+{
+	bool ret;
+
+	spin_lock(&cache->lock);
+	ret = cache->cached != BTRFS_CACHE_FAST;
+	spin_unlock(&cache->lock);
+
+	return ret;
+}
+
+void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
+				struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, space_cache_v1_done(cache));
+}
+
 #ifdef CONFIG_BTRFS_DEBUG
 static void fragment_free_space(struct btrfs_block_group *block_group)
 {
@@ -639,11 +656,28 @@ static noinline void caching_thread(struct btrfs_work *work)
 	mutex_lock(&caching_ctl->mutex);
 	down_read(&fs_info->commit_root_sem);
 
+	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
+		ret = load_free_space_cache(block_group);
+		if (ret == 1) {
+			ret = 0;
+			goto done;
+		}
+
+		/*
+		 * We failed to load the space cache, set ourselves to
+		 * CACHE_STARTED and carry on.
+		 */
+		spin_lock(&block_group->lock);
+		block_group->cached = BTRFS_CACHE_STARTED;
+		spin_unlock(&block_group->lock);
+		wake_up(&caching_ctl->wait);
+	}
+
 	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
 		ret = load_free_space_tree(caching_ctl);
 	else
 		ret = load_extent_tree_free(caching_ctl);
-
+done:
 	spin_lock(&block_group->lock);
 	block_group->caching_ctl = NULL;
 	block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED;
@@ -679,7 +713,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 {
 	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
-	struct btrfs_caching_control *caching_ctl;
+	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
 
 	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
@@ -691,119 +725,41 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	init_waitqueue_head(&caching_ctl->wait);
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->start;
-	refcount_set(&caching_ctl->count, 1);
+	refcount_set(&caching_ctl->count, 2);
 	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
-	/*
-	 * This should be a rare occasion, but this could happen I think in the
-	 * case where one thread starts to load the space cache info, and then
-	 * some other thread starts a transaction commit which tries to do an
-	 * allocation while the other thread is still loading the space cache
-	 * info.  The previous loop should have kept us from choosing this block
-	 * group, but if we've moved to the state where we will wait on caching
-	 * block groups we need to first check if we're doing a fast load here,
-	 * so we can wait for it to finish, otherwise we could end up allocating
-	 * from a block group who's cache gets evicted for one reason or
-	 * another.
-	 */
-	while (cache->cached == BTRFS_CACHE_FAST) {
-		struct btrfs_caching_control *ctl;
-
-		ctl = cache->caching_ctl;
-		refcount_inc(&ctl->count);
-		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
-		spin_unlock(&cache->lock);
-
-		schedule();
-
-		finish_wait(&ctl->wait, &wait);
-		btrfs_put_caching_control(ctl);
-		spin_lock(&cache->lock);
-	}
-
 	if (cache->cached != BTRFS_CACHE_NO) {
-		spin_unlock(&cache->lock);
 		kfree(caching_ctl);
-		return 0;
+
+		caching_ctl = cache->caching_ctl;
+		if (caching_ctl)
+			refcount_inc(&caching_ctl->count);
+		spin_unlock(&cache->lock);
+		goto out;
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	cache->cached = BTRFS_CACHE_FAST;
+	if (btrfs_test_opt(fs_info, SPACE_CACHE))
+		cache->cached = BTRFS_CACHE_FAST;
+	else
+		cache->cached = BTRFS_CACHE_STARTED;
+	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
-	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
+	spin_lock(&fs_info->block_group_cache_lock);
-		mutex_lock(&caching_ctl->mutex);
-		ret = load_free_space_cache(cache);
-
-		spin_lock(&cache->lock);
-		if (ret == 1) {
-			cache->caching_ctl = NULL;
-			cache->cached = BTRFS_CACHE_FINISHED;
-			cache->last_byte_to_unpin = (u64)-1;
-			caching_ctl->progress = (u64)-1;
-		} else {
-			if (load_cache_only) {
-				cache->caching_ctl = NULL;
-				cache->cached = BTRFS_CACHE_NO;
-			} else {
-				cache->cached = BTRFS_CACHE_STARTED;
-				cache->has_caching_ctl = 1;
-			}
-		}
-		spin_unlock(&cache->lock);
-#ifdef CONFIG_BTRFS_DEBUG
-		if (ret == 1 &&
-		    btrfs_should_fragment_free_space(cache)) {
-			u64 bytes_used;
-
-			spin_lock(&cache->space_info->lock);
-			spin_lock(&cache->lock);
-			bytes_used = cache->length - cache->used;
-			cache->space_info->bytes_used += bytes_used >> 1;
-			spin_unlock(&cache->lock);
-			spin_unlock(&cache->space_info->lock);
-			fragment_free_space(cache);
-		}
-#endif
-		mutex_unlock(&caching_ctl->mutex);
-
-		wake_up(&caching_ctl->wait);
-		if (ret == 1) {
-			btrfs_put_caching_control(caching_ctl);
-			btrfs_free_excluded_extents(cache);
-			return 0;
-		}
-	} else {
-		/*
-		 * We're either using the free space tree or no caching at all.
-		 * Set cached to the appropriate value and wakeup any waiters.
-		 */
-		spin_lock(&cache->lock);
-		if (load_cache_only) {
-			cache->caching_ctl = NULL;
-			cache->cached = BTRFS_CACHE_NO;
-		} else {
-			cache->cached = BTRFS_CACHE_STARTED;
-			cache->has_caching_ctl = 1;
-		}
-		spin_unlock(&cache->lock);
-		wake_up(&caching_ctl->wait);
-	}
-
-	if (load_cache_only) {
-		btrfs_put_caching_control(caching_ctl);
-		return 0;
-	}
-
-	down_write(&fs_info->commit_root_sem);
 	refcount_inc(&caching_ctl->count);
 	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
-	up_write(&fs_info->commit_root_sem);
+	spin_unlock(&fs_info->block_group_cache_lock);
 
 	btrfs_get_block_group(cache);
 
 	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);
+out:
+	if (load_cache_only && caching_ctl)
+		btrfs_wait_space_cache_v1_finished(cache, caching_ctl);
+	if (caching_ctl)
+		btrfs_put_caching_control(caching_ctl);
 
 	return ret;
 }
@@ -892,8 +848,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct btrfs_block_group *block_group;
 	struct btrfs_free_cluster *cluster;
-	struct btrfs_root *tree_root = fs_info->tree_root;
-	struct btrfs_key key;
 	struct inode *inode;
 	struct kobject *kobj = NULL;
 	int ret;
@@ -971,42 +925,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&trans->transaction->dirty_bgs_lock);
 	mutex_unlock(&trans->transaction->cache_write_mutex);
 
-	if (!IS_ERR(inode)) {
+	ret = btrfs_remove_free_space_inode(trans, inode, block_group);
-		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
+	if (ret)
-		if (ret) {
-			btrfs_add_delayed_iput(inode);
-			goto out;
-		}
-		clear_nlink(inode);
-		/* One for the block groups ref */
-		spin_lock(&block_group->lock);
-		if (block_group->iref) {
-			block_group->iref = 0;
-			block_group->inode = NULL;
-			spin_unlock(&block_group->lock);
-			iput(inode);
-		} else {
-			spin_unlock(&block_group->lock);
-		}
-		/* One for our lookup ref */
-		btrfs_add_delayed_iput(inode);
-	}
-
-	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
-	key.type = 0;
-	key.offset = block_group->start;
-
-	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
 		goto out;
-	if (ret > 0)
-		btrfs_release_path(path);
-	if (ret == 0) {
-		ret = btrfs_del_item(trans, tree_root, path);
-		if (ret)
-			goto out;
-		btrfs_release_path(path);
-	}
 
 	spin_lock(&fs_info->block_group_cache_lock);
 	rb_erase(&block_group->cache_node,
@@ -1043,7 +964,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	if (block_group->cached == BTRFS_CACHE_STARTED)
 		btrfs_wait_block_group_cache_done(block_group);
 	if (block_group->has_caching_ctl) {
-		down_write(&fs_info->commit_root_sem);
+		spin_lock(&fs_info->block_group_cache_lock);
 		if (!caching_ctl) {
 			struct btrfs_caching_control *ctl;
 
@@ -1057,7 +978,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		}
 		if (caching_ctl)
 			list_del_init(&caching_ctl->list);
-		up_write(&fs_info->commit_root_sem);
+		spin_unlock(&fs_info->block_group_cache_lock);
 		if (caching_ctl) {
 			/* Once for the caching bgs list and once for us. */
 			btrfs_put_caching_control(caching_ctl);
@@ -1723,6 +1644,7 @@ out:
 static int exclude_super_stripes(struct btrfs_block_group *cache)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
+	const bool zoned = btrfs_is_zoned(fs_info);
 	u64 bytenr;
 	u64 *logical;
 	int stripe_len;
@@ -1744,6 +1666,14 @@ static int exclude_super_stripes(struct btrfs_block_group *cache)
 		if (ret)
 			return ret;
 
+		/* Shouldn't have super stripes in sequential zones */
+		if (zoned && nr) {
+			btrfs_err(fs_info,
+			"zoned: block group %llu must not contain super block",
+				  cache->start);
+			return -EUCLEAN;
+		}
+
 		while (nr--) {
 			u64 len = min_t(u64, stripe_len,
 				cache->start + cache->length - logical[nr]);
@@ -1805,7 +1735,7 @@ static struct btrfs_block_group *btrfs_create_block_group_cache(
 	INIT_LIST_HEAD(&cache->discard_list);
 	INIT_LIST_HEAD(&cache->dirty_list);
 	INIT_LIST_HEAD(&cache->io_list);
-	btrfs_init_free_space_ctl(cache);
+	btrfs_init_free_space_ctl(cache, cache->free_space_ctl);
 	atomic_set(&cache->frozen, 0);
 	mutex_init(&cache->free_space_lock);
 	btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
@@ -1985,6 +1915,51 @@ error:
 	return ret;
 }
 
+static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
+	struct btrfs_space_info *space_info;
+	struct rb_node *node;
+	int ret = 0;
+
+	for (node = rb_first_cached(&em_tree->map); node; node = rb_next(node)) {
+		struct extent_map *em;
+		struct map_lookup *map;
+		struct btrfs_block_group *bg;
+
+		em = rb_entry(node, struct extent_map, rb_node);
+		map = em->map_lookup;
+		bg = btrfs_create_block_group_cache(fs_info, em->start);
+		if (!bg) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		/* Fill dummy cache as FULL */
+		bg->length = em->len;
+		bg->flags = map->type;
+		bg->last_byte_to_unpin = (u64)-1;
+		bg->cached = BTRFS_CACHE_FINISHED;
+		bg->used = em->len;
+		bg->flags = map->type;
+		ret = btrfs_add_block_group_cache(fs_info, bg);
+		if (ret) {
+			btrfs_remove_free_space_cache(bg);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		btrfs_update_space_info(fs_info, bg->flags, em->len, em->len,
+					0, &space_info);
+		bg->space_info = space_info;
+		link_block_group(bg);
+
+		set_avail_alloc_bits(fs_info, bg->flags);
+	}
+	if (!ret)
+		btrfs_init_global_block_rsv(fs_info);
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -1995,6 +1970,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 	int need_clear = 0;
 	u64 cache_gen;
 
+	if (!info->extent_root)
+		return fill_dummy_bgs(info);
+
 	key.objectid = 0;
 	key.offset = 0;
 	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
@@ -2152,7 +2130,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	cache->flags = type;
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
-	cache->needs_free_space = 1;
+	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+		cache->needs_free_space = 1;
 	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/* We may have excluded something, so call this just in case */
@@ -2361,6 +2340,9 @@ static int cache_save_setup(struct btrfs_block_group *block_group,
 	int retries = 0;
 	int ret = 0;
 
+	if (!btrfs_test_opt(fs_info, SPACE_CACHE))
+		return 0;
+
 	/*
 	 * If this block group is smaller than 100 megs don't bother caching the
 	 * block group.
@@ -2401,7 +2383,7 @@ again:
 	 * time.
 	 */
 	BTRFS_I(inode)->generation = 0;
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 	if (ret) {
 		/*
 		 * So theoretically we could recover from this, simply set the
@@ -3307,14 +3289,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	struct btrfs_caching_control *caching_ctl;
 	struct rb_node *n;
 
-	down_write(&info->commit_root_sem);
+	spin_lock(&info->block_group_cache_lock);
 	while (!list_empty(&info->caching_block_groups)) {
 		caching_ctl = list_entry(info->caching_block_groups.next,
 					 struct btrfs_caching_control, list);
 		list_del(&caching_ctl->list);
 		btrfs_put_caching_control(caching_ctl);
 	}
-	up_write(&info->commit_root_sem);
+	spin_unlock(&info->block_group_cache_lock);
 
 	spin_lock(&info->unused_bgs_lock);
 	while (!list_empty(&info->unused_bgs)) {

fs/btrfs/block-group.h

@@ -268,6 +268,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
 u64 btrfs_get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 int btrfs_free_block_groups(struct btrfs_fs_info *info);
+void btrfs_wait_space_cache_v1_finished(struct btrfs_block_group *cache,
+				struct btrfs_caching_control *caching_ctl);
 
 static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
 {

fs/btrfs/block-rsv.c

@@ -426,6 +426,14 @@ void btrfs_init_global_block_rsv(struct btrfs_fs_info *fs_info)
 	fs_info->delayed_block_rsv.space_info = space_info;
 	fs_info->delayed_refs_rsv.space_info = space_info;
 
+	/*
+	 * Our various recovery options can leave us with NULL roots, so check
+	 * here and just bail before we go dereferencing NULLs everywhere.
+	 */
+	if (!fs_info->extent_root || !fs_info->csum_root ||
+	    !fs_info->dev_root || !fs_info->chunk_root || !fs_info->tree_root)
+		return;
+
 	fs_info->extent_root->block_rsv = &fs_info->delayed_refs_rsv;
 	fs_info->csum_root->block_rsv = &fs_info->delayed_refs_rsv;
 	fs_info->dev_root->block_rsv = &fs_info->global_block_rsv;

fs/btrfs/btrfs_inode.h

@@ -35,6 +35,13 @@ enum {
 	BTRFS_INODE_IN_DELALLOC_LIST,
 	BTRFS_INODE_HAS_PROPS,
 	BTRFS_INODE_SNAPSHOT_FLUSH,
+	/*
+	 * Set and used when logging an inode and it serves to signal that an
+	 * inode does not have xattrs, so subsequent fsyncs can avoid searching
+	 * for xattrs to log. This bit must be cleared whenever a xattr is added
+	 * to an inode.
+	 */
+	BTRFS_INODE_NO_XATTRS,
 };
 
 /* in memory btrfs inode */
@@ -50,7 +57,8 @@ struct btrfs_inode {
 	/*
 	 * Lock for counters and all fields used to determine if the inode is in
 	 * the log or not (last_trans, last_sub_trans, last_log_commit,
-	 * logged_trans).
+	 * logged_trans), to access/update new_delalloc_bytes and to update the
+	 * VFS' inode number of bytes used.
 	 */
 	spinlock_t lock;
 
@@ -203,16 +211,6 @@ struct btrfs_inode {
 	/* Hook into fs_info->delayed_iputs */
 	struct list_head delayed_iput;
 
-	/*
-	 * To avoid races between lockless (i_mutex not held) direct IO writes
-	 * and concurrent fsync requests. Direct IO writes must acquire read
-	 * access on this semaphore for creating an extent map and its
-	 * corresponding ordered extent. The fast fsync path must acquire write
-	 * access on this semaphore before it collects ordered extents and
-	 * extent maps.
-	 */
-	struct rw_semaphore dio_sem;
-
 	struct inode vfs_inode;
 };
 
@@ -341,8 +339,7 @@ static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
 		u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num)
 {
 	struct btrfs_root *root = inode->root;
-	struct btrfs_super_block *sb = root->fs_info->super_copy;
+	const u32 csum_size = root->fs_info->csum_size;
-	const u16 csum_size = btrfs_super_csum_size(sb);
 
 	/* Output minus objectid, which is more meaningful */
 	if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID)

fs/btrfs/check-integrity.c

@@ -233,7 +233,6 @@ struct btrfsic_stack_frame {
 struct btrfsic_state {
 	u32 print_mask;
 	int include_extent_data;
-	int csum_size;
 	struct list_head all_blocks_list;
 	struct btrfsic_block_hashtable block_hashtable;
 	struct btrfsic_block_link_hashtable block_link_hashtable;
@@ -660,8 +659,6 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
 		return -1;
 	}
 
-	state->csum_size = btrfs_super_csum_size(selected_super);
-
 	for (pass = 0; pass < 3; pass++) {
 		int num_copies;
 		int mirror_num;
@@ -954,7 +951,7 @@ static noinline_for_stack int btrfsic_process_metablock(
 	sf->prev = NULL;
 
 continue_with_new_stack_frame:
-	sf->block->generation = le64_to_cpu(sf->hdr->generation);
+	sf->block->generation = btrfs_stack_header_generation(sf->hdr);
 	if (0 == sf->hdr->level) {
 		struct btrfs_leaf *const leafhdr =
 		    (struct btrfs_leaf *)sf->hdr;
@@ -1723,7 +1720,7 @@ static noinline_for_stack int btrfsic_test_for_metadata(
 		crypto_shash_update(shash, data, sublen);
 	}
 	crypto_shash_final(shash, csum);
-	if (memcmp(csum, h->csum, state->csum_size))
+	if (memcmp(csum, h->csum, fs_info->csum_size))
 		return 1;
 
 	return 0; /* is metadata */
@@ -2695,8 +2692,7 @@ static void __btrfsic_submit_bio(struct bio *bio)
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_disk=%p)\n",
 			       bio_op(bio), bio->bi_opf, segs,
-			       (unsigned long long)bio->bi_iter.bi_sector,
+			       bio->bi_iter.bi_sector, dev_bytenr, bio->bi_disk);
-			       dev_bytenr, bio->bi_disk);
 
 		mapped_datav = kmalloc_array(segs,
 					     sizeof(*mapped_datav), GFP_NOFS);
@@ -2797,7 +2793,6 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 	state->fs_info = fs_info;
 	state->print_mask = print_mask;
 	state->include_extent_data = including_extent_data;
-	state->csum_size = 0;
 	state->metablock_size = fs_info->nodesize;
 	state->datablock_size = fs_info->sectorsize;
 	INIT_LIST_HEAD(&state->all_blocks_list);

fs/btrfs/compression.c

@@ -131,10 +131,8 @@ static int btrfs_decompress_bio(struct compressed_bio *cb);
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
 				      unsigned long disk_size)
 {
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
-
 	return sizeof(struct compressed_bio) +
-		(DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size;
+		(DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * fs_info->csum_size;
 }
 
 static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
@@ -142,7 +140,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
-	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
 	struct page *page;
 	unsigned long i;
 	char *kaddr;
@@ -150,7 +148,7 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
 	struct compressed_bio *cb = bio->bi_private;
 	u8 *cb_sum = cb->sums;
 
-	if (inode->flags & BTRFS_INODE_NODATASUM)
+	if (!fs_info->csum_root || (inode->flags & BTRFS_INODE_NODATASUM))
 		return 0;
 
 	shash->tfm = fs_info->csum_shash;
@@ -220,7 +218,7 @@ static void end_compressed_bio_read(struct bio *bio)
 
 	inode = cb->inode;
 	ret = check_compressed_csum(BTRFS_I(inode), bio,
-				    (u64)bio->bi_iter.bi_sector << 9);
+				    bio->bi_iter.bi_sector << 9);
 	if (ret)
 		goto csum_failed;
 
@@ -622,13 +620,12 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	unsigned long pg_index;
 	struct page *page;
 	struct bio *comp_bio;
-	u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
+	u64 cur_disk_byte = bio->bi_iter.bi_sector << 9;
 	u64 em_len;
 	u64 em_start;
 	struct extent_map *em;
 	blk_status_t ret = BLK_STS_RESOURCE;
 	int faili = 0;
-	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 	u8 *sums;
 
 	em_tree = &BTRFS_I(inode)->extent_tree;
@@ -722,15 +719,12 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			 */
 			refcount_inc(&cb->pending_bios);
 
-			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+			ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
-				ret = btrfs_lookup_bio_sums(inode, comp_bio,
+			BUG_ON(ret); /* -ENOMEM */
-							    (u64)-1, sums);
-				BUG_ON(ret); /* -ENOMEM */
-			}
 
 			nr_sectors = DIV_ROUND_UP(comp_bio->bi_iter.bi_size,
 						  fs_info->sectorsize);
-			sums += csum_size * nr_sectors;
+			sums += fs_info->csum_size * nr_sectors;
 
 			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 			if (ret) {
@@ -751,10 +745,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	ret = btrfs_bio_wq_end_io(fs_info, comp_bio, BTRFS_WQ_ENDIO_DATA);
 	BUG_ON(ret); /* -ENOMEM */
 
-	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
+	ret = btrfs_lookup_bio_sums(inode, comp_bio, sums);
-		ret = btrfs_lookup_bio_sums(inode, comp_bio, (u64)-1, sums);
+	BUG_ON(ret); /* -ENOMEM */
-		BUG_ON(ret); /* -ENOMEM */
-	}
 
 	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num);
 	if (ret) {

fs/btrfs/ctree.c

@@ -1278,14 +1278,11 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	if (!tm)
 		return eb;
 
-	btrfs_set_path_blocking(path);
-	btrfs_set_lock_blocking_read(eb);
-
 	if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		BUG_ON(tm->slot != 0);
 		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
 		if (!eb_rewin) {
-			btrfs_tree_read_unlock_blocking(eb);
+			btrfs_tree_read_unlock(eb);
 			free_extent_buffer(eb);
 			return NULL;
 		}
@@ -1297,13 +1294,13 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	} else {
 		eb_rewin = btrfs_clone_extent_buffer(eb);
 		if (!eb_rewin) {
-			btrfs_tree_read_unlock_blocking(eb);
+			btrfs_tree_read_unlock(eb);
 			free_extent_buffer(eb);
 			return NULL;
 		}
 	}
 
-	btrfs_tree_read_unlock_blocking(eb);
+	btrfs_tree_read_unlock(eb);
 	free_extent_buffer(eb);
 
 	btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin),
@@ -1356,7 +1353,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		old = read_tree_block(fs_info, logical, 0, level, NULL);
+		old = read_tree_block(fs_info, logical, root->root_key.objectid,
+				      0, level, NULL);
 		if (WARN_ON(IS_ERR(old) || !extent_buffer_uptodate(old))) {
 			if (!IS_ERR(old))
 				free_extent_buffer(old);
@@ -1373,9 +1371,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 		free_extent_buffer(eb_root);
 		eb = alloc_dummy_extent_buffer(fs_info, logical);
 	} else {
-		btrfs_set_lock_blocking_read(eb_root);
 		eb = btrfs_clone_extent_buffer(eb_root);
-		btrfs_tree_read_unlock_blocking(eb_root);
+		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
 	}
 
@@ -1483,10 +1480,6 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	search_start = buf->start & ~((u64)SZ_1G - 1);
 
-	if (parent)
-		btrfs_set_lock_blocking_write(parent);
-	btrfs_set_lock_blocking_write(buf);
-
 	/*
 	 * Before CoWing this block for later modification, check if it's
 	 * the subtree root and do the delayed subtree trace if needed.
@@ -1578,7 +1571,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *cur;
 	u64 blocknr;
-	u64 gen;
 	u64 search_start = *last_ret;
 	u64 last_block = 0;
 	u64 other;
@@ -1586,14 +1578,10 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 	int end_slot;
 	int i;
 	int err = 0;
-	int parent_level;
-	int uptodate;
 	u32 blocksize;
 	int progress_passed = 0;
 	struct btrfs_disk_key disk_key;
 
-	parent_level = btrfs_header_level(parent);
-
 	WARN_ON(trans->transaction != fs_info->running_transaction);
 	WARN_ON(trans->transid != fs_info->generation);
 
@@ -1604,10 +1592,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 	if (parent_nritems <= 1)
 		return 0;
 
-	btrfs_set_lock_blocking_write(parent);
-
 	for (i = start_slot; i <= end_slot; i++) {
-		struct btrfs_key first_key;
 		int close = 1;
 
 		btrfs_node_key(parent, &disk_key, i);
@@ -1616,8 +1601,6 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 
 		progress_passed = 1;
 		blocknr = btrfs_node_blockptr(parent, i);
-		gen = btrfs_node_ptr_generation(parent, i);
-		btrfs_node_key_to_cpu(parent, &first_key, i);
 		if (last_block == 0)
 			last_block = blocknr;
 
@@ -1634,36 +1617,13 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
-		cur = find_extent_buffer(fs_info, blocknr);
+		cur = btrfs_read_node_slot(parent, i);
-		if (cur)
+		if (IS_ERR(cur))
-			uptodate = btrfs_buffer_uptodate(cur, gen, 0);
+			return PTR_ERR(cur);
-		else
-			uptodate = 0;
-		if (!cur || !uptodate) {
-			if (!cur) {
-				cur = read_tree_block(fs_info, blocknr, gen,
-						      parent_level - 1,
-						      &first_key);
-				if (IS_ERR(cur)) {
-					return PTR_ERR(cur);
-				} else if (!extent_buffer_uptodate(cur)) {
-					free_extent_buffer(cur);
-					return -EIO;
-				}
-			} else if (!uptodate) {
-				err = btrfs_read_buffer(cur, gen,
-						parent_level - 1,&first_key);
-				if (err) {
-					free_extent_buffer(cur);
-					return err;
-				}
-			}
-		}
 		if (search_start == 0)
 			search_start = last_block;
 
 		btrfs_tree_lock(cur);
-		btrfs_set_lock_blocking_write(cur);
 		err = __btrfs_cow_block(trans, root, cur, parent, i,
 					&cur, search_start,
 					min(16 * blocksize,
@@ -1723,9 +1683,10 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 		oip = offset_in_page(offset);
 
 		if (oip + key_size <= PAGE_SIZE) {
-			const unsigned long idx = offset >> PAGE_SHIFT;
+			const unsigned long idx = get_eb_page_index(offset);
 			char *kaddr = page_address(eb->pages[idx]);
 
+			oip = get_eb_offset_in_page(eb, offset);
 			tmp = (struct btrfs_disk_key *)(kaddr + oip);
 		} else {
 			read_extent_buffer(eb, &unaligned, offset, key_size);
@@ -1801,6 +1762,7 @@ struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
 
 	btrfs_node_key_to_cpu(parent, &first_key, slot);
 	eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot),
+			     btrfs_header_owner(parent),
 			     btrfs_node_ptr_generation(parent, slot),
 			     level - 1, &first_key);
 	if (!IS_ERR(eb) && !extent_buffer_uptodate(eb)) {
@@ -1835,8 +1797,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 	mid = path->nodes[level];
 
-	WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK &&
+	WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK);
-		path->locks[level] != BTRFS_WRITE_LOCK_BLOCKING);
 	WARN_ON(btrfs_header_generation(mid) != trans->transid);
 
 	orig_ptr = btrfs_node_blockptr(mid, orig_slot);
@@ -1865,7 +1826,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		}
 
 		btrfs_tree_lock(child);
-		btrfs_set_lock_blocking_write(child);
 		ret = btrfs_cow_block(trans, root, child, mid, 0, &child,
 				      BTRFS_NESTING_COW);
 		if (ret) {
@@ -1904,7 +1864,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 	if (left) {
 		__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
-		btrfs_set_lock_blocking_write(left);
 		wret = btrfs_cow_block(trans, root, left,
 				       parent, pslot - 1, &left,
 				       BTRFS_NESTING_LEFT_COW);
@@ -1920,7 +1879,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 	if (right) {
 		__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
-		btrfs_set_lock_blocking_write(right);
 		wret = btrfs_cow_block(trans, root, right,
 				       parent, pslot + 1, &right,
 				       BTRFS_NESTING_RIGHT_COW);
@@ -2084,7 +2042,6 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 		u32 left_nr;
 
 		__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
-		btrfs_set_lock_blocking_write(left);
 
 		left_nr = btrfs_header_nritems(left);
 		if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
@@ -2139,7 +2096,6 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 		u32 right_nr;
 
 		__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
-		btrfs_set_lock_blocking_write(right);
 
 		right_nr = btrfs_header_nritems(right);
 		if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
@@ -2243,7 +2199,7 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
 		search = btrfs_node_blockptr(node, nr);
 		if ((search <= target && target - search <= 65536) ||
 		    (search > target && search - target <= 65536)) {
-			readahead_tree_block(fs_info, search);
+			btrfs_readahead_node_child(node, nr);
 			nread += blocksize;
 		}
 		nscan++;
@@ -2252,16 +2208,11 @@ static void reada_for_search(struct btrfs_fs_info *fs_info,
 	}
 }
 
-static noinline void reada_for_balance(struct btrfs_fs_info *fs_info,
+static noinline void reada_for_balance(struct btrfs_path *path, int level)
-				       struct btrfs_path *path, int level)
 {
+	struct extent_buffer *parent;
 	int slot;
 	int nritems;
-	struct extent_buffer *parent;
-	struct extent_buffer *eb;
-	u64 gen;
-	u64 block1 = 0;
-	u64 block2 = 0;
 
 	parent = path->nodes[level + 1];
 	if (!parent)
@@ -2270,32 +2221,10 @@ static noinline void reada_for_balance(struct btrfs_fs_info *fs_info,
 	nritems = btrfs_header_nritems(parent);
 	slot = path->slots[level + 1];
 
-	if (slot > 0) {
+	if (slot > 0)
-		block1 = btrfs_node_blockptr(parent, slot - 1);
+		btrfs_readahead_node_child(parent, slot - 1);
-		gen = btrfs_node_ptr_generation(parent, slot - 1);
+	if (slot + 1 < nritems)
-		eb = find_extent_buffer(fs_info, block1);
+		btrfs_readahead_node_child(parent, slot + 1);
-		/*
-		 * if we get -eagain from btrfs_buffer_uptodate, we
-		 * don't want to return eagain here.  That will loop
-		 * forever
-		 */
-		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
-			block1 = 0;
-		free_extent_buffer(eb);
-	}
-	if (slot + 1 < nritems) {
-		block2 = btrfs_node_blockptr(parent, slot + 1);
-		gen = btrfs_node_ptr_generation(parent, slot + 1);
-		eb = find_extent_buffer(fs_info, block2);
-		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
-			block2 = 0;
-		free_extent_buffer(eb);
-	}
-
-	if (block1)
-		readahead_tree_block(fs_info, block1);
-	if (block2)
-		readahead_tree_block(fs_info, block2);
 }
 
 
@@ -2399,14 +2328,6 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 			return 0;
 		}
 
-		/* the pages were up to date, but we failed
-		 * the generation number check.  Do a full
-		 * read for the generation number that is correct.
-		 * We must do this without dropping locks so
-		 * we can trust our generation number
-		 */
-		btrfs_set_path_blocking(p);
-
 		/* now we're allowed to do a blocking uptodate check */
 		ret = btrfs_read_buffer(tmp, gen, parent_level - 1, &first_key);
 		if (!ret) {
@@ -2426,14 +2347,13 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	 * out which blocks to read.
 	 */
 	btrfs_unlock_up_safe(p, level + 1);
-	btrfs_set_path_blocking(p);
 
 	if (p->reada != READA_NONE)
 		reada_for_search(fs_info, p, level, slot, key->objectid);
 
 	ret = -EAGAIN;
-	tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
+	tmp = read_tree_block(fs_info, blocknr, root->root_key.objectid,
-			      &first_key);
+			      gen, parent_level - 1, &first_key);
 	if (!IS_ERR(tmp)) {
 		/*
 		 * If the read above didn't mark this buffer up to date,
@@ -2468,58 +2388,42 @@ setup_nodes_for_search(struct btrfs_trans_handle *trans,
 		       int *write_lock_level)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int ret;
+	int ret = 0;
 
 	if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >=
 	    BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) {
-		int sret;
 
 		if (*write_lock_level < level + 1) {
 			*write_lock_level = level + 1;
 			btrfs_release_path(p);
-			goto again;
+			return -EAGAIN;
 		}
 
-		btrfs_set_path_blocking(p);
+		reada_for_balance(p, level);
-		reada_for_balance(fs_info, p, level);
+		ret = split_node(trans, root, p, level);
-		sret = split_node(trans, root, p, level);
 
-		BUG_ON(sret > 0);
-		if (sret) {
-			ret = sret;
-			goto done;
-		}
 		b = p->nodes[level];
 	} else if (ins_len < 0 && btrfs_header_nritems(b) <
 		   BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 2) {
-		int sret;
 
 		if (*write_lock_level < level + 1) {
 			*write_lock_level = level + 1;
 			btrfs_release_path(p);
-			goto again;
+			return -EAGAIN;
 		}
 
-		btrfs_set_path_blocking(p);
+		reada_for_balance(p, level);
-		reada_for_balance(fs_info, p, level);
+		ret = balance_level(trans, root, p, level);
-		sret = balance_level(trans, root, p, level);
+		if (ret)
+			return ret;
 
-		if (sret) {
-			ret = sret;
-			goto done;
-		}
 		b = p->nodes[level];
 		if (!b) {
 			btrfs_release_path(p);
-			goto again;
+			return -EAGAIN;
 		}
 		BUG_ON(btrfs_header_nritems(b) == 1);
 	}
-	return 0;
-
-again:
-	ret = -EAGAIN;
-done:
 	return ret;
 }
 
@@ -2616,7 +2520,7 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
 		 * We don't know the level of the root node until we actually
 		 * have it read locked
 		 */
-		b = __btrfs_read_lock_root_node(root, p->recurse);
+		b = btrfs_read_lock_root_node(root);
 		level = btrfs_header_level(b);
 		if (level > write_lock_level)
 			goto out;
@@ -2752,7 +2656,6 @@ again:
 				goto again;
 			}
 
-			btrfs_set_path_blocking(p);
 			if (last_level)
 				err = btrfs_cow_block(trans, root, b, NULL, 0,
 						      &b,
@@ -2822,7 +2725,6 @@ cow_done:
 					goto again;
 				}
 
-				btrfs_set_path_blocking(p);
 				err = split_leaf(trans, root, key,
 						 p, ins_len, ret == 0);
 
@@ -2884,17 +2786,10 @@ cow_done:
 		if (!p->skip_locking) {
 			level = btrfs_header_level(b);
 			if (level <= write_lock_level) {
-				if (!btrfs_try_tree_write_lock(b)) {
+				btrfs_tree_lock(b);
-					btrfs_set_path_blocking(p);
-					btrfs_tree_lock(b);
-				}
 				p->locks[level] = BTRFS_WRITE_LOCK;
 			} else {
-				if (!btrfs_tree_read_lock_atomic(b)) {
+				btrfs_tree_read_lock(b);
-					btrfs_set_path_blocking(p);
-					__btrfs_tree_read_lock(b, BTRFS_NESTING_NORMAL,
-							       p->recurse);
-				}
 				p->locks[level] = BTRFS_READ_LOCK;
 			}
 			p->nodes[level] = b;
@@ -2902,12 +2797,6 @@ cow_done:
 	}
 	ret = 1;
 done:
-	/*
-	 * we don't really know what they plan on doing with the path
-	 * from here on, so for now just mark it as blocking
-	 */
-	if (!p->leave_spinning)
-		btrfs_set_path_blocking(p);
 	if (ret < 0 && !p->skip_release_on_error)
 		btrfs_release_path(p);
 	return ret;
@@ -2999,10 +2888,7 @@ again:
 		}
 
 		level = btrfs_header_level(b);
-		if (!btrfs_tree_read_lock_atomic(b)) {
+		btrfs_tree_read_lock(b);
-			btrfs_set_path_blocking(p);
-			btrfs_tree_read_lock(b);
-		}
 		b = tree_mod_log_rewind(fs_info, p, b, time_seq);
 		if (!b) {
 			ret = -ENOMEM;
@@ -3013,8 +2899,6 @@ again:
 	}
 	ret = 1;
 done:
-	if (!p->leave_spinning)
-		btrfs_set_path_blocking(p);
 	if (ret < 0)
 		btrfs_release_path(p);
 
@@ -3441,7 +3325,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	add_root_to_dirty_list(root);
 	atomic_inc(&c->refs);
 	path->nodes[level] = c;
-	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
+	path->locks[level] = BTRFS_WRITE_LOCK;
 	path->slots[level] = 0;
 	return 0;
 }
@@ -3562,7 +3446,6 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 			   (c_nritems - mid) * sizeof(struct btrfs_key_ptr));
 	btrfs_set_header_nritems(split, c_nritems - mid);
 	btrfs_set_header_nritems(c, mid);
-	ret = 0;
 
 	btrfs_mark_buffer_dirty(c);
 	btrfs_mark_buffer_dirty(split);
@@ -3580,7 +3463,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 		btrfs_tree_unlock(split);
 		free_extent_buffer(split);
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -3814,7 +3697,6 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 		return 1;
 
 	__btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
-	btrfs_set_lock_blocking_write(right);
 
 	free_space = btrfs_leaf_free_space(right);
 	if (free_space < data_size)
@@ -4053,7 +3935,6 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 		return 1;
 
 	__btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
-	btrfs_set_lock_blocking_write(left);
 
 	free_space = btrfs_leaf_free_space(left);
 	if (free_space < data_size) {
@@ -4448,7 +4329,6 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 			goto err;
 	}
 
-	btrfs_set_path_blocking(path);
 	ret = split_leaf(trans, root, &key, path, ins_len, 1);
 	if (ret)
 		goto err;
@@ -4478,8 +4358,6 @@ static noinline int split_item(struct btrfs_path *path,
 	leaf = path->nodes[0];
 	BUG_ON(btrfs_leaf_free_space(leaf) < sizeof(struct btrfs_item));
 
-	btrfs_set_path_blocking(path);
-
 	item = btrfs_item_nr(path->slots[0]);
 	orig_offset = btrfs_item_offset(leaf, item);
 	item_size = btrfs_item_size(leaf, item);
@@ -5055,7 +4933,6 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		if (leaf == root->node) {
 			btrfs_set_header_level(leaf, 0);
 		} else {
-			btrfs_set_path_blocking(path);
 			btrfs_clean_tree_block(leaf);
 			btrfs_del_leaf(trans, root, path, leaf);
 		}
@@ -5077,7 +4954,6 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			slot = path->slots[1];
 			atomic_inc(&leaf->refs);
 
-			btrfs_set_path_blocking(path);
 			wret = push_leaf_left(trans, root, path, 1, 1,
 					      1, (u32)-1);
 			if (wret < 0 && wret != -ENOSPC)
@@ -5248,7 +5124,6 @@ find_next_key:
 		 */
 		if (slot >= nritems) {
 			path->slots[level] = slot;
-			btrfs_set_path_blocking(path);
 			sret = btrfs_find_next_key(root, path, min_key, level,
 						  min_trans);
 			if (sret == 0) {
@@ -5265,7 +5140,6 @@ find_next_key:
 			ret = 0;
 			goto out;
 		}
-		btrfs_set_path_blocking(path);
 		cur = btrfs_read_node_slot(cur, slot);
 		if (IS_ERR(cur)) {
 			ret = PTR_ERR(cur);
@@ -5282,7 +5156,6 @@ out:
 	path->keep_locks = keep_locks;
 	if (ret == 0) {
 		btrfs_unlock_up_safe(path, path->lowest_level + 1);
-		btrfs_set_path_blocking(path);
 		memcpy(min_key, &found_key, sizeof(found_key));
 	}
 	return ret;
@@ -5384,8 +5257,7 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
 	struct btrfs_key key;
 	u32 nritems;
 	int ret;
-	int old_spinning = path->leave_spinning;
+	int i;
-	int next_rw_lock = 0;
 
 	nritems = btrfs_header_nritems(path->nodes[0]);
 	if (nritems == 0)
@@ -5395,11 +5267,9 @@ int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
 again:
 	level = 1;
 	next = NULL;
-	next_rw_lock = 0;
 	btrfs_release_path(path);
 
 	path->keep_locks = 1;
-	path->leave_spinning = 1;
 
 	if (time_seq)
 		ret = btrfs_search_old_slot(root, &key, path, time_seq);
@@ -5459,13 +5329,22 @@ again:
 			continue;
 		}
 
-		if (next) {
+
-			btrfs_tree_unlock_rw(next, next_rw_lock);
+		/*
-			free_extent_buffer(next);
+		 * Our current level is where we're going to start from, and to
+		 * make sure lockdep doesn't complain we need to drop our locks
+		 * and nodes from 0 to our current level.
+		 */
+		for (i = 0; i < level; i++) {
+			if (path->locks[level]) {
+				btrfs_tree_read_unlock(path->nodes[i]);
+				path->locks[i] = 0;
+			}
+			free_extent_buffer(path->nodes[i]);
+			path->nodes[i] = NULL;
 		}
 
 		next = c;
-		next_rw_lock = path->locks[level];
 		ret = read_block_for_search(root, path, &next, level,
 					    slot, &key);
 		if (ret == -EAGAIN)
@@ -5491,28 +5370,18 @@ again:
 				cond_resched();
 				goto again;
 			}
-			if (!ret) {
+			if (!ret)
-				btrfs_set_path_blocking(path);
+				btrfs_tree_read_lock(next);
-				__btrfs_tree_read_lock(next,
-						       BTRFS_NESTING_RIGHT,
-						       path->recurse);
-			}
-			next_rw_lock = BTRFS_READ_LOCK;
 		}
 		break;
 	}
 	path->slots[level] = slot;
 	while (1) {
 		level--;
-		c = path->nodes[level];
-		if (path->locks[level])
-			btrfs_tree_unlock_rw(c, path->locks[level]);
-
-		free_extent_buffer(c);
 		path->nodes[level] = next;
 		path->slots[level] = 0;
 		if (!path->skip_locking)
-			path->locks[level] = next_rw_lock;
+			path->locks[level] = BTRFS_READ_LOCK;
 		if (!level)
 			break;
 
