21 files changed, 315 insertions, 225 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index c3aecfb0a71d..e0375ba9d0fe 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -440,39 +440,26 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 	btrfs_put_caching_control(caching_ctl);
 }
 
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
+static int btrfs_caching_ctl_wait_done(struct btrfs_block_group *cache,
+				       struct btrfs_caching_control *caching_ctl)
+{
+	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
+	return cache->cached == BTRFS_CACHE_ERROR ? -EIO : 0;
+}
+
+static int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache)
 {
 	struct btrfs_caching_control *caching_ctl;
-	int ret = 0;
+	int ret;
 
 	caching_ctl = btrfs_get_caching_control(cache);
 	if (!caching_ctl)
 		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;
-
-	wait_event(caching_ctl->wait, btrfs_block_group_done(cache));
-	if (cache->cached == BTRFS_CACHE_ERROR)
-		ret = -EIO;
+	ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	btrfs_put_caching_control(caching_ctl);
 	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)
 {
@@ -750,9 +737,8 @@ done:
 	btrfs_put_block_group(block_group);
 }
 
-int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only)
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
 {
-	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_caching_control *caching_ctl = NULL;
 	int ret = 0;
@@ -785,10 +771,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 	}
 	WARN_ON(cache->caching_ctl);
 	cache->caching_ctl = caching_ctl;
-	if (btrfs_test_opt(fs_info, SPACE_CACHE))
-		cache->cached = BTRFS_CACHE_FAST;
-	else
-		cache->cached = BTRFS_CACHE_STARTED;
+	cache->cached = BTRFS_CACHE_STARTED;
 	cache->has_caching_ctl = 1;
 	spin_unlock(&cache->lock);
 
@@ -801,8 +784,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, int load_cache_only
 
 	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 (wait && caching_ctl)
+		ret = btrfs_caching_ctl_wait_done(cache, caching_ctl);
 	if (caching_ctl)
 		btrfs_put_caching_control(caching_ctl);
 
@@ -1640,9 +1623,11 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 				div64_u64(zone_unusable * 100, bg->length));
 		trace_btrfs_reclaim_block_group(bg);
 		ret = btrfs_relocate_chunk(fs_info, bg->start);
-		if (ret)
+		if (ret) {
+			btrfs_dec_block_group_ro(bg);
 			btrfs_err(fs_info, "error relocating chunk %llu",
 				  bg->start);
+		}
 
 next:
 		btrfs_put_block_group(bg);
@@ -3310,7 +3295,7 @@ int btrfs_update_block_group(struct btrfs_trans_handle *trans,
 		 * space back to the block group, otherwise we will leak space.
 		 */
 		if (!alloc && !btrfs_block_group_done(cache))
-			btrfs_cache_block_group(cache, 1);
+			btrfs_cache_block_group(cache, true);
 
 		byte_in_group = bytenr - cache->start;
 		WARN_ON(byte_in_group > cache->length);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index 35e0e860cc0b..6b3cdc4cbc41 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -263,9 +263,7 @@ void btrfs_dec_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_nocow_writers(struct btrfs_block_group *bg);
 void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
 				           u64 num_bytes);
-int btrfs_wait_block_group_cache_done(struct btrfs_block_group *cache);
-int btrfs_cache_block_group(struct btrfs_block_group *cache,
-			    int load_cache_only);
+int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait);
 void btrfs_put_caching_control(struct btrfs_caching_control *ctl);
 struct btrfs_caching_control *btrfs_get_caching_control(
 		struct btrfs_block_group *cache);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 6e556031a8f3..ebfa35fe1c38 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2075,6 +2075,9 @@ cow_done:
 
