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
  ...

1 files changed, 152 insertions, 31 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 07a2b4f69b10..41b718cfea40 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -459,6 +459,12 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec
 		return 0;
 
 	found_start = btrfs_header_bytenr(eb);
+
+	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {
+		WARN_ON(found_start != 0);
+		return 0;
+	}
+
 	/*
 	 * Please do not consolidate these warnings into a single if.
 	 * It is useful to know what went wrong.
@@ -591,6 +597,59 @@ out:
 	return ret;
 }
 
+static int validate_subpage_buffer(struct page *page, u64 start, u64 end,
+				   int mirror)
+{
+	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
+	struct extent_buffer *eb;
+	bool reads_done;
+	int ret = 0;
+
+	/*
+	 * We don't allow bio merge for subpage metadata read, so we should
+	 * only get one eb for each endio hook.
+	 */
+	ASSERT(end == start + fs_info->nodesize - 1);
+	ASSERT(PagePrivate(page));
+
+	eb = find_extent_buffer(fs_info, start);
+	/*
+	 * When we are reading one tree block, eb must have been inserted into
+	 * the radix tree. If not, something is wrong.
+	 */
+	ASSERT(eb);
+
+	reads_done = atomic_dec_and_test(&eb->io_pages);
+	/* Subpage read must finish in page read */
+	ASSERT(reads_done);
+
+	eb->read_mirror = mirror;
+	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
+		ret = -EIO;
+		goto err;
+	}
+	ret = validate_extent_buffer(eb);
+	if (ret < 0)
+		goto err;
+
+	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
+		btree_readahead_hook(eb, ret);
+
+	set_extent_buffer_uptodate(eb);
+
+	free_extent_buffer(eb);
+	return ret;
+err:
+	/*
+	 * end_bio_extent_readpage decrements io_pages in case of error,
+	 * make sure it has something to decrement.
+	 */
+	atomic_inc(&eb->io_pages);
+	clear_extent_buffer_uptodate(eb);
+	free_extent_buffer(eb);
+	return ret;
+}
+
 int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio,
 				   struct page *page, u64 start, u64 end,
 				   int mirror)
@@ -600,6 +659,10 @@ int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio,
 	int reads_done;
 
 	ASSERT(page->private);
+
+	if (btrfs_sb(page->mapping->host->i_sb)->sectorsize < PAGE_SIZE)
+		return validate_subpage_buffer(page, start, end, mirror);
+
 	eb = (struct extent_buffer *)page->private;
 
 	/*
@@ -646,7 +709,7 @@ static void end_workqueue_bio(struct bio *bio)
 	fs_info = end_io_wq->info;
 	end_io_wq->status = bio->bi_status;
 
-	if (bio_op(bio) == REQ_OP_WRITE) {
+	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
 		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
 			wq = fs_info->endio_meta_write_workers;
 		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
@@ -808,6 +871,8 @@ static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio,
 static int check_async_write(struct btrfs_fs_info *fs_info,
 			     struct btrfs_inode *bi)
 {
+	if (btrfs_is_zoned(fs_info))
+		return 0;
 	if (atomic_read(&bi->sync_writers))
 		return 0;
 	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
@@ -822,7 +887,7 @@ blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
 	int async = check_async_write(fs_info, BTRFS_I(inode));
 	blk_status_t ret;
 
-	if (bio_op(bio) != REQ_OP_WRITE) {
+	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
 		/*
 		 * called for a read, do the setup so that checksum validation
 		 * can happen in the async kernel threads
@@ -1016,7 +1081,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->orphan_cleanup_state = 0;
 
 	root->last_trans = 0;
-	root->highest_objectid = 0;
+	root->free_objectid = 0;
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
 	root->inode_tree = RB_ROOT;
@@ -1189,7 +1254,6 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 					 struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *root;
-	struct extent_buffer *leaf;
 
 	root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS);
 	if (!root)
@@ -1199,6 +1263,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
 