@@ -5526,23 +5395,12 @@ again:
 			goto done;
 		}
 
-		if (!path->skip_locking) {
+		if (!path->skip_locking)
-			ret = btrfs_try_tree_read_lock(next);
+			btrfs_tree_read_lock(next);
-			if (!ret) {
-				btrfs_set_path_blocking(path);
-				__btrfs_tree_read_lock(next,
-						       BTRFS_NESTING_RIGHT,
-						       path->recurse);
-			}
-			next_rw_lock = BTRFS_READ_LOCK;
-		}
 	}
 	ret = 0;
 done:
 	unlock_up(path, 0, 1, 0, NULL);
-	path->leave_spinning = old_spinning;
-	if (!old_spinning)
-		btrfs_set_path_blocking(path);
 
 	return ret;
 }
@@ -5564,7 +5422,6 @@ int btrfs_previous_item(struct btrfs_root *root,
 
 	while (1) {
 		if (path->slots[0] == 0) {
-			btrfs_set_path_blocking(path);
 			ret = btrfs_prev_leaf(root, path);
 			if (ret != 0)
 				return ret;
@@ -5606,7 +5463,6 @@ int btrfs_previous_extent_item(struct btrfs_root *root,
 
 	while (1) {
 		if (path->slots[0] == 0) {
-			btrfs_set_path_blocking(path);
 			ret = btrfs_prev_leaf(root, path);
 			if (ret != 0)
 				return ret;

fs/btrfs/ctree.h

@@ -27,6 +27,7 @@
 #include <linux/dynamic_debug.h>
 #include <linux/refcount.h>
 #include <linux/crc32c.h>
+#include <linux/iomap.h>
 #include "extent-io-tree.h"
 #include "extent_io.h"
 #include "extent_map.h"
@@ -65,12 +66,6 @@ struct btrfs_ref;
 
 #define BTRFS_OLDEST_GENERATION	0ULL
 
-/*
- * the max metadata block size.  This limit is somewhat artificial,
- * but the memmove costs go through the roof for larger blocks.
- */
-#define BTRFS_MAX_METADATA_BLOCKSIZE 65536
-
 /*
  * we can actually store much bigger names, but lets not confuse the rest
  * of linux
@@ -369,11 +364,9 @@ struct btrfs_path {
 	unsigned int search_for_split:1;
 	unsigned int keep_locks:1;
 	unsigned int skip_locking:1;
-	unsigned int leave_spinning:1;
 	unsigned int search_commit_root:1;
 	unsigned int need_commit_sem:1;
 	unsigned int skip_release_on_error:1;
-	unsigned int recurse:1;
 };
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
 					sizeof(struct btrfs_item))
@@ -468,10 +461,11 @@ struct btrfs_discard_ctl {
 	struct btrfs_block_group *block_group;
 	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
 	u64 prev_discard;
+	u64 prev_discard_time;
 	atomic_t discardable_extents;
 	atomic64_t discardable_bytes;
 	u64 max_discard_size;
-	unsigned long delay;
+	u64 delay_ms;
 	u32 iops_limit;
 	u32 kbps_limit;
 	u64 discard_extent_bytes;
@@ -558,6 +552,9 @@ enum {
 
 	/* Indicate that the discard workqueue can service discards. */
 	BTRFS_FS_DISCARD_RUNNING,
+
+	/* Indicate that we need to cleanup space cache v1 */
+	BTRFS_FS_CLEANUP_SPACE_CACHE_V1,
 };
 
 /*
@@ -911,6 +908,7 @@ struct btrfs_fs_info {
 
 	/* Extent buffer radix tree */
 	spinlock_t buffer_lock;
+	/* Entries are eb->start / sectorsize */
 	struct radix_tree_root buffer_radix;
 
 	/* next backup root to be overwritten */
@@ -933,6 +931,10 @@ struct btrfs_fs_info {
 	/* Cached block sizes */
 	u32 nodesize;
 	u32 sectorsize;
+	/* ilog2 of sectorsize, use to avoid 64bit division */
+	u32 sectorsize_bits;
+	u32 csum_size;
+	u32 csums_per_leaf;
 	u32 stripesize;
 
 	/* Block groups and devices containing active swapfiles. */
@@ -950,6 +952,18 @@ struct btrfs_fs_info {
 	/* Type of exclusive operation running */
 	unsigned long exclusive_operation;
 
+	/*
+	 * Zone size > 0 when in ZONED mode, otherwise it's used for a check
+	 * if the mode is enabled
+	 */
+	union {
+		u64 zone_size;
+		u64 zoned;
+	};
+
+	/* Max size to emit ZONE_APPEND write command */
+	u64 max_zone_append_size;
+
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	spinlock_t ref_verify_lock;
 	struct rb_root block_tree;
@@ -1020,7 +1034,7 @@ enum {
 	BTRFS_ROOT_DEAD_RELOC_TREE,
 	/* Mark dead root stored on device whose cleanup needs to be resumed */
 	BTRFS_ROOT_DEAD_TREE,
-	/* The root has a log tree. Used only for subvolume roots. */
+	/* The root has a log tree. Used for subvolume roots and the tree root. */
 	BTRFS_ROOT_HAS_LOG_TREE,
 	/* Qgroup flushing is in progress */
 	BTRFS_ROOT_QGROUP_FLUSHING,
@@ -1059,15 +1073,6 @@ struct btrfs_root {
 	spinlock_t accounting_lock;
 	struct btrfs_block_rsv *block_rsv;
 
-	/* free ino cache stuff */
-	struct btrfs_free_space_ctl *free_ino_ctl;
-	enum btrfs_caching_type ino_cache_state;
-	spinlock_t ino_cache_lock;
-	wait_queue_head_t ino_cache_wait;
-	struct btrfs_free_space_ctl *free_ino_pinned;
-	u64 ino_cache_progress;
-	struct inode *ino_cache_inode;
-
 	struct mutex log_mutex;
 	wait_queue_head_t log_writer_wait;
 	wait_queue_head_t log_commit_wait[2];
@@ -1226,6 +1231,63 @@ struct btrfs_replace_extent_info {
 	int insertions;
 };
 
+/* Arguments for btrfs_drop_extents() */
+struct btrfs_drop_extents_args {
+	/* Input parameters */
+
+	/*
+	 * If NULL, btrfs_drop_extents() will allocate and free its own path.
+	 * If 'replace_extent' is true, this must not be NULL. Also the path
+	 * is always released except if 'replace_extent' is true and
+	 * btrfs_drop_extents() sets 'extent_inserted' to true, in which case
+	 * the path is kept locked.
+	 */
+	struct btrfs_path *path;
+	/* Start offset of the range to drop extents from */
+	u64 start;
+	/* End (exclusive, last byte + 1) of the range to drop extents from */
+	u64 end;
+	/* If true drop all the extent maps in the range */
+	bool drop_cache;
+	/*
+	 * If true it means we want to insert a new extent after dropping all
+	 * the extents in the range. If this is true, the 'extent_item_size'
+	 * parameter must be set as well and the 'extent_inserted' field will
+	 * be set to true by btrfs_drop_extents() if it could insert the new
+	 * extent.
+	 * Note: when this is set to true the path must not be NULL.
+	 */
+	bool replace_extent;
+	/*
+	 * Used if 'replace_extent' is true. Size of the file extent item to
+	 * insert after dropping all existing extents in the range
+	 */
+	u32 extent_item_size;
+
+	/* Output parameters */
+
+	/*
+	 * Set to the minimum between the input parameter 'end' and the end
+	 * (exclusive, last byte + 1) of the last dropped extent. This is always
+	 * set even if btrfs_drop_extents() returns an error.
+	 */
+	u64 drop_end;
+	/*
+	 * The number of allocated bytes found in the range. This can be smaller
+	 * than the range's length when there are holes in the range.
+	 */
+	u64 bytes_found;
+	/*
+	 * Only set if 'replace_extent' is true. Set to true if we were able
+	 * to insert a replacement extent after dropping all extents in the
+	 * range, otherwise set to false by btrfs_drop_extents().
+	 * Also, if btrfs_drop_extents() has set this to true it means it
+	 * returned with the path locked, otherwise if it has set this to
+	 * false it has returned with the path released.
+	 */
+	bool extent_inserted;
+};
+
 struct btrfs_file_private {
 	void *filldir_buf;
 };
@@ -1284,7 +1346,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG	 (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG		(1 << 16)
-#define BTRFS_MOUNT_INODE_MAP_CACHE	(1 << 17)
+/* bit 17 is free */
 #define BTRFS_MOUNT_USEBACKUPROOT	(1 << 18)
 #define BTRFS_MOUNT_SKIP_BALANCE	(1 << 19)
 #define BTRFS_MOUNT_CHECK_INTEGRITY	(1 << 20)
@@ -1297,6 +1359,8 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
 #define BTRFS_MOUNT_NOLOGREPLAY		(1 << 27)
 #define BTRFS_MOUNT_REF_VERIFY		(1 << 28)
 #define BTRFS_MOUNT_DISCARD_ASYNC	(1 << 29)
+#define BTRFS_MOUNT_IGNOREBADROOTS	(1 << 30)
+#define BTRFS_MOUNT_IGNOREDATACSUMS	(1 << 31)
 
 #define BTRFS_DEFAULT_COMMIT_INTERVAL	(30)
 #define BTRFS_DEFAULT_MAX_INLINE	(2048)
@@ -1329,9 +1393,7 @@ do {									\
  * transaction commit)
  */
 
-#define BTRFS_PENDING_SET_INODE_MAP_CACHE	(0)
+#define BTRFS_PENDING_COMMIT			(0)
-#define BTRFS_PENDING_CLEAR_INODE_MAP_CACHE	(1)
-#define BTRFS_PENDING_COMMIT			(2)
 
 #define btrfs_test_pending(info, opt)	\
 	test_bit(BTRFS_PENDING_##opt, &(info)->pending_changes)
@@ -1404,7 +1466,7 @@ struct btrfs_map_token {
 };
 
 #define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
-				((bytes) >> (fs_info)->sb->s_blocksize_bits)
+				((bytes) >> (fs_info)->sectorsize_bits)
 
 static inline void btrfs_init_map_token(struct btrfs_map_token *token,
 					struct extent_buffer *eb)
@@ -1489,13 +1551,14 @@ static inline void btrfs_set_token_##name(struct btrfs_map_token *token,\
 #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits)		\
 static inline u##bits btrfs_##name(const struct extent_buffer *eb)	\
 {									\
-	const type *p = page_address(eb->pages[0]);			\
+	const type *p = page_address(eb->pages[0]) +			\
+			offset_in_page(eb->start);			\
 	return get_unaligned_le##bits(&p->member);			\
 }									\
 static inline void btrfs_set_##name(const struct extent_buffer *eb,	\
 				    u##bits val)			\
 {									\
-	type *p = page_address(eb->pages[0]);				\
+	type *p = page_address(eb->pages[0]) + offset_in_page(eb->start); \
 	put_unaligned_le##bits(val, &p->member);			\
 }
 
@@ -2085,6 +2148,7 @@ BTRFS_SETGET_FUNCS(disk_root_level, struct btrfs_root_item, level, 8);
 BTRFS_SETGET_STACK_FUNCS(root_generation, struct btrfs_root_item,
 			 generation, 64);
 BTRFS_SETGET_STACK_FUNCS(root_bytenr, struct btrfs_root_item, bytenr, 64);
+BTRFS_SETGET_STACK_FUNCS(root_drop_level, struct btrfs_root_item, drop_level, 8);
 BTRFS_SETGET_STACK_FUNCS(root_level, struct btrfs_root_item, level, 8);
 BTRFS_SETGET_STACK_FUNCS(root_dirid, struct btrfs_root_item, root_dirid, 64);
 BTRFS_SETGET_STACK_FUNCS(root_refs, struct btrfs_root_item, refs, 32);
@@ -2517,7 +2581,17 @@ int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
 				     enum btrfs_inline_ref_type is_data);
 u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset);
 
-u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
+/*
+ * Take the number of bytes to be checksummmed and figure out how many leaves
+ * it would require to store the csums for that many bytes.
+ */
+static inline u64 btrfs_csum_bytes_to_leaves(
+			const struct btrfs_fs_info *fs_info, u64 csum_bytes)
+{
+	const u64 num_csums = csum_bytes >> fs_info->sectorsize_bits;
+
+	return DIV_ROUND_UP_ULL(num_csums, fs_info->csums_per_leaf);
+}
 
 /*
  * Use this if we would be adding new items, as we could split nodes as we cow
@@ -2592,7 +2666,6 @@ int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 			       u64 start, u64 len, int delalloc);
 int btrfs_pin_reserved_extent(struct btrfs_trans_handle *trans, u64 start,
 			      u64 len);
-void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_ref *generic_ref);
@@ -2939,8 +3012,7 @@ struct btrfs_inode_extref *btrfs_find_name_in_ext_backref(
 struct btrfs_dio_private;
 int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		    struct btrfs_root *root, u64 bytenr, u64 len);
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst);
-				   u64 offset, u8 *dst);
 int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     u64 objectid, u64 pos,
@@ -2967,13 +3039,13 @@ int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start,
 					u64 len);
 int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
 				      u64 len);
-void btrfs_inode_safe_disk_i_size_write(struct inode *inode, u64 new_i_size);
+void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size);
 u64 btrfs_file_extent_end(const struct btrfs_path *path);
 
 /* inode.c */
 blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
 				   int mirror_num, unsigned long bio_flags);
-int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u64 phy_offset,
+int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
 			   struct page *page, u64 start, u64 end, int mirror);
 struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 					   u64 start, u64 len);
@@ -2993,11 +3065,11 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
 int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry);
-int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
-			int front);
+			 int front);
 int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
-			       struct inode *inode, u64 new_size,
+			       struct btrfs_inode *inode, u64 new_size,
 			       u32 min_type);
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
@@ -3037,14 +3109,13 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 				    struct page *page, size_t pg_offset,
 				    u64 start, u64 end);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root,
+		       struct btrfs_root *root, struct btrfs_inode *inode);
-			      struct inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root, struct inode *inode);
+				struct btrfs_root *root, struct btrfs_inode *inode);
 int btrfs_orphan_add(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
-int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
+int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size);
 void btrfs_add_delayed_iput(struct inode *inode);
 void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
 int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
@@ -3062,7 +3133,18 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
 void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					  u64 end, int uptodate);
 extern const struct dentry_operations btrfs_dentry_operations;
-ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
+extern const struct iomap_ops btrfs_dio_iomap_ops;
+extern const struct iomap_dio_ops btrfs_dio_ops;
+
+/* Inode locking type flags, by default the exclusive lock is taken */
+#define BTRFS_ILOCK_SHARED	(1U << 0)
+#define BTRFS_ILOCK_TRY 	(1U << 1)
+
+int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags);
+void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags);
+void btrfs_update_inode_bytes(struct btrfs_inode *inode,
+			      const u64 add_bytes,
+			      const u64 del_bytes);
 
 /* ioctl.c */
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
@@ -3092,16 +3174,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
 void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned);
 extern const struct file_operations btrfs_file_operations;
-int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
-			 struct btrfs_root *root, struct btrfs_inode *inode,
-			 struct btrfs_path *path, u64 start, u64 end,
-			 u64 *drop_end, int drop_cache,
-			 int replace_extent,
-			 u32 extent_item_size,
-			 int *key_inserted);
 int btrfs_drop_extents(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root, struct inode *inode, u64 start,
+		       struct btrfs_root *root, struct btrfs_inode *inode,
-		       u64 end, int drop_cache);
+		       struct btrfs_drop_extents_args *args);
 int btrfs_replace_file_extents(struct inode *inode, struct btrfs_path *path,
 			   const u64 start, const u64 end,
 			   struct btrfs_replace_extent_info *extent_info,
@@ -3111,7 +3186,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
-		      struct extent_state **cached);
+		      struct extent_state **cached, bool noreserve);
 int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
 int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos,
 			   size_t *write_bytes);
@@ -3290,6 +3365,39 @@ static inline void assertfail(const char *expr, const char* file, int line) { }
 #define ASSERT(expr)	(void)(expr)
 #endif
 
+/*
+ * Get the correct offset inside the page of extent buffer.
+ *
+ * @eb:		target extent buffer
+ * @start:	offset inside the extent buffer
+ *
+ * Will handle both sectorsize == PAGE_SIZE and sectorsize < PAGE_SIZE cases.
+ */
+static inline size_t get_eb_offset_in_page(const struct extent_buffer *eb,
+					   unsigned long offset)
+{
+	/*
+	 * For sectorsize == PAGE_SIZE case, eb->start will always be aligned
+	 * to PAGE_SIZE, thus adding it won't cause any difference.
+	 *
+	 * For sectorsize < PAGE_SIZE, we must only read the data that belongs
+	 * to the eb, thus we have to take the eb->start into consideration.
+	 */
+	return offset_in_page(offset + eb->start);
+}
+
+static inline unsigned long get_eb_page_index(unsigned long offset)
+{
+	/*
+	 * For sectorsize == PAGE_SIZE case, plain >> PAGE_SHIFT is enough.
+	 *
+	 * For sectorsize < PAGE_SIZE case, we only support 64K PAGE_SIZE,
+	 * and have ensured that all tree blocks are contained in one page,
+	 * thus we always get index == 0.
+	 */
+	return offset >> PAGE_SHIFT;
+}
+
 /*
  * Use that for functions that are conditionally exported for sanity tests but
  * otherwise static
@@ -3599,4 +3707,9 @@ static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
 }
 #endif
 
+static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
+{
+	return fs_info->zoned != 0;
+}
+
 #endif

fs/btrfs/delayed-inode.c

@@ -740,13 +740,6 @@ static int btrfs_batch_insert_items(struct btrfs_root *root,
 		goto out;
 	}
 
-	/*
-	 * we need allocate some memory space, but it might cause the task
-	 * to sleep, so we set all locked nodes in the path to blocking locks
-	 * first.
-	 */
-	btrfs_set_path_blocking(path);
-
 	keys = kmalloc_array(nitems, sizeof(struct btrfs_key), GFP_NOFS);
 	if (!keys) {
 		ret = -ENOMEM;
@@ -1154,7 +1147,6 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr)
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->leave_spinning = 1;
 
 	block_rsv = trans->block_rsv;
 	trans->block_rsv = &fs_info->delayed_block_rsv;
@@ -1219,7 +1211,6 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 		btrfs_release_delayed_node(delayed_node);
 		return -ENOMEM;
 	}
-	path->leave_spinning = 1;
 
 	block_rsv = trans->block_rsv;
 	trans->block_rsv = &delayed_node->root->fs_info->delayed_block_rsv;
@@ -1264,7 +1255,6 @@ int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode)
 		ret = -ENOMEM;
 		goto trans_out;
 	}
-	path->leave_spinning = 1;
 
 	block_rsv = trans->block_rsv;
 	trans->block_rsv = &fs_info->delayed_block_rsv;
@@ -1333,7 +1323,6 @@ static void btrfs_async_run_delayed_root(struct btrfs_work *work)
 		if (!delayed_node)
 			break;
 
-		path->leave_spinning = 1;
 		root = delayed_node->root;
 
 		trans = btrfs_join_transaction(root);
@@ -1826,27 +1815,29 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 }
 
 int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root, struct inode *inode)
+			       struct btrfs_root *root,
+			       struct btrfs_inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 	int ret = 0;
 
-	delayed_node = btrfs_get_or_create_delayed_node(BTRFS_I(inode));
+	delayed_node = btrfs_get_or_create_delayed_node(inode);
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
 
 	mutex_lock(&delayed_node->mutex);
 	if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
-		fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
+		fill_stack_inode_item(trans, &delayed_node->inode_item,
+				      &inode->vfs_inode);
 		goto release_node;
 	}
 
-	ret = btrfs_delayed_inode_reserve_metadata(trans, root, BTRFS_I(inode),
+	ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode,
 						   delayed_node);
 	if (ret)
 		goto release_node;
 
-	fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
+	fill_stack_inode_item(trans, &delayed_node->inode_item, &inode->vfs_inode);
 	set_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags);
 	delayed_node->count++;
 	atomic_inc(&root->fs_info->delayed_root->items);

fs/btrfs/delayed-inode.h

@@ -110,7 +110,8 @@ int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode);
 
 
 int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root, struct inode *inode);
+			       struct btrfs_root *root,
+			       struct btrfs_inode *inode);
 int btrfs_fill_inode(struct inode *inode, u32 *rdev);
 int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode);
 

fs/btrfs/dev-replace.c

@@ -21,6 +21,7 @@
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "sysfs.h"
+#include "zoned.h"
 
 /*
  * Device replace overview
@@ -96,7 +97,7 @@ no_valid_dev_replace_entry_found:
 		 * a replace target, fail the mount.
 		 */
 		if (btrfs_find_device(fs_info->fs_devices,
-				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
 			btrfs_err(fs_info,
 			"found replace target device without a valid replace item");
 			ret = -EUCLEAN;
@@ -159,7 +160,7 @@ no_valid_dev_replace_entry_found:
 		 * replace target, fail the mount.
 		 */
 		if (btrfs_find_device(fs_info->fs_devices,
-				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) {
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
 			btrfs_err(fs_info,
 			"replace devid present without an active replace item");
 			ret = -EUCLEAN;
@@ -171,10 +172,10 @@ no_valid_dev_replace_entry_found:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
 		dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices,
-						src_devid, NULL, NULL, true);
+						src_devid, NULL, NULL);
 		dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices,
 							BTRFS_DEV_REPLACE_DEVID,
-							NULL, NULL, true);
+							NULL, NULL);
 		/*
 		 * allow 'btrfs dev replace_cancel' if src/tgt device is
 		 * missing
@@ -259,6 +260,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return PTR_ERR(bdev);
 	}
 
+	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
+		btrfs_err(fs_info,
+		"dev-replace: zoned type of target device mismatch with filesystem");
+		ret = -EINVAL;
+		goto error;
+	}
+
 	sync_blockdev(bdev);
 
 	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
@@ -313,6 +321,10 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_info->fs_devices;
 
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret)
+		goto error;
+
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	list_add(&device->dev_list, &fs_info->fs_devices->devices);
 	fs_info->fs_devices->num_devices++;

fs/btrfs/dir-item.c

@@ -127,7 +127,6 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->leave_spinning = 1;
 
 	btrfs_cpu_key_to_disk(&disk_key, location);
 

fs/btrfs/discard.c

@@ -355,7 +355,7 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
-		unsigned long delay = discard_ctl->delay;
+		u64 delay = discard_ctl->delay_ms * NSEC_PER_MSEC;
 		u32 kbps_limit = READ_ONCE(discard_ctl->kbps_limit);
 
 		/*
@@ -366,9 +366,9 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 		if (kbps_limit && discard_ctl->prev_discard) {
 			u64 bps_limit = ((u64)kbps_limit) * SZ_1K;
 			u64 bps_delay = div64_u64(discard_ctl->prev_discard *
-						  MSEC_PER_SEC, bps_limit);
+						  NSEC_PER_SEC, bps_limit);
 
-			delay = max(delay, msecs_to_jiffies(bps_delay));
+			delay = max(delay, bps_delay);
 		}
 
 		/*
@@ -378,11 +378,20 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 		if (now < block_group->discard_eligible_time) {
 			u64 bg_timeout = block_group->discard_eligible_time - now;
 
-			delay = max(delay, nsecs_to_jiffies(bg_timeout));
+			delay = max(delay, bg_timeout);
+		}
+
+		if (override && discard_ctl->prev_discard) {
+			u64 elapsed = now - discard_ctl->prev_discard_time;
+
+			if (delay > elapsed)
+				delay -= elapsed;
+			else
+				delay = 0;
 		}
 
 		mod_delayed_work(discard_ctl->discard_workers,
-				 &discard_ctl->work, delay);
+				 &discard_ctl->work, nsecs_to_jiffies(delay));
 	}
 out:
 	spin_unlock(&discard_ctl->lock);
@@ -465,7 +474,12 @@ static void btrfs_discard_workfn(struct work_struct *work)
 		discard_ctl->discard_extent_bytes += trimmed;
 	}
 
+	/*
+	 * Updated without locks as this is inside the workfn and nothing else
+	 * is reading the values
+	 */
 	discard_ctl->prev_discard = trimmed;
+	discard_ctl->prev_discard_time = ktime_get_ns();
 
 	/* Determine next steps for a block_group */
 	if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
@@ -519,7 +533,6 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
 	s64 discardable_bytes;
 	u32 iops_limit;
 	unsigned long delay;
-	unsigned long lower_limit = BTRFS_DISCARD_MIN_DELAY_MSEC;
 
 	discardable_extents = atomic_read(&discard_ctl->discardable_extents);
 	if (!discardable_extents)
@@ -550,12 +563,13 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
 
 	iops_limit = READ_ONCE(discard_ctl->iops_limit);
 	if (iops_limit)
-		lower_limit = max_t(unsigned long, lower_limit,
+		delay = MSEC_PER_SEC / iops_limit;
-				    MSEC_PER_SEC / iops_limit);
+	else
+		delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
 
-	delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
+	delay = clamp(delay, BTRFS_DISCARD_MIN_DELAY_MSEC,
-	delay = clamp(delay, lower_limit, BTRFS_DISCARD_MAX_DELAY_MSEC);
+		      BTRFS_DISCARD_MAX_DELAY_MSEC);
-	discard_ctl->delay = msecs_to_jiffies(delay);
+	discard_ctl->delay_ms = delay;
 
 	spin_unlock(&discard_ctl->lock);
 }
@@ -563,15 +577,14 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
 /**
  * btrfs_discard_update_discardable - propagate discard counters
  * @block_group: block_group of interest
- * @ctl: free_space_ctl of @block_group
  *
  * This propagates deltas of counters up to the discard_ctl.  It maintains a
  * current counter and a previous counter passing the delta up to the global
  * stat.  Then the current counter value becomes the previous counter value.
  */
-void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
+void btrfs_discard_update_discardable(struct btrfs_block_group *block_group)
-				      struct btrfs_free_space_ctl *ctl)
 {
+	struct btrfs_free_space_ctl *ctl;
 	struct btrfs_discard_ctl *discard_ctl;
 	s32 extents_delta;
 	s64 bytes_delta;
@@ -581,8 +594,10 @@ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
 	    !btrfs_is_block_group_data_only(block_group))
 		return;
 
+	ctl = block_group->free_space_ctl;
 	discard_ctl = &block_group->fs_info->discard_ctl;
 
+	lockdep_assert_held(&ctl->tree_lock);
 	extents_delta = ctl->discardable_extents[BTRFS_STAT_CURR] -
 			ctl->discardable_extents[BTRFS_STAT_PREV];
 	if (extents_delta) {
@@ -684,10 +699,11 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 		INIT_LIST_HEAD(&discard_ctl->discard_list[i]);
 
 	discard_ctl->prev_discard = 0;
+	discard_ctl->prev_discard_time = 0;
 	atomic_set(&discard_ctl->discardable_extents, 0);
 	atomic64_set(&discard_ctl->discardable_bytes, 0);
 	discard_ctl->max_discard_size = BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE;
-	discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
+	discard_ctl->delay_ms = BTRFS_DISCARD_MAX_DELAY_MSEC;
 	discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
 	discard_ctl->kbps_limit = 0;
 	discard_ctl->discard_extent_bytes = 0;

fs/btrfs/discard.h

@@ -28,8 +28,7 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
 
 /* Update operations */
 void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);
-void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
+void btrfs_discard_update_discardable(struct btrfs_block_group *block_group);
-				      struct btrfs_free_space_ctl *ctl);
 
 /* Setup/cleanup operations */
 void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info);

fs/btrfs/disk-io.h

@@ -43,13 +43,15 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info);
 int btrfs_verify_level_key(struct extent_buffer *eb, int level,
 			   struct btrfs_key *first_key, u64 parent_transid);
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
-				      u64 parent_transid, int level,
+				      u64 owner_root, u64 parent_transid,
-				      struct btrfs_key *first_key);
+				      int level, struct btrfs_key *first_key);
-void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr);
 struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
-						u64 bytenr);
+						u64 bytenr, u64 owner_root,
+						int level);
 void btrfs_clean_tree_block(struct extent_buffer *buf);
+void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info);
+int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info);
 int __cold open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
@@ -79,7 +81,7 @@ void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info);
 void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info);
 void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 				 struct btrfs_root *root);
-int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset,
+int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio,
 				   struct page *page, u64 start, u64 end,
 				   int mirror);
 blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
@@ -112,10 +114,10 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid, int level,
 		      struct btrfs_key *first_key);
 blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata);
-blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
-			int mirror_num, unsigned long bio_flags,
+				 int mirror_num, unsigned long bio_flags,
-			u64 bio_offset, void *private_data,
+				 u64 dio_file_offset,
-			extent_submit_bio_start_t *submit_bio_start);
+				 extent_submit_bio_start_t *submit_bio_start);
 blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
 			  int mirror_num);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
@@ -131,16 +133,15 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 int btree_lock_page_hook(struct page *page, void *data,
 				void (*flush_fn)(void *));
 int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
+int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_init_lockdep(void);
 void btrfs_set_buffer_lockdep_class(u64 objectid,
 			            struct extent_buffer *eb, int level);
 #else
-static inline void btrfs_init_lockdep(void)
-{ }
 static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
 					struct extent_buffer *eb, int level)
 {

fs/btrfs/export.c

@@ -222,7 +222,6 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->leave_spinning = 1;
 
 	if (ino == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = BTRFS_I(inode)->root->root_key.objectid;

fs/btrfs/extent-io-tree.h

@@ -21,10 +21,24 @@ struct io_failure_record;
 #define EXTENT_NORESERVE	(1U << 11)
 #define EXTENT_QGROUP_RESERVED	(1U << 12)
 #define EXTENT_CLEAR_DATA_RESV	(1U << 13)
+/*
+ * Must be cleared only during ordered extent completion or on error paths if we
+ * did not manage to submit bios and create the ordered extents for the range.
+ * Should not be cleared during page release and page invalidation (if there is
+ * an ordered extent in flight), that is left for the ordered extent completion.
+ */
 #define EXTENT_DELALLOC_NEW	(1U << 14)
+/*
+ * When an ordered extent successfully completes for a region marked as a new
+ * delalloc range, use this flag when clearing a new delalloc range to indicate
+ * that the VFS' inode number of bytes should be incremented and the inode's new
+ * delalloc bytes decremented, in an atomic way to prevent races with stat(2).
+ */
+#define EXTENT_ADD_INODE_BYTES  (1U << 15)
 #define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
 				 EXTENT_CLEAR_DATA_RESV)
-#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING)
+#define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING | \
+				 EXTENT_ADD_INODE_BYTES)
 
 /*
  * Redefined bits above which are used only in the device allocation tree,
@@ -73,7 +87,7 @@ struct extent_state {
 	/* ADD NEW ELEMENTS AFTER THIS */
 	wait_queue_head_t wq;
 	refcount_t refs;
-	unsigned state;
+	u32 state;
 
 	struct io_failure_record *failrec;
 
@@ -105,19 +119,18 @@ void __cold extent_io_exit(void);
 
 u64 count_range_bits(struct extent_io_tree *tree,
 		     u64 *start, u64 search_end,
-		     u64 max_bytes, unsigned bits, int contig);
+		     u64 max_bytes, u32 bits, int contig);
 
 void free_extent_state(struct extent_state *state);
 int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, int filled,
+		   u32 bits, int filled, struct extent_state *cached_state);
-		   struct extent_state *cached_state);
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		unsigned bits, struct extent_changeset *changeset);
+			     u32 bits, struct extent_changeset *changeset);
 int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
+		     u32 bits, int wake, int delete,
 		     struct extent_state **cached);
 int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, int wake, int delete,
+		     u32 bits, int wake, int delete,
 		     struct extent_state **cached, gfp_t mask,
 		     struct extent_changeset *changeset);
 
@@ -141,7 +154,7 @@ static inline int unlock_extent_cached_atomic(struct extent_io_tree *tree,
 }
 
 static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
+				    u64 end, u32 bits)
 {
 	int wake = 0;
 
@@ -152,17 +165,19 @@ static inline int clear_extent_bits(struct extent_io_tree *tree, u64 start,
 }
 
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits, struct extent_changeset *changeset);
+			   u32 bits, struct extent_changeset *changeset);
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   unsigned bits, u64 *failed_start,
+		   u32 bits, unsigned exclusive_bits, u64 *failed_start,
-		   struct extent_state **cached_state, gfp_t mask);
+		   struct extent_state **cached_state, gfp_t mask,
+		   struct extent_changeset *changeset);
 int set_extent_bits_nowait(struct extent_io_tree *tree, u64 start, u64 end,
-			   unsigned bits);
+			   u32 bits);
 
 static inline int set_extent_bits(struct extent_io_tree *tree, u64 start,
-		u64 end, unsigned bits)
+		u64 end, u32 bits)
 {
-	return set_extent_bit(tree, start, end, bits, NULL, NULL, GFP_NOFS);
+	return set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
+			      NULL);
 }
 
 static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
@@ -175,8 +190,8 @@ static inline int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
 static inline int set_extent_dirty(struct extent_io_tree *tree, u64 start,
 		u64 end, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
+	return set_extent_bit(tree, start, end, EXTENT_DIRTY, 0, NULL, NULL,
-			      NULL, mask);
+			      mask, NULL);
 }
 
 static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
@@ -188,16 +203,16 @@ static inline int clear_extent_dirty(struct extent_io_tree *tree, u64 start,
 }
 
 int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		       unsigned bits, unsigned clear_bits,
+		       u32 bits, u32 clear_bits,
 		       struct extent_state **cached_state);
 
 static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
-				      u64 end, unsigned int extra_bits,
+				      u64 end, u32 extra_bits,
 				      struct extent_state **cached_state)
 {
 	return set_extent_bit(tree, start, end,
 			      EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
-			      NULL, cached_state, GFP_NOFS);
+			      0, NULL, cached_state, GFP_NOFS, NULL);
 }
 
 static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
@@ -205,30 +220,30 @@ static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
 {
 	return set_extent_bit(tree, start, end,
 			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, GFP_NOFS);
+			      0, NULL, cached_state, GFP_NOFS, NULL);
 }
 
 static inline int set_extent_new(struct extent_io_tree *tree, u64 start,
 		u64 end)
 {
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL, NULL,
+	return set_extent_bit(tree, start, end, EXTENT_NEW, 0, NULL, NULL,
-			GFP_NOFS);
+			      GFP_NOFS, NULL);
 }
 
 static inline int set_extent_uptodate(struct extent_io_tree *tree, u64 start,
 		u64 end, struct extent_state **cached_state, gfp_t mask)
 {
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
+	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, NULL,
-			      cached_state, mask);
+			      cached_state, mask, NULL);
 }
 
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
-			  u64 *start_ret, u64 *end_ret, unsigned bits,
+			  u64 *start_ret, u64 *end_ret, u32 bits,
 			  struct extent_state **cached_state);
 void find_first_clear_extent_bit(struct extent_io_tree *tree, u64 start,
-				 u64 *start_ret, u64 *end_ret, unsigned bits);
+				 u64 *start_ret, u64 *end_ret, u32 bits);
 int find_contiguous_extent_bit(struct extent_io_tree *tree, u64 start,
-			       u64 *start_ret, u64 *end_ret, unsigned bits);
+			       u64 *start_ret, u64 *end_ret, u32 bits);
 int extent_invalidatepage(struct extent_io_tree *tree,
 			  struct page *page, unsigned long offset);
 bool btrfs_find_delalloc_range(struct extent_io_tree *tree, u64 *start,

fs/btrfs/extent-tree.c

@@ -1465,7 +1465,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
 	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
 					   parent, root_objectid, owner,
@@ -1489,7 +1488,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	path->leave_spinning = 1;
 	/* now insert the actual backref */
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		BUG_ON(refs_to_add != 1);
@@ -1605,7 +1603,6 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
 	}
 
 again:
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 1);
 	if (ret < 0) {
 		err = ret;
@@ -2132,25 +2129,6 @@ static u64 find_middle(struct rb_root *root)
 }
 #endif
 
-/*
- * Takes the number of bytes to be csumm'ed and figures out how many leaves it
- * would require to store the csums for that many bytes.
- */
-u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes)
-{
-	u64 csum_size;
-	u64 num_csums_per_leaf;
-	u64 num_csums;
-
-	csum_size = BTRFS_MAX_ITEM_SIZE(fs_info);
-	num_csums_per_leaf = div64_u64(csum_size,
-			(u64)btrfs_super_csum_size(fs_info->super_copy));
-	num_csums = div64_u64(csum_bytes, fs_info->sectorsize);
-	num_csums += num_csums_per_leaf - 1;
-	num_csums = div64_u64(num_csums, num_csums_per_leaf);
-	return num_csums;
-}
-
 /*
  * this starts processing the delayed reference count updates and
  * extent insertions we have queued up so far.  count can be
@@ -2663,6 +2641,11 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 		BUG_ON(!btrfs_block_group_done(block_group));
 		ret = btrfs_remove_free_space(block_group, start, num_bytes);
 	} else {
+		/*
+		 * We must wait for v1 caching to finish, otherwise we may not
+		 * remove our space.
+		 */
+		btrfs_wait_space_cache_v1_finished(block_group, caching_ctl);
 		mutex_lock(&caching_ctl->mutex);
 
 		if (start >= caching_ctl->progress) {
@@ -2730,31 +2713,6 @@ btrfs_inc_block_group_reservations(struct btrfs_block_group *bg)
 	atomic_inc(&bg->reservations);
 }
 
-void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_caching_control *next;
-	struct btrfs_caching_control *caching_ctl;
-	struct btrfs_block_group *cache;
-
-	down_write(&fs_info->commit_root_sem);
-
-	list_for_each_entry_safe(caching_ctl, next,
-				 &fs_info->caching_block_groups, list) {
-		cache = caching_ctl->block_group;
-		if (btrfs_block_group_done(cache)) {
-			cache->last_byte_to_unpin = (u64)-1;
-			list_del_init(&caching_ctl->list);
-			btrfs_put_caching_control(caching_ctl);
-		} else {
-			cache->last_byte_to_unpin = caching_ctl->progress;
-		}
-	}
-
-	up_write(&fs_info->commit_root_sem);
-
-	btrfs_update_global_block_rsv(fs_info);
-}
-
 /*
  * Returns the free cluster for the given space info and sets empty_cluster to
  * what it should be based on the mount options.
@@ -2816,11 +2774,13 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 		len = cache->start + cache->length - start;
 		len = min(len, end + 1 - start);
 
-		if (start < cache->last_byte_to_unpin) {
+		down_read(&fs_info->commit_root_sem);
-			len = min(len, cache->last_byte_to_unpin - start);
+		if (start < cache->last_byte_to_unpin && return_free_space) {
-			if (return_free_space)
+			u64 add_len = min(len, cache->last_byte_to_unpin - start);
-				btrfs_add_free_space(cache, start, len);
+
+			btrfs_add_free_space(cache, start, add_len);
 		}
+		up_read(&fs_info->commit_root_sem);
 
 		start += len;
 		total_unpinned += len;
@@ -3040,8 +3000,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
-
 	is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
 
 	if (!is_data && refs_to_drop != 1) {
@@ -3106,7 +3064,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				goto out;
 			}
 			btrfs_release_path(path);
-			path->leave_spinning = 1;
 
 			/* Slow path to locate EXTENT/METADATA_ITEM */
 			key.objectid = bytenr;
@@ -4448,7 +4405,6 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
 				      ins, size);
 	if (ret) {
@@ -4533,7 +4489,6 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
 				      &extent_key, size);
 	if (ret) {
@@ -4662,7 +4617,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
 
-	buf = btrfs_find_create_tree_block(fs_info, bytenr);
+	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level);
 	if (IS_ERR(buf))
 		return buf;
 
@@ -4679,12 +4634,16 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		return ERR_PTR(-EUCLEAN);
 	}
 
+	/*
+	 * This needs to stay, because we could allocate a freed block from an
+	 * old tree into a new tree, so we need to make sure this new block is
+	 * set to the appropriate level and owner.
+	 */
 	btrfs_set_buffer_lockdep_class(owner, buf, level);
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
-	btrfs_set_lock_blocking_write(buf);
 	set_extent_buffer_uptodate(buf);
 
 	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
@@ -4905,7 +4864,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
 				continue;
 		}
 reada:
-		readahead_tree_block(fs_info, bytenr);
+		btrfs_readahead_node_child(eb, slot);
 		nread++;
 	}
 	wc->reada_slot = slot;
@@ -5064,16 +5023,13 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 
 	next = find_extent_buffer(fs_info, bytenr);
 	if (!next) {
-		next = btrfs_find_create_tree_block(fs_info, bytenr);
+		next = btrfs_find_create_tree_block(fs_info, bytenr,
+				root->root_key.objectid, level - 1);
 		if (IS_ERR(next))
 			return PTR_ERR(next);
-
-		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
-					       level - 1);
 		reada = 1;
 	}
 	btrfs_tree_lock(next);
-	btrfs_set_lock_blocking_write(next);
 
 	ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
 				       &wc->refs[level - 1],
@@ -5124,8 +5080,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	if (!next) {
 		if (reada && level == 1)
 			reada_walk_down(trans, root, wc, path);
-		next = read_tree_block(fs_info, bytenr, generation, level - 1,
+		next = read_tree_block(fs_info, bytenr, root->root_key.objectid,
-				       &first_key);
+				       generation, level - 1, &first_key);
 		if (IS_ERR(next)) {
 			return PTR_ERR(next);
 		} else if (!extent_buffer_uptodate(next)) {
@@ -5133,7 +5089,6 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 			return -EIO;
 		}
 		btrfs_tree_lock(next);
-		btrfs_set_lock_blocking_write(next);
 	}
 
 	level--;
@@ -5145,7 +5100,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	}
 	path->nodes[level] = next;
 	path->slots[level] = 0;
-	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
+	path->locks[level] = BTRFS_WRITE_LOCK;
 	wc->level = level;
 	if (wc->level == 1)
 		wc->reada_slot = 0;
@@ -5273,8 +5228,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 		if (!path->locks[level]) {
 			BUG_ON(level == 0);
 			btrfs_tree_lock(eb);
-			btrfs_set_lock_blocking_write(eb);
+			path->locks[level] = BTRFS_WRITE_LOCK;
-			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						       eb->start, level, 1,
@@ -5317,8 +5271,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 		if (!path->locks[level] &&
 		    btrfs_header_generation(eb) == trans->transid) {
 			btrfs_tree_lock(eb);
-			btrfs_set_lock_blocking_write(eb);
+			path->locks[level] = BTRFS_WRITE_LOCK;
-			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 		}
 		btrfs_clean_tree_block(eb);
 	}
@@ -5486,9 +5439,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
 		level = btrfs_header_level(root->node);
 		path->nodes[level] = btrfs_lock_root_node(root);
-		btrfs_set_lock_blocking_write(path->nodes[level]);
 		path->slots[level] = 0;
-		path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
+		path->locks[level] = BTRFS_WRITE_LOCK;
 		memset(&wc->update_progress, 0,
 		       sizeof(wc->update_progress));
 	} else {
@@ -5496,7 +5448,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		memcpy(&wc->update_progress, &key,
 		       sizeof(wc->update_progress));
 
-		level = root_item->drop_level;
+		level = btrfs_root_drop_level(root_item);
 		BUG_ON(level == 0);
 		path->lowest_level = level;
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -5516,8 +5468,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		level = btrfs_header_level(root->node);
 		while (1) {
 			btrfs_tree_lock(path->nodes[level]);
-			btrfs_set_lock_blocking_write(path->nodes[level]);
+			path->locks[level] = BTRFS_WRITE_LOCK;
-			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 
 			ret = btrfs_lookup_extent_info(trans, fs_info,
 						path->nodes[level]->start,
@@ -5529,7 +5480,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 			}
 			BUG_ON(wc->refs[level] == 0);
 