 		if (!p->skip_locking) {
 			level = btrfs_header_level(b);
+
+			btrfs_maybe_reset_lockdep_class(root, b);
+
 			if (level <= write_lock_level) {
 				btrfs_tree_lock(b);
 				p->locks[level] = BTRFS_WRITE_LOCK;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4db85b9dc7ed..df8c99c99df9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -505,7 +505,6 @@ struct btrfs_free_cluster {
 enum btrfs_caching_type {
 	BTRFS_CACHE_NO,
 	BTRFS_CACHE_STARTED,
-	BTRFS_CACHE_FAST,
 	BTRFS_CACHE_FINISHED,
 	BTRFS_CACHE_ERROR,
 };
@@ -1089,8 +1088,6 @@ struct btrfs_fs_info {
 
 	spinlock_t zone_active_bgs_lock;
 	struct list_head zone_active_bgs;
-	/* Waiters when BTRFS_FS_NEED_ZONE_FINISH is set */
-	wait_queue_head_t zone_finish_wait;
 
 	/* Updates are not protected by any lock */
 	struct btrfs_commit_stats commit_stats;
@@ -1173,6 +1170,8 @@ enum {
 	BTRFS_ROOT_ORPHAN_CLEANUP,
 	/* This root has a drop operation that was started previously. */
 	BTRFS_ROOT_UNFINISHED_DROP,
+	/* This reloc root needs to have its buffers lockdep class reset. */
+	BTRFS_ROOT_RESET_LOCKDEP_CLASS,
 };
 
 static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f43196a893ca..41cddd3ff059 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -165,7 +165,7 @@ no_valid_dev_replace_entry_found:
 		 */
 		if (btrfs_find_device(fs_info->fs_devices, &args)) {
 			btrfs_err(fs_info,
-			"replace devid present without an active replace item");
+"replace without active item, run 'device scan --forget' on the target device");
 			ret = -EUCLEAN;
 		} else {
 			dev_replace->srcdev = NULL;
@@ -1129,8 +1129,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		up_write(&dev_replace->rwsem);
 
 		/* Scrub for replace must not be running in suspended state */
-		ret = btrfs_scrub_cancel(fs_info);
-		ASSERT(ret != -ENOTCONN);
+		btrfs_scrub_cancel(fs_info);
 
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4c3166f3c725..1af28b066b42 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -87,88 +87,6 @@ struct async_submit_bio {
 };
 
 /*
- * Lockdep class keys for extent_buffer->lock's in this root.  For a given
- * eb, the lockdep key is determined by the btrfs_root it belongs to and
- * the level the eb occupies in the tree.
- *
- * Different roots are used for different purposes and may nest inside each
- * other and they require separate keysets.  As lockdep keys should be
- * static, assign keysets according to the purpose of the root as indicated
- * by btrfs_root->root_key.objectid.  This ensures that all special purpose
- * roots have separate keysets.
- *
- * Lock-nesting across peer nodes is always done with the immediate parent
- * node locked thus preventing deadlock.  As lockdep doesn't know this, use
- * subclass to avoid triggering lockdep warning in such cases.
- *
- * The key is set by the readpage_end_io_hook after the buffer has passed
- * csum validation but before the pages are unlocked.  It is also set by
- * btrfs_init_new_buffer on freshly allocated blocks.
- *
- * We also add a check to make sure the highest level of the tree is the
- * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
- * needs update as well.
- */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# if BTRFS_MAX_LEVEL != 8
-#  error
-# endif
-
-#define DEFINE_LEVEL(stem, level)					\
-	.names[level] = "btrfs-" stem "-0" #level,
-
-#define DEFINE_NAME(stem)						\
-	DEFINE_LEVEL(stem, 0)						\
-	DEFINE_LEVEL(stem, 1)						\
-	DEFINE_LEVEL(stem, 2)						\
-	DEFINE_LEVEL(stem, 3)						\
-	DEFINE_LEVEL(stem, 4)						\
-	DEFINE_LEVEL(stem, 5)						\
-	DEFINE_LEVEL(stem, 6)						\
-	DEFINE_LEVEL(stem, 7)
-
-static struct btrfs_lockdep_keyset {
-	u64			id;		/* root objectid */
-	/* Longest entry: btrfs-free-space-00 */
-	char			names[BTRFS_MAX_LEVEL][20];
-	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
-} btrfs_lockdep_keysets[] = {
-	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
-	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
-	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
-	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
-	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
-	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
-	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
-	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
-	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
-	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
-	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
-	{ .id = 0,				DEFINE_NAME("tree")	},
-};
-
-#undef DEFINE_LEVEL
-#undef DEFINE_NAME
-
-void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
-				    int level)
-{
-	struct btrfs_lockdep_keyset *ks;
-
-	BUG_ON(level >= ARRAY_SIZE(ks->keys));
-
-	/* find the matching keyset, id 0 is the default entry */
-	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
-		if (ks->id == objectid)
-			break;
-
-	lockdep_set_class_and_name(&eb->lock,
-				   &ks->keys[level], ks->names[level]);
-}
-
-#endif
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -3150,7 +3068,6 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	init_waitqueue_head(&fs_info->transaction_blocked_wait);
 	init_waitqueue_head(&fs_info->async_submit_wait);
 	init_waitqueue_head(&fs_info->delayed_iputs_wait);
-	init_waitqueue_head(&fs_info->zone_finish_wait);
 