+	return root;
+}
+
+int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root)
+{
+	struct extent_buffer *leaf;
+
 	/*
 	 * DON'T set SHAREABLE bit for log trees.
 	 *
@@ -1211,16 +1283,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
 			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
-	if (IS_ERR(leaf)) {
-		btrfs_put_root(root);
-		return ERR_CAST(leaf);
-	}
+	if (IS_ERR(leaf))
+		return PTR_ERR(leaf);
 
 	root->node = leaf;
 
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
-	return root;
+
+	return 0;
 }
 
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
@@ -1231,6 +1302,16 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 	log_root = alloc_log_tree(trans, fs_info);
 	if (IS_ERR(log_root))
 		return PTR_ERR(log_root);
+
+	if (!btrfs_is_zoned(fs_info)) {
+		int ret = btrfs_alloc_log_tree_node(trans, log_root);
+
+		if (ret) {
+			btrfs_put_root(log_root);
+			return ret;
+		}
+	}
+
 	WARN_ON(fs_info->log_root_tree);
 	fs_info->log_root_tree = log_root;
 	return 0;
@@ -1242,11 +1323,18 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *log_root;
 	struct btrfs_inode_item *inode_item;
+	int ret;
 
 	log_root = alloc_log_tree(trans, fs_info);
 	if (IS_ERR(log_root))
 		return PTR_ERR(log_root);
 
+	ret = btrfs_alloc_log_tree_node(trans, log_root);
+	if (ret) {
+		btrfs_put_root(log_root);
+		return ret;
+	}
+
 	log_root->last_trans = trans->transid;
 	log_root->root_key.offset = root->root_key.objectid;
 
@@ -1367,14 +1455,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 	}
 
 	mutex_lock(&root->objectid_mutex);
-	ret = btrfs_find_highest_objectid(root,
-					&root->highest_objectid);
+	ret = btrfs_init_root_free_objectid(root);
 	if (ret) {
 		mutex_unlock(&root->objectid_mutex);
 		goto fail;
 	}
 
-	ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+	ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);
 
 	mutex_unlock(&root->objectid_mutex);
 
@@ -1470,7 +1557,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 {
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
-	percpu_counter_destroy(&fs_info->dio_bytes);
+	percpu_counter_destroy(&fs_info->ordered_bytes);
 	percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
 	btrfs_free_csum_hash(fs_info);
 	btrfs_free_stripe_hash_table(fs_info);
@@ -2427,13 +2514,21 @@ static int validate_super(struct btrfs_fs_info *fs_info,
 		btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
 		ret = -EINVAL;
 	}
-	/* Only PAGE SIZE is supported yet */
-	if (sectorsize != PAGE_SIZE) {
+
+	/*
+	 * For 4K page size, we only support 4K sector size.
+	 * For 64K page size, we support read-write for 64K sector size, and
+	 * read-only for 4K sector size.
+	 */
+	if ((PAGE_SIZE == SZ_4K && sectorsize != PAGE_SIZE) ||
+	    (PAGE_SIZE == SZ_64K && (sectorsize != SZ_4K &&
+				     sectorsize != SZ_64K))) {
 		btrfs_err(fs_info,
-			"sectorsize %llu not supported yet, only support %lu",
+			"sectorsize %llu not yet supported for page size %lu",
 			sectorsize, PAGE_SIZE);
 		ret = -EINVAL;
 	}
+
 	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
 	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
 		btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
@@ -2646,14 +2741,13 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		 * No need to hold btrfs_root::objectid_mutex since the fs
 		 * hasn't been fully initialised and we are the only user
 		 */
-		ret = btrfs_find_highest_objectid(tree_root,
-						&tree_root->highest_objectid);
+		ret = btrfs_init_root_free_objectid(tree_root);
 		if (ret < 0) {
 			handle_error = true;
 			continue;
 		}
 
-		ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+		ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);
 
 		ret = btrfs_read_roots(fs_info);
 		if (ret < 0) {
@@ -2695,11 +2789,13 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->buffer_lock);
 	spin_lock_init(&fs_info->unused_bgs_lock);
+	spin_lock_init(&fs_info->treelog_bg_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->unused_bg_unpin_mutex);
 	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
+	mutex_init(&fs_info->zoned_meta_io_lock);
 	seqlock_init(&fs_info->profiles_lock);
 
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
@@ -2804,7 +2900,7 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
 	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);
 