-			if (level == root_item->drop_level)
+			if (level == btrfs_root_drop_level(root_item))
 				break;
 
 			btrfs_tree_unlock(path->nodes[level]);
@@ -5574,7 +5525,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 		}
 		btrfs_cpu_key_to_disk(&root_item->drop_progress,
 				      &wc->drop_progress);
-		root_item->drop_level = wc->drop_level;
+		btrfs_set_root_drop_level(root_item, wc->drop_level);
 
 		BUG_ON(wc->level == 0);
 		if (btrfs_should_end_transaction(trans) ||
@@ -5704,7 +5655,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	level = btrfs_header_level(node);
 	path->nodes[level] = node;
 	path->slots[level] = 0;
-	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
+	path->locks[level] = BTRFS_WRITE_LOCK;
 
 	wc->refs[parent_level] = 1;
 	wc->flags[parent_level] = BTRFS_BLOCK_FLAG_FULL_BACKREF;

fs/btrfs/extent_io.h

@@ -6,6 +6,7 @@
 #include <linux/rbtree.h>
 #include <linux/refcount.h>
 #include <linux/fiemap.h>
+#include <linux/btrfs_tree.h>
 #include "ulist.h"
 
 /*
@@ -71,11 +72,10 @@ typedef blk_status_t (submit_bio_hook_t)(struct inode *inode, struct bio *bio,
 					 int mirror_num,
 					 unsigned long bio_flags);
 
-typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
+typedef blk_status_t (extent_submit_bio_start_t)(struct inode *inode,
-		struct bio *bio, u64 bio_offset);
+		struct bio *bio, u64 dio_file_offset);
 
-#define INLINE_EXTENT_BUFFER_PAGES 16
+#define INLINE_EXTENT_BUFFER_PAGES     (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE)
-#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
 struct extent_buffer {
 	u64 start;
 	unsigned long len;
@@ -87,31 +87,13 @@ struct extent_buffer {
 	int read_mirror;
 	struct rcu_head rcu_head;
 	pid_t lock_owner;
-
-	int blocking_writers;
-	atomic_t blocking_readers;
-	bool lock_recursed;
 	/* >= 0 if eb belongs to a log tree, -1 otherwise */
-	short log_index;
+	s8 log_index;
 
-	/* protects write locks */
+	struct rw_semaphore lock;
-	rwlock_t lock;
 
-	/* readers use lock_wq while they wait for the write
-	 * lock holders to unlock
-	 */
-	wait_queue_head_t write_lock_wq;
-
-	/* writers use read_lock_wq while they wait for readers
-	 * to unlock
-	 */
-	wait_queue_head_t read_lock_wq;
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
 #ifdef CONFIG_BTRFS_DEBUG
-	int spinning_writers;
-	atomic_t spinning_readers;
-	atomic_t read_locks;
-	int write_locks;
 	struct list_head leak_list;
 #endif
 };
@@ -199,7 +181,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 void set_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
-					  u64 start);
+					  u64 start, u64 owner_root, int level);
 struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len);
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
@@ -215,11 +197,20 @@ void free_extent_buffer_stale(struct extent_buffer *eb);
 int read_extent_buffer_pages(struct extent_buffer *eb, int wait,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
+void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
+				u64 bytenr, u64 owner_root, u64 gen, int level);
+void btrfs_readahead_node_child(struct extent_buffer *node, int slot);
 
 static inline int num_extent_pages(const struct extent_buffer *eb)
 {
-	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
+	/*
-	       (eb->start >> PAGE_SHIFT);
+	 * For sectorsize == PAGE_SIZE case, since nodesize is always aligned to
+	 * sectorsize, it's just eb->len >> PAGE_SHIFT.
+	 *
+	 * For sectorsize < PAGE_SIZE case, we could have nodesize < PAGE_SIZE,
+	 * thus have to ensure we get at least one page.
+	 */
+	return (eb->len >> PAGE_SHIFT) ?: 1;
 }
 
 static inline int extent_buffer_uptodate(const struct extent_buffer *eb)
@@ -270,8 +261,7 @@ void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
-				  unsigned bits_to_clear,
+				  u32 bits_to_clear, unsigned long page_ops);
-				  unsigned long page_ops);
 struct bio *btrfs_bio_alloc(u64 first_byte);
 struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs);
 struct bio *btrfs_bio_clone(struct bio *bio);
@@ -307,7 +297,7 @@ struct io_failure_record {
 
 
 blk_status_t btrfs_submit_read_repair(struct inode *inode,
-				      struct bio *failed_bio, u64 phy_offset,
+				      struct bio *failed_bio, u32 bio_offset,
 				      struct page *page, unsigned int pgoff,
 				      u64 start, u64 end, int failed_mirror,
 				      submit_bio_hook_t *submit_bio_hook);

fs/btrfs/file-item.c

@@ -38,27 +38,27 @@
  * Finally new_i_size should only be set in the case of truncate where we're not
  * ready to use i_size_read() as the limiter yet.
  */
-void btrfs_inode_safe_disk_i_size_write(struct inode *inode, u64 new_i_size)
+void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size)
 {
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 start, end, i_size;
 	int ret;
 
-	i_size = new_i_size ?: i_size_read(inode);
+	i_size = new_i_size ?: i_size_read(&inode->vfs_inode);
 	if (btrfs_fs_incompat(fs_info, NO_HOLES)) {
-		BTRFS_I(inode)->disk_i_size = i_size;
+		inode->disk_i_size = i_size;
 		return;
 	}
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
-	ret = find_contiguous_extent_bit(&BTRFS_I(inode)->file_extent_tree, 0,
+	ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start,
-					 &start, &end, EXTENT_DIRTY);
+					 &end, EXTENT_DIRTY);
 	if (!ret && start == 0)
 		i_size = min(i_size, end + 1);
 	else
 		i_size = 0;
-	BTRFS_I(inode)->disk_i_size = i_size;
+	inode->disk_i_size = i_size;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_unlock(&inode->lock);
 }
 
 /**
@@ -142,7 +142,6 @@ int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 	file_key.offset = pos;
 	file_key.type = BTRFS_EXTENT_DATA_KEY;
 
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &file_key,
 				      sizeof(*item));
 	if (ret < 0)
@@ -181,7 +180,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 	struct btrfs_csum_item *item;
 	struct extent_buffer *leaf;
 	u64 csum_offset = 0;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
 	int csums_in_item;
 
 	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
@@ -201,7 +200,7 @@ btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 			goto fail;
 
 		csum_offset = (bytenr - found_key.offset) >>
-				fs_info->sb->s_blocksize_bits;
+				fs_info->sectorsize_bits;
 		csums_in_item = btrfs_item_size_nr(leaf, path->slots[0]);
 		csums_in_item /= csum_size;
 
@@ -239,12 +238,117 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * Find checksums for logical bytenr range [disk_bytenr, disk_bytenr + len) and
+ * estore the result to @dst.
+ *
+ * Return >0 for the number of sectors we found.
+ * Return 0 for the range [disk_bytenr, disk_bytenr + sectorsize) has no csum
+ * for it. Caller may want to try next sector until one range is hit.
+ * Return <0 for fatal error.
+ */
+static int search_csum_tree(struct btrfs_fs_info *fs_info,
+			    struct btrfs_path *path, u64 disk_bytenr,
+			    u64 len, u8 *dst)
+{
+	struct btrfs_csum_item *item = NULL;
+	struct btrfs_key key;
+	const u32 sectorsize = fs_info->sectorsize;
+	const u32 csum_size = fs_info->csum_size;
+	u32 itemsize;
+	int ret;
+	u64 csum_start;
+	u64 csum_len;
+
+	ASSERT(IS_ALIGNED(disk_bytenr, sectorsize) &&
+	       IS_ALIGNED(len, sectorsize));
+
+	/* Check if the current csum item covers disk_bytenr */
+	if (path->nodes[0]) {
+		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				      struct btrfs_csum_item);
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		itemsize = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
+
+		csum_start = key.offset;
+		csum_len = (itemsize / csum_size) * sectorsize;
+
+		if (in_range(disk_bytenr, csum_start, csum_len))
+			goto found;
+	}
+
+	/* Current item doesn't contain the desired range, search again */
+	btrfs_release_path(path);
+	item = btrfs_lookup_csum(NULL, fs_info->csum_root, path, disk_bytenr, 0);
+	if (IS_ERR(item)) {
+		ret = PTR_ERR(item);
+		goto out;
+	}
+	btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+	itemsize = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
+
+	csum_start = key.offset;
+	csum_len = (itemsize / csum_size) * sectorsize;
+	ASSERT(in_range(disk_bytenr, csum_start, csum_len));
+
+found:
+	ret = (min(csum_start + csum_len, disk_bytenr + len) -
+		   disk_bytenr) >> fs_info->sectorsize_bits;
+	read_extent_buffer(path->nodes[0], dst, (unsigned long)item,
+			ret * csum_size);
+out:
+	if (ret == -ENOENT)
+		ret = 0;
+	return ret;
+}
+
+/*
+ * Locate the file_offset of @cur_disk_bytenr of a @bio.
+ *
+ * Bio of btrfs represents read range of
+ * [bi_sector << 9, bi_sector << 9 + bi_size).
+ * Knowing this, we can iterate through each bvec to locate the page belong to
+ * @cur_disk_bytenr and get the file offset.
+ *
+ * @inode is used to determine if the bvec page really belongs to @inode.
+ *
+ * Return 0 if we can't find the file offset
+ * Return >0 if we find the file offset and restore it to @file_offset_ret
+ */
+static int search_file_offset_in_bio(struct bio *bio, struct inode *inode,
+				     u64 disk_bytenr, u64 *file_offset_ret)
+{
+	struct bvec_iter iter;
+	struct bio_vec bvec;
+	u64 cur = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	int ret = 0;
+
+	bio_for_each_segment(bvec, bio, iter) {
+		struct page *page = bvec.bv_page;
+
+		if (cur > disk_bytenr)
+			break;
+		if (cur + bvec.bv_len <= disk_bytenr) {
+			cur += bvec.bv_len;
+			continue;
+		}
+		ASSERT(in_range(disk_bytenr, cur, bvec.bv_len));
+		if (page->mapping && page->mapping->host &&
+		    page->mapping->host == inode) {
+			ret = 1;
+			*file_offset_ret = page_offset(page) + bvec.bv_offset +
+					   disk_bytenr - cur;
+			break;
+		}
+	}
+	return ret;
+}
+
 /**
- * btrfs_lookup_bio_sums - Look up checksums for a bio.
+ * Lookup the checksum for the read bio in csum tree.
+ *
  * @inode: inode that the bio is for.
  * @bio: bio to look up.
- * @offset: Unless (u64)-1, look up checksums for this offset in the file.
- *          If (u64)-1, use the page offsets from the bio instead.
  * @dst: Buffer of size nblocks * btrfs_super_csum_size() used to return
  *       checksum (nblocks = bio->bi_iter.bi_size / fs_info->sectorsize). If
  *       NULL, the checksum buffer is allocated and returned in
@@ -252,31 +356,40 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
  *
  * Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise.
  */
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u8 *dst)
-				   u64 offset, u8 *dst)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-	struct btrfs_csum_item *item = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_path *path;
-	const bool page_offsets = (offset == (u64)-1);
+	const u32 sectorsize = fs_info->sectorsize;
+	const u32 csum_size = fs_info->csum_size;
+	u32 orig_len = bio->bi_iter.bi_size;
+	u64 orig_disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 cur_disk_bytenr;
 	u8 *csum;
-	u64 item_start_offset = 0;
+	const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits;
-	u64 item_last_offset = 0;
-	u64 disk_bytenr;
-	u64 page_bytes_left;
-	u32 diff;
-	int nblocks;
 	int count = 0;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
+	if (!fs_info->csum_root || (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM))
+		return BLK_STS_OK;
+
+	/*
+	 * This function is only called for read bio.
+	 *
+	 * This means two things:
+	 * - All our csums should only be in csum tree
+	 *   No ordered extents csums, as ordered extents are only for write
+	 *   path.
+	 * - No need to bother any other info from bvec
+	 *   Since we're looking up csums, the only important info is the
+	 *   disk_bytenr and the length, which can be extracted from bi_iter
+	 *   directly.
+	 */
+	ASSERT(bio_op(bio) == REQ_OP_READ);
 	path = btrfs_alloc_path();
 	if (!path)
 		return BLK_STS_RESOURCE;
 
-	nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
 	if (!dst) {
 		struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
 
@@ -295,7 +408,11 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 		csum = dst;
 	}
 
-	if (bio->bi_iter.bi_size > PAGE_SIZE * 8)
+	/*
+	 * If requested number of sectors is larger than one leaf can contain,
+	 * kick the readahead for csum tree.
+	 */
+	if (nblocks > fs_info->csums_per_leaf)
 		path->reada = READA_FORWARD;
 
 	/*
@@ -309,85 +426,62 @@ blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 		path->skip_locking = 1;
 	}
 
-	disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
+	for (cur_disk_bytenr = orig_disk_bytenr;
+	     cur_disk_bytenr < orig_disk_bytenr + orig_len;
+	     cur_disk_bytenr += (count * sectorsize)) {
+		u64 search_len = orig_disk_bytenr + orig_len - cur_disk_bytenr;
+		unsigned int sector_offset;
+		u8 *csum_dst;
 
-	bio_for_each_segment(bvec, bio, iter) {
-		page_bytes_left = bvec.bv_len;
-		if (count)
-			goto next;
-
-		if (page_offsets)
-			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
-		count = btrfs_find_ordered_sum(BTRFS_I(inode), offset,
-					       disk_bytenr, csum, nblocks);
-		if (count)
-			goto found;
-
-		if (!item || disk_bytenr < item_start_offset ||
-		    disk_bytenr >= item_last_offset) {
-			struct btrfs_key found_key;
-			u32 item_size;
-
-			if (item)
-				btrfs_release_path(path);
-			item = btrfs_lookup_csum(NULL, fs_info->csum_root,
-						 path, disk_bytenr, 0);
-			if (IS_ERR(item)) {
-				count = 1;
-				memset(csum, 0, csum_size);
-				if (BTRFS_I(inode)->root->root_key.objectid ==
-				    BTRFS_DATA_RELOC_TREE_OBJECTID) {
-					set_extent_bits(io_tree, offset,
-						offset + fs_info->sectorsize - 1,
-						EXTENT_NODATASUM);
-				} else {
-					btrfs_info_rl(fs_info,
-						   "no csum found for inode %llu start %llu",
-					       btrfs_ino(BTRFS_I(inode)), offset);
-				}
-				item = NULL;
-				btrfs_release_path(path);
-				goto found;
-			}
-			btrfs_item_key_to_cpu(path->nodes[0], &found_key,
-					      path->slots[0]);
-
-			item_start_offset = found_key.offset;
-			item_size = btrfs_item_size_nr(path->nodes[0],
-						       path->slots[0]);
-			item_last_offset = item_start_offset +
-				(item_size / csum_size) *
-				fs_info->sectorsize;
-			item = btrfs_item_ptr(path->nodes[0], path->slots[0],
-					      struct btrfs_csum_item);
-		}
 		/*
-		 * this byte range must be able to fit inside
+		 * Although both cur_disk_bytenr and orig_disk_bytenr is u64,
-		 * a single leaf so it will also fit inside a u32
+		 * we're calculating the offset to the bio start.
+		 *
+		 * Bio size is limited to UINT_MAX, thus unsigned int is large
+		 * enough to contain the raw result, not to mention the right
+		 * shifted result.
 		 */
-		diff = disk_bytenr - item_start_offset;
+		ASSERT(cur_disk_bytenr - orig_disk_bytenr < UINT_MAX);
-		diff = diff / fs_info->sectorsize;
+		sector_offset = (cur_disk_bytenr - orig_disk_bytenr) >>
-		diff = diff * csum_size;
+				fs_info->sectorsize_bits;
-		count = min_t(int, nblocks, (item_last_offset - disk_bytenr) >>
+		csum_dst = csum + sector_offset * csum_size;
-					    inode->i_sb->s_blocksize_bits);
+
-		read_extent_buffer(path->nodes[0], csum,
+		count = search_csum_tree(fs_info, path, cur_disk_bytenr,
-				   ((unsigned long)item) + diff,
+					 search_len, csum_dst);
-				   csum_size * count);
+		if (count <= 0) {
-found:
+			/*
-		csum += count * csum_size;
+			 * Either we hit a critical error or we didn't find
-		nblocks -= count;
+			 * the csum.
-next:
+			 * Either way, we put zero into the csums dst, and skip
-		while (count > 0) {
+			 * to the next sector.
-			count--;
+			 */
-			disk_bytenr += fs_info->sectorsize;
+			memset(csum_dst, 0, csum_size);
-			offset += fs_info->sectorsize;
+			count = 1;
-			page_bytes_left -= fs_info->sectorsize;
+
-			if (!page_bytes_left)
+			/*
-				break; /* move to next bio */
+			 * For data reloc inode, we need to mark the range
+			 * NODATASUM so that balance won't report false csum
+			 * error.
+			 */
+			if (BTRFS_I(inode)->root->root_key.objectid ==
+			    BTRFS_DATA_RELOC_TREE_OBJECTID) {
+				u64 file_offset;
+				int ret;
+
+				ret = search_file_offset_in_bio(bio, inode,
+						cur_disk_bytenr, &file_offset);
+				if (ret)
+					set_extent_bits(io_tree, file_offset,
+						file_offset + sectorsize - 1,
+						EXTENT_NODATASUM);
+			} else {
+				btrfs_warn_rl(fs_info,
+			"csum hole found for disk bytenr range [%llu, %llu)",
+				cur_disk_bytenr, cur_disk_bytenr + sectorsize);
+			}
 		}
 	}
 
-	WARN_ON_ONCE(count);
 	btrfs_free_path(path);
 	return BLK_STS_OK;
 }
@@ -406,7 +500,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	int ret;
 	size_t size;
 	u64 csum_end;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
 
 	ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
 	       IS_ALIGNED(end + 1, fs_info->sectorsize));
@@ -433,8 +527,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
 		if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID &&
 		    key.type == BTRFS_EXTENT_CSUM_KEY) {
-			offset = (start - key.offset) >>
+			offset = (start - key.offset) >> fs_info->sectorsize_bits;
-				 fs_info->sb->s_blocksize_bits;
 			if (offset * csum_size <
 			    btrfs_item_size_nr(leaf, path->slots[0] - 1))
 				path->slots[0]--;
@@ -484,10 +577,9 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			sums->bytenr = start;
 			sums->len = (int)size;
 
-			offset = (start - key.offset) >>
+			offset = (start - key.offset) >> fs_info->sectorsize_bits;
-				fs_info->sb->s_blocksize_bits;
 			offset *= csum_size;
-			size >>= fs_info->sb->s_blocksize_bits;
+			size >>= fs_info->sectorsize_bits;
 
 			read_extent_buffer(path->nodes[0],
 					   sums->sums,
@@ -539,7 +631,6 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 	int i;
 	u64 offset;
 	unsigned nofs_flag;
-	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
 	nofs_flag = memalloc_nofs_save();
 	sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
@@ -557,7 +648,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 	else
 		offset = 0; /* shut up gcc */
 
-	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
+	sums->bytenr = bio->bi_iter.bi_sector << 9;
 	index = 0;
 
 	shash->tfm = fs_info->csum_shash;
@@ -596,7 +687,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 				ordered = btrfs_lookup_ordered_extent(inode,
 								offset);
 				ASSERT(ordered); /* Logic error */
-				sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9)
+				sums->bytenr = (bio->bi_iter.bi_sector << 9)
 					+ total_bytes;
 				index = 0;
 			}
@@ -607,7 +698,7 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 					    fs_info->sectorsize,
 					    sums->sums + index);
 			kunmap_atomic(data);
-			index += csum_size;
+			index += fs_info->csum_size;
 			offset += fs_info->sectorsize;
 			this_sum_bytes += fs_info->sectorsize;
 			total_bytes += fs_info->sectorsize;
@@ -637,14 +728,14 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info,
 				       u64 bytenr, u64 len)
 {
 	struct extent_buffer *leaf;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
 	u64 csum_end;
 	u64 end_byte = bytenr + len;
-	u32 blocksize_bits = fs_info->sb->s_blocksize_bits;
+	u32 blocksize_bits = fs_info->sectorsize_bits;
 
 	leaf = path->nodes[0];
 	csum_end = btrfs_item_size_nr(leaf, path->slots[0]) / csum_size;
-	csum_end <<= fs_info->sb->s_blocksize_bits;
+	csum_end <<= blocksize_bits;
 	csum_end += key->offset;
 
 	if (key->offset < bytenr && csum_end <= end_byte) {
@@ -691,8 +782,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 	u64 csum_end;
 	struct extent_buffer *leaf;
 	int ret;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
-	int blocksize_bits = fs_info->sb->s_blocksize_bits;
+	u32 blocksize_bits = fs_info->sectorsize_bits;
 
 	ASSERT(root == fs_info->csum_root ||
 	       root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
@@ -706,7 +797,6 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		key.offset = end_byte - 1;
 		key.type = BTRFS_EXTENT_CSUM_KEY;
 
-		path->leave_spinning = 1;
 		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 		if (ret > 0) {
 			if (path->slots[0] == 0)
@@ -846,7 +936,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 	int index = 0;
 	int found_next;
 	int ret;
-	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
+	const u32 csum_size = fs_info->csum_size;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -921,7 +1011,7 @@ again:
 	if (btrfs_leaf_free_space(leaf) >= csum_size) {
 		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
 		csum_offset = (bytenr - found_key.offset) >>
-			fs_info->sb->s_blocksize_bits;
+			fs_info->sectorsize_bits;
 		goto extend_csum;
 	}
 
@@ -939,8 +1029,7 @@ again:
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-	csum_offset = (bytenr - found_key.offset) >>
+	csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits;
-			fs_info->sb->s_blocksize_bits;
 
 	if (found_key.type != BTRFS_EXTENT_CSUM_KEY ||
 	    found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
@@ -956,7 +1045,7 @@ extend_csum:
 		u32 diff;
 
 		tmp = sums->len - total_bytes;
-		tmp >>= fs_info->sb->s_blocksize_bits;
+		tmp >>= fs_info->sectorsize_bits;
 		WARN_ON(tmp < 1);
 
 		extend_nr = max_t(int, 1, (int)tmp);
@@ -981,9 +1070,9 @@ insert:
 		u64 tmp;
 
 		tmp = sums->len - total_bytes;
-		tmp >>= fs_info->sb->s_blocksize_bits;
+		tmp >>= fs_info->sectorsize_bits;
 		tmp = min(tmp, (next_offset - file_key.offset) >>
-					 fs_info->sb->s_blocksize_bits);
+					 fs_info->sectorsize_bits);
 
 		tmp = max_t(u64, 1, tmp);
 		tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size));
@@ -991,10 +1080,8 @@ insert:
 	} else {
 		ins_size = csum_size;
 	}
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &file_key,
 				      ins_size);
-	path->leave_spinning = 0;
 	if (ret < 0)
 		goto out;
 	if (WARN_ON(ret != 0))
@@ -1007,8 +1094,7 @@ csum:
 	item = (struct btrfs_csum_item *)((unsigned char *)item +
 					  csum_offset * csum_size);
 found:
-	ins_size = (u32)(sums->len - total_bytes) >>
+	ins_size = (u32)(sums->len - total_bytes) >> fs_info->sectorsize_bits;
-		   fs_info->sb->s_blocksize_bits;
 	ins_size *= csum_size;
 	ins_size = min_t(u32, (unsigned long)item_end - (unsigned long)item,
 			      ins_size);

fs/btrfs/free-space-cache.c

@@ -16,7 +16,6 @@
 #include "transaction.h"
 #include "disk-io.h"
 #include "extent_io.h"
-#include "inode-map.h"
 #include "volumes.h"
 #include "space-info.h"
 #include "delalloc-space.h"
@@ -33,16 +32,18 @@ struct btrfs_trim_range {
 	struct list_head list;
 };
 
-static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl,
-				struct btrfs_free_space *bitmap_info);
 static int link_free_space(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info);
 static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
 			      struct btrfs_free_space *info);
-static int btrfs_wait_cache_io_root(struct btrfs_root *root,
+static int search_bitmap(struct btrfs_free_space_ctl *ctl,
-			     struct btrfs_trans_handle *trans,
+			 struct btrfs_free_space *bitmap_info, u64 *offset,
-			     struct btrfs_io_ctl *io_ctl,
+			 u64 *bytes, bool for_alloc);
-			     struct btrfs_path *path);
+static void free_bitmap(struct btrfs_free_space_ctl *ctl,
+			struct btrfs_free_space *bitmap_info);
+static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
+			      struct btrfs_free_space *info, u64 offset,
+			      u64 bytes);
 
 static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 					       struct btrfs_path *path,
@@ -141,17 +142,15 @@ static int __create_free_space_inode(struct btrfs_root *root,
 	struct btrfs_free_space_header *header;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *leaf;
-	u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC;
+	/* We inline CRCs for the free disk space cache */
+	const u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC |
+			  BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW;
 	int ret;
 
 	ret = btrfs_insert_empty_inode(trans, root, path, ino);
 	if (ret)
 		return ret;
 
-	/* We inline crc's for the free disk space cache */
-	if (ino != BTRFS_FREE_INO_OBJECTID)
-		flags |= BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW;
-
 	leaf = path->nodes[0];
 	inode_item = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_inode_item);
@@ -207,6 +206,65 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
 					 ino, block_group->start);
 }
 
+/*
+ * inode is an optional sink: if it is NULL, btrfs_remove_free_space_inode
+ * handles lookup, otherwise it takes ownership and iputs the inode.
+ * Don't reuse an inode pointer after passing it into this function.
+ */
+int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
+				  struct inode *inode,
+				  struct btrfs_block_group *block_group)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int ret = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	if (!inode)
+		inode = lookup_free_space_inode(block_group, path);
+	if (IS_ERR(inode)) {
+		if (PTR_ERR(inode) != -ENOENT)
+			ret = PTR_ERR(inode);
+		goto out;
+	}
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
+	if (ret) {
+		btrfs_add_delayed_iput(inode);
+		goto out;
+	}
+	clear_nlink(inode);
+	/* One for the block groups ref */
+	spin_lock(&block_group->lock);
+	if (block_group->iref) {
+		block_group->iref = 0;
+		block_group->inode = NULL;
+		spin_unlock(&block_group->lock);
+		iput(inode);
+	} else {
+		spin_unlock(&block_group->lock);
+	}
+	/* One for the lookup ref */
+	btrfs_add_delayed_iput(inode);
+
+	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
+	key.type = 0;
+	key.offset = block_group->start;
+	ret = btrfs_search_slot(trans, trans->fs_info->tree_root, &key, path,
+				-1, 1);
+	if (ret) {
+		if (ret > 0)
+			ret = 0;
+		goto out;
+	}
+	ret = btrfs_del_item(trans, trans->fs_info->tree_root, path);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv)
 {
@@ -267,12 +325,12 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 	 * We skip the throttling logic for free space cache inodes, so we don't
 	 * need to check for -EAGAIN.
 	 */
-	ret = btrfs_truncate_inode_items(trans, root, inode,
+	ret = btrfs_truncate_inode_items(trans, root, BTRFS_I(inode),
 					 0, BTRFS_EXTENT_DATA_KEY);
 	if (ret)
 		goto fail;
 
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 
 fail:
 	if (locked)
@@ -304,16 +362,11 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 		       int write)
 {
 	int num_pages;
-	int check_crcs = 0;
 
 	num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
-	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID)
-		check_crcs = 1;
-
 	/* Make sure we can fit our crcs and generation into the first page */
-	if (write && check_crcs &&
+	if (write && (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
-	    (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
 		return -ENOSPC;
 
 	memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
@@ -324,7 +377,6 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 
 	io_ctl->num_pages = num_pages;
 	io_ctl->fs_info = btrfs_sb(inode->i_sb);
-	io_ctl->check_crcs = check_crcs;
 	io_ctl->inode = inode;
 
 	return 0;
@@ -419,13 +471,8 @@ static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
 	 * Skip the csum areas.  If we don't check crcs then we just have a
 	 * 64bit chunk at the front of the first page.
 	 */
-	if (io_ctl->check_crcs) {
+	io_ctl->cur += (sizeof(u32) * io_ctl->num_pages);
-		io_ctl->cur += (sizeof(u32) * io_ctl->num_pages);
+	io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages);
-		io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages);
-	} else {
-		io_ctl->cur += sizeof(u64);
-		io_ctl->size -= sizeof(u64) * 2;
-	}
 
 	put_unaligned_le64(generation, io_ctl->cur);
 	io_ctl->cur += sizeof(u64);
@@ -439,14 +486,8 @@ static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation)
 	 * Skip the crc area.  If we don't check crcs then we just have a 64bit
 	 * chunk at the front of the first page.
 	 */
-	if (io_ctl->check_crcs) {
+	io_ctl->cur += sizeof(u32) * io_ctl->num_pages;
-		io_ctl->cur += sizeof(u32) * io_ctl->num_pages;
+	io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages);
-		io_ctl->size -= sizeof(u64) +
-			(sizeof(u32) * io_ctl->num_pages);
-	} else {
-		io_ctl->cur += sizeof(u64);
-		io_ctl->size -= sizeof(u64) * 2;
-	}
 
 	cache_gen = get_unaligned_le64(io_ctl->cur);
 	if (cache_gen != generation) {
@@ -466,11 +507,6 @@ static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index)
 	u32 crc = ~(u32)0;
 	unsigned offset = 0;
 
-	if (!io_ctl->check_crcs) {
-		io_ctl_unmap_page(io_ctl);
-		return;
-	}
-
 	if (index == 0)
 		offset = sizeof(u32) * io_ctl->num_pages;
 
@@ -488,11 +524,6 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index)
 	u32 crc = ~(u32)0;
 	unsigned offset = 0;
 
-	if (!io_ctl->check_crcs) {
-		io_ctl_map_page(io_ctl, 0);
-		return 0;
-	}
-
 	if (index == 0)
 		offset = sizeof(u32) * io_ctl->num_pages;
 
@@ -625,42 +656,42 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
 	return 0;
 }
 
-/*
+static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
- * Since we attach pinned extents after the fact we can have contiguous sections
- * of free space that are split up in entries.  This poses a problem with the
- * tree logging stuff since it could have allocated across what appears to be 2
- * entries since we would have merged the entries when adding the pinned extents
- * back to the free space cache.  So run through the space cache that we just
- * loaded and merge contiguous entries.  This will make the log replay stuff not
- * blow up and it will make for nicer allocator behavior.
- */
-static void merge_space_tree(struct btrfs_free_space_ctl *ctl)
 {
-	struct btrfs_free_space *e, *prev = NULL;
+	struct btrfs_block_group *block_group = ctl->private;
-	struct rb_node *n;
+	u64 max_bytes;
+	u64 bitmap_bytes;
+	u64 extent_bytes;
+	u64 size = block_group->length;
+	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
+	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
 
-again:
+	max_bitmaps = max_t(u64, max_bitmaps, 1);
-	spin_lock(&ctl->tree_lock);
+
-	for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
+	ASSERT(ctl->total_bitmaps <= max_bitmaps);
-		e = rb_entry(n, struct btrfs_free_space, offset_index);
+
-		if (!prev)
+	/*
-			goto next;
+	 * We are trying to keep the total amount of memory used per 1GiB of
-		if (e->bitmap || prev->bitmap)
+	 * space to be MAX_CACHE_BYTES_PER_GIG.  However, with a reclamation
-			goto next;
+	 * mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of
-		if (prev->offset + prev->bytes == e->offset) {
+	 * bitmaps, we may end up using more memory than this.
-			unlink_free_space(ctl, prev);
+	 */
-			unlink_free_space(ctl, e);
+	if (size < SZ_1G)
-			prev->bytes += e->bytes;
+		max_bytes = MAX_CACHE_BYTES_PER_GIG;
-			kmem_cache_free(btrfs_free_space_cachep, e);
+	else
-			link_free_space(ctl, prev);
+		max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G);
-			prev = NULL;
+
-			spin_unlock(&ctl->tree_lock);
+	bitmap_bytes = ctl->total_bitmaps * ctl->unit;
-			goto again;
+
-		}
+	/*
-next:
+	 * we want the extent entry threshold to always be at most 1/2 the max
-		prev = e;
+	 * bytes we can have, or whatever is less than that.
-	}
+	 */
-	spin_unlock(&ctl->tree_lock);
+	extent_bytes = max_bytes - bitmap_bytes;
+	extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1);
+
+	ctl->extents_thresh =
+		div_u64(extent_bytes, sizeof(struct btrfs_free_space));
 }
 
 static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
@@ -753,16 +784,6 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 			goto free_cache;
 		}
 
-		/*
-		 * Sync discard ensures that the free space cache is always
-		 * trimmed.  So when reading this in, the state should reflect
-		 * that.  We also do this for async as a stop gap for lack of
-		 * persistence.
-		 */
-		if (btrfs_test_opt(fs_info, DISCARD_SYNC) ||
-		    btrfs_test_opt(fs_info, DISCARD_ASYNC))
-			e->trim_state = BTRFS_TRIM_STATE_TRIMMED;
-
 		if (!e->bytes) {
 			kmem_cache_free(btrfs_free_space_cachep, e);
 			goto free_cache;
@@ -791,7 +812,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 			spin_lock(&ctl->tree_lock);
 			ret = link_free_space(ctl, e);
 			ctl->total_bitmaps++;
-			ctl->op->recalc_thresholds(ctl);
+			recalculate_thresholds(ctl);
 			spin_unlock(&ctl->tree_lock);
 			if (ret) {
 				btrfs_err(fs_info,
@@ -816,19 +837,11 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 		ret = io_ctl_read_bitmap(&io_ctl, e);
 		if (ret)
 			goto free_cache;
-		e->bitmap_extents = count_bitmap_extents(ctl, e);
-		if (!btrfs_free_space_trimmed(e)) {
-			ctl->discardable_extents[BTRFS_STAT_CURR] +=
-				e->bitmap_extents;
-			ctl->discardable_bytes[BTRFS_STAT_CURR] += e->bytes;
-		}
 	}
 
 	io_ctl_drop_pages(&io_ctl);
-	merge_space_tree(ctl);
 	ret = 1;
 out:
-	btrfs_discard_update_discardable(ctl->private, ctl);
 	io_ctl_free(&io_ctl);
 	return ret;
 free_cache:
@@ -837,16 +850,59 @@ free_cache:
 	goto out;
 }
 
+static int copy_free_space_cache(struct btrfs_block_group *block_group,
+				 struct btrfs_free_space_ctl *ctl)
+{
+	struct btrfs_free_space *info;
+	struct rb_node *n;
+	int ret = 0;
+
+	while (!ret && (n = rb_first(&ctl->free_space_offset)) != NULL) {
+		info = rb_entry(n, struct btrfs_free_space, offset_index);
+		if (!info->bitmap) {
+			unlink_free_space(ctl, info);
+			ret = btrfs_add_free_space(block_group, info->offset,
+						   info->bytes);
+			kmem_cache_free(btrfs_free_space_cachep, info);
+		} else {
+			u64 offset = info->offset;
+			u64 bytes = ctl->unit;
+
+			while (search_bitmap(ctl, info, &offset, &bytes,
+					     false) == 0) {
+				ret = btrfs_add_free_space(block_group, offset,
+							   bytes);
+				if (ret)
+					break;
+				bitmap_clear_bits(ctl, info, offset, bytes);
+				offset = info->offset;
+				bytes = ctl->unit;
+			}
+			free_bitmap(ctl, info);
+		}
+		cond_resched();
+	}
+	return ret;
+}
+
 int load_free_space_cache(struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct btrfs_free_space_ctl tmp_ctl = {};
 	struct inode *inode;
 	struct btrfs_path *path;
 	int ret = 0;
 	bool matched;
 	u64 used = block_group->used;
 
+	/*
+	 * Because we could potentially discard our loaded free space, we want
+	 * to load everything into a temporary structure first, and then if it's
+	 * valid copy it all into the actual free space ctl.
+	 */
+	btrfs_init_free_space_ctl(block_group, &tmp_ctl);
+
 	/*
 	 * If this block group has been marked to be cleared for one reason or
 	 * another then we can't trust the on disk cache, so just return.
@@ -898,19 +954,25 @@ int load_free_space_cache(struct btrfs_block_group *block_group)
 	}
 	spin_unlock(&block_group->lock);
 
-	ret = __load_free_space_cache(fs_info->tree_root, inode, ctl,
+	ret = __load_free_space_cache(fs_info->tree_root, inode, &tmp_ctl,
 				      path, block_group->start);
 	btrfs_free_path(path);
 	if (ret <= 0)
 		goto out;
 
-	spin_lock(&ctl->tree_lock);
+	matched = (tmp_ctl.free_space == (block_group->length - used -
-	matched = (ctl->free_space == (block_group->length - used -
+					  block_group->bytes_super));
-				       block_group->bytes_super));
-	spin_unlock(&ctl->tree_lock);
 
-	if (!matched) {
+	if (matched) {
-		__btrfs_remove_free_space_cache(ctl);
+		ret = copy_free_space_cache(block_group, &tmp_ctl);
+		/*
+		 * ret == 1 means we successfully loaded the free space cache,
+		 * so we need to re-set it here.
+		 */
+		if (ret == 0)
+			ret = 1;
+	} else {
+		__btrfs_remove_free_space_cache(&tmp_ctl);
 		btrfs_warn(fs_info,
 			   "block group %llu has wrong amount of free space",
 			   block_group->start);
@@ -929,6 +991,9 @@ out:
 			   block_group->start);
 	}
 
+	spin_lock(&ctl->tree_lock);
+	btrfs_discard_update_discardable(block_group);
+	spin_unlock(&ctl->tree_lock);
 	iput(inode);
 	return ret;
 }
@@ -1191,7 +1256,7 @@ out:
 	  "failed to write free space cache for block group %llu error %d",
 				  block_group->start, ret);
 	}
-	btrfs_update_inode(trans, root, inode);
+	btrfs_update_inode(trans, root, BTRFS_I(inode));
 
 	if (block_group) {
 		/* the dirty list is protected by the dirty_bgs_lock */
@@ -1220,14 +1285,6 @@ out:
 
 }
 
-static int btrfs_wait_cache_io_root(struct btrfs_root *root,
-				    struct btrfs_trans_handle *trans,
-				    struct btrfs_io_ctl *io_ctl,
-				    struct btrfs_path *path)
-{
-	return __btrfs_wait_cache_io(root, trans, NULL, io_ctl, path, 0);
-}
-
 int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
 			struct btrfs_block_group *block_group,
 			struct btrfs_path *path)
@@ -1332,7 +1389,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	/* Everything is written out, now we dirty the pages in the file. */
 	ret = btrfs_dirty_pages(BTRFS_I(inode), io_ctl->pages,
 				io_ctl->num_pages, 0, i_size_read(inode),
-				&cached_state);
+				&cached_state, false);
 	if (ret)
 		goto out_nospc;
 
@@ -1381,7 +1438,7 @@ out:
 		invalidate_inode_pages2(inode->i_mapping);
 		BTRFS_I(inode)->generation = 0;
 	}
-	btrfs_update_inode(trans, root, inode);
+	btrfs_update_inode(trans, root, BTRFS_I(inode));
 	if (must_iput)
 		iput(inode);
 	return ret;
@@ -1672,44 +1729,6 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
 	return ret;
 }
 
-static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
-{
-	struct btrfs_block_group *block_group = ctl->private;
-	u64 max_bytes;
-	u64 bitmap_bytes;
-	u64 extent_bytes;
-	u64 size = block_group->length;
-	u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit;
-	u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg);
-
-	max_bitmaps = max_t(u64, max_bitmaps, 1);
-
-	ASSERT(ctl->total_bitmaps <= max_bitmaps);
-
-	/*
-	 * We are trying to keep the total amount of memory used per 1GiB of
-	 * space to be MAX_CACHE_BYTES_PER_GIG.  However, with a reclamation
-	 * mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of
-	 * bitmaps, we may end up using more memory than this.
-	 */
-	if (size < SZ_1G)
-		max_bytes = MAX_CACHE_BYTES_PER_GIG;
-	else
-		max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G);
-
-	bitmap_bytes = ctl->total_bitmaps * ctl->unit;
-
-	/*
-	 * we want the extent entry threshold to always be at most 1/2 the max
-	 * bytes we can have, or whatever is less than that.
-	 */
-	extent_bytes = max_bytes - bitmap_bytes;
-	extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1);
-
-	ctl->extents_thresh =
-		div_u64(extent_bytes, sizeof(struct btrfs_free_space));
-}
-
 static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 				       struct btrfs_free_space *info,
 				       u64 offset, u64 bytes)
@@ -1912,29 +1931,6 @@ out:
 	return NULL;
 }
 
-static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl,
-				struct btrfs_free_space *bitmap_info)
-{
-	struct btrfs_block_group *block_group = ctl->private;
-	u64 bytes = bitmap_info->bytes;
-	unsigned int rs, re;
-	int count = 0;
-
-	if (!block_group || !bytes)
-		return count;
-
-	bitmap_for_each_set_region(bitmap_info->bitmap, rs, re, 0,
-				   BITS_PER_BITMAP) {
-		bytes -= (rs - re) * ctl->unit;
-		count++;
-
-		if (!bytes)
-			break;
-	}
-
-	return count;
-}
-
 static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info, u64 offset)
 {
@@ -1944,8 +1940,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 	INIT_LIST_HEAD(&info->list);
 	link_free_space(ctl, info);
 	ctl->total_bitmaps++;
-
+	recalculate_thresholds(ctl);
-	ctl->op->recalc_thresholds(ctl);
 }
 
 static void free_bitmap(struct btrfs_free_space_ctl *ctl,
@@ -1967,7 +1962,7 @@ static void free_bitmap(struct btrfs_free_space_ctl *ctl,
 	kmem_cache_free(btrfs_free_space_bitmap_cachep, bitmap_info->bitmap);
 	kmem_cache_free(btrfs_free_space_cachep, bitmap_info);
 	ctl->total_bitmaps--;
-	ctl->op->recalc_thresholds(ctl);
+	recalculate_thresholds(ctl);
 }
 
 static noinline int remove_from_bitmap(struct btrfs_free_space_ctl *ctl,
@@ -2134,7 +2129,6 @@ static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
 }
 
 static const struct btrfs_free_space_op free_space_op = {
-	.recalc_thresholds	= recalculate_thresholds,
 	.use_bitmap		= use_bitmap,
 };
 