 	/* Usable values until the real ones are cached from the superblock */
 	fs_info->nodesize = 4096;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8993b428e09c..47ad8e0a2d33 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -137,14 +137,4 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags);
 int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid);
 int btrfs_init_root_free_objectid(struct btrfs_root *root);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void btrfs_set_buffer_lockdep_class(u64 objectid,
-			            struct extent_buffer *eb, int level);
-#else
-static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
-					struct extent_buffer *eb, int level)
-{
-}
-#endif
-
 #endif
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ea3ec1e761e8..6914cd8024ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2551,17 +2551,10 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
 		return -EINVAL;
 
 	/*
-	 * pull in the free space cache (if any) so that our pin
-	 * removes the free space from the cache.  We have load_only set
-	 * to one because the slow code to read in the free extents does check
-	 * the pinned extents.
+	 * Fully cache the free space first so that our pin removes the free space
+	 * from the cache.
 	 */
-	btrfs_cache_block_group(cache, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(cache);
+	ret = btrfs_cache_block_group(cache, true);
 	if (ret)
 		goto out;
 
@@ -2584,12 +2577,7 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
 	if (!block_group)
 		return -EINVAL;
 
-	btrfs_cache_block_group(block_group, 1);
-	/*
-	 * Make sure we wait until the cache is completely built in case it is
-	 * missing or is invalid and therefore needs to be rebuilt.
-	 */
-	ret = btrfs_wait_block_group_cache_done(block_group);
+	ret = btrfs_cache_block_group(block_group, true);
 	if (ret)
 		goto out;
 
@@ -4399,7 +4387,7 @@ have_block_group:
 		ffe_ctl->cached = btrfs_block_group_done(block_group);
 		if (unlikely(!ffe_ctl->cached)) {
 			ffe_ctl->have_caching_bg = true;
-			ret = btrfs_cache_block_group(block_group, 0);
+			ret = btrfs_cache_block_group(block_group, false);
 
 			/*
 			 * If we get ENOMEM here or something else we want to
@@ -4867,6 +4855,7 @@ 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;
+	u64 lockdep_owner = owner;
 
 	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner, level);
 	if (IS_ERR(buf))
@@ -4886,11 +4875,26 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	}
 
 	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 *
+	 * The exception however is in replace_path() in relocation, where we
+	 * hold the lock on the original fs root and then search for the reloc
+	 * root.  At that point we need to make sure any reloc root buffers are
+	 * set to the BTRFS_TREE_RELOC_OBJECTID lockdep class in order to make
+	 * lockdep happy.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID &&
+	    !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	/*
 	 * 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_set_buffer_lockdep_class(lockdep_owner, buf, level);
+
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
@@ -6153,13 +6157,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 		if (end - start >= range->minlen) {
 			if (!btrfs_block_group_done(cache)) {
-				ret = btrfs_cache_block_group(cache, 0);
-				if (ret) {
-					bg_failed++;
-					bg_ret = ret;
-					continue;
-				}
-				ret = btrfs_wait_block_group_cache_done(cache);
+				ret = btrfs_cache_block_group(cache, true);
 				if (ret) {
 					bg_failed++;
 					bg_ret = ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index bfae67c593c5..cf4f19e80e2f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3233,7 +3233,7 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	u32 bio_size = bio->bi_iter.bi_size;
 	u32 real_size;
 	const sector_t sector = disk_bytenr >> SECTOR_SHIFT;
-	bool contig;
+	bool contig = false;
 	int ret;
 
