Merge tag 'for-6.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "Mainly core changes, refactoring and optimizations.

  Performance is improved in some areas, overall there may be a
  cumulative improvement due to refactoring that removed lookups in the
  IO path or simplified IO submission tracking.

  Core:

   - submit IO synchronously for fast checksums (crc32c and xxhash),
     remove high priority worker kthread

   - read extent buffer in one go, simplify IO tracking, bio submission
     and locking

   - remove additional tracking of redirtied extent buffers, originally
     added for zoned mode but actually not needed

   - track ordered extent pointer in bio to avoid rbtree lookups during
     IO

   - scrub, use recovered data stripes as cache to avoid unnecessary
     read

   - in zoned mode, optimize logical to physical mappings of extents

   - remove PageError handling, not set by VFS nor writeback

   - cleanups, refactoring, better structure packing

   - lots of error handling improvements

   - more assertions, lockdep annotations

   - print assertion failure with the exact line where it happens

   - tracepoint updates

   - more debugging prints

  Performance:

   - speedup in fsync(), better tracking of inode logged status can
     avoid transaction commit

   - IO path structures track logical offsets in data structures and
     does not need to look it up

  User visible changes:

   - don't commit transaction for every created subvolume, this can
     reduce time when many subvolumes are created in a batch

   - print affected files when relocation fails

   - trigger orphan file cleanup during START_SYNC ioctl

  Notable fixes:

   - fix crash when disabling quota and relocation

   - fix crashes when removing roots from drity list

   - fix transacion abort during relocation when converting from newer
     profiles not covered by fallback

   - in zoned mode, stop reclaiming block groups if filesystem becomes
     read-only

   - fix rare race condition in tree mod log rewind that can miss some
     btree node slots

   - with enabled fsverity, drop up-to-date page bit in case the
     verification fails"

* tag 'for-6.5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (194 commits)
  btrfs: fix race between quota disable and relocation
  btrfs: add comment to struct btrfs_fs_info::dirty_cowonly_roots
  btrfs: fix race when deleting free space root from the dirty cow roots list
  btrfs: fix race when deleting quota root from the dirty cow roots list
  btrfs: tracepoints: also show actual number of the outstanding extents
  btrfs: update i_version in update_dev_time
  btrfs: make btrfs_compressed_bioset static
  btrfs: add handling for RAID1C23/DUP to btrfs_reduce_alloc_profile
  btrfs: scrub: remove btrfs_fs_info::scrub_wr_completion_workers
  btrfs: scrub: remove scrub_ctx::csum_list member
  btrfs: do not BUG_ON after failure to migrate space during truncation
  btrfs: do not BUG_ON on failure to get dir index for new snapshot
  btrfs: send: do not BUG_ON() on unexpected symlink data extent
  btrfs: do not BUG_ON() when dropping inode items from log root
  btrfs: replace BUG_ON() at split_item() with proper error handling
  btrfs: do not BUG_ON() on tree mod log failures at btrfs_del_ptr()
  btrfs: do not BUG_ON() on tree mod log failures at insert_ptr()
  btrfs: do not BUG_ON() on tree mod log failure at insert_new_root()
  btrfs: do not BUG_ON() on tree mod log failures at push_nodes_for_insert()
  btrfs: abort transaction at update_ref_for_cow() when ref count is zero
  ...

1 files changed, 25 insertions, 12 deletions

diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 29a225836e28..a2315a4b8b75 100644
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -533,6 +533,16 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
 }
 
