btrfs: zoned: serialize metadata IO

We cannot use zone append for writing metadata, because the B-tree nodes
have references to each other using logical address. Without knowing
the address in advance, we cannot construct the tree in the first place.
So we need to serialize write IOs for metadata.

We cannot add a mutex around allocation and submission because metadata
blocks are allocated in an earlier stage to build up B-trees.

Add a zoned_meta_io_lock and hold it during metadata IO submission in
btree_write_cache_pages() to serialize IOs.

Furthermore, this adds a per-block group metadata IO submission pointer
"meta_write_pointer" to ensure sequential writing, which can break when
attempting to write back blocks in an unfinished transaction. If the
writing out failed because of a hole and the write out is for data
integrity (WB_SYNC_ALL), it returns EAGAIN.

A caller like fsync() code should handle this properly e.g. by falling
back to a full transaction commit.

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

1 files changed, 24 insertions, 1 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 14a68f3589cc..dfa6c6106b94 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -26,6 +26,7 @@
 #include "disk-io.h"
 #include "subpage.h"
 #include "zoned.h"
+#include "block-group.h"
 
 static struct kmem_cache *extent_state_cache;
 static struct kmem_cache *extent_buffer_cache;
@@ -4161,6 +4162,7 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 			  struct extent_buffer **eb_context)
 {
 	struct address_space *mapping = page->mapping;
+	struct btrfs_block_group *cache = NULL;
 	struct extent_buffer *eb;
 	int ret;
 
@@ -4193,13 +4195,31 @@ static int submit_eb_page(struct page *page, struct writeback_control *wbc,
 	if (!ret)
 		return 0;
 
+	if (!btrfs_check_meta_write_pointer(eb->fs_info, eb, &cache)) {
+		/*
+		 * If for_sync, this hole will be filled with
+		 * trasnsaction commit.
+		 */
+		if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
+			ret = -EAGAIN;
+		else
+			ret = 0;
+		free_extent_buffer(eb);
+		return ret;
+	}
+
 	*eb_context = eb;
 
 	ret = lock_extent_buffer_for_io(eb, epd);
 	if (ret <= 0) {
+		btrfs_revert_meta_write_pointer(cache, eb);
+		if (cache)
+			btrfs_put_block_group(cache);
 		free_extent_buffer(eb);
 		return ret;
 	}
+	if (cache)
+		btrfs_put_block_group(cache);
 	ret = write_one_eb(eb, wbc, epd);
 	free_extent_buffer(eb);
 	if (ret < 0)
@@ -4245,6 +4265,7 @@ int btree_write_cache_pages(struct address_space *mapping,
 		tag = PAGECACHE_TAG_TOWRITE;
 	else
 		tag = PAGECACHE_TAG_DIRTY;
+	btrfs_zoned_meta_io_lock(fs_info);
 retry:
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		tag_pages_for_writeback(mapping, index, end);
@@ -4285,7 +4306,7 @@ retry:
 	}
 	if (ret < 0) {
 		end_write_bio(&epd, ret);
-		return ret;
+		goto out;
 	}
 	/*
 	 * If something went wrong, don't allow any metadata write bio to be
@@ -4320,6 +4341,8 @@ retry:
 		ret = -EROFS;
 		end_write_bio(&epd, ret);
 	}
+out:
+	btrfs_zoned_meta_io_unlock(fs_info);
 	return ret;
 }