 	ASSERT(bio);
@@ -3242,10 +3242,35 @@ static int btrfs_bio_add_page(struct btrfs_bio_ctrl *bio_ctrl,
 	if (bio_ctrl->compress_type != compress_type)
 		return 0;
 
-	if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE)
+
+	if (bio->bi_iter.bi_size == 0) {
+		/* We can always add a page into an empty bio. */
+		contig = true;
+	} else if (bio_ctrl->compress_type == BTRFS_COMPRESS_NONE) {
+		struct bio_vec *bvec = bio_last_bvec_all(bio);
+
+		/*
+		 * The contig check requires the following conditions to be met:
+		 * 1) The pages are belonging to the same inode
+		 *    This is implied by the call chain.
+		 *
+		 * 2) The range has adjacent logical bytenr
+		 *
+		 * 3) The range has adjacent file offset
+		 *    This is required for the usage of btrfs_bio->file_offset.
+		 */
+		if (bio_end_sector(bio) == sector &&
+		    page_offset(bvec->bv_page) + bvec->bv_offset +
+		    bvec->bv_len == page_offset(page) + pg_offset)
+			contig = true;
+	} else {
+		/*
+		 * For compression, all IO should have its logical bytenr
+		 * set to the starting bytenr of the compressed extent.
+		 */
 		contig = bio->bi_iter.bi_sector == sector;
-	else
-		contig = bio_end_sector(bio) == sector;
+	}
+
 	if (!contig)
 		return 0;
 
@@ -6140,6 +6165,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *exists = NULL;
 	struct page *p;
 	struct address_space *mapping = fs_info->btree_inode->i_mapping;
+	u64 lockdep_owner = owner_root;
 	int uptodate = 1;
 	int ret;
 
@@ -6164,7 +6190,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
-	btrfs_set_buffer_lockdep_class(owner_root, eb, level);
+
+	/*
+	 * The reloc trees are just snapshots, so we need them to appear to be
+	 * just like any other fs tree WRT lockdep.
+	 */
+	if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID)
+		lockdep_owner = BTRFS_FS_TREE_OBJECTID;
+
+	btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level);
 
 	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66c822182ecc..5a3f6e0d9688 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2482,6 +2482,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
@@ -2498,6 +2499,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
 		btrfs_set_file_extent_offset(leaf, fi, 0);
+		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
 		btrfs_mark_buffer_dirty(leaf);
 		goto out;
 	}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f0c97d25b4a0..1372210869b1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1644,10 +1644,9 @@ static noinline int run_delalloc_zoned(struct btrfs_inode *inode,
 			done_offset = end;
 
 		if (done_offset == start) {
-			struct btrfs_fs_info *info = inode->root->fs_info;
-
-			wait_var_event(&info->zone_finish_wait,
-				       !test_bit(BTRFS_FS_NEED_ZONE_FINISH, &info->flags));
+			wait_on_bit_io(&inode->root->fs_info->flags,
+				       BTRFS_FS_NEED_ZONE_FINISH,
+				       TASK_UNINTERRUPTIBLE);
 			continue;
 		}
 
@@ -7694,6 +7693,20 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
 	bool unlock_extents = false;
 