 /*
+ * Detect if extent bits request NOWAIT semantics and set the gfp mask accordingly,
+ * unset the EXTENT_NOWAIT bit.
+ */
+static void set_gfp_mask_from_bits(u32 *bits, gfp_t *mask)
+{
+	*mask = (*bits & EXTENT_NOWAIT ? GFP_NOWAIT : GFP_NOFS);
+	*bits &= EXTENT_NOWAIT - 1;
+}
+
+/*
  * Clear some bits on a range in the tree.  This may require splitting or
  * inserting elements in the tree, so the gfp mask is used to indicate which
  * allocations or sleeping are allowed.
@@ -546,7 +556,7 @@ static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
  */
 int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		       u32 bits, struct extent_state **cached_state,
-		       gfp_t mask, struct extent_changeset *changeset)
+		       struct extent_changeset *changeset)
 {
 	struct extent_state *state;
 	struct extent_state *cached;
@@ -556,7 +566,9 @@ int __clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	int clear = 0;
 	int wake;
 	int delete = (bits & EXTENT_CLEAR_ALL_BITS);
+	gfp_t mask;
 
+	set_gfp_mask_from_bits(&bits, &mask);
 	btrfs_debug_check_extent_io_range(tree, start, end);
 	trace_btrfs_clear_extent_bit(tree, start, end - start + 1, bits);
 
@@ -953,7 +965,8 @@ out:
 
 /*
  * Set some bits on a range in the tree.  This may require allocations or
- * sleeping, so the gfp mask is used to indicate what is allowed.
+ * sleeping. By default all allocations use GFP_NOFS, use EXTENT_NOWAIT for
+ * GFP_NOWAIT.
  *
  * If any of the exclusive bits are set, this will fail with -EEXIST if some
  * part of the range already has the desired bits set.  The extent_state of the
@@ -968,7 +981,7 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 			    u32 bits, u64 *failed_start,
 			    struct extent_state **failed_state,
 			    struct extent_state **cached_state,
-			    struct extent_changeset *changeset, gfp_t mask)
+			    struct extent_changeset *changeset)
 {
 	struct extent_state *state;
 	struct extent_state *prealloc = NULL;
@@ -978,7 +991,9 @@ static int __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 last_start;
 	u64 last_end;
 	u32 exclusive_bits = (bits & EXTENT_LOCKED);
+	gfp_t mask;
 
+	set_gfp_mask_from_bits(&bits, &mask);
 	btrfs_debug_check_extent_io_range(tree, start, end);
 	trace_btrfs_set_extent_bit(tree, start, end - start + 1, bits);
 
@@ -1188,10 +1203,10 @@ out:
 }
 
 int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
-		   u32 bits, struct extent_state **cached_state, gfp_t mask)
+		   u32 bits, struct extent_state **cached_state)
 {
 	return __set_extent_bit(tree, start, end, bits, NULL, NULL,
-				cached_state, NULL, mask);
+				cached_state, NULL);
 }
 
 /*
@@ -1687,8 +1702,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	ASSERT(!(bits & EXTENT_LOCKED));
 
-	return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL,
-				changeset, GFP_NOFS);
+	return __set_extent_bit(tree, start, end, bits, NULL, NULL, NULL, changeset);
 }
 
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1700,8 +1714,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	 */
 	ASSERT(!(bits & EXTENT_LOCKED));
 
-	return __clear_extent_bit(tree, start, end, bits, NULL, GFP_NOFS,
-				  changeset);
+	return __clear_extent_bit(tree, start, end, bits, NULL, changeset);
 }
 
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1711,7 +1724,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 failed_start;
 
 	err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
-			       NULL, cached, NULL, GFP_NOFS);
+			       NULL, cached, NULL);
 	if (err == -EEXIST) {
 		if (failed_start > start)
 			clear_extent_bit(tree, start, failed_start - 1,
@@ -1733,7 +1746,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 	u64 failed_start;
 
 	err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
-			       &failed_state, cached_state, NULL, GFP_NOFS);
+			       &failed_state, cached_state, NULL);
 	while (err == -EEXIST) {
 		if (failed_start != start)
 			clear_extent_bit(tree, start, failed_start - 1,
@@ -1743,7 +1756,7 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 				&failed_state);
 		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
 				       &failed_start, &failed_state,
-				       cached_state, NULL, GFP_NOFS);
+				       cached_state, NULL);
 	}
 	return err;
 }