Merge tag 'for-6.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This brings mostly refactoring, cleanups, minor performance
  optimizations and usual fixes. The folio API conversions are most
  noticeable.

  There's one less visible change that could have a high impact. The
  extent lock scope for read is reduced, not held for the entire
  operation. In the buffered read case it's left to page or inode lock,
  some direct io read synchronization is still needed.

  This used to prevent deadlocks induced by page faults during direct
  io, so there was a 4K limitation on the requests, e.g. for io_uring.
  In the future this will allow smoother integration with iomap where
  the extent read lock was a major obstacle.

  User visible changes:

   - the FSTRIM ioctl updates the processed range even after an error or
     interruption

   - cleaner thread is woken up in SYNC ioctl instead of waking the
     transaction thread that can take some delay before waking up the
     cleaner, this can speed up cleaning of deleted subvolumes

   - print an error message when opening a device fail, e.g. when it's
     unexpectedly read-only

  Core changes:

   - improved extent map handling in various ways (locking, iteration, ...)

   - new assertions and locking annotations

   - raid-stripe-tree locking fixes

   - use xarray for tracking dirty qgroup extents, switched from rb-tree

   - turn the subpage test to compile-time condition if possible (e.g.
     on x86_64 with 4K pages), this allows to skip a lot of ifs and
     remove dead code

   - more preparatory work for compression in subpage mode

  Cleanups and refactoring

   - folio API conversions, many simple cases where page is passed so
     switch it to folios

   - more subpage code refactoring, update page state bitmap processing

   - introduce auto free for btrfs_path structure, use for the simple
     cases"

* tag 'for-6.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (110 commits)
  btrfs: only unlock the to-be-submitted ranges inside a folio
  btrfs: merge btrfs_folio_unlock_writer() into btrfs_folio_end_writer_lock()
  btrfs: BTRFS_PATH_AUTO_FREE in orphan.c
  btrfs: use btrfs_path auto free in zoned.c
  btrfs: DEFINE_FREE for struct btrfs_path
  btrfs: remove btrfs_folio_end_all_writers()
  btrfs: constify more pointer parameters
  btrfs: rework BTRFS_I as macro to preserve parameter const
  btrfs: add and use helper to verify the calling task has locked the inode
  btrfs: always update fstrim_range on failure in FITRIM ioctl
  btrfs: convert copy_inline_to_page() to use folio
  btrfs: convert btrfs_decompress() to take a folio
  btrfs: convert zstd_decompress() to take a folio
  btrfs: convert lzo_decompress() to take a folio
  btrfs: convert zlib_decompress() to take a folio
  btrfs: convert try_release_extent_mapping() to take a folio
  btrfs: convert try_release_extent_state() to take a folio
  btrfs: convert submit_eb_page() to take a folio
  btrfs: convert submit_eb_subpage() to take a folio
  btrfs: convert read_key_bytes() to take a folio
  ...

Author: torvalds

fs/btrfs/backref.c

@@ -219,8 +219,8 @@ static void free_pref(struct prelim_ref *ref)
  * A -1 return indicates ref1 is a 'lower' block than ref2, while 1
  * indicates a 'higher' block.
  */
-static int prelim_ref_compare(struct prelim_ref *ref1,
-			      struct prelim_ref *ref2)
+static int prelim_ref_compare(const struct prelim_ref *ref1,
+			      const struct prelim_ref *ref2)
 {
 	if (ref1->level < ref2->level)
 		return -1;
@@ -251,7 +251,7 @@ static int prelim_ref_compare(struct prelim_ref *ref1,
 }
 
 static void update_share_count(struct share_check *sc, int oldcount,
-			       int newcount, struct prelim_ref *newref)
+			       int newcount, const struct prelim_ref *newref)
 {
 	if ((!sc) || (oldcount == 0 && newcount < 1))
 		return;

fs/btrfs/bio.c

@@ -53,7 +53,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
 
 /*
  * Allocate a btrfs_bio structure.  The btrfs_bio is the main I/O container for
- * btrfs, and is used for all I/O submitted through btrfs_submit_bio.
+ * btrfs, and is used for all I/O submitted through btrfs_submit_bbio().
  *
  * Just like the underlying bio_alloc_bioset it will not fail as it is backed by
  * a mempool.
@@ -120,12 +120,6 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
 	}
 }
 
