btrfs: zoned: redirty released extent buffers

Tree manipulating operations like merging nodes often release
once-allocated tree nodes. Such nodes are cleaned so that pages in the
node are not uselessly written out. On zoned volumes, however, such
optimization blocks the following IOs as the cancellation of the write
out of the freed blocks breaks the sequential write sequence expected by
the device.

Introduce a list of clean and unwritten extent buffers that have been
released in a transaction. Redirty the buffers so that
btree_write_cache_pages() can send proper bios to the devices.

Besides it clears the entire content of the extent buffer not to confuse
raw block scanners e.g. 'btrfs check'. By clearing the content,
csum_dirty_buffer() complains about bytenr mismatch, so avoid the
checking and checksum using newly introduced buffer flag
EXTENT_BUFFER_NO_CHECK.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>

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.
@@ -4774,6 +4780,8 @@ 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);
 }

fs/btrfs/extent-tree.c

@@ -3292,8 +3292,10 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
 			ret = check_ref_cleanup(trans, buf->start);
-			if (!ret)
+			if (!ret) {
+				btrfs_redirty_list_add(trans->transaction, buf);
 				goto out;
+			}
 		}
 
 		cache = btrfs_lookup_block_group(fs_info, buf->start);
@@ -3304,6 +3306,13 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
+		if (btrfs_is_zoned(fs_info)) {
+			btrfs_redirty_list_add(trans->transaction, buf);
+			pin_down_extent(trans, cache, buf->start, buf->len, 1);
+			btrfs_put_block_group(cache);
+			goto out;
+		}
+
 		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
@@ -4635,6 +4644,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	__btrfs_tree_lock(buf, nest);
 	btrfs_clean_tree_block(buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
+	clear_bit(EXTENT_BUFFER_NO_CHECK, &buf->bflags);
 
 	set_extent_buffer_uptodate(buf);
 

fs/btrfs/extent_io.c

@@ -25,6 +25,7 @@
 #include "backref.h"
 #include "disk-io.h"
 #include "subpage.h"
+#include "zoned.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -5182,6 +5183,7 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 
 	btrfs_leak_debug_add(&fs_info->eb_leak_lock, &eb->leak_list,
 			     &fs_info->allocated_ebs);
+	INIT_LIST_HEAD(&eb->release_list);
 
 	spin_lock_init(&eb->refs_lock);
 	atomic_set(&eb->refs, 1);
@@ -6111,6 +6113,8 @@ void write_extent_buffer(const struct extent_buffer *eb, const void *srcv,
 	char *src = (char *)srcv;
 	unsigned long i = get_eb_page_index(start);
 
+	WARN_ON(test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags));
+
 	if (check_eb_range(eb, start, len))
 		return;
 

fs/btrfs/extent_io.h

@@ -31,6 +31,7 @@ enum {
 	EXTENT_BUFFER_IN_TREE,
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
+	EXTENT_BUFFER_NO_CHECK,
 };
 
 /* these are flags for __process_pages_contig */
@@ -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

fs/btrfs/transaction.c

@@ -21,6 +21,7 @@
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
+#include "zoned.h"
 
 #define BTRFS_ROOT_TRANS_TAG 0
 
@@ -380,6 +381,8 @@ loop:
 	spin_lock_init(&cur_trans->dirty_bgs_lock);
 	INIT_LIST_HEAD(&cur_trans->deleted_bgs);
 	spin_lock_init(&cur_trans->dropped_roots_lock);
+	INIT_LIST_HEAD(&cur_trans->releasing_ebs);
+	spin_lock_init(&cur_trans->releasing_ebs_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
 			IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -2350,6 +2353,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		goto scrub_continue;
 	}
 
+	/*
+	 * At this point, we should have written all the tree blocks allocated
+	 * in this transaction. So it's now safe to free the redirtyied extent
+	 * buffers.
+	 */
+	btrfs_free_redirty_list(cur_trans);
+
 	ret = write_all_supers(fs_info, 0);
 	/*
 	 * the super is written, we can safely allow the tree-loggers

fs/btrfs/transaction.h

@@ -93,6 +93,9 @@ struct btrfs_transaction {
 	 */
 	atomic_t pending_ordered;
 	wait_queue_head_t pending_wait;
+
+	spinlock_t releasing_ebs_lock;
+	struct list_head releasing_ebs;
 };
 
 #define __TRANS_FREEZABLE	(1U << 0)

fs/btrfs/tree-log.c

@@ -19,6 +19,7 @@
 #include "qgroup.h"
 #include "block-group.h"
 #include "space-info.h"
+#include "zoned.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -2752,6 +2753,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 						free_extent_buffer(next);
 						return ret;
 					}
+					btrfs_redirty_list_add(
+						trans->transaction, next);
 				} else {
 					if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
 						clear_extent_buffer_dirty(next);
@@ -3296,6 +3299,9 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 	clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
 			  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
 	extent_io_tree_release(&log->log_csum_range);
+
+	if (trans && log->node)
+		btrfs_redirty_list_add(trans->transaction, log->node);
 	btrfs_put_root(log);
 }
 

fs/btrfs/zoned.c

@@ -10,6 +10,7 @@
 #include "rcu-string.h"
 #include "disk-io.h"
 #include "block-group.h"
+#include "transaction.h"
 
 /* Maximum number of zones to report per blkdev_report_zones() call */
 #define BTRFS_REPORT_NR_ZONES   4096
@@ -1181,3 +1182,39 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache)
 	/* Should not have any excluded extents. Just in case, though */
 	btrfs_free_excluded_extents(cache);
 }
+
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+			    struct extent_buffer *eb)
+{
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+
+	if (!btrfs_is_zoned(fs_info) ||
+	    btrfs_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN) ||
+	    !list_empty(&eb->release_list))
+		return;
+
+	set_extent_buffer_dirty(eb);
+	set_extent_bits_nowait(&trans->dirty_pages, eb->start,
+			       eb->start + eb->len - 1, EXTENT_DIRTY);
+	memzero_extent_buffer(eb, 0, eb->len);
+	set_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags);
+
+	spin_lock(&trans->releasing_ebs_lock);
+	list_add_tail(&eb->release_list, &trans->releasing_ebs);
+	spin_unlock(&trans->releasing_ebs_lock);
+	atomic_inc(&eb->refs);
+}
+
+void btrfs_free_redirty_list(struct btrfs_transaction *trans)
+{
+	spin_lock(&trans->releasing_ebs_lock);
+	while (!list_empty(&trans->releasing_ebs)) {
+		struct extent_buffer *eb;
+
+		eb = list_first_entry(&trans->releasing_ebs,
+				      struct extent_buffer, release_list);
+		list_del_init(&eb->release_list);
+		free_extent_buffer(eb);
+	}
+	spin_unlock(&trans->releasing_ebs_lock);
+}

fs/btrfs/zoned.h

@@ -43,6 +43,9 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical,
 int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size);
 int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new);
 void btrfs_calc_zone_unusable(struct btrfs_block_group *cache);
+void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+			    struct extent_buffer *eb);
+void btrfs_free_redirty_list(struct btrfs_transaction *trans);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
 				     struct blk_zone *zone)
@@ -126,6 +129,10 @@ static inline int btrfs_load_block_group_zone_info(
 
 static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { }
 
+static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans,
+					  struct extent_buffer *eb) { }
+static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { }
+
 #endif
 
 static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)