Merge tag 'for-5.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This brings updates of space handling, performance improvements or bug
  fixes. The subpage block size and zoned mode features have reached
  state where they're usable but with limitations.

  Performance or related:

   - do not block on deleted block group mutex in the cleaner, avoids
     some long stalls

   - improved flushing: make it work better with ticket space
     reservations and avoid excessive transaction commits in some
     scenarios, slightly improves throughput for random write load

   - preemptive background flushing: separate the logic from ticket
     reservations, improve the accounting and decisions when to flush in
     low space conditions

   - less lock contention related to running delayed refs, let just one
     thread do the flushing when there are many inside transaction
     commit

   - dbench workload improvements: avoid unnecessary work when logging
     inodes, fewer fallbacks to transaction commit and thus less waiting
     for it (+7% throughput, -20% latency)

  Core:

   - subpage block size
      - currently read-only support
      - refactor and generalize code where sectorsize is assumed to be
        page size, add the subpage handling everywhere
      - the read-write support is on the way, page sizes are still
        limited to 4K or 64K

   - zoned mode, first working version but with limitations
      - SMR/ZBC/ZNS friendly allocation mode, utilizing the "no fixed
        location for structures" and chunked allocation
      - superblock as the only fixed data structure needs special
        handling, uses 2 consecutive zones as a ring buffer
      - tree-log support with a dedicated block group to avoid unordered
        writes
      - emulated zones on non-zoned devices
      - not yet working
      - all non-single block group profiles, requires more zone write
        pointer synchronization between the multiple block groups
      - fitrim due to dependency on space cache, can be implemented

  Fixes:

   - ref-verify: proper tree owner and node level tracking

   - fix pinned byte accounting, causing some early ENOSPC now more
     likely due to other changes in delayed refs

  Other:

   - error handling fixes and improvements

   - more error injection points

   - more function documentation

   - more and updated tracepoints

   - subset of W=1 checked by default

   - update comments to allow more automatic kdoc parameter checks"

* tag 'for-5.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (144 commits)
  btrfs: zoned: enable to mount ZONED incompat flag
  btrfs: zoned: deal with holes writing out tree-log pages
  btrfs: zoned: reorder log node allocation on zoned filesystem
  btrfs: zoned: serialize log transaction on zoned filesystems
  btrfs: zoned: extend zoned allocator to use dedicated tree-log block group
  btrfs: split alloc_log_tree()
  btrfs: zoned: relocate block group to repair IO failure in zoned filesystems
  btrfs: zoned: enable relocation on a zoned filesystem
  btrfs: zoned: support dev-replace in zoned filesystems
  btrfs: zoned: implement copying for zoned device-replace
  btrfs: zoned: implement cloning for zoned device-replace
  btrfs: zoned: mark block groups to copy for device-replace
  btrfs: zoned: do not use async metadata checksum on zoned filesystems
  btrfs: zoned: wait for existing extents before truncating
  btrfs: zoned: serialize metadata IO
  btrfs: zoned: introduce dedicated data write path for zoned filesystems
  btrfs: zoned: enable zone append writing for direct IO
  btrfs: zoned: use ZONE_APPEND write for zoned mode
  btrfs: save irq flags when looking up an ordered extent
  btrfs: zoned: cache if block group is on a sequential zone
  ...

block/bio.c

@@ -851,6 +851,39 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio,
 }
 EXPORT_SYMBOL(bio_add_pc_page);
 
+/**
+ * bio_add_zone_append_page - attempt to add page to zone-append bio
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ *
+ * Attempt to add a page to the bio_vec maplist of a bio that will be submitted
+ * for a zone-append request. This can fail for a number of reasons, such as the
+ * bio being full or the target block device is not a zoned block device or
+ * other limitations of the target block device. The target block device must
+ * allow bio's up to PAGE_SIZE, so it is always possible to add a single page
+ * to an empty bio.
+ *
+ * Returns: number of bytes added to the bio, or 0 in case of a failure.
+ */
+int bio_add_zone_append_page(struct bio *bio, struct page *page,
+			     unsigned int len, unsigned int offset)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+	bool same_page = false;
+
+	if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
+		return 0;
+
+	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+		return 0;
+
+	return bio_add_hw_page(q, bio, page, len, offset,
+			       queue_max_zone_append_sectors(q), &same_page);
+}
+EXPORT_SYMBOL_GPL(bio_add_zone_append_page);
+
 /**
  * __bio_try_merge_page - try appending data to an existing bvec.
  * @bio: destination bio

fs/btrfs/Makefile

 # SPDX-License-Identifier: GPL-2.0
 
+# Subset of W=1 warnings
+subdir-ccflags-y += -Wextra -Wunused -Wno-unused-parameter
+subdir-ccflags-y += -Wmissing-declarations
+subdir-ccflags-y += -Wmissing-format-attribute
+subdir-ccflags-y += -Wmissing-prototypes
+subdir-ccflags-y += -Wold-style-definition
+subdir-ccflags-y += -Wmissing-include-dirs
+subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
+subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
+subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
+subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+# The following turn off the warnings enabled by -Wextra
+subdir-ccflags-y += -Wno-missing-field-initializers
+subdir-ccflags-y += -Wno-sign-compare
+subdir-ccflags-y += -Wno-type-limits
+
 obj-$(CONFIG_BTRFS_FS) := btrfs.o
 
 btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
@@ -11,7 +27,8 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
 	   reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
 	   uuid-tree.o props.o free-space-tree.o tree-checker.o space-info.o \
-	   block-rsv.o delalloc-space.o block-group.o discard.o reflink.o
+	   block-rsv.o delalloc-space.o block-group.o discard.o reflink.o \
+	   subpage.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
 btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o

fs/btrfs/backref.c

@@ -1501,7 +1501,13 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
 }
 
 /**
- * btrfs_check_shared - tell us whether an extent is shared
+ * Check if an extent is shared or not
+ *
+ * @root:   root inode belongs to
+ * @inum:   inode number of the inode whose extent we are checking
+ * @bytenr: logical bytenr of the extent we are checking
+ * @roots:  list of roots this extent is shared among
+ * @tmp:    temporary list used for iteration
  *
  * btrfs_check_shared uses the backref walking code but will short
  * circuit as soon as it finds a root or inode that doesn't match the
@@ -2541,13 +2547,6 @@ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache,
 		list_del(&edge->list[UPPER]);
 		btrfs_backref_free_edge(cache, edge);
 
-		if (RB_EMPTY_NODE(&upper->rb_node)) {
-			BUG_ON(!list_empty(&node->upper));
-			btrfs_backref_drop_node(cache, node);
-			node = upper;
-			node->lowest = 1;
-			continue;
-		}
 		/*
 		 * Add the node to leaf node list if no other child block
 		 * cached.
@@ -2624,7 +2623,7 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache,
 		/* Only reloc backref cache cares about a specific root */
 		if (cache->is_reloc) {
 			root = find_reloc_root(cache->fs_info, cur->bytenr);
-			if (WARN_ON(!root))
+			if (!root)
 				return -ENOENT;
 			cur->root = root;
 		} else {

fs/btrfs/backref.h

@@ -296,6 +296,9 @@ static inline void btrfs_backref_free_node(struct btrfs_backref_cache *cache,
 					   struct btrfs_backref_node *node)
 {
 	if (node) {
+		ASSERT(list_empty(&node->list));
+		ASSERT(list_empty(&node->lower));
+		ASSERT(node->eb == NULL);
 		cache->nr_nodes--;
 		btrfs_put_root(node->root);
 		kfree(node);
@@ -340,11 +343,11 @@ static inline void btrfs_backref_drop_node_buffer(
 static inline void btrfs_backref_drop_node(struct btrfs_backref_cache *tree,
 					   struct btrfs_backref_node *node)
 {
-	BUG_ON(!list_empty(&node->upper));
+	ASSERT(list_empty(&node->upper));
 
 	btrfs_backref_drop_node_buffer(node);
-	list_del(&node->list);
-	list_del(&node->lower);
+	list_del_init(&node->list);
+	list_del_init(&node->lower);
 	if (!RB_EMPTY_NODE(&node->rb_node))
 		rb_erase(&node->rb_node, &tree->rb_root);
 	btrfs_backref_free_node(tree, node);

fs/btrfs/block-group.h

@@ -95,6 +95,8 @@ struct btrfs_block_group {
 	unsigned int iref:1;
 	unsigned int has_caching_ctl:1;
 	unsigned int removed:1;
+	unsigned int to_copy:1;
+	unsigned int relocating_repair:1;
 
 	int disk_cache_state;
 