-	ret = percpu_counter_init(&fs_info->dio_bytes, 0, GFP_KERNEL);
+	ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL);
 	if (ret)
 		return ret;
 
@@ -3140,8 +3236,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
 		btrfs_info(fs_info, "has skinny extents");
 
-	fs_info->zoned = (features & BTRFS_FEATURE_INCOMPAT_ZONED);
-
 	/*
 	 * flag our filesystem as having big metadata blocks if
 	 * they are bigger than the page size
@@ -3194,6 +3288,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_alloc;
 	}
 
+	/* For 4K sector size support, it's only read-only */
+	if (PAGE_SIZE == SZ_64K && sectorsize == SZ_4K) {
+		if (!sb_rdonly(sb) || btrfs_super_log_root(disk_super)) {
+			btrfs_err(fs_info,
+	"subpage sectorsize %u only supported read-only for page size %lu",
+				sectorsize, PAGE_SIZE);
+			err = -EINVAL;
+			goto fail_alloc;
+		}
+	}
+
 	ret = btrfs_init_workqueues(fs_info, fs_devices);
 	if (ret) {
 		err = ret;
@@ -3261,6 +3366,19 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_tree_roots;
 
 	/*
+	 * Get zone type information of zoned block devices. This will also
+	 * handle emulation of a zoned filesystem if a regular device has the
+	 * zoned incompat feature flag set.
+	 */
+	ret = btrfs_get_dev_zone_info_all_devices(fs_info);
+	if (ret) {
+		btrfs_err(fs_info,
+			  "zoned: failed to read device zone info: %d",
+			  ret);
+		goto fail_block_groups;
+	}
+
+	/*
 	 * If we have a uuid root and we're not being told to rescan we need to
 	 * check the generation here so we can set the
 	 * BTRFS_FS_UPDATE_UUID_TREE_GEN bit.  Otherwise we could commit the
@@ -4114,6 +4232,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
+	cancel_work_sync(&fs_info->preempt_reclaim_work);
 
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);
@@ -4166,9 +4285,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 		       percpu_counter_sum(&fs_info->delalloc_bytes));
 	}
 
-	if (percpu_counter_sum(&fs_info->dio_bytes))
+	if (percpu_counter_sum(&fs_info->ordered_bytes))
 		btrfs_info(fs_info, "at unmount dio bytes count %lld",
-			   percpu_counter_sum(&fs_info->dio_bytes));
+			   percpu_counter_sum(&fs_info->ordered_bytes));
 
 	btrfs_sysfs_remove_mounted(fs_info);
 	btrfs_sysfs_remove_fsid(fs_info->fs_devices);
@@ -4689,6 +4808,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				     EXTENT_DIRTY);
 	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);
 
+	btrfs_free_redirty_list(cur_trans);
+
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
 }
@@ -4746,7 +4867,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_init_root_free_objectid(struct btrfs_root *root)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -4770,10 +4891,10 @@ int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
 		slot = path->slots[0] - 1;
 		l = path->nodes[0];
 		btrfs_item_key_to_cpu(l, &found_key, slot);
-		*objectid = max_t(u64, found_key.objectid,
-				  BTRFS_FIRST_FREE_OBJECTID - 1);
+		root->free_objectid = max_t(u64, found_key.objectid + 1,
+					    BTRFS_FIRST_FREE_OBJECTID);
 	} else {
-		*objectid = BTRFS_FIRST_FREE_OBJECTID - 1;
+		root->free_objectid = BTRFS_FIRST_FREE_OBJECTID;
 	}
 	ret = 0;
 error:
@@ -4781,12 +4902,12 @@ error:
 	return ret;
 }
 
-int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid)
 {
 	int ret;
 	mutex_lock(&root->objectid_mutex);
 
-	if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
+	if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
 		btrfs_warn(root->fs_info,
 			   "the objectid of root %llu reaches its highest value",
 			   root->root_key.objectid);
@@ -4794,7 +4915,7 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
 		goto out;
 	}
 
-	*objectid = ++root->highest_objectid;
+	*objectid = root->free_objectid++;
 	ret = 0;
 out:
 	mutex_unlock(&root->objectid_mutex);