 	/*
+	 * We could potentially fault if we have a buffer > PAGE_SIZE, and if
+	 * we're NOWAIT we may submit a bio for a partial range and return
+	 * EIOCBQUEUED, which would result in an errant short read.
+	 *
+	 * The best way to handle this would be to allow for partial completions
+	 * of iocb's, so we could submit the partial bio, return and fault in
+	 * the rest of the pages, and then submit the io for the rest of the
+	 * range.  However we don't have that currently, so simply return
+	 * -EAGAIN at this point so that the normal path is used.
+	 */
+	if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE)
+		return -EAGAIN;
+
+	/*
 	 * Cap the size of reads to that usually seen in buffered I/O as we need
 	 * to allocate a contiguous array for the checksums.
 	 */
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 33461b4f9c8b..9063072b399b 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -14,6 +14,93 @@
 #include "locking.h"
 
 /*
+ * Lockdep class keys for extent_buffer->lock's in this root.  For a given
+ * eb, the lockdep key is determined by the btrfs_root it belongs to and
+ * the level the eb occupies in the tree.
+ *
+ * Different roots are used for different purposes and may nest inside each
+ * other and they require separate keysets.  As lockdep keys should be
+ * static, assign keysets according to the purpose of the root as indicated
+ * by btrfs_root->root_key.objectid.  This ensures that all special purpose
+ * roots have separate keysets.
+ *
+ * Lock-nesting across peer nodes is always done with the immediate parent
+ * node locked thus preventing deadlock.  As lockdep doesn't know this, use
+ * subclass to avoid triggering lockdep warning in such cases.
+ *
+ * The key is set by the readpage_end_io_hook after the buffer has passed
+ * csum validation but before the pages are unlocked.  It is also set by
+ * btrfs_init_new_buffer on freshly allocated blocks.
+ *
+ * We also add a check to make sure the highest level of the tree is the
+ * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
+ * needs update as well.
+ */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if BTRFS_MAX_LEVEL != 8
+#error
+#endif
+
+#define DEFINE_LEVEL(stem, level)					\
+	.names[level] = "btrfs-" stem "-0" #level,
+
+#define DEFINE_NAME(stem)						\
+	DEFINE_LEVEL(stem, 0)						\
+	DEFINE_LEVEL(stem, 1)						\
+	DEFINE_LEVEL(stem, 2)						\
+	DEFINE_LEVEL(stem, 3)						\
+	DEFINE_LEVEL(stem, 4)						\
+	DEFINE_LEVEL(stem, 5)						\
+	DEFINE_LEVEL(stem, 6)						\
+	DEFINE_LEVEL(stem, 7)
+
+static struct btrfs_lockdep_keyset {
+	u64			id;		/* root objectid */
+	/* Longest entry: btrfs-free-space-00 */
+	char			names[BTRFS_MAX_LEVEL][20];
+	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
+} btrfs_lockdep_keysets[] = {
+	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
+	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
+	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
+	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
+	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
+	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
+	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
+	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
+	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
+	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
+	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
+	{ .id = 0,				DEFINE_NAME("tree")	},
+};
+
+#undef DEFINE_LEVEL
+#undef DEFINE_NAME
+
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level)
+{
+	struct btrfs_lockdep_keyset *ks;
+
+	BUG_ON(level >= ARRAY_SIZE(ks->keys));
+
+	/* Find the matching keyset, id 0 is the default entry */
+	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
+		if (ks->id == objectid)
+			break;
+
+	lockdep_set_class_and_name(&eb->lock, &ks->keys[level], ks->names[level]);
+}
+
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb)
+{
+	if (test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state))
+		btrfs_set_buffer_lockdep_class(root->root_key.objectid,
+					       eb, btrfs_header_level(eb));
+}
+
+#endif
+
+/*
  * Extent buffer locking
  * =====================
  *
@@ -164,6 +251,8 @@ struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_lock(eb);
 		if (eb == root->node)
 			break;
@@ -185,6 +274,8 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root)
 