@@ -2508,7 +2502,7 @@ link:
 	if (ret)
 		kmem_cache_free(btrfs_free_space_cachep, info);
 out:
-	btrfs_discard_update_discardable(block_group, ctl);
+	btrfs_discard_update_discardable(block_group);
 	spin_unlock(&ctl->tree_lock);
 
 	if (ret) {
@@ -2643,7 +2637,7 @@ again:
 		goto again;
 	}
 out_lock:
-	btrfs_discard_update_discardable(block_group, ctl);
+	btrfs_discard_update_discardable(block_group);
 	spin_unlock(&ctl->tree_lock);
 out:
 	return ret;
@@ -2674,10 +2668,10 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 		   "%d blocks of free space at or bigger than bytes is", count);
 }
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group)
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
+			       struct btrfs_free_space_ctl *ctl)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
-	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 
 	spin_lock_init(&ctl->tree_lock);
 	ctl->unit = fs_info->sectorsize;
@@ -2779,7 +2773,7 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl)
 	spin_lock(&ctl->tree_lock);
 	__btrfs_remove_free_space_cache_locked(ctl);
 	if (ctl->private)
-		btrfs_discard_update_discardable(ctl->private, ctl);
+		btrfs_discard_update_discardable(ctl->private);
 	spin_unlock(&ctl->tree_lock);
 }
 
@@ -2801,7 +2795,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
 		cond_resched_lock(&ctl->tree_lock);
 	}
 	__btrfs_remove_free_space_cache_locked(ctl);
-	btrfs_discard_update_discardable(block_group, ctl);
+	btrfs_discard_update_discardable(block_group);
 	spin_unlock(&ctl->tree_lock);
 
 }
@@ -2885,7 +2879,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			link_free_space(ctl, entry);
 	}
 out:
-	btrfs_discard_update_discardable(block_group, ctl);
+	btrfs_discard_update_discardable(block_group);
 	spin_unlock(&ctl->tree_lock);
 
 	if (align_gap_len)
@@ -3054,7 +3048,7 @@ out:
 			kmem_cache_free(btrfs_free_space_bitmap_cachep,
 					entry->bitmap);
 			ctl->total_bitmaps--;
-			ctl->op->recalc_thresholds(ctl);
+			recalculate_thresholds(ctl);
 		} else if (!btrfs_free_space_trimmed(entry)) {
 			ctl->discardable_extents[BTRFS_STAT_CURR]--;
 		}
@@ -3828,166 +3822,62 @@ int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
 	return ret;
 }
 
-/*
+bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info)
- * Find the left-most item in the cache tree, and then return the
- * smallest inode number in the item.
- *
- * Note: the returned inode number may not be the smallest one in
- * the tree, if the left-most item is a bitmap.
- */
-u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root)
 {
-	struct btrfs_free_space_ctl *ctl = fs_root->free_ino_ctl;
+	return btrfs_super_cache_generation(fs_info->super_copy);
-	struct btrfs_free_space *entry = NULL;
+}
-	u64 ino = 0;
 
-	spin_lock(&ctl->tree_lock);
+static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info,
+				       struct btrfs_trans_handle *trans)
+{
+	struct btrfs_block_group *block_group;
+	struct rb_node *node;
+	int ret;
 
-	if (RB_EMPTY_ROOT(&ctl->free_space_offset))
+	btrfs_info(fs_info, "cleaning free space cache v1");
-		goto out;
 
-	entry = rb_entry(rb_first(&ctl->free_space_offset),
+	node = rb_first(&fs_info->block_group_cache_tree);
-			 struct btrfs_free_space, offset_index);
+	while (node) {
-
+		block_group = rb_entry(node, struct btrfs_block_group, cache_node);
-	if (!entry->bitmap) {
+		ret = btrfs_remove_free_space_inode(trans, NULL, block_group);
-		ino = entry->offset;
+		if (ret)
-
+			goto out;
-		unlink_free_space(ctl, entry);
+		node = rb_next(node);
-		entry->offset++;
-		entry->bytes--;
-		if (!entry->bytes)
-			kmem_cache_free(btrfs_free_space_cachep, entry);
-		else
-			link_free_space(ctl, entry);
-	} else {
-		u64 offset = 0;
-		u64 count = 1;
-		int ret;
-
-		ret = search_bitmap(ctl, entry, &offset, &count, true);
-		/* Logic error; Should be empty if it can't find anything */
-		ASSERT(!ret);
-
-		ino = offset;
-		bitmap_clear_bits(ctl, entry, offset, 1);
-		if (entry->bytes == 0)
-			free_bitmap(ctl, entry);
 	}
 out:
-	spin_unlock(&ctl->tree_lock);
-
-	return ino;
-}
-
-struct inode *lookup_free_ino_inode(struct btrfs_root *root,
-				    struct btrfs_path *path)
-{
-	struct inode *inode = NULL;
-
-	spin_lock(&root->ino_cache_lock);
-	if (root->ino_cache_inode)
-		inode = igrab(root->ino_cache_inode);
-	spin_unlock(&root->ino_cache_lock);
-	if (inode)
-		return inode;
-
-	inode = __lookup_free_space_inode(root, path, 0);
-	if (IS_ERR(inode))
-		return inode;
-
-	spin_lock(&root->ino_cache_lock);
-	if (!btrfs_fs_closing(root->fs_info))
-		root->ino_cache_inode = igrab(inode);
-	spin_unlock(&root->ino_cache_lock);
-
-	return inode;
-}
-
-int create_free_ino_inode(struct btrfs_root *root,
-			  struct btrfs_trans_handle *trans,
-			  struct btrfs_path *path)
-{
-	return __create_free_space_inode(root, trans, path,
-					 BTRFS_FREE_INO_OBJECTID, 0);
-}
-
-int load_free_ino_cache(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
-{
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	struct btrfs_path *path;
-	struct inode *inode;
-	int ret = 0;
-	u64 root_gen = btrfs_root_generation(&root->root_item);
-
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
-		return 0;
-
-	/*
-	 * If we're unmounting then just return, since this does a search on the
-	 * normal root and not the commit root and we could deadlock.
-	 */
-	if (btrfs_fs_closing(fs_info))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return 0;
-
-	inode = lookup_free_ino_inode(root, path);
-	if (IS_ERR(inode))
-		goto out;
-
-	if (root_gen != BTRFS_I(inode)->generation)
-		goto out_put;
-
-	ret = __load_free_space_cache(root, inode, ctl, path, 0);
-
-	if (ret < 0)
-		btrfs_err(fs_info,
-			"failed to load free ino cache for root %llu",
-			root->root_key.objectid);
-out_put:
-	iput(inode);
-out:
-	btrfs_free_path(path);
 	return ret;
 }
 
-int btrfs_write_out_ino_cache(struct btrfs_root *root,
+int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active)
-			      struct btrfs_trans_handle *trans,
-			      struct btrfs_path *path,
-			      struct inode *inode)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_trans_handle *trans;
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	int ret;
-	struct btrfs_io_ctl io_ctl;
-	bool release_metadata = true;
 
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
+	/*
-		return 0;
+	 * update_super_roots will appropriately set or unset
+	 * super_copy->cache_generation based on SPACE_CACHE and
+	 * BTRFS_FS_CLEANUP_SPACE_CACHE_V1. For this reason, we need a
+	 * transaction commit whether we are enabling space cache v1 and don't
+	 * have any other work to do, or are disabling it and removing free
+	 * space inodes.
+	 */
+	trans = btrfs_start_transaction(fs_info->tree_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
 
-	memset(&io_ctl, 0, sizeof(io_ctl));
+	if (!active) {
-	ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, trans);
+		set_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
-	if (!ret) {
+		ret = cleanup_free_space_cache_v1(fs_info, trans);
-		/*
+		if (ret) {
-		 * At this point writepages() didn't error out, so our metadata
+			btrfs_abort_transaction(trans, ret);
-		 * reservation is released when the writeback finishes, at
+			btrfs_end_transaction(trans);
-		 * inode.c:btrfs_finish_ordered_io(), regardless of it finishing
+			goto out;
-		 * with or without an error.
+		}
-		 */
-		release_metadata = false;
-		ret = btrfs_wait_cache_io_root(root, trans, &io_ctl, path);
 	}
 
-	if (ret) {
+	ret = btrfs_commit_transaction(trans);
-		if (release_metadata)
+out:
-			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+	clear_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags);
-					inode->i_size, true);
-		btrfs_debug(fs_info,
-			  "failed to write free ino cache for root %llu error %d",
-			  root->root_key.objectid, ret);
-	}
 
 	return ret;
 }

fs/btrfs/free-space-cache.h

@@ -60,7 +60,6 @@ struct btrfs_free_space_ctl {
 };
 
 struct btrfs_free_space_op {
-	void (*recalc_thresholds)(struct btrfs_free_space_ctl *ctl);
 	bool (*use_bitmap)(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info);
 };
@@ -76,7 +75,6 @@ struct btrfs_io_ctl {
 	int num_pages;
 	int entries;
 	int bitmaps;
-	unsigned check_crcs:1;
 };
 
 struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
@@ -84,6 +82,9 @@ struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group,
 int create_free_space_inode(struct btrfs_trans_handle *trans,
 			    struct btrfs_block_group *block_group,
 			    struct btrfs_path *path);
+int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans,
+				  struct inode *inode,
+				  struct btrfs_block_group *block_group);
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv);
@@ -97,19 +98,9 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
 int btrfs_write_out_cache(struct btrfs_trans_handle *trans,
 			  struct btrfs_block_group *block_group,
 			  struct btrfs_path *path);
-struct inode *lookup_free_ino_inode(struct btrfs_root *root,
-				    struct btrfs_path *path);
-int create_free_ino_inode(struct btrfs_root *root,
-			  struct btrfs_trans_handle *trans,
-			  struct btrfs_path *path);
-int load_free_ino_cache(struct btrfs_fs_info *fs_info,
-			struct btrfs_root *root);
-int btrfs_write_out_ino_cache(struct btrfs_root *root,
-			      struct btrfs_trans_handle *trans,
-			      struct btrfs_path *path,
-			      struct inode *inode);
 
-void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group);
+void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group,
+			       struct btrfs_free_space_ctl *ctl);
 int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 			   struct btrfs_free_space_ctl *ctl,
 			   u64 bytenr, u64 size,
@@ -126,7 +117,6 @@ bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group);
 u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 offset, u64 bytes, u64 empty_size,
 			       u64 *max_extent_size);
-u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root);
 void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 			   u64 bytes);
 int btrfs_find_space_cluster(struct btrfs_block_group *block_group,
@@ -148,6 +138,8 @@ int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group,
 				   u64 *trimmed, u64 start, u64 end, u64 minlen,
 				   u64 maxlen, bool async);
 
+bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info);
+int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active);
 /* Support functions for running our sanity tests */
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int test_add_free_space_entry(struct btrfs_block_group *cache,

fs/btrfs/free-space-tree.c

@@ -136,9 +136,10 @@ static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
+static inline u32 free_space_bitmap_size(const struct btrfs_fs_info *fs_info,
+					 u64 size)
 {
-	return DIV_ROUND_UP((u32)div_u64(size, sectorsize), BITS_PER_BYTE);
+	return DIV_ROUND_UP(size >> fs_info->sectorsize_bits, BITS_PER_BYTE);
 }
 
 static unsigned long *alloc_bitmap(u32 bitmap_size)
@@ -200,8 +201,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->length,
+	bitmap_size = free_space_bitmap_size(fs_info, block_group->length);
-					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
 		ret = -ENOMEM;
@@ -290,8 +290,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 		u32 data_size;
 
 		extent_size = min(end - i, bitmap_range);
-		data_size = free_space_bitmap_size(extent_size,
+		data_size = free_space_bitmap_size(fs_info, extent_size);
-						   fs_info->sectorsize);
 
 		key.objectid = i;
 		key.type = BTRFS_FREE_SPACE_BITMAP_KEY;
@@ -339,8 +338,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	int done = 0, nr;
 	int ret;
 
-	bitmap_size = free_space_bitmap_size(block_group->length,
+	bitmap_size = free_space_bitmap_size(fs_info, block_group->length);
-					     fs_info->sectorsize);
 	bitmap = alloc_bitmap(bitmap_size);
 	if (!bitmap) {
 		ret = -ENOMEM;
@@ -383,8 +381,8 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 						     fs_info->sectorsize *
 						     BITS_PER_BYTE);
 				bitmap_cursor = ((char *)bitmap) + bitmap_pos;
-				data_size = free_space_bitmap_size(found_key.offset,
+				data_size = free_space_bitmap_size(fs_info,
-								   fs_info->sectorsize);
+								found_key.offset);
 
 				ptr = btrfs_item_ptr_offset(leaf, path->slots[0] - 1);
 				read_extent_buffer(leaf, bitmap_cursor, ptr,
@@ -416,7 +414,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
 
-	nrbits = div_u64(block_group->length, block_group->fs_info->sectorsize);
+	nrbits = block_group->length >> block_group->fs_info->sectorsize_bits;
 	start_bit = find_next_bit_le(bitmap, nrbits, 0);
 
 	while (start_bit < nrbits) {
@@ -540,8 +538,8 @@ static void free_space_set_bits(struct btrfs_block_group *block_group,
 		end = found_end;
 
 	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
-	first = div_u64(*start - found_start, fs_info->sectorsize);
+	first = (*start - found_start) >> fs_info->sectorsize_bits;
-	last = div_u64(end - found_start, fs_info->sectorsize);
+	last = (end - found_start) >> fs_info->sectorsize_bits;
 	if (bit)
 		extent_buffer_bitmap_set(leaf, ptr, first, last - first);
 	else
@@ -1195,8 +1193,6 @@ static int clear_free_space_tree(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
-
 	key.objectid = 0;
 	key.type = 0;
 	key.offset = 0;

fs/btrfs/inode-item.c

@@ -119,8 +119,6 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
-
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
 		ret = -ENOENT;
@@ -193,8 +191,6 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
-
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0) {
 		ret = -ENOENT;
@@ -270,7 +266,6 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      ins_len);
 	if (ret == -EEXIST) {
@@ -327,7 +322,6 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
 	path->skip_release_on_error = 1;
 	ret = btrfs_insert_empty_item(trans, root, path, &key,
 				      ins_len);

fs/btrfs/inode-map.c

@@ -1,582 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2007 Oracle.  All rights reserved.
- */
-
-#include <linux/kthread.h>
-#include <linux/pagemap.h>
-
-#include "ctree.h"
-#include "disk-io.h"
-#include "free-space-cache.h"
-#include "inode-map.h"
-#include "transaction.h"
-#include "delalloc-space.h"
-
-static void fail_caching_thread(struct btrfs_root *root)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-
-	btrfs_warn(fs_info, "failed to start inode caching task");
-	btrfs_clear_pending_and_info(fs_info, INODE_MAP_CACHE,
-				     "disabling inode map caching");
-	spin_lock(&root->ino_cache_lock);
-	root->ino_cache_state = BTRFS_CACHE_ERROR;
-	spin_unlock(&root->ino_cache_lock);
-	wake_up(&root->ino_cache_wait);
-}
-
-static int caching_kthread(void *data)
-{
-	struct btrfs_root *root = data;
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	struct btrfs_key key;
-	struct btrfs_path *path;
-	struct extent_buffer *leaf;
-	u64 last = (u64)-1;
-	int slot;
-	int ret;
-
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		fail_caching_thread(root);
-		return -ENOMEM;
-	}
-
-	/* Since the commit root is read-only, we can safely skip locking. */
-	path->skip_locking = 1;
-	path->search_commit_root = 1;
-	path->reada = READA_FORWARD;
-
-	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
-	key.offset = 0;
-	key.type = BTRFS_INODE_ITEM_KEY;
-again:
-	/* need to make sure the commit_root doesn't disappear */
-	down_read(&fs_info->commit_root_sem);
-
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-
-	while (1) {
-		if (btrfs_fs_closing(fs_info))
-			goto out;
-
-		leaf = path->nodes[0];
-		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret < 0)
-				goto out;
-			else if (ret > 0)
-				break;
-
-			if (need_resched() ||
-			    btrfs_transaction_in_commit(fs_info)) {
-				leaf = path->nodes[0];
-
-				if (WARN_ON(btrfs_header_nritems(leaf) == 0))
-					break;
-
-				/*
-				 * Save the key so we can advances forward
-				 * in the next search.
-				 */
-				btrfs_item_key_to_cpu(leaf, &key, 0);
-				btrfs_release_path(path);
-				root->ino_cache_progress = last;
-				up_read(&fs_info->commit_root_sem);
-				schedule_timeout(1);
-				goto again;
-			} else
-				continue;
-		}
-
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-
-		if (key.type != BTRFS_INODE_ITEM_KEY)
-			goto next;
-
-		if (key.objectid >= root->highest_objectid)
-			break;
-
-		if (last != (u64)-1 && last + 1 != key.objectid) {
-			__btrfs_add_free_space(fs_info, ctl, last + 1,
-					       key.objectid - last - 1, 0);
-			wake_up(&root->ino_cache_wait);
-		}
-
-		last = key.objectid;
-next:
-		path->slots[0]++;
-	}
-
-	if (last < root->highest_objectid - 1) {
-		__btrfs_add_free_space(fs_info, ctl, last + 1,
-				       root->highest_objectid - last - 1, 0);
-	}
-
-	spin_lock(&root->ino_cache_lock);
-	root->ino_cache_state = BTRFS_CACHE_FINISHED;
-	spin_unlock(&root->ino_cache_lock);
-
-	root->ino_cache_progress = (u64)-1;
-	btrfs_unpin_free_ino(root);
-out:
-	wake_up(&root->ino_cache_wait);
-	up_read(&fs_info->commit_root_sem);
-
-	btrfs_free_path(path);
-
-	return ret;
-}
-
-static void start_caching(struct btrfs_root *root)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	struct task_struct *tsk;
-	int ret;
-	u64 objectid;
-
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
-		return;
-
-	spin_lock(&root->ino_cache_lock);
-	if (root->ino_cache_state != BTRFS_CACHE_NO) {
-		spin_unlock(&root->ino_cache_lock);
-		return;
-	}
-
-	root->ino_cache_state = BTRFS_CACHE_STARTED;
-	spin_unlock(&root->ino_cache_lock);
-
-	ret = load_free_ino_cache(fs_info, root);
-	if (ret == 1) {
-		spin_lock(&root->ino_cache_lock);
-		root->ino_cache_state = BTRFS_CACHE_FINISHED;
-		spin_unlock(&root->ino_cache_lock);
-		wake_up(&root->ino_cache_wait);
-		return;
-	}
-
-	/*
-	 * It can be quite time-consuming to fill the cache by searching
-	 * through the extent tree, and this can keep ino allocation path
-	 * waiting. Therefore at start we quickly find out the highest
-	 * inode number and we know we can use inode numbers which fall in
-	 * [highest_ino + 1, BTRFS_LAST_FREE_OBJECTID].
-	 */
-	ret = btrfs_find_free_objectid(root, &objectid);
-	if (!ret && objectid <= BTRFS_LAST_FREE_OBJECTID) {
-		__btrfs_add_free_space(fs_info, ctl, objectid,
-				       BTRFS_LAST_FREE_OBJECTID - objectid + 1,
-				       0);
-		wake_up(&root->ino_cache_wait);
-	}
-
-	tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu",
-			  root->root_key.objectid);
-	if (IS_ERR(tsk))
-		fail_caching_thread(root);
-}
-
-int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
-{
-	if (!btrfs_test_opt(root->fs_info, INODE_MAP_CACHE))
-		return btrfs_find_free_objectid(root, objectid);
-
-again:
-	*objectid = btrfs_find_ino_for_alloc(root);
-
-	if (*objectid != 0)
-		return 0;
-
-	start_caching(root);
-
-	wait_event(root->ino_cache_wait,
-		   root->ino_cache_state == BTRFS_CACHE_FINISHED ||
-		   root->ino_cache_state == BTRFS_CACHE_ERROR ||
-		   root->free_ino_ctl->free_space > 0);
-
-	if (root->ino_cache_state == BTRFS_CACHE_FINISHED &&
-	    root->free_ino_ctl->free_space == 0)
-		return -ENOSPC;
-	else if (root->ino_cache_state == BTRFS_CACHE_ERROR)
-		return btrfs_find_free_objectid(root, objectid);
-	else
-		goto again;
-}
-
-void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
-
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
-		return;
-again:
-	if (root->ino_cache_state == BTRFS_CACHE_FINISHED) {
-		__btrfs_add_free_space(fs_info, pinned, objectid, 1, 0);
-	} else {
-		down_write(&fs_info->commit_root_sem);
-		spin_lock(&root->ino_cache_lock);
-		if (root->ino_cache_state == BTRFS_CACHE_FINISHED) {
-			spin_unlock(&root->ino_cache_lock);
-			up_write(&fs_info->commit_root_sem);
-			goto again;
-		}
-		spin_unlock(&root->ino_cache_lock);
-
-		start_caching(root);
-
-		__btrfs_add_free_space(fs_info, pinned, objectid, 1, 0);
-
-		up_write(&fs_info->commit_root_sem);
-	}
-}
-
-/*
- * When a transaction is committed, we'll move those inode numbers which are
- * smaller than root->ino_cache_progress from pinned tree to free_ino tree, and
- * others will just be dropped, because the commit root we were searching has
- * changed.
- *
- * Must be called with root->fs_info->commit_root_sem held
- */
-void btrfs_unpin_free_ino(struct btrfs_root *root)
-{
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset;
-	spinlock_t *rbroot_lock = &root->free_ino_pinned->tree_lock;
-	struct btrfs_free_space *info;
-	struct rb_node *n;
-	u64 count;
-
-	if (!btrfs_test_opt(root->fs_info, INODE_MAP_CACHE))
-		return;
-
-	while (1) {
-		spin_lock(rbroot_lock);
-		n = rb_first(rbroot);
-		if (!n) {
-			spin_unlock(rbroot_lock);
-			break;
-		}
-
-		info = rb_entry(n, struct btrfs_free_space, offset_index);
-		BUG_ON(info->bitmap); /* Logic error */
-
-		if (info->offset > root->ino_cache_progress)
-			count = 0;
-		else
-			count = min(root->ino_cache_progress - info->offset + 1,
-				    info->bytes);
-
-		rb_erase(&info->offset_index, rbroot);
-		spin_unlock(rbroot_lock);
-		if (count)
-			__btrfs_add_free_space(root->fs_info, ctl,
-					       info->offset, count, 0);
-		kmem_cache_free(btrfs_free_space_cachep, info);
-	}
-}
-
-#define INIT_THRESHOLD	((SZ_32K / 2) / sizeof(struct btrfs_free_space))
-#define INODES_PER_BITMAP (PAGE_SIZE * 8)
-
-/*
- * The goal is to keep the memory used by the free_ino tree won't
- * exceed the memory if we use bitmaps only.
- */
-static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl)
-{
-	struct btrfs_free_space *info;
-	struct rb_node *n;
-	int max_ino;
-	int max_bitmaps;
-
-	n = rb_last(&ctl->free_space_offset);
-	if (!n) {
-		ctl->extents_thresh = INIT_THRESHOLD;
-		return;
-	}
-	info = rb_entry(n, struct btrfs_free_space, offset_index);
-
-	/*
-	 * Find the maximum inode number in the filesystem. Note we
-	 * ignore the fact that this can be a bitmap, because we are
-	 * not doing precise calculation.
-	 */
-	max_ino = info->bytes - 1;
-
-	max_bitmaps = ALIGN(max_ino, INODES_PER_BITMAP) / INODES_PER_BITMAP;
-	if (max_bitmaps <= ctl->total_bitmaps) {
-		ctl->extents_thresh = 0;
-		return;
-	}
-
-	ctl->extents_thresh = (max_bitmaps - ctl->total_bitmaps) *
-				PAGE_SIZE / sizeof(*info);
-}
-
-/*
- * We don't fall back to bitmap, if we are below the extents threshold
- * or this chunk of inode numbers is a big one.
- */
-static bool use_bitmap(struct btrfs_free_space_ctl *ctl,
-		       struct btrfs_free_space *info)
-{
-	if (ctl->free_extents < ctl->extents_thresh ||
-	    info->bytes > INODES_PER_BITMAP / 10)
-		return false;
-
-	return true;
-}
-
-static const struct btrfs_free_space_op free_ino_op = {
-	.recalc_thresholds	= recalculate_thresholds,
-	.use_bitmap		= use_bitmap,
-};
-
-static void pinned_recalc_thresholds(struct btrfs_free_space_ctl *ctl)
-{
-}
-
-static bool pinned_use_bitmap(struct btrfs_free_space_ctl *ctl,
-			      struct btrfs_free_space *info)
-{
-	/*
-	 * We always use extents for two reasons:
-	 *
-	 * - The pinned tree is only used during the process of caching
-	 *   work.
-	 * - Make code simpler. See btrfs_unpin_free_ino().
-	 */
-	return false;
-}
-
-static const struct btrfs_free_space_op pinned_free_ino_op = {
-	.recalc_thresholds	= pinned_recalc_thresholds,
-	.use_bitmap		= pinned_use_bitmap,
-};
-
-void btrfs_init_free_ino_ctl(struct btrfs_root *root)
-{
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
-
-	spin_lock_init(&ctl->tree_lock);
-	ctl->unit = 1;
-	ctl->start = 0;
-	ctl->private = NULL;
-	ctl->op = &free_ino_op;
-	INIT_LIST_HEAD(&ctl->trimming_ranges);
-	mutex_init(&ctl->cache_writeout_mutex);
-
-	/*
-	 * Initially we allow to use 16K of ram to cache chunks of
-	 * inode numbers before we resort to bitmaps. This is somewhat
-	 * arbitrary, but it will be adjusted in runtime.
-	 */
-	ctl->extents_thresh = INIT_THRESHOLD;
-
-	spin_lock_init(&pinned->tree_lock);
-	pinned->unit = 1;
-	pinned->start = 0;
-	pinned->private = NULL;
-	pinned->extents_thresh = 0;
-	pinned->op = &pinned_free_ino_op;
-}
-
-int btrfs_save_ino_cache(struct btrfs_root *root,
-			 struct btrfs_trans_handle *trans)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
-	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;
-	int prealloc;
-	bool retry = false;
-
-	/* only fs tree and subvol/snap needs ino cache */
-	if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID &&
-	    (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID ||
-	     root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID))
-		return 0;
-
-	/* Don't save inode cache if we are deleting this root */
-	if (btrfs_root_refs(&root->root_item) == 0)
-		return 0;
-
-	if (!btrfs_test_opt(fs_info, INODE_MAP_CACHE))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	rsv = trans->block_rsv;
-	trans->block_rsv = &fs_info->trans_block_rsv;
-
-	num_bytes = trans->bytes_reserved;
-	/*
-	 * 1 item for inode item insertion if need
-	 * 4 items for inode item update (in the worst case)
-	 * 1 items for slack space if we need do truncation
-	 * 1 item for free space object
-	 * 3 items for pre-allocation
-	 */
-	trans->bytes_reserved = btrfs_calc_insert_metadata_size(fs_info, 10);
-	ret = btrfs_block_rsv_add(root, trans->block_rsv,
-				  trans->bytes_reserved,
-				  BTRFS_RESERVE_NO_FLUSH);
-	if (ret)
-		goto out;
-	trace_btrfs_space_reservation(fs_info, "ino_cache", trans->transid,
-				      trans->bytes_reserved, 1);
-again:
-	inode = lookup_free_ino_inode(root, path);
-	if (IS_ERR(inode) && (PTR_ERR(inode) != -ENOENT || retry)) {
-		ret = PTR_ERR(inode);
-		goto out_release;
-	}
-
-	if (IS_ERR(inode)) {
-		BUG_ON(retry); /* Logic error */
-		retry = true;
-
-		ret = create_free_ino_inode(root, trans, path);
-		if (ret)
-			goto out_release;
-		goto again;
-	}
-
-	BTRFS_I(inode)->generation = 0;
-	ret = btrfs_update_inode(trans, root, inode);
-	if (ret) {
-		btrfs_abort_transaction(trans, ret);
-		goto out_put;
-	}
-
-	if (i_size_read(inode) > 0) {
-		ret = btrfs_truncate_free_space_cache(trans, NULL, inode);
-		if (ret) {
-			if (ret != -ENOSPC)
-				btrfs_abort_transaction(trans, ret);
-			goto out_put;
-		}
-	}
-
-	spin_lock(&root->ino_cache_lock);
-	if (root->ino_cache_state != BTRFS_CACHE_FINISHED) {
-		ret = -1;
-		spin_unlock(&root->ino_cache_lock);
-		goto out_put;
-	}
-	spin_unlock(&root->ino_cache_lock);
-
-	spin_lock(&ctl->tree_lock);
-	prealloc = sizeof(struct btrfs_free_space) * ctl->free_extents;
-	prealloc = ALIGN(prealloc, PAGE_SIZE);
-	prealloc += ctl->total_bitmaps * PAGE_SIZE;
-	spin_unlock(&ctl->tree_lock);
-
-	/* Just to make sure we have enough space */
-	prealloc += 8 * PAGE_SIZE;
-
-	ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, 0,
-					   prealloc);
-	if (ret)
-		goto out_put;
-
-	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
-					      prealloc, prealloc, &alloc_hint);
-	if (ret) {
-		btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
-		btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true);
-		goto out_put;
-	}
-
-	ret = btrfs_write_out_ino_cache(root, trans, path, inode);
-	btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
-out_put:
-	iput(inode);
-out_release:
-	trace_btrfs_space_reservation(fs_info, "ino_cache", trans->transid,
-				      trans->bytes_reserved, 0);
-	btrfs_block_rsv_release(fs_info, trans->block_rsv,
-				trans->bytes_reserved, NULL);
-out:
-	trans->block_rsv = rsv;
-	trans->bytes_reserved = num_bytes;
-
-	btrfs_free_path(path);
-	extent_changeset_free(data_reserved);
-	return ret;
-}
-
-int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
-{
-	struct btrfs_path *path;
-	int ret;
-	struct extent_buffer *l;
-	struct btrfs_key search_key;
-	struct btrfs_key found_key;
-	int slot;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	search_key.objectid = BTRFS_LAST_FREE_OBJECTID;
-	search_key.type = -1;
-	search_key.offset = (u64)-1;
-	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
-	if (ret < 0)
-		goto error;
-	BUG_ON(ret == 0); /* Corruption */
-	if (path->slots[0] > 0) {
-		slot = path->slots[0] - 1;
-		l = path->nodes[0];
-		btrfs_item_key_to_cpu(l, &found_key, slot);
-		*objectid = max_t(u64, found_key.objectid,
-				  BTRFS_FIRST_FREE_OBJECTID - 1);
-	} else {
-		*objectid = BTRFS_FIRST_FREE_OBJECTID - 1;
-	}
-	ret = 0;
-error:
-	btrfs_free_path(path);
-	return ret;
-}
-
-int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
-{
-	int ret;
-	mutex_lock(&root->objectid_mutex);
-
-	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
-		btrfs_warn(root->fs_info,
-			   "the objectid of root %llu reaches its highest value",
-			   root->root_key.objectid);
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	*objectid = ++root->highest_objectid;
-	ret = 0;
-out:
-	mutex_unlock(&root->objectid_mutex);
-	return ret;
-}

fs/btrfs/inode-map.h

@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef BTRFS_INODE_MAP_H
-#define BTRFS_INODE_MAP_H
-
-void btrfs_init_free_ino_ctl(struct btrfs_root *root);
-void btrfs_unpin_free_ino(struct btrfs_root *root);
-void btrfs_return_ino(struct btrfs_root *root, u64 objectid);
-int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid);
-int btrfs_save_ino_cache(struct btrfs_root *root,
-			 struct btrfs_trans_handle *trans);
-
-int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
-int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
-
-#endif

fs/btrfs/ioctl.c

@@ -34,7 +34,6 @@
 #include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
-#include "inode-map.h"
 #include "backref.h"
 #include "rcu-string.h"
 #include "send.h"
@@ -193,6 +192,15 @@ static int check_fsflags(unsigned int old_flags, unsigned int flags)
 	return 0;
 }
 
+static int check_fsflags_compatible(struct btrfs_fs_info *fs_info,
+				    unsigned int flags)
+{
+	if (btrfs_is_zoned(fs_info) && (flags & FS_NOCOW_FL))
+		return -EPERM;
+
+	return 0;
+}
+
 static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
@@ -230,6 +238,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	if (ret)
 		goto out_unlock;
 
+	ret = check_fsflags_compatible(fs_info, fsflags);
+	if (ret)
+		goto out_unlock;
+
 	binode_flags = binode->flags;
 	if (fsflags & FS_SYNC_FL)
 		binode_flags |= BTRFS_INODE_SYNC;
@@ -336,7 +348,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
 	btrfs_sync_inode_flags_to_i_flags(inode);
 	inode_inc_iversion(inode);
 	inode->i_ctime = current_time(inode);
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 
  out_end_trans:
 	btrfs_end_transaction(trans);
@@ -479,7 +491,7 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg)
 	btrfs_sync_inode_flags_to_i_flags(inode);
 	inode_inc_iversion(inode);
 	inode->i_ctime = current_time(inode);
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 
 	btrfs_end_transaction(trans);
 
@@ -733,7 +745,7 @@ static noinline int create_subvol(struct inode *dir,
 	}
 
 	btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2);
-	ret = btrfs_update_inode(trans, root, dir);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(dir));
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
@@ -1275,6 +1287,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	u64 page_end;
 	u64 page_cnt;
 	u64 start = (u64)start_index << PAGE_SHIFT;
+	u64 search_start;
 	int ret;
 	int i;
 	int i_done;
@@ -1371,6 +1384,40 @@ again:
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree,
 			 page_start, page_end - 1, &cached_state);
+
+	/*
+	 * When defragmenting we skip ranges that have holes or inline extents,
+	 * (check should_defrag_range()), to avoid unnecessary IO and wasting
+	 * space. At btrfs_defrag_file(), we check if a range should be defragged
+	 * before locking the inode and then, if it should, we trigger a sync
+	 * page cache readahead - we lock the inode only after that to avoid
+	 * blocking for too long other tasks that possibly want to operate on
+	 * other file ranges. But before we were able to get the inode lock,
+	 * some other task may have punched a hole in the range, or we may have
+	 * now an inline extent, in which case we should not defrag. So check
+	 * for that here, where we have the inode and the range locked, and bail
+	 * out if that happened.
+	 */
+	search_start = page_start;
+	while (search_start < page_end) {
+		struct extent_map *em;
+
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, search_start,
+				      page_end - search_start);
+		if (IS_ERR(em)) {
+			ret = PTR_ERR(em);
+			goto out_unlock_range;
+		}
+		if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
+			free_extent_map(em);
+			/* Ok, 0 means we did not defrag anything */
+			ret = 0;
+			goto out_unlock_range;
+		}
+		search_start = extent_map_end(em);
+		free_extent_map(em);
+	}
+
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
 			  page_end - 1, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
 			  EXTENT_DEFRAG, 0, 0, &cached_state);
@@ -1401,6 +1448,10 @@ again:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return i_done;
+
+out_unlock_range:
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+			     page_start, page_end - 1, &cached_state);
 out:
 	for (i = 0; i < i_done; i++) {
 		unlock_page(pages[i]);
@@ -1678,7 +1729,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 		btrfs_info(fs_info, "resizing devid %llu", devid);
 	}
 
-	device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
+	device = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
 	if (!device) {
 		btrfs_info(fs_info, "resizer unable to find device %llu",
 			   devid);
@@ -3321,7 +3372,7 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 
 	rcu_read_lock();
 	dev = btrfs_find_device(fs_info->fs_devices, di_args->devid, s_uuid,
-				NULL, true);
+				NULL);
 
 	if (!dev) {
 		ret = -ENODEV;
@@ -3393,7 +3444,6 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 		ret = -ENOMEM;
 		goto out_free;
 	}
-	path->leave_spinning = 1;
 
 	trans = btrfs_start_transaction(root, 1);
 	if (IS_ERR(trans)) {

fs/btrfs/locking.c

@@ -17,404 +17,89 @@
  * Extent buffer locking
  * =====================
  *
- * The locks use a custom scheme that allows to do more operations than are
+ * We use a rw_semaphore for tree locking, and the semantics are exactly the
- * available fromt current locking primitives. The building blocks are still
+ * same:
- * rwlock and wait queues.
- *
- * Required semantics:
  *
  * - reader/writer exclusion
  * - writer/writer exclusion
  * - reader/reader sharing
- * - spinning lock semantics
- * - blocking lock semantics
  * - try-lock semantics for readers and writers
- * - one level nesting, allowing read lock to be taken by the same thread that
- *   already has write lock
- *
- * The extent buffer locks (also called tree locks) manage access to eb data
- * related to the storage in the b-tree (keys, items, but not the individual
- * members of eb).
- * We want concurrency of many readers and safe updates. The underlying locking
- * is done by read-write spinlock and the blocking part is implemented using
- * counters and wait queues.
- *
- * spinning semantics - the low-level rwlock is held so all other threads that
- *                      want to take it are spinning on it.
- *
- * blocking semantics - the low-level rwlock is not held but the counter
- *                      denotes how many times the blocking lock was held;
- *                      sleeping is possible
- *
- * Write lock always allows only one thread to access the data.
- *
- *
- * Debugging
- * ---------
- *
- * There are additional state counters that are asserted in various contexts,
- * removed from non-debug build to reduce extent_buffer size and for
- * performance reasons.
- *
- *
- * Lock recursion
- * --------------
- *
- * A write operation on a tree might indirectly start a look up on the same
- * tree.  This can happen when btrfs_cow_block locks the tree and needs to
- * lookup free extents.
- *
- * btrfs_cow_block
- *   ..
- *   alloc_tree_block_no_bg_flush
- *     btrfs_alloc_tree_block
- *       btrfs_reserve_extent
- *         ..
- *         load_free_space_cache
- *           ..
- *           btrfs_lookup_file_extent
- *             btrfs_search_slot
- *
- *
- * Locking pattern - spinning
- * --------------------------
- *
- * The simple locking scenario, the +--+ denotes the spinning section.
- *
- * +- btrfs_tree_lock
- * | - extent_buffer::rwlock is held
- * | - no heavy operations should happen, eg. IO, memory allocations, large
- * |   structure traversals
- * +- btrfs_tree_unock
-*
-*
- * Locking pattern - blocking
- * --------------------------
- *
- * The blocking write uses the following scheme.  The +--+ denotes the spinning
- * section.
- *
- * +- btrfs_tree_lock
- * |
- * +- btrfs_set_lock_blocking_write
- *
- *   - allowed: IO, memory allocations, etc.
- *
- * -- btrfs_tree_unlock - note, no explicit unblocking necessary
- *
- *
- * Blocking read is similar.
- *
- * +- btrfs_tree_read_lock
- * |
- * +- btrfs_set_lock_blocking_read
- *
- *  - heavy operations allowed
- *
- * +- btrfs_tree_read_unlock_blocking
- * |
- * +- btrfs_tree_read_unlock
  *
+ * The rwsem implementation does opportunistic spinning which reduces number of
+ * times the locking task needs to sleep.
  */
 
-#ifdef CONFIG_BTRFS_DEBUG
-static inline void btrfs_assert_spinning_writers_get(struct extent_buffer *eb)
-{
-	WARN_ON(eb->spinning_writers);
-	eb->spinning_writers++;
-}
-
-static inline void btrfs_assert_spinning_writers_put(struct extent_buffer *eb)
-{
-	WARN_ON(eb->spinning_writers != 1);
-	eb->spinning_writers--;
-}
-
-static inline void btrfs_assert_no_spinning_writers(struct extent_buffer *eb)
-{
-	WARN_ON(eb->spinning_writers);
-}
-
-static inline void btrfs_assert_spinning_readers_get(struct extent_buffer *eb)
-{
-	atomic_inc(&eb->spinning_readers);
-}
-
-static inline void btrfs_assert_spinning_readers_put(struct extent_buffer *eb)
-{
-	WARN_ON(atomic_read(&eb->spinning_readers) == 0);
-	atomic_dec(&eb->spinning_readers);
-}
-
-static inline void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb)
-{
-	atomic_inc(&eb->read_locks);
-}
-
-static inline void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb)
-{
-	atomic_dec(&eb->read_locks);
-}
-
-static inline void btrfs_assert_tree_read_locked(struct extent_buffer *eb)
-{
-	BUG_ON(!atomic_read(&eb->read_locks));
-}
-
-static inline void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb)
-{
-	eb->write_locks++;
-}
-
-static inline void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb)
-{
-	eb->write_locks--;
-}
-
-#else
-static void btrfs_assert_spinning_writers_get(struct extent_buffer *eb) { }
-static void btrfs_assert_spinning_writers_put(struct extent_buffer *eb) { }
-static void btrfs_assert_no_spinning_writers(struct extent_buffer *eb) { }
-static void btrfs_assert_spinning_readers_put(struct extent_buffer *eb) { }
-static void btrfs_assert_spinning_readers_get(struct extent_buffer *eb) { }
-static void btrfs_assert_tree_read_locked(struct extent_buffer *eb) { }
-static void btrfs_assert_tree_read_locks_get(struct extent_buffer *eb) { }
-static void btrfs_assert_tree_read_locks_put(struct extent_buffer *eb) { }
-static void btrfs_assert_tree_write_locks_get(struct extent_buffer *eb) { }
-static void btrfs_assert_tree_write_locks_put(struct extent_buffer *eb) { }
-#endif
-
 /*
- * Mark already held read lock as blocking. Can be nested in write lock by the
+ * __btrfs_tree_read_lock - lock extent buffer for read
- * same thread.
+ * @eb:		the eb to be locked
+ * @nest:	the nesting level to be used for lockdep
  *
- * Use when there are potentially long operations ahead so other thread waiting
+ * This takes the read lock on the extent buffer, using the specified nesting
- * on the lock will not actively spin but sleep instead.
+ * level for lockdep purposes.
- *
- * The rwlock is released and blocking reader counter is increased.
  */
-void btrfs_set_lock_blocking_read(struct extent_buffer *eb)
+void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
-{
-	trace_btrfs_set_lock_blocking_read(eb);
-	/*
-	 * No lock is required.  The lock owner may change if we have a read
-	 * lock, but it won't change to or away from us.  If we have the write
-	 * lock, we are the owner and it'll never change.
-	 */
-	if (eb->lock_recursed && current->pid == eb->lock_owner)
-		return;
-	btrfs_assert_tree_read_locked(eb);
-	atomic_inc(&eb->blocking_readers);
-	btrfs_assert_spinning_readers_put(eb);
-	read_unlock(&eb->lock);
-}
-
-/*
- * Mark already held write lock as blocking.
- *
- * Use when there are potentially long operations ahead so other threads
- * waiting on the lock will not actively spin but sleep instead.
- *
- * The rwlock is released and blocking writers is set.
- */
-void btrfs_set_lock_blocking_write(struct extent_buffer *eb)
-{
-	trace_btrfs_set_lock_blocking_write(eb);
-	/*
-	 * No lock is required.  The lock owner may change if we have a read
-	 * lock, but it won't change to or away from us.  If we have the write
-	 * lock, we are the owner and it'll never change.
-	 */
-	if (eb->lock_recursed && current->pid == eb->lock_owner)
-		return;
-	if (eb->blocking_writers == 0) {
-		btrfs_assert_spinning_writers_put(eb);
-		btrfs_assert_tree_locked(eb);
-		WRITE_ONCE(eb->blocking_writers, 1);
-		write_unlock(&eb->lock);
-	}
-}
-
-/*
- * Lock the extent buffer for read. Wait for any writers (spinning or blocking).
- * Can be nested in write lock by the same thread.
- *
- * Use when the locked section does only lightweight actions and busy waiting
- * would be cheaper than making other threads do the wait/wake loop.
- *
- * The rwlock is held upon exit.
- */
-void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest,
-			    bool recurse)
 {
 	u64 start_ns = 0;
 
 	if (trace_btrfs_tree_read_lock_enabled())
 		start_ns = ktime_get_ns();
-again:
+
-	read_lock(&eb->lock);
+	down_read_nested(&eb->lock, nest);
-	BUG_ON(eb->blocking_writers == 0 &&
+	eb->lock_owner = current->pid;
-	       current->pid == eb->lock_owner);
-	if (eb->blocking_writers) {
-		if (current->pid == eb->lock_owner) {
-			/*
-			 * This extent is already write-locked by our thread.
-			 * We allow an additional read lock to be added because
-			 * it's for the same thread. btrfs_find_all_roots()
-			 * depends on this as it may be called on a partly
-			 * (write-)locked tree.
-			 */
-			WARN_ON(!recurse);
-			BUG_ON(eb->lock_recursed);
-			eb->lock_recursed = true;
-			read_unlock(&eb->lock);
-			trace_btrfs_tree_read_lock(eb, start_ns);
-			return;
-		}
-		read_unlock(&eb->lock);
-		wait_event(eb->write_lock_wq,
-			   READ_ONCE(eb->blocking_writers) == 0);
-		goto again;
-	}
-	btrfs_assert_tree_read_locks_get(eb);
-	btrfs_assert_spinning_readers_get(eb);
 	trace_btrfs_tree_read_lock(eb, start_ns);
 }
 