@@ -181,8 +183,19 @@ struct btrfs_block_group {
 	 */
 	int needs_free_space;
 
+	/* Flag indicating this block group is placed on a sequential zone */
+	bool seq_zone;
+
 	/* Record locked full stripes for RAID5/6 block group */
 	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
+
+	/*
+	 * Allocation offset for the block group to implement sequential
+	 * allocation. This is used only on a zoned filesystem.
+	 */
+	u64 alloc_offset;
+	u64 zone_unusable;
+	u64 meta_write_pointer;
 };
 
 static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
@@ -270,6 +283,9 @@ 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);
+int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
+		       struct block_device *bdev, u64 physical, u64 **logical,
+		       int *naddrs, int *stripe_len);
 
 static inline u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
 {
@@ -296,9 +312,4 @@ static inline int btrfs_block_group_done(struct btrfs_block_group *cache)
 void btrfs_freeze_block_group(struct btrfs_block_group *cache);
 void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);
 
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
-		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
-#endif
-
 #endif /* BTRFS_BLOCK_GROUP_H */

fs/btrfs/btrfs_inode.h

@@ -325,7 +325,8 @@ struct btrfs_dio_private {
 	struct inode *inode;
 	u64 logical_offset;
 	u64 disk_bytenr;
-	u64 bytes;
+	/* Used for bio::bi_size */
+	u32 bytes;
 
 	/*
 	 * References to this structure. There is one reference per in-flight

fs/btrfs/compression.c

@@ -542,13 +542,19 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			goto next;
 		}
 
-		end = last_offset + PAGE_SIZE - 1;
 		/*
 		 * at this point, we have a locked page in the page cache
 		 * for these bytes in the file.  But, we have to make
 		 * sure they map to this compressed extent on disk.
 		 */
-		set_page_extent_mapped(page);
+		ret = set_page_extent_mapped(page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			break;
+		}
+
+		end = last_offset + PAGE_SIZE - 1;
 		lock_extent(tree, last_offset, end);
 		read_lock(&em_tree->lock);
 		em = lookup_extent_mapping(em_tree, last_offset,

fs/btrfs/ctree.c

@@ -221,9 +221,12 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_inc_ref(trans, root, cow, 1);
 	else
 		ret = btrfs_inc_ref(trans, root, cow, 0);
-
-	if (ret)
+	if (ret) {
+		btrfs_tree_unlock(cow);
+		free_extent_buffer(cow);
+		btrfs_abort_transaction(trans, ret);
 		return ret;
+	}
 
 	btrfs_mark_buffer_dirty(cow);
 	*cow_ret = cow;
@@ -1494,6 +1497,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	return ret;
 }
+ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO);
 
 /*
  * helper function for defrag to decide if two blocks pointed to by a
@@ -2821,6 +2825,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		btrfs_release_path(p);
 	return ret;
 }
+ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO);
 
 /*
  * Like btrfs_search_slot, this looks for a key in the given tree. It uses the

fs/btrfs/ctree.h

@@ -298,7 +298,8 @@ struct btrfs_super_block {
 	 BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA |	\
 	 BTRFS_FEATURE_INCOMPAT_NO_HOLES	|	\
 	 BTRFS_FEATURE_INCOMPAT_METADATA_UUID	|	\
-	 BTRFS_FEATURE_INCOMPAT_RAID1C34)
+	 BTRFS_FEATURE_INCOMPAT_RAID1C34	|	\
+	 BTRFS_FEATURE_INCOMPAT_ZONED)
 
 #define BTRFS_FEATURE_INCOMPAT_SAFE_SET			\
 	(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -797,7 +798,7 @@ struct btrfs_fs_info {
 	/* used to keep from writing metadata until there is a nice batch */
 	struct percpu_counter dirty_metadata_bytes;
 	struct percpu_counter delalloc_bytes;
-	struct percpu_counter dio_bytes;
+	struct percpu_counter ordered_bytes;
 	s32 dirty_metadata_batch;
 	s32 delalloc_batch;
 
@@ -933,6 +934,7 @@ struct btrfs_fs_info {
 	/* Used to reclaim the metadata space in the background. */
 	struct work_struct async_reclaim_work;
 	struct work_struct async_data_reclaim_work;
+	struct work_struct preempt_reclaim_work;
 
 	spinlock_t unused_bgs_lock;
 	struct list_head unused_bgs;
@@ -974,6 +976,9 @@ struct btrfs_fs_info {
 
 	/* Max size to emit ZONE_APPEND write command */
 	u64 max_zone_append_size;
+	struct mutex zoned_meta_io_lock;
+	spinlock_t treelog_bg_lock;
+	u64 treelog_bg;
 
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 	spinlock_t ref_verify_lock;
@@ -1104,7 +1109,7 @@ struct btrfs_root {
 
 	u32 type;
 
-	u64 highest_objectid;
+	u64 free_objectid;
 
 	struct btrfs_key defrag_progress;
 	struct btrfs_key defrag_max;
@@ -2740,6 +2745,7 @@ enum btrfs_flush_state {
 	ALLOC_CHUNK_FORCE	=	8,
 	RUN_DELAYED_IPUTS	=	9,
 	COMMIT_TRANS		=	10,
+	FORCE_COMMIT_TRANS	=	11,
 };
 
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
@@ -3100,15 +3106,14 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       u32 min_type);
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
 			       bool in_reclaim_context);
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *new_root,
-			     struct btrfs_root *parent_root,
-			     u64 new_dirid);
+			     struct btrfs_root *parent_root);
  void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 			       unsigned *bits);
 void btrfs_clear_delalloc_extent(struct inode *inode,
@@ -3119,6 +3124,8 @@ void btrfs_split_delalloc_extent(struct inode *inode,
 				 struct extent_state *orig, u64 split);
 int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio,
 			     unsigned long bio_flags);
+bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio,
+				      unsigned int size);
 void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);

fs/btrfs/delalloc-space.c

@@ -191,12 +191,14 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode,
 }
 
 /**
- * btrfs_inode_rsv_release - release any excessive reservation.
- * @inode - the inode we need to release from.
- * @qgroup_free - free or convert qgroup meta.
- *   Unlike normal operation, qgroup meta reservation needs to know if we are
- *   freeing qgroup reservation or just converting it into per-trans.  Normally
- *   @qgroup_free is true for error handling, and false for normal release.
+ * Release any excessive reservation
+ *
+ * @inode:       the inode we need to release from
+ * @qgroup_free: free or convert qgroup meta. Unlike normal operation, qgroup
+ *               meta reservation needs to know if we are freeing qgroup
+ *               reservation or just converting it into per-trans.  Normally
+ *               @qgroup_free is true for error handling, and false for normal
+ *               release.
  *
  * This is the same as btrfs_block_rsv_release, except that it handles the
  * tracepoint for the reservation.
@@ -361,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 }
 
 /**
- * btrfs_delalloc_release_metadata - release a metadata reservation for an inode
+ * Release a metadata reservation for an inode
+ *
  * @inode: the inode to release the reservation for.
  * @num_bytes: the number of bytes we are releasing.
  * @qgroup_free: free qgroup reservation or convert it to per-trans reservation
@@ -455,11 +458,13 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 }
 