 	while (1) {
 		eb = btrfs_root_node(root);
+
+		btrfs_maybe_reset_lockdep_class(root, eb);
 		btrfs_tree_read_lock(eb);
 		if (eb == root->node)
 			break;
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index bbc45534ae9a..ab268be09bb5 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -131,4 +131,18 @@ void btrfs_drew_write_unlock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_lock(struct btrfs_drew_lock *lock);
 void btrfs_drew_read_unlock(struct btrfs_drew_lock *lock);
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb, int level);
+void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root, struct extent_buffer *eb);
+#else
+static inline void btrfs_set_buffer_lockdep_class(u64 objectid,
+					struct extent_buffer *eb, int level)
+{
+}
+static inline void btrfs_maybe_reset_lockdep_class(struct btrfs_root *root,
+						   struct extent_buffer *eb)
+{
+}
+#endif
+
 #endif
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index a6dc827e75af..45c02aba2492 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1326,7 +1326,9 @@ again:
 		btrfs_release_path(path);
 
 		path->lowest_level = level;
+		set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+		clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
 		path->lowest_level = 0;
 		if (ret) {
 			if (ret > 0)
@@ -3573,7 +3575,12 @@ int prepare_to_relocate(struct reloc_control *rc)
 		 */
 		return PTR_ERR(trans);
 	}
-	return btrfs_commit_transaction(trans);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret)
+		unset_reloc_control(rc);
+
+	return ret;
 }
 
 static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index a64b26b16904..d647cb2938c0 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -349,9 +349,10 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 	key.offset = ref_id;
 again:
 	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
-	if (ret < 0)
+	if (ret < 0) {
+		err = ret;
 		goto out;
-	if (ret == 0) {
+	} else if (ret == 0) {
 		leaf = path->nodes[0];
 		ref = btrfs_item_ptr(leaf, path->slots[0],
 				     struct btrfs_root_ref);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d0cbeb7ae81c..435559ba94fa 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -199,7 +199,7 @@ static u64 calc_chunk_size(const struct btrfs_fs_info *fs_info, u64 flags)
 	ASSERT(flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
 
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
-		return SZ_1G;
+		return BTRFS_MAX_DATA_CHUNK_SIZE;
 	else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
 		return SZ_32M;
 
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 9e0e0ae2288c..43f905ab0a18 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1233,7 +1233,8 @@ static void extent_err(const struct extent_buffer *eb, int slot,
 }
 
 static int check_extent_item(struct extent_buffer *leaf,
-			     struct btrfs_key *key, int slot)
+			     struct btrfs_key *key, int slot,
+			     struct btrfs_key *prev_key)
 {
 	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
@@ -1453,6 +1454,26 @@ static int check_extent_item(struct extent_buffer *leaf,
 			   total_refs, inline_refs);
 		return -EUCLEAN;
 	}
+
+	if ((prev_key->type == BTRFS_EXTENT_ITEM_KEY) ||
+	    (prev_key->type == BTRFS_METADATA_ITEM_KEY)) {
+		u64 prev_end = prev_key->objectid;
+
+		if (prev_key->type == BTRFS_METADATA_ITEM_KEY)
+			prev_end += fs_info->nodesize;
+		else
+			prev_end += prev_key->offset;
+
+		if (unlikely(prev_end > key->objectid)) {
+			extent_err(leaf, slot,
+	"previous extent [%llu %u %llu] overlaps current extent [%llu %u %llu]",
+				   prev_key->objectid, prev_key->type,
+				   prev_key->offset, key->objectid, key->type,
+				   key->offset);
+			return -EUCLEAN;
+		}
+	}
+
 	return 0;
 }
 