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
-	__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, false);
+	__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL);
 }
 
 /*
- * Lock extent buffer for read, optimistically expecting that there are no
+ * Try-lock for read.
- * contending blocking writers. If there are, don't wait.
- *
- * Return 1 if the rwlock has been taken, 0 otherwise
- */
-int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
-{
-	if (READ_ONCE(eb->blocking_writers))
-		return 0;
-
-	read_lock(&eb->lock);
-	/* Refetch value after lock */
-	if (READ_ONCE(eb->blocking_writers)) {
-		read_unlock(&eb->lock);
-		return 0;
-	}
-	btrfs_assert_tree_read_locks_get(eb);
-	btrfs_assert_spinning_readers_get(eb);
-	trace_btrfs_tree_read_lock_atomic(eb);
-	return 1;
-}
-
-/*
- * Try-lock for read. Don't block or wait for contending writers.
  *
  * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_read_lock(struct extent_buffer *eb)
 {
-	if (READ_ONCE(eb->blocking_writers))
+	if (down_read_trylock(&eb->lock)) {
-		return 0;
+		eb->lock_owner = current->pid;
-
+		trace_btrfs_try_tree_read_lock(eb);
-	if (!read_trylock(&eb->lock))
+		return 1;
-		return 0;
-
-	/* Refetch value after lock */
-	if (READ_ONCE(eb->blocking_writers)) {
-		read_unlock(&eb->lock);
-		return 0;
 	}
-	btrfs_assert_tree_read_locks_get(eb);
+	return 0;
-	btrfs_assert_spinning_readers_get(eb);
-	trace_btrfs_try_tree_read_lock(eb);
-	return 1;
 }
 
 /*
- * Try-lock for write. May block until the lock is uncontended, but does not
+ * Try-lock for write.
- * wait until it is free.
  *
  * Retrun 1 if the rwlock has been taken, 0 otherwise
  */
 int btrfs_try_tree_write_lock(struct extent_buffer *eb)
 {
-	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers))
+	if (down_write_trylock(&eb->lock)) {
-		return 0;
+		eb->lock_owner = current->pid;
-
+		trace_btrfs_try_tree_write_lock(eb);
-	write_lock(&eb->lock);
+		return 1;
-	/* Refetch value after lock */
-	if (READ_ONCE(eb->blocking_writers) || atomic_read(&eb->blocking_readers)) {
-		write_unlock(&eb->lock);
-		return 0;
 	}
-	btrfs_assert_tree_write_locks_get(eb);
+	return 0;
-	btrfs_assert_spinning_writers_get(eb);
-	eb->lock_owner = current->pid;
-	trace_btrfs_try_tree_write_lock(eb);
-	return 1;
 }
 
 /*
- * Release read lock. Must be used only if the lock is in spinning mode.  If
+ * Release read lock.
- * the read lock is nested, must pair with read lock before the write unlock.
- *
- * The rwlock is not held upon exit.
  */
 void btrfs_tree_read_unlock(struct extent_buffer *eb)
 {
 	trace_btrfs_tree_read_unlock(eb);
-	/*
+	eb->lock_owner = 0;
-	 * if we're nested, we have the write lock.  No new locking
+	up_read(&eb->lock);
-	 * is needed as long as we are the lock owner.
-	 * The write unlock will do a barrier for us, and the lock_recursed
-	 * field only matters to the lock owner.
-	 */
-	if (eb->lock_recursed && current->pid == eb->lock_owner) {
-		eb->lock_recursed = false;
-		return;
-	}
-	btrfs_assert_tree_read_locked(eb);
-	btrfs_assert_spinning_readers_put(eb);
-	btrfs_assert_tree_read_locks_put(eb);
-	read_unlock(&eb->lock);
 }
 
 /*
- * Release read lock, previously set to blocking by a pairing call to
+ * __btrfs_tree_lock - lock eb for write
- * btrfs_set_lock_blocking_read(). Can be nested in write lock by the same
+ * @eb:		the eb to lock
- * thread.
+ * @nest:	the nesting to use for the lock
  *
- * State of rwlock is unchanged, last reader wakes waiting threads.
+ * Returns with the eb->lock write locked.
- */
-void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
-{
-	trace_btrfs_tree_read_unlock_blocking(eb);
-	/*
-	 * if we're nested, we have the write lock.  No new locking
-	 * is needed as long as we are the lock owner.
-	 * The write unlock will do a barrier for us, and the lock_recursed
-	 * field only matters to the lock owner.
-	 */
-	if (eb->lock_recursed && current->pid == eb->lock_owner) {
-		eb->lock_recursed = false;
-		return;
-	}
-	btrfs_assert_tree_read_locked(eb);
-	WARN_ON(atomic_read(&eb->blocking_readers) == 0);
-	/* atomic_dec_and_test implies a barrier */
-	if (atomic_dec_and_test(&eb->blocking_readers))
-		cond_wake_up_nomb(&eb->read_lock_wq);
-	btrfs_assert_tree_read_locks_put(eb);
-}
-
-/*
- * Lock for write. Wait for all blocking and spinning readers and writers. This
- * starts context where reader lock could be nested by the same thread.
- *
- * The rwlock is held for write upon exit.
  */
 void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
 	__acquires(&eb->lock)
@@ -424,19 +109,7 @@ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest)
 	if (trace_btrfs_tree_lock_enabled())
 		start_ns = ktime_get_ns();
 
-	WARN_ON(eb->lock_owner == current->pid);
+	down_write_nested(&eb->lock, nest);
-again:
-	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
-	wait_event(eb->write_lock_wq, READ_ONCE(eb->blocking_writers) == 0);
-	write_lock(&eb->lock);
-	/* Refetch value after lock */
-	if (atomic_read(&eb->blocking_readers) ||
-	    READ_ONCE(eb->blocking_writers)) {
-		write_unlock(&eb->lock);
-		goto again;
-	}
-	btrfs_assert_spinning_writers_get(eb);
-	btrfs_assert_tree_write_locks_get(eb);
 	eb->lock_owner = current->pid;
 	trace_btrfs_tree_lock(eb, start_ns);
 }
@@ -447,68 +120,13 @@ void btrfs_tree_lock(struct extent_buffer *eb)
 }
 
 /*
- * Release the write lock, either blocking or spinning (ie. there's no need
+ * Release the write lock.
- * for an explicit blocking unlock, like btrfs_tree_read_unlock_blocking).
- * This also ends the context for nesting, the read lock must have been
- * released already.
- *
- * Tasks blocked and waiting are woken, rwlock is not held upon exit.
  */
 void btrfs_tree_unlock(struct extent_buffer *eb)
 {
-	/*
-	 * This is read both locked and unlocked but always by the same thread
-	 * that already owns the lock so we don't need to use READ_ONCE
-	 */
-	int blockers = eb->blocking_writers;
-
-	BUG_ON(blockers > 1);
-
-	btrfs_assert_tree_locked(eb);
 	trace_btrfs_tree_unlock(eb);
 	eb->lock_owner = 0;
-	btrfs_assert_tree_write_locks_put(eb);
+	up_write(&eb->lock);
-
-	if (blockers) {
-		btrfs_assert_no_spinning_writers(eb);
-		/* Unlocked write */
-		WRITE_ONCE(eb->blocking_writers, 0);
-		/*
-		 * We need to order modifying blocking_writers above with
-		 * actually waking up the sleepers to ensure they see the
-		 * updated value of blocking_writers
-		 */
-		cond_wake_up(&eb->write_lock_wq);
-	} else {
-		btrfs_assert_spinning_writers_put(eb);
-		write_unlock(&eb->lock);
-	}
-}
-
-/*
- * Set all locked nodes in the path to blocking locks.  This should be done
- * before scheduling
- */
-void btrfs_set_path_blocking(struct btrfs_path *p)
-{
-	int i;
-
-	for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
-		if (!p->nodes[i] || !p->locks[i])
-			continue;
-		/*
-		 * If we currently have a spinning reader or writer lock this
-		 * will bump the count of blocking holders and drop the
-		 * spinlock.
-		 */
-		if (p->locks[i] == BTRFS_READ_LOCK) {
-			btrfs_set_lock_blocking_read(p->nodes[i]);
-			p->locks[i] = BTRFS_READ_LOCK_BLOCKING;
-		} else if (p->locks[i] == BTRFS_WRITE_LOCK) {
-			btrfs_set_lock_blocking_write(p->nodes[i]);
-			p->locks[i] = BTRFS_WRITE_LOCK_BLOCKING;
-		}
-	}
 }
 
 /*
@@ -564,14 +182,13 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
  *
  * Return: root extent buffer with read lock held
  */
-struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root,
+struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
-						  bool recurse)
 {
 	struct extent_buffer *eb;
 
 	while (1) {
 		eb = btrfs_root_node(root);
-		__btrfs_tree_read_lock(eb, BTRFS_NESTING_NORMAL, recurse);
+		btrfs_tree_read_lock(eb);
 		if (eb == root->node)
 			break;
 		btrfs_tree_read_unlock(eb);

fs/btrfs/locking.h

@@ -13,8 +13,6 @@
 
 #define BTRFS_WRITE_LOCK 1
 #define BTRFS_READ_LOCK 2
-#define BTRFS_WRITE_LOCK_BLOCKING 3
-#define BTRFS_READ_LOCK_BLOCKING 4
 
 /*
  * We are limited in number of subclasses by MAX_LOCKDEP_SUBCLASSES, which at
@@ -89,42 +87,28 @@ void __btrfs_tree_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
 void btrfs_tree_lock(struct extent_buffer *eb);
 void btrfs_tree_unlock(struct extent_buffer *eb);
 
-void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest,
+void __btrfs_tree_read_lock(struct extent_buffer *eb, enum btrfs_lock_nesting nest);
-			    bool recurse);
 void btrfs_tree_read_lock(struct extent_buffer *eb);
 void btrfs_tree_read_unlock(struct extent_buffer *eb);
-void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb);
-void btrfs_set_lock_blocking_read(struct extent_buffer *eb);
-void btrfs_set_lock_blocking_write(struct extent_buffer *eb);
 int btrfs_try_tree_read_lock(struct extent_buffer *eb);
 int btrfs_try_tree_write_lock(struct extent_buffer *eb);
-int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
-struct extent_buffer *__btrfs_read_lock_root_node(struct btrfs_root *root,
+struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root);
-						  bool recurse);
-
-static inline struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
-{
-	return __btrfs_read_lock_root_node(root, false);
-}
 
 #ifdef CONFIG_BTRFS_DEBUG
 static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) {
-	BUG_ON(!eb->write_locks);
+	lockdep_assert_held(&eb->lock);
 }
 #else
 static inline void btrfs_assert_tree_locked(struct extent_buffer *eb) { }
 #endif
 
-void btrfs_set_path_blocking(struct btrfs_path *p);
 void btrfs_unlock_up_safe(struct btrfs_path *path, int level);
 
 static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
 {
-	if (rw == BTRFS_WRITE_LOCK || rw == BTRFS_WRITE_LOCK_BLOCKING)
+	if (rw == BTRFS_WRITE_LOCK)
 		btrfs_tree_unlock(eb);
-	else if (rw == BTRFS_READ_LOCK_BLOCKING)
-		btrfs_tree_read_unlock_blocking(eb);
 	else if (rw == BTRFS_READ_LOCK)
 		btrfs_tree_read_unlock(eb);
 	else

fs/btrfs/ordered-data.c

@@ -854,51 +854,6 @@ out:
 	return entry;
 }
 
-/*
- * search the ordered extents for one corresponding to 'offset' and
- * try to find a checksum.  This is used because we allow pages to
- * be reclaimed before their checksum is actually put into the btree
- */
-int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset,
-			   u64 disk_bytenr, u8 *sum, int len)
-{
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
-	struct btrfs_ordered_sum *ordered_sum;
-	struct btrfs_ordered_extent *ordered;
-	struct btrfs_ordered_inode_tree *tree = &inode->ordered_tree;
-	unsigned long num_sectors;
-	unsigned long i;
-	u32 sectorsize = btrfs_inode_sectorsize(inode);
-	const u8 blocksize_bits = inode->vfs_inode.i_sb->s_blocksize_bits;
-	const u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
-	int index = 0;
-
-	ordered = btrfs_lookup_ordered_extent(inode, offset);
-	if (!ordered)
-		return 0;
-
-	spin_lock_irq(&tree->lock);
-	list_for_each_entry_reverse(ordered_sum, &ordered->list, list) {
-		if (disk_bytenr >= ordered_sum->bytenr &&
-		    disk_bytenr < ordered_sum->bytenr + ordered_sum->len) {
-			i = (disk_bytenr - ordered_sum->bytenr) >> blocksize_bits;
-			num_sectors = ordered_sum->len >> blocksize_bits;
-			num_sectors = min_t(int, len - index, num_sectors - i);
-			memcpy(sum + index, ordered_sum->sums + i * csum_size,
-			       num_sectors * csum_size);
-
-			index += (int)num_sectors * csum_size;
-			if (index == len)
-				goto out;
-			disk_bytenr += num_sectors * sectorsize;
-		}
-	}
-out:
-	spin_unlock_irq(&tree->lock);
-	btrfs_put_ordered_extent(ordered);
-	return index;
-}
-
 /*
  * btrfs_flush_ordered_range - Lock the passed range and ensures all pending
  * ordered extents in it are run to completion.

fs/btrfs/ordered-data.h

@@ -137,9 +137,8 @@ static inline int btrfs_ordered_sum_size(struct btrfs_fs_info *fs_info,
 					 unsigned long bytes)
 {
 	int num_sectors = (int)DIV_ROUND_UP(bytes, fs_info->sectorsize);
-	int csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
-	return sizeof(struct btrfs_ordered_sum) + num_sectors * csum_size;
+	return sizeof(struct btrfs_ordered_sum) + num_sectors * fs_info->csum_size;
 }
 
 static inline void
@@ -184,8 +183,6 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
 		u64 len);
 void btrfs_get_ordered_extents_for_logging(struct btrfs_inode *inode,
 					   struct list_head *list);
-int btrfs_find_ordered_sum(struct btrfs_inode *inode, u64 offset,
-			   u64 disk_bytenr, u8 *sum, int len);
 u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
 void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,

fs/btrfs/print-tree.c

@@ -177,8 +177,7 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 		__le64 subvol_id;
 
 		read_extent_buffer(l, &subvol_id, offset, sizeof(subvol_id));
-		pr_info("\t\tsubvol_id %llu\n",
+		pr_info("\t\tsubvol_id %llu\n", le64_to_cpu(subvol_id));
-		       (unsigned long long)le64_to_cpu(subvol_id));
 		item_size -= sizeof(u64);
 		offset += sizeof(u64);
 	}
@@ -191,15 +190,8 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 static void print_eb_refs_lock(struct extent_buffer *eb)
 {
 #ifdef CONFIG_BTRFS_DEBUG
-	btrfs_info(eb->fs_info,
+	btrfs_info(eb->fs_info, "refs %u lock_owner %u current %u",
-"refs %u lock (w:%d r:%d bw:%d br:%d sw:%d sr:%d) lock_owner %u current %u",
+		   atomic_read(&eb->refs), eb->lock_owner, current->pid);
-		   atomic_read(&eb->refs), eb->write_locks,
-		   atomic_read(&eb->read_locks),
-		   eb->blocking_writers,
-		   atomic_read(&eb->blocking_readers),
-		   eb->spinning_writers,
-		   atomic_read(&eb->spinning_readers),
-		   eb->lock_owner, current->pid);
 #endif
 }
 
@@ -398,6 +390,7 @@ void btrfs_print_tree(struct extent_buffer *c, bool follow)
 
 		btrfs_node_key_to_cpu(c, &first_key, i);
 		next = read_tree_block(fs_info, btrfs_node_blockptr(c, i),
+				       btrfs_header_owner(c),
 				       btrfs_node_ptr_generation(c, i),
 				       level - 1, &first_key);
 		if (IS_ERR(next)) {

fs/btrfs/qgroup.c

@@ -894,8 +894,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	path->leave_spinning = 1;
-
 	key.objectid = 0;
 	key.offset = 0;
 	key.type = 0;
@@ -1944,34 +1942,22 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
 		struct btrfs_key dst_key;
 
 		if (src_path->nodes[cur_level] == NULL) {
-			struct btrfs_key first_key;
 			struct extent_buffer *eb;
 			int parent_slot;
-			u64 child_gen;
-			u64 child_bytenr;
 
 			eb = src_path->nodes[cur_level + 1];
 			parent_slot = src_path->slots[cur_level + 1];
-			child_bytenr = btrfs_node_blockptr(eb, parent_slot);
-			child_gen = btrfs_node_ptr_generation(eb, parent_slot);
-			btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
 
-			eb = read_tree_block(fs_info, child_bytenr, child_gen,
+			eb = btrfs_read_node_slot(eb, parent_slot);
-					     cur_level, &first_key);
 			if (IS_ERR(eb)) {
 				ret = PTR_ERR(eb);
 				goto out;
-			} else if (!extent_buffer_uptodate(eb)) {
-				free_extent_buffer(eb);
-				ret = -EIO;
-				goto out;
 			}
 
 			src_path->nodes[cur_level] = eb;
 
 			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_read(eb);
+			src_path->locks[cur_level] = BTRFS_READ_LOCK;
-			src_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING;
 		}
 
 		src_path->slots[cur_level] = dst_path->slots[cur_level];
@@ -2066,10 +2052,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
 
 	/* Read the tree block if needed */
 	if (dst_path->nodes[cur_level] == NULL) {
-		struct btrfs_key first_key;
 		int parent_slot;
 		u64 child_gen;
-		u64 child_bytenr;
 
 		/*
 		 * dst_path->nodes[root_level] must be initialized before
@@ -2088,31 +2072,23 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
 		  */
 		eb = dst_path->nodes[cur_level + 1];
 		parent_slot = dst_path->slots[cur_level + 1];
-		child_bytenr = btrfs_node_blockptr(eb, parent_slot);
 		child_gen = btrfs_node_ptr_generation(eb, parent_slot);
-		btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
 
 		/* This node is old, no need to trace */
 		if (child_gen < last_snapshot)
 			goto out;
 
-		eb = read_tree_block(fs_info, child_bytenr, child_gen,
+		eb = btrfs_read_node_slot(eb, parent_slot);
-				     cur_level, &first_key);
 		if (IS_ERR(eb)) {
 			ret = PTR_ERR(eb);
 			goto out;
-		} else if (!extent_buffer_uptodate(eb)) {
-			free_extent_buffer(eb);
-			ret = -EIO;
-			goto out;
 		}
 
 		dst_path->nodes[cur_level] = eb;
 		dst_path->slots[cur_level] = 0;
 
 		btrfs_tree_read_lock(eb);
-		btrfs_set_lock_blocking_read(eb);
+		dst_path->locks[cur_level] = BTRFS_READ_LOCK;
-		dst_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING;
 		need_cleanup = true;
 	}
 
@@ -2256,38 +2232,28 @@ walk_down:
 	level = root_level;
 	while (level >= 0) {
 		if (path->nodes[level] == NULL) {
-			struct btrfs_key first_key;
 			int parent_slot;
-			u64 child_gen;
 			u64 child_bytenr;
 
 			/*
-			 * We need to get child blockptr/gen from parent before
+			 * We need to get child blockptr from parent before we
-			 * we can read it.
+			 * can read it.
 			  */
 			eb = path->nodes[level + 1];
 			parent_slot = path->slots[level + 1];
 			child_bytenr = btrfs_node_blockptr(eb, parent_slot);
-			child_gen = btrfs_node_ptr_generation(eb, parent_slot);
-			btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
 
-			eb = read_tree_block(fs_info, child_bytenr, child_gen,
+			eb = btrfs_read_node_slot(eb, parent_slot);
-					     level, &first_key);
 			if (IS_ERR(eb)) {
 				ret = PTR_ERR(eb);
 				goto out;
-			} else if (!extent_buffer_uptodate(eb)) {
-				free_extent_buffer(eb);
-				ret = -EIO;
-				goto out;
 			}
 
 			path->nodes[level] = eb;
 			path->slots[level] = 0;
 
 			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_read(eb);
+			path->locks[level] = BTRFS_READ_LOCK;
-			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
 
 			ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
 							fs_info->nodesize,
@@ -4242,7 +4208,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 	spin_unlock(&blocks->lock);
 
 	/* Read out reloc subtree root */
-	reloc_eb = read_tree_block(fs_info, block->reloc_bytenr,
+	reloc_eb = read_tree_block(fs_info, block->reloc_bytenr, 0,
 				   block->reloc_generation, block->level,
 				   &block->first_key);
 	if (IS_ERR(reloc_eb)) {

fs/btrfs/raid56.c

@@ -1097,7 +1097,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 
 	/* see if we can add this page onto our existing bio */
 	if (last) {
-		u64 last_end = (u64)last->bi_iter.bi_sector << 9;
+		u64 last_end = last->bi_iter.bi_sector << 9;
 		last_end += last->bi_iter.bi_size;
 
 		/*
@@ -1163,7 +1163,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 		struct bvec_iter iter;
 		int i = 0;
 
-		start = (u64)bio->bi_iter.bi_sector << 9;
+		start = bio->bi_iter.bi_sector << 9;
 		stripe_offset = start - rbio->bbio->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
@@ -1374,7 +1374,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
 static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
 				   struct bio *bio)
 {
-	u64 logical = (u64)bio->bi_iter.bi_sector << 9;
+	u64 logical = bio->bi_iter.bi_sector << 9;
 	int i;
 
 	for (i = 0; i < rbio->nr_data; i++) {
@@ -2150,7 +2150,7 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
 	if (rbio->faila == -1) {
 		btrfs_warn(fs_info,
 	"%s could not find the bad stripe in raid56 so that we cannot recover any more (bio has logical %llu len %llu, bbio has map_type %llu)",
-			   __func__, (u64)bio->bi_iter.bi_sector << 9,
+			   __func__, bio->bi_iter.bi_sector << 9,
 			   (u64)bio->bi_iter.bi_size, bbio->map_type);
 		if (generic_io)
 			btrfs_put_bbio(bbio);

fs/btrfs/reada.c

@@ -52,6 +52,7 @@ struct reada_extctl {
 
 struct reada_extent {
 	u64			logical;
+	u64			owner_root;
 	struct btrfs_key	top;
 	struct list_head	extctl;
 	int 			refcnt;
@@ -59,6 +60,7 @@ struct reada_extent {
 	struct reada_zone	*zones[BTRFS_MAX_MIRRORS];
 	int			nzones;
 	int			scheduled;
+	int			level;
 };
 
 struct reada_zone {
@@ -87,7 +89,8 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info);
 static void __reada_start_machine(struct btrfs_fs_info *fs_info);
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, u64 generation);
+			   struct btrfs_key *top, u64 owner_root,
+			   u64 generation, int level);
 
 /* recurses */
 /* in case of err, eb might be NULL */
@@ -165,7 +168,9 @@ static void __readahead_hook(struct btrfs_fs_info *fs_info,
 			if (rec->generation == generation &&
 			    btrfs_comp_cpu_keys(&key, &rc->key_end) < 0 &&
 			    btrfs_comp_cpu_keys(&next_key, &rc->key_start) > 0)
-				reada_add_block(rc, bytenr, &next_key, n_gen);
+				reada_add_block(rc, bytenr, &next_key,
+						btrfs_header_owner(eb), n_gen,
+						btrfs_header_level(eb) - 1);
 		}
 	}
 
@@ -298,7 +303,8 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 
 static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 					      u64 logical,
-					      struct btrfs_key *top)
+					      struct btrfs_key *top,
+					      u64 owner_root, int level)
 {
 	int ret;
 	struct reada_extent *re = NULL;
@@ -331,6 +337,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&re->extctl);
 	spin_lock_init(&re->lock);
 	re->refcnt = 1;
+	re->owner_root = owner_root;
+	re->level = level;
 
 	/*
 	 * map block
@@ -531,6 +539,8 @@ static void reada_zone_release(struct kref *kref)
 {
 	struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
 
+	lockdep_assert_held(&zone->device->fs_info->reada_lock);
+
 	radix_tree_delete(&zone->device->reada_zones,
 			  zone->end >> PAGE_SHIFT);
 
@@ -546,14 +556,15 @@ static void reada_control_release(struct kref *kref)
 }
 
 static int reada_add_block(struct reada_control *rc, u64 logical,
-			   struct btrfs_key *top, u64 generation)
+			   struct btrfs_key *top, u64 owner_root,
+			   u64 generation, int level)
 {
 	struct btrfs_fs_info *fs_info = rc->fs_info;
 	struct reada_extent *re;
 	struct reada_extctl *rec;
 
 	/* takes one ref */
-	re = reada_find_extent(fs_info, logical, top);
+	re = reada_find_extent(fs_info, logical, top, owner_root, level);
 	if (!re)
 		return -1;
 
@@ -645,12 +656,13 @@ static int reada_pick_zone(struct btrfs_device *dev)
 }
 
 static int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
-				    int mirror_num, struct extent_buffer **eb)
+				    u64 owner_root, int level, int mirror_num,
+				    struct extent_buffer **eb)
 {
 	struct extent_buffer *buf = NULL;
 	int ret;
 
-	buf = btrfs_find_create_tree_block(fs_info, bytenr);
+	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
 	if (IS_ERR(buf))
 		return 0;
 
@@ -738,7 +750,8 @@ static int reada_start_machine_dev(struct btrfs_device *dev)
 	logical = re->logical;
 
 	atomic_inc(&dev->reada_in_flight);
-	ret = reada_tree_block_flagged(fs_info, logical, mirror_num, &eb);
+	ret = reada_tree_block_flagged(fs_info, logical, re->owner_root,
+				       re->level, mirror_num, &eb);
 	if (ret)
 		__readahead_hook(fs_info, re, NULL, ret);
 	else if (eb)
@@ -945,6 +958,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 	u64 start;
 	u64 generation;
 	int ret;
+	int level;
 	struct extent_buffer *node;
 	static struct btrfs_key max_key = {
 		.objectid = (u64)-1,
@@ -967,9 +981,11 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 	node = btrfs_root_node(root);
 	start = node->start;
 	generation = btrfs_header_generation(node);
+	level = btrfs_header_level(node);
 	free_extent_buffer(node);
 
-	ret = reada_add_block(rc, start, &max_key, generation);
+	ret = reada_add_block(rc, start, &max_key, root->root_key.objectid,
+			      generation, level);
 	if (ret) {
 		kfree(rc);
 		return ERR_PTR(ret);

fs/btrfs/ref-verify.c

@@ -551,34 +551,19 @@ static int process_leaf(struct btrfs_root *root,
 static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
 			  int level, u64 *bytenr, u64 *num_bytes)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *eb;
-	u64 block_bytenr, gen;
 	int ret = 0;
 
 	while (level >= 0) {
 		if (level) {
-			struct btrfs_key first_key;
+			eb = btrfs_read_node_slot(path->nodes[level],
-
+						  path->slots[level]);
-			block_bytenr = btrfs_node_blockptr(path->nodes[level],
-							   path->slots[level]);
-			gen = btrfs_node_ptr_generation(path->nodes[level],
-							path->slots[level]);
-			btrfs_node_key_to_cpu(path->nodes[level], &first_key,
-					      path->slots[level]);
-			eb = read_tree_block(fs_info, block_bytenr, gen,
-					     level - 1, &first_key);
 			if (IS_ERR(eb))
 				return PTR_ERR(eb);
-			if (!extent_buffer_uptodate(eb)) {
-				free_extent_buffer(eb);
-				return -EIO;
-			}
 			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_read(eb);
 			path->nodes[level-1] = eb;
 			path->slots[level-1] = 0;
-			path->locks[level-1] = BTRFS_READ_LOCK_BLOCKING;
+			path->locks[level-1] = BTRFS_READ_LOCK;
 		} else {
 			ret = process_leaf(root, path, bytenr, num_bytes);
 			if (ret)
@@ -799,8 +784,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 		if (!be) {
 			btrfs_err(fs_info,
 "trying to do action %d to bytenr %llu num_bytes %llu but there is no existing entry!",
-				  action, (unsigned long long)bytenr,
+				  action, bytenr, num_bytes);
-				  (unsigned long long)num_bytes);
 			dump_ref_action(fs_info, ra);
 			kfree(ref);
 			kfree(ra);
@@ -1001,11 +985,10 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 		return -ENOMEM;
 
 	eb = btrfs_read_lock_root_node(fs_info->extent_root);
-	btrfs_set_lock_blocking_read(eb);
 	level = btrfs_header_level(eb);
 	path->nodes[level] = eb;
 	path->slots[level] = 0;
-	path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+	path->locks[level] = BTRFS_READ_LOCK;
 
 	while (1) {
 		/*

fs/btrfs/reflink.c

@@ -31,10 +31,10 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 		endoff = destoff + olen;
 	if (endoff > inode->i_size) {
 		i_size_write(inode, endoff);
-		btrfs_inode_safe_disk_i_size_write(inode, 0);
+		btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
 	}
 
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		btrfs_end_transaction(trans);
@@ -163,6 +163,7 @@ static int clone_copy_inline_extent(struct inode *dst,
 	const u64 aligned_end = ALIGN(new_key->offset + datal,
 				      fs_info->sectorsize);
 	struct btrfs_trans_handle *trans = NULL;
+	struct btrfs_drop_extents_args drop_args = { 0 };
 	int ret;
 	struct btrfs_key key;
 
@@ -252,7 +253,11 @@ copy_inline_extent:
 		trans = NULL;
 		goto out;
 	}
-	ret = btrfs_drop_extents(trans, root, dst, drop_start, aligned_end, 1);
+	drop_args.path = path;
+	drop_args.start = drop_start;
+	drop_args.end = aligned_end;
+	drop_args.drop_cache = true;
+	ret = btrfs_drop_extents(trans, root, BTRFS_I(dst), &drop_args);
 	if (ret)
 		goto out;
 	ret = btrfs_insert_empty_item(trans, root, path, new_key, size);
@@ -263,7 +268,7 @@ copy_inline_extent:
 			    btrfs_item_ptr_offset(path->nodes[0],
 						  path->slots[0]),
 			    size);
-	inode_add_bytes(dst, datal);
+	btrfs_update_inode_bytes(BTRFS_I(dst), datal, drop_args.bytes_found);
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(dst)->runtime_flags);
 	ret = btrfs_inode_set_file_extent_range(BTRFS_I(dst), 0, aligned_end);
 out:
@@ -347,7 +352,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 		u64 drop_start;
 
 		/* Note the key will change type as we walk through the tree */
-		path->leave_spinning = 1;
 		ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
 				0, 0);
 		if (ret < 0)
@@ -417,7 +421,6 @@ process_slot:
 				   size);
 
 		btrfs_release_path(path);
-		path->leave_spinning = 0;
 
 		memcpy(&new_key, &key, sizeof(new_key));
 		new_key.objectid = btrfs_ino(BTRFS_I(inode));
@@ -533,7 +536,6 @@ process_slot:
 		 * mixing buffered and direct IO writes against this file.
 		 */
 		btrfs_release_path(path);
-		path->leave_spinning = 0;
 
 		ret = btrfs_replace_file_extents(inode, path, last_dest_end,
 				destoff + len - 1, NULL, &trans);
@@ -652,7 +654,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
 	if (destoff > inode->i_size) {
 		const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);
 
-		ret = btrfs_cont_expand(inode, inode->i_size, destoff);
+		ret = btrfs_cont_expand(BTRFS_I(inode), inode->i_size, destoff);
 		if (ret)
 			return ret;
 		/*

fs/btrfs/relocation.c

@@ -18,7 +18,6 @@
 #include "btrfs_inode.h"
 #include "async-thread.h"
 #include "free-space-cache.h"
-#include "inode-map.h"
 #include "qgroup.h"
 #include "print-tree.h"
 #include "delalloc-space.h"
@@ -783,7 +782,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
 		btrfs_set_root_refs(root_item, 0);
 		memset(&root_item->drop_progress, 0,
 		       sizeof(struct btrfs_disk_key));
-		root_item->drop_level = 0;
+		btrfs_set_root_drop_level(root_item, 0);
 	}
 
 	btrfs_tree_unlock(eb);
@@ -1196,7 +1195,6 @@ again:
 	btrfs_node_key_to_cpu(path->nodes[lowest_level], &key, slot);
 
 	eb = btrfs_lock_root_node(dest);
-	btrfs_set_lock_blocking_write(eb);
 	level = btrfs_header_level(eb);
 
 	if (level < lowest_level) {
@@ -1210,7 +1208,6 @@ again:
 				      BTRFS_NESTING_COW);
 		BUG_ON(ret);
 	}
-	btrfs_set_lock_blocking_write(eb);
 
 	if (next_key) {
 		next_key->objectid = (u64)-1;
@@ -1220,8 +1217,6 @@ again:
 
 	parent = eb;
 	while (1) {
-		struct btrfs_key first_key;
-
 		level = btrfs_header_level(parent);
 		BUG_ON(level < lowest_level);
 
@@ -1237,7 +1232,6 @@ again:
 		old_bytenr = btrfs_node_blockptr(parent, slot);
 		blocksize = fs_info->nodesize;
 		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);
-		btrfs_node_key_to_cpu(parent, &first_key, slot);
 
 		if (level <= max_level) {
 			eb = path->nodes[level];
@@ -1262,15 +1256,10 @@ again:
 				break;
 			}
 
-			eb = read_tree_block(fs_info, old_bytenr, old_ptr_gen,
+			eb = btrfs_read_node_slot(parent, slot);
-					     level - 1, &first_key);
 			if (IS_ERR(eb)) {
 				ret = PTR_ERR(eb);
 				break;
-			} else if (!extent_buffer_uptodate(eb)) {
-				ret = -EIO;
-				free_extent_buffer(eb);
-				break;
 			}
 			btrfs_tree_lock(eb);
 			if (cow) {
@@ -1279,7 +1268,6 @@ again:
 						      BTRFS_NESTING_COW);
 				BUG_ON(ret);
 			}
-			btrfs_set_lock_blocking_write(eb);
 
 			btrfs_tree_unlock(parent);
 			free_extent_buffer(parent);
@@ -1418,10 +1406,8 @@ static noinline_for_stack
 int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 			 int *level)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *eb = NULL;
 	int i;
-	u64 bytenr;
 	u64 ptr_gen = 0;
 	u64 last_snapshot;
 	u32 nritems;
@@ -1429,8 +1415,6 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 	last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 
 	for (i = *level; i > 0; i--) {
-		struct btrfs_key first_key;
-
 		eb = path->nodes[i];
 		nritems = btrfs_header_nritems(eb);
 		while (path->slots[i] < nritems) {
@@ -1450,16 +1434,9 @@ int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
 			return 0;
 		}
 
-		bytenr = btrfs_node_blockptr(eb, path->slots[i]);
+		eb = btrfs_read_node_slot(eb, path->slots[i]);
-		btrfs_node_key_to_cpu(eb, &first_key, path->slots[i]);
+		if (IS_ERR(eb))
-		eb = read_tree_block(fs_info, bytenr, ptr_gen, i - 1,
-				     &first_key);
-		if (IS_ERR(eb)) {
 			return PTR_ERR(eb);
-		} else if (!extent_buffer_uptodate(eb)) {
-			free_extent_buffer(eb);
-			return -EIO;
-		}
 		BUG_ON(btrfs_header_level(eb) != i - 1);
 		path->nodes[i - 1] = eb;
 		path->slots[i - 1] = 0;
@@ -1575,7 +1552,7 @@ static void insert_dirty_subvol(struct btrfs_trans_handle *trans,
 	reloc_root_item = &reloc_root->root_item;
 	memset(&reloc_root_item->drop_progress, 0,
 		sizeof(reloc_root_item->drop_progress));
-	reloc_root_item->drop_level = 0;
+	btrfs_set_root_drop_level(reloc_root_item, 0);
 	btrfs_set_root_refs(reloc_root_item, 0);
 	btrfs_update_reloc_root(trans, root);
 
@@ -1652,8 +1629,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	int level;
 	int max_level;
 	int replaced = 0;
-	int ret;
+	int ret = 0;
-	int err = 0;
 	u32 min_reserved;
 
 	path = btrfs_alloc_path();
@@ -1672,7 +1648,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	} else {
 		btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
 
-		level = root_item->drop_level;
+		level = btrfs_root_drop_level(root_item);
 		BUG_ON(level == 0);
 		path->lowest_level = level;
 		ret = btrfs_search_slot(NULL, reloc_root, &key, path, 0, 0);
@@ -1704,13 +1680,11 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 	while (1) {
 		ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved,
 					     BTRFS_RESERVE_FLUSH_LIMIT);
-		if (ret) {
+		if (ret)
-			err = ret;
 			goto out;
-		}
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
-			err = PTR_ERR(trans);
+			ret = PTR_ERR(trans);
 			trans = NULL;
 			goto out;
 		}
@@ -1732,10 +1706,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 		max_level = level;
 
 		ret = walk_down_reloc_tree(reloc_root, path, &level);
-		if (ret < 0) {
+		if (ret < 0)
-			err = ret;
 			goto out;
-		}
 		if (ret > 0)
 			break;
 
@@ -1746,11 +1718,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 			ret = replace_path(trans, rc, root, reloc_root, path,
 					   &next_key, level, max_level);
 		}
-		if (ret < 0) {
+		if (ret < 0)
-			err = ret;
 			goto out;
-		}
-
 		if (ret > 0) {
 			level = ret;
 			btrfs_node_key_to_cpu(path->nodes[level], &key,
@@ -1769,7 +1738,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 		 */
 		btrfs_node_key(path->nodes[level], &root_item->drop_progress,
 			       path->slots[level]);
-		root_item->drop_level = level;
+		btrfs_set_root_drop_level(root_item, level);
 
 		btrfs_end_transaction_throttle(trans);
 		trans = NULL;
@@ -1789,12 +1758,10 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 			      BTRFS_NESTING_COW);
 	btrfs_tree_unlock(leaf);
 	free_extent_buffer(leaf);
-	if (ret < 0)
-		err = ret;
 out:
 	btrfs_free_path(path);
 
-	if (err == 0)
+	if (ret == 0)
 		insert_dirty_subvol(trans, rc, root);
 
 	if (trans)
@@ -1805,7 +1772,7 @@ out:
 	if (replaced && rc->stage == UPDATE_DATA_PTRS)
 		invalidate_extent_cache(root, &key, &next_key);
 
-	return err;
+	return ret;
 }
 
 static noinline_for_stack
@@ -2205,7 +2172,6 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 			 struct btrfs_key *key,
 			 struct btrfs_path *path, int lowest)
 {
-	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
 	struct btrfs_backref_node *upper;
 	struct btrfs_backref_edge *edge;
 	struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1];
@@ -2213,17 +2179,14 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 	struct extent_buffer *eb;
 	u32 blocksize;
 	u64 bytenr;
-	u64 generation;
 	int slot;
-	int ret;
+	int ret = 0;
-	int err = 0;
 
 	BUG_ON(lowest && node->eb);
 
 	path->lowest_level = node->level + 1;
 	rc->backref_cache.path[node->level] = node;
 	list_for_each_entry(edge, &node->upper, list[LOWER]) {
-		struct btrfs_key first_key;
 		struct btrfs_ref ref = { 0 };
 
 		cond_resched();
@@ -2235,10 +2198,8 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 		if (upper->eb && !upper->locked) {
 			if (!lowest) {
 				ret = btrfs_bin_search(upper->eb, key, &slot);
-				if (ret < 0) {
+				if (ret < 0)
-					err = ret;
 					goto next;
-				}
 				BUG_ON(ret);
 				bytenr = btrfs_node_blockptr(upper->eb, slot);
 				if (node->eb->start == bytenr)
@@ -2250,10 +2211,8 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 		if (!upper->eb) {
 			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
 			if (ret) {
-				if (ret < 0)
+				if (ret > 0)
-					err = ret;
+					ret = -ENOENT;
-				else
-					err = -ENOENT;
 
 				btrfs_release_path(path);
 				break;
@@ -2273,10 +2232,8 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 			btrfs_release_path(path);
 		} else {
 			ret = btrfs_bin_search(upper->eb, key, &slot);
-			if (ret < 0) {
+			if (ret < 0)
-				err = ret;
 				goto next;
-			}
 			BUG_ON(ret);
 		}
 