 /**
- * btrfs_delalloc_release_space - release data and metadata space for delalloc
- * @inode: inode we're releasing space for
- * @start: start position of the space already reserved
- * @len: the len of the space already reserved
- * @release_bytes: the len of the space we consumed or didn't use
+ * Release data and metadata space for delalloc
+ *
+ * @inode:       inode we're releasing space for
+ * @reserved:    list of changed/reserved ranges
+ * @start:       start position of the space already reserved
+ * @len:         length of the space already reserved
+ * @qgroup_free: should qgroup reserved-space also be freed
  *
  * This function will release the metadata space that was not used and will
  * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes

fs/btrfs/delayed-inode.c

@@ -1154,7 +1154,7 @@ static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans, int nr)
 	delayed_root = fs_info->delayed_root;
 
 	curr_node = btrfs_first_delayed_node(delayed_root);
-	while (curr_node && (!count || (count && nr--))) {
+	while (curr_node && (!count || nr--)) {
 		ret = __btrfs_commit_inode_delayed_items(trans, path,
 							 curr_node);
 		if (ret) {

fs/btrfs/delayed-ref.c

@@ -69,9 +69,10 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans)
 }
 
 /**
- * btrfs_delayed_refs_rsv_release - release a ref head's reservation.
- * @fs_info - the fs_info for our fs.
- * @nr - the number of items to drop.
+ * Release a ref head's reservation
+ *
+ * @fs_info:  the filesystem
+ * @nr:       number of items to drop
  *
  * This drops the delayed ref head's count from the delayed refs rsv and frees
  * any excess reservation we had.
@@ -114,10 +115,11 @@ void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
 }
 
 /**
- * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv.
- * @fs_info - the fs info for our fs.
- * @src - the source block rsv to transfer from.
- * @num_bytes - the number of bytes to transfer.
+ * Transfer bytes to our delayed refs rsv
+ *
+ * @fs_info:   the filesystem
+ * @src:       source block rsv to transfer from
+ * @num_bytes: number of bytes to transfer
  *
  * This transfers up to the num_bytes amount from the src rsv to the
  * delayed_refs_rsv.  Any extra bytes are returned to the space info.
@@ -162,9 +164,10 @@ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
 }
 
 /**
- * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage.
- * @fs_info - the fs_info for our fs.
- * @flush - control how we can flush for this reservation.
+ * Refill based on our delayed refs usage
+ *
+ * @fs_info: the filesystem
+ * @flush:   control how we can flush for this reservation.
  *
  * This will refill the delayed block_rsv up to 1 items size worth of space and
  * will return -ENOSPC if we can't make the reservation.
@@ -648,12 +651,12 @@ static int insert_delayed_ref(struct btrfs_trans_handle *trans,
  */
 static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
 			 struct btrfs_delayed_ref_head *existing,
-			 struct btrfs_delayed_ref_head *update,
-			 int *old_ref_mod_ret)
+			 struct btrfs_delayed_ref_head *update)
 {
 	struct btrfs_delayed_ref_root *delayed_refs =
 		&trans->transaction->delayed_refs;
 	struct btrfs_fs_info *fs_info = trans->fs_info;
+	u64 flags = btrfs_ref_head_to_space_flags(existing);
 	int old_ref_mod;
 
 	BUG_ON(existing->is_data != update->is_data);
@@ -701,8 +704,6 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
 	 * currently, for refs we just added we know we're a-ok.
 	 */
 	old_ref_mod = existing->total_ref_mod;
-	if (old_ref_mod_ret)
-		*old_ref_mod_ret = old_ref_mod;
 	existing->ref_mod += update->ref_mod;
 	existing->total_ref_mod += update->ref_mod;
 
@@ -724,6 +725,27 @@ static noinline void update_existing_head_ref(struct btrfs_trans_handle *trans,
 			trans->delayed_ref_updates += csum_leaves;
 		}
 	}
+
+	/*
+	 * This handles the following conditions:
+	 *
+	 * 1. We had a ref mod of 0 or more and went negative, indicating that
+	 *    we may be freeing space, so add our space to the
+	 *    total_bytes_pinned counter.
+	 * 2. We were negative and went to 0 or positive, so no longer can say
+	 *    that the space would be pinned, decrement our counter from the
+	 *    total_bytes_pinned counter.
+	 * 3. We are now at 0 and have ->must_insert_reserved set, which means
+	 *    this was a new allocation and then we dropped it, and thus must
+	 *    add our space to the total_bytes_pinned counter.
+	 */
+	if (existing->total_ref_mod < 0 && old_ref_mod >= 0)
+		btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes);
+	else if (existing->total_ref_mod >= 0 && old_ref_mod < 0)
+		btrfs_mod_total_bytes_pinned(fs_info, flags, -existing->num_bytes);
+	else if (existing->total_ref_mod == 0 && existing->must_insert_reserved)
+		btrfs_mod_total_bytes_pinned(fs_info, flags, existing->num_bytes);
+
 	spin_unlock(&existing->lock);
 }
 
@@ -798,8 +820,7 @@ static noinline struct btrfs_delayed_ref_head *
 add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		     struct btrfs_delayed_ref_head *head_ref,
 		     struct btrfs_qgroup_extent_record *qrecord,
-		     int action, int *qrecord_inserted_ret,
-		     int *old_ref_mod, int *new_ref_mod)
+		     int action, int *qrecord_inserted_ret)
 {
 	struct btrfs_delayed_ref_head *existing;
 	struct btrfs_delayed_ref_root *delayed_refs;
@@ -821,8 +842,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		update_existing_head_ref(trans, existing, head_ref,
-					 old_ref_mod);
+		update_existing_head_ref(trans, existing, head_ref);
 		/*
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
@@ -830,14 +850,17 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
 		head_ref = existing;
 	} else {
-		if (old_ref_mod)
-			*old_ref_mod = 0;
+		u64 flags = btrfs_ref_head_to_space_flags(head_ref);
+
 		if (head_ref->is_data && head_ref->ref_mod < 0) {
 			delayed_refs->pending_csums += head_ref->num_bytes;
 			trans->delayed_ref_updates +=
 				btrfs_csum_bytes_to_leaves(trans->fs_info,
 							   head_ref->num_bytes);
 		}
+		if (head_ref->ref_mod < 0)
+			btrfs_mod_total_bytes_pinned(trans->fs_info, flags,
+						     head_ref->num_bytes);
 		delayed_refs->num_heads++;
 		delayed_refs->num_heads_ready++;
 		atomic_inc(&delayed_refs->num_entries);
@@ -845,8 +868,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	}
 	if (qrecord_inserted_ret)
 		*qrecord_inserted_ret = qrecord_inserted;
-	if (new_ref_mod)
-		*new_ref_mod = head_ref->total_ref_mod;
 
 	return head_ref;
 }
@@ -909,8 +930,7 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
  */
 int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_ref *generic_ref,
-			       struct btrfs_delayed_extent_op *extent_op,
-			       int *old_ref_mod, int *new_ref_mod)
+			       struct btrfs_delayed_extent_op *extent_op)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_tree_ref *ref;
@@ -977,8 +997,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	 * the spin lock
 	 */
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
-					action, &qrecord_inserted,
-					old_ref_mod, new_ref_mod);
+					action, &qrecord_inserted);
 
 	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
@@ -1006,8 +1025,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
  */
 int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_ref *generic_ref,
-			       u64 reserved, int *old_ref_mod,
-			       int *new_ref_mod)
+			       u64 reserved)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_data_ref *ref;
@@ -1073,8 +1091,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	 * the spin lock
 	 */
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
-					action, &qrecord_inserted,
-					old_ref_mod, new_ref_mod);
+					action, &qrecord_inserted);
 