@@ -1621,7 +1642,7 @@ static int check_leaf_item(struct extent_buffer *leaf,
 		break;
 	case BTRFS_EXTENT_ITEM_KEY:
 	case BTRFS_METADATA_ITEM_KEY:
-		ret = check_extent_item(leaf, key, slot);
+		ret = check_extent_item(leaf, key, slot, prev_key);
 		break;
 	case BTRFS_TREE_BLOCK_REF_KEY:
 	case BTRFS_SHARED_DATA_REF_KEY:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index dcf75a8daa20..9205c4a5ca81 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1146,7 +1146,9 @@ again:
 	extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
 					   inode_objectid, parent_objectid, 0,
 					   0);
-	if (!IS_ERR_OR_NULL(extref)) {
+	if (IS_ERR(extref)) {
+		return PTR_ERR(extref);
+	} else if (extref) {
 		u32 item_size;
 		u32 cur_offset = 0;
 		unsigned long base;
@@ -1457,7 +1459,7 @@ static int add_link(struct btrfs_trans_handle *trans,
 	 * on the inode will not free it. We will fixup the link count later.
 	 */
 	if (other_inode->i_nlink == 0)
-		inc_nlink(other_inode);
+		set_nlink(other_inode, 1);
 add_link:
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			     name, namelen, 0, ref_index);
@@ -1600,7 +1602,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				 * free it. We will fixup the link count later.
 				 */
 				if (!ret && inode->i_nlink == 0)
-					inc_nlink(inode);
+					set_nlink(inode, 1);
 			}
 			if (ret < 0)
 				goto out;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 272901514b0c..f63ff91e2883 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2345,8 +2345,11 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
 				    &bdev, &disk_super);
-	if (ret)
+	if (ret) {
+		btrfs_put_dev_args_from_path(args);
 		return ret;
+	}
+
 	args->devid = btrfs_stack_device_id(&disk_super->dev_item);
 	memcpy(args->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE);
 	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
@@ -5264,6 +5267,9 @@ static int decide_stripe_size_regular(struct alloc_chunk_ctl *ctl,
 				       ctl->stripe_size);
 	}
 
+	/* Stripe size should not go beyond 1G. */
+	ctl->stripe_size = min_t(u64, ctl->stripe_size, SZ_1G);
+
 	/* Align to BTRFS_STRIPE_LEN */
 	ctl->stripe_size = round_down(ctl->stripe_size, BTRFS_STRIPE_LEN);
 	ctl->chunk_size = ctl->stripe_size * data_stripes;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 7421abcf325a..5bb8d8c86311 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -371,6 +371,9 @@ static int btrfs_xattr_handler_set(const struct xattr_handler *handler,
 				   const char *name, const void *buffer,
 				   size_t size, int flags)
 {
+	if (btrfs_root_readonly(BTRFS_I(inode)->root))
+		return -EROFS;
+
 	name = xattr_full_name(handler, name);
 	return btrfs_setxattr_trans(inode, name, buffer, size, flags);
 }
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b150b07ba1a7..62e7007a7e46 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -421,10 +421,19 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
 	 * since btrfs adds the pages one by one to a bio, and btrfs cannot
 	 * increase the metadata reservation even if it increases the number of
 	 * extents, it is safe to stick with the limit.
+	 *
+	 * With the zoned emulation, we can have non-zoned device on the zoned
+	 * mode. In this case, we don't have a valid max zone append size. So,
+	 * use max_segments * PAGE_SIZE as the pseudo max_zone_append_size.
 	 */
-	zone_info->max_zone_append_size =
-		min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
-		      (u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	if (bdev_is_zoned(bdev)) {
+		zone_info->max_zone_append_size = min_t(u64,
+			(u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT,
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT);
+	} else {
+		zone_info->max_zone_append_size =
+			(u64)bdev_max_segments(bdev) << PAGE_SHIFT;
+	}
 	if (!IS_ALIGNED(nr_sectors, zone_sectors))
 		zone_info->nr_zones++;
 
@@ -1178,7 +1187,7 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
  * offset.
  */
 static int calculate_alloc_pointer(struct btrfs_block_group *cache,
-				   u64 *offset_ret)
+				   u64 *offset_ret, bool new)
 {
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_root *root;
@@ -1188,6 +1197,21 @@ static int calculate_alloc_pointer(struct btrfs_block_group *cache,
 	int ret;
 	u64 length;
 