@@ -2287,7 +2244,7 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 		"lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
 					  bytenr, node->bytenr, slot,
 					  upper->eb->start);
-				err = -EIO;
+				ret = -EIO;
 				goto next;
 			}
 		} else {
@@ -2296,30 +2253,20 @@ static int do_relocation(struct btrfs_trans_handle *trans,
 		}
 
 		blocksize = root->fs_info->nodesize;
-		generation = btrfs_node_ptr_generation(upper->eb, slot);
+		eb = btrfs_read_node_slot(upper->eb, slot);
-		btrfs_node_key_to_cpu(upper->eb, &first_key, slot);
-		eb = read_tree_block(fs_info, bytenr, generation,
-				     upper->level - 1, &first_key);
 		if (IS_ERR(eb)) {
-			err = PTR_ERR(eb);
+			ret = PTR_ERR(eb);
-			goto next;
-		} else if (!extent_buffer_uptodate(eb)) {
-			free_extent_buffer(eb);
-			err = -EIO;
 			goto next;
 		}
 		btrfs_tree_lock(eb);
-		btrfs_set_lock_blocking_write(eb);
 
 		if (!node->eb) {
 			ret = btrfs_cow_block(trans, root, eb, upper->eb,
 					      slot, &eb, BTRFS_NESTING_COW);
 			btrfs_tree_unlock(eb);
 			free_extent_buffer(eb);
-			if (ret < 0) {
+			if (ret < 0)
-				err = ret;
 				goto next;
-			}
 			BUG_ON(node->eb != eb);
 		} else {
 			btrfs_set_node_blockptr(upper->eb, slot,
@@ -2345,19 +2292,19 @@ next:
 			btrfs_backref_drop_node_buffer(upper);
 		else
 			btrfs_backref_unlock_node_buffer(upper);
-		if (err)
+		if (ret)
 			break;
 	}
 
-	if (!err && node->pending) {
+	if (!ret && node->pending) {
 		btrfs_backref_drop_node_buffer(node);
 		list_move_tail(&node->list, &rc->backref_cache.changed);
 		node->pending = 0;
 	}
 
 	path->lowest_level = 0;
-	BUG_ON(err == -ENOSPC);
+	BUG_ON(ret == -ENOSPC);
-	return err;
+	return ret;
 }
 
 static int link_to_upper(struct btrfs_trans_handle *trans,
@@ -2446,7 +2393,7 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info,
 {
 	struct extent_buffer *eb;
 
-	eb = read_tree_block(fs_info, block->bytenr, block->key.offset,
+	eb = read_tree_block(fs_info, block->bytenr, 0, block->key.offset,
 			     block->level, NULL);
 	if (IS_ERR(eb)) {
 		return PTR_ERR(eb);
@@ -2546,7 +2493,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	/* Kick in readahead for tree blocks with missing keys */
 	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
 		if (!block->key_ready)
-			readahead_tree_block(fs_info, block->bytenr);
+			btrfs_readahead_tree_block(fs_info, block->bytenr, 0, 0,
+						   block->level);
 	}
 
 	/* Get first keys */
@@ -3071,7 +3019,7 @@ int add_data_references(struct reloc_control *rc,
 	while ((ref_node = ulist_next(leaves, &leaf_uiter))) {
 		struct extent_buffer *eb;
 
-		eb = read_tree_block(fs_info, ref_node->val, 0, 0, NULL);
+		eb = read_tree_block(fs_info, ref_node->val, 0, 0, 0, NULL);
 		if (IS_ERR(eb)) {
 			ret = PTR_ERR(eb);
 			break;
@@ -3694,7 +3642,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
 
 	memset(&root->root_item.drop_progress, 0,
 		sizeof(root->root_item.drop_progress));
-	root->root_item.drop_level = 0;
+	btrfs_set_root_drop_level(&root->root_item, 0);
 	btrfs_set_root_refs(&root->root_item, 0);
 	ret = btrfs_update_root(trans, fs_info->tree_root,
 				&root->root_key, &root->root_item);

fs/btrfs/scrub.c

@@ -20,6 +20,7 @@
 #include "rcu-string.h"
 #include "raid56.h"
 #include "block-group.h"
+#include "zoned.h"
 
 /*
  * This is only the first step towards a full-features scrub. It reads all
@@ -71,11 +72,9 @@ struct scrub_page {
 	u64			physical;
 	u64			physical_for_dev_replace;
 	atomic_t		refs;
-	struct {
+	u8			mirror_num;
-		unsigned int	mirror_num:8;
+	int			have_csum:1;
-		unsigned int	have_csum:1;
+	int			io_error:1;
-		unsigned int	io_error:1;
-	};
 	u8			csum[BTRFS_CSUM_SIZE];
 
 	struct scrub_recover	*recover;
@@ -131,7 +130,7 @@ struct scrub_parity {
 
 	int			nsectors;
 
-	u64			stripe_len;
+	u32			stripe_len;
 
 	refcount_t		refs;
 
@@ -161,7 +160,6 @@ struct scrub_ctx {
 	atomic_t		workers_pending;
 	spinlock_t		list_lock;
 	wait_queue_head_t	list_wait;
-	u16			csum_size;
 	struct list_head	csum_list;
 	atomic_t		cancel_req;
 	int			readonly;
@@ -235,15 +233,15 @@ static void scrub_parity_get(struct scrub_parity *sparity);
 static void scrub_parity_put(struct scrub_parity *sparity);
 static int scrub_add_page_to_rd_bio(struct scrub_ctx *sctx,
 				    struct scrub_page *spage);
-static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
+static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len,
 		       u64 physical, struct btrfs_device *dev, u64 flags,
-		       u64 gen, int mirror_num, u8 *csum, int force,
+		       u64 gen, int mirror_num, u8 *csum,
 		       u64 physical_for_dev_replace);
 static void scrub_bio_end_io(struct bio *bio);
 static void scrub_bio_end_io_worker(struct btrfs_work *work);
 static void scrub_block_complete(struct scrub_block *sblock);
 static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
-			       u64 extent_logical, u64 extent_len,
+			       u64 extent_logical, u32 extent_len,
 			       u64 *extent_physical,
 			       struct btrfs_device **extent_dev,
 			       int *extent_mirror_num);
@@ -256,10 +254,10 @@ static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
 
-static inline int scrub_is_page_on_raid56(struct scrub_page *page)
+static inline int scrub_is_page_on_raid56(struct scrub_page *spage)
 {
-	return page->recover &&
+	return spage->recover &&
-	       (page->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
+	       (spage->recover->bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK);
 }
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
@@ -610,7 +608,6 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
 	atomic_set(&sctx->bios_in_flight, 0);
 	atomic_set(&sctx->workers_pending, 0);
 	atomic_set(&sctx->cancel_req, 0);
-	sctx->csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
 	spin_lock_init(&sctx->list_lock);
 	spin_lock_init(&sctx->stat_lock);
@@ -1092,11 +1089,11 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	success = 1;
 	for (page_num = 0; page_num < sblock_bad->page_count;
 	     page_num++) {
-		struct scrub_page *page_bad = sblock_bad->pagev[page_num];
+		struct scrub_page *spage_bad = sblock_bad->pagev[page_num];
 		struct scrub_block *sblock_other = NULL;
 
 		/* skip no-io-error page in scrub */
-		if (!page_bad->io_error && !sctx->is_dev_replace)
+		if (!spage_bad->io_error && !sctx->is_dev_replace)
 			continue;
 
 		if (scrub_is_page_on_raid56(sblock_bad->pagev[0])) {
@@ -1108,7 +1105,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 			 * sblock_for_recheck array to target device.
 			 */
 			sblock_other = NULL;
-		} else if (page_bad->io_error) {
+		} else if (spage_bad->io_error) {
 			/* try to find no-io-error page in mirrors */
 			for (mirror_index = 0;
 			     mirror_index < BTRFS_MAX_MIRRORS &&
@@ -1147,7 +1144,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 							       sblock_other,
 							       page_num, 0);
 			if (0 == ret)
-				page_bad->io_error = 0;
+				spage_bad->io_error = 0;
 			else
 				success = 0;
 		}
@@ -1325,13 +1322,13 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		for (mirror_index = 0; mirror_index < nmirrors;
 		     mirror_index++) {
 			struct scrub_block *sblock;
-			struct scrub_page *page;
+			struct scrub_page *spage;
 
 			sblock = sblocks_for_recheck + mirror_index;
 			sblock->sctx = sctx;
 
-			page = kzalloc(sizeof(*page), GFP_NOFS);
+			spage = kzalloc(sizeof(*spage), GFP_NOFS);
-			if (!page) {
+			if (!spage) {
 leave_nomem:
 				spin_lock(&sctx->stat_lock);
 				sctx->stat.malloc_errors++;
@@ -1339,17 +1336,17 @@ leave_nomem:
 				scrub_put_recover(fs_info, recover);
 				return -ENOMEM;
 			}
-			scrub_page_get(page);
+			scrub_page_get(spage);
-			sblock->pagev[page_index] = page;
+			sblock->pagev[page_index] = spage;
-			page->sblock = sblock;
+			spage->sblock = sblock;
-			page->flags = flags;
+			spage->flags = flags;
-			page->generation = generation;
+			spage->generation = generation;
-			page->logical = logical;
+			spage->logical = logical;
-			page->have_csum = have_csum;
+			spage->have_csum = have_csum;
 			if (have_csum)
-				memcpy(page->csum,
+				memcpy(spage->csum,
 				       original_sblock->pagev[0]->csum,
-				       sctx->csum_size);
+				       sctx->fs_info->csum_size);
 
 			scrub_stripe_index_and_offset(logical,
 						      bbio->map_type,
@@ -1360,23 +1357,23 @@ leave_nomem:
 						      mirror_index,
 						      &stripe_index,
 						      &stripe_offset);
-			page->physical = bbio->stripes[stripe_index].physical +
+			spage->physical = bbio->stripes[stripe_index].physical +
 					 stripe_offset;
-			page->dev = bbio->stripes[stripe_index].dev;
+			spage->dev = bbio->stripes[stripe_index].dev;
 
 			BUG_ON(page_index >= original_sblock->page_count);
-			page->physical_for_dev_replace =
+			spage->physical_for_dev_replace =
 				original_sblock->pagev[page_index]->
 				physical_for_dev_replace;
 			/* for missing devices, dev->bdev is NULL */
-			page->mirror_num = mirror_index + 1;
+			spage->mirror_num = mirror_index + 1;
 			sblock->page_count++;
-			page->page = alloc_page(GFP_NOFS);
+			spage->page = alloc_page(GFP_NOFS);
-			if (!page->page)
+			if (!spage->page)
 				goto leave_nomem;
 
 			scrub_get_recover(recover);
-			page->recover = recover;
+			spage->recover = recover;
 		}
 		scrub_put_recover(fs_info, recover);
 		length -= sublen;
@@ -1394,19 +1391,19 @@ static void scrub_bio_wait_endio(struct bio *bio)
 
 static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 					struct bio *bio,
-					struct scrub_page *page)
+					struct scrub_page *spage)
 {
 	DECLARE_COMPLETION_ONSTACK(done);
 	int ret;
 	int mirror_num;
 
-	bio->bi_iter.bi_sector = page->logical >> 9;
+	bio->bi_iter.bi_sector = spage->logical >> 9;
 	bio->bi_private = &done;
 	bio->bi_end_io = scrub_bio_wait_endio;
 
-	mirror_num = page->sblock->pagev[0]->mirror_num;
+	mirror_num = spage->sblock->pagev[0]->mirror_num;
-	ret = raid56_parity_recover(fs_info, bio, page->recover->bbio,
+	ret = raid56_parity_recover(fs_info, bio, spage->recover->bbio,
-				    page->recover->map_length,
+				    spage->recover->map_length,
 				    mirror_num, 0);
 	if (ret)
 		return ret;
@@ -1431,10 +1428,10 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info,
 	bio_set_dev(bio, first_page->dev->bdev);
 
 	for (page_num = 0; page_num < sblock->page_count; page_num++) {
-		struct scrub_page *page = sblock->pagev[page_num];
+		struct scrub_page *spage = sblock->pagev[page_num];
 
-		WARN_ON(!page->page);
+		WARN_ON(!spage->page);
-		bio_add_page(bio, page->page, PAGE_SIZE, 0);
+		bio_add_page(bio, spage->page, PAGE_SIZE, 0);
 	}
 
 	if (scrub_submit_raid56_bio_wait(fs_info, bio, first_page)) {
@@ -1475,24 +1472,24 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 
 	for (page_num = 0; page_num < sblock->page_count; page_num++) {
 		struct bio *bio;
-		struct scrub_page *page = sblock->pagev[page_num];
+		struct scrub_page *spage = sblock->pagev[page_num];
 
-		if (page->dev->bdev == NULL) {
+		if (spage->dev->bdev == NULL) {
-			page->io_error = 1;
+			spage->io_error = 1;
 			sblock->no_io_error_seen = 0;
 			continue;
 		}
 
-		WARN_ON(!page->page);
+		WARN_ON(!spage->page);
 		bio = btrfs_io_bio_alloc(1);
-		bio_set_dev(bio, page->dev->bdev);
+		bio_set_dev(bio, spage->dev->bdev);
 
-		bio_add_page(bio, page->page, PAGE_SIZE, 0);
+		bio_add_page(bio, spage->page, PAGE_SIZE, 0);
-		bio->bi_iter.bi_sector = page->physical >> 9;
+		bio->bi_iter.bi_sector = spage->physical >> 9;
 		bio->bi_opf = REQ_OP_READ;
 
 		if (btrfsic_submit_bio_wait(bio)) {
-			page->io_error = 1;
+			spage->io_error = 1;
 			sblock->no_io_error_seen = 0;
 		}
 
@@ -1548,36 +1545,36 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 					    struct scrub_block *sblock_good,
 					    int page_num, int force_write)
 {
-	struct scrub_page *page_bad = sblock_bad->pagev[page_num];
+	struct scrub_page *spage_bad = sblock_bad->pagev[page_num];
-	struct scrub_page *page_good = sblock_good->pagev[page_num];
+	struct scrub_page *spage_good = sblock_good->pagev[page_num];
 	struct btrfs_fs_info *fs_info = sblock_bad->sctx->fs_info;
 
-	BUG_ON(page_bad->page == NULL);
+	BUG_ON(spage_bad->page == NULL);
-	BUG_ON(page_good->page == NULL);
+	BUG_ON(spage_good->page == NULL);
 	if (force_write || sblock_bad->header_error ||
-	    sblock_bad->checksum_error || page_bad->io_error) {
+	    sblock_bad->checksum_error || spage_bad->io_error) {
 		struct bio *bio;
 		int ret;
 
-		if (!page_bad->dev->bdev) {
+		if (!spage_bad->dev->bdev) {
 			btrfs_warn_rl(fs_info,
 				"scrub_repair_page_from_good_copy(bdev == NULL) is unexpected");
 			return -EIO;
 		}
 
 		bio = btrfs_io_bio_alloc(1);
-		bio_set_dev(bio, page_bad->dev->bdev);
+		bio_set_dev(bio, spage_bad->dev->bdev);
-		bio->bi_iter.bi_sector = page_bad->physical >> 9;
+		bio->bi_iter.bi_sector = spage_bad->physical >> 9;
 		bio->bi_opf = REQ_OP_WRITE;
 
-		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
+		ret = bio_add_page(bio, spage_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
 			bio_put(bio);
 			return -EIO;
 		}
 
 		if (btrfsic_submit_bio_wait(bio)) {
-			btrfs_dev_stat_inc_and_print(page_bad->dev,
+			btrfs_dev_stat_inc_and_print(spage_bad->dev,
 				BTRFS_DEV_STAT_WRITE_ERRS);
 			atomic64_inc(&fs_info->dev_replace.num_write_errors);
 			bio_put(bio);
@@ -1798,11 +1795,15 @@ static int scrub_checksum_data(struct scrub_block *sblock)
 
 	shash->tfm = fs_info->csum_shash;
 	crypto_shash_init(shash);
-	crypto_shash_digest(shash, kaddr, PAGE_SIZE, csum);
 
-	if (memcmp(csum, spage->csum, sctx->csum_size))
+	/*
+	 * In scrub_pages() and scrub_pages_for_parity() we ensure each spage
+	 * only contains one sector of data.
+	 */
+	crypto_shash_digest(shash, kaddr, fs_info->sectorsize, csum);
+
+	if (memcmp(csum, spage->csum, fs_info->csum_size))
 		sblock->checksum_error = 1;
-
 	return sblock->checksum_error;
 }
 
@@ -1814,16 +1815,26 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	u8 calculated_csum[BTRFS_CSUM_SIZE];
 	u8 on_disk_csum[BTRFS_CSUM_SIZE];
-	const int num_pages = sctx->fs_info->nodesize >> PAGE_SHIFT;
+	/*
+	 * This is done in sectorsize steps even for metadata as there's a
+	 * constraint for nodesize to be aligned to sectorsize. This will need
+	 * to change so we don't misuse data and metadata units like that.
+	 */
+	const u32 sectorsize = sctx->fs_info->sectorsize;
+	const int num_sectors = fs_info->nodesize >> fs_info->sectorsize_bits;
 	int i;
 	struct scrub_page *spage;
 	char *kaddr;
 
 	BUG_ON(sblock->page_count < 1);
+
+	/* Each member in pagev is just one block, not a full page */
+	ASSERT(sblock->page_count == num_sectors);
+
 	spage = sblock->pagev[0];
 	kaddr = page_address(spage->page);
 	h = (struct btrfs_header *)kaddr;
-	memcpy(on_disk_csum, h->csum, sctx->csum_size);
+	memcpy(on_disk_csum, h->csum, sctx->fs_info->csum_size);
 
 	/*
 	 * we don't use the getter functions here, as we
@@ -1848,15 +1859,15 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 	shash->tfm = fs_info->csum_shash;
 	crypto_shash_init(shash);
 	crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE,
-			    PAGE_SIZE - BTRFS_CSUM_SIZE);
+			    sectorsize - BTRFS_CSUM_SIZE);
 
-	for (i = 1; i < num_pages; i++) {
+	for (i = 1; i < num_sectors; i++) {
 		kaddr = page_address(sblock->pagev[i]->page);
-		crypto_shash_update(shash, kaddr, PAGE_SIZE);
+		crypto_shash_update(shash, kaddr, sectorsize);
 	}
 
 	crypto_shash_final(shash, calculated_csum);
-	if (memcmp(calculated_csum, on_disk_csum, sctx->csum_size))
+	if (memcmp(calculated_csum, on_disk_csum, sctx->fs_info->csum_size))
 		sblock->checksum_error = 1;
 
 	return sblock->header_error || sblock->checksum_error;
@@ -1893,7 +1904,7 @@ static int scrub_checksum_super(struct scrub_block *sblock)
 	crypto_shash_digest(shash, kaddr + BTRFS_CSUM_SIZE,
 			BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, calculated_csum);
 
-	if (memcmp(calculated_csum, s->csum, sctx->csum_size))
+	if (memcmp(calculated_csum, s->csum, sctx->fs_info->csum_size))
 		++fail_cor;
 
 	if (fail_cor + fail_gen) {
@@ -2150,12 +2161,13 @@ bbio_out:
 	spin_unlock(&sctx->stat_lock);
 }
 
-static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
+static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u32 len,
 		       u64 physical, struct btrfs_device *dev, u64 flags,
-		       u64 gen, int mirror_num, u8 *csum, int force,
+		       u64 gen, int mirror_num, u8 *csum,
 		       u64 physical_for_dev_replace)
 {
 	struct scrub_block *sblock;
+	const u32 sectorsize = sctx->fs_info->sectorsize;
 	int index;
 
 	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
@@ -2174,7 +2186,12 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 
 	for (index = 0; len > 0; index++) {
 		struct scrub_page *spage;
-		u64 l = min_t(u64, len, PAGE_SIZE);
+		/*
+		 * Here we will allocate one page for one sector to scrub.
+		 * This is fine if PAGE_SIZE == sectorsize, but will cost
+		 * more memory for PAGE_SIZE > sectorsize case.
+		 */
+		u32 l = min(sectorsize, len);
 
 		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
@@ -2198,7 +2215,7 @@ leave_nomem:
 		spage->mirror_num = mirror_num;
 		if (csum) {
 			spage->have_csum = 1;
-			memcpy(spage->csum, csum, sctx->csum_size);
+			memcpy(spage->csum, csum, sctx->fs_info->csum_size);
 		} else {
 			spage->have_csum = 0;
 		}
@@ -2231,7 +2248,7 @@ leave_nomem:
 			}
 		}
 
-		if (force)
+		if (flags & BTRFS_EXTENT_FLAG_SUPER)
 			scrub_submit(sctx);
 	}
 
@@ -2295,12 +2312,11 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work)
 
 static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 				       unsigned long *bitmap,
-				       u64 start, u64 len)
+				       u64 start, u32 len)
 {
 	u64 offset;
-	u64 nsectors64;
 	u32 nsectors;
-	int sectorsize = sparity->sctx->fs_info->sectorsize;
+	u32 sectorsize_bits = sparity->sctx->fs_info->sectorsize_bits;
 
 	if (len >= sparity->stripe_len) {
 		bitmap_set(bitmap, 0, sparity->nsectors);
@@ -2309,11 +2325,8 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 
 	start -= sparity->logic_start;
 	start = div64_u64_rem(start, sparity->stripe_len, &offset);
-	offset = div_u64(offset, sectorsize);
+	offset = offset >> sectorsize_bits;
-	nsectors64 = div_u64(len, sectorsize);
+	nsectors = len >> sectorsize_bits;
-
-	ASSERT(nsectors64 < UINT_MAX);
-	nsectors = (u32)nsectors64;
 
 	if (offset + nsectors <= sparity->nsectors) {
 		bitmap_set(bitmap, offset, nsectors);
@@ -2325,13 +2338,13 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 }
 
 static inline void scrub_parity_mark_sectors_error(struct scrub_parity *sparity,
-						   u64 start, u64 len)
+						   u64 start, u32 len)
 {
 	__scrub_mark_bitmap(sparity, sparity->ebitmap, start, len);
 }
 
 static inline void scrub_parity_mark_sectors_data(struct scrub_parity *sparity,
-						  u64 start, u64 len)
+						  u64 start, u32 len)
 {
 	__scrub_mark_bitmap(sparity, sparity->dbitmap, start, len);
 }
@@ -2359,48 +2372,77 @@ static void scrub_block_complete(struct scrub_block *sblock)
 		u64 end = sblock->pagev[sblock->page_count - 1]->logical +
 			  PAGE_SIZE;
 
+		ASSERT(end - start <= U32_MAX);
 		scrub_parity_mark_sectors_error(sblock->sparity,
 						start, end - start);
 	}
 }
 
+static void drop_csum_range(struct scrub_ctx *sctx, struct btrfs_ordered_sum *sum)
+{
+	sctx->stat.csum_discards += sum->len >> sctx->fs_info->sectorsize_bits;
+	list_del(&sum->list);
+	kfree(sum);
+}
+
+/*
+ * Find the desired csum for range [logical, logical + sectorsize), and store
+ * the csum into @csum.
+ *
+ * The search source is sctx->csum_list, which is a pre-populated list
+ * storing bytenr ordered csum ranges.  We're reponsible to cleanup any range
+ * that is before @logical.
+ *
+ * Return 0 if there is no csum for the range.
+ * Return 1 if there is csum for the range and copied to @csum.
+ */
 static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
 {
-	struct btrfs_ordered_sum *sum = NULL;
+	bool found = false;
-	unsigned long index;
-	unsigned long num_sectors;
 
 	while (!list_empty(&sctx->csum_list)) {
+		struct btrfs_ordered_sum *sum = NULL;
+		unsigned long index;
+		unsigned long num_sectors;
+
 		sum = list_first_entry(&sctx->csum_list,
 				       struct btrfs_ordered_sum, list);
+		/* The current csum range is beyond our range, no csum found */
 		if (sum->bytenr > logical)
-			return 0;
-		if (sum->bytenr + sum->len > logical)
 			break;
 
-		++sctx->stat.csum_discards;
+		/*
-		list_del(&sum->list);
+		 * The current sum is before our bytenr, since scrub is always
-		kfree(sum);
+		 * done in bytenr order, the csum will never be used anymore,
-		sum = NULL;
+		 * clean it up so that later calls won't bother with the range,
+		 * and continue search the next range.
+		 */
+		if (sum->bytenr + sum->len <= logical) {
+			drop_csum_range(sctx, sum);
+			continue;
+		}
+
+		/* Now the csum range covers our bytenr, copy the csum */
+		found = true;
+		index = (logical - sum->bytenr) >> sctx->fs_info->sectorsize_bits;
+		num_sectors = sum->len >> sctx->fs_info->sectorsize_bits;
+
+		memcpy(csum, sum->sums + index * sctx->fs_info->csum_size,
+		       sctx->fs_info->csum_size);
+
+		/* Cleanup the range if we're at the end of the csum range */
+		if (index == num_sectors - 1)
+			drop_csum_range(sctx, sum);
+		break;
 	}
-	if (!sum)
+	if (!found)
 		return 0;
-
-	index = div_u64(logical - sum->bytenr, sctx->fs_info->sectorsize);
-	ASSERT(index < UINT_MAX);
-
-	num_sectors = sum->len / sctx->fs_info->sectorsize;
-	memcpy(csum, sum->sums + index * sctx->csum_size, sctx->csum_size);
-	if (index == num_sectors - 1) {
-		list_del(&sum->list);
-		kfree(sum);
-	}
 	return 1;
 }
 
 /* scrub extent tries to collect up to 64 kB for each bio */
 static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
-			u64 logical, u64 len,
+			u64 logical, u32 len,
 			u64 physical, struct btrfs_device *dev, u64 flags,
 			u64 gen, int mirror_num, u64 physical_for_dev_replace)
 {
@@ -2432,7 +2474,7 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 	}
 
 	while (len) {
-		u64 l = min_t(u64, len, blocksize);
+		u32 l = min(len, blocksize);
 		int have_csum = 0;
 
 		if (flags & BTRFS_EXTENT_FLAG_DATA) {
@@ -2442,7 +2484,7 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 				++sctx->stat.no_csum;
 		}
 		ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen,
-				  mirror_num, have_csum ? csum : NULL, 0,
+				  mirror_num, have_csum ? csum : NULL,
 				  physical_for_dev_replace);
 		if (ret)
 			return ret;
@@ -2455,14 +2497,17 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 }
 
 static int scrub_pages_for_parity(struct scrub_parity *sparity,
-				  u64 logical, u64 len,
+				  u64 logical, u32 len,
 				  u64 physical, struct btrfs_device *dev,
 				  u64 flags, u64 gen, int mirror_num, u8 *csum)
 {
 	struct scrub_ctx *sctx = sparity->sctx;
 	struct scrub_block *sblock;
+	const u32 sectorsize = sctx->fs_info->sectorsize;
 	int index;
 
+	ASSERT(IS_ALIGNED(len, sectorsize));
+
 	sblock = kzalloc(sizeof(*sblock), GFP_KERNEL);
 	if (!sblock) {
 		spin_lock(&sctx->stat_lock);
@@ -2481,7 +2526,6 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 
 	for (index = 0; len > 0; index++) {
 		struct scrub_page *spage;
-		u64 l = min_t(u64, len, PAGE_SIZE);
 
 		spage = kzalloc(sizeof(*spage), GFP_KERNEL);
 		if (!spage) {
@@ -2508,7 +2552,7 @@ leave_nomem:
 		spage->mirror_num = mirror_num;
 		if (csum) {
 			spage->have_csum = 1;
-			memcpy(spage->csum, csum, sctx->csum_size);
+			memcpy(spage->csum, csum, sctx->fs_info->csum_size);
 		} else {
 			spage->have_csum = 0;
 		}
@@ -2516,9 +2560,12 @@ leave_nomem:
 		spage->page = alloc_page(GFP_KERNEL);
 		if (!spage->page)
 			goto leave_nomem;
-		len -= l;
+
-		logical += l;
+
-		physical += l;
+		/* Iterate over the stripe range in sectorsize steps */
+		len -= sectorsize;
+		logical += sectorsize;
+		physical += sectorsize;
 	}
 
 	WARN_ON(sblock->page_count == 0);
@@ -2539,7 +2586,7 @@ leave_nomem:
 }
 
 static int scrub_extent_for_parity(struct scrub_parity *sparity,
-				   u64 logical, u64 len,
+				   u64 logical, u32 len,
 				   u64 physical, struct btrfs_device *dev,
 				   u64 flags, u64 gen, int mirror_num)
 {
@@ -2563,7 +2610,7 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
 	}
 
 	while (len) {
-		u64 l = min_t(u64, len, blocksize);
+		u32 l = min(len, blocksize);
 		int have_csum = 0;
 
 		if (flags & BTRFS_EXTENT_FLAG_DATA) {
@@ -2767,7 +2814,8 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	u64 generation;
 	u64 extent_logical;
 	u64 extent_physical;
-	u64 extent_len;
+	/* Check the comment in scrub_stripe() for why u32 is enough here */
+	u32 extent_len;
 	u64 mapped_length;
 	struct btrfs_device *extent_dev;
 	struct scrub_parity *sparity;
@@ -2776,7 +2824,8 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	int extent_mirror_num;
 	int stop_loop = 0;
 
-	nsectors = div_u64(map->stripe_len, fs_info->sectorsize);
+	ASSERT(map->stripe_len <= U32_MAX);
+	nsectors = map->stripe_len >> fs_info->sectorsize_bits;
 	bitmap_len = scrub_calc_parity_bitmap_len(nsectors);
 	sparity = kzalloc(sizeof(struct scrub_parity) + 2 * bitmap_len,
 			  GFP_NOFS);
@@ -2787,6 +2836,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 		return -ENOMEM;
 	}
 
+	ASSERT(map->stripe_len <= U32_MAX);
 	sparity->stripe_len = map->stripe_len;
 	sparity->nsectors = nsectors;
 	sparity->sctx = sctx;
@@ -2881,6 +2931,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 			}
 again:
 			extent_logical = key.objectid;
+			ASSERT(bytes <= U32_MAX);
 			extent_len = bytes;
 
 			if (extent_logical < logic_start) {
@@ -2959,9 +3010,11 @@ next:
 		logic_start += map->stripe_len;
 	}
 out:
-	if (ret < 0)
+	if (ret < 0) {
+		ASSERT(logic_end - logic_start <= U32_MAX);
 		scrub_parity_mark_sectors_error(sparity, logic_start,
 						logic_end - logic_start);
+	}
 	scrub_parity_put(sparity);
 	scrub_submit(sctx);
 	mutex_lock(&sctx->wr_lock);
@@ -3003,7 +3056,11 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	u64 offset;
 	u64 extent_logical;
 	u64 extent_physical;
-	u64 extent_len;
+	/*
+	 * Unlike chunk length, extent length should never go beyond
+	 * BTRFS_MAX_EXTENT_SIZE, thus u32 is enough here.
+	 */
+	u32 extent_len;
 	u64 stripe_logical;
 	u64 stripe_end;
 	struct btrfs_device *extent_dev;
@@ -3084,17 +3141,21 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 	key_end.offset = (u64)-1;
 	reada1 = btrfs_reada_add(root, &key, &key_end);
 
-	key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+	if (cache->flags & BTRFS_BLOCK_GROUP_DATA) {
-	key.type = BTRFS_EXTENT_CSUM_KEY;
+		key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
-	key.offset = logical;
+		key.type = BTRFS_EXTENT_CSUM_KEY;
-	key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
+		key.offset = logical;
-	key_end.type = BTRFS_EXTENT_CSUM_KEY;
+		key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
-	key_end.offset = logic_end;
+		key_end.type = BTRFS_EXTENT_CSUM_KEY;
-	reada2 = btrfs_reada_add(csum_root, &key, &key_end);
+		key_end.offset = logic_end;
+		reada2 = btrfs_reada_add(csum_root, &key, &key_end);
+	} else {
+		reada2 = NULL;
+	}
 
 	if (!IS_ERR(reada1))
 		btrfs_reada_wait(reada1);
-	if (!IS_ERR(reada2))
+	if (!IS_ERR_OR_NULL(reada2))
 		btrfs_reada_wait(reada2);
 
 
@@ -3248,6 +3309,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 
 again:
 			extent_logical = key.objectid;
+			ASSERT(bytes <= U32_MAX);
 			extent_len = bytes;
 
 			/*
@@ -3704,10 +3766,12 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >
 		    scrub_dev->commit_total_bytes)
 			break;
+		if (!btrfs_check_super_location(scrub_dev, bytenr))
+			continue;
 
 		ret = scrub_pages(sctx, bytenr, BTRFS_SUPER_INFO_SIZE, bytenr,
 				  scrub_dev, BTRFS_EXTENT_FLAG_SUPER, gen, i,
-				  NULL, 1, bytenr);
+				  NULL, bytenr);
 		if (ret)
 			return ret;
 	}
@@ -3821,14 +3885,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		return -EINVAL;
 	}
 
-	if (fs_info->sectorsize != PAGE_SIZE) {
-		/* not supported for data w/o checksums */
-		btrfs_err_rl(fs_info,
-			   "scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails",
-		       fs_info->sectorsize, PAGE_SIZE);
-		return -EINVAL;
-	}
-
 	if (fs_info->nodesize >
 	    PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK ||
 	    fs_info->sectorsize > PAGE_SIZE * SCRUB_MAX_PAGES_PER_BLOCK) {
@@ -3855,7 +3911,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 		goto out_free_ctx;
 
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
+	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
 	if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) &&
 		     !is_dev_replace)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
@@ -4032,7 +4088,7 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
 	struct scrub_ctx *sctx = NULL;
 
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
+	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
 	if (dev)
 		sctx = dev->scrub_ctx;
 	if (sctx)
@@ -4043,7 +4099,7 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
 }
 
 static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
-			       u64 extent_logical, u64 extent_len,
+			       u64 extent_logical, u32 extent_len,
 			       u64 *extent_physical,
 			       struct btrfs_device **extent_dev,
 			       int *extent_mirror_num)

fs/btrfs/send.c

@@ -2410,7 +2410,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 			    sctx->send_root->root_item.uuid);
 
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_CTRANSID,
-		    le64_to_cpu(sctx->send_root->root_item.ctransid));
+		    btrfs_root_ctransid(&sctx->send_root->root_item));
 	if (parent_root) {
 		if (!btrfs_is_empty_uuid(parent_root->root_item.received_uuid))
 			TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
@@ -2419,7 +2419,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
 			TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
 				     parent_root->root_item.uuid);
 		TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
-			    le64_to_cpu(sctx->parent_root->root_item.ctransid));
+			    btrfs_root_ctransid(&sctx->parent_root->root_item));
 	}
 
 	ret = send_cmd(sctx);
@@ -5101,7 +5101,7 @@ static int send_clone(struct send_ctx *sctx,
 		TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
 			     clone_root->root->root_item.uuid);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
-		    le64_to_cpu(clone_root->root->root_item.ctransid));
+		    btrfs_root_ctransid(&clone_root->root->root_item));
 	TLV_PUT_PATH(sctx, BTRFS_SEND_A_CLONE_PATH, p);
 	TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_OFFSET,
 			clone_root->offset);

fs/btrfs/struct-funcs.c

@@ -57,8 +57,9 @@ u##bits btrfs_get_token_##bits(struct btrfs_map_token *token,		\
 			       const void *ptr, unsigned long off)	\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = member_offset >> PAGE_SHIFT;		\
+	const unsigned long idx = get_eb_page_index(member_offset);	\
-	const unsigned long oip = offset_in_page(member_offset);	\
+	const unsigned long oip = get_eb_offset_in_page(token->eb,	\
+							member_offset);	\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = PAGE_SIZE - oip;				\
@@ -85,8 +86,8 @@ u##bits btrfs_get_##bits(const struct extent_buffer *eb,		\
 			 const void *ptr, unsigned long off)		\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long oip = offset_in_page(member_offset);	\
+	const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \
-	const unsigned long idx = member_offset >> PAGE_SHIFT;		\
+	const unsigned long idx = get_eb_page_index(member_offset);	\
 	char *kaddr = page_address(eb->pages[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = PAGE_SIZE - oip;				\
@@ -106,8 +107,9 @@ void btrfs_set_token_##bits(struct btrfs_map_token *token,		\
 			    u##bits val)				\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long idx = member_offset >> PAGE_SHIFT;		\
+	const unsigned long idx = get_eb_page_index(member_offset);	\
-	const unsigned long oip = offset_in_page(member_offset);	\
+	const unsigned long oip = get_eb_offset_in_page(token->eb,	\
+							member_offset);	\
 	const int size = sizeof(u##bits);				\
 	u8 lebytes[sizeof(u##bits)];					\
 	const int part = PAGE_SIZE - oip;				\
@@ -136,8 +138,8 @@ void btrfs_set_##bits(const struct extent_buffer *eb, void *ptr,	\
 		      unsigned long off, u##bits val)			\
 {									\
 	const unsigned long member_offset = (unsigned long)ptr + off;	\
-	const unsigned long oip = offset_in_page(member_offset);	\
+	const unsigned long oip = get_eb_offset_in_page(eb, member_offset); \
-	const unsigned long idx = member_offset >> PAGE_SHIFT;		\
+	const unsigned long idx = get_eb_page_index(member_offset);	\
 	char *kaddr = page_address(eb->pages[idx]);			\
 	const int size = sizeof(u##bits);				\
 	const int part = PAGE_SIZE - oip;				\

fs/btrfs/super.c

@@ -44,6 +44,7 @@
 #include "backref.h"
 #include "space-info.h"
 #include "sysfs.h"
+#include "zoned.h"
 #include "tests/btrfs-tests.h"
 #include "block-group.h"
 #include "discard.h"
@@ -240,9 +241,13 @@ void __cold btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, .
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (__ratelimit(ratelimit))
+	if (__ratelimit(ratelimit)) {
-		printk("%sBTRFS %s (device %s): %pV\n", lvl, type,
+		if (fs_info)
-			fs_info ? fs_info->sb->s_id : "<unknown>", &vaf);
+			printk("%sBTRFS %s (device %s): %pV\n", lvl, type,
+				fs_info->sb->s_id, &vaf);
+		else
+			printk("%sBTRFS %s: %pV\n", lvl, type, &vaf);
+	}
 
 	va_end(args);
 }
@@ -333,7 +338,6 @@ enum {
 	Opt_device,
 	Opt_fatal_errors,
 	Opt_flushoncommit, Opt_noflushoncommit,
-	Opt_inode_cache, Opt_noinode_cache,
 	Opt_max_inline,
 	Opt_barrier, Opt_nobarrier,
 	Opt_datacow, Opt_nodatacow,
@@ -360,9 +364,13 @@ enum {
 	Opt_rescue,
 	Opt_usebackuproot,
 	Opt_nologreplay,
+	Opt_ignorebadroots,
+	Opt_ignoredatacsums,
+	Opt_rescue_all,
 
 	/* Deprecated options */
 	Opt_recovery,
+	Opt_inode_cache, Opt_noinode_cache,
 
 	/* Debugging options */
 	Opt_check_integrity,
@@ -455,9 +463,25 @@ static const match_table_t tokens = {
 static const match_table_t rescue_tokens = {
 	{Opt_usebackuproot, "usebackuproot"},
 	{Opt_nologreplay, "nologreplay"},
+	{Opt_ignorebadroots, "ignorebadroots"},
+	{Opt_ignorebadroots, "ibadroots"},
+	{Opt_ignoredatacsums, "ignoredatacsums"},
+	{Opt_ignoredatacsums, "idatacsums"},
+	{Opt_rescue_all, "all"},
 	{Opt_err, NULL},
 };
 
+static bool check_ro_option(struct btrfs_fs_info *fs_info, unsigned long opt,
+			    const char *opt_name)
+{
+	if (fs_info->mount_opt & opt) {
+		btrfs_err(fs_info, "%s must be used with ro mount option",
+			  opt_name);
+		return true;
+	}
+	return false;
+}
+
 static int parse_rescue_options(struct btrfs_fs_info *info, const char *options)
 {
 	char *opts;
@@ -487,6 +511,23 @@ static int parse_rescue_options(struct btrfs_fs_info *info, const char *options)
 			btrfs_set_and_info(info, NOLOGREPLAY,
 					   "disabling log replay at mount time");
 			break;
+		case Opt_ignorebadroots:
+			btrfs_set_and_info(info, IGNOREBADROOTS,
+					   "ignoring bad roots");
+			break;
+		case Opt_ignoredatacsums:
+			btrfs_set_and_info(info, IGNOREDATACSUMS,
+					   "ignoring data csums");
+			break;
+		case Opt_rescue_all:
+			btrfs_info(info, "enabling all of the rescue options");
+			btrfs_set_and_info(info, IGNOREDATACSUMS,
+					   "ignoring data csums");
+			btrfs_set_and_info(info, IGNOREBADROOTS,
+					   "ignoring bad roots");
+			btrfs_set_and_info(info, NOLOGREPLAY,
+					   "disabling log replay at mount time");
+			break;
 		case Opt_err:
 			btrfs_info(info, "unrecognized rescue option '%s'", p);
 			ret = -EINVAL;
@@ -511,7 +552,6 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *p, *num;
-	u64 cache_gen;
 	int intarg;
 	int ret = 0;
 	char *compress_type;
@@ -521,11 +561,17 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	bool saved_compress_force;
 	int no_compress = 0;
 
-	cache_gen = btrfs_super_cache_generation(info->super_copy);
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
 		btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
-	else if (cache_gen)
+	else if (btrfs_free_space_cache_v1_active(info)) {
-		btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+		if (btrfs_is_zoned(info)) {
+			btrfs_info(info,
+			"zoned: clearing existing space cache");
+			btrfs_set_super_cache_generation(info->super_copy, 0);
+		} else {
+			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+		}
+	}
 