 	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);
@@ -1117,7 +1134,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 	spin_lock(&delayed_refs->lock);
 
 	add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD,
-			     NULL, NULL, NULL);
+			     NULL);
 
 	spin_unlock(&delayed_refs->lock);
 

fs/btrfs/delayed-ref.h

@@ -135,6 +135,11 @@ struct btrfs_delayed_data_ref {
 	u64 offset;
 };
 
+enum btrfs_delayed_ref_flags {
+	/* Indicate that we are flushing delayed refs for the commit */
+	BTRFS_DELAYED_REFS_FLUSHING,
+};
+
 struct btrfs_delayed_ref_root {
 	/* head ref rbtree */
 	struct rb_root_cached href_root;
@@ -158,12 +163,7 @@ struct btrfs_delayed_ref_root {
 
 	u64 pending_csums;
 
-	/*
-	 * set when the tree is flushing before a transaction commit,
-	 * used by the throttling code to decide if new updates need
-	 * to be run right away
-	 */
-	int flushing;
+	unsigned long flags;
 
 	u64 run_delayed_start;
 
@@ -326,6 +326,16 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 	}
 }
 
+static inline u64 btrfs_ref_head_to_space_flags(
+				struct btrfs_delayed_ref_head *head_ref)
+{
+	if (head_ref->is_data)
+		return BTRFS_BLOCK_GROUP_DATA;
+	else if (head_ref->is_system)
+		return BTRFS_BLOCK_GROUP_SYSTEM;
+	return BTRFS_BLOCK_GROUP_METADATA;
+}
+
 static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *head)
 {
 	if (refcount_dec_and_test(&head->refs))
@@ -334,12 +344,10 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea
 
 int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_ref *generic_ref,
-			       struct btrfs_delayed_extent_op *extent_op,
-			       int *old_ref_mod, int *new_ref_mod);
+			       struct btrfs_delayed_extent_op *extent_op);
 int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       struct btrfs_ref *generic_ref,
-			       u64 reserved, int *old_ref_mod,
-			       int *new_ref_mod);
+			       u64 reserved);
 int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
 				struct btrfs_delayed_extent_op *extent_op);

fs/btrfs/dev-replace.c

@@ -22,6 +22,7 @@
 #include "dev-replace.h"
 #include "sysfs.h"
 #include "zoned.h"
+#include "block-group.h"
 
 /*
  * Device replace overview
@@ -459,6 +460,185 @@ static char* btrfs_dev_name(struct btrfs_device *device)
 		return rcu_str_deref(device->name);
 }
 
+static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
+				    struct btrfs_device *src_dev)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	struct btrfs_root *root = fs_info->dev_root;
+	struct btrfs_dev_extent *dev_extent = NULL;
+	struct btrfs_block_group *cache;
+	struct btrfs_trans_handle *trans;
+	int ret = 0;
+	u64 chunk_offset;
+
+	/* Do not use "to_copy" on non zoned filesystem for now */
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	mutex_lock(&fs_info->chunk_mutex);
+
+	/* Ensure we don't have pending new block group */
+	spin_lock(&fs_info->trans_lock);
+	while (fs_info->running_transaction &&
+	       !list_empty(&fs_info->running_transaction->dev_update_list)) {
+		spin_unlock(&fs_info->trans_lock);
+		mutex_unlock(&fs_info->chunk_mutex);
+		trans = btrfs_attach_transaction(root);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			mutex_lock(&fs_info->chunk_mutex);
+			if (ret == -ENOENT) {
+				spin_lock(&fs_info->trans_lock);
+				continue;
+			} else {
+				goto unlock;
+			}
+		}
+
+		ret = btrfs_commit_transaction(trans);
+		mutex_lock(&fs_info->chunk_mutex);
+		if (ret)
+			goto unlock;
+
+		spin_lock(&fs_info->trans_lock);
+	}
+	spin_unlock(&fs_info->trans_lock);
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	path->reada = READA_FORWARD;
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+
+	key.objectid = src_dev->devid;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto free_path;
+	if (ret > 0) {
+		if (path->slots[0] >=
+		    btrfs_header_nritems(path->nodes[0])) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto free_path;
+			if (ret > 0) {
+				ret = 0;
+				goto free_path;
+			}
+		} else {
+			ret = 0;
+		}
+	}
+
+	while (1) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+		if (found_key.objectid != src_dev->devid)
+			break;
+
+		if (found_key.type != BTRFS_DEV_EXTENT_KEY)
+			break;
+
+		if (found_key.offset < key.offset)
+			break;
+
+		dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+
+		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent);
+
+		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+		if (!cache)
+			goto skip;
+
+		spin_lock(&cache->lock);
+		cache->to_copy = 1;
+		spin_unlock(&cache->lock);
+
+		btrfs_put_block_group(cache);
+
+skip:
+		ret = btrfs_next_item(root, path);
+		if (ret != 0) {
+			if (ret > 0)
+				ret = 0;
+			break;
+		}
+	}
+
+free_path:
+	btrfs_free_path(path);
+unlock:
+	mutex_unlock(&fs_info->chunk_mutex);
+
+	return ret;
+}
+
+bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
+				      struct btrfs_block_group *cache,
+				      u64 physical)
+{
+	struct btrfs_fs_info *fs_info = cache->fs_info;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 chunk_offset = cache->start;
+	int num_extents, cur_extent;
+	int i;
+
+	/* Do not use "to_copy" on non zoned filesystem for now */
+	if (!btrfs_is_zoned(fs_info))
+		return true;
+
+	spin_lock(&cache->lock);
+	if (cache->removed) {
+		spin_unlock(&cache->lock);
+		return true;
+	}
+	spin_unlock(&cache->lock);
+
+	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(!IS_ERR(em));
+	map = em->map_lookup;
+
+	num_extents = cur_extent = 0;
+	for (i = 0; i < map->num_stripes; i++) {
+		/* We have more device extent to copy */
+		if (srcdev != map->stripes[i].dev)
+			continue;
+
+		num_extents++;
+		if (physical == map->stripes[i].physical)
+			cur_extent = i;
+	}
+
+	free_extent_map(em);
+
+	if (num_extents > 1 && cur_extent < num_extents - 1) {
+		/*
+		 * Has more stripes on this device. Keep this block group
+		 * readonly until we finish all the stripes.
+		 */
+		return false;
+	}
+
+	/* Last stripe on this device */
+	spin_lock(&cache->lock);
+	cache->to_copy = 0;
+	spin_unlock(&cache->lock);
+
+	return true;
+}
+
 static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
 		int read_src)
@@ -500,6 +680,10 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	if (ret)
 		return ret;
 
+	ret = mark_block_group_to_copy(fs_info, src_device);
+	if (ret)
+		return ret;
+
 	down_write(&dev_replace->rwsem);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
@@ -715,7 +899,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
+	ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;

fs/btrfs/dev-replace.h

@@ -18,5 +18,8 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
 void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info);
 int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info);
 int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace);
+bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
+				      struct btrfs_block_group *cache,
+				      u64 physical);
 
 #endif

fs/btrfs/discard.c

@@ -185,10 +185,12 @@ static struct btrfs_block_group *find_next_block_group(
 }
 
 /**
- * peek_discard_list - wrap find_next_block_group()
- * @discard_ctl: discard control
+ * Wrap find_next_block_group()
+ *
+ * @discard_ctl:   discard control
  * @discard_state: the discard_state of the block_group after state management
  * @discard_index: the discard_index of the block_group after state management
+ * @now:           time when discard was invoked, in ns
  *
  * This wraps find_next_block_group() and sets the block_group to be in use.
  * discard_state's control flow is managed here.  Variables related to

fs/btrfs/disk-io.h

@@ -120,6 +120,8 @@ blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
 				 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_alloc_log_tree_node(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info);
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
@@ -133,8 +135,8 @@ 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 btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_init_root_free_objectid(struct btrfs_root *root);
 int __init btrfs_end_io_wq_init(void);
 void __cold btrfs_end_io_wq_exit(void);
 

fs/btrfs/extent_io.h

@@ -31,16 +31,17 @@ enum {
 	EXTENT_BUFFER_IN_TREE,
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
+	EXTENT_BUFFER_NO_CHECK,
 };
 