-void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
-{
-	bbio->bio.bi_status = status;
-	__btrfs_bio_end_io(bbio);
-}
-
 static void btrfs_orig_write_end_io(struct bio *bio);
 
 static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
@@ -147,8 +141,9 @@ static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
 	}
 }
 
-static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio)
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 {
+	bbio->bio.bi_status = status;
 	if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
 		struct btrfs_bio *orig_bbio = bbio->private;
 
@@ -179,7 +174,7 @@ static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
 static void btrfs_repair_done(struct btrfs_failed_bio *fbio)
 {
 	if (atomic_dec_and_test(&fbio->repair_count)) {
-		btrfs_orig_bbio_end_io(fbio->bbio);
+		btrfs_bio_end_io(fbio->bbio, fbio->bbio->bio.bi_status);
 		mempool_free(fbio, &btrfs_failed_bio_pool);
 	}
 }
@@ -211,7 +206,7 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio,
 			goto done;
 		}
 
-		btrfs_submit_bio(repair_bbio, mirror);
+		btrfs_submit_bbio(repair_bbio, mirror);
 		return;
 	}
 
@@ -280,7 +275,7 @@ static struct btrfs_failed_bio *repair_one_sector(struct btrfs_bio *failed_bbio,
 
 	mirror = next_repair_mirror(fbio, failed_bbio->mirror_num);
 	btrfs_debug(fs_info, "submitting repair read to mirror %d", mirror);
-	btrfs_submit_bio(repair_bbio, mirror);
+	btrfs_submit_bbio(repair_bbio, mirror);
 	return fbio;
 }
 
@@ -326,7 +321,7 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de
 	if (fbio)
 		btrfs_repair_done(fbio);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 }
 
 static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)
@@ -360,7 +355,7 @@ static void btrfs_end_bio_work(struct work_struct *work)
 	if (is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, bbio->bio.bi_private);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 }
 
 static void btrfs_simple_end_io(struct bio *bio)
@@ -380,7 +375,7 @@ static void btrfs_simple_end_io(struct bio *bio)
 	} else {
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
 			btrfs_record_physical_zoned(bbio);
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 	}
 }
 
@@ -394,7 +389,7 @@ static void btrfs_raid56_end_io(struct bio *bio)
 	if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, NULL);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 
 	btrfs_put_bioc(bioc);
 }
@@ -424,7 +419,7 @@ static void btrfs_orig_write_end_io(struct bio *bio)
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
 		stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
-	btrfs_orig_bbio_end_io(bbio);
+	btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 	btrfs_put_bioc(bioc);
 }
 
@@ -502,8 +497,8 @@ static void btrfs_submit_mirrored_bio(struct btrfs_io_context *bioc, int dev_nr)
 	btrfs_submit_dev_bio(bioc->stripes[dev_nr].dev, bio);
 }
 
-static void __btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
-			       struct btrfs_io_stripe *smap, int mirror_num)
+static void btrfs_submit_bio(struct bio *bio, struct btrfs_io_context *bioc,
+			     struct btrfs_io_stripe *smap, int mirror_num)
 {
 	if (!bioc) {
 		/* Single mirror read/write fast path. */
@@ -593,7 +588,7 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free)
 
 	/* If an error occurred we just want to clean up the bio and move on. */
 	if (bio->bi_status) {
-		btrfs_orig_bbio_end_io(async->bbio);
+		btrfs_bio_end_io(async->bbio, async->bbio->bio.bi_status);
 		return;
 	}
 