 	/*
 	 * Even the options are empty, we still need to do extra check
@@ -832,14 +878,9 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			}
 			break;
 		case Opt_inode_cache:
-			btrfs_warn(info,
-	"the 'inode_cache' option is deprecated and will have no effect from 5.11");
-			btrfs_set_pending_and_info(info, INODE_MAP_CACHE,
-					   "enabling inode map caching");
-			break;
 		case Opt_noinode_cache:
-			btrfs_clear_pending_and_info(info, INODE_MAP_CACHE,
+			btrfs_warn(info,
-					     "disabling inode map caching");
+	"the 'inode_cache' option is deprecated and has no effect since 5.11");
 			break;
 		case Opt_clear_cache:
 			btrfs_set_and_info(info, CLEAR_CACHE,
@@ -968,14 +1009,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		}
 	}
 check:
-	/*
+	/* We're read-only, don't have to check. */
-	 * Extra check for current option against current flag
+	if (new_flags & SB_RDONLY)
-	 */
+		goto out;
-	if (btrfs_test_opt(info, NOLOGREPLAY) && !(new_flags & SB_RDONLY)) {
+
-		btrfs_err(info,
+	if (check_ro_option(info, BTRFS_MOUNT_NOLOGREPLAY, "nologreplay") ||
-			  "nologreplay must be used with ro mount option");
+	    check_ro_option(info, BTRFS_MOUNT_IGNOREBADROOTS, "ignorebadroots") ||
+	    check_ro_option(info, BTRFS_MOUNT_IGNOREDATACSUMS, "ignoredatacsums"))
 		ret = -EINVAL;
-	}
 out:
 	if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE) &&
 	    !btrfs_test_opt(info, FREE_SPACE_TREE) &&
@@ -984,6 +1025,8 @@ out:
 		ret = -EINVAL;
 
 	}
+	if (!ret)
+		ret = btrfs_check_mountopts_zoned(info);
 	if (!ret && btrfs_test_opt(info, SPACE_CACHE))
 		btrfs_info(info, "disk space caching is enabled");
 	if (!ret && btrfs_test_opt(info, FREE_SPACE_TREE))
@@ -1127,7 +1170,6 @@ char *btrfs_get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
 		ret = -ENOMEM;
 		goto err;
 	}
-	path->leave_spinning = 1;
 
 	name = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!name) {
@@ -1256,7 +1298,6 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
-	path->leave_spinning = 1;
 
 	/*
 	 * Find the "default" dir item which points to the root item that we
@@ -1383,11 +1424,18 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	return btrfs_commit_transaction(trans);
 }
 
+static void print_rescue_option(struct seq_file *seq, const char *s, bool *printed)
+{
+	seq_printf(seq, "%s%s", (*printed) ? ":" : ",rescue=", s);
+	*printed = true;
+}
+
 static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 {
 	struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
 	const char *compress_type;
 	const char *subvol_name;
+	bool printed = false;
 
 	if (btrfs_test_opt(info, DEGRADED))
 		seq_puts(seq, ",degraded");
@@ -1420,7 +1468,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 	if (btrfs_test_opt(info, NOTREELOG))
 		seq_puts(seq, ",notreelog");
 	if (btrfs_test_opt(info, NOLOGREPLAY))
-		seq_puts(seq, ",rescue=nologreplay");
+		print_rescue_option(seq, "nologreplay", &printed);
+	if (btrfs_test_opt(info, USEBACKUPROOT))
+		print_rescue_option(seq, "usebackuproot", &printed);
+	if (btrfs_test_opt(info, IGNOREBADROOTS))
+		print_rescue_option(seq, "ignorebadroots", &printed);
+	if (btrfs_test_opt(info, IGNOREDATACSUMS))
+		print_rescue_option(seq, "ignoredatacsums", &printed);
 	if (btrfs_test_opt(info, FLUSHONCOMMIT))
 		seq_puts(seq, ",flushoncommit");
 	if (btrfs_test_opt(info, DISCARD_SYNC))
@@ -1429,9 +1483,9 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",discard=async");
 	if (!(info->sb->s_flags & SB_POSIXACL))
 		seq_puts(seq, ",noacl");
-	if (btrfs_test_opt(info, SPACE_CACHE))
+	if (btrfs_free_space_cache_v1_active(info))
 		seq_puts(seq, ",space_cache");
-	else if (btrfs_test_opt(info, FREE_SPACE_TREE))
+	else if (btrfs_fs_compat_ro(info, FREE_SPACE_TREE))
 		seq_puts(seq, ",space_cache=v2");
 	else
 		seq_puts(seq, ",nospace_cache");
@@ -1445,8 +1499,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",enospc_debug");
 	if (btrfs_test_opt(info, AUTO_DEFRAG))
 		seq_puts(seq, ",autodefrag");
-	if (btrfs_test_opt(info, INODE_MAP_CACHE))
-		seq_puts(seq, ",inode_cache");
 	if (btrfs_test_opt(info, SKIP_BALANCE))
 		seq_puts(seq, ",skip_balance");
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
@@ -1810,6 +1862,8 @@ static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
 static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
 					 unsigned long old_opts)
 {
+	const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE);
+
 	/*
 	 * We need to cleanup all defragable inodes if the autodefragment is
 	 * close or the filesystem is read only.
@@ -1826,12 +1880,15 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
 	else if (btrfs_raw_test_opt(old_opts, DISCARD_ASYNC) &&
 		 !btrfs_test_opt(fs_info, DISCARD_ASYNC))
 		btrfs_discard_cleanup(fs_info);
+
+	/* If we toggled space cache */
+	if (cache_opt != btrfs_free_space_cache_v1_active(fs_info))
+		btrfs_set_free_space_cache_v1_active(fs_info, cache_opt);
 }
 
 static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
-	struct btrfs_root *root = fs_info->tree_root;
 	unsigned old_flags = sb->s_flags;
 	unsigned long old_opts = fs_info->mount_opt;
 	unsigned long old_compress_type = fs_info->compress_type;
@@ -1862,6 +1919,22 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	btrfs_resize_thread_pool(fs_info,
 		fs_info->thread_pool_size, old_thread_pool_size);
 
+	if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) !=
+	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+	    (!sb_rdonly(sb) || (*flags & SB_RDONLY))) {
+		btrfs_warn(fs_info,
+		"remount supports changing free space tree only from ro to rw");
+		/* Make sure free space cache options match the state on disk */
+		if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+			btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+			btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
+		}
+		if (btrfs_free_space_cache_v1_active(fs_info)) {
+			btrfs_clear_opt(fs_info->mount_opt, FREE_SPACE_TREE);
+			btrfs_set_opt(fs_info->mount_opt, SPACE_CACHE);
+		}
+	}
+
 	if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
 		goto out;
 
@@ -1924,39 +1997,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 		}
 
-		ret = btrfs_cleanup_fs_roots(fs_info);
+		/*
+		 * NOTE: when remounting with a change that does writes, don't
+		 * put it anywhere above this point, as we are not sure to be
+		 * safe to write until we pass the above checks.
+		 */
+		ret = btrfs_start_pre_rw_mount(fs_info);
 		if (ret)
 			goto restore;
 
-		/* recover relocation */
-		mutex_lock(&fs_info->cleaner_mutex);
-		ret = btrfs_recover_relocation(root);
-		mutex_unlock(&fs_info->cleaner_mutex);
-		if (ret)
-			goto restore;
-
-		ret = btrfs_resume_balance_async(fs_info);
-		if (ret)
-			goto restore;
-
-		ret = btrfs_resume_dev_replace_async(fs_info);
-		if (ret) {
-			btrfs_warn(fs_info, "failed to resume dev_replace");
-			goto restore;
-		}
-
-		btrfs_qgroup_rescan_resume(fs_info);
-
-		if (!fs_info->uuid_root) {
-			btrfs_info(fs_info, "creating UUID tree");
-			ret = btrfs_create_uuid_tree(fs_info);
-			if (ret) {
-				btrfs_warn(fs_info,
-					   "failed to create the UUID tree %d",
-					   ret);
-				goto restore;
-			}
-		}
 		sb->s_flags &= ~SB_RDONLY;
 
 		set_bit(BTRFS_FS_OPEN, &fs_info->flags);
@@ -1970,6 +2019,7 @@ out:
 
 	wake_up_process(fs_info->transaction_kthread);
 	btrfs_remount_cleanup(fs_info, old_opts);
+	btrfs_clear_oneshot_options(fs_info);
 	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
 
 	return 0;
@@ -2156,7 +2206,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	u64 total_used = 0;
 	u64 total_free_data = 0;
 	u64 total_free_meta = 0;
-	int bits = dentry->d_sb->s_blocksize_bits;
+	u32 bits = fs_info->sectorsize_bits;
 	__be32 *fsid = (__be32 *)fs_info->fs_devices->fsid;
 	unsigned factor = 1;
 	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
@@ -2462,6 +2512,11 @@ static void __init btrfs_print_mod_info(void)
 #endif
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 			", ref-verify=on"
+#endif
+#ifdef CONFIG_BLK_DEV_ZONED
+			", zoned=yes"
+#else
+			", zoned=no"
 #endif
 			;
 	pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options);
@@ -2523,8 +2578,6 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		goto free_end_io_wq;
 
-	btrfs_init_lockdep();
-
 	btrfs_print_mod_info();
 
 	err = btrfs_run_sanity_tests();

fs/btrfs/sysfs.c

@@ -263,6 +263,10 @@ BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
 BTRFS_FEAT_ATTR_INCOMPAT(metadata_uuid, METADATA_UUID);
 BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
 BTRFS_FEAT_ATTR_INCOMPAT(raid1c34, RAID1C34);
+/* Remove once support for zoned allocation is feature complete */
+#ifdef CONFIG_BTRFS_DEBUG
+BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED);
+#endif
 
 static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -278,6 +282,9 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
 	BTRFS_FEAT_ATTR_PTR(metadata_uuid),
 	BTRFS_FEAT_ATTR_PTR(free_space_tree),
 	BTRFS_FEAT_ATTR_PTR(raid1c34),
+#ifdef CONFIG_BTRFS_DEBUG
+	BTRFS_FEAT_ATTR_PTR(zoned),
+#endif
 	NULL
 };
 
@@ -329,10 +336,35 @@ static ssize_t send_stream_version_show(struct kobject *kobj,
 }
 BTRFS_ATTR(static_feature, send_stream_version, send_stream_version_show);
 
+static const char *rescue_opts[] = {
+	"usebackuproot",
+	"nologreplay",
+	"ignorebadroots",
+	"ignoredatacsums",
+	"all",
+};
+
+static ssize_t supported_rescue_options_show(struct kobject *kobj,
+					     struct kobj_attribute *a,
+					     char *buf)
+{
+	ssize_t ret = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(rescue_opts); i++)
+		ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+				 (i ? " " : ""), rescue_opts[i]);
+	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+	return ret;
+}
+BTRFS_ATTR(static_feature, supported_rescue_options,
+	   supported_rescue_options_show);
+
 static struct attribute *btrfs_supported_static_feature_attrs[] = {
 	BTRFS_ATTR_PTR(static_feature, rmdir_subvol),
 	BTRFS_ATTR_PTR(static_feature, supported_checksums),
 	BTRFS_ATTR_PTR(static_feature, send_stream_version),
+	BTRFS_ATTR_PTR(static_feature, supported_rescue_options),
 	NULL
 };
 
@@ -433,7 +465,8 @@ static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj,
 		return -EINVAL;
 
 	WRITE_ONCE(discard_ctl->iops_limit, iops_limit);
-
+	btrfs_discard_calc_delay(discard_ctl);
+	btrfs_discard_schedule_work(discard_ctl, true);
 	return len;
 }
 BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show,
@@ -463,7 +496,7 @@ static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj,
 		return -EINVAL;
 
 	WRITE_ONCE(discard_ctl->kbps_limit, kbps_limit);
-
+	btrfs_discard_schedule_work(discard_ctl, true);
 	return len;
 }
 BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show,
@@ -854,6 +887,82 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj,
 }
 BTRFS_ATTR(, exclusive_operation, btrfs_exclusive_operation_show);
 
+static ssize_t btrfs_generation_show(struct kobject *kobj,
+				     struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+
+	return scnprintf(buf, PAGE_SIZE, "%llu\n", fs_info->generation);
+}
+BTRFS_ATTR(, generation, btrfs_generation_show);
+
+/*
+ * Look for an exact string @string in @buffer with possible leading or
+ * trailing whitespace
+ */
+static bool strmatch(const char *buffer, const char *string)
+{
+	const size_t len = strlen(string);
+
+	/* Skip leading whitespace */
+	buffer = skip_spaces(buffer);
+
+	/* Match entire string, check if the rest is whitespace or empty */
+	if (strncmp(string, buffer, len) == 0 &&
+	    strlen(skip_spaces(buffer + len)) == 0)
+		return true;
+
+	return false;
+}
+
+static const char * const btrfs_read_policy_name[] = { "pid" };
+
+static ssize_t btrfs_read_policy_show(struct kobject *kobj,
+				      struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	ssize_t ret = 0;
+	int i;
+
+	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
+		if (fs_devices->read_policy == i)
+			ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s[%s]",
+					 (ret == 0 ? "" : " "),
+					 btrfs_read_policy_name[i]);
+		else
+			ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s",
+					 (ret == 0 ? "" : " "),
+					 btrfs_read_policy_name[i]);
+	}
+
+	ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n");
+
+	return ret;
+}
+
+static ssize_t btrfs_read_policy_store(struct kobject *kobj,
+				       struct kobj_attribute *a,
+				       const char *buf, size_t len)
+{
+	struct btrfs_fs_devices *fs_devices = to_fs_devs(kobj);
+	int i;
+
+	for (i = 0; i < BTRFS_NR_READ_POLICY; i++) {
+		if (strmatch(buf, btrfs_read_policy_name[i])) {
+			if (i != fs_devices->read_policy) {
+				fs_devices->read_policy = i;
+				btrfs_info(fs_devices->fs_info,
+					   "read policy set to '%s'",
+					   btrfs_read_policy_name[i]);
+			}
+			return len;
+		}
+	}
+
+	return -EINVAL;
+}
+BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, label),
 	BTRFS_ATTR_PTR(, nodesize),
@@ -863,6 +972,8 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, metadata_uuid),
 	BTRFS_ATTR_PTR(, checksum),
 	BTRFS_ATTR_PTR(, exclusive_operation),
+	BTRFS_ATTR_PTR(, generation),
+	BTRFS_ATTR_PTR(, read_policy),
 	NULL,
 };
 
@@ -1207,7 +1318,7 @@ static const char *alloc_name(u64 flags)
 	default:
 		WARN_ON(1);
 		return "invalid-combination";
-	};
+	}
 }
 
 /*

fs/btrfs/tests/btrfs-tests.c

@@ -134,6 +134,7 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize)
 
 	fs_info->nodesize = nodesize;
 	fs_info->sectorsize = sectorsize;
+	fs_info->sectorsize_bits = ilog2(sectorsize);
 	set_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
 
 	test_mnt->mnt_sb->s_fs_info = fs_info;
@@ -224,7 +225,7 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info,
 	INIT_LIST_HEAD(&cache->list);
 	INIT_LIST_HEAD(&cache->cluster_list);
 	INIT_LIST_HEAD(&cache->bg_list);
-	btrfs_init_free_space_ctl(cache);
+	btrfs_init_free_space_ctl(cache, cache->free_space_ctl);
 	mutex_init(&cache->free_space_lock);
 
 	return cache;

fs/btrfs/tests/extent-io-tests.c

@@ -379,54 +379,50 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 static int test_eb_bitmaps(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_fs_info *fs_info;
-	unsigned long len;
 	unsigned long *bitmap = NULL;
 	struct extent_buffer *eb = NULL;
 	int ret;
 
 	test_msg("running extent buffer bitmap tests");
 
-	/*
+	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
-	 * In ppc64, sectorsize can be 64K, thus 4 * 64K will be larger than
-	 * BTRFS_MAX_METADATA_BLOCKSIZE.
-	 */
-	len = (sectorsize < BTRFS_MAX_METADATA_BLOCKSIZE)
-		? sectorsize * 4 : sectorsize;
-
-	fs_info = btrfs_alloc_dummy_fs_info(len, len);
 	if (!fs_info) {
 		test_std_err(TEST_ALLOC_FS_INFO);
 		return -ENOMEM;
 	}
 
-	bitmap = kmalloc(len, GFP_KERNEL);
+	bitmap = kmalloc(nodesize, GFP_KERNEL);
 	if (!bitmap) {
 		test_err("couldn't allocate test bitmap");
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	eb = __alloc_dummy_extent_buffer(fs_info, 0, len);
+	eb = __alloc_dummy_extent_buffer(fs_info, 0, nodesize);
 	if (!eb) {
 		test_std_err(TEST_ALLOC_ROOT);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = __test_eb_bitmaps(bitmap, eb, len);
+	ret = __test_eb_bitmaps(bitmap, eb, nodesize);
 	if (ret)
 		goto out;
 
-	/* Do it over again with an extent buffer which isn't page-aligned. */
 	free_extent_buffer(eb);
-	eb = __alloc_dummy_extent_buffer(fs_info, nodesize / 2, len);
+
+	/*
+	 * Test again for case where the tree block is sectorsize aligned but
+	 * not nodesize aligned.
+	 */
+	eb = __alloc_dummy_extent_buffer(fs_info, sectorsize, nodesize);
 	if (!eb) {
 		test_std_err(TEST_ALLOC_ROOT);
 		ret = -ENOMEM;
 		goto out;
 	}
 
-	ret = __test_eb_bitmaps(bitmap, eb, len);
+	ret = __test_eb_bitmaps(bitmap, eb, nodesize);
 out:
 	free_extent_buffer(eb);
 	kfree(bitmap);

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

@@ -399,7 +399,6 @@ test_steal_space_from_bitmap_to_extent(struct btrfs_block_group *cache,
 	u64 offset;
 	u64 max_extent_size;
 	const struct btrfs_free_space_op test_free_space_ops = {
-		.recalc_thresholds = cache->free_space_ctl->op->recalc_thresholds,
 		.use_bitmap = test_use_bitmap,
 	};
 	const struct btrfs_free_space_op *orig_free_space_ops;

fs/btrfs/tests/qgroup-tests.c

@@ -36,7 +36,6 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
 		return -ENOMEM;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(&trans, root, path, &ins, size);
 	if (ret) {
 		test_err("couldn't insert ref %d", ret);
@@ -86,7 +85,6 @@ static int add_tree_ref(struct btrfs_root *root, u64 bytenr, u64 num_bytes,
 		return -ENOMEM;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
 	if (ret) {
 		test_err("couldn't find extent ref");
@@ -135,7 +133,6 @@ static int remove_extent_item(struct btrfs_root *root, u64 bytenr,
 		test_std_err(TEST_ALLOC_ROOT);
 		return -ENOMEM;
 	}
-	path->leave_spinning = 1;
 
 	ret = btrfs_search_slot(&trans, root, &key, path, -1, 1);
 	if (ret) {
@@ -170,7 +167,6 @@ static int remove_extent_ref(struct btrfs_root *root, u64 bytenr,
 		return -ENOMEM;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(&trans, root, &key, path, 0, 1);
 	if (ret) {
 		test_err("couldn't find extent ref");

fs/btrfs/transaction.c

@@ -16,7 +16,6 @@
 #include "transaction.h"
 #include "locking.h"
 #include "tree-log.h"
-#include "inode-map.h"
 #include "volumes.h"
 #include "dev-replace.h"
 #include "qgroup.h"
@@ -155,6 +154,7 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root, *tmp;
+	struct btrfs_caching_control *caching_ctl, *next;
 
 	down_write(&fs_info->commit_root_sem);
 	list_for_each_entry_safe(root, tmp, &cur_trans->switch_commits,
@@ -162,8 +162,6 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
 		list_del_init(&root->dirty_list);
 		free_extent_buffer(root->commit_root);
 		root->commit_root = btrfs_root_node(root);
-		if (is_fstree(root->root_key.objectid))
-			btrfs_unpin_free_ino(root);
 		extent_io_tree_release(&root->dirty_log_pages);
 		btrfs_qgroup_clean_swapped_blocks(root);
 	}
@@ -180,6 +178,47 @@ static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
 		spin_lock(&cur_trans->dropped_roots_lock);
 	}
 	spin_unlock(&cur_trans->dropped_roots_lock);
+
+	/*
+	 * We have to update the last_byte_to_unpin under the commit_root_sem,
+	 * at the same time we swap out the commit roots.
+	 *
+	 * This is because we must have a real view of the last spot the caching
+	 * kthreads were while caching.  Consider the following views of the
+	 * extent tree for a block group
+	 *
+	 * commit root
+	 * +----+----+----+----+----+----+----+
+	 * |\\\\|    |\\\\|\\\\|    |\\\\|\\\\|
+	 * +----+----+----+----+----+----+----+
+	 * 0    1    2    3    4    5    6    7
+	 *
+	 * new commit root
+	 * +----+----+----+----+----+----+----+
+	 * |    |    |    |\\\\|    |    |\\\\|
+	 * +----+----+----+----+----+----+----+
+	 * 0    1    2    3    4    5    6    7
+	 *
+	 * If the cache_ctl->progress was at 3, then we are only allowed to
+	 * unpin [0,1) and [2,3], because the caching thread has already
+	 * processed those extents.  We are not allowed to unpin [5,6), because
+	 * the caching thread will re-start it's search from 3, and thus find
+	 * the hole from [4,6) to add to the free space cache.
+	 */
+	spin_lock(&fs_info->block_group_cache_lock);
+	list_for_each_entry_safe(caching_ctl, next,
+				 &fs_info->caching_block_groups, list) {
+		struct btrfs_block_group *cache = caching_ctl->block_group;
+
+		if (btrfs_block_group_done(cache)) {
+			cache->last_byte_to_unpin = (u64)-1;
+			list_del_init(&caching_ctl->list);
+			btrfs_put_caching_control(caching_ctl);
+		} else {
+			cache->last_byte_to_unpin = caching_ctl->progress;
+		}
+	}
+	spin_unlock(&fs_info->block_group_cache_lock);
 	up_write(&fs_info->commit_root_sem);
 }
 
@@ -856,24 +895,24 @@ void btrfs_throttle(struct btrfs_fs_info *fs_info)
 	wait_current_trans(fs_info);
 }
 
-static int should_end_transaction(struct btrfs_trans_handle *trans)
+static bool should_end_transaction(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 
 	if (btrfs_check_space_for_delayed_refs(fs_info))
-		return 1;
+		return true;
 
 	return !!btrfs_block_rsv_check(&fs_info->global_block_rsv, 5);
 }
 
-int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
+bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
 	    cur_trans->delayed_refs.flushing)
-		return 1;
+		return true;
 
 	return should_end_transaction(trans);
 }
@@ -1300,8 +1339,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
 			btrfs_free_log(trans, root);
 			btrfs_update_reloc_root(trans, root);
 
-			btrfs_save_ino_cache(root, trans);
-
 			/* see comments in should_cow_block() */
 			clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
 			smp_mb__after_atomic();
@@ -1598,8 +1635,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	btrfs_set_lock_blocking_write(old);
-
 	ret = btrfs_copy_root(trans, root, old, &tmp, objectid);
 	/* clean up in any case */
 	btrfs_tree_unlock(old);
@@ -1681,7 +1716,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 					 dentry->d_name.len * 2);
 	parent_inode->i_mtime = parent_inode->i_ctime =
 		current_time(parent_inode);
-	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
+	ret = btrfs_update_inode_fallback(trans, parent_root, BTRFS_I(parent_inode));
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
@@ -1761,6 +1796,8 @@ static void update_super_roots(struct btrfs_fs_info *fs_info)
 	super->root_level = root_item->level;
 	if (btrfs_test_opt(fs_info, SPACE_CACHE))
 		super->cache_generation = root_item->generation;
+	else if (test_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags))
+		super->cache_generation = 0;
 	if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
 		super->uuid_tree_generation = root_item->generation;
 }
@@ -1956,10 +1993,8 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
        }
 }
 
-static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
+static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-
 	/*
 	 * We use writeback_inodes_sb here because if we used
 	 * btrfs_start_delalloc_roots we would deadlock with fs freeze.
@@ -1969,50 +2004,15 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
 	 * from already being in a transaction and our join_transaction doesn't
 	 * have to re-take the fs freeze lock.
 	 */
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
 		writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
-	} else {
-		struct btrfs_pending_snapshot *pending;
-		struct list_head *head = &trans->transaction->pending_snapshots;
-
-		/*
-		 * Flush dellaloc for any root that is going to be snapshotted.
-		 * This is done to avoid a corrupted version of files, in the
-		 * snapshots, that had both buffered and direct IO writes (even
-		 * if they were done sequentially) due to an unordered update of
-		 * the inode's size on disk.
-		 */
-		list_for_each_entry(pending, head, list) {
-			int ret;
-
-			ret = btrfs_start_delalloc_snapshot(pending->root);
-			if (ret)
-				return ret;
-		}
-	}
 	return 0;
 }
 
-static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
+static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
-
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
 		btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
-	} else {
-		struct btrfs_pending_snapshot *pending;
-		struct list_head *head = &trans->transaction->pending_snapshots;
-
-		/*
-		 * Wait for any dellaloc that we started previously for the roots
-		 * that are going to be snapshotted. This is to avoid a corrupted
-		 * version of files in the snapshots that had both buffered and
-		 * direct IO writes (even if they were done sequentially).
-		 */
-		list_for_each_entry(pending, head, list)
-			btrfs_wait_ordered_extents(pending->root,
-						   U64_MAX, 0, U64_MAX);
-	}
 }
 
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
@@ -2150,7 +2150,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	extwriter_counter_dec(cur_trans, trans->type);
 
-	ret = btrfs_start_delalloc_flush(trans);
+	ret = btrfs_start_delalloc_flush(fs_info);
 	if (ret)
 		goto cleanup_transaction;
 
@@ -2166,7 +2166,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	if (ret)
 		goto cleanup_transaction;
 
-	btrfs_wait_delalloc_flush(trans);
+	btrfs_wait_delalloc_flush(fs_info);
 
 	/*
 	 * Wait for all ordered extents started by a fast fsync that joined this
@@ -2293,8 +2293,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		goto unlock_tree_log;
 	}
 
-	btrfs_prepare_extent_commit(fs_info);
-
 	cur_trans = fs_info->running_transaction;
 
 	btrfs_set_root_node(&fs_info->tree_root->root_item,
@@ -2435,10 +2433,6 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
 	btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid);
 
 	btrfs_kill_all_delayed_nodes(root);
-	if (root->ino_cache_inode) {
-		iput(root->ino_cache_inode);
-		root->ino_cache_inode = NULL;
-	}
 
 	if (btrfs_header_backref_rev(root->node) <
 			BTRFS_MIXED_BACKREF_REV)
@@ -2459,16 +2453,6 @@ void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info)
 	if (!prev)
 		return;
 
-	bit = 1 << BTRFS_PENDING_SET_INODE_MAP_CACHE;
-	if (prev & bit)
-		btrfs_set_opt(fs_info->mount_opt, INODE_MAP_CACHE);
-	prev &= ~bit;
-
-	bit = 1 << BTRFS_PENDING_CLEAR_INODE_MAP_CACHE;
-	if (prev & bit)
-		btrfs_clear_opt(fs_info->mount_opt, INODE_MAP_CACHE);
-	prev &= ~bit;
-
 	bit = 1 << BTRFS_PENDING_COMMIT;
 	if (prev & bit)
 		btrfs_debug(fs_info, "pending commit done");

fs/btrfs/transaction.h

@@ -112,7 +112,6 @@ struct btrfs_transaction {
 #define TRANS_EXTWRITERS	(__TRANS_START | __TRANS_ATTACH)
 
 #define BTRFS_SEND_TRANS_STUB	((void *)1)
-#define BTRFS_DIO_SYNC_STUB	((void *)2)
 
 struct btrfs_trans_handle {
 	u64 transid;
@@ -219,7 +218,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
 int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 				   int wait_for_unblock);
 int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
-int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
+bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
 void btrfs_throttle(struct btrfs_fs_info *fs_info);
 int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);

fs/btrfs/tree-defrag.c

@@ -52,7 +52,6 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
 		u32 nritems;
 
 		root_node = btrfs_lock_root_node(root);
-		btrfs_set_lock_blocking_write(root_node);
 		nritems = btrfs_header_nritems(root_node);
 		root->defrag_max.objectid = 0;
 		/* from above we know this is not a leaf */

fs/btrfs/tree-log.c

@@ -17,7 +17,6 @@
 #include "backref.h"
 #include "compression.h"
 #include "qgroup.h"
-#include "inode-map.h"
 #include "block-group.h"
 #include "space-info.h"
 
@@ -139,8 +138,25 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 			   struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_root *tree_root = fs_info->tree_root;
 	int ret = 0;
 
+	/*
+	 * First check if the log root tree was already created. If not, create
+	 * it before locking the root's log_mutex, just to keep lockdep happy.
+	 */
+	if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state)) {
+		mutex_lock(&tree_root->log_mutex);
+		if (!fs_info->log_root_tree) {
+			ret = btrfs_init_log_root_tree(trans, fs_info);
+			if (!ret)
+				set_bit(BTRFS_ROOT_HAS_LOG_TREE, &tree_root->state);
+		}
+		mutex_unlock(&tree_root->log_mutex);
+		if (ret)
+			return ret;
+	}
+
 	mutex_lock(&root->log_mutex);
 
 	if (root->log_root) {
@@ -156,13 +172,6 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 			set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
 		}
 	} else {
-		mutex_lock(&fs_info->tree_log_mutex);
-		if (!fs_info->log_root_tree)
-			ret = btrfs_init_log_root_tree(trans, fs_info);
-		mutex_unlock(&fs_info->tree_log_mutex);
-		if (ret)
-			goto out;
-
 		ret = btrfs_add_log_tree(trans, root);
 		if (ret)
 			goto out;
@@ -172,7 +181,6 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 		root->log_start_pid = current->pid;
 	}
 
-	atomic_inc(&root->log_batch);
 	atomic_inc(&root->log_writers);
 	if (ctx && !ctx->logging_new_name) {
 		int index = root->log_transid % 2;
@@ -576,6 +584,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				      struct extent_buffer *eb, int slot,
 				      struct btrfs_key *key)
 {
+	struct btrfs_drop_extents_args drop_args = { 0 };
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int found_type;
 	u64 extent_end;
@@ -653,7 +662,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	btrfs_release_path(path);
 
 	/* drop any overlapping extents */
-	ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1);
+	drop_args.start = start;
+	drop_args.end = extent_end;
+	drop_args.drop_cache = true;
+	ret = btrfs_drop_extents(trans, root, BTRFS_I(inode), &drop_args);
 	if (ret)
 		goto out;
 
@@ -828,9 +840,9 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	inode_add_bytes(inode, nbytes);
 update_inode:
-	ret = btrfs_update_inode(trans, root, inode);
+	btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 out:
 	if (inode)
 		iput(inode);
@@ -1529,7 +1541,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			if (ret)
 				goto out;
 
-			btrfs_update_inode(trans, root, inode);
+			btrfs_update_inode(trans, root, BTRFS_I(inode));
 		}
 
 		ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen;
@@ -1564,18 +1576,6 @@ out:
 	return ret;
 }
 
-static int insert_orphan_item(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root, u64 ino)
-{
-	int ret;
-
-	ret = btrfs_insert_orphan_item(trans, root, ino);
-	if (ret == -EEXIST)
-		ret = 0;
-
-	return ret;
-}
-
 static int count_inode_extrefs(struct btrfs_root *root,
 		struct btrfs_inode *inode, struct btrfs_path *path)
 {
@@ -1716,7 +1716,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 
 	if (nlink != inode->i_nlink) {
 		set_nlink(inode, nlink);
-		btrfs_update_inode(trans, root, inode);
+		btrfs_update_inode(trans, root, BTRFS_I(inode));
 	}
 	BTRFS_I(inode)->index_cnt = (u64)-1;
 
@@ -1727,7 +1727,9 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 			if (ret)
 				goto out;
 		}
-		ret = insert_orphan_item(trans, root, ino);
+		ret = btrfs_insert_orphan_item(trans, root, ino);
+		if (ret == -EEXIST)
+			ret = 0;
 	}
 
 out:
@@ -1820,7 +1822,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 			set_nlink(inode, 1);
 		else
 			inc_nlink(inode);
-		ret = btrfs_update_inode(trans, root, inode);
+		ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 	} else if (ret == -EEXIST) {
 		ret = 0;
 	} else {
@@ -1973,7 +1975,7 @@ out:
 	btrfs_release_path(path);
 	if (!ret && update_size) {
 		btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2);
-		ret = btrfs_update_inode(trans, root, dir);
+		ret = btrfs_update_inode(trans, root, BTRFS_I(dir));
 	}
 	kfree(name);
 	iput(dir);
@@ -2586,6 +2588,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 			 * those prealloc extents just after replaying them.
 			 */
 			if (S_ISREG(mode)) {
+				struct btrfs_drop_extents_args drop_args = { 0 };
 				struct inode *inode;
 				u64 from;
 
@@ -2596,12 +2599,18 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 				}
 				from = ALIGN(i_size_read(inode),
 					     root->fs_info->sectorsize);
-				ret = btrfs_drop_extents(wc->trans, root, inode,
+				drop_args.start = from;
-							 from, (u64)-1, 1);
+				drop_args.end = (u64)-1;
+				drop_args.drop_cache = true;
+				ret = btrfs_drop_extents(wc->trans, root,
+							 BTRFS_I(inode),
+							 &drop_args);
 				if (!ret) {
+					inode_sub_bytes(inode,
+							drop_args.bytes_found);
 					/* Update the inode's nbytes. */
 					ret = btrfs_update_inode(wc->trans,
-								 root, inode);
+							root, BTRFS_I(inode));
 				}
 				iput(inode);
 				if (ret)
@@ -2709,7 +2718,9 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 		btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
 		blocksize = fs_info->nodesize;
 
-		next = btrfs_find_create_tree_block(fs_info, bytenr);
+		next = btrfs_find_create_tree_block(fs_info, bytenr,
+						    btrfs_header_owner(cur),
+						    *level - 1);
 		if (IS_ERR(next))
 			return PTR_ERR(next);
 
@@ -2732,7 +2743,6 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 				if (trans) {
 					btrfs_tree_lock(next);
-					btrfs_set_lock_blocking_write(next);
 					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
@@ -2801,7 +2811,6 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 
 				if (trans) {
 					btrfs_tree_lock(next);
-					btrfs_set_lock_blocking_write(next);
 					btrfs_clean_tree_block(next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
@@ -2883,7 +2892,6 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 
 			if (trans) {
 				btrfs_tree_lock(next);
-				btrfs_set_lock_blocking_write(next);
 				btrfs_clean_tree_block(next);
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
@@ -3023,6 +3031,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	int log_transid = 0;
 	struct btrfs_log_ctx root_log_ctx;
 	struct blk_plug plug;
+	u64 log_root_start;
+	u64 log_root_level;
 
 	mutex_lock(&root->log_mutex);
 	log_transid = ctx->log_transid;
@@ -3200,22 +3210,31 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		goto out_wake_log_root;
 	}
 
-	btrfs_set_super_log_root(fs_info->super_for_commit,
+	log_root_start = log_root_tree->node->start;
-				 log_root_tree->node->start);
+	log_root_level = btrfs_header_level(log_root_tree->node);
-	btrfs_set_super_log_root_level(fs_info->super_for_commit,
-				       btrfs_header_level(log_root_tree->node));
-
 	log_root_tree->log_transid++;
 	mutex_unlock(&log_root_tree->log_mutex);
 
 	/*
-	 * Nobody else is going to jump in and write the ctree
+	 * Here we are guaranteed that nobody is going to write the superblock
-	 * super here because the log_commit atomic below is protecting
+	 * for the current transaction before us and that neither we do write
-	 * us.  We must be called with a transaction handle pinning
+	 * our superblock before the previous transaction finishes its commit
-	 * the running transaction open, so a full commit can't hop
+	 * and writes its superblock, because:
-	 * in and cause problems either.
+	 *
+	 * 1) We are holding a handle on the current transaction, so no body
+	 *    can commit it until we release the handle;
+	 *
+	 * 2) Before writing our superblock we acquire the tree_log_mutex, so
+	 *    if the previous transaction is still committing, and hasn't yet
+	 *    written its superblock, we wait for it to do it, because a
+	 *    transaction commit acquires the tree_log_mutex when the commit
+	 *    begins and releases it only after writing its superblock.
 	 */
+	mutex_lock(&fs_info->tree_log_mutex);
+	btrfs_set_super_log_root(fs_info->super_for_commit, log_root_start);
+	btrfs_set_super_log_root_level(fs_info->super_for_commit, log_root_level);
 	ret = write_all_supers(fs_info, 1);
+	mutex_unlock(&fs_info->tree_log_mutex);
 	if (ret) {
 		btrfs_set_log_full_commit(trans);
 		btrfs_abort_transaction(trans, ret);
@@ -3300,6 +3319,7 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
 	if (fs_info->log_root_tree) {
 		free_log_tree(trans, fs_info->log_root_tree);
 		fs_info->log_root_tree = NULL;
+		clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &fs_info->tree_root->state);
 	}
 	return 0;
 }
@@ -4196,6 +4216,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 			  struct btrfs_path *path,
 			  struct btrfs_log_ctx *ctx)
 {
+	struct btrfs_drop_extents_args drop_args = { 0 };
 	struct btrfs_root *log = root->log_root;
 	struct btrfs_file_extent_item *fi;
 	struct extent_buffer *leaf;
@@ -4204,19 +4225,21 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	u64 extent_offset = em->start - em->orig_start;
 	u64 block_len;
 	int ret;
-	int extent_inserted = 0;
 
 	ret = log_extent_csums(trans, inode, log, em, ctx);
 	if (ret)
 		return ret;
 
-	ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
+	drop_args.path = path;
-				   em->start + em->len, NULL, 0, 1,
+	drop_args.start = em->start;
-				   sizeof(*fi), &extent_inserted);
+	drop_args.end = em->start + em->len;
+	drop_args.replace_extent = true;
+	drop_args.extent_item_size = sizeof(*fi);
+	ret = btrfs_drop_extents(trans, log, inode, &drop_args);
 	if (ret)
 		return ret;
 
-	if (!extent_inserted) {
+	if (!drop_args.extent_inserted) {
 		key.objectid = btrfs_ino(inode);
 		key.type = BTRFS_EXTENT_DATA_KEY;
 		key.offset = em->start;
@@ -4375,8 +4398,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
 			do {
 				ret = btrfs_truncate_inode_items(trans,
 							 root->log_root,
-							 &inode->vfs_inode,
+							 inode, truncate_offset,
-							 truncate_offset,
 							 BTRFS_EXTENT_DATA_KEY);
 			} while (ret == -EAGAIN);
 			if (ret)
@@ -4415,14 +4437,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	struct extent_map *em, *n;
 	struct list_head extents;
 	struct extent_map_tree *tree = &inode->extent_tree;
-	u64 test_gen;
 	int ret = 0;
 	int num = 0;
 
 	INIT_LIST_HEAD(&extents);
 
 	write_lock(&tree->lock);
-	test_gen = root->fs_info->last_trans_committed;
 
 	list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
 		list_del_init(&em->list);
@@ -4438,7 +4458,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 			goto process;
 		}
 
-		if (em->generation <= test_gen)
+		if (em->generation < trans->transid)
 			continue;
 
 		/* We log prealloc extents beyond eof later. */
@@ -4571,6 +4591,10 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 	const u64 ino = btrfs_ino(inode);
 	int ins_nr = 0;
 	int start_slot = 0;
+	bool found_xattrs = false;
+
+	if (test_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags))
+		return 0;
 
 	key.objectid = ino;
 	key.type = BTRFS_XATTR_ITEM_KEY;
@@ -4609,6 +4633,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 			start_slot = slot;
 		ins_nr++;
 		path->slots[0]++;
+		found_xattrs = true;
 		cond_resched();
 	}
 	if (ins_nr > 0) {
@@ -4618,6 +4643,9 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 			return ret;
 	}
 
+	if (!found_xattrs)
+		set_bit(BTRFS_INODE_NO_XATTRS, &inode->runtime_flags);
+
 	return 0;
 }
 
@@ -5303,7 +5331,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 					  &inode->runtime_flags);
 				while(1) {
 					ret = btrfs_truncate_inode_items(trans,
-						log, &inode->vfs_inode, 0, 0);
+						log, inode, 0, 0);
 					if (ret != -EAGAIN)
 						break;
 				}
@@ -5442,11 +5470,10 @@ out_unlock:
 static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
 					  struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	bool ret = false;
 
 	mutex_lock(&inode->log_mutex);
-	if (inode->last_unlink_trans > fs_info->last_trans_committed) {
+	if (inode->last_unlink_trans >= trans->transid) {
 		/*
 		 * Make sure any commits to the log are forced to be full
 		 * commits.
@@ -5468,8 +5495,7 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
 static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 					       struct btrfs_inode *inode,
 					       struct dentry *parent,
-					       struct super_block *sb,
+					       struct super_block *sb)
-					       u64 last_committed)
 {
 	int ret = 0;
 	struct dentry *old_parent = NULL;
@@ -5481,8 +5507,8 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 	 * and other fun in this file.
 	 */
 	if (S_ISREG(inode->vfs_inode.i_mode) &&
-	    inode->generation <= last_committed &&
+	    inode->generation < trans->transid &&
-	    inode->last_unlink_trans <= last_committed)
+	    inode->last_unlink_trans < trans->transid)
 		goto out;
 
 	if (!S_ISDIR(inode->vfs_inode.i_mode)) {
@@ -5828,7 +5854,6 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
 
 	while (true) {
 		struct btrfs_fs_info *fs_info = root->fs_info;
-		const u64 last_committed = fs_info->last_trans_committed;
 		struct extent_buffer *leaf = path->nodes[0];
 		int slot = path->slots[0];
 		struct btrfs_key search_key;
@@ -5847,7 +5872,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
 		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 
-		if (BTRFS_I(inode)->generation > last_committed)
+		if (BTRFS_I(inode)->generation >= trans->transid)
 			ret = btrfs_log_inode(trans, root, BTRFS_I(inode),
 					      LOG_INODE_EXISTS, ctx);
 		btrfs_add_delayed_iput(inode);
@@ -5888,7 +5913,6 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans,
 				  struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *root = inode->root;
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct dentry *old_parent = NULL;
 	struct super_block *sb = inode->vfs_inode.i_sb;
 	int ret = 0;
@@ -5902,7 +5926,7 @@ static int log_new_ancestors_fast(struct btrfs_trans_handle *trans,
 		if (root != inode->root)
 			break;
 
-		if (inode->generation > fs_info->last_trans_committed) {
+		if (inode->generation >= trans->transid) {
 			ret = btrfs_log_inode(trans, root, inode,
 					      LOG_INODE_EXISTS, ctx);
 			if (ret)
@@ -6019,7 +6043,6 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct super_block *sb;
 	int ret = 0;
-	u64 last_committed = fs_info->last_trans_committed;
 	bool log_dentries = false;
 
 	sb = inode->vfs_inode.i_sb;
@@ -6029,23 +6052,12 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	/*
-	 * The prev transaction commit doesn't complete, we need do
-	 * full commit by ourselves.
-	 */
-	if (fs_info->last_trans_log_full_commit >
-	    fs_info->last_trans_committed) {
-		ret = 1;
-		goto end_no_trans;
-	}
-
 	if (btrfs_root_refs(&root->root_item) == 0) {
 		ret = 1;
 		goto end_no_trans;
 	}
 