 /* these are flags for __process_pages_contig */
 #define PAGE_UNLOCK		(1 << 0)
-#define PAGE_CLEAR_DIRTY	(1 << 1)
-#define PAGE_SET_WRITEBACK	(1 << 2)
-#define PAGE_END_WRITEBACK	(1 << 3)
-#define PAGE_SET_PRIVATE2	(1 << 4)
-#define PAGE_SET_ERROR		(1 << 5)
-#define PAGE_LOCK		(1 << 6)
+/* Page starts writeback, clear dirty bit and set writeback bit */
+#define PAGE_START_WRITEBACK	(1 << 1)
+#define PAGE_END_WRITEBACK	(1 << 2)
+#define PAGE_SET_PRIVATE2	(1 << 3)
+#define PAGE_SET_ERROR		(1 << 4)
+#define PAGE_LOCK		(1 << 5)
 
 /*
  * page->private values.  Every page that is controlled by the extent
@@ -93,6 +94,7 @@ struct extent_buffer {
 	struct rw_semaphore lock;
 
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+	struct list_head release_list;
 #ifdef CONFIG_BTRFS_DEBUG
 	struct list_head leak_list;
 #endif
@@ -178,7 +180,8 @@ int btree_write_cache_pages(struct address_space *mapping,
 void extent_readahead(struct readahead_control *rac);
 int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		  u64 start, u64 len);
-void set_page_extent_mapped(struct page *page);
+int set_page_extent_mapped(struct page *page);
+void clear_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start, u64 owner_root, int level);

fs/btrfs/extent_map.c

@@ -385,9 +385,12 @@ static void extent_map_device_clear_bits(struct extent_map *em, unsigned bits)
 }
 
 /**
- * add_extent_mapping - add new extent map to the extent tree
+ * Add new extent map to the extent tree
+ *
  * @tree:	tree to insert new map in
  * @em:		map to insert
+ * @modified:	indicate whether the given @em should be added to the
+ *	        modified list, which indicates the extent needs to be logged
  *
  * Insert @em into @tree or perform a simple forward/backward merge with
  * existing mappings.  The extent_map struct passed in will be inserted
@@ -574,12 +577,13 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree,
 }
 
 /**
- * btrfs_add_extent_mapping - add extent mapping into em_tree
- * @fs_info - used for tracepoint
- * @em_tree - the extent tree into which we want to insert the extent mapping
- * @em_in   - extent we are inserting
- * @start   - start of the logical range btrfs_get_extent() is requesting
- * @len     - length of the logical range btrfs_get_extent() is requesting
+ * Add extent mapping into em_tree
+ *
+ * @fs_info:  the filesystem
+ * @em_tree:  extent tree into which we want to insert the extent mapping
+ * @em_in:    extent we are inserting
+ * @start:    start of the logical range btrfs_get_extent() is requesting
+ * @len:      length of the logical range btrfs_get_extent() is requesting
  *
  * Note that @em_in's range may be different from [start, start+len),
  * but they must be overlapped.

fs/btrfs/file-item.c

@@ -24,8 +24,10 @@
 				       PAGE_SIZE))
 
 /**
- * @inode - the inode we want to update the disk_i_size for
- * @new_i_size - the i_size we want to set to, 0 if we use i_size
+ * Set inode's size according to filesystem options
+ *
+ * @inode:      inode we want to update the disk_i_size for
+ * @new_i_size: i_size we want to set to, 0 if we use i_size
  *
  * With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read()
  * returns as it is perfectly fine with a file that has holes without hole file
@@ -62,9 +64,11 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz
 }
 
 /**
- * @inode - the inode we're modifying
- * @start - the start file offset of the file extent we've inserted
- * @len - the logical length of the file extent item
+ * Mark range within a file as having a new extent inserted
+ *
+ * @inode: inode being modified
+ * @start: start file offset of the file extent we've inserted
+ * @len:   logical length of the file extent item
  *
  * Call when we are inserting a new file extent where there was none before.
  * Does not need to call this in the case where we're replacing an existing file
@@ -88,9 +92,11 @@ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start,
 }
 
 /**
- * @inode - the inode we're modifying
- * @start - the start file offset of the file extent we've inserted
- * @len - the logical length of the file extent item
+ * Marks an inode range as not having a backing extent
+ *
+ * @inode: inode being modified
+ * @start: start file offset of the file extent we've inserted
+ * @len:   logical length of the file extent item
  *
  * Called when we drop a file extent, for example when we truncate.  Doesn't
  * need to be called for cases where we're replacing a file extent, like when

fs/btrfs/file.c

@@ -453,12 +453,11 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
 }
 
 /*
- * after copy_from_user, pages need to be dirtied and we need to make
- * sure holes are created between the current EOF and the start of
- * any next extents (if required).
- *
- * this also makes the decision about creating an inline extent vs
- * doing real data extents, marking pages dirty and delalloc as required.
+ * After btrfs_copy_from_user(), update the following things for delalloc:
+ * - Mark newly dirtied pages as DELALLOC in the io tree.
+ *   Used to advise which range is to be written back.
+ * - Mark modified pages as Uptodate/Dirty and not needing COW fixup
+ * - Update inode size for past EOF write
  */
 int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
@@ -1370,6 +1369,12 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
 			goto fail;
 		}
 
+		err = set_page_extent_mapped(pages[i]);
+		if (err < 0) {
+			faili = i;
+			goto fail;
+		}
+
 		if (i == 0)
 			err = prepare_uptodate_page(inode, pages[i], pos,
 						    force_uptodate);
@@ -1454,23 +1459,11 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 	}
 
 	/*
-	 * It's possible the pages are dirty right now, but we don't want
-	 * to clean them yet because copy_from_user may catch a page fault
-	 * and we might have to fall back to one page at a time.  If that
-	 * happens, we'll unlock these pages and we'd have a window where
-	 * reclaim could sneak in and drop the once-dirty page on the floor
-	 * without writing it.
-	 *
-	 * We have the pages locked and the extent range locked, so there's
-	 * no way someone can start IO on any dirty pages in this range.
-	 *
-	 * We'll call btrfs_dirty_pages() later on, and that will flip around
-	 * delalloc bits and dirty the pages as required.
+	 * We should be called after prepare_pages() which should have locked
+	 * all pages in the range.
 	 */
-	for (i = 0; i < num_pages; i++) {
-		set_page_extent_mapped(pages[i]);
+	for (i = 0; i < num_pages; i++)
 		WARN_ON(!PageLocked(pages[i]));
-	}
 
 	return ret;
 }
@@ -1997,9 +1990,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_inode *inode = BTRFS_I(file_inode(file));
 	ssize_t num_written = 0;
 	const bool sync = iocb->ki_flags & IOCB_DSYNC;
 
