Merge tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "The usual mix of performance improvements and new features.

  The core change is reworking how checksums are processed, with
  followup cleanups and simplifications. There are two minor changes in
  block layer and iomap code.

  Features:

   - block group allocation class heuristics:
      - pack files by size (up to 128k, up to 8M, more) to avoid
        fragmentation in block groups, assuming that file size and life
        time is correlated, in particular this may help during balance
      - with tracepoints and extensible in the future

  Performance:

   - send: cache directory utimes and only emit the command when
     necessary
      - speedup up to 10x
      - smaller final stream produced (no redundant utimes commands
        issued)
      - compatibility not affected

   - fiemap: skip backref checks for shared leaves
      - speedup 3x on sample filesystem with all leaves shared (e.g. on
        snapshots)

   - micro optimized b-tree key lookup, speedup in metadata operations
     (sample benchmark: fs_mark +10% of files/sec)

  Core changes:

   - change where checksumming is done in the io path:
      - checksum and read repair does verification at lower layer
      - cascaded cleanups and simplifications

   - raid56 refactoring and cleanups

  Fixes:

   - sysfs: make sure that a run-time change of a feature is correctly
     tracked by the feature files

   - scrub: better reporting of tree block errors

  Other:

   - locally enable -Wmaybe-uninitialized after fixing all warnings

   - misc cleanups, spelling fixes

  Other code:

   - block: export bio_split_rw

   - iomap: remove IOMAP_F_ZONE_APPEND"

* tag 'for-6.3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (109 commits)
  btrfs: make kobj_type structures constant
  btrfs: remove the bdev argument to btrfs_rmap_block
  btrfs: don't rely on unchanging ->bi_bdev for zone append remaps
  btrfs: never return true for reads in btrfs_use_zone_append
  btrfs: pass a btrfs_bio to btrfs_use_append
  btrfs: set bbio->file_offset in alloc_new_bio
  btrfs: use file_offset to limit bios size in calc_bio_boundaries
  btrfs: do unsigned integer division in the extent buffer binary search loop
  btrfs: eliminate extra call when doing binary search on extent buffer
  btrfs: raid56: handle endio in scrub_rbio
  btrfs: raid56: handle endio in recover_rbio
  btrfs: raid56: handle endio in rmw_rbio
  btrfs: raid56: submit the read bios from scrub_assemble_read_bios
  btrfs: raid56: fold rmw_read_wait_recover into rmw_read_bios
  btrfs: raid56: fold recover_assemble_read_bios into recover_rbio
  btrfs: raid56: add a bio_list_put helper
  btrfs: raid56: wait for I/O completion in submit_read_bios
  btrfs: raid56: simplify code flow in rmw_rbio
  btrfs: raid56: simplify error handling and code flow in raid56_parity_write
  btrfs: replace btrfs_wait_tree_block_writeback by wait_on_extent_buffer_writeback
  ...

1 files changed, 30 insertions, 3 deletions

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 46851511b661..90e40d5ceccd 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1252,8 +1252,12 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_share_check_ctx *ct
 					struct btrfs_root *root,
 					u64 bytenr, int level, bool *is_shared)
 {
+	const struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_backref_shared_cache_entry *entry;
 
+	if (!current->journal_info)
+		lockdep_assert_held(&fs_info->commit_root_sem);
+
 	if (!ctx->use_path_cache)
 		return false;
 
@@ -1288,7 +1292,7 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_share_check_ctx *ct
 	 * could be a snapshot sharing this extent buffer.
 	 */
 	if (entry->is_shared &&
-	    entry->gen != btrfs_get_last_root_drop_gen(root->fs_info))
+	    entry->gen != btrfs_get_last_root_drop_gen(fs_info))
 		return false;
 
 	*is_shared = entry->is_shared;
@@ -1318,9 +1322,13 @@ static void store_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx
 				       struct btrfs_root *root,
 				       u64 bytenr, int level, bool is_shared)
 {
+	const struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_backref_shared_cache_entry *entry;
 	u64 gen;
 
+	if (!current->journal_info)
+		lockdep_assert_held(&fs_info->commit_root_sem);
+
 	if (!ctx->use_path_cache)
 		return;
 
@@ -1336,7 +1344,7 @@ static void store_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx
 	ASSERT(level >= 0);
 
 	if (is_shared)
-		gen = btrfs_get_last_root_drop_gen(root->fs_info);
+		gen = btrfs_get_last_root_drop_gen(fs_info);
 	else
 		gen = btrfs_root_last_snapshot(&root->root_item);
 
@@ -1864,6 +1872,8 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		.have_delayed_delete_refs = false,
 	};
 	int level;
+	bool leaf_cached;
+	bool leaf_is_shared;
 
 	for (int i = 0; i < BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE; i++) {
 		if (ctx->prev_extents_cache[i].bytenr == bytenr)
@@ -1885,6 +1895,23 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		walk_ctx.time_seq = elem.seq;
 	}
 
+	ctx->use_path_cache = true;
+
+	/*
+	 * We may have previously determined that the current leaf is shared.
+	 * If it is, then we have a data extent that is shared due to a shared
+	 * subtree (caused by snapshotting) and we don't need to check for data
+	 * backrefs. If the leaf is not shared, then we must do backref walking
+	 * to determine if the data extent is shared through reflinks.
+	 */
+	leaf_cached = lookup_backref_shared_cache(ctx, root,
+						  ctx->curr_leaf_bytenr, 0,
+						  &leaf_is_shared);
+	if (leaf_cached && leaf_is_shared) {
+		ret = 1;
+		goto out_trans;
+	}
+
 	walk_ctx.ignore_extent_item_pos = true;
 	walk_ctx.trans = trans;
 	walk_ctx.fs_info = fs_info;
@@ -1893,7 +1920,6 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 	/* -1 means we are in the bytenr of the data extent. */
 	level = -1;
 	ULIST_ITER_INIT(&uiter);
-	ctx->use_path_cache = true;
 	while (1) {
 		bool is_shared;
 		bool cached;
@@ -1964,6 +1990,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr,
 		ctx->prev_extents_cache_slot = slot;
 	}
 
+out_trans:
 	if (trans) {
 		btrfs_put_tree_mod_seq(fs_info, &elem);
 		btrfs_end_transaction(trans);