@@ -603,7 +598,7 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free)
 	 * context.  This changes nothing when cgroups aren't in use.
 	 */
 	bio->bi_opf |= REQ_BTRFS_CGROUP_PUNT;
-	__btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num);
+	btrfs_submit_bio(bio, async->bioc, &async->smap, async->mirror_num);
 }
 
 static bool should_async_write(struct btrfs_bio *bbio)
@@ -678,7 +673,10 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 	blk_status_t ret;
 	int error;
 
-	smap.is_scrub = !bbio->inode;
+	if (!bbio->inode || btrfs_is_data_reloc_root(inode->root))
+		smap.rst_search_commit_root = true;
+	else
+		smap.rst_search_commit_root = false;
 
 	btrfs_bio_counter_inc_blocked(fs_info);
 	error = btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length,
@@ -749,7 +747,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		}
 	}
 
-	__btrfs_submit_bio(bio, bioc, &smap, mirror_num);
+	btrfs_submit_bio(bio, bioc, &smap, mirror_num);
 done:
 	return map_length == length;
 
@@ -765,16 +763,14 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset);
 		ASSERT(remaining);
 
-		remaining->bio.bi_status = ret;
-		btrfs_orig_bbio_end_io(remaining);
+		btrfs_bio_end_io(remaining, ret);
 	}
-	bbio->bio.bi_status = ret;
-	btrfs_orig_bbio_end_io(bbio);
+	btrfs_bio_end_io(bbio, ret);
 	/* Do not submit another chunk */
 	return true;
 }
 
-void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num)
+void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num)
 {
 	/* If bbio->inode is not populated, its file_offset must be 0. */
 	ASSERT(bbio->inode || bbio->file_offset == 0);
@@ -786,7 +782,7 @@ void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num)
 /*
  * Submit a repair write.
  *
- * This bypasses btrfs_submit_bio deliberately, as that writes all copies in a
+ * This bypasses btrfs_submit_bbio() deliberately, as that writes all copies in a
  * RAID setup.  Here we only want to write the one bad copy, so we do the
  * mapping ourselves and submit the bio directly.
  *
@@ -875,7 +871,7 @@ void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_
 		ASSERT(smap.dev == fs_info->dev_replace.srcdev);
 		smap.dev = fs_info->dev_replace.tgtdev;
 	}
-	__btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num);
+	btrfs_submit_bio(&bbio->bio, NULL, &smap, mirror_num);
 	return;
 
 fail:

fs/btrfs/bio.h

@@ -29,7 +29,7 @@ typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
 
 /*
  * Highlevel btrfs I/O structure.  It is allocated by btrfs_bio_alloc and
- * passed to btrfs_submit_bio for mapping to the physical devices.
+ * passed to btrfs_submit_bbio() for mapping to the physical devices.
  */
 struct btrfs_bio {
 	/*
@@ -42,7 +42,7 @@ struct btrfs_bio {
 	union {
 		/*
 		 * For data reads: checksumming and original I/O information.
-		 * (for internal use in the btrfs_submit_bio machinery only)
+		 * (for internal use in the btrfs_submit_bbio() machinery only)
 		 */
 		struct {
 			u8 *csum;
@@ -104,7 +104,7 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status);
 /* Submit using blkcg_punt_bio_submit. */
 #define REQ_BTRFS_CGROUP_PUNT			REQ_FS_PRIVATE
 
-void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num);
+void btrfs_submit_bbio(struct btrfs_bio *bbio, int mirror_num);
 void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace);
 int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
 			    u64 length, u64 logical, struct folio *folio,

fs/btrfs/block-group.c

@@ -23,7 +23,7 @@
 #include "extent-tree.h"
 