@@ -2008,7 +1999,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 * have opened a file as writable, we have to stop this write operation
 	 * to ensure consistency.
 	 */
-	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+	if (test_bit(BTRFS_FS_STATE_ERROR, &inode->root->fs_info->fs_state))
 		return -EROFS;
 
 	if (!(iocb->ki_flags & IOCB_DIRECT) &&
@@ -2016,7 +2007,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 		return -EOPNOTSUPP;
 
 	if (sync)
-		atomic_inc(&BTRFS_I(inode)->sync_writers);
+		atomic_inc(&inode->sync_writers);
 
 	if (iocb->ki_flags & IOCB_DIRECT)
 		num_written = btrfs_direct_write(iocb, from);
@@ -2028,14 +2019,14 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occurred.
 	 */
-	spin_lock(&BTRFS_I(inode)->lock);
-	BTRFS_I(inode)->last_sub_trans = root->log_transid;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
+	inode->last_sub_trans = inode->root->log_transid;
+	spin_unlock(&inode->lock);
 	if (num_written > 0)
 		num_written = generic_write_sync(iocb, num_written);
 
 	if (sync)
-		atomic_dec(&BTRFS_I(inode)->sync_writers);
+		atomic_dec(&inode->sync_writers);
 
 	current->backing_dev_info = NULL;
 	return num_written;
@@ -2177,8 +2168,12 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 * commit waits for their completion, to avoid data loss if we fsync,
 	 * the current transaction commits before the ordered extents complete
 	 * and a power failure happens right after that.
+	 *
+	 * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the
+	 * logical address recorded in the ordered extent may change. We need
+	 * to wait for the IO to stabilize the logical address.
 	 */
-	if (full_sync) {
+	if (full_sync || btrfs_is_zoned(fs_info)) {
 		ret = btrfs_wait_ordered_range(inode, start, len);
 	} else {
 		/*
@@ -2241,6 +2236,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = PTR_ERR(trans);
 		goto out_release_extents;
 	}
+	trans->in_fsync = true;
 
 	ret = btrfs_log_dentry_safe(trans, dentry, &ctx);
 	btrfs_release_log_ctx_extents(&ctx);

fs/btrfs/free-space-cache.c

@@ -198,7 +198,7 @@ int create_free_space_inode(struct btrfs_trans_handle *trans,
 	int ret;
 	u64 ino;
 
-	ret = btrfs_find_free_objectid(trans->fs_info->tree_root, &ino);
+	ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino);
 	if (ret < 0)
 		return ret;
 
@@ -431,11 +431,22 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
 	int i;
 
 	for (i = 0; i < io_ctl->num_pages; i++) {
+		int ret;
+
 		page = find_or_create_page(inode->i_mapping, i, mask);
 		if (!page) {
 			io_ctl_drop_pages(io_ctl);
 			return -ENOMEM;
 		}
+
+		ret = set_page_extent_mapped(page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			io_ctl_drop_pages(io_ctl);
+			return ret;
+		}
+
 		io_ctl->pages[i] = page;
 		if (uptodate && !PageUptodate(page)) {
 			btrfs_readpage(NULL, page);
@@ -455,10 +466,8 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate)
 		}
 	}
 
-	for (i = 0; i < io_ctl->num_pages; i++) {
+	for (i = 0; i < io_ctl->num_pages; i++)
 		clear_page_dirty_for_io(io_ctl->pages[i]);
-		set_page_extent_mapped(io_ctl->pages[i]);
-	}
 
 	return 0;
 }
@@ -775,8 +784,10 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 	while (num_entries) {
 		e = kmem_cache_zalloc(btrfs_free_space_cachep,
 				      GFP_NOFS);
-		if (!e)
+		if (!e) {
+			ret = -ENOMEM;
 			goto free_cache;
+		}
 
 		ret = io_ctl_read_entry(&io_ctl, e, &type);
 		if (ret) {
@@ -785,6 +796,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 		}
 
 		if (!e->bytes) {
+			ret = -1;
 			kmem_cache_free(btrfs_free_space_cachep, e);
 			goto free_cache;
 		}
@@ -805,6 +817,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 			e->bitmap = kmem_cache_zalloc(
 					btrfs_free_space_bitmap_cachep, GFP_NOFS);
 			if (!e->bitmap) {
+				ret = -ENOMEM;
 				kmem_cache_free(
 					btrfs_free_space_cachep, e);
 				goto free_cache;
@@ -1295,11 +1308,14 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
 }
 
 /**
- * __btrfs_write_out_cache - write out cached info to an inode
- * @root - the root the inode belongs to
- * @ctl - the free space cache we are going to write out
- * @block_group - the block_group for this cache if it belongs to a block_group
- * @trans - the trans handle
+ * Write out cached info to an inode
+ *
+ * @root:        root the inode belongs to
+ * @inode:       freespace inode we are writing out
+ * @ctl:         free space cache we are going to write out
+ * @block_group: block_group for this cache if it belongs to a block_group
+ * @io_ctl:      holds context for the io
+ * @trans:       the trans handle
  *
  * This function writes out a free space cache struct to disk for quick recovery
  * on mount.  This will return 0 if it was successful in writing the cache out,
@@ -2461,6 +2477,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	u64 filter_bytes = bytes;
 
+	ASSERT(!btrfs_is_zoned(fs_info));
+
 	info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS);
 	if (!info)
 		return -ENOMEM;
@@ -2518,11 +2536,49 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
+static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+					u64 bytenr, u64 size, bool used)
+{
+	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	u64 offset = bytenr - block_group->start;
+	u64 to_free, to_unusable;
+
+	spin_lock(&ctl->tree_lock);
+	if (!used)
+		to_free = size;
+	else if (offset >= block_group->alloc_offset)
+		to_free = size;
+	else if (offset + size <= block_group->alloc_offset)
+		to_free = 0;
+	else
+		to_free = offset + size - block_group->alloc_offset;
+	to_unusable = size - to_free;
+
+	ctl->free_space += to_free;
+	block_group->zone_unusable += to_unusable;
+	spin_unlock(&ctl->tree_lock);
+	if (!used) {
+		spin_lock(&block_group->lock);
+		block_group->alloc_offset -= size;
+		spin_unlock(&block_group->lock);
+	}
+
+	/* All the region is now unusable. Mark it as unused and reclaim */
+	if (block_group->zone_unusable == block_group->length)
+		btrfs_mark_bg_unused(block_group);
+
+	return 0;
+}
+
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size)
 {
 	enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    true);
+
 	if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC))
 		trim_state = BTRFS_TRIM_STATE_TRIMMED;
 
@@ -2531,6 +2587,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group,
 				      bytenr, size, trim_state);
 }
 
+int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
+				u64 bytenr, u64 size)
+{
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    false);
+
+	return btrfs_add_free_space(block_group, bytenr, size);
+}
+
 /*
  * This is a subtle distinction because when adding free space back in general,
  * we want it to be added as untrimmed for async. But in the case where we add
@@ -2541,6 +2607,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
 {
 	enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 
+	if (btrfs_is_zoned(block_group->fs_info))
+		return __btrfs_add_free_space_zoned(block_group, bytenr, size,
+						    true);
+
 	if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) ||
 	    btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
 		trim_state = BTRFS_TRIM_STATE_TRIMMED;
@@ -2558,6 +2628,23 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group,
 	int ret;
 	bool re_search = false;
 
+	if (btrfs_is_zoned(block_group->fs_info)) {
+		/*
+		 * This can happen with conventional zones when replaying log.
+		 * Since the allocation info of tree-log nodes are not recorded
+		 * to the extent-tree, calculate_alloc_pointer() failed to
+		 * advance the allocation pointer after last allocated tree log
+		 * node blocks.
+		 *
+		 * This function is called from
+		 * btrfs_pin_extent_for_log_replay() when replaying the log.
+		 * Advance the pointer not to overwrite the tree-log nodes.
+		 */
+		if (block_group->alloc_offset < offset + bytes)
+			block_group->alloc_offset = offset + bytes;
+		return 0;
+	}
+
 	spin_lock(&ctl->tree_lock);
 
 again:
@@ -2652,6 +2739,16 @@ void btrfs_dump_free_space(struct btrfs_block_group *block_group,
 	struct rb_node *n;
 	int count = 0;
 