+	/*
+	 * Avoid  tree lookups for a new block group, there's no use for it.
+	 * It must always be 0.
+	 *
+	 * Also, we have a lock chain of extent buffer lock -> chunk mutex.
+	 * For new a block group, this function is called from
+	 * btrfs_make_block_group() which is already taking the chunk mutex.
+	 * Thus, we cannot call calculate_alloc_pointer() which takes extent
+	 * buffer locks to avoid deadlock.
+	 */
+	if (new) {
+		*offset_ret = 0;
+		return 0;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -1323,6 +1347,13 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		else
 			num_conventional++;
 
+		/*
+		 * Consider a zone as active if we can allow any number of
+		 * active zones.
+		 */
+		if (!device->zone_info->max_active_zones)
+			__set_bit(i, active);
+
 		if (!is_sequential) {
 			alloc_offsets[i] = WP_CONVENTIONAL;
 			continue;
@@ -1389,45 +1420,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			__set_bit(i, active);
 			break;
 		}
-
-		/*
-		 * Consider a zone as active if we can allow any number of
-		 * active zones.
-		 */
-		if (!device->zone_info->max_active_zones)
-			__set_bit(i, active);
 	}
 
 	if (num_sequential > 0)
 		cache->seq_zone = true;
 
 	if (num_conventional > 0) {
-		/*
-		 * Avoid calling calculate_alloc_pointer() for new BG. It
-		 * is no use for new BG. It must be always 0.
-		 *
-		 * Also, we have a lock chain of extent buffer lock ->
-		 * chunk mutex.  For new BG, this function is called from
-		 * btrfs_make_block_group() which is already taking the
-		 * chunk mutex. Thus, we cannot call
-		 * calculate_alloc_pointer() which takes extent buffer
-		 * locks to avoid deadlock.
-		 */
-
 		/* Zone capacity is always zone size in emulation */
 		cache->zone_capacity = cache->length;
-		if (new) {
-			cache->alloc_offset = 0;
-			goto out;
-		}
-		ret = calculate_alloc_pointer(cache, &last_alloc);
-		if (ret || map->num_stripes == num_conventional) {
-			if (!ret)
-				cache->alloc_offset = last_alloc;
-			else
-				btrfs_err(fs_info,
+		ret = calculate_alloc_pointer(cache, &last_alloc, new);
+		if (ret) {
+			btrfs_err(fs_info,
 			"zoned: failed to determine allocation offset of bg %llu",
-					  cache->start);
+				  cache->start);
+			goto out;
+		} else if (map->num_stripes == num_conventional) {
+			cache->alloc_offset = last_alloc;
+			cache->zone_is_active = 1;
 			goto out;
 		}
 	}
@@ -1495,13 +1504,6 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 		goto out;
 	}
 
-	if (cache->zone_is_active) {
-		btrfs_get_block_group(cache);
-		spin_lock(&fs_info->zone_active_bgs_lock);
-		list_add_tail(&cache->active_bg_list, &fs_info->zone_active_bgs);
-		spin_unlock(&fs_info->zone_active_bgs_lock);
-	}
-
 out:
 	if (cache->alloc_offset > fs_info->zone_size) {
 		btrfs_err(fs_info,
@@ -1526,10 +1528,16 @@ out:
 		ret = -EIO;
 	}
 
-	if (!ret)
+	if (!ret) {
 		cache->meta_write_pointer = cache->alloc_offset + cache->start;
-
-	if (ret) {
+		if (cache->zone_is_active) {
+			btrfs_get_block_group(cache);
+			spin_lock(&fs_info->zone_active_bgs_lock);
+			list_add_tail(&cache->active_bg_list,
+				      &fs_info->zone_active_bgs);
+			spin_unlock(&fs_info->zone_active_bgs_lock);
+		}
+	} else {
 		kfree(cache->physical_map);
 		cache->physical_map = NULL;
 	}
@@ -2007,8 +2015,7 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
 	/* For active_bg_list */
 	btrfs_put_block_group(block_group);
 
-	clear_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
-	wake_up_all(&fs_info->zone_finish_wait);
+	clear_and_wake_up_bit(BTRFS_FS_NEED_ZONE_FINISH, &fs_info->flags);
 
 	return 0;
 }