-	ret = check_parent_dirs_for_sync(trans, inode, parent, sb,
+	ret = check_parent_dirs_for_sync(trans, inode, parent, sb);
-			last_committed);
 	if (ret)
 		goto end_no_trans;
 
@@ -6075,8 +6087,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * and other fun in this file.
 	 */
 	if (S_ISREG(inode->vfs_inode.i_mode) &&
-	    inode->generation <= last_committed &&
+	    inode->generation < trans->transid &&
-	    inode->last_unlink_trans <= last_committed) {
+	    inode->last_unlink_trans < trans->transid) {
 		ret = 0;
 		goto end_trans;
 	}
@@ -6125,7 +6137,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item
 	 * and has a link count of 2.
 	 */
-	if (inode->last_unlink_trans > last_committed) {
+	if (inode->last_unlink_trans >= trans->transid) {
 		ret = btrfs_log_all_parents(trans, inode, ctx);
 		if (ret)
 			goto end_trans;
@@ -6434,7 +6446,6 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_log_ctx ctx;
 
 	/*
@@ -6448,8 +6459,8 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * if this inode hasn't been logged and directory we're renaming it
 	 * from hasn't been logged, we don't need to log it
 	 */
-	if (inode->logged_trans <= fs_info->last_trans_committed &&
+	if (inode->logged_trans < trans->transid &&
-	    (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
+	    (!old_dir || old_dir->logged_trans < trans->transid))
 		return;
 
 	btrfs_init_log_ctx(&ctx, &inode->vfs_inode);

fs/btrfs/uuid-tree.c

@@ -129,8 +129,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type,
 	} else {
 		btrfs_warn(fs_info,
 			   "insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!",
-			   ret, (unsigned long long)key.objectid,
+			   ret, key.objectid, key.offset, type);
-			   (unsigned long long)key.offset, type);
 		goto out;
 	}
 

fs/btrfs/volumes.c

@@ -31,6 +31,7 @@
 #include "space-info.h"
 #include "block-group.h"
 #include "discard.h"
+#include "zoned.h"
 
 const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
 	[BTRFS_RAID_RAID10] = {
@@ -374,6 +375,7 @@ void btrfs_free_device(struct btrfs_device *device)
 	rcu_string_free(device->name);
 	extent_io_tree_release(&device->alloc_state);
 	bio_put(device->flush_bio);
+	btrfs_destroy_dev_zone_info(device);
 	kfree(device);
 }
 
@@ -667,6 +669,10 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
 	clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	device->mode = flags;
 
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret != 0)
+		goto error_free_page;
+
 	fs_devices->open_devices++;
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
 	    device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -822,7 +828,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 	} else {
 		mutex_lock(&fs_devices->device_list_mutex);
 		device = btrfs_find_device(fs_devices, devid,
-				disk_super->dev_item.uuid, NULL, false);
+				disk_super->dev_item.uuid, NULL);
 
 		/*
 		 * If this disk has been pulled into an fs devices created by
@@ -1044,7 +1050,7 @@ error:
 }
 
 static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
-				      int step, struct btrfs_device **latest_dev)
+				      struct btrfs_device **latest_dev)
 {
 	struct btrfs_device *device, *next;
 
@@ -1089,16 +1095,16 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
  * After we have read the system tree and know devids belonging to this
  * filesystem, remove the device which does not belong there.
  */
-void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step)
+void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *latest_dev = NULL;
 	struct btrfs_fs_devices *seed_dev;
 
 	mutex_lock(&uuid_mutex);
-	__btrfs_free_extra_devids(fs_devices, step, &latest_dev);
+	__btrfs_free_extra_devids(fs_devices, &latest_dev);
 
 	list_for_each_entry(seed_dev, &fs_devices->seed_list, seed_list)
-		__btrfs_free_extra_devids(seed_dev, step, &latest_dev);
+		__btrfs_free_extra_devids(seed_dev, &latest_dev);
 
 	fs_devices->latest_bdev = latest_dev->bdev;
 
@@ -1137,6 +1143,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 		device->bdev = NULL;
 	}
 	clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+	btrfs_destroy_dev_zone_info(device);
 
 	device->fs_info = NULL;
 	atomic_set(&device->dev_stats_ccnt, 0);
@@ -1217,6 +1224,7 @@ static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
 	fs_devices->latest_bdev = latest_dev->bdev;
 	fs_devices->total_rw_bytes = 0;
 	fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_REGULAR;
+	fs_devices->read_policy = BTRFS_READ_POLICY_PID;
 
 	return 0;
 }
@@ -1268,7 +1276,7 @@ void btrfs_release_disk_super(struct btrfs_super_block *super)
 }
 
 static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev,
-						       u64 bytenr)
+						       u64 bytenr, u64 bytenr_orig)
 {
 	struct btrfs_super_block *disk_super;
 	struct page *page;
@@ -1299,7 +1307,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev
 	/* align our pointer to the offset of the super block */
 	disk_super = p + offset_in_page(bytenr);
 
-	if (btrfs_super_bytenr(disk_super) != bytenr ||
+	if (btrfs_super_bytenr(disk_super) != bytenr_orig ||
 	    btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
 		btrfs_release_disk_super(p);
 		return ERR_PTR(-EINVAL);
@@ -1334,7 +1342,8 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 	bool new_device_added = false;
 	struct btrfs_device *device = NULL;
 	struct block_device *bdev;
-	u64 bytenr;
+	u64 bytenr, bytenr_orig;
+	int ret;
 
 	lockdep_assert_held(&uuid_mutex);
 
@@ -1344,14 +1353,18 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
 	 * So, we need to add a special mount option to scan for
 	 * later supers, using BTRFS_SUPER_MIRROR_MAX instead
 	 */
-	bytenr = btrfs_sb_offset(0);
 	flags |= FMODE_EXCL;
 
 	bdev = blkdev_get_by_path(path, flags, holder);
 	if (IS_ERR(bdev))
 		return ERR_CAST(bdev);
 
-	disk_super = btrfs_read_disk_super(bdev, bytenr);
+	bytenr_orig = btrfs_sb_offset(0);
+	ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr);
+	if (ret)
+		return ERR_PTR(ret);
+
+	disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig);
 	if (IS_ERR(disk_super)) {
 		device = ERR_CAST(disk_super);
 		goto error_bdev_put;
@@ -2015,6 +2028,11 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 		if (IS_ERR(disk_super))
 			continue;
 
+		if (bdev_is_zoned(bdev)) {
+			btrfs_reset_sb_log_zones(bdev, copy_num);
+			continue;
+		}
+
 		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
 
 		page = virt_to_page(disk_super);
@@ -2293,10 +2311,10 @@ static struct btrfs_device *btrfs_find_device_by_path(
 	dev_uuid = disk_super->dev_item.uuid;
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
 		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   disk_super->metadata_uuid, true);
+					   disk_super->metadata_uuid);
 	else
 		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   disk_super->fsid, true);
+					   disk_super->fsid);
 
 	btrfs_release_disk_super(disk_super);
 	if (!device)
@@ -2316,7 +2334,7 @@ struct btrfs_device *btrfs_find_device_by_devspec(
 
 	if (devid) {
 		device = btrfs_find_device(fs_info->fs_devices, devid, NULL,
-					   NULL, true);
+					   NULL);
 		if (!device)
 			return ERR_PTR(-ENOENT);
 		return device;
@@ -2465,7 +2483,7 @@ next_slot:
 		read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item),
 				   BTRFS_FSID_SIZE);
 		device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-					   fs_uuid, true);
+					   fs_uuid);
 		BUG_ON(!device); /* Logic error */
 
 		if (device->fs_devices->seeding) {
@@ -2507,6 +2525,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
+	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
+		ret = -EINVAL;
+		goto error;
+	}
+
 	if (fs_devices->seeding) {
 		seeding_dev = 1;
 		down_write(&sb->s_umount);
@@ -2540,10 +2563,17 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	}
 	rcu_assign_pointer(device->name, name);
 
+	device->fs_info = fs_info;
+	device->bdev = bdev;
+
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret)
+		goto error_free_device;
+
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		goto error_free_device;
+		goto error_free_zone;
 	}
 
 	q = bdev_get_queue(bdev);
@@ -2556,8 +2586,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 					 fs_info->sectorsize);
 	device->disk_total_bytes = device->total_bytes;
 	device->commit_total_bytes = device->total_bytes;
-	device->fs_info = fs_info;
-	device->bdev = bdev;
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
 	device->mode = FMODE_EXCL;
@@ -2704,6 +2732,8 @@ error_trans:
 		sb->s_flags |= SB_RDONLY;
 	if (trans)
 		btrfs_end_transaction(trans);
+error_free_zone:
+	btrfs_destroy_dev_zone_info(device);
 error_free_device:
 	btrfs_free_device(device);
 error:
@@ -5479,7 +5509,18 @@ static int find_live_mirror(struct btrfs_fs_info *fs_info,
 	else
 		num_stripes = map->num_stripes;
 
-	preferred_mirror = first + current->pid % num_stripes;
+	switch (fs_info->fs_devices->read_policy) {
+	default:
+		/* Shouldn't happen, just warn and use pid instead of failing */
+		btrfs_warn_rl(fs_info,
+			      "unknown read_policy type %u, reset to pid",
+			      fs_info->fs_devices->read_policy);
+		fs_info->fs_devices->read_policy = BTRFS_READ_POLICY_PID;
+		fallthrough;
+	case BTRFS_READ_POLICY_PID:
+		preferred_mirror = first + (current->pid % num_stripes);
+		break;
+	}
 
 	if (dev_replace_is_ongoing &&
 	    fs_info->dev_replace.cont_reading_from_srcdev_mode ==
@@ -6335,7 +6376,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 	bio->bi_iter.bi_sector = physical >> 9;
 	btrfs_debug_in_rcu(fs_info,
 	"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-		bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector,
+		bio_op(bio), bio->bi_opf, bio->bi_iter.bi_sector,
 		(unsigned long)dev->bdev->bd_dev, rcu_str_deref(dev->name),
 		dev->devid, bio->bi_iter.bi_size);
 	bio_set_dev(bio, dev->bdev);
@@ -6367,7 +6408,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 {
 	struct btrfs_device *dev;
 	struct bio *first_bio = bio;
-	u64 logical = (u64)bio->bi_iter.bi_sector << 9;
+	u64 logical = bio->bi_iter.bi_sector << 9;
 	u64 length = 0;
 	u64 map_length;
 	int ret;
@@ -6447,8 +6488,7 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
  * If @seed is true, traverse through the seed devices.
  */
 struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices,
-				       u64 devid, u8 *uuid, u8 *fsid,
+				       u64 devid, u8 *uuid, u8 *fsid)
-				       bool seed)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *seed_devs;
@@ -6655,7 +6695,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 				   btrfs_stripe_dev_uuid_nr(chunk, i),
 				   BTRFS_UUID_SIZE);
 		map->stripes[i].dev = btrfs_find_device(fs_info->fs_devices,
-							devid, uuid, NULL, true);
+							devid, uuid, NULL);
 		if (!map->stripes[i].dev &&
 		    !btrfs_test_opt(fs_info, DEGRADED)) {
 			free_extent_map(em);
@@ -6794,7 +6834,7 @@ static int read_one_dev(struct extent_buffer *leaf,
 	}
 
 	device = btrfs_find_device(fs_info->fs_devices, devid, dev_uuid,
-				   fs_uuid, true);
+				   fs_uuid);
 	if (!device) {
 		if (!btrfs_test_opt(fs_info, DEGRADED)) {
 			btrfs_report_missing_device(fs_info, devid,
@@ -6857,6 +6897,16 @@ static int read_one_dev(struct extent_buffer *leaf,
 	}
 
 	fill_device_from_item(leaf, dev_item, device);
+	if (device->bdev) {
+		u64 max_total_bytes = i_size_read(device->bdev->bd_inode);
+
+		if (device->total_bytes > max_total_bytes) {
+			btrfs_err(fs_info,
+			"device total_bytes should be at most %llu but found %llu",
+				  max_total_bytes, device->total_bytes);
+			return -EINVAL;
+		}
+	}
 	set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
 	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
 	   !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
@@ -6891,11 +6941,11 @@ int btrfs_read_sys_array(struct btrfs_fs_info *fs_info)
 	 * fixed to BTRFS_SUPER_INFO_SIZE. If nodesize > sb size, this will
 	 * overallocate but we can keep it as-is, only the first page is used.
 	 */
-	sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET);
+	sb = btrfs_find_create_tree_block(fs_info, BTRFS_SUPER_INFO_OFFSET,
+					  root->root_key.objectid, 0);
 	if (IS_ERR(sb))
 		return PTR_ERR(sb);
 	set_extent_buffer_uptodate(sb);
-	btrfs_set_buffer_lockdep_class(root->root_key.objectid, sb, 0);
 	/*
 	 * The sb extent buffer is artificial and just used to read the system array.
 	 * set_extent_buffer_uptodate() call does not properly mark all it's
@@ -7059,12 +7109,8 @@ static void readahead_tree_node_children(struct extent_buffer *node)
 	int i;
 	const int nr_items = btrfs_header_nritems(node);
 
-	for (i = 0; i < nr_items; i++) {
+	for (i = 0; i < nr_items; i++)
-		u64 start;
+		btrfs_readahead_node_child(node, i);
-
-		start = btrfs_node_blockptr(node, i);
-		readahead_tree_block(node->fs_info, start);
-	}
 }
 
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
@@ -7451,8 +7497,7 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
 	int i;
 
 	mutex_lock(&fs_devices->device_list_mutex);
-	dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL,
+	dev = btrfs_find_device(fs_info->fs_devices, stats->devid, NULL, NULL);
-				true);
 	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (!dev) {
@@ -7583,28 +7628,13 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
 	}
 
 	/* Make sure no dev extent is beyond device bondary */
-	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL, true);
+	dev = btrfs_find_device(fs_info->fs_devices, devid, NULL, NULL);
 	if (!dev) {
 		btrfs_err(fs_info, "failed to find devid %llu", devid);
 		ret = -EUCLEAN;
 		goto out;
 	}
 
-	/* It's possible this device is a dummy for seed device */
-	if (dev->disk_total_bytes == 0) {
-		struct btrfs_fs_devices *devs;
-
-		devs = list_first_entry(&fs_info->fs_devices->seed_list,
-					struct btrfs_fs_devices, seed_list);
-		dev = btrfs_find_device(devs, devid, NULL, NULL, false);
-		if (!dev) {
-			btrfs_err(fs_info, "failed to find seed devid %llu",
-				  devid);
-			ret = -EUCLEAN;
-			goto out;
-		}
-	}
-
 	if (physical_offset + physical_len > dev->disk_total_bytes) {
 		btrfs_err(fs_info,
 "dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu",
@@ -7659,6 +7689,19 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info)
 	u64 prev_dev_ext_end = 0;
 	int ret = 0;
 
+	/*
+	 * We don't have a dev_root because we mounted with ignorebadroots and
+	 * failed to load the root, so we want to skip the verification in this
+	 * case for sure.
+	 *
+	 * However if the dev root is fine, but the tree itself is corrupted
+	 * we'd still fail to mount.  This verification is only to make sure
+	 * writes can happen safely, so instead just bypass this check
+	 * completely in the case of IGNOREBADROOTS.
+	 */
+	if (btrfs_test_opt(fs_info, IGNOREBADROOTS))
+		return 0;
+
 	key.objectid = 1;
 	key.type = BTRFS_DEV_EXTENT_KEY;
 	key.offset = 0;

fs/btrfs/volumes.h

@@ -52,6 +52,8 @@ struct btrfs_io_geometry {
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
 #define BTRFS_DEV_STATE_NO_READA	(5)
 
+struct btrfs_zoned_device_info;
+
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
 	struct list_head dev_alloc_list; /* chunk mutex */
@@ -65,6 +67,8 @@ struct btrfs_device {
 
 	struct block_device *bdev;
 
+	struct btrfs_zoned_device_info *zone_info;
+
 	/* the mode sent to blkdev_get */
 	fmode_t mode;
 
@@ -211,6 +215,16 @@ enum btrfs_chunk_allocation_policy {
 	BTRFS_CHUNK_ALLOC_REGULAR,
 };
 
+/*
+ * Read policies for mirrored block group profiles, read picks the stripe based
+ * on these policies.
+ */
+enum btrfs_read_policy {
+	/* Use process PID to choose the stripe */
+	BTRFS_READ_POLICY_PID,
+	BTRFS_NR_READ_POLICY,
+};
+
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 	u8 metadata_uuid[BTRFS_FSID_SIZE];
@@ -264,6 +278,9 @@ struct btrfs_fs_devices {
 	struct completion kobj_unregister;
 
 	enum btrfs_chunk_allocation_policy chunk_alloc_policy;
+
+	/* Policy used to read the mirrored stripes */
+	enum btrfs_read_policy read_policy;
 };
 
 #define BTRFS_BIO_INLINE_CSUM_SIZE	64
@@ -436,7 +453,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path,
 					   fmode_t flags, void *holder);
 int btrfs_forget_devices(const char *path);
 void btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
-void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
+void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices);
 void btrfs_assign_next_active_device(struct btrfs_device *device,
 				     struct btrfs_device *this_dev);
 struct btrfs_device *btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info,
@@ -453,7 +470,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
 		      struct btrfs_device *device, u64 new_size);
 struct btrfs_device *btrfs_find_device(struct btrfs_fs_devices *fs_devices,
-				       u64 devid, u8 *uuid, u8 *fsid, bool seed);
+				       u64 devid, u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
 int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
 int btrfs_balance(struct btrfs_fs_info *fs_info,

fs/btrfs/xattr.c

@@ -213,9 +213,11 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 out:
 	btrfs_free_path(path);
-	if (!ret)
+	if (!ret) {
 		set_bit(BTRFS_INODE_COPY_EVERYTHING,
 			&BTRFS_I(inode)->runtime_flags);
+		clear_bit(BTRFS_INODE_NO_XATTRS, &BTRFS_I(inode)->runtime_flags);
+	}
 	return ret;
 }
 
@@ -239,7 +241,7 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name,
 
 	inode_inc_iversion(inode);
 	inode->i_ctime = current_time(inode);
-	ret = btrfs_update_inode(trans, root, inode);
+	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 	BUG_ON(ret);
 out:
 	btrfs_end_transaction(trans);
@@ -390,7 +392,7 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler,
 	if (!ret) {
 		inode_inc_iversion(inode);
 		inode->i_ctime = current_time(inode);
-		ret = btrfs_update_inode(trans, root, inode);
+		ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
 		BUG_ON(ret);
 	}
 

fs/btrfs/zoned.c

@@ -0,0 +1,616 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include "ctree.h"
+#include "volumes.h"
+#include "zoned.h"
+#include "rcu-string.h"
+
+/* Maximum number of zones to report per blkdev_report_zones() call */
+#define BTRFS_REPORT_NR_ZONES   4096
+
+/* Number of superblock log zones */
+#define BTRFS_NR_SB_LOG_ZONES 2
+
+static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
+{
+	struct blk_zone *zones = data;
+
+	memcpy(&zones[idx], zone, sizeof(*zone));
+
+	return 0;
+}
+
+static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones,
+			    u64 *wp_ret)
+{
+	bool empty[BTRFS_NR_SB_LOG_ZONES];
+	bool full[BTRFS_NR_SB_LOG_ZONES];
+	sector_t sector;
+
+	ASSERT(zones[0].type != BLK_ZONE_TYPE_CONVENTIONAL &&
+	       zones[1].type != BLK_ZONE_TYPE_CONVENTIONAL);
+
+	empty[0] = (zones[0].cond == BLK_ZONE_COND_EMPTY);
+	empty[1] = (zones[1].cond == BLK_ZONE_COND_EMPTY);
+	full[0] = (zones[0].cond == BLK_ZONE_COND_FULL);
+	full[1] = (zones[1].cond == BLK_ZONE_COND_FULL);
+
+	/*
+	 * Possible states of log buffer zones
+	 *
+	 *           Empty[0]  In use[0]  Full[0]
+	 * Empty[1]         *          x        0
+	 * In use[1]        0          x        0
+	 * Full[1]          1          1        C
+	 *
+	 * Log position:
+	 *   *: Special case, no superblock is written
+	 *   0: Use write pointer of zones[0]
+	 *   1: Use write pointer of zones[1]
+	 *   C: Compare super blcoks from zones[0] and zones[1], use the latest
+	 *      one determined by generation
+	 *   x: Invalid state
+	 */
+
+	if (empty[0] && empty[1]) {
+		/* Special case to distinguish no superblock to read */
+		*wp_ret = zones[0].start << SECTOR_SHIFT;
+		return -ENOENT;
+	} else if (full[0] && full[1]) {
+		/* Compare two super blocks */
+		struct address_space *mapping = bdev->bd_inode->i_mapping;
+		struct page *page[BTRFS_NR_SB_LOG_ZONES];
+		struct btrfs_super_block *super[BTRFS_NR_SB_LOG_ZONES];
+		int i;
+
+		for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++) {
+			u64 bytenr;
+
+			bytenr = ((zones[i].start + zones[i].len)
+				   << SECTOR_SHIFT) - BTRFS_SUPER_INFO_SIZE;
+
+			page[i] = read_cache_page_gfp(mapping,
+					bytenr >> PAGE_SHIFT, GFP_NOFS);
+			if (IS_ERR(page[i])) {
+				if (i == 1)
+					btrfs_release_disk_super(super[0]);
+				return PTR_ERR(page[i]);
+			}
+			super[i] = page_address(page[i]);
+		}
+
+		if (super[0]->generation > super[1]->generation)
+			sector = zones[1].start;
+		else
+			sector = zones[0].start;
+
+		for (i = 0; i < BTRFS_NR_SB_LOG_ZONES; i++)
+			btrfs_release_disk_super(super[i]);
+	} else if (!full[0] && (empty[1] || full[1])) {
+		sector = zones[0].wp;
+	} else if (full[0]) {
+		sector = zones[1].wp;
+	} else {
+		return -EUCLEAN;
+	}
+	*wp_ret = sector << SECTOR_SHIFT;
+	return 0;
+}
+
+/*
+ * The following zones are reserved as the circular buffer on ZONED btrfs.
+ *  - The primary superblock: zones 0 and 1
+ *  - The first copy: zones 16 and 17
+ *  - The second copy: zones 1024 or zone at 256GB which is minimum, and
+ *                     the following one
+ */
+static inline u32 sb_zone_number(int shift, int mirror)
+{
+	ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+
+	switch (mirror) {
+	case 0: return 0;
+	case 1: return 16;
+	case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+	}
+
+	return 0;
+}
+
+static int btrfs_get_dev_zones(struct btrfs_device *device, u64 pos,
+			       struct blk_zone *zones, unsigned int *nr_zones)
+{
+	int ret;
+
+	if (!*nr_zones)
+		return 0;
+
+	ret = blkdev_report_zones(device->bdev, pos >> SECTOR_SHIFT, *nr_zones,
+				  copy_zone_info_cb, zones);
+	if (ret < 0) {
+		btrfs_err_in_rcu(device->fs_info,
+				 "zoned: failed to read zone %llu on %s (devid %llu)",
+				 pos, rcu_str_deref(device->name),
+				 device->devid);
+		return ret;
+	}
+	*nr_zones = ret;
+	if (!ret)
+		return -EIO;
+
+	return 0;
+}
+
+int btrfs_get_dev_zone_info(struct btrfs_device *device)
+{
+	struct btrfs_zoned_device_info *zone_info = NULL;
+	struct block_device *bdev = device->bdev;
+	struct request_queue *queue = bdev_get_queue(bdev);
+	sector_t nr_sectors;
+	sector_t sector = 0;
+	struct blk_zone *zones = NULL;
+	unsigned int i, nreported = 0, nr_zones;
+	unsigned int zone_sectors;
+	int ret;
+
+	if (!bdev_is_zoned(bdev))
+		return 0;
+
+	if (device->zone_info)
+		return 0;
+
+	zone_info = kzalloc(sizeof(*zone_info), GFP_KERNEL);
+	if (!zone_info)
+		return -ENOMEM;
+
+	nr_sectors = bdev->bd_part->nr_sects;
+	zone_sectors = bdev_zone_sectors(bdev);
+	/* Check if it's power of 2 (see is_power_of_2) */
+	ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
+	zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+	zone_info->zone_size_shift = ilog2(zone_info->zone_size);
+	zone_info->max_zone_append_size =
+		(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
+	zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors);
+	if (!IS_ALIGNED(nr_sectors, zone_sectors))
+		zone_info->nr_zones++;
+
+	zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
+	if (!zone_info->seq_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL);
+	if (!zone_info->empty_zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	zones = kcalloc(BTRFS_REPORT_NR_ZONES, sizeof(struct blk_zone), GFP_KERNEL);
+	if (!zones) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* Get zones type */
+	while (sector < nr_sectors) {
+		nr_zones = BTRFS_REPORT_NR_ZONES;
+		ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT, zones,
+					  &nr_zones);
+		if (ret)
+			goto out;
+
+		for (i = 0; i < nr_zones; i++) {
+			if (zones[i].type == BLK_ZONE_TYPE_SEQWRITE_REQ)
+				__set_bit(nreported, zone_info->seq_zones);
+			if (zones[i].cond == BLK_ZONE_COND_EMPTY)
+				__set_bit(nreported, zone_info->empty_zones);
+			nreported++;
+		}
+		sector = zones[nr_zones - 1].start + zones[nr_zones - 1].len;
+	}
+
+	if (nreported != zone_info->nr_zones) {
+		btrfs_err_in_rcu(device->fs_info,
+				 "inconsistent number of zones on %s (%u/%u)",
+				 rcu_str_deref(device->name), nreported,
+				 zone_info->nr_zones);
+		ret = -EIO;
+		goto out;
+	}
+
+	/* Validate superblock log */
+	nr_zones = BTRFS_NR_SB_LOG_ZONES;
+	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+		u32 sb_zone;
+		u64 sb_wp;
+		int sb_pos = BTRFS_NR_SB_LOG_ZONES * i;
+
+		sb_zone = sb_zone_number(zone_info->zone_size_shift, i);
+		if (sb_zone + 1 >= zone_info->nr_zones)
+			continue;
+
+		sector = sb_zone << (zone_info->zone_size_shift - SECTOR_SHIFT);
+		ret = btrfs_get_dev_zones(device, sector << SECTOR_SHIFT,
+					  &zone_info->sb_zones[sb_pos],
+					  &nr_zones);
+		if (ret)
+			goto out;
+
+		if (nr_zones != BTRFS_NR_SB_LOG_ZONES) {
+			btrfs_err_in_rcu(device->fs_info,
+	"zoned: failed to read super block log zone info at devid %llu zone %u",
+					 device->devid, sb_zone);
+			ret = -EUCLEAN;
+			goto out;
+		}
+
+		/*
+		 * If zones[0] is conventional, always use the beggining of the
+		 * zone to record superblock. No need to validate in that case.
+		 */
+		if (zone_info->sb_zones[BTRFS_NR_SB_LOG_ZONES * i].type ==
+		    BLK_ZONE_TYPE_CONVENTIONAL)
+			continue;
+
+		ret = sb_write_pointer(device->bdev,
+				       &zone_info->sb_zones[sb_pos], &sb_wp);
+		if (ret != -ENOENT && ret) {
+			btrfs_err_in_rcu(device->fs_info,
+			"zoned: super block log zone corrupted devid %llu zone %u",
+					 device->devid, sb_zone);
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+
+
+	kfree(zones);
+
+	device->zone_info = zone_info;
+
+	/* device->fs_info is not safe to use for printing messages */
+	btrfs_info_in_rcu(NULL,
+			"host-%s zoned block device %s, %u zones of %llu bytes",
+			bdev_zoned_model(bdev) == BLK_ZONED_HM ? "managed" : "aware",
+			rcu_str_deref(device->name), zone_info->nr_zones,
+			zone_info->zone_size);
+
+	return 0;
+
+out:
+	kfree(zones);
+	bitmap_free(zone_info->empty_zones);
+	bitmap_free(zone_info->seq_zones);
+	kfree(zone_info);
+
+	return ret;
+}
+
+void btrfs_destroy_dev_zone_info(struct btrfs_device *device)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return;
+
+	bitmap_free(zone_info->seq_zones);
+	bitmap_free(zone_info->empty_zones);
+	kfree(zone_info);
+	device->zone_info = NULL;
+}
+
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone)
+{
+	unsigned int nr_zones = 1;
+	int ret;
+
+	ret = btrfs_get_dev_zones(device, pos, zone, &nr_zones);
+	if (ret != 0 || !nr_zones)
+		return ret ? ret : -EIO;
+
+	return 0;
+}
+
+int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_device *device;
+	u64 zoned_devices = 0;
+	u64 nr_devices = 0;
+	u64 zone_size = 0;
+	u64 max_zone_append_size = 0;
+	const bool incompat_zoned = btrfs_is_zoned(fs_info);
+	int ret = 0;
+
+	/* Count zoned devices */
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		enum blk_zoned_model model;
+
+		if (!device->bdev)
+			continue;
+
+		model = bdev_zoned_model(device->bdev);
+		if (model == BLK_ZONED_HM ||
+		    (model == BLK_ZONED_HA && incompat_zoned)) {
+			struct btrfs_zoned_device_info *zone_info;
+
+			zone_info = device->zone_info;
+			zoned_devices++;
+			if (!zone_size) {
+				zone_size = zone_info->zone_size;
+			} else if (zone_info->zone_size != zone_size) {
+				btrfs_err(fs_info,
+		"zoned: unequal block device zone sizes: have %llu found %llu",
+					  device->zone_info->zone_size,
+					  zone_size);
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!max_zone_append_size ||
+			    (zone_info->max_zone_append_size &&
+			     zone_info->max_zone_append_size < max_zone_append_size))
+				max_zone_append_size =
+					zone_info->max_zone_append_size;
+		}
+		nr_devices++;
+	}
+
+	if (!zoned_devices && !incompat_zoned)
+		goto out;
+
+	if (!zoned_devices && incompat_zoned) {
+		/* No zoned block device found on ZONED filesystem */
+		btrfs_err(fs_info,
+			  "zoned: no zoned devices found on a zoned filesystem");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (zoned_devices && !incompat_zoned) {
+		btrfs_err(fs_info,
+			  "zoned: mode not enabled but zoned device found");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (zoned_devices != nr_devices) {
+		btrfs_err(fs_info,
+			  "zoned: cannot mix zoned and regular devices");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * stripe_size is always aligned to BTRFS_STRIPE_LEN in
+	 * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size,
+	 * check the alignment here.
+	 */
+	if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) {
+		btrfs_err(fs_info,
+			  "zoned: zone size %llu not aligned to stripe %u",
+			  zone_size, BTRFS_STRIPE_LEN);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
+		btrfs_err(fs_info, "zoned: mixed block groups not supported");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	fs_info->zone_size = zone_size;
+	fs_info->max_zone_append_size = max_zone_append_size;
+
+	btrfs_info(fs_info, "zoned mode enabled with zone size %llu", zone_size);
+out:
+	return ret;
+}
+
+int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
+{
+	if (!btrfs_is_zoned(info))
+		return 0;
+
+	/*
+	 * Space cache writing is not COWed. Disable that to avoid write errors
+	 * in sequential zones.
+	 */
+	if (btrfs_test_opt(info, SPACE_CACHE)) {
+		btrfs_err(info, "zoned: space cache v1 is not supported");
+		return -EINVAL;
+	}
+
+	if (btrfs_test_opt(info, NODATACOW)) {
+		btrfs_err(info, "zoned: NODATACOW not supported");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sb_log_location(struct block_device *bdev, struct blk_zone *zones,
+			   int rw, u64 *bytenr_ret)
+{
+	u64 wp;
+	int ret;
+
+	if (zones[0].type == BLK_ZONE_TYPE_CONVENTIONAL) {
+		*bytenr_ret = zones[0].start << SECTOR_SHIFT;
+		return 0;
+	}
+
+	ret = sb_write_pointer(bdev, zones, &wp);
+	if (ret != -ENOENT && ret < 0)
+		return ret;
+
+	if (rw == WRITE) {
+		struct blk_zone *reset = NULL;
+
+		if (wp == zones[0].start << SECTOR_SHIFT)
+			reset = &zones[0];
+		else if (wp == zones[1].start << SECTOR_SHIFT)
+			reset = &zones[1];
+
+		if (reset && reset->cond != BLK_ZONE_COND_EMPTY) {
+			ASSERT(reset->cond == BLK_ZONE_COND_FULL);
+
+			ret = blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+					       reset->start, reset->len,
+					       GFP_NOFS);
+			if (ret)
+				return ret;
+
+			reset->cond = BLK_ZONE_COND_EMPTY;
+			reset->wp = reset->start;
+		}
+	} else if (ret != -ENOENT) {
+		/* For READ, we want the precious one */
+		if (wp == zones[0].start << SECTOR_SHIFT)
+			wp = (zones[1].start + zones[1].len) << SECTOR_SHIFT;
+		wp -= BTRFS_SUPER_INFO_SIZE;
+	}
+
+	*bytenr_ret = wp;
+	return 0;
+
+}
+
+int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
+			       u64 *bytenr_ret)
+{
+	struct blk_zone zones[BTRFS_NR_SB_LOG_ZONES];
+	unsigned int zone_sectors;
+	u32 sb_zone;
+	int ret;
+	u64 zone_size;
+	u8 zone_sectors_shift;
+	sector_t nr_sectors;
+	u32 nr_zones;
+
+	if (!bdev_is_zoned(bdev)) {
+		*bytenr_ret = btrfs_sb_offset(mirror);
+		return 0;
+	}
+
+	ASSERT(rw == READ || rw == WRITE);
+
+	zone_sectors = bdev_zone_sectors(bdev);
+	if (!is_power_of_2(zone_sectors))
+		return -EINVAL;
+	zone_size = zone_sectors << SECTOR_SHIFT;
+	zone_sectors_shift = ilog2(zone_sectors);
+	nr_sectors = bdev->bd_part->nr_sects;
+	nr_zones = nr_sectors >> zone_sectors_shift;
+
+	sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
+	if (sb_zone + 1 >= nr_zones)
+		return -ENOENT;
+
+	ret = blkdev_report_zones(bdev, sb_zone << zone_sectors_shift,
+				  BTRFS_NR_SB_LOG_ZONES, copy_zone_info_cb,
+				  zones);
+	if (ret < 0)
+		return ret;
+	if (ret != BTRFS_NR_SB_LOG_ZONES)
+		return -EIO;
+
+	return sb_log_location(bdev, zones, rw, bytenr_ret);
+}
+
+int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
+			  u64 *bytenr_ret)
+{
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	u32 zone_num;
+
+	if (!zinfo) {
+		*bytenr_ret = btrfs_sb_offset(mirror);
+		return 0;
+	}
+
+	zone_num = sb_zone_number(zinfo->zone_size_shift, mirror);
+	if (zone_num + 1 >= zinfo->nr_zones)
+		return -ENOENT;
+
+	return sb_log_location(device->bdev,
+			       &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror],
+			       rw, bytenr_ret);
+}
+
+static inline bool is_sb_log_zone(struct btrfs_zoned_device_info *zinfo,
+				  int mirror)
+{
+	u32 zone_num;
+
+	if (!zinfo)
+		return false;
+
+	zone_num = sb_zone_number(zinfo->zone_size_shift, mirror);
+	if (zone_num + 1 >= zinfo->nr_zones)
+		return false;
+
+	if (!test_bit(zone_num, zinfo->seq_zones))
+		return false;
+
+	return true;
+}
+
+void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
+{
+	struct btrfs_zoned_device_info *zinfo = device->zone_info;
+	struct blk_zone *zone;
+
+	if (!is_sb_log_zone(zinfo, mirror))
+		return;
+
+	zone = &zinfo->sb_zones[BTRFS_NR_SB_LOG_ZONES * mirror];
+	if (zone->cond != BLK_ZONE_COND_FULL) {
+		if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
+
+		if (zone->wp == zone->start + zone->len)
+			zone->cond = BLK_ZONE_COND_FULL;
+
+		return;
+	}
+
+	zone++;
+	ASSERT(zone->cond != BLK_ZONE_COND_FULL);
+	if (zone->cond == BLK_ZONE_COND_EMPTY)
+		zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+	zone->wp += (BTRFS_SUPER_INFO_SIZE >> SECTOR_SHIFT);
+
+	if (zone->wp == zone->start + zone->len)
+		zone->cond = BLK_ZONE_COND_FULL;
+}
+
+int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
+{
+	sector_t zone_sectors;
+	sector_t nr_sectors;
+	u8 zone_sectors_shift;
+	u32 sb_zone;
+	u32 nr_zones;
+
+	zone_sectors = bdev_zone_sectors(bdev);
+	zone_sectors_shift = ilog2(zone_sectors);
+	nr_sectors = bdev->bd_part->nr_sects;
+	nr_zones = nr_sectors >> zone_sectors_shift;
+
+	sb_zone = sb_zone_number(zone_sectors_shift + SECTOR_SHIFT, mirror);
+	if (sb_zone + 1 >= nr_zones)
+		return -ENOENT;
+
+	return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+				sb_zone << zone_sectors_shift,
+				zone_sectors * BTRFS_NR_SB_LOG_ZONES, GFP_NOFS);
+}

fs/btrfs/zoned.h

@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef BTRFS_ZONED_H
+#define BTRFS_ZONED_H
+
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include "volumes.h"
+#include "disk-io.h"
+
+struct btrfs_zoned_device_info {
+	/*
+	 * Number of zones, zone size and types of zones if bdev is a
+	 * zoned block device.
+	 */
+	u64 zone_size;
+	u8  zone_size_shift;
+	u64 max_zone_append_size;
+	u32 nr_zones;
+	unsigned long *seq_zones;
+	unsigned long *empty_zones;
+	struct blk_zone sb_zones[2 * BTRFS_SUPER_MIRROR_MAX];
+};
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+		       struct blk_zone *zone);
+int btrfs_get_dev_zone_info(struct btrfs_device *device);
+void btrfs_destroy_dev_zone_info(struct btrfs_device *device);
+int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info);
+int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info);
+int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw,
+			       u64 *bytenr_ret);
+int btrfs_sb_log_location(struct btrfs_device *device, int mirror, int rw,
+			  u64 *bytenr_ret);
+void btrfs_advance_sb_log(struct btrfs_device *device, int mirror);
+int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror);
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
+				     struct blk_zone *zone)
+{
+	return 0;
+}
+
+static inline int btrfs_get_dev_zone_info(struct btrfs_device *device)
+{
+	return 0;
+}
+
+static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { }
+
+static inline int btrfs_check_zoned_mode(const struct btrfs_fs_info *fs_info)
+{
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	btrfs_err(fs_info, "zoned block devices support is not enabled");
+	return -EOPNOTSUPP;
+}
+
+static inline int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info)
+{
+	return 0;
+}
+
+static inline int btrfs_sb_log_location_bdev(struct block_device *bdev,
+					     int mirror, int rw, u64 *bytenr_ret)
+{
+	*bytenr_ret = btrfs_sb_offset(mirror);
+	return 0;
+}
+
+static inline int btrfs_sb_log_location(struct btrfs_device *device, int mirror,
+					int rw, u64 *bytenr_ret)
+{
+	*bytenr_ret = btrfs_sb_offset(mirror);
+	return 0;
+}
+
+static inline void btrfs_advance_sb_log(struct btrfs_device *device, int mirror)
+{ }
+
+static inline int btrfs_reset_sb_log_zones(struct block_device *bdev, int mirror)
+{
+	return 0;
+}
+
+#endif
+
+static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return false;
+
+	return test_bit(pos >> zone_info->zone_size_shift, zone_info->seq_zones);
+}
+
+static inline bool btrfs_dev_is_empty_zone(struct btrfs_device *device, u64 pos)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+
+	if (!zone_info)
+		return true;
+
+	return test_bit(pos >> zone_info->zone_size_shift, zone_info->empty_zones);
+}
+
+static inline void btrfs_dev_set_empty_zone_bit(struct btrfs_device *device,
+						u64 pos, bool set)
+{
+	struct btrfs_zoned_device_info *zone_info = device->zone_info;
+	unsigned int zno;
+
+	if (!zone_info)
+		return;
+
+	zno = pos >> zone_info->zone_size_shift;
+	if (set)
+		set_bit(zno, zone_info->empty_zones);
+	else
+		clear_bit(zno, zone_info->empty_zones);
+}
+
+static inline void btrfs_dev_set_zone_empty(struct btrfs_device *device, u64 pos)
+{
+	btrfs_dev_set_empty_zone_bit(device, pos, true);
+}
+
+static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, u64 pos)
+{
+	btrfs_dev_set_empty_zone_bit(device, pos, false);
+}
+
+static inline bool btrfs_check_device_zone_type(const struct btrfs_fs_info *fs_info,
+						struct block_device *bdev)
+{
+	u64 zone_size;
+
+	if (btrfs_is_zoned(fs_info)) {
+		zone_size = bdev_zone_sectors(bdev) << SECTOR_SHIFT;
+		/* Do not allow non-zoned device */
+		return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size;
+	}
+
+	/* Do not allow Host Manged zoned device */
+	return bdev_zoned_model(bdev) != BLK_ZONED_HM;
+}
+
+static inline bool btrfs_check_super_location(struct btrfs_device *device, u64 pos)
+{
+	/*
+	 * On a non-zoned device, any address is OK. On a zoned device,
+	 * non-SEQUENTIAL WRITE REQUIRED zones are capable.
+	 */
+	return device->zone_info == NULL || !btrfs_dev_is_sequential(device, pos);
+}
+
+#endif

include/uapi/linux/btrfs.h

@@ -307,6 +307,7 @@ struct btrfs_ioctl_fs_info_args {
 #define BTRFS_FEATURE_INCOMPAT_NO_HOLES		(1ULL << 9)
 #define BTRFS_FEATURE_INCOMPAT_METADATA_UUID	(1ULL << 10)
 #define BTRFS_FEATURE_INCOMPAT_RAID1C34		(1ULL << 11)
+#define BTRFS_FEATURE_INCOMPAT_ZONED		(1ULL << 12)
 
 struct btrfs_ioctl_feature_flags {
 	__u64 compat_flags;

include/uapi/linux/btrfs_tree.h

@@ -299,7 +299,8 @@
  */
 #define BTRFS_STRING_ITEM_KEY	253
 
-
+/* Maximum metadata block size (nodesize) */
+#define BTRFS_MAX_METADATA_BLOCKSIZE			65536
 
 /* 32 bytes in various csum fields */
 #define BTRFS_CSUM_SIZE 32