 #ifdef CONFIG_BTRFS_DEBUG
-int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group)
+int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group)
 {
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 
@@ -40,9 +40,9 @@ int btrfs_should_fragment_free_space(struct btrfs_block_group *block_group)
  *
  * Should be called with balance_lock held
  */
-static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
+static u64 get_restripe_target(const struct btrfs_fs_info *fs_info, u64 flags)
 {
-	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+	const struct btrfs_balance_control *bctl = fs_info->balance_ctl;
 	u64 target = 0;
 
 	if (!bctl)
@@ -1415,9 +1415,9 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 }
 
 static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
-				 struct btrfs_block_group *bg)
+				 const struct btrfs_block_group *bg)
 {
-	struct btrfs_fs_info *fs_info = bg->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_transaction *prev_trans = NULL;
 	const u64 start = bg->start;
 	const u64 end = start + bg->length - 1;
@@ -1756,14 +1756,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a,
 	return bg1->used > bg2->used;
 }
 
-static inline bool btrfs_should_reclaim(struct btrfs_fs_info *fs_info)
+static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_is_zoned(fs_info))
 		return btrfs_zoned_should_reclaim(fs_info);
 	return true;
 }
 
-static bool should_reclaim_block_group(struct btrfs_block_group *bg, u64 bytes_freed)
+static bool should_reclaim_block_group(const struct btrfs_block_group *bg, u64 bytes_freed)
 {
 	const int thresh_pct = btrfs_calc_reclaim_threshold(bg->space_info);
 	u64 thresh_bytes = mult_perc(bg->length, thresh_pct);
@@ -2006,8 +2006,8 @@ void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
-static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
-			   struct btrfs_path *path)
+static int read_bg_from_eb(struct btrfs_fs_info *fs_info, const struct btrfs_key *key,
+			   const struct btrfs_path *path)
 {
 	struct btrfs_chunk_map *map;
 	struct btrfs_block_group_item bg;
@@ -2055,7 +2055,7 @@ static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 
 static int find_first_block_group(struct btrfs_fs_info *fs_info,
 				  struct btrfs_path *path,
-				  struct btrfs_key *key)
+				  const struct btrfs_key *key)
 {
 	struct btrfs_root *root = btrfs_block_group_root(fs_info);
 	int ret;
@@ -2640,8 +2640,8 @@ static int insert_block_group_item(struct btrfs_trans_handle *trans,
 }
 
 static int insert_dev_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_device *device, u64 chunk_offset,
-			    u64 start, u64 num_bytes)
+			     const struct btrfs_device *device, u64 chunk_offset,
+			     u64 start, u64 num_bytes)
 {
 	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_root *root = fs_info->dev_root;
@@ -2817,7 +2817,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
  * For extent tree v2 we use the block_group_item->chunk_offset to point at our
  * global root id.  For v1 it's always set to BTRFS_FIRST_CHUNK_TREE_OBJECTID.
  */
-static u64 calculate_global_root_id(struct btrfs_fs_info *fs_info, u64 offset)
+static u64 calculate_global_root_id(const struct btrfs_fs_info *fs_info, u64 offset)
 {
 	u64 div = SZ_1G;
 	u64 index;
@@ -3842,8 +3842,8 @@ static void force_metadata_allocation(struct btrfs_fs_info *info)
 	}
 }
 
-static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
-			      struct btrfs_space_info *sinfo, int force)
+static int should_alloc_chunk(const struct btrfs_fs_info *fs_info,
+			      const struct btrfs_space_info *sinfo, int force)
 {
 	u64 bytes_used = btrfs_space_info_used(sinfo, false);
 	u64 thresh;
@@ -4218,7 +4218,7 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	return ret;
 }
 
-static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
+static u64 get_profile_num_devs(const struct btrfs_fs_info *fs_info, u64 type)
 {
 	u64 num_dev;
 
@@ -4622,7 +4622,7 @@ int btrfs_use_block_group_size_class(struct btrfs_block_group *bg,
 	return 0;
 }
 
-bool btrfs_block_group_should_use_size_class(struct btrfs_block_group *bg)
+bool btrfs_block_group_should_use_size_class(const struct btrfs_block_group *bg)
 {
 	if (btrfs_is_zoned(bg->fs_info))
 		return false;