+	/*
+	 * Zoned btrfs does not use free space tree and cluster. Just print
+	 * out the free space after the allocation offset.
+	 */
+	if (btrfs_is_zoned(fs_info)) {
+		btrfs_info(fs_info, "free space %llu",
+			   block_group->length - block_group->alloc_offset);
+		return;
+	}
+
 	spin_lock(&ctl->tree_lock);
 	for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
@@ -2845,6 +2942,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 	u64 align_gap_len = 0;
 	enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 
+	ASSERT(!btrfs_is_zoned(block_group->fs_info));
+
 	spin_lock(&ctl->tree_lock);
 	entry = find_free_space(ctl, &offset, &bytes_search,
 				block_group->full_stripe_len, max_extent_size);
@@ -2976,6 +3075,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 	struct rb_node *node;
 	u64 ret = 0;
 
+	ASSERT(!btrfs_is_zoned(block_group->fs_info));
+
 	spin_lock(&cluster->lock);
 	if (bytes > cluster->max_size)
 		goto out;
@@ -3752,6 +3853,8 @@ int btrfs_trim_block_group(struct btrfs_block_group *block_group,
 	int ret;
 	u64 rem = 0;
 
+	ASSERT(!btrfs_is_zoned(block_group->fs_info));
+
 	*trimmed = 0;
 
 	spin_lock(&block_group->lock);

fs/btrfs/free-space-cache.h

@@ -107,6 +107,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info,
 			   enum btrfs_trim_state trim_state);
 int btrfs_add_free_space(struct btrfs_block_group *block_group,
 			 u64 bytenr, u64 size);
+int btrfs_add_free_space_unused(struct btrfs_block_group *block_group,
+				u64 bytenr, u64 size);
 int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group,
 				       u64 bytenr, u64 size);
 int btrfs_remove_free_space(struct btrfs_block_group *block_group,

fs/btrfs/ioctl.c

@@ -527,6 +527,14 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/*
+	 * btrfs_trim_block_group() depends on space cache, which is not
+	 * available in zoned filesystem. So, disallow fitrim on a zoned
+	 * filesystem for now.
+	 */
+	if (btrfs_is_zoned(fs_info))
+		return -EOPNOTSUPP;
+
 	/*
 	 * If the fs is mounted with nologreplay, which requires it to be
 	 * mounted in RO mode as well, we can not allow discard on free space
@@ -606,14 +614,13 @@ static noinline int create_subvol(struct inode *dir,
 	int err;
 	dev_t anon_dev = 0;
 	u64 objectid;
-	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
 	u64 index = 0;
 
 	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
 	if (!root_item)
 		return -ENOMEM;
 
-	ret = btrfs_find_free_objectid(fs_info->tree_root, &objectid);
+	ret = btrfs_get_free_objectid(fs_info->tree_root, &objectid);
 	if (ret)
 		goto fail_free;
 
@@ -693,7 +700,7 @@ static noinline int create_subvol(struct inode *dir,
 	free_extent_buffer(leaf);
 	leaf = NULL;
 
-	btrfs_set_root_dirid(root_item, new_dirid);
+	btrfs_set_root_dirid(root_item, BTRFS_FIRST_FREE_OBJECTID);
 
 	key.objectid = objectid;
 	key.offset = 0;
@@ -716,7 +723,7 @@ static noinline int create_subvol(struct inode *dir,
 
 	btrfs_record_root_in_trans(trans, new_root);
 
-	ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid);
+	ret = btrfs_create_subvol_root(trans, new_root, root);
 	btrfs_put_root(new_root);
 	if (ret) {
 		/* We potentially lose an unused inode item here */
@@ -724,10 +731,6 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	mutex_lock(&new_root->objectid_mutex);
-	new_root->highest_objectid = new_dirid;
-	mutex_unlock(&new_root->objectid_mutex);
-
 	/*
 	 * insert the directory item
 	 */
@@ -1319,6 +1322,13 @@ static int cluster_pages_for_defrag(struct inode *inode,
 		if (!page)
 			break;
 
+		ret = set_page_extent_mapped(page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			break;
+		}
+
 		page_start = page_offset(page);
 		page_end = page_start + PAGE_SIZE - 1;
 		while (1) {
@@ -1440,7 +1450,6 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	for (i = 0; i < i_done; i++) {
 		clear_page_dirty_for_io(pages[i]);
 		ClearPageChecked(pages[i]);
-		set_page_extent_mapped(pages[i]);
 		set_page_dirty(pages[i]);
 		unlock_page(pages[i]);
 		put_page(pages[i]);
@@ -4951,7 +4960,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
-		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
+		ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(inode->i_sb, 1);

fs/btrfs/ordered-data.h

@@ -27,7 +27,7 @@ struct btrfs_ordered_sum {
 };
 
 /*
- * bits for the flags field:
+ * Bits for btrfs_ordered_extent::flags.
  *
  * BTRFS_ORDERED_IO_DONE is set when all of the blocks are written.
  * It is used to make sure metadata is inserted into the tree only once
@@ -38,24 +38,36 @@ struct btrfs_ordered_sum {
  * IO is done and any metadata is inserted into the tree.
  */
 enum {
+	/*
+	 * Different types for direct io, one and only one of the 4 type can
+	 * be set when creating ordered extent.
+	 *
+	 * REGULAR:	For regular non-compressed COW write
+	 * NOCOW:	For NOCOW write into existing non-hole extent
+	 * PREALLOC:	For NOCOW write into preallocated extent
+	 * COMPRESSED:	For compressed COW write
+	 */
+	BTRFS_ORDERED_REGULAR,
+	BTRFS_ORDERED_NOCOW,
+	BTRFS_ORDERED_PREALLOC,
+	BTRFS_ORDERED_COMPRESSED,
+
+	/*
+	 * Extra bit for direct io, can only be set for
+	 * REGULAR/NOCOW/PREALLOC. No direct io for compressed extent.
+	 */
+	BTRFS_ORDERED_DIRECT,
+
+	/* Extra status bits for ordered extents */
+
 	/* set when all the pages are written */
 	BTRFS_ORDERED_IO_DONE,
 	/* set when removed from the tree */
 	BTRFS_ORDERED_COMPLETE,
-	/* set when we want to write in place */
-	BTRFS_ORDERED_NOCOW,
-	/* writing a zlib compressed extent */
-	BTRFS_ORDERED_COMPRESSED,
-	/* set when writing to preallocated extent */
-	BTRFS_ORDERED_PREALLOC,
-	/* set when we're doing DIO with this extent */
-	BTRFS_ORDERED_DIRECT,
 	/* We had an io error when writing this out */
 	BTRFS_ORDERED_IOERR,
 	/* Set when we have to truncate an extent */
 	BTRFS_ORDERED_TRUNCATED,
-	/* Regular IO for COW */
-	BTRFS_ORDERED_REGULAR,
 	/* Used during fsync to track already logged extents */
 	BTRFS_ORDERED_LOGGED,
 	/* We have already logged all the csums of the ordered extent */
@@ -127,6 +139,14 @@ struct btrfs_ordered_extent {
 	struct completion completion;
 	struct btrfs_work flush_work;
 	struct list_head work_list;
+
+	/*
+	 * Used to reverse-map physical address returned from ZONE_APPEND write
+	 * command in a workqueue context
+	 */
+	u64 physical;
+	struct gendisk *disk;
+	u8 partno;
 };
 
 /*
@@ -152,11 +172,11 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
 void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
 void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 				struct btrfs_ordered_extent *entry);
-int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
-				   struct btrfs_ordered_extent **cached,
-				   u64 file_offset, u64 io_size, int uptodate);
-int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
-				   struct btrfs_ordered_extent **cached,
+bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
+				    struct btrfs_ordered_extent **cached,
+				    u64 file_offset, u64 io_size, int uptodate);
+bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
+				   struct btrfs_ordered_extent **finished_ret,
 				   u64 *file_offset, u64 io_size,
 				   int uptodate);
 int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
@@ -167,8 +187,7 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
 				 u64 disk_num_bytes, int type);
 int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
 				      u64 disk_bytenr, u64 num_bytes,
-				      u64 disk_num_bytes, int type,
-				      int compress_type);
+				      u64 disk_num_bytes, int compress_type);
 void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 			   struct btrfs_ordered_sum *sum);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
@@ -190,6 +209,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
 					u64 end,
 					struct extent_state **cached_state);
+int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
+			       u64 post);
 int __init ordered_data_init(void);
 void __cold ordered_data_exit(void);
 

fs/btrfs/raid56.c

@@ -233,8 +233,7 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info)
 	}
 
 	x = cmpxchg(&info->stripe_hash_table, NULL, table);
-	if (x)
-		kvfree(x);
+	kvfree(x);
 	return 0;
 }
 

fs/btrfs/ref-verify.c

@@ -495,14 +495,15 @@ static int process_extent_item(struct btrfs_fs_info *fs_info,
 }
 
 static int process_leaf(struct btrfs_root *root,
-			struct btrfs_path *path, u64 *bytenr, u64 *num_bytes)
+			struct btrfs_path *path, u64 *bytenr, u64 *num_bytes,
+			int *tree_block_level)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *leaf = path->nodes[0];
 	struct btrfs_extent_data_ref *dref;
 	struct btrfs_shared_data_ref *sref;
 	u32 count;
-	int i = 0, tree_block_level = 0, ret = 0;
+	int i = 0, ret = 0;
 	struct btrfs_key key;
 	int nritems = btrfs_header_nritems(leaf);
 
@@ -515,15 +516,15 @@ static int process_leaf(struct btrfs_root *root,
 		case BTRFS_METADATA_ITEM_KEY:
 			*bytenr = key.objectid;
 			ret = process_extent_item(fs_info, path, &key, i,
-						  &tree_block_level);
+						  tree_block_level);
 			break;
 		case BTRFS_TREE_BLOCK_REF_KEY:
 			ret = add_tree_block(fs_info, key.offset, 0,
-					     key.objectid, tree_block_level);
+					     key.objectid, *tree_block_level);
 			break;
 		case BTRFS_SHARED_BLOCK_REF_KEY:
 			ret = add_tree_block(fs_info, 0, key.offset,
-					     key.objectid, tree_block_level);
+					     key.objectid, *tree_block_level);
 			break;
 		case BTRFS_EXTENT_DATA_REF_KEY:
 			dref = btrfs_item_ptr(leaf, i,
@@ -549,7 +550,8 @@ static int process_leaf(struct btrfs_root *root,
 
 /* Walk down to the leaf from the given level */
 static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
-			  int level, u64 *bytenr, u64 *num_bytes)
+			  int level, u64 *bytenr, u64 *num_bytes,
+			  int *tree_block_level)
 {
 	struct extent_buffer *eb;
 	int ret = 0;
@@ -565,7 +567,8 @@ static int walk_down_tree(struct btrfs_root *root, struct btrfs_path *path,
 			path->slots[level-1] = 0;
 			path->locks[level-1] = BTRFS_READ_LOCK;
 		} else {
-			ret = process_leaf(root, path, bytenr, num_bytes);
+			ret = process_leaf(root, path, bytenr, num_bytes,
+					   tree_block_level);
 			if (ret)
 				break;
 		}
@@ -666,18 +669,18 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 	u64 bytenr = generic_ref->bytenr;
 	u64 num_bytes = generic_ref->len;
 	u64 parent = generic_ref->parent;
-	u64 ref_root;
-	u64 owner;
-	u64 offset;
+	u64 ref_root = 0;
+	u64 owner = 0;
+	u64 offset = 0;
 
 	if (!btrfs_test_opt(fs_info, REF_VERIFY))
 		return 0;
 
 	if (generic_ref->type == BTRFS_REF_METADATA) {
-		ref_root = generic_ref->tree_ref.root;
+		if (!parent)
+			ref_root = generic_ref->tree_ref.root;
 		owner = generic_ref->tree_ref.level;
-		offset = 0;
-	} else {
+	} else if (!parent) {
 		ref_root = generic_ref->data_ref.ref_root;
 		owner = generic_ref->data_ref.ino;
 		offset = generic_ref->data_ref.offset;
@@ -693,13 +696,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
 		goto out;
 	}
 
-	if (parent) {
-		ref->parent = parent;
-	} else {
-		ref->root_objectid = ref_root;
-		ref->owner = owner;
-		ref->offset = offset;
-	}
+	ref->parent = parent;
+	ref->owner = owner;
+	ref->root_objectid = ref_root;
+	ref->offset = offset;
 	ref->num_refs = (action == BTRFS_DROP_DELAYED_REF) ? -1 : 1;
 
 	memcpy(&ra->ref, ref, sizeof(struct ref_entry));
@@ -974,6 +974,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_path *path;
 	struct extent_buffer *eb;
+	int tree_block_level = 0;
 	u64 bytenr = 0, num_bytes = 0;
 	int ret, level;
 
@@ -998,7 +999,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info)
 		 * different leaf from the original extent item.
 		 */
 		ret = walk_down_tree(fs_info->extent_root, path, level,
-				     &bytenr, &num_bytes);
+				     &bytenr, &num_bytes, &tree_block_level);
 		if (ret)
 			break;
 		ret = walk_up_tree(path, &level);

fs/btrfs/reflink.c

@@ -81,7 +81,10 @@ static int copy_inline_to_page(struct btrfs_inode *inode,
 		goto out_unlock;
 	}
 
-	set_page_extent_mapped(page);
+	ret = set_page_extent_mapped(page);
+	if (ret < 0)
+		goto out_unlock;
+
 	clear_extent_bit(&inode->io_tree, file_offset, range_end,
 			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
 			 0, 0, NULL);

fs/btrfs/super.c

@@ -48,7 +48,6 @@
 #include "tests/btrfs-tests.h"
 #include "block-group.h"
 #include "discard.h"
-
 #include "qgroup.h"
 #define CREATE_TRACE_POINTS
 #include <trace/events/btrfs.h>
@@ -2028,6 +2027,13 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			ret = -EINVAL;
 			goto restore;
 		}
+		if (fs_info->sectorsize < PAGE_SIZE) {
+			btrfs_warn(fs_info,
+	"read-write mount is not yet allowed for sectorsize %u page size %lu",
+				   fs_info->sectorsize, PAGE_SIZE);
+			ret = -EINVAL;
+			goto restore;
+		}
 
 		/*
 		 * NOTE: when remounting with a change that does writes, don't

fs/btrfs/sysfs.c

@@ -666,6 +666,7 @@ SPACE_INFO_ATTR(bytes_pinned);
 SPACE_INFO_ATTR(bytes_reserved);
 SPACE_INFO_ATTR(bytes_may_use);
 SPACE_INFO_ATTR(bytes_readonly);
+SPACE_INFO_ATTR(bytes_zone_unusable);
 SPACE_INFO_ATTR(disk_used);
 SPACE_INFO_ATTR(disk_total);
 BTRFS_ATTR(space_info, total_bytes_pinned,
@@ -679,6 +680,7 @@ static struct attribute *space_info_attrs[] = {
 	BTRFS_ATTR_PTR(space_info, bytes_reserved),
 	BTRFS_ATTR_PTR(space_info, bytes_may_use),
 	BTRFS_ATTR_PTR(space_info, bytes_readonly),
+	BTRFS_ATTR_PTR(space_info, bytes_zone_unusable),
 	BTRFS_ATTR_PTR(space_info, disk_used),
 	BTRFS_ATTR_PTR(space_info, disk_total),
 	BTRFS_ATTR_PTR(space_info, total_bytes_pinned),

include/linux/iomap.h

@@ -55,6 +55,7 @@ struct vm_fault;
 #define IOMAP_F_SHARED		0x04
 #define IOMAP_F_MERGED		0x08
 #define IOMAP_F_BUFFER_HEAD	0x10
+#define IOMAP_F_ZONE_APPEND	0x20
 
 /*
  * Flags set by the core iomap code during operations: